Journal of Intelligent & Fuzzy Systems - Volume 41, issue 1

Authors: Van Nguyen, Kiet | Duy Nguyen, Nhat | Do, Phong Nguyen-Thuan | Gia-Tuan Nguyen, Anh | Nguyen, Ngan Luu-Thuy

Article Type: Research Article

Abstract: Machine Reading Comprehension has attracted significant interest in research on natural language understanding, and large-scale datasets and neural network-based methods have been developed for this task. However, most developments of resources and methods in machine reading comprehension have been investigated using two resource-rich languages, English and Chinese. This article proposes a system called ViReader for open-domain machine reading comprehension in Vietnamese by using Wikipedia as the textual knowledge source, where the answer to any particular question is a textual span derived directly from texts on Vietnamese Wikipedia. Our system combines a sentence retriever component, based on techniques of information retrieval …to extract the relevant sentences, with a transfer learning-based answer extractor trained to predict answers based on Wikipedia texts. Experiments on multiple datasets for machine reading comprehension in Vietnamese and other languages demonstrate that (1) our ViReader system is highly competitive with prevalent machine learning-based systems, and (2) multi-task learning by using a combination consisting of the sentence retriever and answer extractor is an end-to-end reading comprehension system. The sentence retriever component of our proposed system retrieves the sentences that are most likely to provide the answer response to the given question. The transfer learning-based answer extractor then reads the document from which the sentences have been retrieved, predicts the answer, and returns it to the user. The ViReader system achieves new state-of-the-art performances, with values of 70.83 % EM (exact match) and 89.54 % F1, outperforming the BERT-based system by 11.55% and 9.54% , respectively. It also obtains state-of-the-art performance on UIT-ViNewsQA (another Vietnamese dataset consisting of online health-domain news) and BiPaR (a bilingual dataset on English and Chinese novel texts). Compared with the BERT-based system, our system achieves significant improvements (in terms of F1) with 7.65% for English and 6.13% for Chinese on the BiPaR dataset. Furthermore, we build a ViReader application programming interface that programmers can employ in Artificial Intelligence applications. Show more

Keywords: Machine reading comprehension, question answering, transfer learning, sentence transformer

DOI: 10.3233/JIFS-210683

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 1993-2011, 2021

Authors: Kumar, Mukul | Katyal, Nipun | Ruban, Nersisson | Lyakso, Elena | Mary Mekala, A. | Joseph Raj, Alex Noel | Maarc Richard, G.

Article Type: Research Article

Abstract: Over the years the need for differentiating various emotions from oral communication plays an important role in emotion based studies. There have been different algorithms to classify the kinds of emotion. Although there is no measure of fidelity of the emotion under consideration, which is primarily due to the reason that most of the readily available datasets that are annotated are produced by actors and not generated in real-world scenarios. Therefore, the predicted emotion lacks an important aspect called authenticity, which is whether an emotion is actual or stimulated. In this research work, we have developed a transfer learning and …style transfer based hybrid convolutional neural network algorithm to classify the emotion as well as the fidelity of the emotion. The model is trained on features extracted from a dataset that contains stimulated as well as actual utterances. We have compared the developed algorithm with conventional machine learning and deep learning techniques by few metrics like accuracy, Precision, Recall and F1 score. The developed model performs much better than the conventional machine learning and deep learning models. The research aims to dive deeper into human emotion and make a model that understands it like humans do with precision, recall, F1 score values of 0.994, 0.996, 0.995 for speech authenticity and 0.992, 0.989, 0.99 for speech emotion classification respectively. Show more

Keywords: Deep learning, speech fidelity classification, linear prediction cepstral coefficients (LPCC), mel frequency cepstral coefficients (MFCC), speech emotion recognition

DOI: 10.3233/JIFS-210711

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2013-2024, 2021

Authors: Gul, Rizwan | Shabir, Muhammad

Article Type: Research Article

Abstract: Pawlak’s rough set theory based on single granulation has been extended to multi-granulation rough set structure in recent years. Multi-granulation rough set theory has become a flouring research direction in rough set theory. In this paper, we propose the notion of (α , β )-multi-granulation bipolar fuzzified rough set ((α , β )-MGBFRSs). For this purpose, a collection of bipolar fuzzy tolerance relations has been used. In the framework of multi-granulation, we proposed two types of (α , β )-multi-granulation bipolar fuzzified rough sets model. One is called the optimistic (α , β )-multi-granulation bipolar fuzzified rough sets ((α , …β ) o -MGBFRSs) and the other is called the pessimistic (α , β )-multi-granulation bipolar fuzzified rough sets ((α , β ) p -MGBFRSs). Subsequently, a number of important structural properties and results of proposed models are investigated in detail. The relationships among the (α , β )-MGBFRSs, (α , β ) o -MGBFRSs and (α , β ) p -MGBFRSs are also established. In order to illustrate our proposed models, some examples are considered, which are helpful for applying this theory in practical issues. Moreover, several important measures associated with (α , β )-multi-granulation bipolar fuzzified rough set like the measure of accuracy , the measure of precision , and accuracy of approximation are presented. Finally, we construct a new approach to multi-criteria group decision-making method based on (α , β )-MGBFRSs, and the validity of this technique is illustrated by a practical application. Compared with the existing results, we also expound its advantages. Show more

Keywords: Rough set, multi-granulation rough approximations, bipolar fuzzy tolerance relation, (α, β)-bipolar fuzzified rough set, (α, β)-multi-granulation bipolar fuzzified rough sets, decision making method

DOI: 10.3233/JIFS-210717

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2025-2060, 2021

Authors: Sakthidasan Sankaran, K. | Gao, Xiao-Zhi

Article Type: Research Article

Abstract: Nowadays, numerous algorithms on power allocation have been proposed for maximizing the EE (Energy efficiency) and SE (Spectral efficiency) in the Distributed Antenna System (DAS). Moreover, the conservative techniques employed for power allocation seem to be problematic, due to their high computational complexity. The main objective of this paper focuses on optimizing the power allocation in order to enhance the EE and SE along with the improved antenna capacity using an effective optimization approach with the clustering model. To obtain the optimized power allocation and antenna capacity, Multi-scale resource Grasshopper Optimization Algorithm (Multi-scale resource GOA) scheme is proposed and employed. …Furthermore, clustering is developed based on the Discriminative cluster-based Expectation maximization (DC-EM) clustering algorithms, which also helps to reduce the interference rate and computational complexity. The performance analysis is made under various scenarios and circumstances. The proposed system (DAS with GOA-EM) is assessed and compared with the existing approaches in terms of both the EE and SE, which demonstrates that its superiority. Show more

Keywords: Distributed Antenna system, power allocation, energy efficiency, spectral efficiency, optimization algorithms

DOI: 10.3233/JIFS-210727

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2061-2072, 2021

Authors: Islam, Sk Rabiul | Pal, Madhumangal

Article Type: Research Article

Abstract: Topological indices have an important role in molecular chemistry, network theory, spectral graph theory and several physical worlds. Most of the topological indices are defined in a crisp graph. As fuzzy graphs are more generalization of crisp graphs, those indices have more application in fuzzy graphs also. In this article, we introduced the fuzzy hyper-Wiener index (FHWI) and studied this index for various fuzzy graphs like path, cycle, star, etc and provided some interesting bounds of FHWI for that fuzzy graph. A lower bound of FHWI is established for n -vertex connected fuzzy graph depending on strength of a strong …edges. A relation between FHWI of a tree and its maximum spanning tree is established and this index is calculated for the saturated cycle. Also, at the end of the article, an application in the share market of this index is presented. Show more

Keywords: Fuzzy graph, wiener index, hyper-wiener index, fuzzy hyper-wiener index

DOI: 10.3233/JIFS-210736

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2073-2083, 2021

Authors: Qureshi, Shahana Gajala | Shandilya, Shishir Kumar

Article Type: Research Article

Abstract: WSN (Wireless Sensor Network) is a network of devices which can transfer the data collected from an examined field via wireless links. Thus secure data transmission is required for accurate transfer of data from source to destination as data passes through various intermediate nodes. The study intends to perform shortest, secure path routing on the basis of trust through novel Hybridized Crow Whale Optimization (H-CWO) and QoS based bipartite Coverage Routing (QOS-CR) as well as to analyze the system’s performance. Nodes are randomly deployed in the network area. Initially, a trust metric formation is implemented via novel H-CWO and the …authenticated nodes are selected. Then through the secure routing protocol, Cluster head (CH) is selected to perform clustering. Neighbourhood hop prediction is executed to determine the shortest path routing and secure data transfer is performed through novel QOS-CR. The proposed system is analyzed by comparing it with various existing methods in terms of delay, throughput, energy and alive nodes. The results attained from comparative analysis revealed the efficiency of the proposed system. The proposed novel H-CWO and QOS-CR exhibited minimum delay, high throughput, energy and maximum alive nodes thereby ensuring safe transmission of data from source node to destination node. Show more

Keywords: Wireless sensor networks, trust metric, secured routing, hybrid crow whale optimization and QOS based bipartite coverage routing

DOI: 10.3233/JIFS-210766

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2085-2099, 2021

Authors: Cao, Mengxue | Lu, Laijun | Zhong, Yu

Article Type: Research Article

Abstract: How to more effectively perform anomaly detection of combination information has always been an important issue for the scholars in various fields. In order to identify and extract the geochemical anomaly information related to polymetallic mineralization in the Hunjiang area, this article uses the hybrid method that combines multivariate canonical harmonic trend analysis (MCHTA), singularity analysis with radius-areal metal amount and improved adaptive fuzzy self-organizing map (IAFSOM). First, multiple sets of combination feature information with multi-dimensional variables will be obtained through the MCHTA method, which information is considered as the initial information for the subsequent analysis. Next, the singularity analysis …method is used to process the combination concentration value to calculate the singularity indexes. Finally, the singularity indexes are classified by the IAFSOM method, and nine groups of sample data are obtained. The analysis results found that the samples information in fourth group covered most of the low α -values. The main conclusions in this study are as follows: (1) The MCHTA method can effectively detect the combination information related to geochemical anomaly; (2) The application of singularity analysis method with radius-areal metal amount can reveal the significant characteristics of mineralization combination elements; (3) IAFSOM can be used as an effective tool for the classification and identification of geochemical anomaly with combination information; (4) the hybrid method that combines MCHTA method, singularity analysis and IAFSOM model has a good indication significance in the prospecting of geochemical anomalies, and could provide a good method for geochemical prospecting. Show more

Keywords: Key words: Multivariate canonical harmonic trend analysis (MCHTA), singularity analysis with radius-areal metal amount, improved adaptive fuzzy self-organizing mapping (IAFSOM), iron polymetallic mineralization, Hunjiang district

DOI: 10.3233/JIFS-210786

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2101-2110, 2021

Authors: Song, Juan | Ni, Zhiwei | Jin, Feifei | Wu, Wenying | Li, Ping

Article Type: Research Article

Abstract: Probabilistic dual hesitant fuzzy sets (PDHFSs) have good flexibility and integrity in expressing fuzzy and uncertain information. However, some crucial problems related to PDHFSs remain unsolved, such as how to define probabilistic dual hesitant fuzzy preference relations (PDHFPRs) and solve group decision-making (GDM) problems with PDHFPRs. This paper establishes the concept of PDHFPRs and investigates consensus-based GDM methods with PDHFPRs. First, a new distance measure is proposed to quantify the difference between two PDHFPRs, which does not increase the virtual elements of membership and non-membership degrees, and can contain all distance combination of membership and non-membership elements. Therefore, the distance …calculation results are not affected by the subjectivity of decision-makers (DMs). Second, the consensus measures for PDHFPRs are proposed, which are effective tool to measure the consensus level among DMs. Moreover, two consensus-based GDM methods are proposed, which can improve the group consensus level for PDHFPRs by changing the PDHFPR with the worst consensus level or modifying the weights of DMs. Finally, the proposed methods are applied to the location selection of large-scale industrial solid waste treatment facilities. The comparison with existing methods illustrates the validity and feasibility of the proposed methods. Show more

Keywords: Group decision-making, probabilistic dual hesitant fuzzy preference relations, distance measure, consensus

DOI: 10.3233/JIFS-210796

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2111-2128, 2021

Authors: Zhang, Xiangxiang | Chang, Liu | Luo, Jingwen | Wu, Jia

Article Type: Research Article

Abstract: With the rise of the Internet of Things, the opportunistic network of portable smart devices has become a new hot spot in academic research in recent years. The mobility of nodes in opportunistic networks makes the communication links between nodes unstable, so data forwarding is an important research content in opportunistic networks. However, the traditional opportunistic network algorithm only considers the transmission of information and does not consider the social relationship between people, resulting in a low transmission rate and high network overhead. Therefore, this paper proposes an efficient data transmission model based on community clustering. According to the user’s …social relationship and the release location of the points of interest, the nodes with a high degree of interest relevance are divided into the same community. Weaken the concept of a central point in the community, and users can share information to solve the problem of excessive load on some nodes in the network and sizeable end-to-end delay. Show more

Keywords: Opportunistic social networks, community clustering, interest point, community reconstruction, data transmission, IoT system

DOI: 10.3233/JIFS-210807

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2129-2144, 2021

Authors: Zhao, Peng | Han, Baoming | Li, Dewei | Li, Yawei

Article Type: Research Article

Abstract: As a key operation for the daily maintenance of electric multiple units (EMU), the first-level maintenance operation directly affects the utilization efficiency of the EMU. The fixed operation sequence of EMU trains, the limitation of the track capacity and inconsistent arrival time of EMU trains give rise to such problems as extended waiting time, idle tracks and waste of maintenance capacity. To solve these problems and optimize the assignment of EMU-to-track, we propose a flexible job-shop sequence scheduling (Flexible-JSS) mode for the first-level maintenance of EMU trains, and a flexible sequence and tracks sharing (FSTS) model for the first-level maintenance …at electric multiple units depot (EMUD) has also been proposed in this paper. The FSTS model is designed to shorten the latest completion time after taking into account the constraints such as the train length, track capacity, the operation sequence of all EMU trains, the operation process of a single EMU train, and the train-set scheduling plan. A modified genetic algorithm is used to solve the model. The feasibility and effectiveness of the model and algorithm are verified by a real case, and the comparison with the other two fixed job-shop sequence scheduling (Fixed-JSS) modes proves that the Flexible-JSS mode can improve the efficiency and ability of the first-level maintenance at EMUD impressively. Show more

Keywords: First-level maintenance operation, flexible job-shop sequence scheduling mode, flexible sequence and tracks sharing (FSTS) model, modified genetic algorithm, the latest completion time

DOI: 10.3233/JIFS-210823

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 1, pp. 2145-2160, 2021