Journal of Artificial Intelligence and Soft Computing Research Feed

Application of Multidimensional ACO Pheromone for Multi-Objective Optimization

Wed, 01 Jul 2026 00:00:00 GMT

In this work, we investigate an approach that enriches the information encoded within the ACO pheromone structure in order to enhance the performance of swarm optimization. While this concept has been extensively studied in the context of single-objective optimization, this paper provides a comprehensive evaluation of its extension to multi-objective optimization problems. The results demonstrate that this enhanced pheromone representation remains effective in multi-objective settings.

Multi-Swarm Bees Algorithm with GPU Computing for Belt Conveyor Production System

Wed, 01 Jul 2026 00:00:00 GMT

The paper presents the application of the Bees Algorithm to solve the NP -hard optimisation problem related to the Belt Conveyor Systems. For this purpose, the mathematical model for a real-life example of the Belt Conveyor Production System (BCPS) was defined. Creating the multi-swarm Bees Algorithm for solving this optimisation problem on a CUDA platform within the accepted time for real production systems, and analyzing the impact of control parameters on the algorithm's performance are the main objectives of our study. Moreover, the impact of the different block and grid sizes was checked. To ensure comparability of the results, extensive tests have been carried out using the multi-swarm version designed for the GPU and the mono-swarm version designed for the CPU platform. The results show that the proposed multi-swarm Bees Algorithm algorithm for the CUDA platform gives considerable acceleration of the calculations, but often requires the larger size of the neighbourhood.

A Novel Method for Improving Deep Learning Performance Using Rough Set Theory

Wed, 01 Jul 2026 00:00:00 GMT

Dimensionality reduction is a key stage in data processing. Eliminating irrelevant attributes from the input dataset enables more efficient processing and supports the development of robust Machine Learning models. In particular, when dealing with large datasets, attribute reduction algorithms can significantly reduce computational complexity while minimizing the loss of valuable information contained in the data. This paper explores the potential application of a Feature selection method based on Rough Set Theory for multivariate data. The experiments were conducted on the publicly available Taiwan Credit dataset. The results show that limiting the input feature space to a minimal set of attributes generated by a reduct selection algorithm not only reduces training and inference time for Machine Learning or Deep Learning models but may also improve their classification performance. The models achieved higher Accuracy and better adaptability to the input data, as confirmed by increased or comparable Precision and Recall scores. Additionally, the findings indicate that applying Feature selection using a reduct set can lead to more efficient data processing. These results suggest that integrating Rough Set Theory with Deep Learning models still represents a promising approach to analyzing attribute-value data.

Multiagent Dynamic Task Allocation Based on Graph Neural Reinforcement Learning Algorithm

Wed, 01 Jul 2026 00:00:00 GMT

Multi-agent dynamic task allocation (MADTA) for UAV swarm and autonomous systems remains a formidable challenge in highly uncertain and stochastic environments, where conventional reinforcement learning methods struggle with variable input dimensions and coordination conflicts. This paper proposes a spatiotemporal topology-aware graph reinforcement learning (STA-GRL) framework to address these limitations. By modeling the environment as a dynamic bipartite graph, the framework integrates a spatiotemporal gated graph attention (STGGA) module that employs a temporal gating mechanism to dynamically prioritize tasks with rapidly decaying deadlines. A topology-aware critic is further designed to penalize spatial conflicts among agents via an enhanced adjacency matrix. Extensive simulations demonstrate that STA-GRL significantly surpasses state-of-the-art baselines. In the primary evaluation scenario with 30 agents and an intermediate task arrival rate (λ = 0.6), STA-GRL achieves a task completion rate of 86.8% and an average response time of 18.4 seconds, while reducing the average conflict rate to just 2.1%. Moreover, ablation studies confirm the critical contribution of each architectural component, with the temporal gate improving the completion rate by 7.3% and the topology-aware critic reducing conflicts by 6.4%.

SOFAN-UNet: A Short Optimization Approach for Attention Networks in U-Net Using Particle Swarm Strategy for Precise Brain Tumor Segmentation

Wed, 01 Jul 2026 00:00:00 GMT

Accurate segmentation of brain tumors in magnetic resonance imaging (MRI) is essential for clinical diagnosis and treatment planning. However, variations in tumor morphology, location, and modality-specific appearance make the task highly complex for conventional deep learning approaches. This study introduces SOFAN-UNet, a novel segmentation framework that improves tumor localization and boundary delineation through hybrid attention mechanisms and bio-inspired optimization. The proposed SOFAN-UNet architecture builds on the traditional U-Net structure and incorporates a hybrid attention mechanism combining Squeeze-and-Excitation (SE) and Self-Attention modules. A short optimization strategy, implemented via Particle Swarm Optimization (PSO), is used to dynamically calibrate attention gate parameters, including scale factors and filter sizes, within a constrained search space. This enables efficient learning of discriminative tumor features while preserving spatial detail through optimized skip connections. The model was evaluated across three benchmark datasets—FBTS, BraTS 2021, and BraTS 2018—using DSC, JI, HD, ASSD, AUC, and MCC metrics. Ablation studies and five-fold cross-validation were conducted to assess robustness. SOFAN-UNet achieved state-of-the-art performance, with Dice scores reaching 0.9685 and Jaccard Index up to 0.9389. It demonstrated strong generalization across MRI modalities and tumor types, maintained low boundary error (HD < 2.5), and achieved AUC values above 0.999. Ablation results confirmed the effectiveness of PSO-based calibration and attention integration, especially for heterogeneous tumor regions. The SOFAN-UNet model offers a highly accurate and computationally efficient framework for brain tumor segmentation. Its robustness across datasets and imaging modalities supports its potential for clinical deployment and further extension to subregion tumor analysis.

A Holistic Approach to Multi-Modal Skin Lesion Diagnosis Supported by Statistical and Explainability-Based Investigation of Artifacts

Mon, 29 Jun 2026 00:00:00 GMT

Skin cancer is a prevalent and potentially life-threatening condition, where early and accurate detection is crucial for effective treatment. Traditional diagnosis, based on visual assessment, faces challenges due to inter-class variability and the similarity between benign and malignant lesions. Although automated diagnostic systems are gaining attention, few offer comprehensive evaluations. This study addresses this gap by systematically assessing such systems and reporting extensive performance metrics.This study contributes to both artificial intelligence and dermatological image analysis by introducing an automated system for multi-class skin lesion classification. The system was evaluated under various configurations, including original and artifact-inpainted images. Three approaches were employed: deep learning, radiomics-based and hybrid. Additionally, to enhance the interpretability, the system generates segmentation masks and attribution maps.Models were evaluated using five-fold cross-validation on the International Skin Imaging Collaboration (ISIC) 2018 Challenge Task 3 training dataset, with final performance assessed on the official test set. The best-performing model achieved a micro accuracy of 79.76±0.73, macro F1-score of 73.62±1.38, precision of 74.80±0.84, and recall of 73.93±2.19, surpassing comparable methods reported in the literature.The contribution to the research community is the release of a novel set of 57630 binary artifact labels for the ISIC-2018 Task 3 dataset, enabling research on the impact of visual artifacts such as hair, rulers, and interface fluids. This contribution is supported by statistical analysis and attribution map assessment, revealing significant differences in artifact occurrence across lesion classes and highlighting the utility of these labels in identifying and mitigating bias in skin lesion classification.

Anomaly Prediction Method for Complex Scenarios Based On Multi-Modal Causal Intervention

Mon, 29 Jun 2026 00:00:00 GMT

Anomaly prediction is vital for ensuring the safe operation of pump station facilities. However, traditional models are often hampered by spurious correlation stemming from unobservable confounding factors, thereby degrading detection accuracy. To address this, this paper proposes the Causal Intervention with Front-door Adjustment Model (CIFAM) to eliminate spurious correlation in complex features. Initially, CIFAM integrates video and signal data, utilizing graph attention networks and clustering to construct a multi-level structural attribute graph that represents dynamic operational dependencies. The model incorporates causal dilated convolution to capture long-term memory while preventing information leakage, alongside a random edge dropping strategy to simulate causal intervention. By applying the front-door adjustment criterion, CIFAM extracts robust intermediate representations to block interference paths. Furthermore, contrastive learning and Adaptive Instance Normalization (AdaIN) are employed to decouple features, bolstering model robustness in complex scenarios. Experimental results demonstrate that CIFAM achieves state-of-the-art performance across multiple industrial benchmarks, specifically reaching 91.1% accuracy and a 90.6% Micro-F1 score on the OURS dataset. The model exhibits exceptional robustness and sample utilization efficiency. Furthermore, with minor modifications, this algorithm can be generalized to various monitoring scenarios, such as power generator set monitoring, semiconductor production lines, and UAV-assisted monitoring for oil pipelines or high-voltage power line maintenance.

Graflow: A Microservice Anomaly Detection Method Based on Cross-Modal Feature Fusion and Multi-Scale Graph Attention Networks

Mon, 29 Jun 2026 00:00:00 GMT

With the widespread adoption of microservice architectures, software systems have become increasingly complex and dynamic, leading to more diverse types of anomalies. Traditional single-modal anomaly detection methods are no longer sufficient for accurately identifying system anomalies and locating their root causes. To address these challenges, this paper proposes GRAFlow, an anomaly detection and root cause localization method based on cross-modal feature fusion and multi-scale graph attention networks. GRAFlow integrates three key modalities—logs, performance metrics, and traces—and employs a cross-modal attention mechanism to dynamically model the semantic interactions among these heterogeneous data sources, thereby enhancing detection accuracy and robustness. Additionally, a multi-scale graph attention network is introduced to capture both local dependencies and long-range propagation paths among microservices, enabling more comprehensive system state modeling. The model jointly optimizes both anomaly detection and root cause localization tasks. Experimental results on two real-world microservice datasets, TrainTicket and SocialNetwork, demonstrate that GRAFlow significantly outperforms existing state-of-the-art methods across multiple evaluation metrics, including accuracy, F1 score, HR@K, and NDCG@K, confirming its effectiveness and robustness in complex system environments.

Learning-Based Risk-Perception Strategies for Intelligent Co-Control of Energy Efficiency and Safety in Autonomous Driving: A Survey

Mon, 29 Jun 2026 00:00:00 GMT

The integration of intelligent transportation systems and autonomous driving is reshaping modern mobility by mitigating the longstanding trade-off between traffic efficiency and road safety. Enabled by vehicle-to-everything (V2X) communications, connected and autonomous vehicles (CAVs) are increasingly integrated into vehicle–road–cloud collaborative networks, resulting in measurable improvements in traffic capacity, energy efficiency, and collision avoidance. However, the coexistence of CAVs, human-driven vehicles, and vulnerable road users (VRUs) introduces complex challenges in collaborative control, real-time risk perception, and data security. To address these issues, this review synthesizes recent advances through a tripartite lens: collaborative driving, risk-aware perception, and energy-efficient operation. Our analysis identifies three recurring scientific questions: (i) how to effectively couple dynamic risk perception with cooperative control under uncertainty; (ii) how to enable secure, privacy-preserving collaboration across heterogeneous agents; and (iii) how to guarantee VRU safety in mixed-autonomy traffic. Representative approaches fall into three categories: (1) multimodal collaborative decision-making frameworks combining hierarchical deep reinforcement learning and model predictive control; (2) federated learning architectures that preserve data privacy while enabling cross-vehicle knowledge sharing; and (3) human-centric safety mechanisms leveraging ultra-wideband sensing and heterogeneous graph neural networks for VRU detection and intent prediction. Collectively, these findings demonstrate that risk-aware, energy-efficient cooperative driving is technically feasible, yet its large-scale deployment hinges on interdisciplinary innovation, standardized communication protocols, and regulatory alignment.

Predicting Future E-Commerce Purchases from Multi-Visit Sequences and Behavioural Micro-Interactions

Mon, 29 Jun 2026 00:00:00 GMT

This paper investigates future purchase prediction in e-commerce using sequences of user visits and behavioural micro-interactions. The study is based on anonymised production data from three e-commerce domains, comprising approximately 690,000 users and 2.61 million visits. User histories are modelled as temporally ordered sequences of visits, with each visit represented by 21 features. Six models are evaluated: three tabular approaches (SVM, XGBoost, CatBoost) and three sequential architectures (RNN, LSTM, GRU), each tested in two variants addressing class imbalance. The experimental setup employs a temporal train–test split, five random seeds, and bootstrap-based significance testing. The top-performing sequential models achieve an AUC-PR of approximately 0.379, significantly outperforming the strongest tabular baseline, XGBoost (AUC-PR ≈ 0.364). This advantage remains consistent across domain-specific evaluations as well as in a leave-one-shop-out setting. Further analysis shows that mouse movement and scrolling-related features provide the strongest predictive signal, whereas extending user histories beyond 40 visits yields only marginal performance gains.

A Visually Explainable Dynamic Similarity Network for Few-Shot Classification

Wed, 25 Feb 2026 00:00:00 GMT

Few-shot learning (FSL) aims to transfer knowledge from known to unknown categories using limited samples. However, the opaque nature of neural networks makes it challenging to discern the knowledge learned by the model, and existing methods often lack explainability, limiting their reliable application in high-stakes fields such as medical diagnosis and autonomous driving. To address this, we propose a visually explainable dynamic similarity network (VEDSNet), which achieves a balance of performance, explainability, and efficiency through a lightweight architecture (approximately 6.8M parameters, built on a ViT-Tiny backbone). The Feature Decomposition Module (FDM) generates fine-grained, semantically meaningful representations via parallel feature learning, providing intuitive visual insights into the model’s decisions. The Dynamic Metric Module (DMM) employs a sample-adaptive dual-metric strategy to enhance discrimination with limited data, switching to a single metric for efficiency when data is sufficient. Experiments on standard datasets demonstrate that VEDSNet achieves high classification accuracy while providing clear visual explanations of its decision-making process, making it suitable for efficient deployment in resource-constrained scenarios.

An Improved Yolo Algorithm Based on Concise Decoupled Head for Real-Time Object Detection in Night Scenarios

Wed, 25 Feb 2026 00:00:00 GMT

This paper proposes CDH-YOLO, an efficient, real-time pedestrian detection model for nighttime RGB images. Built on YOLOv5, CDH-YOLO incorporates structural reparameterization to optimize the backbone network and integrates convolutional block attention module to enhance feature representation. Transposed convolution replaces nearest neighbor interpolation for upsampling to preserve semantic information. A lightweight decoupled head addresses spatial misalignment between classification and regression tasks, while SIoU loss improves training convergence and localization accuracy. Experiments on the KAIST dataset demonstrate that CDH-YOLO achieves superior accuracy with real-time performance, significantly outperforming existing methods in nighttime pedestrian detection.

Phishing Fraud Identity Inference Based on Graph Gated Recurrent Neural Network

Wed, 25 Feb 2026 00:00:00 GMT

Since the proposal of the blockchain, its application scenarios have been continuously expanded. However, the anonymity feature of the blockchain has hindered market regulation, leading to numerous illegal activities such as phishing fraud, which has now become a serious type of crime. Currently, most phishing fraud detection technologies on blockchain platforms use transaction data to construct basic raw transaction graphs and then use neural network methods to mine key information. This study proposes a graph gated recurrent neural network (GGRNN) model that fully integrates temporal and spatial information, effectively utilizing time-related information in the transaction graph. It first takes an account as the center node to obtain its second-order transaction data and then constructs a dynamic transaction graph (DTG). Subsequently, the DTG is fed to the GGRNN to process the temporal features in a gated recurrent unit (GRU) framework and introduce graph convolutional network (GCN) operations to fully use the node neigh-bourhood topology features, obtain the embedded representation of the graph, and then perform graph classification for phishing node detection. To verify the effectiveness of the proposed model, it was applied to real-world Ethereum transaction datasets. Numerical results show that the proposed GGRNN model significantly outperforms state-of-the-art methods.

Inverse Meets Distillation: Heterogeneous Teacher–Assistant Dual-Path Learning for Unsupervised Defect Detection

Wed, 25 Feb 2026 00:00:00 GMT

Unsupervised defect detection is crucial for industrial inspection, but teacher–student (T–S) frameworks tend to overfit a single teacher’s feature manifold, leading to poor generalization on subtle anomalies. We introduce TAD++, a dual-path distillation framework that combines heterogeneous Teacher–Assistant–Student (T–A–S) guidance with a pseudo-defect inverse-distillation branch. A compact assistant, structurally distinct from the teacher, is trained to co-distill the student, thereby mitigating single-teacher bias. In parallel, the inverse-distillation path tasks the student with reconstructing normal appearances from defect-injected inputs, serving as a regularization term to prevent anomaly leakage. A dynamic attention weighting module adaptively fuses these heterogeneous guidance signals. Crucially, the assistant, inverse branch, and weight modules are strictly training-only. This design ensures that while TAD++ benefits from a rigorous multi-phase optimization, it maintains zero additional inference latency and memory overhead compared to standard T–S baselines. On MVTec AD, BTAD, and VisA, TAD++ achieves consistent improvements in both image-level detection and pixel-level localization, with extensive ablations confirming the efficacy of the heterogeneous dual-path design.

SatSOM: Saturation Self-Organizing Maps for Continual Learning

Wed, 25 Feb 2026 00:00:00 GMT

Continual learning poses a fundamental challenge for neural systems, which typically suffer from catastrophic forgetting when exposed to sequential tasks. Self-Organizing Maps (SOMs), despite their inherent interpretability and efficiency, also exhibit this vulnerability. In this paper, we introduce Saturation Self-Organizing Maps (SatSOM)—an extension designed to enhance knowledge retention in continual learning scenarios. Sat-SOM incorporates a novel saturation mechanism that progressively reduces the learning rate and neighborhood radius of neurons as they accumulate information. This dynamic effectively stabilizes well-trained neurons, redirecting new learning to underutilized regions of the map. To further accommodate tasks of unknown complexity, we introduce a dynamic variant capable of adaptive grid expansion. We evaluate SatSOM on sequential versions of the FashionMNIST and KMNIST datasets, showing that it significantly outperforms existing SOM-based methods and approaches the retention capabilities of a k-nearest neighbors (kNN) baseline. Ablation studies confirm the critical role of the saturation mechanism. SatSOM offers a lightweight and interpretable solution for sequential learning and provides a foundation for implementing adaptive plasticity in complex architectures.

Community Detection with Higher-Order Edge Enhancement in Temporal Networks

Mon, 09 Feb 2026 00:00:00 GMT

Dynamic community detection often suffers from the instability of results, making consistent community identification across network snapshots critically important. However, the cut off between snapshots might lead to the loss of some higher-order structures, such as closed triangle motifs. In view of this, we examine the relationship between the missing higher-order structures and the instability, and find a positive correlation between higher-order loss ratio (HOLR) and temporal smoothing normalized mutual information (TSNMI). Based on this finding, we propose a new-brand higher-order edge enhancement (HOEE) algorithm, aiming to effectively reconstruct higher-order interactions to overcome the instability issue. The HOEE algorithm employs the higher-order activity potential (HAP) of nodes between consecutive snapshots to recover the loss of higher-order information by the transformation of the triangle motif, thus ensuring the temporal stability of dynamic communities. Experimental evaluation on synthetic and real-world dynamic networks demonstrates that HOEE outperforms state-of-the-art methods in community detection accuracy and significantly reduces community instability. Theoretical analysis confirms stability guarantees and characterizes graph property changes induced by HOEE. The HOEE algorithm effectively enhances temporal community stability through higher-order interaction reconstruction, providing a robust solution for dynamic network analysis.

MambaSC: A Feature Matching Method Using Mamba2 with Self and Cross-Attention for Multimodal Images

Mon, 09 Feb 2026 00:00:00 GMT

Multimodal image matching remains a challenging yet essential task in the field of computer vision. In recent years, detector-free methods have emerged as promising approaches, achieving high matching accuracy by leveraging global modeling capabilities. While transformer-based methods are effective, they often suffer from significant computational overhead, limiting their efficiency.To address this, we propose MambaSC, a novel framework that integrates Mamba with self-attention and cross-attention mechanisms to balance accuracy and efficiency. Specifically, MambaSC introduces the M2Backbone for efficient feature extraction and the MSC Module to enhance feature interaction and alignment.Extensive experiments across multiple multimodal image datasets demonstrate that MambaSC consistently outperforms state-of-the-art methods while maintaining computational efficiency, making it a compelling solution for complex multimodal image matching scenarios. Code is available at: https://github.com/LiaoYun0x0/MambaSC.

FRLog: Log Anomaly Detection Based on Three-Stage Training with Reft Fine-Tuning for Large Language Model

Mon, 09 Feb 2026 00:00:00 GMT

The goal of log anomaly detection is to accurately detect system anomalies from logs. Traditional methods often suffer from insufficient generalization and delayed anomaly detection when dealing with semantically diverse and loosely structured log data. As the complexity of the system increases, the size of the logs is getting larger and larger, and it has become impractical to analyze them manually. To this end, this paper proposes FRLog, a log anomaly detection framework based on large language model, which realizes contextualized semantic embeddings of log sequences by fusing BERT and LLaMA models, thereby enabling more accurate log anomaly detection. Meanwhile, the parameter fine-tuning strategy ReFT is introduced, and the semantic bootstrapping, representation alignment and global tuning process are optimized by a three-phase collaborative training mechanism. Experimental results on three typical log datasets, BGL, HDFS and Thunderbird, show that FRLog outperforms the existing mainstream methods in terms of F1, Precision and Recall, especially in complex scenarios, demonstrating stronger anomaly discrimination and sample efficiency, which verifies its superiority and robustness in the log anomaly detection task.

Artificial Intelligence in Music: A Bibliometric and Systematic Review of Creation, Performance, and Education

Mon, 09 Feb 2026 00:00:00 GMT

The integration of artificial intelligence (AI) into the music domain has catalyzed a transformative shift in how music is composed, performed, and taught. This paper introduces and frames the concept of music intelligence and employs bibliometric and systematic review methodologies to comprehensively analyze music intelligence. Music intelligence encompasses the development and application of intelligent systems that not only automate or enhance traditional musical tasks but also foster new modes of creativity, interaction, and pedagogy. Tracing the evolution from early rule-based systems to modern deep learning and multimodal models, we examine how AI is increasingly embedded in musical workflows. We highlight applications ranging from generative composition and expressive performance interpretation to real-time accompaniment and personalized education. By positioning AI as an active collaborator rather than a mere tool, this study underscores the need for collaborative efforts among computer scientists, musicians, educators, and cognitive scientists to fully realize the potential of intelligent music systems. Our biblio-metric analysis indicates an annual growth rate of 14.92%, with China, the US, and the UK contributing 52.9% of global research output. The findings reveal a rapidly expanding interdisciplinary field characterized by increasing international collaboration, methodological diversification, and a growing focus on human-AI co-creativity. However, persistent gaps remain in cultural inclusivity, interpretability, and ethical governance.

Opinion Evolution and Guidance Model Based on Social Networks and Information Networks

Mon, 09 Feb 2026 00:00:00 GMT

In human society, opinion evolution and guidance for opinion evolution are useful for maintaining social stability, business development, and so on. To tackle these issues, we propose an opinion evolution and guidance model based on social networks and information networks (namded EGSDCN) for the first time. Firstly, we develop an opinion evolution model based on the information networks and social networks (ISOE). Specifically, we first update the individual’s opinion by judging the quality of the information obtained by individual from the information network. Then, we filter the trusted neighbor set for individuals by quantifying individuals’ attributes and update individual’s opinion after weighting analysis of the trusted neighbor set. Finally, we conduct information exchange between the social and information networks. For guiding opinion evolution, we develop a group opinion guidance strategy based on individual stubbornness differences (termed PDGM). Specifically, we first divide the guided individuals into stubborn and non-stubborn groups. Then, for the non-stubborn group, a linear function model is used to intervene individual stubbornness. For the stubborn group, we propose the interest and opinion change functions to dynamically adjust individuals’ opinion. Extensive simulation experiments have been conducted and proved that our proposed model is effective.