Journal of Intelligent & Fuzzy Systems - Volume 42, issue 3

Authors: Zhou, Yinfeng | Li, Jinjin | Wang, Hongkun | Sun, Wen

Article Type: Research Article

Abstract: In knowledge space theory (KST), knowledge structure is an effective feature to evaluate individuals’ knowledge and guide future learning. How to construct knowledge structures is one of the key research problems in KST. At present, the knowledge structure has been generalized to the polytomous knowledge structure. This article mainly focuses on the special polytomous knowledge structures delineated by skills, which are called fuzzy knowledge structures. We consider how to construct fuzzy knowledge structures based on the relationship between items and skills, and how to find the learning paths for specific knowledge domains. First, we construct knowledge structures in four models, …which are the conjunctive model of skill maps, the disjunctive and conjunctive models of fuzzy skill maps, and the competency model of fuzzy skill multimaps. Second, we assess individuals’ skills and find the learning paths for the specific knowledge domains in the first three models. Finding the learning paths for a specific knowledge domain can guide learning and improve the learning efficiency of individuals. Finally, we analyze some data sets to show that the algorithms proposed are effective and applicable. These works can be applied to adaptive learning systems, which bring great convenience for assessing individuals’ knowledge and guiding future learning. Show more

Keywords: Fuzzy knowledge structure, learning path, disjunctive model, conjunctive model, competency model

DOI: 10.3233/JIFS-212018

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2629-2645, 2022

Authors: Prakash, R | Ayyar, K

Article Type: Research Article

Abstract: This paper presents an Enhanced Whale Optimization Algorithm (EWO) approach for tuning to perfection of Fractional Order Proportional Integral and integral order Controller (FOPI λ ) is used to sensorless speed control of permanent magnet Brushless DC (PMBLDC) motor under the operating dynamic condition such as (i) speed change by set speed command signal (ii) varying load conditions, (iii) integrated conditions and (iv) controller parameters uncertainty. On the other hand, it deals with a reduced THD (Total Harmonic Distortion) under dynamic operating conditions to improve the power quality for the above control system. Here present are three optimization techniques, namely …(i) Enhanced Whale Optimization (EWO), (ii) Invasive Weed Optimization (IWO), and (iii) Social Spider Optimization (SSO) for fine-tuning of the FOPI λ controller parameters with reduction of THD. The proposed optimization algorithm optimized FOPI λ controller are compared under various BLDC motor operating conditions. Based on the results of MATLAB/Simulink models, the proposed algorithms are evaluated. Here, both the simulation and the results of the experiments are validated for the proposed controller technique. It demonstrates that the effectiveness of the proposed controllers is completely validated by comparing the three intelligent optimization techniques mentioned above. The EWO optimized FOPI λ controller for speed control of sensorless PMBLDC motor clearly outperforms the other two intelligent controllers by minimizing the time domain parameters, THD, performance Indices error, convergence time, control efforts, cost function, mean and standard deviation. Show more

Keywords: BLDC motor drives, fractional order PID controller (FOPIλ), whale optimization algorithm, sensorless speed control techniques

DOI: 10.3233/JIFS-212167

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2647-2666, 2022

Authors: Murugesan, Malathi | Kaliannan, Kalaiselvi | Balraj, Shankarlal | Singaram, Kokila | Kaliannan, Thenmalar | Albert, Johny Renoald

Article Type: Research Article

Abstract: Deep learning algorithms will be used to detect lung nodule anomalies at an earlier stage. The primary goal of this effort is to properly identify lung cancer, which is critical in preserving a person’s life. Lung cancer has been a source of concern for people all around the world for decades. Several researchers presented numerous issues and solutions for various stages of a computer-aided system for diagnosing lung cancer in its early stages, as well as information about lung cancer. Computer vision is one of the field of artificial intelligence this is a better way to detect and prevent the …lung cancer. This study focuses on the stages involved in detecting lung tumor regions, namely pre-processing, segmentation, and classification models. An adaptive median filter is used in pre-processing to identify the noise. The work’s originality seeks to create a simple yet effective model for the rapid identification and U-net architecture based segmentation of lung nodules. This approach focuses on the identification and segmentation of lung cancer by detecting picture normalcy and abnormalities. Show more

Keywords: Lung cancer, pre-processing, support vector machine, deep learning, U-Net, classification accuracy

DOI: 10.3233/JIFS-212189

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2667-2679, 2022

Authors: Angappamudaliar Palanisamy, Senthil Kumar | Selvaraj, Dinesh | Ramasamy, SivaBalaKrishnan

Article Type: Research Article

Abstract: In the field of mobile robot decision making and control, path planning is an essential element as it defines the performance of the design. It is one of the hot topics in artificial intelligence and researchers pay more attention to develop an efficient model. The key requirements that must be considered while designing a navigational system for mobile robots are origin point, obstacles, destination point, path planning, and realistic decision mechanism. However, conventional systems have limitations as slow response, long planning, large turns, and unsafe factors. Aiming at the problems, this research work presents a hybrid optimized path planning model …for a mobile robot. Improved particle swarm optimization and Modified Whale optimization models are incorporated as a hybrid multi-objective approach to obtain the shortest, smoothest, and safest path for a mobile robot. Experimental results demonstrate that the proposed hybrid optimization model is suitable for mobile robot navigation for dynamic environments by obtaining a shorter, smoother, and safer path than existing algorithms. Show more

Keywords: Path planning, path optimization, hybrid optimization, mobile robot, improved particle swarm optimization

DOI: 10.3233/JIFS-211801

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2681-2693, 2022

Authors: Iqbal, M. Mohamed | Latha, K.

Article Type: Research Article

Abstract: Link prediction plays a predominant role in complex network analysis. It indicates to determine the probability of the presence of future links that depends on available information. The existing standard classical similarity indices-based link prediction models considered the neighbour nodes have a similar effect towards link probability. Nevertheless, the common neighbor nodes residing in different communities may vary in real-world networks. In this paper, a novel community information-based link prediction model has been proposed in which every neighboring node’s community information (community centrality) has been considered to predict the link between the given node pair. In the proposed model, the …given social network graph can be divided into different communities and community centrality is calculated for every derived community based on degree, closeness, and betweenness basic graph centrality measures. Afterward, the new community centrality-based similarity indices have been introduced to compute the community centralities which are applied to nine existing basic similarity indices. The empirical analysis on 13 real-world social networks datasets manifests that the proposed model yields better prediction accuracy of 97% rather than existing models. Moreover, the proposed model is parallelized efficiently to work on large complex networks using Spark GraphX Big Data-based parallel Graph processing technique and it attains a lesser execution time of 250 seconds. Show more

Keywords: Link prediction, social network, performance evaluation, prediction accuracy, parallel louvain algorithm

DOI: 10.3233/JIFS-211821

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2695-2711, 2022

Authors: Pang, Jing | Yao, Bingxue | Li, Lingqiang

Article Type: Research Article

Abstract: In this paper, we point out that Lin’s general neighborhood systems-based rough set model is an extension of Qian’s optimistic rough set model, and thus called optimistic general neighborhood systmes-based rough set model. Then we present a new rough set model based on general neighborhood systems, and prove that it is an extension of Qian’s pessimistic rough set model. Later, we study the basic properties of the proposed pessimistic rough sets, and define the serial, reflexive, symmetric, transitive and Euclidean conditions for general neighborhood systems, and explore the further properties of related rough sets. Furthermore, we apply the pessimistic general …neighborhood systems-based rough set model in the research of incomplete information system, and build a three-way decision model based on it. A simple practical example to show the effectiveness of our model is also presented. Show more

Keywords: Rough set, neighborhood system, pessimistic rough approximation operator, three-way decision

DOI: 10.3233/JIFS-211851

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2713-2725, 2022

Authors: Luo, Wentao | Feng, Pingfa | Zhang, Jianfu | Yu, Dingwen | Wu, Zhijun

Article Type: Research Article

Abstract: As the service life of the assembly equipment are short, the tightening data it produces are very limited. Therefore, data-driven assembly quality diagnosis is still a challenge task in industries. Transfer learning can be used to address small data problems. However, transfer learning has strict requirements on the training dataset, which is hard to satisfy. To solve the above problem, an Improved Deep Convolution Generative Adversarial Transfer Learning Model (IDCGAN-TM) is proposed, which integrates three modules: The generative learning module automatically produces source datasets based on small target datasets by using the improved generative-adversarial theory. The feature learning module improves …the feature extraction ability by building a lightweight deep learning model (DL). The transfer learning module consists of a pre-trained DL and a one fully connected layer to better perform the intelligent quality diagnosis on the training small sample data. A parallel computing method is adopted to obtain produced source data efficiently. Real assembly quality diagnosis cases are designed and discussed to validate the advance of the proposed model. In addition, the comparison experiments are designed to show that the proposed approach holds the better transfer diagnosis performance compared with the existing three state-of-art approaches. Show more

Keywords: Transfer learning, generative adversarial learning, small sample learning, quality diagnosis

DOI: 10.3233/JIFS-211860

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2727-2741, 2022

Authors: Sambath Kumar, K. | Rajendran, A.

Article Type: Research Article

Abstract: Manual segmentation of brain tumor is not only a tedious task that may bring human mistakes. An automatic segmentation gives results faster, and it extends the survival rate with an earlier treatment plan. So, an automatic brain tumor segmentation model, modified inception module based U-Net (IMU-Net) proposed. It takes Magnetic resonance (MR) images from the BRATS 2017 training dataset with four modalities (FLAIR, T1, T1ce, and T2). The concatenation of two series 3×3 kernels, one 5×5, and one 1×1 convolution kernels are utilized to extract the whole tumor (WT), core tumor (CT), and enhance tumor (ET). The modified inception module …(IM) collects all the relevant features and provides better segmentation results. The proposed deep learning model contains 40 convolution layers and utilizes intensity normalization and data augmentation operation for further improvement. It achieved the mean dice similarity coefficient (DSC) of 0.90, 0.77, 0.74, and the mean Intersection over Union (IOU) of 0.79, 0.70, 0.70 for WT, CT, and ET during the evaluation. Show more

Keywords: Brain tumor, automatic segmentation, deep neural network, inception, convolution

DOI: 10.3233/JIFS-211879

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2743-2754, 2022

Authors: Liu, Wei | Wang, Yuhong

Article Type: Research Article

Abstract: In view of the present situation that most aggregation methods of fuzzy preference information are extended or mixed by classical aggregation operators, which leads to the aggregation accuracy is not high. The purpose of this paper is to develop a novel method for spatial aggregation of fuzzy preference information. Thus we map the fuzzy preference information to a set of three-dimensional coordinate and construct the spatial aggregation model based on Steiner-Weber point. Then, the plant growth simulation algorithm (PGSA) algorithm is used to find the spatial aggregation point. According to the comparison and analysis of the numerical example, the aggregation …matrix established by our method is closer to the group preference matrices. Therefore, the optimal aggregation point obtained by using the optimal aggregation method based on spatial Steiner-Weber point can best represent the comprehensive opinion of the decision makers. Show more

Keywords: Fuzzy preference information, Steiner-Weber point, spatial aggregation model, aggregation operator, PGSA

DOI: 10.3233/JIFS-211913

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2755-2773, 2022

Authors: Honghong, Zhang | Xusheng, Gan | Ying, Liu | Yarong, Wu | Jingjuan, Sun | Liang, Tong | Feng, Yang

Article Type: Research Article

Abstract: To provide real-time safety assessment for low-altitude unmanned aerial vehicle (UAV) air traffic management, and to ensure the UAVs safe operation in low-altitude airspace, a risk assessment framework is proposed. It considers the accidents probability and the accidents hazards. Firstly, accidents probability model based on the System Theoretic Process Analysis-Bayesian Network (STPA-BN) algorithm is built. Potential system hazards are effectively identified and analyzed through the STPA process. The accidents cause identified based on the STPA process is taken as the root node. The relevant failure probability table is given respectively. It constitutes the BN used to analyze the system accidents …probability. This method uses a combination of qualitative and quantitative methods to calculate the accidents probability. Then, based on the UAV fall model, considering the uncertainty of the UAV operation process, the UAV fall point distribution is determined based on the Monte-Carlo method, and the impact area of the fall is calculated. Thus the system risk value is obtained. Finally, through case analysis, the validity and rationality of the proposed risk assessment framework are verified. Show more

Keywords: Unmanned aerial vehicle system, air traffic management, risk assessment

DOI: 10.3233/JIFS-211927

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2775-2792, 2022

Authors: Jeyaprakash, P. | Agees Kumar, C. | Ravi, A.

Article Type: Research Article

Abstract: Electricity is the most critical facility for humans. All traditional energy supplies are rapidly depleting. As a result, the energy resources are moved from traditional to non-conventional. In this research, mixture of two energy tools, namely wind and solar energy are used. Using a Hybrid Energy Storage System (HESS), continuous power can be provided. Electricity can be produced at a cost that is affordable. The integration of solar and wind in a hybrid system cause an increase in the system’s stability, which is the key benefit of this research. The system’s power transmission efficiency and reliability can be greatly enhanced …by integrating these two intermittent sources. When one of the energy source is unavailable or inadequate to meet load demands, the other energy source will supply the power. The major contribution in this research is that, the proposed bidirectional single-inductor multiple-port (BSIMP) converter significantly lowers the component count, smaller circuit size and lower cost, allowing HESS to be integrated into DC microgrid. Minimum number of components are used for the same number of ESs in HESS in the proposed BSIMP converter. The hybridization of battery and supercapacitor (SC) for storage purpose is more cost effective, as compared to the battery energy storage system, thus improving the battery stress and hence used for large scale grid energy storage. SC’s are accepted as backup and found very useful in delivering high power, not possible with batteries. The use of SC in addition to batteries can be one solution for achieving the low life cycle economy. The Single Objective Adaptive Firefly Algorithm (SOAFA) is introduced for optimising the Proportional-Integral (PI) controller parameters. The system cost is reduced by about 32%, with the constraints on wind turbine swept area, PV area, total battery and SC capacity with the proposed optimisation algorithm. Show more

Keywords: Bidirectional single-inductor multiple-port (BSIMP) converter, Single Objective Adaptive firefly Algorithm (SOAFA), PI controller, Hybrid Energy Storage System (HESS)

DOI: 10.3233/JIFS-212262

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2793-2808, 2022

Authors: Sha, Gang | Wu, Junsheng | Yu, Bin

Article Type: Research Article

Abstract: Purpose: at present, more and more deep learning algorithms are used to detect and segment lesions from spinal CT (Computed Tomography) images. But these algorithms usually require computers with high performance and occupy large resources, so they are not suitable for the clinical embedded and mobile devices, which only have limited computational resources and also expect a relative good performance in detecting and segmenting lesions. Methods: in this paper, we present a model based on Yolov3-tiny to detect three spinal fracture lesions, cfracture (cervical fracture), tfracture (thoracic fracture), and lfracture (lumbar fracture) with a small size model. We …construct this novel model by replacing the traditional convolutional layers in YoloV3-tiny with fire modules from SqueezeNet, so as to reduce the parameters and model size, meanwhile get accurate lesions detection. Then we remove the batch normalization layers in the fire modules after the comparative experiments, though the overall performance of fire module without batch normalization layers is slightly improved, we can reduce computation complexity and low occupations of computer resources for fast lesions detection. Results: the experiments show that the shrank model only has a size of 13 MB (almost a third of Yolov3-tiny), while the mAP (mean Average Precsion) is 91.3%, and IOU (intersection over union) is 90.7. The detection time is 0.015 second per CT image, and BFLOP/s (Billion Floating Point Operations per Second) value is less than Yolov3-tiny. Conclusion: the model we presented can be deployed in clinical embedded and mobile devices, meanwhile has a relative accurate and rapid real-time lesions detection. Show more

Keywords: Deep learning, Yolov3-tiny, shrank model, fire module, detection and location

DOI: 10.3233/JIFS-212255

Citation: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 3, pp. 2809-2828, 2022