Journal of Intelligent & Fuzzy Systems - Volume 46, issue 5-6

Authors: Deng, Lulu | Zhang, Changlun | He, Qiang | Wang, Hengyou | Huo, Lianzhi | Mu, Haibing

Article Type: Research Article

Abstract: The semantic segmentation of high-resolution remote sensing images has broad application prospects in land cover classification, road extraction, urban planning and other fields. To alleviate the influence of the large data volume and complex background of high-resolution remote sensing images, the usual approach is to downsample them or cut them into small pieces for separate processing. Even if combining the two methods can improve the segmentation efficiency, it ignores the differences between the middle and the edge regions. Therefore, we consider the characteristics of large and irregular region in high-resolution remote sensing images, and then propose an irregular adaptive refinement …network to locate the irregular edge region, which will be refined adaptively. Specifically, on the basis of effectively preserving the global and local information, the prediction confidence is calculated to locate pixel points that are poorly segmented, so as to form irregular regions requiring further refinement, avoiding to ‘over-refine’ intermediate region with good segmentation. At the same time, considering the difference in the refinement degree of different pixels, we propose to adaptively integrate the local segmentation results to refine the coarse segmentation results. In addition, in order to bridge the gap between the two extreme ends of the scale space, we introduce a multi-scale framework. Finally, we conducted experiments on the Deepglobe dataset showing that the proposed method performed 0.37% to 0.87% better than the previous state-of-the-art methods in terms of mean Intersection over Union (mIoU). Show more

Keywords: High spatial resolution, remote sensing image, semantic segmentation, adaptive

DOI: 10.3233/JIFS-232958

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11235-11246, 2024

Authors: Liu, Fuchen | Zhou, Sijia | Zhang, Dezhou | Wang, Xiaocui

Article Type: Research Article

Abstract: Deep learning has demonstrated remarkable advantages in the field of human pose estimation. However, traditional methods often rely on widening and deepening networks to enhance the performance of human pose estimation, consequently increasing the parameter count and complexity of the networks. To address this issue, this paper introduces Ghost Attentional Down network, a lightweight human pose estimation network based on HRNet. This network leverages the fusion of features from high-resolution and low-resolution branches to boost performance. Additionally, GADNet utilizes GaBlock and GdBlock, which incorporate lightweight convolutions and attention mechanisms, for feature extraction, thereby reducing the parameter count and computational complexity …of the network. The fusion of relationships between different channels ensures the optimal utilization of informative feature channels and resolves the issue of feature redundancy. Experimental results conducted on the COCO dataset, with consistent image resolution and environmental settings, demonstrate that employing GADNet leads to a reduction of 60.7% in parameter count and 61.2% in computational complexity compared to the HRNet network model, while achieving comparable accuracy levels. Moreover, when compared to commonly used human pose estimation networks such as Cascaded Pyramid Network (CPN), Stacked Hourglass Network, and HRNet, GADNet achieves high-precision detection of human keypoints even with fewer parameters and lower computational complexity, our network has higher accuracy compared to MobileNet and ShuffleNet. Show more

Keywords: Human pose estimation, high-resolution network, attention mechanism, feature redundancy

DOI: 10.3233/JIFS-233501

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11247-11261, 2024

Authors: Sun, Xiaochuan | Wang, Yu | Hao, Mingxiang | Li, Yingqi | Huang, Tianyu

Article Type: Research Article

Abstract: Reservoir structure optimization of echo state networks (ESN) is an important enabler for improving network performance. In this regard, pruning provides an effective means to optimize reservoir structure by removing redundant components in the network. Existing studies achieve reservoir pruning by removing insignificant neuronal connections. However, such processing causes the optimized neurons to still remain in the reservoir and thus hinder network inference by participating in computations, leading to suboptimal utilization of pruning benefits by the network. To solve this problem, this paper proposes an adaptive pruning algorithm for ESN within the detrended multiple cross-correlation (DMC2 ) framework, i.e., DMAP. …On the whole, it contains two main functional parts: DMC2 measure of reservoir neurons and reservoir pruning. Specifically, the former is used to quantify the correlation among neurons. Based on this, the latter can remove neurons with high correlation from the reservoir completely, and finally obtain the optimal network structure by retraining the output weights. Experiment results show that DMAP-ESN outperforms its competitors in nonlinear approximation capability and reservoir stability. Show more

Keywords: Echo state network, reservoir structure optimization, pruning, time-series prediction, detrended multiple cross-correlation

DOI: 10.3233/JIFS-233605

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11263-11275, 2024

Authors: Renganathan, Alagammai | Nataraj, Sathees Kumar | Vasantha, Kavitha | Texina, Staphney

Article Type: Research Article

Abstract: Polycyclic Aromatic Hydrocarbons (PAHs) are complex chemical compounds that occur naturally in unprocessed food when it is exposed to contaminated air during transportation, natural emission such as volcano, forest fire and through pesticides spray. It is reported by different agencies that there are 16 types of PAHs in which BaP (Benzo[a] pyrene), BaA (Benz[a]anthracene), BbF(Benzo [b] fluoranthene), Chr (Chrysene) are considered to be carcinogenic and it can occur due to different processes. In processed food it occurs due to various processing methods like overheating, incomplete burning, drying etc. The presence of PAH in food is conventionally found through analytical, traditional, …and semi-automatic methods. These methods are found to be valuable but expensive and time-consuming. Further, these methods are used only for the detection of PAHs and the toxicity level is measured or identified based on expert knowledge of researchers and the Standards. Therefore, in this research, a simple harmfulness index system has been developed using Fuzzy Logic System(FLS). The proposed system has been designed based on the PAH values of different food and food products. Hence to initiate the study and to determine the significance of the results, PAH data have been collected from different articles that have investigated food products experimentally. These PAH data were analyzed using statistical measures such as Min , Mean , Max, Standard Deviation, Variance and Kurtosis method. Based on the observations from the results, the fuzzy sets were designed with four membership functions for each PAH and the rules were framed. The strength output from the inference engine has been associated with harmfulness index such as normal, low risk, medium risk, and high risk. From the evaluation, it can be observed that 89.72% of the food samples were recognized along with their degree of harmfulness. Also it can be inferred that 11% of the misclassified samples showed clear metrics of their harmfulness with PAH variations. Show more

Keywords: Polycyclic aromatic hydrocarbons, statistical analysis, fuzzy logic system, measure of toxicity, harmfulness index system

DOI: 10.3233/JIFS-233778

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11277-11291, 2024

Authors: Nguyen, Manh Hung | Van Nguyen, Hong | Tran, Van Quan

Article Type: Research Article

Abstract: Forecasting container ship arrival times is challenging, requiring a thorough analysis for accuracy. This study investigates the effectiveness of machine learning (ML) techniques in maritime transportation. Using a dataset of 581 samples with 8 input variables and 1 output variable (arrival time), ML models are constructed. The Pearson correlation matrix reduces input variables to 7 key factors: freight forwarder, dispatch location, loading and discharge ports, post-discharge location, dispatch day of the week, and dispatch week. The ranking of ML performance for predicting the arrival time of container ships can be arranged in descending order as GB-PSO > XGB > RF > RF-PSO > GB > KNN > SVR. The best ML model, …GB-PSO, demonstrates high accuracy in predicting the arrival time of container ships, with R2 = 0.7054, RMSE = 7.4081 days, MAE = 5.1891 days, and MAPE = 0.0993% for the testing dataset. This is a promising research outcome as it seems to be the first time that an approach involving the use of minimal and easily collectible input factors (such as freight forwarder, dispatch time and place, port of loading, post port of discharge, port of discharge) and the combination of a machine learning model has been introduced for predicting the arrival time of container ships. Show more

Keywords: Machine learning, container ships, arrival time, freight forwarder, place of dispatch, port of loading

DOI: 10.3233/JIFS-234552

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11293-11310, 2024

Authors: Premanand, V. | Arulalan, V. | Kumar, Dhananjay

Article Type: Research Article

Abstract: A Multiple moving object detection, tracking, and counting algorithm is mainly designed exclusively suitable for congested areas. The counting system can alleviate the betrayal performance in the crowded areas. Most of the existing methods developed for tracking and counting face serious challenges in detection due to high densities of the target. This condition urged the researchers to update the existing systems. The present methodology was designed to address such issues. In the present methodology, the contrast was initially enhanced between the objects and their backgrounds using a Double Plateau Histogram Equalization (DPHE). Then, the motion was estimated for the contrast-enhanced …image to identify the moment of the object using the modified Adaptive Distance Covariance Rood Pattern Search (ADCRPS) algorithm. After that, the morphological operation was deployed to sharpen the images by removing all the unwanted things. Then, the features were extracted and important features were selected using the modified Chaotic Tent Shuffled Shepherd Optimization (CTSSO) Algorithm. With the selected features object, detection was done using the proposed Scaled Non-Monotonic Cauchy Dense Convolutional Neural Network (SNMC-DenCNN). The detected object was then tracked with the aid of Channel and Spatial Reliability Tracker (CSRT). Finally, the objects were counted by intersection over union (IOU) by explicitly computing the association between detected and tracked objects. Also, the experimental results showed the effectiveness and efficiency of the proposed system with enhanced accuracy. Show more

Keywords: Double Plateau Histogram Equalization (DPHE), Adaptive Distance Covariance Rood Pattern Search (ADCRPS), Chaotic Tent Shuffled Shepherd Optimization (CTSSO), Scaled Non-Monotonic Cauchy Dense Convolution Neural Network (SNMC-DenCNN), Channel and Spatial Reliability Tracker (CSRT)

DOI: 10.3233/JIFS-234840

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11311-11329, 2024

Authors: Belal, Mohamad Mulham | Sundaram, Divya Meena

Article Type: Research Article

Abstract: Visualization-based malware detection gets more and more attention for detecting sophisticated malware that traditional antivirus software may miss. The approach involves creating a visual representation of the memory or portable executable files (PEs). However, most current visualization-based malware classification models focus on convolution neural networks instead of Vision transformers (ViT) even though ViT has a higher performance and captures the spatial representation of malware. Therefore, more research should be performed on malware classification using vision transformers. This paper proposes a multi-variants vision transformer-based malware image classification model using multi-criteria decision-making. The proposed method employs Multi-variants transformer encoders to show different …visual representation embeddings sets of one malware image. The proposed architecture contains five steps: (1) patch extraction and embeddings, (2) positional encoding, (3) multi-variants transformer encoders, (4) classification, and (5) decision-making. The variants of transformer encoders are transfer learning-based models i.e., it was originally trained on ImageNet dataset. Moreover, the proposed malware classifier employs MEREC-VIKOR, a hybrid standard evaluation approach, which combines multi-inconsistent performance metrics. The performance of the transformer encoder variants is assessed both on individual malware families and across the entire set of malware families within two datasets i.e., MalImg and Microsoft BIG datasets achieving overall accuracy 97.64 and 98.92 respectively. Although the proposed method achieves high performance, the metrics exhibit inconsistency across some malware families. The results of standard evaluation metrics i.e., Q, R, and U show that TE3 outperform the TE1, TE2, and TE4 variants achieving minimal values equal to 0. Finally, the proposed architecture demonstrates a comparable performance to the state-of-the-art that use CNNs. Show more

Keywords: Vision transformer, MCDM, VIKOR, MEREC, image malware classifier

DOI: 10.3233/JIFS-235154

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11331-11351, 2024

Authors: Hayel, Rafa | El Hindi, Khalil | Hosny, Manar | Alharbi, Rawan

Article Type: Research Article

Abstract: Instance-Based Learning, such as the k Nearest Neighbor (kNN), offers a straightforward and effective solution for text classification. However, as a lazy learner, kNN’s performance heavily relies on the quality and quantity of training instances, often leading to time and space inefficiencies. This challenge has spurred the development of instance-reduction techniques aimed at retaining essential instances and discarding redundant ones. While such trimming optimizes computational demands, it might adversely affect classification accuracy. This study introduces the novel Selective Learning Vector Quantization (SLVQ) algorithm, specifically designed to enhance the performance of datasets reduced through such techniques. Unlike traditional LVQ algorithms that …employ random vector weights (codebook vectors), SLVQ utilizes instances selected by the reduction algorithm as the initial weight vectors. Importantly, as these instances often contain nominal values, SLVQ modifies the distances between these nominal values, rather than modifying the values themselves, aiming to improve their representation of the training set. This approach is crucial because nominal attributes are common in real-world datasets and require effective distance measures, such as the Value Difference Measure (VDM), to handle them properly. Therefore, SLVQ adjusts the VDM distances between nominal values, instead of altering the attribute values of the codebook vectors. Hence, the innovation of the SLVQ approach lies in its integration of instance reduction techniques for selecting initial codebook vectors and its effective handling of nominal attributes. Our experiments, conducted on 17 text classification datasets with four different instance reduction algorithms, confirm SLVQ’s effectiveness. It significantly enhances the kNN’s classification accuracy of reduced datasets. In our empirical study, the SLVQ method improved the performance of these datasets, achieving average classification accuracies of 82.55%, 84.07%, 78.54%, and 83.18%, compared to the average accuracies of 76.25%, 79.62%, 66.54%, and 78.19% achieved by non-fine-tuned datasets, respectively. Show more

Keywords: Machine learning, instance based learning, learning vector quantization, k-nearest neighbor, value difference metric (VDM)

DOI: 10.3233/JIFS-235290

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11353-11366, 2024

Authors: Wei, Guangcun | Fu, Jihua | Pan, Zhifei | Fang, Qingge | Zhang, Zhi

Article Type: Research Article

Abstract: The text in natural scenes is often smaller compared to artificially designed text. Due to the small proportion of pixels, low resolution, less semantic information, and susceptibility to complex scenes, tiny text detection often results in many missed detections. To address this issue, this paper draws inspiration from small object detection methods and proposes TiTDet, a detection algorithm more suitable for tiny text. Due to the small proportion of pixels, low resolution, less semantic information, and susceptibility to complex scenes, tiny text detection often results in many missed detections. To address this issue, this paper draws inspiration from small object …detection methods and proposes TiTDet, a detection algorithm more suitable for tiny text. Firstly, this paper incorporates a context extraction module and an attention-guided module. These modules guide contextual information learning through a self attention mechanism, while eliminating the possible negative impact caused by redundant information. Regarding multi-scale feature fusion, this paper proposes a fine-grained effective fusion factor, making the fusion process emphasize small object learning more and highlight the feature expression of tiny texts. In terms of post-processing, this paper proposes a differentiable binarization module, incorporating the binarization process into model training. Leveraging the implicit information in the data to drive model improvement can enhance the post-processing effect. Lastly, this paper proposes a scale-sensitive loss, which can handle tiny texts more fairly, fully considering the positional relationship between the predicted and real regions, and better guiding the model training. This paper proves that TiTDet exhibits high sensitivity and accuracy in detecting tiny texts, achieving an 86.0% F1-score on ICDAR2015. The paper also compares the superiority of the method on CTW1500 and Total-Text. Show more

Keywords: Tiny text detection, context extraction module, attention-guided module, effective fusion factor, scale-sensitive loss

DOI: 10.3233/JIFS-236317

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11367-11379, 2024

Authors: Tekkali, Chandana Gouri | Natarajan, Karthika

Article Type: Research Article

Abstract: Imbalanced Learning is a significant issue in machine learning, affecting the performance and accuracy of binary or multi-classification algorithms, especially in large-scale data handling and classification. There are some popular techniques to covert this imbalanced data into a balanced one such as undersampling, under-sampling with tomek links, randomized oversampling, synthetic minority oversampling technique (SMOTE), and adaptive synthetic generation (ADASYN). Generally, the ADASYN algorithm could be used to propagate minority sample points to rise the imbalanced ratio between majority and minority sample points, but in some cases, it may conflict with decision boundary points and noisy points. This paper proposed a …Refitted AdaSyn Algorithm (RAA) with Gaussian Distribution (GD). So that new minority samples are distributed much closer to the center of the minority sample to spotlight the conflicts. The classification accuracy has improved with RAA over formal ADASYN. For examining the proposed work the imbalanced benchmark datasets like European, Banksim, Paymentcard, and UCI credit card are considered. Vanilla Generative Adversarial Network (GAN) is a deep learning model used to classify fraud and non-fraud transactions, demonstrating significant differences between balanced and imbalanced learning approaches and achieving an accuracy of 97.5% on dataset DS4. Show more

Keywords: Imbalanced learning, synthetic minority oversampling technique, adaptive synthetic, refitted Adasyn algorithm (RAA)

DOI: 10.3233/JIFS-236392

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 5-6, pp. 11381-11396, 2024