Journal of Intelligent & Fuzzy Systems - Volume 41, issue 6

Authors: Bhuvaneswari, R. | Ganesh Vaidyanathan, S.

Article Type: Research Article

Abstract: Diabetic Retinopathy (DR) is one of the most common diabetic diseases that affect the retina’s blood vessels. Too much of the glucose level in blood leads to blockage of blood vessels in the retina, weakening and damaging the retina. Automatic classification of diabetic retinopathy is a challenging task in medical research. This work proposes a Mixture of Ensemble Classifiers (MEC) to classify and grade diabetic retinopathy images using hierarchical features. We use an ensemble of classifiers such as support vector machine, random forest, and Adaboost classifiers that use the hierarchical feature maps obtained at every pooling layer of a convolutional …neural network (CNN) for training. The feature maps are generated by applying the filters to the output of the previous layer. Lastly, we predict the class label or the grade for the given test diabetic retinopathy image by considering the class labels of all the ensembled classifiers. We have tested our approaches on the E-ophtha dataset for the classification task and the Messidor dataset for the grading task. We achieved an accuracy of 95.8% and 96.2% for the E-ophtha and Messidor datasets, respectively. A comparison among prominent convolutional neural network architectures and the proposed approach is provided. Show more

Keywords: Diabetic retinopathy, convolutional neural network(CNN), feature extraction, ensemble of classifiers

DOI: 10.3233/JIFS-211364

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7407-7419, 2021

Authors: Liang, Pei | Hu, Junhua | Chin, KwaiSang

Article Type: Research Article

Abstract: The use of probabilistic linguistic preference relations (PLPRs) in pairwise comparisons enhances the flexibility of quantitative decision making. To promote the application of probabilistic linguistic term sets (PLTSs) and PLPRs, this paper introduces the consistency and consensus measures and adjustment strategies to guarantee the rationality of preference information utilized in the group decision making process. First of all, a novel entropy-based similarity measure is developed with PLTSs. Hereafter an improved consistency measure is defined on the basis of the proposed similarity measure, and a convergent algorithm is constructed to deal with the consistency improving process. Furthermore, a similarity-based consensus measure …is developed in a given PLPR, and the consensus reaching process is presented to deal with the unacceptable consensus degree. The proposed consistency improving and consensus reaching processes follow a principle of minimum information loss, called a local adjustment strategy. In particular, the presented methods not only overcome the deficiencies in existing studies but also enhance the interpretation and reduce the complexity of the group decision making process. Finally, the proposed consistency measure and improving process, as well as consensus measure and reaching process are verified through a numerical example for the medical plan selection issue. The result and in-depth comparison analysis validate the feasibility and effectiveness of the proposed methods. Show more

Keywords: Group decision making, PLTSs, PLPRs, consistency, consensus

DOI: 10.3233/JIFS-211371

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7421-7445, 2021

Authors: Ergun, Halime

Article Type: Research Article

Abstract: Fiber and vessel structures located in the cross-section are anatomical features that play an important role in identifying tree species. In order to determine the microscopic anatomical structure of these cell types, each cell must be accurately segmented. In this study, a segmentation method is proposed for wood cell images based on deep convolutional neural networks. The network, which was developed by combining two-stage CNN structures, was trained using the Adam optimization algorithm. For evaluation, the method was compared with SegNet and U-Net architectures, trained with the same dataset. The losses in these models trained were compared using IoU (Intersection …over Union), accuracy, and BF-score measurements on the test data. The automatic identification of the cells in the wood images obtained using a microscope will provide a fast, inexpensive, and reliable tool for those working in this field. Show more

Keywords: Image segmentation, fiber-vessel, microscopic wood cells, deep convolutional neural networks

DOI: 10.3233/JIFS-211386

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7447-7456, 2021

Authors: Yu, Xiaobing | Wu, Xuejing | Chen, Hong | Wang, Xuming | Li, Chenliang | Ji, Zhonghui

Article Type: Research Article

Abstract: Social vulnerability assessment is of great significance for risk management and reduction. Carrying out the assessment is beneficial to the sustainability of the development of society and the economy. For this purpose, Jiangsu province in China is taken as the study area to explore the social vulnerability assessment at a city level. A framework has been constructed from three dimensions of demographics, economics, and social security. In our study, a new approach based on the maximizing deviation method and TODIM model is proposed to evaluate social vulnerability in Jiangsu province. For the sake of analysis, we divide 13 cities of …Jiangsu province into three parts, namely the southern part, central part, and northern part, according to the geographical location. As a result, the north part performance of social vulnerability is the worst among the three regions. The average of the northern part has always obviously exceeded the others of Jiangsu province from 2012 to 2017, which indicates that the north part is the most vulnerable to natural hazards. In addition, the performance of the southern part is relatively better than that of the central region. Especially, Suqian has always been at the bottom from 2012 to 2017, which reveals the ability to withstand natural disasters is the most insufficient. Our findings also imply that social vulnerability is related to local economic development to some extent. Show more

Keywords: Social vulnerability, maximizing deviation method, TODIM model, risk management

DOI: 10.3233/JIFS-211428

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7457-7471, 2021

Authors: Chu, Xiaolin | Zhao, Ruijuan

Article Type: Research Article

Abstract: Building carbon emission prediction plays an irreplaceable role in low-carbon economy development, public health protection and environmental sustainability. It is significant to identify influential factors mainly contributed to building emission and predict emission accurately in order to harness the growth from the source. In this paper, 11 influencing factors of building carbon emission are identified and a support vector regression (SVR) prediction model is proposed to forecast building carbon emission considering improvement the prediction accuracy, generalization, and robustness. In the SVR model, parameters are optimized by particle swarm optimization (PSO) algorithm with the aim to improve performance. Cases in Shanghai’s …building sector are adopted to demonstrate practical applications of the proposed PSO-SVR prediction model. The results indicate that the presented prediction system has an outstanding performance in forecasting building carbon emission under multi-criteria evaluation. Furthermore, compared to the results from other four prediction models (e.g., linear regression, decision tree), it is shown that PSO-SVR model can achieve higher accuracy (e.g., improvement average of 1.01% R2 under training subset), better generalization (e.g., improvement average of 19.89% R2 under testing subset), and better robustness (e.g., improvement average of 18.93% R2 under different levels of noise intensity). Show more

Keywords: Building carbon emission, prediction model, support vector regression (SVR), particle swarm optimization (PSO), low-carbon economy development

DOI: 10.3233/JIFS-211435

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7473-7484, 2021

Authors: Wang, Fen | Ali, Zeeshan | Mahmood, Tahir | Zeng, Shouzhen

Article Type: Research Article

Abstract: The Muirhead mean (MM) operators offer a flexible arrangement with its modifiable factors because of Muirhead’s general structure. On the other hand, MM aggregation operators perform a significant role in conveying the magnitude level of options and characteristics. In this manuscript, the complex spherical fuzzy uncertain linguistic set (CSFULS), covering the grade of truth, abstinence, falsity, and their uncertain linguistic terms is proposed to accomplish with awkward and intricate data in actual life dilemmas. Furthermore, by using the MM aggregation operators with the CSFULS, the complex spherical fuzzy uncertain linguistic MM (CSFULMM), complex spherical fuzzy uncertain linguistic weighted MM (CSFULWMM), …complex spherical fuzzy uncertain linguistic dual MM (CSFULDMM), complex spherical fuzzy uncertain linguistic dual weighted MM (CSFULDWMM) operators, and their important results are also elaborated with the help of some remarkable cases. Additionally, multi-attribute decision-making (MADM) based on the Multi-MOORA (Multi-Objective Optimization Based on a Ratio Analysis plus full multiplicative form), and proposed operators are developed. To determine the rationality and reliability of the elaborated approach, some numerical examples are illustrated. Finally, the supremacy and comparative analysis of the elaborated approaches with the help of graphical expressions are also developed. Show more

Keywords: Complex spherical fuzzy uncertain linguistic sets, Muirhead mean Aggregation operators, Dual Muirhead mean Aggregation operators, Multi-attribute decision-making methods.

DOI: 10.3233/JIFS-211455

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7485-7510, 2021

Authors: Li, Chao | Yan, Yeyu | Zhao, Zhongying | Luo, Jun | Zeng, Qingtian

Article Type: Research Article

Abstract: Owing the continuous enrichment of mobile application resources, mobile applications carry almost all user behaviors and preferences. The analysis of user behavior regarding mobile terminals has become an important research direction. The frequency with which users click on mobile applications reflects their preferences to a certain extent. In this study, we propose a mobile application click-frequency prediction model based on heterogeneous information network representation. This model first constructs a heterogeneous information network between users’ mobile devices and mobile applications. To generate a meaningful sequence of network-embedded nodes, we perform a random walk on a specified meta-path. Finally, the prediction of …users’ mobile application click frequency is completed using representation fusion and matrix factorization. Experiments show that our method outperforms other baseline methods in terms of the mean absolute error and root mean square error. Therefore, the application of a heterogeneous information network representation method to the prediction model is effective. This study is significant to the behavior research of mobile terminal users. Show more

Keywords: Heterogeneous information network, network representation learning, prediction algorithm, mobile application

DOI: 10.3233/JIFS-211488

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7511-7526, 2021

Authors: Vo, Tham

Article Type: Research Article

Abstract: Recently, many pre-trained text embedding models have been applied to effectively extract latent features from texts and achieve remarkable performance in various downstream tasks of sentiment analysis domain. However, these pre-trained text embedding models also encounter limitations related to the capability preserving the syntactical structure as well as the global long-range dependent relationships of words. Thus, they might fail to recognize the relevant syntactical features of words as valuable evidences for analyzing sentiment aspects. To overcome these limitations, we proposed a novel deep semantic contextual embedding technique for sentiment analysis, called as: SE4SA. Our proposed SE4SA is a multi-level text …embedding model which enables to jointly exploit the long-range syntactical and sequential representations of texts. Then, these achieved rich semantic textual representations can support to have a better understanding on the sentiment aspects of the given text corpus, thereby resulting the better performance on sentiment analysis task. Extensive experiments in several benchmark datasets demonstrate the effectiveness or our proposed SE4SA model in comparing with recent state-of-the-art model. Show more

Keywords: Sentiment analysis, GCN, BERT, attention, masked language model

DOI: 10.3233/JIFS-211535

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7527-7546, 2021

Authors: Ma, Qihang | Zhang, Jian | Zhang, Jiahao

Article Type: Research Article

Abstract: Local information coding helps capture the fine-grained features of the point cloud. The point cloud coding mechanism should be applicable to the point cloud data in different formats. However, the local features of the point cloud are directly affected by the attributes, size and scale of the object. This paper proposes an Adaptive Locally-Coded point cloud classification and segmentation Network coupled with Genetic Algorithm(ALCN-GA), which can automatically adjust the size of search cube to complete network training. ALCN-GA can adapt to the features of 3D data at different points, whose adjustment mechanism is realized by designing a robust crossover and …mutation strategy. The proposed method is tested on the ModelNet40 dataset and S3DIS dataset. Respectively, the overall accuracy and average accuracy is 89.5% and 86.5% in classification, and overall accuracy and mIoU of segmentation is 80.34% and 51.05%. Compared with PointNet, average accuracy in classification and mIoU of segmentation is improved about 10% and 11% severally. Show more

Keywords: Genetic algorithm, 3D classification, segmentation, deep learning, local coding

DOI: 10.3233/JIFS-211541

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7547-7562, 2021

Authors: Zhang, Jinping | Deng, Xiaoping | Li, Chengdong | Su, Guanqun | Yu, Yulong

Article Type: Research Article

Abstract: Building energy consumption (BEC) prediction often requires constructing a corresponding model for each building based historical data. However, the constructed model for one building is difficult to be reused in other buildings. Recent approaches have shown that cloud-edge collaboration architecture is promising in realizing model reuse. How to complete the reuse of cloud energy consumption prediction models at the edge and reduce the computational cost of the model training is one of the key issues that need to be solved. To handle the above problems, a cloud-edge collaboration based transferring prediction method for BEC is proposed in this paper. Specifically, …a model library stored prediction models for different types of buildings is constructed based the historical energy consumption data and the long short-term memory (LSTM) network in the cloud firstly; then, the similarity measurement strategies of time series with different granularity are given, and the model to be transferred from the model library is matched by analyzing the similarity between observation data uploaded to the cloud and the historical data collected in the cloud; finally, the fine-tuning strategy of the matching prediction model is given, and this model is fine-tuned at the edge to achieve its reuse in concrete application scenarios. Experiments on practical datasets reveal that compared with the prediction model which doesn’t utilize the transfer strategy, the proposed prediction model has better performance according to MAE and RMSE. Experimental results also confirm that the proposed method effectively reduces the computational cost of the network training at the edge. Show more

Keywords: Cloud-edge collaboration, transfer learning, data driven, similarity analysis, energy consumption prediction

DOI: 10.3233/JIFS-211607

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7563-7575, 2021

Authors: Lin, Shaopei | Zhu, Wei

Article Type: Research Article

Abstract: This paper summarizes the relationship of subjective information with artificial intelligence (AI) technology and points out how the role of subjective information and its position in AI. Eventually, the characteristic of digital era is the “softening of the theories and hardening of the experiences”. Subjective information is widely used in digital revolution for transforming the qualitative estimations into quasi-quantitative solutions, such as the empirical methods in decision making for quantitative management, etc., it will be the transferor for realizing it. The theoretical formulation of how subjective information is digitized through “Fuzzy-AI Model” for digital revolution is presented in this paper; …it has becoming a universal problem solver of utilizing AI technology for quantizing the degree uncertainties in decision-making and fuzzy estimation. Besides, the “Big Data” searching will heavily depend on the completeness of its source information, yet “subjective information” approach can directly predict human thinking or the internal law of complicated objective events into an explicit digital form, for the completeness of source information to make the correct and comprehensive “Big Data” prediction possible. Practical case studies are presented. Show more

Keywords: Subjective information, AI application, mathematical operator, fuzzy-AI model, intelligent design

DOI: 10.3233/JIFS-211624

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7577-7587, 2021

Authors: Yihong, Li | Yunpeng, Wang | Tao, Li | Xiaolong, Lan | Han, Song

Article Type: Research Article

Abstract: DBSCAN (density-based spatial clustering of applications with noise) is one of the most widely used density-based clustering algorithms, which can find arbitrary shapes of clusters, determine the number of clusters, and identify noise samples automatically. However, the performance of DBSCAN is significantly limited as it is quite sensitive to the parameters of eps and MinPts . Eps represents the eps-neighborhood and MinPts stands for a minimum number of points. Additionally, a dataset with large variations in densities will probably trap the DBSCAN because its parameters are fixed. In order to overcome these limitations, we propose a new …density-clustering algorithm called GNN-DBSCAN which uses an adaptive Grid to divide the dataset and defines local core samples by using the Nearest Neighbor. With the help of grid, the dataset space will be divided into a finite number of cells. After that, the nearest neighbor lying in every filled cell and adjacent filled cells are defined as the local core samples. Then, GNN-DBSCAN obtains global core samples by enhancing and screening local core samples. In this way, our algorithm can identify higher-quality core samples than DBSCAN. Lastly, give these global core samples and use dynamic radius based on k-nearest neighbors to cluster the datasets. Dynamic radius can overcome the problems of DBSCAN caused by its fixed parameter eps. Therefore, our method can perform better on dataset with large variations in densities. Experiments on synthetic and real-world datasets were conducted. The results indicate that the average Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), Adjusted Mutual Information (AMI) and V-measure of our proposed algorithm outperform the existing algorithm DBSCAN, DPC, ADBSCAN, and HDBSCAN. Show more

Keywords: Density-based clustering algorithm, Grid, The nearest neighbor, DBSCAN

DOI: 10.3233/JIFS-211922

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7589-7601, 2021

Authors: More, Sujeet | Singla, Jimmy

Article Type: Research Article

Abstract: Knee rheumatoid arthritis (RA) is the highly prevalent, chronic, progressive condition in the world. To diagnose this disease in the early stage in detail analysis with magnetic resonance (MR) image is possible. The imaging modality feature allows unbiased assessment of joint space narrowing (JSN), cartilage volume, and other vital features. This provides a fine-grained RA severity evaluation of the knee, contrasted to the benchmark, and generally used Kellgren Lawrence (KL) assessment. In this research, an intelligent system is developed to predict KL grade from the knee dataset. Our approach is based on hybrid deep learning of 50 layers (ResNet50) with …skip connections. The proposed approach also uses Adam optimizer to provide learning linearity in the training stage. Our approach yields KL grade and JSN for femoral and tibial tissue with lateral and medial compartments. Furthermore, the approach also yields area under curve (AUC) of 0.98, accuracy 96.85%, mean absolute error (MAE) 0.015, precision 98.31%, and other commonly used parameters for the existence of radiographic RA progression which is improved than the existing state-of-the-art. Show more

Keywords: Magnetic resonance imaging, ResNet50, MultiResUNet, Sparse aware noise reduction Convolutional neural network (SANR_CNN), Adam optimizer

DOI: 10.3233/JIFS-212015

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 6, pp. 7603-7614, 2021