Journal of Intelligent & Fuzzy Systems - Volume 43, issue 1

Authors: Gupta, Bhavna | Kaur, Harmeet | Bedi, Punam

Article Type: Research Article

Abstract: A robust collaborative system of active products (a product is called active when its ownership does not get transferred from provider to requestor at the time of its usage) should have an in-built mechanism which can make entities (service provider(s) and requestor(s)) to decide with whom to collaborate. In the absence of such a mechanism, the system is bound to have high job failure rate, resulting in wastage of resources. This paper proposes a Trust based Multi-Agent Framework (TbMAF) for collaborative systems of active products which enable only trustworthy entities to collaborate, safeguarding both users’ sensitive applications and providers’ resources. …The trustworthiness of service provider(s) and requestor(s) is computed using Fuzzy Inference System (FIS) and Radial Basis Function Neural Network (RBFNN) methodologies, respectively. A prototype based on the proposed system has been tested using real time data of a collaborative system namely, EGEE (Enabling Grids for E-science). This paper finds evidence that the job failure rate is lower when collaborations take place only between trustworthy entities. Further, the proposed framework is found to be robust against malicious entities and can capture the evolving behavior of entities as well. Show more

Keywords: Trust, reputation, recommendation, active product, collaborative system

DOI: 10.3233/JIFS-212691

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 939-956, 2022

Authors: Shan, Chuanhui | Chen, Xiumei

Article Type: Research Article

Abstract: Because of the advantages of deep learning and information fusion technology, it has drawn much attention for researchers to combine them to achieve target recognition, positioning, and tracking. However, when the existing neural network process multichannel images (e.g., color images), multiple channels as a whole input into neural networks, which makes it hard for networks to fully learn information in R, G, and B channels of images. Therefore, it is not conducive to the final learning effect of the networks. To solve the problem, using different combinations of R, G, and B channels of color images for feature-level fusion, this …paper proposes three fusion types as “R/G/B”, “R+G/G+B/B+R”, and “R+G+B/R+G+B/R+G+B” multichannel concat-fusional convolutional neural networks. Experimental results show that multichannel concat-fusional convolutional neural networks with fusional types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” achieve better performance than the corresponding non-fusional convolutional neural networks on different datasets. It shows that networks with fusion types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” can learn more fully information of R, G, and B channels of color images and improve the learning performance of networks. Show more

Keywords: Information fusion technology, “R+G/G+B/B+R” fusional type, “R+G+B/R+G+B/R+G+B” fusional type, multichannel concat-fusional convolutional neural network, convolutional neural network

DOI: 10.3233/JIFS-212718

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 957-969, 2022

Authors: Poornima, R. | Elangovan, Mohanraj | Nagarajan, G.

Article Type: Research Article

Abstract: The evolving new and modern technologies raise the risks in the network which will be affected by several attacks and thus give rise to developing efficient network attack detection and classification methods. Here in this article for predicting and classifying the network attacks, the LSTM neural network with XGBoost is suggested in which the NSL-KDD dataset was utilized to train the LSTM in the study. In the beginning, the unnecessary data and the noisy data will be eliminated using the dataset and the feature subset with the most compelling features will be selected using the feature selection. By utilizing the …essential data, the proposed system will be trained and the training parameter values will be modified for maximizing the functionality of the proposed system. Then, the result of the proposed system will be evaluated with some of the existing machine learning and deep learning algorithms such as SVM, LR, RF, DNN, and CNN with the performance metrics like Accuracy, F1 score, Recall, and Precision. It was found that the proposed model outperforms better than the other algorithms as this model is trained with the most important features and due to this, the training time and overfitting of the learning model was reduced thereby increasing the model effectiveness Show more

Keywords: Deep learning, feature selection, LSTM, network attack, XGBoost

DOI: 10.3233/JIFS-212731

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 971-984, 2022

Authors: Yadav, Yadavendra | Chand, Satish | Sahoo, Ramesh Ch. | Sahoo, Biswa Mohan | Kumar, Somesh

Article Type: Research Article

Abstract:  Machine learning and deep learning methods have become exponentially more accurate. These methods are now as precise as experts of respective fields, so it is being used in almost all areas of life. Nowadays, people have more faith in machines than men, so, in this vein, deep learning models with the concept of transfer learning of CNN are used to detect and classify diabetic retinopathy and its different stages. The backbone of various CNN-based models such as InceptionResNetV2, InceptionV3, Xception, MobileNetV2, VGG19, and DenceNet201 are used to classify this vision loss disease. In these base models, transfer learning has been …applied by adding some layers like batch normalization, dropout, and dense layers to make the model more effective and accurate for the given problem. The training of the resulting models has been done for the Kaggle retinopathy 2019 dataset with about 3662 fundus fluorescein angiography colored images. Performance of all six trained models have been measured on the test dataset in terms of precision, recall, F1 score, macro average, weighted average, confusion matrix, and accuracy. A confusion matrix is based on maximum class probability prediction that is the incapability of the confusion matrix. The ROC-AUC of different classes and the models are analyzed. ROC-AUC is based on the actual probability of different categories. The results obtained from this study show that InceptionResNetV2 is proven the best model for diabetic retinopathy detection and classification, among other models considered here. It can work accurately in case of less training data. Thus, this model may detect and classify diabetic retinopathy automatically and accurately at an early stage. So it would be beneficial for humans to reduce the effects of diabetes. As a result of this, the impact of diabetes on vision loss can be minimized, and that would be a blessing in the medical field. Show more

Keywords: Diabetic retinopathy, nonproliferative, proliferative, maculopathy, transfer learning

DOI: 10.3233/JIFS-212771

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 985-999, 2022

Authors: Wong, Shi-Ting | Too, Chian-Wen | Yap, Wun-She | Khor, Kok-Chin

Article Type: Research Article

Abstract: With technological advancement, visual search has become an effective tool for searching important information by providing images. We propose a practical medical equipment recognition that can be used in visual search through deep transfer learning. We evaluated three deep learning models, i.e., VGG-16, ResNet-50, and Inception-v3, to recognise ten different classes of medical equipment. A data set consisting of 2,666 images had been collected and augmented to measure the models’ effectiveness. The models pre-trained with the ImageNet data set were transferred to the final models, and the last layers were replaced and trained with the collected data set. A grid …search method was then used to find the best combination of hyperparameters, such as optimiser, batch size, epoch number, dropout rate, and learning rate. We tested the models using photos captured using smartphones. The results showed that Inception-v3 outperformed the other two models with the highest accuracy of 0.9454. This is the first study that uses deep transfer learning for recognising medical equipment to our best knowledge. Such recognition technology can potentially be implemented in visual search for helping consumers to check the validity of medical equipment. Show more

Keywords: Medical equipment, object recognition, deep transfer learning

DOI: 10.3233/JIFS-212786

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1001-1010, 2022

Authors: Wei, Xiaolong | Huang, Xianglin | Yang, LiFang | Cao, Gang | Tao, Zhulin | Wang, Bing | An, Jing

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-212795

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1011-1022, 2022

Authors: Elayaraja, P. | Kumarganesh, S. | Martin Sagayam, K. | Dang, Hien | Pomplun, Marc

Article Type: Research Article

Abstract: Cervical cancer can be cured if it is initially screened and giving timely treatment to the patients. This paper proposes an optimization technique for exposing and segmenting the cancer portion in cervical images using transform and windowing technique. The image processing steps are preprocessing, transformation, feature extraction, feature optimization, classification, and segmentation involved in the proposed work. Initially, Gabor transform is enforced on the cervical test image to modify the pixels associated with the spatial domain into multi-resolution domain. Subsequently, the parameters of the multi-level features are extracted from the Gabor transformed cervical image. Then, the extracted features are optimized …using the Genetic Algorithm (GA), and the optimistic prominent part is classified by the Convolutional Neural Networks (CNN). Finally, the Finite Segmentation Algorithm (FSA) is used to detect and segment the cancer region in cervical images. The proposed GA based CNN classification method describes the effectual detection and classification of cervical cancer by the parameters such as sensitivity, specificity and accuracy. The experimental results are shown 99.37% of average sensitivity, 98.9% of average specificity and 99.21% of average accuracy, 97.8% of PPV, 91.8% of NPV, 96.8% of FPR and 90.4% of FNR. Show more

Keywords: Cervical cancer, Gabor, features, optimization, ANFIS, classification, Artificial Neural Network

DOI: 10.3233/JIFS-212871

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1023-1033, 2022

Authors: Bhatia, Tanveen Kaur | Kumar, Amit | Sharma, M.K. | Appadoo, S.S.

Article Type: Research Article

Abstract: To the best of author’s knowledge, only one approach is proposed in the literature to solve fuzzy linear fractional minimal cost flow problems (minimal cost flow problems in which each known arc cost is represented either by a triangular fuzzy number or a trapezoidal fuzzy number). In this paper, the mathematical incorrect assumptions, considered in the existing approach to solve fuzzy linear fractional minimal cost flow problems, are pointed out. Also, by generalizing an existing approach for solving fuzzy linear fractional programming problems, an approach (named as Mehar approach) is proposed to solve fuzzy linear fractional minimal cost flow problems. …Furthermore, two numerical examples are solved to illustrate the proposed Mehar approach. Show more

Keywords: Linear fractional minimal cost flow problem, triangular fuzzy numbers, trapezoidal fuzzy numbers, lexicographic approach

DOI: 10.3233/JIFS-212909

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1035-1051, 2022

Authors: Wang, Xiaohan | He, Zengyu | Wang, Pei | Zha, Xinmeng | Gong, Zimin

Article Type: Research Article

Abstract: Due to the limitation of positioning devices, there is a certain error between GPS positioning data and the real location on the map, and the positioning data needs to be processed to have better usability. For example, accurate location is needed for traffic flow control, automatic driving navigation, logistics tracking, etc. There are few studies specifically for circular road sections. In addition, many existing map matching methods based on Hidden Markov model (HMM) also have the problem that GPS points are easily to be matched to tangent or non-adjacent road sections at circular road sections. Therefore, the contextual voting map …matching method for circular road sections (STDV-matching) is proposed. The method proposes multiple subsequent point direction analysis methods based on STD-matching to determine entry into the circular section, and adds candidate section frequency voting analysis to reduce matching errors. The effectiveness of the proposed method is verified at the circular section by comparing it with three existing HMM methods through experiments using two real map and trajectory datasets. Show more

Keywords: Map matching, circular road, GPS, voting

DOI: 10.3233/JIFS-213054

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1053-1063, 2022

Authors: Lin, Yang | Ling, Yiqun | Yang, Zhe | Wang, Chunli | Li, Chuankun

Article Type: Research Article

Abstract: In the modern industrial process, a complete production process is achieved by requiring a variety of equipment to cooperate with each other. The abnormality in any equipment will have a large or small impact on process safety or product quality, resulting in increased risk. In recent years, many data-driven early-warning methods have been developed in academia. However, most of the methods need to be implemented on the support of normal and fault data. In order to overcome the problem, this paper establishes a new early-warning model based on negative selection algorithm (NSA) for centrifugal compressor unit without fault data. Firstly, …a nearest neighbor fixed boundary negative selection algorithm (NFB-NSA) is proposed by optimizing detector generation mechanism and matching rules for test samples. Secondly, the performance of NFB-NSA is tested by Iris dataset. The experimental results among NFB-NSA, V-detector, and other anomaly detection methods for Iris dataset shows that NFB-NSA can achieve the highest detection accuracy and the lowest false alarm rate in most cases. Finally, the early-warning of centrifugal compressor unit under normal samples is carried on by NFB-NSA in this paper. Validated by field data, NFB-NSA is demonstrated to be of excellent accuracy and robustness by results of experiments. Moreover, the influence of size of training sample on performance of NFB-NSA is obtained. Show more

Keywords: Early-warning, Centrifugal compressor unit, Fault data, NFB-NSA

DOI: 10.3233/JIFS-213075

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 1, pp. 1065-1075, 2022