Flexi-YOLO: A lightweight method for road crack detection in complex environments. by Jiexiang Yang, Renjie Tian, Zexing Zhou, Xingyue Tan, Pingyang He

“…Road crack detection is critical to global infrastructure maintenance and public safety, and complex background environments and nonlinear damage crack patterns challenge the need for real-time, efficient, and accurate detection.This paper proposes a lightweight yet robust Flexi-YOLO model based on the YOLOv8 algorithm. We designed Wise-IoU as the model's loss function to optimize the regression accuracy of its bounding boxes and enhance robustness to low-quality samples. …”
Get full text

Enhancing Consumer Decision-Making in Skincare: Implementation of the VIKOR Method for Product Recommendation Systems by Diah Arifah Prastiningtyas, Greta Septy Purwiantono, Febry Eka Purwiantono, Addin Aditya

“…By demonstrating the efficacy of the VIKOR method, this research paves the way for its future application in various industries, offering a replicable and adaptable model for improving decision processes in consumer goods selection across diverse markets. …”
Get full text

A Fault Detection Framework for Rotating Machinery with a Spectrogram and Convolutional Autoencoder by Hoyeon Lee, Jaehong Yu

“…In modern industrial systems, establishing the optimal maintenance policy for rotating machinery is essential to improve productivity and prevent catastrophic accidents. …”
Get full text

Intelligent Trust Evaluation Method for Underwater Sensor Networks Based on Fuzzy Clustering and Dynamic Weight Allocation by Zhaohui WANG, Guangjie HAN, Jiaxin DU, Chuan LIN, Lei WANG

“…Then, the unsupervised machine learning algorithm, namely fuzzy C-means clustering, was employed to enable adaptive node trust decision-making. …”
Get full text

Nondestructive freshness recognition of chicken breast meat based on deep learning by Rui Jian, Guangbo Li, Xie Jun, Guolong Shi

“…Experimental results show that in the improved algorithm, YOLOv8n_CA_DSC3 achieves suboptimal recall rate but optimal precision, average precision at IoU = 0.5, and average precision at IoU = 0.5:0.95. …”
Get full text

Implications of machine learning techniques for prediction of motor health disorders in Saudi Arabia by Ehab M. Almetwally, I. Elbatal, Mohammed Elgarhy, Amr R. Kamel

“…Decisions are made easier and social health care is improved with the help of this system because timely interventions are implemented, patient outcomes are improved, and resource allocation is optimized.…”
Get full text

Intra-day dispatch method via deep reinforcement learning based on pre-training and expert knowledge by Yanbo Chen, Qintao Du, Huayu Dong, Tao Huang, Jiahao Ma, Zitao Xu, Zhihao Wang

“…In recent years, due to high self-learning and self-optimization ability, reinforcement learning has emerged in the field of economic dispatch, which can solve model-free dynamic programming problems that cannot be effectively solved by traditional optimization methods. …”
Get full text

Short-Term Traffic Flow Prediction: A Method of Combined Deep Learnings by Chuanxiang Ren, Chunxu Chai, Changchang Yin, Haowei Ji, Xuezhen Cheng, Ge Gao, Heng Zhang

“…Then, the neuron number, loss function, optimization algorithm, and other parameters of the CDLP model are discussed and set through experiments. …”
Get full text

ADAM-DETR: an intelligent rice disease detection method based on adaptive multi-scale feature fusion by Hanyu Song, Xinyue Huang, Ziqiang Wang, Jianwei Hu, Huasheng Zhang, Hui Yang

“…The algorithm innovatively designs three core modules: the AdaptiveVision Network (AVN) backbone for enhanced feature extraction, the Dual-Domain Enhanced Transformer (DDET) module for spatiotemporal-frequency domain collaboration, and the Adaptive Multi-scale Feature Model (AMFM) for improved feature fusion. …”
Get full text

Rolling Bearing Fault Diagnosis Method Based on Fusion of CNN and CSSVM by LI Yunfeng, LAN Xiaosheng, SHEN Hongchang, XU Tongle

“…The results show that the combination of convolutional neural network to extract fault features and parameters to optimize the classification model structure of support vector machine can not only improve the diagnostic accuracy, but also have strong generalization performance.…”
Get full text

MAOOA‐Residual‐Attention‐BiConvLSTM: An Automated Deep Learning Framework for Global TEC Map Prediction by Haoran Wang, Haijun Liu, Jing Yuan, Huijun Le, Weifeng Shan, Liangchao Li

“…It also includes an optimization algorithm, MAOOA, for optimizing the hyper‐parameters of the model. …”
Get full text

Berth Allocation and Quay Crane Assignment Considering the Uncertain Maintenance Requirements by Siwei Li, Liying Song

“…To address this novel problem, we propose a proactive-reactive method that incorporates a reliability-based model into the Swarm Optimization with Differential Evolution (SWO-DE) algorithm. …”
Get full text

Integration of Artificial Neural Network in a IEEE 5 BUS System by T. L. Makosso, A. Almaktoof, K. Abo-Al-Ez

“…In the context of Artificial Neural Networks (ANNs), the Levenberg-Marquardt (LM) algorithm is an extensively utilized optimization method. …”
Get full text

Three-Dimensional Guidance Approach with Obstacle Avoidance against Maneuvering Targets by Zi-jie Jiang, Xiu-xia Yang, Yi Zhang, Cong Wang, Hao Yu

“…Secondly, to improve the guidance accuracy against the maneuvering target, an MPC controller with disturbance estimation is designed, which transforms the global optimization problem into a finite-horizon optimal control problem. …”
Get full text

Obstacle Avoidance Control of Autonomous Undersea Vehicle Based on DVFH+ in Ocean Current Environment by Zhongben ZHU, Jiahao ZHANG, Yifan XUE, Hongde QIN

“…Additionally, by considering the drift angle compensation in the real ocean current environment, the obstacle avoidance algorithm was optimized to improve its robustness and adaptability. …”
Get full text

Frequency Regulation Provided by Doubly Fed Induction Generator Based Variable-Speed Wind Turbines Using Inertial Emulation and Droop Control in Hybrid Wind–Diesel Power Systems by Muhammad Asad, José Ángel Sánchez-Fernández

“…Wind energy (WE) is the most adopted renewable energy source due to its technical readiness, competitive cost, and environmentally friendly characteristics. …”
Get full text

Future of Alzheimer's detection: Advancing diagnostic accuracy through the integration of qEEG and artificial intelligence by Sahar Rezaei, Farzan Asadirad, Alireza Motamedi, Mohammadsadegh Kamran, Farzaneh Parsa, Haniyeh Samimi, Parna Ghannadikhosh, Mahdi Zahmatyar, Seyed Ali Hosseinzadeh, Hossein Arabi

“…This review highlights the significant potential of AI-enhanced qEEG as a non-invasive, cost-effective tool for the diagnosis of AD in its prodromal and dementia stages, while also identifying areas requiring further research to optimize its clinical application. …”
Get full text

Classification of Complex Power Quality Disturbances Based on Lissajous Trajectory and Lightweight DenseNet by Xi Zhang, Jianyong Zheng, Fei Mei, Huiyu Miao

“…The experimental results demonstrate that, compared with current mainstream PQD classification methods, the proposed algorithm not only achieves superior disturbance classification accuracy and noise robustness but also significantly improves response speed in PQD classification tasks through its concise visualization conversion process and lightweight model design.…”
Get full text

AGW-YOLO-Based UAV Remote Sensing Approach for Monitoring Levee Cracks by HU Weibo, ZHOU Shaoliang, ZHAO Erfeng, ZHAO Xueqiang

“…The advanced WIoUv3 loss function further boosted the model's performance, achieving a mAP@0.5 of 84.5% and an F1 score of 83%, marking an approximate 3.4% improvement over the baseline, and showcasing a favorable balance between detection accuracy and model efficiency. …”
Get full text

Integration of Hash Encoding Technique with Machine Learning for Employee Turnover Prediction by Ahya Radiatul Kamila, Johanes Fernandes Andry, Francka Sakti Lee, Felliks F. Tampinongkol

“…It is part of the preprocessing stage, aiming to reduce memory usage, speed up data preprocessing, and improve model performance. After preprocessing is completed, the prediction model is trained using the Random Forest algorithm to predict employee turnover. …”
Get full text