<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0">
    <channel>
        <title>Journal of Artificial Intelligence and Soft Computing Research Feed</title>
        <link>https://sciendo.com/journal/JAISCR</link>
        <description>Sciendo RSS Feed for Journal of Artificial Intelligence and Soft Computing Research</description>
        <lastBuildDate>Sun, 10 May 2026 10:11:00 GMT</lastBuildDate>
        <docs>https://validator.w3.org/feed/docs/rss2.html</docs>
        <generator>https://github.com/jpmonette/feed</generator>
        <image>
            <title>Journal of Artificial Intelligence and Soft Computing Research Feed</title>
            <url>https://sciendo-parsed.s3.eu-central-1.amazonaws.com/65e70f12a96a436ce0118a95/cover-image.jpg</url>
            <link>https://sciendo.com/journal/JAISCR</link>
        </image>
        <copyright>All rights reserved 2026, SAN University</copyright>
        <item>
            <title><![CDATA[Inverse Meets Distillation: Heterogeneous Teacher–Assistant Dual-Path Learning for Unsupervised Defect Detection]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0014</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0014</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[An Improved Yolo Algorithm Based on Concise Decoupled Head for Real-Time Object Detection in Night Scenarios]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0011</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0011</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[A Visually Explainable Dynamic Similarity Network for Few-Shot Classification]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0012</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0012</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[SatSOM: Saturation Self-Organizing Maps for Continual Learning]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0015</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0015</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Phishing Fraud Identity Inference Based on Graph Gated Recurrent Neural Network]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0013</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0013</guid>
            <pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Opinion Evolution and Guidance Model Based on Social Networks and Information Networks]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0006</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0006</guid>
            <pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[MambaSC: A Feature Matching Method Using Mamba2 with Self and Cross-Attention for Multimodal Images]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0009</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0009</guid>
            <pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[FRLog: Log Anomaly Detection Based on Three-Stage Training with Reft Fine-Tuning for Large Language Model]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0007</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0007</guid>
            <pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Community Detection with Higher-Order Edge Enhancement in Temporal Networks]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0008</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0008</guid>
            <pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Artificial Intelligence in Music: A Bibliometric and Systematic Review of Creation, Performance, and Education]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0010</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0010</guid>
            <pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate>
            <description><![CDATA[

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.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Input-To-State Stable Sampled-Data Synchronisation Of Markovian Jump Lur’e Networks Under Actuator Saturation]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0004</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0004</guid>
            <pubDate>Fri, 26 Sep 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

This paper tackles the challenge of achieving Input-to-state stable (ISS) synchronization in actuator-saturated sampled-data control (SDC) networks for Markovian jump (MJ) Lur’e networks. We investigate the impacts of actuator saturation on system performance and stability, proposing a control strategy that ensures synchronization in the presence of external disturbances. Our analysis employs a Wirtinger-based integral inequality alongside a modified free matrix-based integral inequality (MFMBII), providing a framework for examining Lur’e networks. Initially, we create an MFMBII that combines the dynamics of MJ Lur’e networks and takes into consideration time-varying delays. Second, we formulate two sufficient conditions for the SDC design that ensure mean-square ISS error of specification for the hybrid closed-loop system. We do this by combining the MFMBII method with the Lyapunov-Krasovskii functional (LKF). Through a systematic methodology, we demonstrate that the proposed method maintains bounded state responses and converges to a common trajectory at an exponential rate. The results highlight the effectiveness of integrating ISS with SDC in managing complex dynamical networks. Finally, the proposed ISS method is validated through a numerical example, confirming its efficacy.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[S3diff: Semantic Fusion and Structure-Guided Global Generation from a Single Image with Diffusion Models]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0002</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0002</guid>
            <pubDate>Fri, 26 Sep 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Single-image generation models generate high-quality and diverse images by learning the internal distribution of patches within a single image, addressing the issue of data scarcity and attracting increasing attention. However, existing methods are unsatisfactory when dealing with images with global structures, such as animal images. To address this issue, we propose Semantic fusion and Structure-guided global generation from a Single image with Diffusion models (S3Diff). Specifically, during training, we employ a semantic extractor to extract high-level semantic features from training images and use the proposed semantic fusion block to fuse semantic features with image features, enhancing the model’s understanding of image semantics and improving the quality of the generated images. During sampling, we apply manifold constrained gradient based on image structure to enforce the generation path to regress to the manifold of the original image, preserving reasonable global structures. Extensive experiments on public datasets demonstrate the thorough exploration of hyperparameters and the rationality of key designs, with quantitative and qualitative comparisons against baseline methods and validating that our proposed method preserves reasonable semantic and structural relationships, can generate high-quality and diverse images, significantly improving the model’s global generation capabilities.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[A Hybridizing-Enhanced Quantum-Inspired Differential Evolution Algorithm with Multi-Strategy for Complicated Optimization]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0001</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0001</guid>
            <pubDate>Fri, 26 Sep 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Differential Evolution (DE) has been found to be inefficient and inaccurate for high-dimensional complex problems. Quantum-inspired Differential Evolution (QDE) possesses quantum computational properties, enabling effective handling of high-dimensional problems. However, QDE is plagued by issues of excessive mutation and poor convergence. Therefore, a hybrid enhanced Quantum-inspired Differential Evolution algorithm, termed QAHQDE, is proposed. Within QAHQDE, an improved chaotic strategy is designed. Non-repeating distributed quantum positions are generated, enhancing the diversity of initialized individuals. A quantum-adaptive mutation strategy is adopted to address the over-mutation problem inherent in QDE. The mutation degree is adaptively reduced, and convergence performance is thereby improved. A novel hybrid mutation strategy is constructed. Weighted mutation operators are combined with standard differential evolution. Local and global search capabilities are balanced, and convergence accuracy is enhanced. The performance of QAHQDE was evaluated against 38 algorithms using 48 benchmark functions from CEC2005, CEC2010, and CEC2013, across dimensions D=100, 500, 1000, and 3000. Experimental results demonstrate that QAHQDE outperforms QDE by at least three orders of magnitude. Superior convergence performance, higher convergence accuracy, and excellent stability are exhibited by QAHQDE on most functions.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Chestxgen: Dynamic Memory-Augmented Vision-Language Transformer with Context-Aware Gating for Radiology Report Generation]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0003</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0003</guid>
            <pubDate>Fri, 26 Sep 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Chest X-ray analysis is vital for clinical screening, diagnosis, and treatment planning. The increasing workload on radiologists calls for robust automated solutions to generate accurate and standardized reports. Conventional report generation models often struggle to detect rare and anomalous diseases, particularly when faced with imbalanced datasets, which can compromise diagnostic knowledge accuracy. To address these limitations, we propose ChestXGen, a novel multimodal framework for automated radiology report generation. Our model is based on a fully Transformer-based encoder-decoder architecture that integrates Memory Augmented Transformer (MAT) blocks with a Context-Aware Bi-Gate (CABG) mechanism. These enable the model to capture long-range dependencies, effectively fuse visual and textual features, and better handle underrepresented conditions. Visual features are extracted using a ResNet-101-V2 backbone and refined through a shared memory module that continuously reinforces cross-modal associations. This integrated approach facilitates the generation of comprehensive, accurate, and contextually coherent reports. Extensive evaluation on the large-scale MIMIC-CXR dataset, comprising 377,110 images and corresponding free-text reports demonstrate that ChestXGen outperforms previous models on BLEU-1, BLEU-2, BLEU-3, and METEOR metrics. The results demonstrate the efficacy of Transformer-based models in substantially reducing radiologists’ reporting burden while concurrently enhancing the precision and reliability of diagnostic interpretations.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Hypergraph Formalism for Fuzzy Signature-Based Robot Environment Representation]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2026-0005</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2026-0005</guid>
            <pubDate>Fri, 26 Sep 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

This paper introduces a pioneering approach to robot environment representation by integrating a novel hypergraph-based method for modeling fuzzy signatures with a quadtree-like structure for obstacle detection. By structuring fuzzy signatures through hypergraphs, we establish a robust framework that not only streamlines information representation but also simplifies the aggregation-based decision-making process. This synergy is applied to the domain of mobile robotics, where accurate and efficient environment representation is essential. Utilizing a quadtree-like structure for data organization, our technique systematically evaluates feature points against a set of fuzzy operations, determining the significance of obstacles and reconstructing the environmental model through the traversal of the quadtree-like structure. Furthermore, the hypergraph-based formalism sets the stage for a future transition to a tensor-based representation of fuzzy signatures, as envisioned in future work.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Stacking Large Language Models is All You Need: A Case Study on Phishing Url Detection]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2025-0017</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2025-0017</guid>
            <pubDate>Fri, 11 Jul 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Prompt-engineered Large Language Models (LLMs) have gained widespread adoption across various applications due to their ability to perform complex tasks without requiring additional training. Despite their impressive performance, there is considerable scope for improvement, particularly in addressing the limitations of individual models. One promising avenue is the use of ensemble learning strategies, which combine the strengths of multiple models to enhance overall performance. In this study, we investigate the effectiveness of stacking ensemble techniques for chat-based LLMs in text classification tasks, with a focus on phishing URL detection. Notably, we introduce and evaluate three stacking methods: (1) prompt-based stacking, which uses multiple prompts to generate diverse responses from a single LLM; (2) model-based stacking, which combines responses from multiple LLMs using a unified prompt; (3) hybrid stacking, which integrates the first two approaches by employing multiple prompts across different LLMs to generate responses. For each of these methods, we explore meta-learners of varying complexities, ranging from Logistic Regression to BERT. Additionally, we investigate the impact of including the input text as a feature for the meta-learner. Our results demonstrate that stacking ensembles consistently outperform individual models, achieving superior performance with minimal training and computational overhead. These findings highlight the potential of stacking ensembles in mitigating the limitations of existing methods and significantly enhancing the efficiency and accuracy of chat-based LLMs for text classification tasks.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[NEST: A Novel Ensemble Method for Estimating Spatio-Temporal Gait Parameters Using Inertial Measurement Units]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2025-0016</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2025-0016</guid>
            <pubDate>Fri, 11 Jul 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Accurately estimating spatio-temporal gait parameters such as stride height, stride length, stance time, swing time, and stride speed, is crucial for sports medicine and preventive healthcare. To enable users to measure their spatio-temporal gait parameters in real-life scenarios, several existing studies propose to install one inertial measurement unit (IMU) in each shoe, and design methods to estimate these gait parameters according to the readings of IMUs. Therefore, this paper proposes a novel ensemble method, NEST (standing for Novel Ensemble method for Spatio-Temporal gait parameters measurement), for the multi-task measurement of the aforementioned five spatio-temporal gait parameters. NEST consists of a K-Nearest Neighbor (KNN) regressor branch and a deep learning branch. The KNN regressor branch provides initial estimates, allowing other neural networks to learn to reduce the residual between these estimates and the ground truths. This helps NEST rapidly identify a good optimization direction during the early stage of fine-tuning and expedite convergence speed. The deep learning branch facilitates information sharing among multiple task-specific representations through fully-connected layers, effectively preserving the interdependencies among gait parameters. Several experiments are conducted to evaluate the performance of NEST and other prior methods. Compared to prior handcrafted-statistics-based methods, NEST demonstrates over 65.1% improvement in RMSE (Root-Mean-Square Error) when predicting spatial parameters.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[An Evolutionary Neural Architecture Search Method Accelerated by Multi-Fidelity Evaluation and Genetic Decision Controller]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2025-0020</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2025-0020</guid>
            <pubDate>Fri, 11 Jul 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Deep neural networks (DNNs) are now widely used in numerous fields. However, manually design-ing DNNs is labor-intensive and requires expert knowledge. Evolutionary neural architecture search (ENAS) is an efficient method. Nevertheless, ENAS requires full-epoch training for each candidate architecture to determine fitness values, leading to high computational costs. To accelerate the search process and reduce resource consumption, this paper proposes MFGENAS, an accelerated ENAS method. MFGENAS is implemented within the NSGA-II framework and employs two key acceleration strategies: multi-fidelity evaluation and a genetic decision controller. We demonstrate through experi-mental analysis that classification-based prediction is significantly more effective than regression-based prediction in estimating architecture performance. To reduce the need for expensive evaluations, we introduce a genetic decision controller to evaluate the quality of generated offspring. This process is treated as a classification task: if the controller predicts that the offspring will outperform the parent, the offspring is retained. For this purpose, we adopt a kernel extreme learning machine optimized by an improved polar lights optimizer as the genetic decision controller. Comprehensive experiments vali-date MFGENAS’s performance. On the CIFAR-10 dataset, MFGENAS discovers an architecture with an error rate of 2.39% using only 0.3 GPU days. In contrast, the classical AE-CNN requires 27 GPU days to achieve an architecture with a higher error rate of 4.30%. On the CIFAR-100 dataset, MFGENAS discovers an architecture with an error rate of 16.42% in just 0.3 GPU days, whereas E2EPP requires 8.5 GPU days to reach an error rate of 22.02%.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[A New Version of the Golden Eagle Optimizer Algorithm And Its Application For Solving A Trio-Objective Skillful Team Formation Problem In A Social Network]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2025-0018</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2025-0018</guid>
            <pubDate>Fri, 11 Jul 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

Metaheuristic methods have demonstrated their utility in tackling global optimization problems with and without constraints. However, existing state-of-the-art (SOTA) algorithms often suffer from limitations such as premature convergence, inefficient exploration-exploitation balance, and poor adaptability to complex discrete optimization problems like Team Formation (TF). The Golden Eagle Optimizer (GEO) algorithm is a promising metaheuristic that addresses some of these challenges by effectively managing its hunting spiral motion using two control parameters: cruise (exploration) and attack (exploitation). Despite its strengths, the standard GEO algorithm requires modifications to handle the discrete and multi-objective nature of the TF problem effectively. This paper proposes an amended version of GEO, called AGEO, which integrates specialized operators to enhance its performance in TF scenarios. A skillful TF aims to form teams of experts with complementary skills in social networks (SN) while optimizing multiple objectives, including minimizing communication costs, maximizing the similarity score between team members, and achieving minimal team cardinality. AGEO preserves GEO’s powerful exploitation and exploration mechanisms while introducing tailored operator strategies to overcome the challenges inherent in TF. The AGEO undergoes testing on several well-established benchmark datasets, including Universiti Malaysia Pahang (UMP), Internet Movie Database (IMDB), Association for Computing Machinery (ACM), and Database Systems &amp; Logic Programming (DBLP). Additionally, a comparative study against SOTA metaheuristic algorithms such as Particle Swarm Optimization (PSO), Butterfly Optimization Algorithm (BOA), Crow Search Algorithm (CSA), and Jaya Algorithm demonstrates AGEO’s superior performance in forming highly optimized teams with the least communication cost, lowest team cardinality, and highest similarity score.
]]></description>
            <category>ARTICLE</category>
        </item>
        <item>
            <title><![CDATA[Hybrid Coyote Optimization with Differential Evolution and its Application to the Estimation of Solar Photovoltaic Cell Parameters]]></title>
            <link>https://sciendo.com/article/10.2478/jaiscr-2025-0019</link>
            <guid>https://sciendo.com/article/10.2478/jaiscr-2025-0019</guid>
            <pubDate>Fri, 11 Jul 2025 00:00:00 GMT</pubDate>
            <description><![CDATA[

In order to obtain a Coyote optimization algorithm (COA) is with universal applicability, this paper proposes a novel hybrid algorithm based on COA and Deferential Evolution (DE), named DECOA. Firstly, Global optimum guidance growth scenario of alpha coyotes is introduced into the growth procedure of the alpha coyote of each group, which enables the scenario to approach the global optimum result faster. Secondly, a Gaussian global growth operator is randomly adopted in the growth procedure of ordinary coyotes to make better the global search capacity while preserving the vigorous local search capacity. Thirdly, in order to further improve the social adaptability of coyotes after they grow up, differential expulsion and admission strategy is integrated. Finally, the numbers of the groups are dynamically modified to balance exploitation and exploration. A large number of tests on the benchmark functions from CEC-2017 and CEC-2013 test sets verify the proposed strategy. Especially, compared to many state-of-the-art algorithms, the proposed strategy ranks first 15 times among 29 benchmark functions of CEC-2017 and the average running speed has reached 2.29s. It is extremely important to obtain the PV cell parameters effectively, because the required data to model PV cells will be not provided by the manufacturers. Hence, DECOA is further applied to the scene of parameter estimation of photovoltaic solar cells and modules and the results still indicate that it surpasses the other advanced comparison scenarios.
]]></description>
            <category>ARTICLE</category>
        </item>
    </channel>
</rss>