Latest Publications on Neural Networks
This is our latest selection of worldwide publications on Neural Networks, between many scientific online journals, classified and focused on neural network, artificial neuron, epoch, neural architecture, machine learning, deep learning and support vector machine.
Tip: Further to this selection on Neural Networks, you can search and filter our > publication database < by author, topic, keywords, date or journal.
Selection of Trajectories to Improve Thermal Fields During the Electric Arc Welding Process Using Hybrid Model CFD-FNN
On 2025-02-03 by Sixtos A. Arreola-Villa, Alma Rosa Mndez-Gordillo, Alejandro Prez-Alvarado, Rumualdo Servn-Castaeda, Ismael Caldern-Ramos, Hctor Javier Vergara-Hernndez @MDPI
Keywords: trajectories, thermal fields, hybrid model, CFD, FNN
AI summary: Effective thermal management essential in welding processes. Study examines thermal behavior of AISI 1080 steel plate with blind holes. Experimental results validate computational heat transfer model. Optimization with feedforward neural network minimizes temperature gradients and overheating risks. Hybrid CFD-FNN approach predicts thermal behavior in multipoint welding processes effectively.
Abstract: Effective thermal management is essential in welding processes to maintain structural integrity and material quality, especially in high-precision industrial applications. This study examines the thermal behavior of an AISI 1080 steel plate containing 100 blind holes filled using robotic electric arc welding. Temperature measurements, recorded with eight strategically positioned thermocouples, monitored the thermal evolution throughout the robotic welding process. The experimental results valida[...]
Publication
Adaptive Grasp Pose Optimization for Robotic Arms Using Low-Cost Depth Sensors in Complex Environments
On 2025-02-03 by Aiguo Chen, Xuanfeng Li, Kerui Cen, Chitin Hon @MDPI
Keywords: grasp pose optimization, robotic arms, depth sensors, ellipsoidal modeling
AI summary: Efficient grasp pose estimation algorithm using low-cost depth sensors for robotic arms. Improved success rates and computational efficiency compared to traditional deep learning methods. Stable and reliable grasping performance in complex and noisy environments.
Abstract: This paper presents an efficient grasp pose estimation algorithm for robotic arm systems with a two-finger parallel gripper and a consumer-grade depth camera. Unlike traditional deep learning methods, which suffer from high data dependency and inefficiency with low-precision point clouds, the proposed approach uses ellipsoidal modeling to overcome these issues. The algorithm segments the target and then applies a three-stage optimization to refine the grasping path. Initial estimation fits an el[...]
Publication
A Human Activity Recognition Model for Extracting Temporal and Spatial Features from WiFi Channel State Information
On 2025-02-03 by Jianyuan Hu, Fei Ge, Xinyu Cao, Zhimin Yang @MDPI
Keywords: WiFi Channel State Information, Human Activity Recognition, Deep Learning, Residual Networks, Spatial Features
AI summary: Communication technologies advance wireless networks for human activity recognition. Proposed model utilizes ResNet for spatial feature extraction and GRU for temporal sequence learning. Achieves high accuracy on UT_HAR and NTU-FI HAR datasets, outperforming existing models.
Abstract: With the rapid advancement of communication technologies, wireless networks have not only transformed people&rsquo;s lifestyles but also spurred the development of numerous emerging applications and services. Against this backdrop, research on Wi-Fi-based human activity recognition (HAR) has become a hot topic in both academia and industry. Channel State Information (CSI) contains rich spatiotemporal information. However, existing deep learning methods for human activity recognition (HAR[...]
Publication
Prediction of Member Forces of Steel Tubes on the Basis of a Sensor System with the Use of AI
On 2025-02-03 by Haiyu Li, Heungjin Chung @MDPI
Keywords: prediction, member forces, sensor system, AI, structural health monitoring
AI summary: Development of AI-based sensor system for predicting forces on steel tubes in offshore wind turbine support systems. Improvement in predictive performance using machine learning algorithms. Optimization of input variables for cost-effective and accurate structural health monitoring. Creation of GUI-based system for real-time prediction of steel tube member forces.
Abstract: The rapid development of AI (artificial intelligence), sensor technology, high-speed Internet, and cloud computing has demonstrated the potential of data-driven approaches in structural health monitoring (SHM) within the field of structural engineering. Algorithms based on machine learning (ML) models are capable of discerning intricate structural behavioral patterns from real-time data gathered by sensors, thereby offering solutions to engineering quandaries in structural mechanics and SHM. Thi[...]
Publication
A Deep Learning Model for Detecting the Arrival Time of Weak Underwater Signals in Fluvial Acoustic Tomography Systems
On 2025-02-03 by Weicong Zheng, Xiaojian Yu, Xuming Peng, Chen Yang, Shu Wang, Hanyin Chen, Zhenxuan Bu, Yu Zhang, Yili Zhang, Lingli Lin @MDPI
Keywords: Deep Learning Model, Underwater Signals, Fluvial Acoustic Tomography, Arrival Time Detection, Two-channel DCA-Net
AI summary: Deep learning model proposed to detect arrival time of weak underwater signals in fluvial acoustic tomography systems; Improves feature extraction capability; Outperforms traditional methods and other deep neural networks in low SNR datasets.
Abstract: The fluvial acoustic tomography (FAT) system relies on the arrival time of the system signal to calculate the parameters of the region. The traditional method uses the matching filter method to calculate the peak position of the received acoustic signal after cross-correlation calculation within a certain time as the signal arrival time point, but this method is difficult to be effectively applied to the complex underwater environment, especially in the case of extremely low SNR. To solve this p[...]
Publication
Enhancing Driving Safety of Personal Mobility Vehicles Using On-Board Technologies
On 2025-02-03 by Eru Choi, Tuan Anh Dinh, Min Choi @MDPI
Keywords: safety technologies, driving assistance system, object detection, hardware acceleration, mobility devices
AI summary: Prevent accidents with driving assistance system using sensors and camera. Improve performance of object detection with hardware acceleration. YOLO model accelerated on specialized hardware for high accuracy in detecting obstacles. Future research will focus on enhancing system performance for electric wheelchair safety.
Abstract: Accidents involving electric wheelchairs are a growing concern, with users frequently encountering obstacles that lead to collisions, tipping, or loss of balance. These incidents underscore the need for advanced safety technologies tailored to electric wheelchair users. This research addresses this need by developing a driving assistance system to prevent accidents and enhance user safety. The system incorporates ultrasonic sensors and a front-facing camera to detect obstacles and provide real-t[...]
Publication
