An enhanced GhostNet model for emotion recognition: leveraging efficient feature extraction and attention mechanisms by Jie Sun, Tianwen Xu, Yao Yao

“…The EGT model integrates GhostNet's efficient feature extraction, the Transformer's ability to capture global context, and a dual attention mechanism to selectively enhance critical features. …”
Get full text

Embedded feature fusion for multi-label criteria selection via local search strategy and particle swarm optimization by Suhua Chen, Xu Fang, Feng Zhai, Li Wang, Lin Lv

“…Despite its importance, feature selection remains a complex issue without straightforward solutions, and various approaches using AI and evolutionary algorithms have been proposed to tackle it. …”
Get full text

Fault Detection in Gearboxes Using Fisher Criterion and Adaptive Neuro-Fuzzy Inference by Houssem Habbouche, Tarak Benkedjouh, Yassine Amirat, Mohamed Benbouzid

“…Consequently, deploying expert methods for fault detection and diagnosis is crucial to ensuring the reliability and efficiency of these systems. …”
Get full text

Research on herd sheep facial recognition based on multi-dimensional feature information fusion technology in complex environment by Fu Zhang, Fu Zhang, Xiaopeng Zhao, Shunqing Wang, Yubo Qiu, Sanling Fu, Yakun Zhang

Get full text

Creating and Validating Hybrid Large-Scale, Multi-Modal Traffic Simulations for Efficient Transport Planning by Fabian Schuhmann, Ngoc An Nguyen, Jörg Schweizer, Wei-Chieh Huang, Markus Lienkamp

“…Mobility digital twins (MDTs), which utilize multi-modal microscopic (micro) traffic simulations and an activity-based demand generation, are envisioned as flexible and reliable planning tools for addressing today’s increasingly complex and diverse transport scenarios. Hybrid models may become a resource-efficient solution for building MDTs by creating large-scale, mesoscopic (meso) traffic simulations, using simplified, queue-based network-link models, in combination with more detailed local micro-traffic simulations focused on areas of interest. …”
Get full text

Efficient Method of Road Outlier Recognition Using Deep Learning Coupled with Data Augmentation Approach by Sarfaraz Natha, Fareed Ahmed Jokhio, Muhammad Shafique, Naeem Ahmed, Danish Munir Arain

Get full text

IT Outsourcing Vendor Selection for Digital Transformation Projects in Public Sector using Interval-Valued Spherical Fuzzy AHP by Murat Levent Demircan

“…Consequently, determining the selection criteria of the outsourcing companies that will take part in digital transformation projects in the public sector and the selection methodology to be applied is of great importance. …”
Get full text

Engineered Magnetic-Functionalized Carbon Xerogels for Sustainable Arsenic Removal: Bridging Adsorption Efficiency with Regenerability by Sasirot Khamkure, Prócoro Gamero-Melo, Audberto Reyes-Rosas, Alejandro Zermeño-González, José Luis Álvarez-Cruz, Elim Albiter Escobar, Gabriela Eleonora Moeller-Chávez, Victoria Bustos-Terrones

“…Synergistic effects of magnetite incorporation, tailored pyrolysis, and H₂O₂ modification significantly improved arsenic selectivity and capacity in complex matrices, while enabling magnetic recovery.…”
Get full text

Measuring and Improving the Efficiency of Python Code Generated by LLMs Using CoT Prompting and Fine-Tuning by Ramya Jonnala, Jeong Yang, Young Lee, Gongbo Liang, Zechun Cao

“…Based on its promising performance with CoT prompting, we selected the GPT-4o-Mini model for subsequent fine-tuning, aiming to further enhance both its computational efficiency and accuracy. …”
Get full text

Unconventional phase metal heteronanostructures with tunable exposed interface for efficient tandem nitrate electroreduction to ammonia by Yangbo Ma, Liang Guo, Liang Chang, Weihua Guo, Tao Zhou, Fengkun Hao, Wenda Su, Jingwen Zhou, Guozhi Wang, Mingzheng Shao, Jihan Yu, Jinwen Yin, Yunhao Wang, Fu Liu, An Zhang, Kun Qian, Jie Wang, Xiuyun Zhang, Weijia Zhou, Shengqi Chu, Chongyi Ling, Lin Gan, Zhengxiao Guo, Zhanxi Fan

Get full text

A novel hybrid MCDM framework combining TOPSIS, PROMETHEE II, and VIKOR for peach drying method selection by Burak Gülmez

“…The selection of optimal drying technologies for peach processing presents a complex decision-making challenge due to multiple conflicting criteria. …”
Get full text

Crayfish optimization based pixel selection using block scrambling based encryption for secure cloud computing environment by Vikas K. Soman, V. Natarajan

“…The Crayfish Optimization algorithm is used to select the most suitable pixels for steganography, ensuring that the secret image is embedded in a way that minimizes detection. …”
Get full text

Performance validation of microchannel heat sinks based on single/multiobjective topology optimization and manufactured by selective laser melting by Guangzhao Yang, Mingxuan Cao, Pingnan Huang, Linlin Pan, Xin Zhong, Liang Yang, Weiwei Guo, Matthew M.F. Yuen, Huijun Li

“…This study confirms that the P3D-MOTO provides efficient and energy-saving thermal management solutions, while emphasizing that the integration of topology optimization with SLM can create complex geometries, thereby enhancing thermal performance.…”
Get full text

ITD-YOLO: An Improved YOLO Model for Impurities in Premium Green Tea Detection by Zezhong Ding, Yanfang Li, Bin Hu, Zhiwei Chen, Houzhen Jia, Yali Shi, Xingmin Zhang, Xuesong Zhu, Wenjie Feng, Chunwang Dong

“…To solve this technical problem in the industry, this article proposes a lightweight algorithm for detecting and sorting impurities in premium green tea in order to improve sorting efficiency and reduce labor intensity. …”
Get full text

Outlier detection algorithm based on fast density peak clustering outlier factor by Zhongping ZHANG, Sen LI, Weixiong LIU, Shuxia LIU

“…For the problem that peak density clustering algorithm requires human set parameters and high time complexity, an outlier detection algorithm based on fast density peak clustering outlier factor was proposed.Firstly, k nearest neighbors algorithm was used to replace the density peak of density estimate, which adopted the KD-Tree index data structure calculation of k close neighbors of data objects, and then the way of the product of density and distance was adopted to automatic selection of clustering centers.In addition, the centripetal relative distance and fast density peak clustering outliers were defined to describe the degree of outliers of data objects.Experiments on artificial data sets and real data sets were carried out to verify the algorithm, and compared with some classical and novel algorithms.The validity and time efficiency of the proposed algorithm are verified.…”
Get full text

Outlier detection algorithm based on fast density peak clustering outlier factor by Zhongping ZHANG, Sen LI, Weixiong LIU, Shuxia LIU

“…For the problem that peak density clustering algorithm requires human set parameters and high time complexity, an outlier detection algorithm based on fast density peak clustering outlier factor was proposed.Firstly, k nearest neighbors algorithm was used to replace the density peak of density estimate, which adopted the KD-Tree index data structure calculation of k close neighbors of data objects, and then the way of the product of density and distance was adopted to automatic selection of clustering centers.In addition, the centripetal relative distance and fast density peak clustering outliers were defined to describe the degree of outliers of data objects.Experiments on artificial data sets and real data sets were carried out to verify the algorithm, and compared with some classical and novel algorithms.The validity and time efficiency of the proposed algorithm are verified.…”
Get full text

Enhanced anomaly traffic detection framework using BiGAN and contrastive learning by Haoran Yu, Wenchuan Yang, Baojiang Cui, Runqi Sui, Xuedong Wu

“…However, existing methods face many challenges when processing complex high-dimensional traffic data. Especially in dealing with redundant features, data sparsity and nonlinear features, traditional methods often suffer from high computational complexity and low detection efficiency. …”
Get full text

Classifying IoT Botnet Attacks With Kolmogorov-Arnold Networks: A Comparative Analysis of Architectural Variations by Phuc Hao do, Tran Duc Le, Truong Duy Dinh, van Dai Pham

“…The Original-KAN variant, in particular, excelled in capturing complex, non-linear patterns inherent in IoT botnet traffic, achieving higher accuracy and faster convergence rates. …”
Get full text

Optimized conductor selection and phase balancing in unbalanced distribution networks: Economic optimization via the vortex search algorithm by Brandon Cortés-Caicedo, Jhony Andrés Guzmán-Henao, Oscar Danilo Montoya, Luis Fernando Grisales-Noreña, Rubén Iván Bolaños

“…In this vein, optimal conductor size selection and phase balancing are among the most common strategies for improving these indicators, which involves dealing with complex optimization problems. …”
Get full text

Principles of physical factor selection in the early postoperative period of breast cancer treatment: a randomized controlled study by Inna S. Evstigneeva

“…To develop algorithms for selecting physical factors depending on the clinical and functional state of patients after radical surgical treatment of breast cancer (BC) in the early postoperative period. …”
Get full text