Journal of Intelligent & Fuzzy Systems - Volume 44, issue 3

Authors: Bensoltane, Rajae | Zaki, Taher

Article Type: Research Article

Abstract: Aspect-based sentiment analysis (ABSA) is a challenging task of sentiment analysis that aims at extracting the discussed aspects and identifying the sentiment corresponding to each aspect. We can distinguish three main ABSA tasks: aspect term extraction, aspect category detection (ACD), and aspect sentiment classification. Most Arabic ABSA research has relied on rule-based or machine learning-based methods, with little attention to deep learning techniques. Moreover, most existing Arabic deep learning models are initialized using context-free word embedding models, which cannot handle polysemy. Therefore, this paper aims at overcoming the limitations mentioned above by exploiting the contextualized embeddings from pre-trained language models, …specifically the BERT model. Besides, we combine BERT with a temporal convolutional network and a bidirectional gated recurrent unit network in order to enhance the extracted semantic and contextual features. The evaluation results show that the proposed method has outperformed the baseline and other models by achieving an F1-score of 84.58% for the Arabic ACD task. Furthermore, a set of methods are examined to handle the class imbalance in the used dataset. Data augmentation based on back-translation has shown its effectiveness through enhancing the first results by an overall improvement of more than 3% in terms of F1-score. Show more

Keywords: Aspect-based sentiment analysis, aspect category detection, deep learning, BERT, data augmentation, arabic language

DOI: 10.3233/JIFS-221214

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4123-4136, 2023

Authors: Aruna, K. | Pradeep, G.

Article Type: Research Article

Abstract: Container technology is highly significant in Information and Communication Technology (ICT) systems. To maximize container effectiveness, scaling plays a significant part. Therefore, in the fog computing framework, containers are an ideal solution for hosting and scaling services. Fog networks help to increase the number of connected devices by connecting to external gateways through the Fog of Things (FoT). It is a new approach to designing and implementing fog computing systems for the IoT. The research article aims on a novel Container with a Fog-based Scalable Self-organizing Network (CFSSN) framework and use a Self-Organizing Network based Light Weight Container (SON-LWC) algorithm …for moving container services for scaling expansion. This work focuses on how to transfer service or data from container to fog and self-group network. It goes over the most recent container migration methodologies, covering both live and cold migration services. Using intelligent container improves high bandwidth efficiency and provides a solution for a scalable network. Show more

Keywords: Docker, container, ICT, CFSSN, FoT, DevOps, SON-LWC

DOI: 10.3233/JIFS-221524

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4137-4148, 2023

Authors: Weng, Ling | Lin, Jian | Lv, Shujie | Huang, Yan

Article Type: Research Article

Abstract: As the increasingly serious water pollution problem affects the sustainable development of the ecological environment, the research of water pollution treatment engineering cannot be delayed. Among them, the performance evaluation of water pollution treatment engineering is a major focus. After reading the existing studies, it is found that most of the existing performance evaluation indicators of water pollution treatment engineering have qualitative indicators and there is an unbalanced preference representation. Intuitionistic multiplicative linguistic sets can be a good representation of the qualitative preference and non-preference of decision-makers in the context of decision-making containing unbalanced phenomena. Therefore, to better solve the …problem of water pollution treatment engineering, this paper introduces intuitionistic multiplicative linguistic sets to the problem of water pollution treatment engineering and proposes an effective theory for it. First, considering the multiplicative nature of the intuitionistic multiplicative linguistic set, a new score function and accuracy function are defined, and on this basis, the priority rules of intuitionistic multiplicative linguistic set are given to prepare for the subsequent water pollution treatment engineering performance ranking. And the distance measure of intuitionistic multiplicative linguistic set is introduced and a CRITIC attribute weight determination model under intuitionistic multiplicative linguistic set is obtained on this basis. Secondly, the Choquet integral operator is applied to better represent the correlation between elements. However, the nature of membership degree and non-membership degree shows that it is not reasonable to aggregate the information of intuitionistic multiplicative linguistic sets with a single increasing and decreasing transformation. Therefore, in this paper, we propose the IMLS bi-direction exponent Choquet integral operator, which is inspired by the bi-direction Choquet integral. Lastly, we improve the original preference function of the classical PROMETHEE II method to obtain the bi-directional PROMETHEE II method in intuitionistic multiplicative linguistic information. Finally, a numerical case is also provided to illustrate the scientific and rational application of the bi-directional PROMETHEE II method in intuitionistic multiplicative linguistic information for the performance evaluation of water pollution treatment engineering. Show more

Keywords: Intuitionistic multiplicative linguistic sets, bi-direction Choquet integral, performance evaluation, water pollution treatment, PROMETHEE II method

DOI: 10.3233/JIFS-223373

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4149-4173, 2023

Authors: Rawshdeh, Amani A. | Al-jarrah, Heyam H. | Tiwari, Surabhi | Tallafha, Abdalla A.

Article Type: Research Article

Abstract: In this paper, we use the soft set theory and the concept of semi-linear uniform spaces to introduce the notion of soft semi-linear uniform spaces with its generalization, briefly soft-GSL US . We investigate some properties of soft topology that induced by soft-GSL US . Also, we use the members of soft-GSL US to define a soft proximity space and a soft filter then we establish the relationships between them. Finally, we give the perceptual application of soft semi-linear uniform structures by employing the natural transformation of a soft semi-linear uniform space to a soft proximity.

Keywords: Soft set, soft point, soft topology, soft semi-linear uniform spaces, soft proximity

DOI: 10.3233/JIFS-220587

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4175-4184, 2023

Authors: Lin, Jiaoqing | Yu, Rui | Xu, Xinrui

Article Type: Research Article

Abstract: The construction of real estate projects is a large and complex system project, and the completion of the construction goals on time and with quality is the key to the sustainable development of construction enterprises. In the process of real estate project construction, the management performance of building decoration material suppliers will directly affect the efficiency of real estate enterprises. How to correctly evaluate the building material suppliers (BMSs) of real estate enterprises and establish a good partnership affects the economic benefits of the enterprise and the possibility of subsequent cooperation between the two sides, which has become one of …the issues of importance to real estate enterprises. The selection and application of BMSs is the MAGDM. In this defined paper, the defined 2-tuple linguistic neutrosophic number (2TLNN) grey relational analysis (2TLNN-GRA) decision method is generated based on GRA and 2-tuple linguistic neutrosophic sets (2TLNSs). The 2TLNN-GRA method is generated for MAGDM. Finally, the decision example for BMSs selection is generated and some comparisons is generated. Show more

Keywords: Multiple attribute group decision making (MAGDM), 2TLNSs, GRA method, building material suppliers (BMSs)

DOI: 10.3233/JIFS-221410

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4185-4196, 2023

Authors: Du, Weidong

Article Type: Research Article

Abstract: Nowadays, the model compression method of knowledge distillation has drawn great attentions in Recommender systems (RS). The strategy of bidirectional distillation performs the bidirectional learning for both the teacher and the student models such that these two models can collaboratively improve with each other. However, this strategy cannot effectively exploit representation capabilities of each item and lack of the interpretability for the importance of items. Thus, how to develop an effective sampling scheme is still valuable for us to further study and explore. In this paper, we propose an improved rank discrepancy-aware item sampling strategy to enhance the performance of …bidirectional distillation learning. Specifically, by employing the distillation loss, we train the teacher and student models to reflect the fact that a user has partiality for the unobserved items. Then, we propose the improved rank discrepancy-aware sampling strategy based on feedback learning mechanism to transfer just the useful information which can effectively enhance each other. The key part of the multiple distillation training aims to select valuable items which can be re-distilled in the network for training. The proposed technique can effectively solve the problem of high ambiguity in nature for recommender system. Experimental results on several real-world recommender system datasets well demonstrate that the improved bidirectional distillation strategy shows better performance. Show more

Keywords: Bidirectional distillation, student-teacher learning, rank discrepancy aware items selection, recommender system

DOI: 10.3233/JIFS-222063

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4197-4206, 2023

Authors: Li, Qiyu | Langari, Reza

Article Type: Research Article

Abstract: Human-computer interaction(HCI) has broad range of applications. One particular application domain is rehabilitation devices. Several bioelectric signals can potentially be used in HCI systems in general and rehabilitation devices in particular. Surface ElectroMyoGraphic(sEMG) signal is one of the more important bioelectric signals in this context. The sEMG signal is formed by muscle activation although the details are rather complex. Applications of sEMG are referred is commonly referred to as myoelectric control since the dominant use of this signal is to activate a device even if (as the term control may imply) feedback is not always used in the process. With …the development of deep neural networks, various deep learning architectures are used for sEMG-based gesture recognition with many researchers having reported good performance. Nevertheless, challenges remain in accurately recognizing sEMG patterns generated by gestures produced by hand or the upper arm. For instance one of the difficulties in hand gesture recognition is the influence of limb positions. Several papers have shown that the accuracy of gesture classification decreases when the limb position changes even if the gesture remains the same. Prior work by our team has shown that dynamic gesture recognition is in principle more reliable in detecting human intent, which is often the underlying idea of gesture recognition. In this paper, a Convolutional Neural Network (CNN) with Long Short-Term Memory or LSTM (CNN-LSTM) is proposed to classify five common dynamic gestures. Each dynamic gesture would be performed in five different limb positions as well. The trained neural network model is then used to enable a human subject to control a 6 DoF (Degree of Freedom) robotic arm with 1 DoF gripper. The results show a high level of accurate performance achieved with the proposed approach. In particular, the overall accuracy of the dynamic gesture recognition is 84.2%. The accuracies vary across subjects but remain at approximately 90%for some subjects. Show more

Keywords: Human-computer interaction, sEMG signal, neural network, gesture recognition

DOI: 10.3233/JIFS-222985

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4207-4221, 2023

Authors: Wang, Jing

Article Type: Research Article

Abstract: The clothing images on the Internet is growing rapidly, and there is an increasing demand for the clothing images’ intelligent classification. In this paper, Region-Based Fully Convolutional Networks (R-FCN) is introduced into the clothing image recognition. In the clothing image classification, because the network training time is long and the recognition rate of deformed clothing images is low, an improved framework HSR-FCN is proposed. The regional suggestion network and HyperNet network in R-FCN are integrated in the new framework, the learning approach of image features is changed in HSR-FCN, the higher accuracy can be achieved in a shorter training time. …A spatial transformation network is introduced into the model, the input clothing image and feature map are spatially transformed and aligned, the feature learning is strengthened for multi-angle clothing and deformed clothing. The experimental results show that the improved HSR-FCN model is used to strengthen effectively the learning of deformed clothing images, and with a shorter training time, the average accuracy rate of the original network model R-FCN is increased by about 3%, it reachs 96.69%. Show more

Keywords: Garment images, deep learning, image classification, region-based fully convolutional networks (R-FCN), HyperNet, region proposal networks, spatial transformation networks

DOI: 10.3233/JIFS-220109

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4223-4232, 2023

Authors: Song, Tao

Article Type: Research Article

Abstract: The quality of physical education (PE) teaching in colleges and universities is the basis for the development of PE disciplines in colleges and universities, so currently thinking about how to effectively improve the quality of PE teaching in colleges and universities has become the first and foremost problem for many college and university PE departments to solve. In order to solve this problem, it is necessary to build a reasonable and scientific evaluation and monitoring system of PE teaching quality, because only by establishing an effective evaluation and monitoring system of teaching quality can we evaluate and supervise all the …PE operation properly and scientifically, and then give feedback in the process of evaluation and supervision, such evaluation and monitoring system can greatly promote the continuous improvement of PE teaching quality in colleges and universities. This is also one of the most effective means to improve the quality of PE and achieve the goal of PE in colleges and universities. The PE teaching quality evaluation in Colleges and Universities is frequently viewed as the multiple attribute group decision making (MAGDM) issue. In this paper, the 2-tuple linguistic neutrosophic number grey relational analysis (2TLNN-GRA) method is built based on the traditional grey relational analysis (GRA) and 2-tuple linguistic neutrosophic sets (2TLNNSs). Then, a numerical example for PE teaching quality evaluation in Colleges and Universities has been given and some comparisons is used to illustrate advantages of 2TLNN-GRA method. Show more

Keywords: Multiple attribute group decision making (MAGDM) problems, 2-tuple linguistic neutrosophic sets (2TLNSs), GRA method, teaching quality evaluation

DOI: 10.3233/JIFS-221857

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4233-4244, 2023

Authors: Reji, M. | Joseph, Christeena | Nancy, P. | Lourdes Mary, A.

Article Type: Research Article

Abstract: Intrusion detection systems (IDS) can be used to detect irregularities in network traffic to improve network security and protect data and systems. From 2.4 times in 2018 to three times in 2023, the number of devices linked to IP networks is predicted to outnumber the total population of the world. In 2020, approximately 1.5 billion cyber-attacks on Internet of Things (IoT) devices have been reported. Classification of these attacks in the IoT network is the major objective of this research. This research proposes a hybrid machine learning model using Seagull Optimization Algorithm (SOA) and Extreme Learning Machine (ELM) classifier to …classify and detect attacks in IoT networks. The CIC-IDS-2018 dataset is used in this work to evaluate the proposed model. The SOA is implemented for feature selection from the dataset, and the ELM is used to classify attacks from the selected features. The dataset has 80 features, in the proposed model used only 22 features with higher scores than the original dataset. The dataset is divided into 80% for training and 20% for testing. The proposed SOA-ELM model obtained 94.22% accuracy, 92.95% precision, 93.45% detection rate, and 91.26% f1-score. Show more

Keywords: Intrusion detection, IoT, SOA, ELM, feature selection, attack classification, machine learning

DOI: 10.3233/JIFS-222427

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4245-4255, 2023