Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Purchase individual online access for 1 year to this journal.
Price: EUR 315.00Impact Factor 2023: 2
The purpose of the Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology is to foster advancements of knowledge and help disseminate results concerning recent applications and case studies in the areas of fuzzy logic, intelligent systems, and web-based applications among working professionals and professionals in education and research, covering a broad cross-section of technical disciplines.
The journal will publish original articles on current and potential applications, case studies, and education in intelligent systems, fuzzy systems, and web-based systems for engineering and other technical fields in science and technology. The journal focuses on the disciplines of computer science, electrical engineering, manufacturing engineering, industrial engineering, chemical engineering, mechanical engineering, civil engineering, engineering management, bioengineering, and biomedical engineering. The scope of the journal also includes developing technologies in mathematics, operations research, technology management, the hard and soft sciences, and technical, social and environmental issues.
Authors: Li, Jia | Xue, Shuaihao | Li, Minghui | Shi, Xiaoqiu
Article Type: Research Article
Abstract: Combining the harmony search algorithm (HS) with the local search algorithm (LS) can prevent the HS from falling into a local optimum. However, how LS affects the performance of HS has not yet been studied systematically. Therefore, in this paper, it is first proposed to combine four frequently used LS with HS to obtain several search algorithms (HSLSs). Then, by taking the flexible job-shop scheduling problem (FJSP) as an example and considering decoding times, study how the parameters of HSLSs affect their performance, where the performance is evaluated by the difference rate based on the decoding times. The simulation results …mainly show that (I) as the harmony memory size (HMS) gradually increases, the performance of HSLSs first increases rapidly and then tends to remain unchanged, and HMS is not the larger the better; (II) as harmony memory considering rate increases, the performance continues to improve, while the performance of pitch adjusting rate on HSLSs goes to the opposite; Finally, more benchmark instances are also used to verify the effectiveness of the proposed algorithms. The results of this paper have a certain guiding significance on how to choose LS and other parameters to improve HS for solving FJSP. Show more
Keywords: Algorithm analysis, local search, harmony search, flexible job-shop scheduling problem
DOI: 10.3233/JIFS-239142
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Ma, Dongdong | He, Xiaohai | Wang, Meiling | Fang, Qingmao | Zhu, Han | Hu, Ping
Article Type: Research Article
Abstract: Knowledge graph question answering aims to answer natural language questions using structured knowledge graph data. The key to achieving this is having a correct semantic understanding of the question phrases. Query graph generation is an important step for knowledge graph question answering systems to tackle complex questions. Unlike simple single-hop questions, complex questions often require reasoning between multiple triples to get the right answer due to multiple entities, relationships and constraints, making it difficult to generate correct query graphs. In previous studies, researchers have primarily focused on improving the extraction and representation of question features, neglecting the prior structural information …implicated in the question itself. In this paper, we propose a question structure classifier to classify the question structure, and alleviate the noise interference in query graph through classification results. In the classifier, we strengthen the information about the question structure through the attention mechanism, while weakening the irrelevant information. Moreover, a query graph sorting module based on feature cross-coding is proposed to sort candidate paths in the query graph using fine-grained feature interaction between words. Extensive experiments are conducted on two public datasets (MetaQA and WebQuestionsSP) and the experimental results show that the proposed method outperforms other baselines. Show more
Keywords: Knowledge graph question answering, relation embedding, attention enhancement, feature cross-encoding
DOI: 10.3233/JIFS-233650
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Yue, Lizhu | Lv, Yue
Article Type: Research Article
Abstract: The Vlsekriterijumska Optimizacija I Komprosmisno Resenie (VIKOR) method to some extent modifies the utility function to a value function that can consider different risk preferences. However, the weight and risk attitude parameters involved in the model are difficult to determine, which limits its application. To overcome this problem, a Poset-VIKOR model is proposed. A partial order set is a non-parametric decision-making method. Through the combination of partial order set and VIKOR model, the parameters can be “eliminated”, and a robust method that can run the model is obtained. This method uses the Hasse diagram to express the evaluation results, which …can not only directly display the hierarchical and clustering information, but also show the robustness characteristics of the alternative comparison. Show more
Keywords: VIKOR method, poset, weight, multiple attribute decision making
DOI: 10.3233/JIFS-230680
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Shao, Dangguo | Huang, Chunsheng | Liu, Cuiyin | Ma, Lei | Yi, Sanli
Article Type: Research Article
Abstract: The automatic segmentation of diabetic retinopathy (DR) holds significant importance for assisting physicians in diagnosis and treatment. Given the complexity, high inter-class similarity, and uncertainty of DR, it is crucial to integrate multiscale information between lesions and establish global correlations among them. To address these issues, a novel HRU-TNet (Hybrid Residual U-Transformer Network) algorithm for retinal lesion segmentation is proposed. In this framework, the network is augmented with lightweight self-attention residual U-modules (LSA-RSU) to capture high-frequency details of the lesions and global contextual information. The skip connections are then enhanced through interactive residual transformer fusion modules (IRTF) and channel-cross attention …(CCA), promoting dependencies among features at different scales and filtering out interfering information to guide feature fusion and eliminate ambiguity. Additionally, a novel retinal image enhancement technique is devised, employing local wavelet transformations to capture detailed components of the retinal images, thereby enhancing the representational capacity of the segmentation network. Data augmentation is also performed to ensure network adaptability to small datasets. Comprehensive experiments conducted on the publicly available IDRID and e_ophtha datasets yielded average AUC_PR values of 0.709 and 0.451, respectively. The proposed approach demonstrated superior generalization on the DDR dataset compared to other methods mentioned in the literature. These results demonstrate that our proposed method is better suited for small retinal datasets, exhibiting improved segmentation accuracy and generalization compared to existing approaches. Show more
Keywords: Lesion segmentation, fundus image enhancement, transformer, cross attention fusion, light self-attention residual
DOI: 10.3233/JIFS-240788
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: He, Xiaorong | Fang, Anran | Yu, Dejian
Article Type: Research Article
Abstract: Electronic commerce (EC) has become the most critical business activity in the world. China has become the world’s largest market for EC. Over the past three decades, numerous researches have examined the current status of the development of monolingual EC research in specific scenarios. However, the paradigm shift in EC development through the analysis of the dynamic evolution of semantic information has not yet been examined, and the distinctions and connections between multilingual EC studies have not yet been established. This study analyzed 16,207 English and 17,850 Chinese EC-related articles from the Web of Science database and CNKI by combining …the BERTopic topic model and SBERT sentence embedding-based similarity computations. The results reveal the distributions of global and local topics in the English and Chinese EC literature, analyze the semantic intricacies of topic convergence and evolution across continuous time, as well as the distinctions and connections between English and Chinese topics. Finally, the evolutionary patterns and life cycle of three crucial English and Chinese topics are explored respectively, including their emergence, development, maturity, and decline. Overall, this study provides a comprehensive overview of EC studies from a topic perspective. Show more
Keywords: Electronic commerce, BERTopic, topic modeling, topic evolution, sentence embedding
DOI: 10.3233/JIFS-232825
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-22, 2024
Authors: Kazancı, O. | Hoskova-Mayerova, S. | Davvaz, B.
Article Type: Research Article
Abstract: In recent years, the m-polar fuzziness structure has attracted the attention of researchers and has been commonly applied in algebraic structures. In this article, we present the notion of multi-polar fuzzy hyperideals of ordered semihyperrings, which is a generalization of the concept of bi-polar fuzzy hyperideals of ordered semihyperrings. We investigate some of their associated properties. Furthermore, we characterized regular ordered semihyperring in terms of multi-polar fuzzy quasi-ideals and multi-polar fuzzy bi-ideals.
Keywords: Semihyperring, ordered semihyperring, m-polar fuzzy semihyperring, m-polar fuzzy hyperideals
DOI: 10.3233/JIFS-238654
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-09, 2024
Authors: Ameen, Zanyar A. | Mohammed, Ramadhan A. | Al-shami, Tareq M. | Asaad, Baravan A.
Article Type: Research Article
Abstract: This paper introduces a new fuzzy structure named “fuzzy primal.” Then, it studies the essential properties and discusses their basic operations. By applying the q-neighborhood system in a primal fuzzy topological space and the Łukasiewicz disjunction, we establish a fuzzy operator (·) ⋄ on the family of all fuzzy sets, followed by its core characterizations. Next, we use (·) ⋄ to investigate a further fuzzy operator denoted by Cl ⋄ . To determine a new fuzzy topology from the existing one, the earlier fuzzy operators are explored. Such a new fuzzy topology is called primal fuzzy topology. Various properties of …primal fuzzy topologies are found. Among others, the structure of a fuzzy base that generates a primal fuzzy topology. Furthermore, the concept of compatibility between fuzzy primals and fuzzy topologies is introduced, and some equivalent conditions to that concept are examined. It is shown that if a fuzzy primal is compatible with a fuzzy topology, then the fuzzy base that produces the primal fuzzy topology is itself a fuzzy topology. Show more
Keywords: Fuzzy primal, fuzzy grill, fuzzy ideal, primal fuzzy topology, fuzzy ideal topology
DOI: 10.3233/JIFS-238408
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-10, 2024
Article Type: Research Article
Abstract: Background: Breast cancer diagnosis relies on accurate lesion segmentation in medical images. Automated computer-aided diagnosis reduces clinician workload and improves efficiency, but existing image segmentation methods face challenges in model performance and generalization. Objective: This study aims to develop a generative framework using a denoising diffusion model for efficient and accurate breast cancer lesion segmentation in medical images. Methods: We design a novel generative framework, PalScDiff, that leverages a denoising diffusion probabilistic model to reconstruct the label distribution for medical images, thereby enabling the sampling of diverse, plausible segmentation outcomes. Specifically, with the …condition of the corresponding image, PalScDiff learns to estimate the masses region probability through denoising step by step. Furthermore, we design a Progressive Augmentation Learning strategy to incrementally handle segmentation challenges of irregular and blurred tumors. Moreover, multi-round sampling is employed to achieve robust breast mass segmentation. Results: Our experimental results show that PalScDiff outperforms established models such as U-Net and transformer-based alternatives, achieving an accuracy of 95.15%, precision of 79.74%, Dice coefficient of 77.61%, and Intersection over Union (IOU) of 81.51% . Conclusion: The proposed model demonstrates promising capabilities for accurate and efficient computer-aided segmentation of breast cancer. Show more
Keywords: Diffusion model, consistent regularization, breast cancer, medical image segmentation, data augmentation
DOI: 10.3233/JIFS-239703
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Yang, Guang | Qi, Juntong | Wang, Mingming | Wu, Chong | Liu, Yansheng | Liu, Zhengjun | Ping, Yuan
Article Type: Research Article
Abstract: Target encirclement is widely used in the field of unmanned aerial vehicles(UAVs), which can effectively monitor and intercept external threats. However, the integration from target detection, localization to final tracking is difficult or costly. This article proposes a complete and inexpensive framework of the target encirclement for multiple quadrotors. The framework consists of three modules: object detection, target localization and formation tracking. Firstly, a one-stage object detector based on a convolutional neural network is used to achieve fast and accurate object detection. Then, combined with the position and attitude states of the quadrotor, a 3D target localization scheme to locate …the target position is proposed. Based on consensus theory, a time-varying formation tracking control protocol is proposed. Finally, a multiple quadrotor platform composed of one reconnaissance quadrotor and four hunter quadrotors is built with self-organizing network communication, which avoids the expensive cost of deploying object detection modules on each quadrotor platform. We deployed the framework on the multiple quadrotor platform and conducted static and dynamic localization and encirclement experiments with a minibus as the target. The result shows that the reconnaissance quadrotors can detect and accurately locate targets over 30 fps , and the average deviation of locating the target minibus could reach a minimum of 0.0712 m . The hunter quadrotors could track and encircle the dynamic moving target minibus in a time-varying formation. Experiments demonstrate the effectiveness and practicality of the proposed framework of the target encirclement for multiple quadrotors. Show more
Keywords: Multiple quadrotors, target encirclement, visual detection, target localization, time-varying formation tracking
DOI: 10.3233/JIFS-238335
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Ou, Qiqi | Zhang, Xiaohong | Wang, Jingqian
Article Type: Research Article
Abstract: Fuzzy rough sets (FRSs) play a significant role in the field of data analysis, and one of the common methods for constructing FRSs is the use of the fuzzy logic operators. To further extend FRSs theory to more diverse information backgrounds, this article proposes a covering variable precision fuzzy rough set model based on overlap functions and fuzzy β-neighbourhood operators (OCVPFRS). Some necessary properties of OCVPFRS have also been studied in this work. Furthermore, multi-label classification is a prevalent task in the realm of machine learning. Each object (sample or instance) in multi-label data is associated with various labels (classes), …and there are numerous features or attributes that need to be taken into account within the attribute space. To enhance various performance metrics in the multi-label classification task, attribute reduction is an essential pre-processing step. Therefore, according to overlap functions and fuzzy rough sets’ excellent work on applications: such as image processing and multi-criteria decision-making, we establish an attribute reduction method suitable for multi-label data based on OCVPFRS. Through a series of experiments and comparative analysis with existing multi-label attribute reduction methods, the effectiveness and superiority of the proposed method have been verified. Show more
Keywords: Fuzzy rough sets, overlap functions, fuzzy β-neighbourhood operators, attribute reduction, multi-label classification
DOI: 10.3233/JIFS-238245
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-19, 2024
Authors: Embriz-Islas, Cesar | Benavides-Alvarez, Cesar | Avilés-Cruz, Carlos | Zúñiga-López, Arturo | Ferreyra-Ramírez, Andrés | Rodríguez-Martínez, Eduardo
Article Type: Research Article
Abstract: Speech recognition with visual context is a technique that uses digital image processing to detect lip movements within the frames of a video to predict the words uttered by a speaker. Although models with excellent results already exist, most of them are focused on very controlled environments with few speaker interactions. In this work, a new implementation of a model based on Convolutional Neural Networks (CNN) is proposed, taking into account image frames and three models of audio usage throughout spectrograms. The results obtained are very encouraging in the field of automatic speech recognition.
Keywords: CNN, artificial intelligence, deep learning, speech recognition
DOI: 10.3233/JIFS-219346
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Zavala-Díaz, Jonathan | Olivares-Rojas, Juan C. | Gutiérrez-Gnecchi, José A. | Téllez-Anguiano, Adriana C. | Alcaraz-Chávez, J. Eduardo | Reyes-Archundia, Enrique
Article Type: Research Article
Abstract: Efficient medical information management is essential in today’s healthcare, significantly to automate diagnoses of chronic diseases. This study focuses on the automated identification of diabetic patients through a clinical note classification system. This innovative approach combines rules, information extraction, and machine learning algorithms to promise greater accuracy and adaptability. Initially, the four algorithms evaluated showed similar performance, with Gradient Boosting standing out with an accuracy of 0.999. They were tested on our clinical and oncology notes, where SVM excelled in correctly labeling non-oncology notes with a 0.99. Gradient Boosting had the best average with 0.966. The combination of rules, information …extraction, and Random Forest provided the best average performance, significantly improving the classification of clinical notes and reducing the margin of error in identifying diabetic patients. The principal contribution of this research lies in the pioneering integration of rule-based methods, information extraction techniques, and machine learning algorithms for enhanced accuracy in diabetic patient identification. For future work, we consider implementing these algorithms in natural clinical settings to evaluate their practical performance. Additionally, additional approaches will be explored to improve the accuracy and applicability of clinical note-grading systems in healthcare. Show more
Keywords: NLP, diabetes, machine learning, binary classification, word frequency analysis
DOI: 10.3233/JIFS-219375
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2024
Authors: Martinez, German | Duta, Eduard-Andrei | Sanchez-Romero, Jose-Luis | Jimeno-Morenilla, Antonio | Mora-Mora, Higinio
Article Type: Research Article
Abstract: Within various industrial settings, such as shipping, aeronautics, woodworking, and footwear, there exists a significant challenge: optimizing the extraction of sections from material sheets, a process known as “nesting”, to minimize wasted surface area. This paper investigates efficient solutions to complex nesting problems, emphasizing rapid computation over ultimate precision. We introduce a dual-approach methodology that couples both a greedy technique and a genetic algorithm. The genetic algorithm is instrumental in determining the optimal sequence for placing sections, ensuring each is located in its current best position. A specialized representation system is devised for both the sections and the material sheet, …promoting streamlined computation and tangible results. By balancing speed and accuracy, this study offers robust solutions for real-world nesting challenges within a reduced computational timeframe. Show more
Keywords: Genetic algorithm, 2D nesting, irregular pattern, cutting, industrial automation
DOI: 10.3233/JIFS-219345
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Ling, Lina | Wen, Mi | Wang, Haizhou | Zhu, Zhou | Meng, Xiangjie
Article Type: Research Article
Abstract: The detection of out-of-distribution (OoD) samples in semantic segmentation is crucial for autonomous driving, as deep learning models are typically trained under the assumption of a closed environment, whereas the real world presents an open and diverse set of scenarios. Existing methods employ uncertainty estimation, image reconstruction, and other techniques for OoD sample detection. We have observed that different classes may exhibit connections and associations in varying contexts. For example, objects encountered by autonomous vehicles differ in rural road scenes compared to urban environments, and the likelihood of encountering novel objects varies. This aspect is missing in current anomaly detection …methods and is vital for OoD sample detection. Existing approaches solely consider the relative significance of each prediction class, overlooking the inter-object correlation. Although prediction scores (e.g., max logits) obtained from the segmentation network are applicable for OoD sample detection, the same problem persists, particularly for OoD objects. To address this issue, we propose the utilization of the Mahalanobis distance of max logits to evaluate the final predicted score. By calculating the Mahalanobis distance, the paper aims to uncover correlations between different classes, thus enhancing the effectiveness of OoD detection. To this end, we also extend the state-of-the-art segmentation model, DeepLabV3+, to enable OoD sample detection in this paper. Specifically, this paper proposes a novel backbone network, SOD-ResNet101, for extracting contextual and multi-scale semantic information, leveraging the class correlation feature of the Mahalanobis distance to enhance the detection performance of out-of-distribution objects. Notably, our approach eliminates the need for external datasets or separate network training, making it highly applicable to existing pretraining segmentation models. Show more
Keywords: Semantic segmentation, deep learning, anomaly segmentation, automatic driving, out-of-distribution detection
DOI: 10.3233/JIFS-237799
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Kumar Sahu, Vinay | Pandey, Dhirendra | Singh, Priyanka | Haque Ansari, Md Shamsul | Khan, Asif | Varish, Naushad | Khan, Mohd Waris
Article Type: Research Article
Abstract: The Internet of Things (IoT) strategy enables physical objects to easily produce, receive, and exchange data. IoT devices are getting more common in our daily lives, with diverse applications ranging from consumer sector to industrial and commercial systems. The rapid expansion and widespread use of IoT devices highlight the critical significance of solid and effective cybersecurity standards across the device development life cycle. Therefore, if vulnerability is exploited directly affects the IoT device and the applications. In this paper we investigated and assessed the various real-world critical IoT attacks/vulnerabilities that have affected IoT deployed in the commercial, industrial and consumer …sectors since 2010. Subsequently, we evoke the vulnerabilities or type of attack, exploitation techniques, compromised security factors, intensity of vulnerability and impacts of the expounded real-world attacks/vulnerabilities. We first categorise how each attack affects information security parameters, and then we provide a taxonomy based on the security factors that are affected. Next, we perform a risk assessment of the security parameters that are encountered, using two well-known multi-criteria decision-making (MCDM) techniques namely Fuzzy-Analytic Hierarchy Process (F-AHP) and Fuzzy-Analytic Network Process (F-ANP) to determine the severity of severely impacted information security measures. Show more
Keywords: IoT attacks, fuzzy-ANP, fuzzy-AHP, MCDM, IoT vulnerabilities
DOI: 10.3233/JIFS-233759
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Bochkarev, Vladimir V. | Savinkov, Andrey V. | Shevlyakova, Anna V. | Solovyev, Valery D.
Article Type: Research Article
Abstract: This work considers implementation of a diachronic predictor of valence, arousal and dominance ratings of English words. The estimation of affective ratings is based on data on word co-occurrence statistics in the large diachronic Google Books Ngram corpus. Affective ratings from the NRC VAD dictionary are used as target values for training. When tested on synchronic data, the obtained Pearson‘s correlation coefficients between human affective ratings and their machine ratings are 0.843, 0.779 and 0.792 for valence, aroused and dominance, respectively. We also provide a detailed analysis of the accuracy of the predictor on diachronic data. The main result of …the work is creation of a diachronic affective dictionary of English words. Several examples are considered that illustrate jumps in the time series of affective ratings when a word gains a new meaning. This indicates that changes in affective ratings can serve as markers of lexical-semantic changes. Show more
Keywords: Affective words, affective norms, sentiment dictionary, word valence ratings, lexical semantic change
DOI: 10.3233/JIFS-219358
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Zhang, Yingmin | Yi, Afa | Li, Shuo
Article Type: Research Article
Abstract: The constant development and application of new technologies, such as big data, artificial intelligence and the mobile Internet, have profoundly changed the personal and professional spheres. Despite these advances, finance professionals are still faced with a multitude of routine, repetitive and error-prone tasks. At the same time, they are challenged by the shift to management accounting, resulting in reduced productivity. This paper addresses these issues by introducing a financial statement filing robot developed using Robotic Process Automation (RPA) technology. The application of this robot has been shown to provide superior efficiency and accuracy, reduce the heavy burden of routine tasks, …and facilitate a smooth transition to management accounting practices. In addition, this research provides a valuable reference for the application and diffusion of RPA technology in the financial sector. Given the large amount of text data generated by financial processes, this paper proposes an automatic text categorization model. The effectiveness of the model is demonstrated as a response to address the challenges encountered in the consultation and archiving process. This contribution informs the development of text categorization robots tailored to the needs of finance professionals. Show more
Keywords: RPA technology, robot, financial statements, text classification, naive Bayes classifier model
DOI: 10.3233/JIFS-236716
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-10, 2024
Authors: Jun, Dai | Huijie, Shi | Yanqin, Li | Junwei, Zhao | Naohiko, Hanajima
Article Type: Research Article
Abstract: Cylinder liner is an internal part of the automobile engine, which plays an important role in the automobile internal combustion engine. Therefore, it is a top priority to accurately and quickly detect the cylinder liner surface defects. In order to effectively achieve the classification and localization of surface defects on the cylinder liner, this paper establishes a dataset for surface defects on cylinder liner and proposes a based on improved YOLOv5 algorithm for detecting surface defects on cylinder liner. Firstly, a machine vision system is established to acquire on-site images and perform manual annotation to build the dataset of surface …defects on cylinder liner. Secondly, the GSConv SlimNeck mechanism is introduced to reduce the model complexity; the Bi-directional Feature Pyramid Network (BiFPN) is used to fuse the feature information at different scales to enhance the detection accuracy of small surface defects on cylinder liner; and embedding the SimAM attention mechanism to focus on the object region of interest and improve the accuracy and robustness of the model. The final improved YOLOv5 model reduces the number of model parameters by 15.8% compared to the non-improved YOLOv5. And the experimental results on our self-built dataset for cylinder liner defects show that the mAP0.5 is improved by 0.4%. This means that the accuracy of model detection was not compromised. This method can be applied to actual production processes. Show more
Keywords: Cylinder liner defect detection, YOLOv5, GSConv SlimNeck, BiFPN, SimAM
DOI: 10.3233/JIFS-237793
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Hu, Man | Sun, Dezhi | Bai, Yihan | Xiao, Han | You, Fucheng
Article Type: Research Article
Abstract: In the realm of graph representation learning, Graph Neural Networks (GNNs) have demonstrated exceptional efficacy across diverse tasks. Typically, GNNs employ message-passing schemes to disseminate node features along graph structures, culminating in learned graph representations. However, their heavy reliance on smoothed node features over graph structures, coupled with limited expressiveness in the presence of node attributes, often constrains link prediction performance. To surmount this challenge, we propose GTLP, a Graph Transformer based link prediction framework. GTLP integrates unsupervised GNNs and structure encoding, enabling a holistic consideration of both topological structures and node features. This approach preserves critical node location and …role information, enhancing the model’s expressiveness. By introducing the Graph Transformer model, GTLP adeptly incorporates neighbor information, refining embedding quality and bolstering the model’s learning and generalization capabilities. Notably, our method exhibits superior scalability, accommodating diverse techniques for information extraction, embedding learning, and sampling. Experimental results underscore GTLP’s state-of-the-art performance, outpacing various baselines across five real-world datasets. Show more
Keywords: Deep learning, graph neural networks, graph transformer, link prediction
DOI: 10.3233/JIFS-237506
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Chen, Xinying | Hu, Mingjie
Article Type: Research Article
Abstract: With the rapid proliferation of substantial textual data from sources such as social media, online comments, and news articles, sentiment analysis has become increasingly crucial. However, existing deep learning methods have overlooked the significance of part-of-speech (POS) and emotional words in understanding the emotion of text. Based on this, this paper proposes a sentiment analysis approach that combines multiple features with a dual-channel network. Firstly, the vector representation of the text is obtained through Robustly Optimized BERT Pretraining Approach (RoBERTa). Secondly, the POS features and word emotional features are separately updated using self-attention to calculate weights. Concatenating words, POS and …emotion, feature dimension reduction and fusion are achieved through a linear layer. Finally, the fused feature vector is input into a dual-channel network composed of Bidirectional Gated Recurrent Unit (BiGRU) and Deep Pyramid Convolutional Neural Network (DPCNN). Experimental results demonstrate that the proposed method achieves higher classification accuracy than the comparative methods on three sentiment analysis datasets. Moreover, the experimental results fully validate the effectiveness of the proposed approach. Show more
Keywords: Sentiment analysis, part-of-speech, RoBERTa, bidirectional gated recurrent unit, deep pyramid convolutional neural network
DOI: 10.3233/JIFS-237749
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Nisha, B. Muthu | Selvakumar, J. | Nithya, V.
Article Type: Research Article
Abstract: The provision of secure and sustainable energy services is ensured by this research, also contributing to the advancement of technology align with the Sustainable Development Goals (SDGs). The motivation behind this study stems from the critical need to bolster hardware security within cutting-edge smart grid infrastructure, and more specifically, for smart energy metering technology. To address this need, this paper introduces a feasible and modular approach for enhancing the security through the implementation of a cryptographic key generator. This key generator is based on a modified Delay-based Physically Unclonable Function (PUF), which incorporates the innovative concept of a Delay Locked …Loop(DLL).The reliability of the proposed PUFs has been rigorously assessed, demonstrating impressive performance levels of 98.02% and 99.1% across a wide temperature and supply voltage, spanning from -40°C to 80°C and (3.0-3.6) V. This is showcasing exceptional functionality within the smart meter’s operational parameters.The effectiveness of this approach is confirmed through practical testing conducted on the ZYNQ-7 ZC 702 Field-Programmable Gate Array (FPGA) platform.The outcomes are encouraging by substantial uniqueness (55.96% and 56.2%) and uniformity (51.2% and 49.15%). This research significantly advances the state of the art by surpassing previous investigations into XOR Arbiter PUF (XOR APUF) and Configurable Ring Oscillator PUF (CRO PUF) designs. Furthermore, the paper delves into an examination of the proposed design’s resilience against modeling attacks, along with comprehensive security assessments. Show more
Keywords: Sustainable development goals, smart energy meter, delay locked loop, physically unclonable function, field programmable gate array
DOI: 10.3233/JIFS-240099
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Gowri, S. | Vennila, B. | Antony Crispin Sweety, C.
Article Type: Research Article
Abstract: The primary focus of this work is to develop the concept of bipolar N-neutrosophic supra topological spaces. Also, extended some concepts such as closure and interior operators of N-neutrosophic supra topological spaces to Bipolar N-neutrosophic supra topological spaces. The properties and relationship between weak forms of bipolar N-neutrosophic supra topological open sets are also established. Further, suggested several separations amongst bipolar N-neutrosophic supra sets. Some distance between bipolar N-neutrosophic sets is introduced and an efficient approachfor group multi-criteria decision making based on bipolar N-neutrosophic sets is proposed.
Keywords: Bipolar N-neutrosophic supra topology, bipolar N-neutrosophic supra α-open set, bipolar N-neutrosophic supra semi-open, bipolar N-neutrosophic supra β-open and bipolar N-neutrosophic supra pre-open, N-valued interval neutrosophic sets
DOI: 10.3233/JIFS-224450
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Vallejos, Sebastian | Armentano, Marcelo G. | Berdun, Luis | Schiaffino, Silvia | González Císaro, Sandra | Nigro, Oscar | Balduzzi, Leonardo | Cuesta, Ignacio
Article Type: Research Article
Abstract: Product classification is a critical task for the smooth running of the purchase process in e-commerce websites. When it comes to P2P marketplaces, users can act both as sellers and as buyers, and they need to assign predefined categories to the products they want to sell. Besides being tedious for users, this task can result in ambiguous or inaccurate assignments. This article presents a method for the automatic categorization of items offered in a local P2P marketplace using a multi-level classification approach. Our experiments demonstrated a significant improvement in the classification results of the proposed solution compared to a traditional …direct classification approach. Show more
Keywords: Classification, e-commerce, NLP, P2P marketplace
DOI: 10.3233/JIFS-219344
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2024
Authors: Brännström, Andreas | Nieves, Juan Carlos
Article Type: Research Article
Abstract: This paper introduces an automated decision-making framework for providing controlled agent behavior in systems dealing with human behavior-change. Controlled behavior in such settings is important in order to reduce unexpected side-effects of a system’s actions. The general structure of the framework is based on a psychological theory, the Theory of Planned Behavior (TPB), capturing causes to human motivational states, which enables reasoning about dynamics of human motivation. The framework consists of two main components: 1) an ontological knowledge-base that models an individual’s behavioral challenges to infer motivation states and 2) a transition system that, in a given motivation state, decides …on motivational support, resulting in transitions between motivational states. The system generates plans (sequences of actions) for an agent to facilitate behavior change. A particular use-case is modeled regarding children with Autism Spectrum Conditions (ASC) who commonly experience difficulties in everyday social situations. An evaluation of a proof-of-concept prototype is performed that presents consistencies between ASC experts’ suggestions and plans generated by the system. Show more
Keywords: Interactive agents, strategic decision-making, behavior-change systems, theory of planned behavior, Autism
DOI: 10.3233/JIFS-219335
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2024
Authors: Li, Fuxue | Chi, Chuncheng | Yan, Hong | Zhang, Zhen | Zhao, Zhongchao
Article Type: Research Article
Abstract: Transformer-based neural machine translation (NMT) models have achieved state-of-the-art performance in the machine translation paradigm. These models learn the translation knowledge from the bilingual corpus through the attention mechanism automatically. This differs from the way human translators approach sentence translation, where prior knowledge plays a significant role. Inspired by this, a word translation augmentation (WTA) method is proposed to improve the Transformer-based NMT model. The main steps are as follows: Firstly, constructing the word alignment rules based on the training set. Next, generating the translation rules for source words according to the word alignment rules. Lastly, incorporating the potential translation …candidates for each source word into the NMT model during the training and testing procedure. In addition, the WTA method introduces the idea of Mixup for translation candidates of a source word and employs two augmentation strategies to augment the encoder. The results of experiments on several translation tasks with high-resource and low-resource indicate the effectiveness of the proposed method compared with the corresponding strong baseline, and the improvement in BLEU score achieved ranges from 0.42 to 0.63. Show more
Keywords: Neural machine translation, transformer, word embedding, word translations
DOI: 10.3233/JIFS-236170
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Jia, Liu
Article Type: Research Article
Abstract: This study explores a predictive approach using a combination of a one-dimensional convolutional neural network and support vector machine to enhance the management of cultural product trade between China and South Korea, addressing the trade deficit challenge. The methodology involves the collection and categorization of diverse data related to the trade of cultural products between the two countries, identifying data mining directions. The research incorporates the design of association rule functions to identify viable data sources, and employs a hybrid data clustering algorithm integrating technology and spectral clustering to cluster available data. The features extracted from the data mining process …are utilized as learning samples for trade prediction. Both a one-dimensional convolutional neural network and support vector machine are employed to model and predict cultural product trade between China and South Korea. Experimental results demonstrate the method’s accuracy in predicting trade situations under parameterized conditions. Throughout the prediction process, credibility measurement values and controllable correlation degrees consistently exceed 19 and 12.5, respectively, while uncertainty discrimination degrees and error coefficients remain below 12 and 6. Show more
Keywords: Big data integration, Chinese and Korean cultural products, trade prediction, data mining, convolutional neural network, support vector machine
DOI: 10.3233/JIFS-238061
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: López-López, Aurelio | Garcıa-Gorrostieta, Jesús Miguel | González-López, Samuel
Article Type: Research Article
Abstract: Emotion detection in educational dialogues, particularly within student-teacher interactions, has become a crucial research area for improving the learning experience. In this paper, we employ two models, one generic Bidirectional Encoder Representations from Transformers (BERT) and the Emotion detection model Robustly Optimized BERT Approach (EmoRoBERTa), to automatically classify emotions in a corpus of student-teacher chat interactions. Then subsequently, we validate these classifications using a scheme based on oracles, employing two generative large language models (ChatGPT and Bard). Experiments on emotion detection in dialogues between students and teachers revealed that EmoRoBERTa exhibited a reasonable level of agreement with the oracles, while …ChatGPT demonstrated the highest consistency with EmoRoBERTa’s predictions. Furthermore, we identified the impact of specific words on emotion classification, offering insights into the decision-making process of these models. The results not only highlight the prominent presence of emotions like approval, gratitude, curiosity, disapproval, amusement, confusion, remorse, joy , and surprise but also provide substantial support for the utilization of the proposed emotion detection model to enhance the student learning environment. Exploring the emotional aspects of educational dialogues holds the potential to enhance instruction methods, provide timely assistance to students in need, and create an improved learning atmosphere. Show more
Keywords: Emotion detection, learning interaction, transfer learning, large language models, active learning
DOI: 10.3233/JIFS-219340
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2024
Authors: Ratha, Ashoka Kumar | Behera, Santi Kumari | Devi, A. Geetha | Barpanda, Nalini Kanta | Sethy, Prabira Kumar
Article Type: Research Article
Abstract: With the rise of the fruit processing industry, machine learning and image processing have become necessary for quality control and monitoring of fruits. Recently, strong vision-based solutions have emerged in farming industries that make inspections more accurate at a much lower cost. Advanced deep learning methods play a key role in these solutions. In this study, we built an image-based framework that uses the ResNet-101 CNN model to identify different types of papaya fruit diseases with minimal training data and processing power. A case study to identify commonly encountered papaya fruit diseases during harvesting was used to support the results …of the suggested methodology. A total of 983 images of both healthy and defective papaya were considered during the experiment. In this study, we initially used the ResNet-101 CNN model for classification and then combined the deep features drawn out from the activation layer (fc1000) of the ResNet-101 CNN along with a multi-class Support Vector Machine (SVM) to classify papaya fruit defect detection. After comparing the performance of both approaches, it was found that Cubic SVM is the best classifier using the deep feature of ResNet-101 CNN, achieved with an accuracy of 99.5% and an area under the curve (AUC) of 1 without any classification error. The findings of this experiment reveal that the ResNet-101 CNN with the cubic SVM model can categorize good, diseased, and defective papaya pictures. Moreover, the suggested model executed the task in a greater way in terms of the F1- Score (0.99), sensitivity (99.50%), and precision (99.71%). The present work not only assists the end user in determining the type of disease but also makes it possible for them to take corrective measures during farming. Show more
Keywords: Disease classification, CNN (Convolutional Neural Network), ResNet-101, ML (Machine Learning), SVM (Support Vector Machine)
DOI: 10.3233/JIFS-239875
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Shi, Xiaolong | Kosari, Saeed | Rangasamy, Parvathi | Nivedhaa, R.K. | Rashmanlou, Hossein
Article Type: Research Article
Abstract: Modern image processing techniques are improving beyond old methods, which include advanced approaches, for example deep learning. Convolutional Neural Networks (CNNs) are excellent at automatic feature extraction, whereas Generative Adversarial Networks (GANs) produce realistic images. Transfer learning uses pre-trained models, whereas semantic segmentation identifies pixels in images. Super-resolution, style transfer, and attention mechanisms can increase the quality of images and understanding. Adversarial defenses address purposeful manipulations, while 3D image processing handles three-dimensional data. These advancements make use of improved computational power and massive datasets to revolutionize image processing capabilities. Traditional image processing algorithms frequently fail to handle the complex and …multidimensional structure of color images, particularly when dealing with uncertainty and imprecision. In this study, the 3D-EIFIM frame work is extented and scaled aggregation operations 3D-EIFIM tailored for image data are proposed. By representing each pixel as an entry of 3D-EIFIM and applying aggregation techniques to enable more effective image analysis, manipulation, and enhancement. The practical implications of this research are significant, as it can lead to advancements in fields such as computer vision, medical imaging, and remote sensing. Show more
Keywords: IFP, conjunction, disjunction, IFIM, EIFIM, 3D-IFIM, 3D-EIFIM
DOI: 10.3233/JIFS-238252
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Manju, S.C. | Swarnajyothi, K. | Geetha, J. | Somasundaram, K.
Article Type: Research Article
Abstract: The Padmakar-Ivan (PI) index of a connected graph G is given by PI (G ) = ∑e =(u ,v )∈E (G ) (|V (G ) | - N G (e )) and weighted Padmakar-Ivan index is PI w (G ) = ∑e =(u ,v )∈E (G ) (d G (u ) + d G (v )) (|V (G ) | - N G (e )) . In this paper, we present the PI index for various classes of perfect graphs, including block graphs, the line graph of unicyclic graphs, and split graphs. The theorems established in this study are applied to ascertain the PI index of chain and …cyclic silicates. Furthermore, we derive both the PI and weighted PI indices for the lexicographic product of two regular graphs and determine the exact values for the lexicographic product involving a regular graph and a complete multipartite graph. Show more
Keywords: PI index, weighted pi index, perfect graphs, block graphs, lexicographic product, regular graphs, chain and cyclic tetrahedral frameworks
DOI: 10.3233/JIFS-238204
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Chen, Jiankai | Li, Zhongyan | Wang, Xin | Zhai, Junhai
Article Type: Research Article
Abstract: Monotonic classification is a widely applied classification task where improvements in specific input values do not lead to worse outputs. Monotonic classifiers based on K-nearest neighbors (KNN) have become crucial tools for addressing such tasks. However, these models share drawbacks with traditional KNN classifiers, including high computational complexity and sensitivity to noise. Fuzzy Monotonic K-Nearest Neighbors (FMKNN) is currently the state-of-the-art KNN-based monotonic classifier, mitigating the impact of noise to some extent. Nevertheless, there is still room for improvement in reducing computational complexity and softening monotonicity in FMKNN. In this paper, we propose a prototype selection algorithm based on FMKNN, …named Condensed Fuzzy Monotonic K-Nearest Neighbors (C -FMKNN). This algorithm achieves a dynamic balance between monotonicity and test accuracy by constructing a joint evaluation function that combines fuzzy ranking conditional entropy and correct prediction. Data reduction and simplifying computations can be achieved by using C -FMKNN to filter out instance subsets under the adaptive dynamic balance between monotonicity and test accuracy. Extensive experiments show that the proposed C -FMKNN improves significantly in terms of ACCU, MAE and NMI compared with the involved KNN-based non-monotonic algorithms and non-KNN monotonic algorithms. Compared with the instance selection algorithms MCNN, MENN, and MONIPS, C -FMKNN improves the average values of ACCU, MAE, and NMI by 3.7%, 3.6% and 18.3%, respectively, on the relevant datasets. In particular, compared with the benchmark algorithm FMKNN, C -FMKNN achieves an average data reduction rate of 58.74% while maintaining or improving classification accuracy. Show more
Keywords: Monotonic classification, fuzzy monotonic K-nearest neighbor, fuzzy ranking conditional entropy, joint evaluation function, data reduction
DOI: 10.3233/JIFS-236643
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-22, 2024
Authors: Vimala, S. | Valarmathi, K.
Article Type: Research Article
Abstract: This study proposes a novel method using hybrid CNN-LSTM networks to measure and predict the effectiveness of speech and vision therapy. Traditional methods for evaluating therapy often rely on subjective assessments, lacking precision and efficiency. By combining CNN for visual data and MFCC for speech, alongside LSTM for temporal dependencies, the system captures dynamic changes in patients’ conditions. Pre-processing of audio and visual data enhances accuracy, and the model’s performance outperforms existing methods. This approach exhibits the potential of deep learning in monitoring patient progress effectively in speech and vision therapy, offering valuable insights for improving treatment outcomes. The proposed …system’s effectiveness is assessed by various performance metrics. The suggested system’s results are compared with those of other methods already in use. The study’s findings indicate that the suggested approach is more accurate than other existing models. In conclusion, this study offers important new information on how deep learning methods are being used to track patients’ progress in speech and vision therapy. Show more
Keywords: Monitor, speech and vision, deep learning, therapy patient, recording device, CNN-LSTM, categorization
DOI: 10.3233/JIFS-237363
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Ravi, Vinayakumar
Article Type: Research Article
Abstract: Deep learning-based models are employed in computer-aided diagnosis (CAD) tools development for pediatric pneumonia (P-Pneumonia) detection. The accuracy of the model depends on the scaling of the deep learning model. A survey on deep learning shows that models with a greater number of layers achieve better performances for P-Pneumonia detection. However, the identification of the optimal models is considered to be important work for P-Pneumonia detection. This work presents a hybrid deep learning model for P-Pneumonia detection. The model leverages the EfficientNetV2 model that employs various advanced methodologies to maintain the balance between the model scaling and the performance of …the model in P-Pneumonia detection. The features of EfficientNetV2 models are passed into global weighted average pooling (GWAP) which acts like an attention layer. It helps to extract the important features that point to the infected regions of the radiography image and discard all the unimportant information. The features from GWAP are high in dimension and using kernel-based principal component analysis (K-PCA), the features were reduced. Next, the reduced features are combined together and passed into a stacked classifier. The stacked classifier is a two-stage approach in which the first stage employs a support vector machine (SVM) and random forest tree (RFT) for the prediction of P-Pneumonia using the fused features and logistic regression (LRegr) on values of prediction for classification. Detailed experiments were done for the proposed method in P-Pneumonia detection using publically available benchmark datasets. Various settings in the experimental analysis are done to identify the best model. The proposed model outperformed the other methods by improving the accuracy by 4% in P-Pneumonia detection. To show that the proposed model is robust, the model performances were shown on the completely unseen dataset of P-Pneumonia. The hybrid deep learning-based P-Pneumonia model showed good performance on completely unseen data samples of P-Pneumonia patients. The generalization of the proposed P-Pneumonia model is studied by evaluating the model on similar lung diseases such as COVID-19 (CV-19) and Tuberculosis (TBS). In all the experiments, the P-Pneumonia model has shown good performances on similar lung diseases. This indicates that the model is robust and generalizable on data samples of different patients with similar lung diseases. The P-Pneumonia models can be used in healthcare and clinical environments to assist doctors and healthcare professionals in improving the detection rate of P-Pneumonia. Show more
Keywords: Pediatric pneumonia, machine learning, deep learning, dimensionality reduction, feature fusion
DOI: 10.3233/JIFS-219397
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-18, 2024
Authors: Vaikunta Pai, T. | Nethravathi, P.S. | Birau, Ramona | Popescu, Virgil | Karthik Pai, B.H. | Naik, Pramod Vishnu
Article Type: Research Article
Abstract: Multimodal conversational AI systems have gained significant attention due to their potential to enhance user experience and enable more interactive and engaging interactions. This vital and complex research field seeks to integrate diverse modalities, including text, images, and speech, to develop conversational AI systems capable of comprehending, perceiving, and generating responses within a multimodal framework. By seamlessly incorporating various modalities, these systems can provide a more comprehensive and immersive conversational experience, enabling users to communicate in a more natural and intuitively. This research presents a novel multimodal architecture empowered by Deep Neural Networks (DNNs) for simultaneous integration and processing of …diverse modalities. Multimodal data encompasses various sources like text, images, audio, video, or sensor data. The objective is to merge and harness information from these modalities to amplify learning and enhance performance across a spectrum of tasks. This research explores the extension of ChatGPT, a state-of-the-art conversational AI model, to handle multimodal inputs, including text and images or text and speech. We present a comprehensive analysis of the benefits and challenges of integrating various options into ChatGPT, examining their impact on understanding, interaction, and overall system performance. Through extensive experimentation and evaluation, we demonstrate the potential of multimodal ChatGPT to provide richer, more context-aware conversations, while also highlighting the existing limitations and open research questions in this evolving field. Multimodal ChatGPT outperform the current GPT-3.5 by 16.51% and it is clear that multimodal ChatGPTis capable of better performance and offer a pathway for further progress in the field of language models. Show more
Keywords: Large language model, generative pre-trained transformer, deep learning, State-Of-The-Art (SOTA), artificial intelligence (AI), reinforcement training from human feedback, natural language processing (NLP), convolutional neural networks (CNN), recurrent neural networks (RNN)
DOI: 10.3233/JIFS-239465
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Li, Ye | Zhou, Jingkang
Article Type: Research Article
Abstract: Semi-supervised learning (SSL) aims to reduce reliance on labeled data. Achieving high performance often requires more complex algorithms, therefore, generic SSL algorithms are less effective when it comes to image classification tasks. In this study, we propose ComMatch, a simpler and more effective algorithm that combines negative learning, dynamic thresholding, and predictive stability discriminations into the consistency regularization approach. The introduction of negative learning is to help facilitate training by selecting negative pseudo-labels during stages when the network has low confidence. And ComMatch filters positive and negative pseudo-labels more accurately as training progresses by dynamic thresholds. Since high confidence does …not always mean high accuracy due to network calibration issues, we also introduce network predictive stability, which filters out samples by comparing the standard deviation of the network output with a set threshold, thus largely reducing the influence of noise in the training process. ComMatch significantly outperforms existing algorithms over several datasets, especially when there is less labeled data available. For example, ComMatch achieves 1.82% and 3.6% error rate reduction over FlexMatch and FixMatch on CIFAR-10 with 40 labels respectively. And with 4000 labeled samples, ComMatch achieves 0.54% and 2.65% lower error rates than FixMatch and MixMatch, respectively. Show more
Keywords: Semi-supervised learning, negative learning, dynamic threshold, predictive stability
DOI: 10.3233/JIFS-233940
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Sun, Haobin | Chen, Bingsan | Zhang, Wenshui | Wei, Songma | Lian, Changwei
Article Type: Research Article
Abstract: In the process of production, the label on the product provides the basic product information. Due to the complex text contained on the product labels, the high accuracy recognition for online production labels has always been a challenging problem. To address this issue, a more effective method for complex text detection by improving the convolutional recurrent neural network has been proposed to enhance the recognition accuracy of complex text. Firstly, the SE-DenseNet feature extraction network has been introduced for feature extraction, aiming to improve the model’s depth and feature extraction capacity. Then, the Bi-GRU network is utilized to learn and …model the hidden states and spatial features extracted by SE-DenseNet, anticipate preliminary sequence results, reduce model parameters, and improve the model’s calculation performance. Finally, the CTC network is employed for transcription to convert each feature sequence prediction output by Bi-GRU into a label sequence, achieving complex text recognition. Experimental results on the SVT, IIIT-5K, ICDAR2013 public dataset, and a self-built dataset demonstrate that the proposed model achieves superior outcomes on both public and self-built datasets. Remarkably, the model exhibits the highest recognition accuracy of 93.2% on the ICDAR2013 public dataset, demonstrating its potential to support complex text recognition for online production labels. Show more
Keywords: Online production labels, complex text recognition, SE-DenseNet, Bi-GRU
DOI: 10.3233/JIFS-234748
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Lv, Zhangwei
Article Type: Research Article
Abstract: In the context of China’s cultural and tourism industry, cultural equipment plays a critical role in cultural dissemination, especially in remote areas with harsh road conditions and unique environmental factors. However, the efficiency and stability of manual analysis are significantly challenged by these conditions and the vast yet sparsely collected monitoring data. This study aims to develop a method for extracting valuable information from monitoring data to assess the health status of cultural equipment. We introduce a deep learning-based algorithm that leverages convolutional neural networks (CNNs) to extract local features from multidimensional monitoring indicators and long short-term memory (LSTM) networks …to capture time series features, facilitating the classification of cultural equipment’s health status. The algorithm’s effectiveness is demonstrated through simulation results, highlighting its practicality and applicability in real-world scenarios. This research not only provides a novel approach for cultural equipment health assessment but also contributes significantly to the field by addressing the challenges of data analysis in complex environments, underscoring the importance of technological advancements in preserving cultural heritage. Show more
Keywords: Environmental evaluation, convolutional neural network, long short term memory, health status
DOI: 10.3233/JIFS-241607
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Shamma, Aashitha L. | Vekkot, Susmitha | Gupta, Deepa | Zakariah, Mohammed | Alotaibi, Yousef Ajami
Article Type: Research Article
Abstract: This paper investigates the potential of COVID-19 detection using cough, breathing, and voice patterns. Speech-based features, such as MFCC, zero crossing rate, spectral centroid, spectral bandwidth, and chroma STFT are extracted from audio recordings and evaluated for their effectiveness in identifying COVID-19 cases from Coswara dataset. The explainable AI SHAP tool is employed which identified MFCC, zero crossing rate, and spectral bandwidth as the most influential features. Data augmentation techniques like random sampling, SMOTE, Tomek, and Edited Nearest Neighbours (ENN), are applied to improve the performance of various machine learning models used viz. Naive Bayes, K-nearest neighbours, support vector machines, …XGBoost, and Random Forest. Selecting the top 20 features achieves an accuracy of 73%, a precision of 74%, a recall of 94%, and an F1-score of 83% using the Random Forest model with the Tomek sampling technique. These findings demonstrate that a carefully selected subset of features can achieve comparable performance to the entire feature set while maintaining a high recall rate. The success of the Tomek undersampling technique highlights the ability of model to handle sparse clinical data and predict COVID-19 and associated diseases using speech-based features. Show more
Keywords: Covid-19, MFCC, spectral bandwidth, zero crossing rate, SHAP tool, Tomek
DOI: 10.3233/JIFS-219387
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Zou, Chao | Zhu, Jiwei | Cao, Jiawei | Wang, Xin | Mei, Zhenyu | Zhou, Kui
Article Type: Research Article
Abstract: Prefabricated buildings (PBs) are a new type of building construction, which are less time-consuming and cause low environmental pollution and resource consumption. They play an important role in industrialized construction and clean production and have gained worldwide attention. However, the high construction costs have become a major obstacle to their popularity and application. This study investigates the factors influencing construction costs of PBs in China using a systematic literature review (SLR), fuzzy interpretive structure modeling (fuzzy ISM), and the Matrice d’Impacts croises-multiplication appliqué an classment (MICMAC) technique. First, 32 influencing factors were identified from the SLR. Second, out of which …16 critical factors were selected and mapped in a hierarchical model through semi-structured interview screening, and the MICMAC technique was used to classify the cost-influencing factors of PBs into different categories. The results revealed that all identified factors played pivotal roles in various capacities and influenced the cost of PB construction. This study may assist administrators and policymakers in better understanding the factors that influence the costs of PBs construction to manage and reduce them. Show more
Keywords: Prefabricated buildings, construction costs, critical factors, fuzzy ISM, MICMAC technique
DOI: 10.3233/JIFS-240206
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2024
Authors: Ding, Zongchao
Article Type: Research Article
Abstract: The networks have achieved good results by using sparse connections, weight sharing, pooling, and establishing their own localized receptive fields. This work aims to improve the Space Invariant Artificial Neural Network approach and raise its recognition accuracy and convergence rate. Incorporating the continuous neural architecture into the Space Invariant Artificial Neural Network is the first step toward simultaneously learning the deep features of an image. Second, the skip convolution layer of ResNet serves as the foundation for developing a new residual module named QuickCut3-ResNet. A dual evaluation model is then developed to achieve the combined evaluation of the convolutional and …complete connection process. Ultimately, the best network parameters of the Space Invariant Artificial Neural Network are determined after simulation experiments are used to examine the impact of various network parameters on the network performance. Results from experiments demonstrate that the Space Invariant Artificial Neural Network technique described in this research can learn the image’s varied characteristics, which enhances the Space Invariant Artificial Neural Network’s capacity to recognize images and extract features accurately. Show more
Keywords: Artificial intelligence, big data, space invariant artificial neural network, image recognition, QuickCut3-ResNet
DOI: 10.3233/JIFS-239538
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2024
Authors: Wang, Zhimin | Li, Boquan
Article Type: Research Article
Abstract: This paper introduces an expert system to decision-making. The expert system is linguistic summarization combined with prioritized operators. In the practical decision-making problems, the information of attributes is linguistic type and needs to be converted into numerical type. The validity of the linguistic summarization is recorded as the attribute value. We discuss how to calculate the validity of the linguistic summarization, and present three prioritized operators. Then the three prioritized operators are used to aggregate the attribute values. Finally, a practical example is given. In addition, we conduct a comparative analysis between the expert system method and another multi-attribute decision-making …method by using a measure of specificity, and conclude that the expert system method is better. Show more
Keywords: Expert system, decision-making, linguistic summarization, prioritized operators, comparative analysis
DOI: 10.3233/JIFS-238556
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Lv, Fangxing | Liu, Wenfeng | Yang, Yuzhen | Gao, Yaling | Bao, Longqing
Article Type: Research Article
Abstract: The automatic generation of natural language is a complex and essential task in text processing. This study proposes a novel approach to address this fundamental problem by leveraging an improved version of DST_BERT, a model that converts input text into a vector representation. Our key contribution lies in the joint optimization of two models, NLU (Natural Language Under-standing) and NLG (Natural Language Generation), which enables us to obtain variable representations within a hidden space. This integration enhances the capabilities of both NLU and NLG in generating coherent and contextually appropriate language. The NLU and NLG …models are seamlessly integrated with the hidden variable space, forming a generative representation model. To assess the effectiveness of our proposed approach, we conducted extensive experiments on the E2E and Weather datasets. The results highlight the state-of-the-art performance achieved by our model in generating natural language. Show more
Keywords: Natural language generation, natural language understanding, text summarization
DOI: 10.3233/JIFS-232981
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-9, 2024
Authors: Yang, Fan | Zhou, Qing | Su, Renbin | Xiong, Weihong
Article Type: Research Article
Abstract: Molecular graph representation learning has been widely applied in various domains such as drug design. It leverages deep learning techniques to transform molecular graphs into numerical vectors. Graph Transformer architecture is commonly used for molecular graph representation learning. Nevertheless, existing methods based on the Graph Transformer fail to fully exploit the topological structural information of the molecular graphs, leading to information loss for molecular representation. To solve this problem, we propose a novel molecular graph representation learning method called MTS-Net (Molecular Topological Structure-Network), which combines both global and local topological structure of a molecule. In global topological representation, the molecule …graph is first transformed into a tree structure and then encoded by employing a hash algorithm for tree. In local topological representation, paths between atom pairs are transcoded and incorporated into the calculation of the Transformer attention coefficients. Moreover, MTS-Net has intuitive interpretability for identifying key structures within molecules. Experiments on eight molecular property prediction datasets show that MTS-Net achieves optimal results in three out of five classification tasks, the average accuracy is 0.85, and all three regression tasks. Show more
Keywords: Molecular representation, graph structure, graph transformer, property prediction
DOI: 10.3233/JIFS-236788
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Veeraiah, D. | Sai Kumar, S. | Ganiya, Rajendra Kumar | Rao, Katta Subba | Nageswara Rao, J. | Manjith, Ramaswamy | Rajaram, A.
Article Type: Research Article
Abstract: Medical image fusion plays a crucial role in accurate medical diagnostics by combining images from various modalities. To address this need, we propose an AI model for efficient medical image fusion using multiple modalities. Our approach utilizes a Siamese convolutional neural network to construct a weight map based on pixel movement information extracted from multimodality medical images. We leverage medical picture pyramids to incorporate multiscale techniques, enhancing reliability beyond human visual intuition. Additionally, we dynamically adjust the fusion mode based on local comparisons of deconstructed coefficients. Evaluation metrics including F1-score, recall, accuracy, and precision are computed to assess performance, yielding …impressive results: an F1-score of 0.8551 and a mutual information (MI) value of 2.8059. Experimental results demonstrate the superiority of our method, achieving a remarkable 99.61% accuracy in targeted experiments. Moreover, the Structural Similarity Index (SSIM) of our approach is 0.8551. Compared to state-of-the-art approaches, our model excels in medical picture classification, providing accurate diagnosis through high-quality fused images. This research advances medical image fusion techniques, offering a robust solution for precise medical diagnostics across various modalities. Show more
Keywords: Multimodal medical image fusion, image classification, siamese CNN, LSTM, genetic algorithm
DOI: 10.3233/JIFS-240018
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Huang, Rongbing | Hanif, Muhammad Farhan | Aleem, Aqsa | Siddiqui, Muhammad Kamran | Hanif, Muhammad Faisal | Hussain, Mazhar
Article Type: Research Article
Abstract: The triangular γ-graphyne structure is highlighted in particular, as it is a new configuration with possible applications in medicine. We shed light on this structure’s special qualities and potential uses in healthcare by computing several topological indices linked to it through computational research. Furthermore, we use Shannon’s entropy measure to express the information content of the connection-based topological indices in tandem. This method offers a thorough comprehension of the intricate features and structural properties of the triangular γ-graphyne structure. A logarithmic regression model is built to establish a quantifiable relationship between the computed indices and entropy. The SPSS program was …used in the development of this model, allowing for a thorough examination of the relationship between structural features and informational entropy. A regression model based on triangular graphyne topological indices is used as a predictive tool for entropy estimation. Show more
Keywords: Connection number (CN), triangular γ-graphyne, line graph, logarithmic regression model, Shannon entropy
DOI: 10.3233/JIFS-240356
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Wang, Ke | Gu, Tianrui | Du, Xiaoye
Article Type: Research Article
Abstract: With the rapid economic development and increasingly serious environmental problems, many regions have launched green credit policies. Green credit can reduce the loan interest rate of the environmental protection industry and lower the financing threshold. Traditional risk prediction methods cannot comprehensively evaluate the green credit risk of the enterprise based on the degree of green environmental protection and the industry environment in which the enterprise is located, resulting in the inconsistency between the credit financial risk prediction and the actual results, which increases the bank credit risk. In order to strengthen the management level of green credit and reduce the …probability of non-performing loans, a scientific risk assessment method was constructed by using a combination of automatic encoding network and bidirectional long short-term memory neural network model to predict the financial risks of green credit, driven by multi-modal data. Through the study of multimodal data, this paper took green credit financial risk as the research object, aggregated the information of various enterprises to improve the bank’s capital utilization rate, and also promoted enterprises to take the initiative to transform into the direction of green environmental protection. Finally, the experiment proved that multimodal data fusion model was more superior than random forest in risk prediction, reducing the bank’s non-performing loan rate by 3.1% and improving the bank’s risk control level. Show more
Keywords: Financial risk, green credit, risk prediction, multimodal data
DOI: 10.3233/JIFS-237691
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
Authors: Wang, Hengyou | Ke, Rongji | Jiang, Xiang
Article Type: Research Article
Abstract: Due to its remarkable performance, the convolutional neural network (CNN) has gained widespread usage in image inpainting challenges. However, most of these CNN-based methods reconstruct images only in the spatial domain, which produces satisfactory outcomes for small-region inpainting tasks, but blurs the details and generates incomplete structures for large-region inpainting tasks with complex backgrounds. In this paper, we address the issue of large-region inpainting tasks by our novel Adaptive Fourier Neural Network . Specifically, in our network, a Fourier-based global receptive field module is introduced to incorporate frequency information and expand the receptive field by transforming local convolutions into …global convolutions, enabling the proposed network to transmit global information to the missing region. Furthermore, to better fuse spatial and frequency features, an attention-based joint space-frequency module is proposed to combine spatial and frequency information. Finally, to validate the effectiveness and robustness of our proposed method, we conduct qualitative and quantitative experiments on two popular datasets Paris StreetView and Places. The experimental results demonstrate that our proposed method outperforms state-of-the-art methods by generating sharper, more coherent, and visually plausible inpainting results. Code will be released after this work published: https://github.com/langka9/AFNN.git . Show more
Keywords: Large-region image inpainting, Fourier-based global receptive field, frequency domain, Fourier Neural Network
DOI: 10.3233/JIFS-239513
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-15, 2024
Authors: Ruby Elizabeth, J. | Kesavaraja, D. | Ebenezer Juliet, S.
Article Type: Research Article
Abstract: The retinal illness that causes vision loss frequently on the globe is glaucoma. Hence, the earlier detection of Glaucoma is important. In this article, modified AlexNet deep leaning model is proposed to category the source retinal images into either healthy or Glaucoma through the detection and segmentations of optic disc (OD) and optic cup (OC) regions in retinal pictures. The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC regions are detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region are classified and trained by the suggested AlexNet …deep leaning model. This model classifies the source retinal image into either healthy or Glaucoma. Finally, performance measures have been estimated in relation to ground truth pictures in regards to accuracy, specificity and sensitivity. These performance measures are contrasted with the other previous Glaucoma detection techniques on publicly accessible retinal image datasets HRF and RIGA. The suggested technique as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achieves 100% GDR for severe case on RIGA dataset. AIM: Segmenting the OD and OC areas and classifying the source retinal picture as either healthy or glaucoma-affected. METHODS: The retinal images are preprocessed and OD region is detected and segmented using circulatory filter. Further, OC region is detected and segmented using K-means classification algorithm. Then, the segmented OD and OC region classified are and trained by the suggested AlexNet deep leaning model. RESULTS: The suggested method as described in this work achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achieves 100% GDR for severe case on RIGA dataset. CONCLUSION: This article proposes the modified AlexNet deep learning models for the detections of Glaucoma utilizing retinal images. The OD region is detected using circulatory filter and OC region is detected using k-means classification algorithm. The detected OD and OC regions are utilized to classify the retinal images into either healthy or Glaucoma using the suggested AlexNet model. The proposed method obtains 100% Sey, 93.7% Spy and 96.6% CA on HRF dataset retinal images. The proposed AlexNet method obtains 97.7% Sey, 98% Spy and 97.8% CA on RIGA dataset retinal images. The proposed method stated in this article achieves 91.6% GDR for mild case and also achieves 100% GDR for severe case on HRF dataset. The suggested method as described in this work achieves 97.7% GDR for mild case and also achieves 100% GDR for severe case on RIGA dataset. Show more
Keywords: Retina, deep learning, OD, OC, AlexNet
DOI: 10.3233/JIFS-234131
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Liu, Kai | Wang, Mingyi
Article Type: Research Article
Abstract: China has emerged as one of the nations with the worst air pollution in recent years. The severe air pollution has caused a large number of population migration and also caused serious economic problems. Since the concentration of air pollutants can change quickly in a short amount of time, the study first tracked PM2.5 , PM10 , NO2 , CO, SO2 , and O3 as targets before using the particle swarm optimization algorithm to improve the PIO algorithm, which is based on the traditional pigeon swarm algorithm. To estimate the concentration of air pollutants, combine the wavelet packet decomposition …technique, MDS visualization method, and k-means algorithm. Then, apply the enhanced PIO algorithm to optimize the ELM algorithm. Finally, a new type of decomposition-optimization-clustering-integration hybrid learning model, namely DOCIAPC model, is constructed. The experimental findings indicate that, when predicting the concentration of various air pollutants, the DOCIAPC model’s average direction prediction accuracy is 90.37% . In conclusion, the model suggested in the study has excellent performance and applicability, and it can accurately predict the concentration of air pollutants, help the government take action to reduce air pollution, balance the environment and economy, as well as the allocation of labor and its resources in the city. Show more
Keywords: Air pollution, wavelet packet decomposition, pigeon group algorithm, K-means algorithm, MDS, labor force
DOI: 10.3233/JIFS-235902
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-12, 2024
Authors: Wang, Lu
Article Type: Research Article
Abstract: In this technology world, education is also becoming one of the basic necessities of human life like food, shelter, and clothes. Even in day-to-day daily activities, the world is moving toward an automated process using technology developments. Some of the technology developments in day-to-day life activities are smartphone, internet activities, and home and office appliances. To cope with these advanced technologies, the persons must have basic educational qualification to understand and operate those appliances easily. Apart from this, the education helps the person to develop their personal growth in both knowledge and wealth. With the development of technologies, different Artificial …Intelligence techniques have been applied on the datasets to analyze these factors and enhance the teaching method. But the current techniques were applied to one or two data models that analyze either their educational performance or demographic variable. But these models were not sufficient for analyzing all the factors that affects the education. To overcome this, a single optimized machine-learning approach is proposed in this paper to analyze the factors that affect the education. This analysis helps the faculty to enhance their teaching methodology and understand the student’s mentality toward education. The proposed Hybrid Cuckoo search-particle swarm optimization was implemented on three datasets to determine the factors that affect the education. These optimal factors are determined by identifying their relations to the final results of an individual person. All these optimal factors are combined and grades are grouped to analyze the proposed optimization process performance using regression neural network. The proposed optimization-based neural network was tested on three data models and its performance analysis showed that the proposed model can achieve higher accuracy of 99% that affects the individual education. This shows that the proposed model can help the faculty to enhance their attention to the students individually. Show more
Keywords: Education, demographic factors, optimization, hybrid, cuckoo search optimization, particle swarm, regression neural network
DOI: 10.3233/JIFS-234021
Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2024
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl