Journal of Intelligent & Fuzzy Systems - Volume Pre-press, issue Pre-press

Authors: Al Tahan, Madeline | Hoskova-Mayerova, Sarka | Davvaz, Bijan

Article Type: Research Article

Abstract: In recent years, fuzzy multisets have become a subject of great interest for researchers and have been widely applied to algebraic structures including groups, rings, and many other algebraic structures. In this paper, we introduce the algebraic structure of fuzzy multisets as fuzzy multi-subnear rings (multi-ideals) of near rings. In this regard, we define different operations on fuzzy multi-ideals of near rings and we generalize some results known for fuzzy ideals of near rings to fuzzy multi-ideals of near rings.

Keywords: Near ring, multiset, fuzzy multiset, fuzzy multi-ideal, fuzzy multi-subnear ring

DOI: 10.3233/JIFS-202914

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2021

Authors: Lu, Zhen-Yu | Wang, Xiao-Kang | Wang, Jian-Qiang | Cheng, Peng-Fei | Li, Lin

Article Type: Research Article

Abstract: The wireless propagation model is important for accurate 5 G network deployment. However, the traditional wireless propagation model is faced with the problems of limited application scenarios, unstable prediction results and high marginal cost of improving accuracy. In order to solve these problems, this paper constructs new features from the original data from different angles, and uses the random forest model to select the core features, which are used to train the fusion model based on the linear weighted summation of regression models such as KNN, LightGBM, and Bagging. After training, the final fusion model is obtained, it solves the …problems faced by traditional wireless propagation models. The results and analysis show that the fusion model outperforms the traditional wireless propagation models and the single models that constitutes the fusion model in terms of prediction accuracy and stability, and is not limited by scenarios and easy to deploy. Show more

Keywords: 5 G, wireless propagation model, feature engineering, fusion model

DOI: 10.3233/JIFS-202388

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2021

Authors: Talafha, Mohammad | Alkouri, Abd Ulazeez | Alqaraleh, Sahar | Zureigat, Hamzeh | Aljarrah, Anas

Article Type: Research Article

Abstract: Decision-makers (DMs) usually face many obstacles to give the right decision, multiplicity of them highlights a problem to represent a set of potential values to assign a collective membership degree of an object to a set for several DM’s opinions. However, a hesitant fuzzy set (HFS) deals with such problems. The complexity appears in DM’s opinion which can be changed for the same object but with different times/phases. Each of them has a set of potential values in different times/phases of an object. In this paper, the periodicity of hesitant fuzzy information is studied and applied by extending the range …of HFS from [0, 1] to the unit disk in the complex plane to provide more ability for illustrating the full meaning of information to overcome the obstacles in decision making in the mathematical model. Moreover, the advantage of CHFS is that the amplitude and phase terms of CHFSs can represent hesitant fuzzy information, some basic operations on CHFS are also presented and we study its properties, in addition, several aggregation operators under CHFS are introduced, also, the relation between CHFS and complex intuitionistic fuzzy sets (CIFS) are presented. Finally, an efficient algorithm with a consistent process and an application in multiple attributes decision-making (MADM) problems are presented to show the effectiveness of the presented approach by using CHFS aggregation operators. Show more

Keywords: Hesitant fuzzy set, complex fuzzy sets, complex intuitionistic fuzzy sets, complex hesitant fuzzy sets, CIF aggregation operators, CHF aggregation operators

DOI: 10.3233/JIFS-211156

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-29, 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. Pre-press, no. Pre-press, pp. 1-10, 2021

Authors: Zhang, Nian | Pan, Qian | Wei, Guiwu

Article Type: Research Article

Abstract: In order to effectively solve the decision-making problems with the diversity of evaluation information, the dynamics of research objects, the limitations of subjective authorization, and the irrational behavior of decision-makers, this paper extends catastrophe progression method to solve hybrid multiple attribute decision-making problems based on regret theory. Firstly, some basic theories are introduced. Secondly, the original catastrophe progression method is extended by using the regret theory, which is employed to solve the multiple attribute decision-making problems with hybrid evaluation information. Finally, a real-life case study of selecting a fresh cold chain logistics service provider is used to verify the practicality …and effectiveness of the proposed method, and a comparative analysis with the TOPSIS method and the sensitivity of the regret avoidance coefficient is analyzed in this article. Show more

Keywords: Regret theory, catastrophe progression, hybrid multi-attribute decision-making

DOI: 10.3233/JIFS-210515

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-14, 2021

Authors: Zhou, Lexin | Yang, Wenzhong | Wang, Ting | Wu, Yongzhi

Article Type: Research Article

Abstract: Aspect-based sentiment analysis (ABSA) contains three subtasks, namely aspect term extraction, opinion term extraction and aspect-level sentiment classification. In order to make full use of the relationship between the three subtasks, some recent studies have successfully tried to use a unified framework to solve the problem of aspect-based sentiment analysis. However, these studies have not yet integrated domain knowledge into the model. Inspired by the post-training task, we propose a joint model (RACL-BERT-PT). This model combines the pre-training model BERT-PT with domain knowledge and the unified joint training framework RACL. The experimental results show that our model has achieved better …results than previous experiments on three public data. Show more

Keywords: Aspect-based sentiment analysis, post-training, domain knowledge

DOI: 10.3233/JIFS-210632

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2021

Authors: Priyadarshi, Ankur | Saha, Sujan Kumar

Article Type: Research Article

Abstract: In this paper, we present our effort on the development of a Maithili Named Entity Recognition (NER) system. Maithili is one of the official languages of India, with around 50 million native speakers. Although various NER systems have been developed in several Indian languages, we did not find any openly available NER resource or system in Maithili. For the development, we manually annotated a Maithili NER corpus containing around 200K words. We prepared a baseline classifier using Conditional Random Fields (CRF). Then we ran many experiments using various recurrent neural networks (RNN). We collected larger raw corpus to obtain better …word embedding and character embedding. In our experiments, we found, neural models are better than CRF; a CRF layer is effective for the prediction of the final output in the RNN models; character embedding is effective in Maithili language. We also investigated the effectiveness of gazetteer lists in neural models. We prepared a few gazetteer lists from various web resources and used those in the neural models. The incorporation of the gazetteer layer caused performance improvement. The final system achieved an f-measure of 91.6% with 94.9% precision and 88.53% recall. Show more

Keywords: Named entity recognition, Maithili language, corpus annotation, LSTM model, gazetteer lists

DOI: 10.3233/JIFS-210051

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2021

Authors: Zhou, Weibin | Chen, Tao | Huang, Huafang | Sheng, Chang | Wang, Yangfeng | Wang, Yang | Zhang, Daqiang

Article Type: Research Article

Abstract: Iris segmentation is one of the most important steps in iris recognition. The current iris segmentation network is based on convolutional neural network (CNN). Among these methods, there are still problems with the segmentation networks such as high complexity, insufficient accuracy, etc. To solve these problems, an improved low complexity DenseUnet is proposed to this paper based on U-net for acquiring a high-accuracy iris segmentation network. In this network, the improvements are as follows: (1) Design a dense block module that contains five convolutional layers and all convolutions are dilated convolutions aimed at enhancing feature extraction; (2) Except for the …last convolutional layer, all convolutional layers output feature maps are set to the number 64, and this operation is to reduce the amounts of parameters without affecting the segmentation accuracy; (3) The solution proposed to this paper has low complexity and provides the possibility for the deployment of portable mobile devices. DenseUnet is used on the dataset of IITD, CASIA V4.0 and UBIRIS V2.0 during the experimental stage. The results of the experiments have shown that the iris segmentation network proposed in this paper has a better performance than existing algorithms. Show more

Keywords: Iris segmentation, iris recognition, CNN, U-net, low complexity

DOI: 10.3233/JIFS-211396

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-17, 2021

Authors: Chang, Jingfei | Lu, Yang | Xue, Ping | Wei, Xing | Wei, Zhen

Article Type: Research Article

Abstract: Deep convolutional neural network (CNN) is difficult to deploy to mobile and portable devices due to its large number of parameters and floating-point operations (FLOPs). To tackle this problem, we propose a novel channel pruning method. We use the modified squeeze-and-excitation blocks (MSEB) to measure the importance of the channels in the convolutional layers. The unimportant channels, including convolutional kernels related to them, are pruned directly, which greatly reduces the storage cost and the number of calculations. For ResNet with basic blocks, we propose an approach to consistently prune all residual blocks in the same stage to ensure that the …compact network structure is dimensionally correct. After pruning we retrain the compact network from scratch to restore the accuracy. Finally, we verify our method on CIFAR-10, CIFAR-100 and ILSVRC-2012. The results indicate that the performance of the compact network is better than the original network when the pruning rate is small. Even when the pruning amplitude is large, the accuracy can also be maintained or decreased slightly. On the CIFAR-100, when reducing the parameters and FLOPs up to 82% and 62% respectively, the accuracy of VGG-19 even improve by 0.54% after retraining. The source code is available at https://github.com/JingfeiChang/UCP . Show more

Keywords: Deep learning, convolutional neural network, network pruning, image classification

DOI: 10.3233/JIFS-202290

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-13, 2021

Authors: Kaliraman, Bhawna | Duhan, Manoj

Article Type: Research Article

Abstract: Electroencephalogram (EEG) signals are essential in brain-computer interface systems. Nowadays, these signals are employed in various medical applications. In the past few years, EEG signals gain more attention in security systems to identify users, as these signals are unique for each individual. The current study explores deep learning frameworks for EEG-based user identification. Data from 107 users were considered for the study, which is acquired using 64 channels. Several experimental tests are performed over both convolutional neural network (CNN) and recurrent neural networks (RNN) using a 10-fold cross-validation process to check system effectiveness. In CNN, 1-D Convolutional layer is employed …for the processing of EEG signals. In RNN, LSTM and GRU are used to check system accuracy. For performance measure various metrices were considered such as accuracy, precision, recall and kappa score. Acquired results suggest that gated recurrent unit (GRU) outperforms other models in terms of accuracy and complexity both. GRU model has 91.2% accuracy and has three layers only, which reduces the model’s complexity. The training cost is also decreasing due to the low complexity of the model. Show more

Keywords: Convolutional neural network (CNN), recurrent neural network (RNN), long short-term memory (LSTM), feed forward neural networks (FFNN), rectified linear units (ReLU), gated recurrent unit (GRU)

DOI: 10.3233/JIFS-202490

Citation: Journal of Intelligent & Fuzzy Systems, vol. Pre-press, no. Pre-press, pp. 1-11, 2021