Comprehensive Assessment of Indoor Thermal in Vernacular Building Using Machine Learning Model with GAN-Based Data Imputation: A Case of Aceh Region, Indonesia by Muslimsyah Muslimsyah, Safwan Safwan, Andri Novandri

“…The prediction model adopts a hybrid framework that integrates Multiple Linear Regression (MLR) and Artificial Neural Networks (ANNs), with both models optimized using Support Vector Regression (SVR) to better capture the nonlinear dynamics between inputs and outputs. …”
Get full text

Leveraging advanced deep learning and machine learning approaches for snow depth prediction using remote sensing and ground data by Haytam Elyoussfi, Abdelghani Boudhar, Salwa Belaqziz, Mostafa Bousbaa, Karima Nifa, Bouchra Bargam, Abdelghani Chehbouni

“…The models evaluated include two ML approaches: Support Vector Regression (SVR) and eXtreme Gradient Boosting (XGBoost) and four DL models: 1-Dimensional Convolutional Neural Network (1D-CNN), Long Short-Term Memory Networks (LSTM), Gated Recurrent Unit (GRU), and Bi-directional Long Short-Term Memory Network (Bi-LSTM). …”
Get full text

An intelligent partial charging navigation strategy for electric vehicles by Jinsheng Xiao, Bang Sun, Xun Gao, Hua Yang, Liyuan Wang

“…Employing an improved genetic algorithm for route planning, our method demonstrates a dual advantage – reducing computational complexity and saving an average of 15% in travel time. Experimental results over a 400 km2 traffic road network validate the efficiency of our approach, outperforming existing methods facing similar challenges.…”
Get full text

Document Relevance Filtering by Natural Language Processing and Machine Learning: A Multidisciplinary Case Study of Patents by Raj Bridgelall

“…These results offer a practical framework for optimizing document relevance filtering, enabling researchers and practitioners to efficiently manage large datasets and enhance innovation.…”
Get full text

Comparative Analysis of Train Departure Strategies in a Container Shipment by Alessia Giulianetti, Marco Gotelli, Anna Sciomachen

“…The number of departing trains, cancelled trains, and trains departing with load percentages below 70% is studied. Average loads per train and estimated delays are also analyzed. …”
Get full text

Study on incentive mechanism of reward and punishment on work efficiency of PCB welder based on recurrence quantification analysis and electroencephalogram signals by Zhang Qian, Mingyue Guo, Fuwang Wang

“…The accuracy of the twin support vector machine (TWSVM) reaches 98.71%, which is 0.79% and 14.37% higher than existing EEG-based incentive evaluation methods, such as the phase-locking value combined with convolutional neural network (accuracy: 97.92%) and spectral power features (accuracy: 84.34%). …”
Get full text

Intelligent library shelf management system for open-access environments: A CNN-based approach with enhanced image recognition and disorder detection by Xueqi Zhang

“…To address this issue, an improved library shelf management system based on the convolutional neural network algorithm has been proposed. The new system adopts an optimized convolutional kernel design to improve the accuracy of feature extraction. …”
Get full text

De novo assembly of the common bean transcriptome using short reads for the discovery of drought-responsive genes. by Jing Wu, Lanfen Wang, Long Li, Shumin Wang

“…However, the gene network that mediates plant responses to drought stress remains largely unknown in this species. …”
Get full text

Design and Experimental Study on the Online Monitoring System for Corrosion Environment of the Main Cable in a Trans-Strait Suspension Bridge by ZHANG Yi, ZHOU Yuyuan, ZHAO Mengyao, LIU Xinyi, MA Xiaoze, DONG Zehua

“…The main cable of a suspension bridge is the lifeline of the bridge.The corrosion or broken wires of the main cable in the suspension bridge are directly related to the operation safety and service life of the suspension bridge.In this study， a total of 20 corrosion monitoring sensors were installed in the main cable sheath of the Lingdingyang trans-strait Suspension Bridge in the Shenzhen-Zhongshan Channel using precise resistance corrosion monitoring probes，low-power data collectors，temperature compensation，and wireless networking technology.The probes utilized the bare steel wires of the main cable as the testing elements to monitor in real-time the corrosion rate and amount of corrosion of the high-strength steel wires in the sheath， establishing a distributed wireless monitoring network for main cable corrosion.Through five months of corrosion monitoring tests，it was found that the corrosion rate of the downstream main cable was significantly higher than that of the upstream section，with the most severe corrosion occurring at the lowest span of the main cable，where the average corrosion rate reached 147.91 μm/a.This indicated that， due to the failure to activate the dehumidification and desalination device during the early stages of bridge construction，the residual salt particles and moisture inside the main cable caused severe corrosion.Based on the visual online monitoring of corrosion data inside the main cable， guidance was provided for optimizing the protection scheme of the main cable， ensuring the safe operation of large suspension bridges.…”
Get full text

Defect Detection Method of Carbon Fiber Unidirectional Band Prepreg Based on Enhanced YOLOv8s by Weipeng Su, Mei Sang, Yutong Liu, Xueming Wang

“…The proposed model respectively integrates two attention mechanisms, a Global Attention Mechanism (GAM) and a Deformable Large Kernel Attention (DLKA) Mechanism, into the architecture of YOLOv8s, which is a lightweight version of YOLO optimized for speed. The attention mechanisms are inserted between the backbone network and the detection head, respectively, to enhance feature extraction before target localization. …”
Get full text

Improving Medical Image Quality Using a Super-Resolution Technique with Attention Mechanism by Dong Yun Lee, Jang Yeop Kim, Soo Young Cho

“…Channel attention uses global average pooling and fully connected layers to enhance high-frequency features within channels. …”
Get full text

Evolution of public broadcasting: TeleJurnal’s viewership trends and strategic implications for business sustainability by Săseanu Ramona, Stanomir Ruxandra, Bădulescu Andreea-Alexandra

“…This research examines the viewership trends of TeleJurnal, the network’s main flagship news program, utilizing data from 2018 to 2022, and projects forecasts for 2023–2025. …”
Get full text

A Fine-Grained Aircraft Target Recognition Algorithm for Remote Sensing Images Based on YOLOV8 by Xiao-Nan Jiang, Xiang-Qian Niu, Fan-Lu Wu, Yao Fu, He Bao, Yan-Chao Fan, Yu Zhang, Jun-Yan Pei

“…Initially, this article designs a local detail feature module to tackle the problem of information loss in shallow networks. This module enhances the capture of semantic information while extracting shallow features, thereby preserving more fine-grained features and improving the network's feature extraction capability. …”
Get full text

BESW-YOLO: A Lightweight SAR Image Detection Model Based on YOLOv8n for Complex Scenarios by Xiao Tang, Kun Cao, Yunzhi Xia, Enkun Cui, Weining Zhao, Qiong Chen

“…First, we introduce a novel lightweight feature pyramid network, bidirectional and multiscale attention feature pyramid network, which effectively enhances the fusion of features across different scales. …”
Get full text

New Perspectives on the Causes of Stagnation and Decline in the Sharing Economy: Application of the Hybrid Multi-Attribute Decision-Making Method by Hsu-Hua Lee, Chien-Hua Chen, Ling-Ya Kao, Wen-Tsung Wu, Chu-Hung Liu

“…The DEMATEL technique is used to construct the Influential Network Relationship Map (INRM), while the ANP concept is incorporated to develop the D&ANP model. …”
Get full text

Low-Illumination Parking Scenario Detection Based on Image Adaptive Enhancement by Xixi Xu, Meiqi Zhang, Hao Tang, Weiye Xu, Bowen Sun, Zhu’an Zheng

“…The parking space and obstacle detection module adopts parking space corner detection based on image gradient matching, as well as obstacle detection utilizing yolov5s, whose feature pyramid network structure is optimized. The two modules are cascaded to optimize the prediction parameters of the image adaptive enhancement module, comprehensively considering the similarity loss of parking space corner matching and the obstacle detection loss. …”
Get full text

Evaluation of machine learning techniques for real-time prediction of implanted lower limb mechanics by Chase Maag, Clare K. Fitzpatrick, Paul J. Rullkoetter

“…Several predictive algorithms were explored, including linear regression (LRM), multilayer perceptron (MLP), bi-directional long short-term memory (biLSTM), convolutional neural network (CNN), and transformer-based approaches. The performance of these models was evaluated using average normalized root mean squared error (nRMSE).ResultsThe biLSTM model achieved the highest accuracy, with a significantly lower nRMSE compared to other models. …”
Get full text

Traj-Q-GPSR: A Trajectory-Informed and Q-Learning Enhanced GPSR Protocol for Mission-Oriented FANETs by Mingwei Wu, Bo Jiang, Siji Chen, Hong Xu, Tao Pang, Mingke Gao, Fei Xia

“…To further enhance adaptability, the learning parameters are adjusted in real time according to network dynamics. Additionally, a delay-aware queuing model is introduced to forecast optimal transmission timing, thereby reducing buffering overhead and mitigating redundant retransmissions. …”
Get full text

Enhancing Autonomous Driving Perception: A Practical Approach to Event-Based Object Detection in CARLA and ROS by Jingxiang Feng, Peiran Zhao, Haoran Zheng, Jessada Konpang, Adisorn Sirikham, Phuri Kalnaowakul

“…While the previous research on event-based object detection has predominantly focused on algorithmic enhancements via advanced preprocessing and network optimizations to improve detection accuracy, the practical engineering and integration challenges of deploying these sensors in real-world systems remain underexplored. …”
Get full text

Object Detection for Autonomous Logistics: A YOLOv4 Tiny Approach with ROS Integration and LOCO Dataset Evaluation by Souhaila Khalfallah, Mohamed Bouallegue, Kais Bouallegue

“…The YOLOv4 Tiny model was implemented with Darknet, especially for its adaptability to ROS Melodic framework and capability to fit edge devices. Notably, our network achieved a mean average precision (mAP) of 46% and an intersection over union (IoU) of 50%, surpassing the baseline metrics established by the initial LOCO study. …”
Get full text