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

Authors: Zhao, Dazhi | Hao, Yunquan | Li, Weibin | Tu, Zhe

Article Type: Research Article

Abstract:  Whether the exact amount of training data is enough for a specific task is an important question in machine learning, since it is always very expensive to label many data while insufficient data lead to underfitting. In this paper, the topic that what is the least amount of training data for a model is discussed from the perspective of sampling theorem. If the target function of supervised learning is taken as a multi-dimensional signal and the labeled data as samples, the training process can be regarded as the process of signal recovery. The main result is that the least amount …of training data for a bandlimited task signal corresponds to a sampling rate which is larger than the Nyquist rate. Some numerical experiments are carried out to show the comparison between the learning process and the signal recovery, which demonstrates our result. Based on the equivalence between supervised learning and signal recovery, some spectral methods can be used to reveal underlying mechanisms of various supervised learning models, especially those “black-box” neural networks. Show more

Keywords: Machine learning, sampling theorem, frequency principle, signal recovery, neural network, Gaussian process regression

DOI: 10.3233/JIFS-211024

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4891-4906, 2023

Authors: Sathishkumar, B.R.

Article Type: Research Article

Abstract: Power dissipation at the network level to improve lifespan without degrading the bandwidth and collaboration is a fundamental impediment to effective spectral efficiency in wireless sensor networks (WSNs). This issue is made much more difficult. Wireless energy transfer (WET) for energizing remote sensor nodes gained interest. This research explores an FDD-based on-demand scenario with many relays where a transmitter is powered by direct and relayed links. A threshold is set for transmission energy & channel quality to decide whether the broadcasting can be efficient (for spectrum utilization) or the packet would not arrive at its destination. The network model offers …an energy-efficient scheduling strategy to decide whether to transmit information or not depending on the stored higher energy and network status. An energy-aware polling-based medium access control (MAC) mechanism, composite energy, and information first (CEDF) has also been developed to fine-tune packet delivery ratio by utilizing datagrams and energy packages to set polling prioritization. Computational simulations indicate that energy relayed and the recommended energy-efficient scheduled technique decrease the system’s active power losses supporting all theoretical predictions. Show more

Keywords: Polling, multi-relay, spectral efficiency, sensor network, MAC, data speed and power constraints

DOI: 10.3233/JIFS-223001

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4907-4930, 2023

Authors: Sharma, Preeti | Gangadharappa, M.

Article Type: Research Article

Abstract: Anomalous event recognition has a complicated definition in the complex background due to the sparse occurrence of anomalies. In this paper, we form a framework for classifying multiple anomalies present in video frames that happen in a context such as the sudden moment of people in various directions and anomalous vehicles in the pedestrian park. An attention U-net model on video frames is utilized to create a binary segmented anomalous image that classifies each anomalous object in the video. White pixels indicate the anomaly, and black pixels serve as the background image. For better segmentation, we have assigned a border …to every anomalous object in a binary image. Further to distinguish each anomaly a watershed algorithm is utilized that develops multi-level gray image masks for every anomalous class. This forms a multi-class problem, where each anomalous instance is represented by a different gray color level. We use pixel values, Optical Intensity, entropy values, and Gaussian filter with sigma 5, and 7 to form a feature extraction module for training video images along with their multi-instance gray-level masks. Pixel-level localization and identification of unusual items are done using the feature vectors acquired from the feature extraction module and multi-class stack classifier model. The proposed methodology is evaluated on UCSD Ped1, Ped2 and UMN datasets that obtain pixel-level average accuracy results of 81.15%,87.26% and 82.67% respectively. Show more

Keywords: Anomaly detection, video surveillance, feature extraction, multi-class classification, classifier

DOI: 10.3233/JIFS-221925

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4931-4947, 2023

Authors: Zheng, Tingting | Chen, Hao | Yang, Xiyang

Article Type: Research Article

Abstract: The traditional Ordered Weighting Average (OWA) operator is suitable for aggregating numerical attributes. However, this method fails when the attribute values are given in a linguistic form. In this paper, a novel aggregating method named Entropy and Probability based Fuzzy Induced Ordered Weighted Averaging (EPFIOWA) is proposed for Gaussian-fuzzy-number-based linguistic attributes. A method is first designed to obtain a reasonable weighting vector based on probability distribution and maximal entropy. Such optimal weighting vectors can be obtained under any given level of optimism, and the symmetric properties of the proposed model are proven. The linguistic attributes of EPFIOWA are represented by …Gaussian fuzzy numbers because of their concise form and good operational properties. In particular, the arithmetic operations and distance measures of Gaussian fuzzy numbers required by EPFIOWA are given systematically. A novel method to obtain the order-inducing variables of linguistic attribute values is proposed in the EPFIOWA operators by calculating the distances between any Gaussian fuzzy number and a set of ordered grades. Finally, two numerical examples are used to illustrate the proposed approach, with evaluation results consistent with the observed situation. Show more

Keywords: Gaussian fuzzy numbers, induced ordered weighted averaging operators, order-inducing variables, probability distribution, maximal entropy

DOI: 10.3233/JIFS-222241

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4949-4962, 2023

Authors: Abdulrahim, Basiya K. | Sulaiman, Nejmaddin A. | Sadiq, Gulnar W.

Article Type: Research Article

Abstract: This paper presents an efficient and straightforward methodology with less computational complexities to title the bi-level objective linear fractional programming problem with fuzzy interval coefficients (BILOLFPP with FIC). To construct the methodology, the concept of mean technique is utilized to tackle the fuzzy numbers in addition to adding to α = [mean  (a i ) , mean  (b i )] , i  = 1, …, n , then. Accordingly, the fuzzy programming issue is converted into a single objective linear fractional programming problem (SOLFPP with FIC) by the utilize of weight function. The fuzzy technique has significant structural transform metamorphosis during the …recent decades. Numerous to mention introduced have been undertaken to explanation fuzzy methodology for linear, non-linear programming issues. While, the previous finding that introduced have been conflicting, recent studies of competitive situations indicate that LFPP with fuzzy interval coefficients (LFPP with FIC) has an advantageous effect mostly on comparison situation. One of the suggestions which we found is interval approximations, closed interval approximation of sequential fuzzy number for resolving fuzzy number LFPP without changing it to a crisp issue. A new variant of modified simplex methodology is studied here just for resolving fuzzy number LFPP utilizing fuzzy arithmetic. Consequently, fuzzy representation of some important theories of fuzzy LFPP has been reproved. A fuzzy LFPP with FIC is worked out as numerical examples illustrate to the suggested methodology. On iterative processes, it decreases the overall processing time to explain, the modified simplex methodology for solving BILLFPP with FIC with out to crisp by taking numerical examples and compare with Nasseri, Verdegay and Mahmoudi methodology changing it to a crisp issue [9 ]. Show more

Keywords: Fuzzy number, FFLFPP, FFLFPP with fuzzy interval coefficients, FFBILLFPP with fuzzy interval coefficients, closed interval approximation, modified simplex methodology

DOI: 10.3233/JIFS-222519

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4963-4973, 2023

Authors: Nasr, Asmaa M. | ElGhawalby, Hewayda | Mareay, R.

Article Type: Research Article

Abstract: In several empirical situations, a decision is needed to be made based on data that is captured in some information system. The problem occurs when the information system holds complex data or even too much data attributes. This leads to the need for reducing the number of attributes required to obtain a decision. In this paper, a novel attributes’ reduction method is presented; the proposed method is based on constructing a weighted pre-topology that represents the information system under consideration. In addition, some essential operations for the weighted pre-topological space are presented; as well as, a brief study of their …properties. Show more

Keywords: Fuzzy pretopological space, closure set, interior set, information system

DOI: 10.3233/JIFS-223077

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4975-4985, 2023

Authors: Chen, Chuen-Jyh | Huang, Chieh-Ni | Yang, Shih-Ming

Article Type: Research Article

Abstract: Weather forecasts are essential to aviation safety. Unreliable forecasts not only cause problems to pilots and air traffic controllers, but also lead to aviation accidents and incidents. This study develops a long short-term memory (LSTM) integrating both multiple linear regression and the Pearson’s correlation coefficients to improve forecasting. A numerical dataset of 10 weather features (sea pressure, temperature, dew point temperature, relative humidity, wind speed, wind direction, sunshine rate, global solar radiation, visible mean, and cloud amount) is applied on every calendar day in a year to train and validate the LSTM for temperature forecasting. It is shown that data …standardization is necessary to rescale the data to improve training convergence and reduce training time. In addition, feature selection by multiple linear regression and by Pearson’s correlation coefficients are shown effective to the forecast accuracy of the LSTM. By selecting only the sensitive features (sea pressure, dew point temperature, relative humidity and relative humidity), the temperature forecasting errors can be reduced from RMSE 4.0274 to 2.2215 and MAPE 23.0538% to 5.0069%. LSTM deep learning with data standardization and feature selection is effective in forecasting for aviation safety. Show more

Keywords: Deep learning, aviation weather, long short-term memory, weather forecasting

DOI: 10.3233/JIFS-223183

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4987-4997, 2023

Authors: Chen, Xinzhang | Tian, Xiaoyan | Ye, Hongtu

Article Type: Research Article

Abstract: As the most popular art category in the contemporary art field, visual art is no longer limited to traditional art categories such as painting, sculpture and photography, but develops into more diverse forms of expression with the continuous iteration of science and technology. As the most cutting-edge and popular concept in the world today, the research, development and application of science and technology have attracted close attention from all walks of life, including management, economy, transportation, education and teaching. However, there is no in-depth and clear research between the concept of metaverse and the concept of metaverse in the art …field, especially in the visual art field. We believe that visual art creation under the background of the metaverse will be an important direction of art development in the future, and will also greatly promote the improvement of the visual presentation quality of the metaverse. Therefore, we focus our research in this study on the issue of visual art quality assessment and propose a theory and method for assessing the quality of visual art in a future-oriented metaverse. This method is based on the G1 entropy method in fuzzy mathematics. In our research, we have built a visual art field architecture based on the metaverse. Considering the difference between the traditional visual art evaluation index system and the index system after the introduction of the concept of the future metaverse, we have built a brand-new visual art quality evaluation index system facing the future metaverse. This indicator is composed of four first-class indicators and twelve second-class indicators. We combine the subjective and objective weighting G1 entropy method as the method basis for the quantitative calculation results of the indicator weight. On the basis of quantitative analysis, we propose three-point countermeasures for improving the visual art quality of the future metaverse. Our research makes up for the gap in the theory of visual art quality evaluation after the introduction of the concept of the future metaverse, innovates the analysis of new concepts and the improvement of old methods, builds a new scene of organic combination of new technology and traditional visual art, and provides a new idea for the improvement of visual art quality in the future at home and abroad, It can also provide experience and theoretical support for the academic topic of similar art quality evaluation research at home and abroad. Show more

Keywords: Visual arts, metaverse, field architecture, G1-entropy method, AHP method

DOI: 10.3233/JIFS-223351

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4999-5019, 2023

Authors: Yang, Run

Article Type: Research Article

Abstract: In the past, different useful extensions of fuzzy sets were established by the researchers to manage the vagueness and uncertainty in various practical problems. Usually, the real numbers are utilized to express the decision information, but it is noted that the description of attributes using picture fuzzy sets (PFSs) proves to be more appropriate. As a powerful decision tool, PFSs provides more decision information that requires the application of some specific situations more types of response of human ideas: yes, contain, no, reject. QUALIFLEX (qualitative flexible multiple criteria method), is one of the well-known outranking methods to solve the multiple …attribute group decision making (MAGDM) problems with crisp numbers. The QUALIFLEX method can perfectly address the complex MAGDM problems where a lot of attributes are utilized to assess a limited number of alternatives. The electronic music acoustic quality evaluation is a classical MAGDM. This paper proposes and utilizes the QUALIFLEX to develop the picture fuzzy QUALIFLEX(PF-QUALIFLEX) method for MAGDM. The current study is mainly devoted to explore and extend the measurement of alternatives and ranking according to the QUALIFLEX under the background of PFSs. Furthermore, an example to evaluate the electronic music acoustic quality is handled through the proposed method to substantiate the extended approach. Show more

Keywords: Multiple attribute group decision making (MAGDM), picture fuzzy sets (PFSs), the extended QUALIFLEX method, electronic music acoustic quality evaluation

DOI: 10.3233/JIFS-223377

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 5021-5032, 2023

Authors: Fu, Chengcai | Lu, Fengli | Wu, Fan | Zhang, Guoying

Article Type: Research Article

Abstract: The estimation of gangue content is the main basis for intelligent top coal caving mining by computer vision, and the automatic segmentation of gangue is crucial to computer vision analysis. However, it is still a great challenge due to the degradation of images and the limitation of computing resources. In this paper, a hybrid connected attentional lightweight network (HALNet) with high speed, few parameters and high accuracy is proposed for gangue intelligent segmentation on the conveyor in the top-coal caving face. Firstly, we propose a deep separable dilation convolution block (DSDC) combining deep separable convolution and dilation convolution, which can …provide a larger receptive field to learn more information and reduce the size and computational cost of the model. Secondly, a bridging residual learning framework is designed as the basic unit of encoder and decoder to minimize the loss of semantic information in the process of feature extraction. An attention fusion block (AFB) with skip pathway is introduced to capture more representative and distinctive features through the fusion of high-level and low-level features. Finally, the proposed network is trained through the expanded dataset, and the gangue image segmentation results are obtained by pixel-by-pixel classification method. The experimental results show that the proposed HALNet reduces about 57 percentage parameters compared with U-Net, and achieves state-of-the art performance on dataset. Show more

Keywords: Gangue intelligent segmentation, the top-coal caving face, depthwise separable dilation convolution, attention mechanism

DOI: 10.3233/JIFS-213506

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 5033-5044, 2023