Journal of Intelligent & Fuzzy Systems - Volume 41, issue 2

Authors: Rampriya, R.S. | Sabarinathan, | Suganya, R.

Article Type: Research Article

Abstract: In the near future, combo of UAV (Unmanned Aerial Vehicle) and computer vision will play a vital role in monitoring the condition of the railroad periodically to ensure passenger safety. The most significant module involved in railroad visual processing is obstacle detection, in which caution is obstacle fallen near track gage inside or outside. This leads to the importance of detecting and segment the railroad as three key regions, such as gage inside, rails, and background. Traditional railroad segmentation methods depend on either manual feature selection or expensive dedicated devices such as Lidar, which is typically less reliable in railroad …semantic segmentation. Also, cameras mounted on moving vehicles like a drone can produce high-resolution images, so segmenting precise pixel information from those aerial images has been challenging due to the railroad surroundings chaos. RSNet is a multi-level feature fusion algorithm for segmenting railroad aerial images captured by UAV and proposes an attention-based efficient convolutional encoder for feature extraction, which is robust and computationally efficient and modified residual decoder for segmentation which considers only essential features and produces less overhead with higher performance even in real-time railroad drone imagery. The network is trained and tested on a railroad scenic view segmentation dataset (RSSD), which we have built from real-time UAV images and achieves 0.973 dice coefficient and 0.94 jaccard on test data that exhibits better results compared to the existing approaches like a residual unit and residual squeeze net. Show more

Keywords: Railroad aerial images, efficient net, modified residual net, attention layer, semantic segmentation

DOI: 10.3233/JIFS-210349

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4051-4068, 2021

Authors: Pan, Hongguang | Wen, Fan | Huang, Xiangdong | Lei, Xinyu | Yang, Xiaoling

Article Type: Research Article

Abstract: In the field of super-resolution image reconstruction, as a learning-based method, deep plug-and-play super-resolution (DPSR) algorithm can be used to find the blur kernel by using the existing blind deblurring methods. However, DPSR is not flexible enough in processing images with high- and low-frequency information. Considering a channel attention mechanism can distinguish low-frequency information and features in low-resolution images, in this paper, we firstly introduce this mechanism and design a new residual channel attention networks (RCAN); then the RCAN is adopted to replace deep feature extraction part in DPSR to achieve the adaptive adjustment of channel characteristics. Through four test …experiments based on Set5, Set14, Urban100 and BSD100 datasets, we find that, under different blur kernels and different scale factors, the average peak signal to noise ratio (PSNR) and structural similarity (SSIM) values of our proposed method increase by 0.31dB and 0.55%, respectively; under different noise levels, the average PSNR and SSIM values increase by 0.26dB and 0.51%, respectively. Show more

Keywords: image reconstruction, channel attention mechanism, residual channel attention networks, blur kernel

DOI: 10.3233/JIFS-202696

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4069-4078, 2021

Authors: Ma, Lina | Xu, Fengju | Wang, Lihua | Taslima, Akther

Article Type: Research Article

Abstract: Capital enrichment (CE) results from capital flows, which reflect the capital distribution among different regions and industries. This paper constructs the evaluation model of resource allocation efficiency from the perspective of capital and innovation resources. It expounds on CE’s theoretical mechanism by using the panel data from 2011 to 2018 for system GMM estimation. It finds that the manufacturing capital allocation efficiency (CAE) and innovation resource allocation efficiency (IRAE) show a volatile development trend. Both static and dynamic panel models show that there is a significant U-shaped curvilinear relationship between CE and CAE, CE and IRAE. CE’s inhibitory effect on …CAE and IRAE decreases with the improvement of CE until it exceeds the critical value of 8.27 and 8.93. After that, its impact on CAE and IRAE changes from negative to positive. Show more

Keywords: China’s manufacturing industry, capital enrichment, capital allocation efficiency, innovation resource allocation efficiency

DOI: 10.3233/JIFS-202856

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4079-4095, 2021

Authors: Rodríguez, Antonio

Article Type: Research Article

Abstract: Taking concepts from supply management, we developed a specification-assessment-compliance approach to obtain a transparent multi-criteria decision-making method. We designed an artificial-neuron-like node that allows the implementation of networks to represent hierarchies of evaluation criteria. A new graphical model based on functions in the unit segment uses the concept of Pythagorean fuzzy set (PFS). The specification PFSs’ entropies modulate the widths of one-sided triangular fuzzy numbers (TFNs) with positive slopes that become the evaluation nodes’ activation functions. All the specifications refer to the same point to facilitate the evaluation and ensure coherence. One-sided TFNs with negative slopes biunivocally represent the assessment …PFSs at the input layer of the network. A risk case study on the options for the outsourcing of an information technology development project shows the proposed method’s implementation. We compare the results with those of the application of two other previous methods. Show more

Keywords: Multi-criteria decision-making, Pythagorean fuzzy set, triangular fuzzy number, artificial neuron, information entropy

DOI: 10.3233/JIFS-210029

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4097-4108, 2021

Authors: Riaz, Muhammad | Garg, Harish | Farid, Hafiz Muhammad Athar | Aslam, Muhammad

Article Type: Research Article

Abstract: The low-carbon supply chain management is big a challenge for the researchers due to the rapid increase in global warming and environmental concerns. With the advancement of the environmental concerns and social economy, it is an unavoidable choice for a business to achieve sustainable growth for low-carbon supply chain management. Since the root of the chain depends upon the supplier selection and choosing an excellent low-carbon supply. Green supplier selection is one of the most crucial activities in low-carbon supply chain management, it is critical to develop rigorous requirements and a system for selection in low-carbon green supply chain management …(LCGSCM). A q-rung orthopair fuzzy number (q-ROFN) is pair of membership degree (MD) and non-membership degrees (NMD) which is reliable to address uncertainties in the various real-life problems. This article sets out a decision analysis approach for interactions between MDs and NMDs with the help of q-ROFNs. For this objective, we develop new aggregation operators (AOs) named as, q-rung orthopair fuzzy interaction weighted averaging (q-ROFIWA) operator, q-rung orthopair fuzzy interaction ordered weighted averaging (q-ROFIOWA) operator, q-rung orthopair fuzzy interaction hybrid averaging (q-ROFIHA) operator, q-rung orthopair fuzzy interaction weighted geometric (q-ROFIWG) operator, q-rung orthopair fuzzy interaction ordered weighted geometric (q-ROFIOWG) operator and q-rung orthopair fuzzy interaction hybrid geometric (q-ROFIHG) operator. These AOs define an advanced approach for information fusion and modeling uncertainties in multi-criteria decision-making (MCDM). At the end, a robust MCDM approach based on newly developed AOs is developed. Some significant properties of these AOS are analyzed and the efficiency of the developed approach is assessed with a practical application towards sustainable low-carbon green supply chain management. Show more

Keywords: MCDM, Aggregation operators, interaction relation, low-carbon green supply chain management

DOI: 10.3233/JIFS-210506

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4109-4126, 2021

Authors: Balamurugan, S. | Nageswari, S.

Article Type: Research Article

Abstract: Modular Multilevel Converter (MMC) plays a vital role in high voltage industries because of its high rating power conversion. Due to its usage in high voltage rating power conversion and switched capacitor usage in MMC structure, there arises a problem of unbalanced capacitor voltage, which causes circulating current and disturbance in output current regulation. To manage these problematic parameters, a FOPID (Fractional Order Proportional Integral Derivative) controller has been utilized, due to its dynamic tracking and fast response. Secondly, the gain values of FOPID are not efficient, and they are optimized for each control group at all times of MMC …working conditions. To provide a dynamic gain value by considering the dynamic change of error tracking parameters, Wild Spider Foraging Optimization (WSFO) algorithm has been developed based on the foraging behaviour of wild spider searching food (gain values) in view of changing the error of tracking parameters. The proposed algorithm has been evaluated in MATLAB Simulink by modeling the MMC structure with FOPID controller. The parameters of FOPID are optimized by bio-inspired algorithms like WSFO, Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO). The outcomes of the proposed WSFO-FOPID provide minimum circulating current and effectively balance the capacitor voltage in MMC. When the effectiveness of the results has been verified with the existing ABC and PSO optimization approaches, the proposed algorithm outperforms. Show more

Keywords: Modular multilevel converter, wild spider foraging optimization, circulating current, total harmonic distortion

DOI: 10.3233/JIFS-210528

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4127-4147, 2021

Authors: Li, JX | Zhao, H | Zhu, S.P | Huang, H. | Miao, YJ | Jiang, ZY

Article Type: Research Article

Abstract: The classification of fresh tobacco leaves during the picking process plays an important role in the subsequent roasting. In this paper, a lightweight convolutional neural network is used to detect the maturity of tobacco leaves quickly. Fresh tobacco leaves in the datasets are divided into 3 categories by the picking position, and each category is divided into 4 maturity levels and finally gets 12 types of tobacco leaves with different maturity. To ensure the lightweight of the model, the new network is based on the MobileNetV2 to establish. By utilizing shortcut operation, the shallow network information is preserved, and network …degradation is suppressed. In the tobacco leaf datasets we obtained, the improved network has superior performance and compared with other classic networks, the model size and the number of operations have been reduced. Show more

Keywords: Tobacco classification, lightweight network, MobileNetV2, shortcut

DOI: 10.3233/JIFS-210640

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4149-4158, 2021

Authors: Lei, Deming | Xi, Bingjie

Article Type: Research Article

Abstract: Distributed scheduling has attracted much attention in recent years; however, distributed scheduling problem with uncertainty is seldom considered. In this study, fuzzy distributed two-stage hybrid flow shop scheduling problem (FDTHFSP) with sequence-dependent setup time is addressed and a diversified teaching-learning-based optimization (DTLBO) algorithm is applied to optimize fuzzy makespan and total agreement index. In DTLBO, multiple classes are constructed and categorized into two types according to class quality. Different combinations of global search and neighborhood search are used in two kind of classes. A temporary class with multiple teachers is built based on Pareto rank and difference index and evolved …in a new way. Computational experiments are conducted and results demonstrate that the main strategies of DTLBO are effective and DTLBO has promising advantages on solving the considered problem. Show more

Keywords: Two-stage hybrid flow shop scheduling, distributed scheduling, fuzzy scheduling, teaching-learning-based optimization

DOI: 10.3233/JIFS-210764

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4159-4173, 2021

Authors: Yan, Zhiyu | Lv, Shuang

Article Type: Research Article

Abstract: Accurate prediction of traffic flow is of great significance for alleviating urban traffic congestions. Most previous studies used historical traffic data, in which only one model or algorithm was adopted by the whole prediction space and the differences in various regions were ignored. In this context, based on time and space heterogeneity, a Classification and Regression Trees-K-Nearest Neighbor (CART-KNN) Hybrid Prediction model was proposed to predict short-term taxi demand. Firstly, a concentric partitioning method was applied to divide the test area into discrete small areas according to its boarding density level. Then the CART model was used to divide the …dataset of each area according to its temporal characteristics, and KNN was established for each subset by using the corresponding boarding density data to estimate the parameters of the KNN model. Finally, the proposed method was tested on the New York City Taxi and Limousine Commission (TLC) data, and the traditional KNN model, backpropagation (BP) neural network, long-short term memory model (LSTM) were used to compare with the proposed CART-KNN model. The selected models were used to predict the demand for taxis in New York City, and the Kriging Interpolation was used to obtain all the regional predictions. From the results, it can be suggested that the proposed CART-KNN model performed better than other general models by showing smaller mean absolute percentage error (MAPE) and root mean square error (RMSE) value. The improvement of prediction accuracy of CART-KNN model is helpful to understand the regional demand pattern to partition the boarding density data from the time and space dimensions. The partition method can be extended into many models using traffic data. Show more

Keywords: Short-term taxi demand forecast, CART-KNN hybrid prediction model, spatial and temporal heterogeneity, concentric partitioning, time series

DOI: 10.3233/JIFS-210872

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4175-4186, 2021

Authors: Ge, Yang | Xin, Ding

Article Type: Research Article

Abstract: In the task of Person re-identification (reID), the range of motion of pedestrians often spans multiple camera areas, and their motion direction and behavior cannot be constrained, and irrelevant people or objects in different scenes will also obtain target pedestrian information for us Cause interference. At the same time, the surveillance system also has many characteristics such as a fixed shooting angle of a single camera, different angles between different cameras, and low image resolution. These characteristics make the task of Person re-identification difficult. This paper proposes a Multi-level Feature Extraction Network (MFEN) based on SEResNet-50. Extracting richer and more …diverse pedestrian features from poor-quality images will effectively improve the re-identification ability of the network, and MFEN can obtain Multistage key features in the image through the Feature Re-extraction Method (FRM) proposed in this paper. Experiments show that compared with AANet-50, MFEN has 3.85% /0.71% improvements of mAP/ Rank-1 on the Market1501 dataset, and 2.74% /1.28% improvements of mAP/ Rank-1 on the DukeMTMC-reID dataset. Show more

Keywords: Person re-identification, full supervision, attention mechanism, multi-level feature extraction network, feature re-extraction method

DOI: 10.3233/JIFS-211456

Citation: Journal of Intelligent & Fuzzy Systems, vol. 41, no. 2, pp. 4187-4201, 2021