A novel edge-feature attention fusion framework for underwater image enhancement by Shuai Shen, Haoyi Wang, Weitao Chen, Pingkang Wang, Qianyong Liang, Xuwen Qin, Xuwen Qin

“…Experimental results demonstrate that CUG-UIEF achieves an average peak signal-to-noise ratio of 24.49 dB, an 8.41% improvement over six mainstream algorithms, and a structural similarity index of 0.92, a 1.09% increase. …”
Get full text

Bridging the Gap: A Review of Machine Learning in Water Quality Control by Herlina Abdul Rahim, Nur Athirah Syafiqah Noramli, Indrabayu

“…ML-driven solutions, including LSTM networks and random forest models, enable real-time anomaly detection (e.g., 85% accurate algal bloom prediction 7 days in advance) and operational optimization (15% cost reduction in wastewater treatment). …”
Get full text

AI-based Assessment of Risk Factors for Coronary Heart Disease in Patients With Diabetes Mellitus and Construction of a Prediction Model for a Treatment Regimen by Zhen Gao, Qiyuan Bai, Mingyu Wei, Hao Chen, Yan Yan, Jiahao Mao, Xiangzhi Kong, Yang Yu

“…The processed data were then input into five different algorithms for model construction. The performance of each model was rigorously evaluated using five specific evaluation indicators. …”
Get full text

Development of a machine learning prognostic model for early prediction of scrub typhus progression at hospital admission based on clinical and laboratory features by Youguang Lu, Zixu Wang, Junhu Wang, Yingqing Mao, Chuanshen Jiang, Jinpiao Wu, Haizhou Liu, Haiming Yi, Chao Chen, Wei Guo, Liguan Liu, Yong Qi

“…Eighteen objective clinical and laboratory features collected at admission were screened using various feature selection algorithms, and used to construct models based on six machine learning algorithms.Results The model based on Gradient Boosting Decision Tree using 14 features screened by Recursive Feature Elimination was evaluated as the optimal one. …”
Get full text

CHDPL-Net: a lightweight network for Chinese herbal decoction pieces detection by Chuhe Lin, Zhijun Xie, Xing Jin, Hangjuan Lin, Renguang Shan

“…Additionally, a newly designed downsampling module, RDown, replaces conventional downsampling methods to reduce computational overhead, while the adopted upsampling module, DySample, significantly enhances the recovery of detailed features. To further improve lightweight performance, we apply GhostConv to optimize the SPPF and C2F modules and incorporate a novel attention mechanism, EHA, which makes the model more sensitive to color and texture information, mitigating the performance degradation caused by lightweight design. …”
Get full text

Modeling Techniques and Boundary Conditions in Abdominal Aortic Aneurysm Analysis: Latest Developments in Simulation and Integration of Machine Learning and Data-Driven Approaches by Burcu Ramazanli, Oyku Yagmur, Efe Cesur Sarioglu, Huseyin Enes Salman

“…Research on abdominal aortic aneurysms (AAAs) primarily focuses on developing a clear understanding of the initiation, progression, and treatment of AAA through improved model accuracy. High-fidelity hemodynamic and biomechanical predictions are essential for clinicians to optimize preoperative planning and minimize therapeutic risks. …”
Get full text

Remote Sensing Change Detection by Pyramid Sequential Processing With Mamba by Jiancong Ma, Bo Li, Hanxi Li, Siying Meng, Ruitao Lu, Shaohui Mei

“…These enhancements not only accelerate training but also improve the model’s generalization capability. …”
Get full text

A systematic review of deep learning applications in database query execution by Bogdan Milicevic, Zoran Babovic

“…We categorize these approaches into three groups based on how such models are applied: improving performance of index structures and consequently data manipulation algorithms, query optimization tasks, and externally controlling query optimizers through parameter tuning. …”
Get full text

Design of OFDM-IM system based on IRS-assisted by Mengmeng ZHAO, Liming HE, Fangfang LIU

“…Index modulation (IM) and intelligent reflecting surface (IRS) are emerging mobile communication technologies.In order to improve the reliability of traditional orthogonal frequency division multiplexing (OFDM) system, an orthogonal frequency division multiplexing with index modulation (OFDM-IM) system based on IRS-assisted was designed.Firstly, the OFDM-IM system was designed by using spatial modulation and frequency domain modulation to increase the Euclidean distance between subcarriers.Then, by establishing an equivalent circuit model, a practical IRS model was obtained.Finally, an alternating optimization algorithm was used to optimize the active transmission power of the access point (AP) and passive beamforming of the IRS jointly.The simulation results show that compared to the benchmark scheme, the symbol error rate (SER) or bit error rate (BER) of the OFDM-IM system based on IRS-assisted can be reduced by 60%～90%.Especially in the case of high signal-to-noise ratio, the SER or BER of the system can reach 1.0×10^-6, which indicates that the introduction of IM and IRS technologies has optimized the link transmission quality of end-to-end communication system.In addition, based on the IRS-assisted OFDM-IM system as the standard, simulations are conducted to demonstrate the impact of various parameters from the IRS model and IM.It concludes that the parameters in the system should be selected reasonably according to channel state information (CSI).…”
Get full text

Green Video Transcoding in Cloud Environments Using Kubernetes: A Framework With Dynamic Renewable Energy Allocation and Priority Scheduling by B. M. Beena, Prashanth Cheluvasai Ranga, A. Vinitha Chowdary, Rohan Gamidi, M. Hemasri, Tejaswi Muppala

“…The research addresses these challenges by developing a green, energy-aware video transcoding system that predicts energy availability from renewable sources (solar and wind) using machine learning techniques and optimizes tasks allocation. The system utilizes a Kubernetes-managed backend to dynamically scale resources for FFmpeg-based transcoding while prioritizing renewable energy, minimizing grid usage utilizing the advanced machine learning models, including Random Forest, XGBoost, and CatBoost, predict energy production and guide task assignments. …”
Get full text

A machine learning-based depression risk prediction model for healthy middle-aged and older adult people based on data from the China health and aging tracking study by Fang Xia, Jie Ren, Linlin Liu, Yanyin Cui, Yufang He

“…BackgroundPredicting depression risk in adults is critical for timely interventions to improve quality of life. To develop a scientific basis for depression prevention, machine learning models based on longitudinal data that can assess depression risk are necessary.MethodsData from 2,331 healthy older adults who participated in the China Health and Retirement Longitudinal Study (CHARLS) from 2018 to 2020 were used to develop and validate the predictive model. …”
Get full text

A Novel Model with GA Evolving FWNN for Effluent Quality and Biogas Production Forecast in a Full-Scale Anaerobic Wastewater Treatment Process by Zehua Huang, Renren Wu, XiaoHui Yi, Hongbin Liu, Jiannan Cai, Guoqiang Niu, Mingzhi Huang, Guangguo Ying

“…The analysis results indicate that the FWNN with the optimal algorithm had a high speed of convergence and good quality of prediction, and the FWNN model was more advantageous than the traditional intelligent coupling models (NN, WNN, and FNN) in prediction accuracy and robustness. …”
Get full text

Predicting postoperative neurological outcomes of degenerative cervical myelopathy based on machine learning by Shuai Zhou, Shuai Zhou, Shuai Zhou, Shuai Zhou, Zexiang Liu, Zexiang Liu, Zexiang Liu, Haoge Huang, Haoge Huang, Haoge Huang, Hanxu Xi, Xiao Fan, Xiao Fan, Xiao Fan, Yanbin Zhao, Yanbin Zhao, Yanbin Zhao, Xin Chen, Xin Chen, Xin Chen, Yinze Diao, Yinze Diao, Yinze Diao, Yu Sun, Yu Sun, Yu Sun, Hong Ji, Feifei Zhou, Feifei Zhou, Feifei Zhou

“…After training and optimizing multiple ML algorithms, we generated a model with the highest area under the receiver operating characteristic curve (AUROC) to predict short-term outcomes following DCM surgery. …”
Get full text

YOLOv8n-WSE-Pest: A Lightweight Deep Learning Model Based on YOLOv8n for Pest Identification in Tea Gardens by Hongxu Li, Wenxia Yuan, Yuxin Xia, Zejun Wang, Junjie He, Qiaomei Wang, Shihao Zhang, Limei Li, Fang Yang, Baijuan Wang

“…To enable the intelligent monitoring of pests within tea plantations, this study introduces a novel image recognition algorithm, designated as YOLOv8n-WSE-pest. Taking into account the pest image data collected from organic tea gardens in Yunnan, this study utilizes the YOLOv8n network as a foundation and optimizes the original loss function using WIoU-v3 to achieve dynamic gradient allocation and improve the prediction accuracy. …”
Get full text

Dynamic Reporting Nodes Selection Method for Network Awareness Based on Active–Passive Integrated Network Telemetry in LEO Satellite Networks by Hang Di, Tao Dong, Zhihui Liu, Shuotong Wei, Qiwei Zhang, Dingyun Zhang

“…Specifically, an APINT model is built which can dynamically select the optimal reporting node and reduce awareness time through the bidirectional aggregation of telemetry packets along the service path. …”
Get full text

A Workflow for Integrated Geological Modeling for Shale Gas Reservoirs: A Case Study of the Fuling Shale Gas Reservoir in the Sichuan Basin, China by Xiaofei Shang, Huawei Zhao, Shengxiang Long, Taizhong Duan

“…The selection and optimization of modeling methods, the innovation and development of modeling algorithms, and the evaluation techniques for model uncertainty are areas where breakthroughs may be possible in the geological modeling of shale gas reservoirs. …”
Get full text

Performance Testing and Analysis of a New GNSS Spoofing Detection Method in Different Spoofing Scenarios by Li Junzhi, Wu Haitao, Gao Jinfeng, Liu Fang, Zhang Yu, Li Gangqiang, He Yu

“…To overcome these shortcomings, this study extracts multi-dimensional parameters from observational data. By improving the RF algorithm and introducing a weighted voting mechanism to optimize the classification decision process, a high-precision classification model is constructed. …”
Get full text

Enhancing grid-connected PV-EV charging station performance through a real-time dynamic power management using model predictive control by Aziz Watil, Hamid Chojaa

“…It also provides flexibility in BEV power sizing, optimizing the use of power electronics converters to reduce costs and complexity. …”
Get full text

Fatigue-Aware Sub-Second Combinatorial Auctions for Dynamic Cycle Allocation in Human–Robot Collaborative Assembly by Claudio Urrea

Get full text

Multi-objective trajectory planning for connected and autonomous vehicles in mixed traffic flow by Hui Li, Yunfei Ge, Yahui Guo, Yu Guan, Xu Zhang

“…Therefore, this paper developed a multi-objective trajectory planning model utilizing the TD3 algorithm. Here, we design the state space, action space, and reward function, where the state space encompasses variables such as speed, relative speed, distance to the stop line, relative position, phase state, and remaining phase duration, and the action space outputs optimal acceleration and deceleration. …”
Get full text