Article
Computer Science, Artificial Intelligence
Kang Wang, Yanru Liu, Qianyi Xing, Yuansheng Qian, Jianzhou Wang, Mengzheng Lv
Summary: This study introduces a comprehensive significant wave height combined prediction system, which utilizes outlier detection, sophisticated feature engineering, multi-criteria decision-based model selection, multi-objective homogeneous nuclear molecular optimization, and hybrid kernel density estimation to achieve accurate point and interval predictions of significant wave height.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Shengyingjie Liu, Zongkai Yang, Sannyuya Liu, Ruxia Liang, Jianwen Sun, Qing Li, Xiaoxuan Shen
Summary: Intelligent tutoring systems (ITS) analyze user behavior to customize personalized learning strategies. However, existing methods cannot effectively model ITS data due to the discrete user evolution. This study introduces the concept of a discrete evolution graph (DEG) and proposes the DEGE method to embed ITS data in a hyperbolic space, outperforming other baselines in question annotation and performance prediction.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jingjing Wang, Xinman Zhang, Cong Zhang
Summary: This paper proposes a lightweight edge-guided smoke detection network (ESmokeNet) to improve smoke detection by integrating edge cues and enhancing smoke feature extraction capability. Experimental results show that ESmokeNet has significant superiority in capturing smoke edges and is a lightweight network suitable for smoke detection tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Gianluca Bonifazi, Francesco Cauteruccio, Enrico Corradini, Michele Marchetti, Giorgio Terracina, Domenico Ursino, Luca Virgili
Summary: This paper proposes a model-agnostic XAI framework based on network theory to explain the behavior of classifiers. The framework is different from other model-agnostic XAI approaches, as it is parameter-free and able to handle heterogeneous features. It introduces the concept of dyscrasia to detect the importance and interactions of features.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Haibin Jin, Xiaoquan Chu, Jianfang Qi, Jianying Feng, Weisong Mu
Summary: This study proposes a novel multiple attention transformer super-resolution (MATSR) method for effectively identifying grape leaf diseases. The method utilizes convolution for low-level feature extraction and employs multiple attention transformer components for global and local feature extraction. Furthermore, a dynamic learning strategy is designed to balance the importance of global and local features in grape leaf disease recognition. Experimental results demonstrate that the proposed method achieves good performance on high-resolution grape leaf disease images.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Hu Dong, Longjie Li, Dongwen Tian, Yiyang Sun, Yuncong Zhao
Summary: In this study, a new end-to-end solution for dynamic link prediction is proposed, which effectively learns the representations of node-pairs by leveraging the structural information of individual snapshots, historical features from network evolution, and global knowledge of the collapsed network. Extensive tests on several dynamic networks demonstrate that the proposed method achieves superior effectiveness compared to the baselines in most cases.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Junbo Lian, Guohua Hui
Summary: This paper introduces the Human Evolutionary Optimization Algorithm (HEOA), which is a metaheuristic algorithm inspired by human evolution. The algorithm divides the global search process into two distinct phases and uses unique search strategies. Comparative analysis with other algorithms demonstrates the effectiveness of HEOA in approximating optimal solutions for complex global optimization problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Li Qiao, Kai Liu, Yanfeng Xue, Weidong Tang, Taybeh Salehnia
Summary: This paper presents a new hybrid optimization algorithm (AOA-HHO) for solving the multilevel thresholding image segmentation problem. The algorithm combines the features of arithmetic optimization algorithm and Harris hawks optimizer to obtain better thresholds in both local and global search, improving the accuracy and performance of image segmentation.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Review
Computer Science, Artificial Intelligence
Soroor Motie, Bijan Raahemi
Summary: Financial fraud is a persistent problem in the finance industry, but Graph Neural Networks (GNNs) have emerged as a powerful tool for detecting fraudulent activities. This systematic review provides a comprehensive overview of the current state-of-the-art technologies in using GNNs for financial fraud detection, identifies gaps and limitations in existing research, and suggests potential directions for future research.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Dirui Xie, He Xiao, Yue Zhou, Shukai Duan, Xiaofang Hu
Summary: This article introduces a memristive-based image restoration algorithm that can be deployed on edge devices. By implementing Convolutional Neural Network (CNN) and specific circuit designs, the proposed method outperforms other methods in various image restoration tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Sheng Li, Xiaoheng Tang, Bo Cao, Yuyang Peng, Xiongxiong He, Shufang Ye, Fei Dai
Summary: The research proposes an automated polyp segmentation method using a boundary-guided network, which plays an important role in the early diagnosis and treatment of gastrointestinal diseases. Through two-stage transfer learning, the method accurately identifies the lesion area, especially for small polyps. Experimental results demonstrate its superior performance compared to other methods, achieving high segmentation scores.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Takreem Haider, Saul A. Blanco, Umar Hayat
Summary: Pseudo-random number generators are crucial for image cryptographic algorithms, but traditional methods have limitations. We propose a novel approach that combines elliptic curves and genetic algorithms to improve security and resistance against differential attacks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Zhiyong Ji, Xianhua Wu, Ji Guo, Guo Wei
Summary: Common benchmarking can help assess and improve the performance of Decision-Making Units (DMUs) experiencing similar circumstances. Further exploration is needed, particularly in understanding the similarity between management goals and targets. This study proposes a novel Data Envelopment Analysis (DEA) model and iterative algorithm to identify a common best practice frontier and provide stepwise reallocation paths.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Merve Bulut, Evrencan Ozcan
Summary: The move to predictive and prescriptive maintenance requires cost-effective methods for monitoring degradation and predicting failures. Hydroelectric power plants are where the most powerful and unique techniques of this evolution are observed. The use of fuzzy set theory in process management is encouraged to improve the decision-making process for planning activities in Prescriptive Maintenance Planning (MP). However, existing studies often overlook potential schedule delays and the indirect impact of sustainable strategy on revenues.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Borui Cai, Guangyan Huang, Shuiqiao Yang, Yong Xiang, Chi-Hung Chi
Summary: This paper proposes a semi-supervised time series clustering method (SE-Shapelets) that utilizes a small number of labeled and propagated pseudo-labeled time series to discover representative shapelets and improve clustering accuracy. The method uses a salient subsequence chain (SSC) and a linear discriminant selection (LDS) algorithm to discover and select shapelets, and experiments show higher clustering accuracy compared to other semi-supervised time series clustering methods.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Jinyan Hu, Yanping Jiang
Summary: This paper examines the allocation problem of shared parking spaces considering parking unpunctuality and no-shows. It proposes an effective approach using sample average approximation (SAA) combined with an accelerating Benders decomposition (ABD) algorithm to solve the problem. The numerical experiments demonstrate the significance of supply-demand balance for the operation and user satisfaction of the shared parking system.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Shengjie Cheng, Peiyong Zhou, Yu Liu, Hongji Ma, Alimjan Aysa, Kurban Ubul
Summary: This paper presents an improved knowledge distillation algorithm that can effectively compress models and improve detection performance on mobile devices by enhancing global feature representation and introducing an interpretable feature shifting method.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Xian Mo, Jun Pang, Zhiming Liu
Summary: This research proposes a temporal attributed network embedding framework based on autoencoders to address the issue of handling outlier nodes in temporal attributed networks. By modeling node information using an outlier-aware autoencoder and incorporating attribute features into link structure through simplified feature preprocessing, experimental results show that the proposed model outperforms other baseline models in node classification and link prediction tasks.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Mengyuan Sun, Yong Tian, Xunuo Wang, Xiao Huang, Qianqian Li, Zhixiong Li, Jiangchen Li
Summary: Flight delays are a worldwide challenge that significantly affects the safety and efficiency of air transportation systems. This study proposes a transport causality knowledge-guided extended graph convolutional network framework to address the crucial issues in propagated delay prediction. By developing a causality knowledge-guided airport delay propagation network and utilizing a causality-embedded adjacency matrix for delay prediction, the proposed method significantly improves the prediction performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Artificial Intelligence
Aybike Ozyuksel Ciftcioglu
Summary: One of the main challenges in using reinforced concrete materials in structures is to comprehend their fire resistance. This research proposes a novel ensemble machine learning approach to classify columns according to their fire resistance characteristics, and demonstrates that it outperforms other classifiers in practical applications.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)