Trinocular Vision-Driven Robotic Fertilization: Enhanced YOLOv8n for Precision Mulberry Growth Synchronization by Ma Ming, Osama Elsherbiny, Jianmin Gao

“…These improvements included the introduction of the Asymptotic Feature Pyramid Network (AFPN), the optimization of feature extraction using the MSBlock module, the adoption of a dynamic ATSS label assignment strategy, and the replacement of the CIoU loss function with the Focal_XIoU loss function. Furthermore, an artificial neural network was utilized to calculate the coordinates of the robotic arm. …”
Get full text

The Impact of Minimally Invasive Surgical Modality and Task Complexity on Cognitive Workload: An fNIRS Study by Fuat Ücrak, Kurtulus Izzetoglu, Mert Deniz Polat, Ümit Gür, Turan Şahin, Serhat Ilgaz Yöner, Neslihan Gökmen İnan, Mehmet Emin Aksoy, Cengizhan Öztürk

“…However, these modalities differ in their cognitive demands and skill acquisition requirements, which can influence the learning curve and operative performance. To assess and evaluate this variability across these modalities, a functional near-infrared spectroscopy (fNIRS) system is used as an objective method for monitoring cognitive activity in surgical trainees. fNIRS can provide insights and further our understanding of the mental demands of different surgical techniques and their association with varying task complexity. …”
Get full text

Modulating Cognition-Linked Histone Acetyltransferases (HATs) as a Therapeutic Strategy for Neurodegenerative Diseases: Recent Advances and Future Trends by Huong Anh Mai, Christina M. Thomas, Gu Gu Nge, Felice Elefant

Get full text

Research on the Classification of Sun-Dried Wild Ginseng Based on an Improved ResNeXt50 Model by Dongming Li, Zhenkun Zhao, Yingying Yin, Chunxi Zhao

“…Next, the ELU activation function replaces the original ReLU activation function. …”
Get full text

Revolutionizing proton exchange membrane fuel cell modeling through hybrid aquila optimizer and arithmetic algorithm optimization by Manish Kumar Singla, S. A. Muhammed Ali, Ramesh Kumar, Pradeep Jangir, Mohammad Khishe, G. Gulothungan, Haitham A. Mahmoud

Get full text

Multi-Ground Station Collaborative Measurement and Control Technology for Giant Constellation System by Yang LIU, Di ZHOU, Min SHENG, Jiandong LI, Shiguang HAO, Xiaotian ZHENG

“…Measurement and control technology is the key technology to ensure the effi cient operation, maintenance and management of the constellation system.In recent years, with the continuous expansion of the constellation scale, mega-constellation system has gradually formed, which makes the demand for constellation measurement and control show an explosive growth, which puts forward new requirements for the completion of the constellation system measurement and control tasks.Firstly, the constraints of the megaconstellation system measurement and control tasks and the equipment constraints of the ground measurement and control station were analyzed, and the problem modeling was given; Secondly, an interaction method of the ground station agent based on the learning planning segment was proposed, by introduced the constraint penalty operator and the multi-ground station joint the penalty operator was designed to optimized the objective function.Finally, a multi-ground station Agent reinforcement learning algorithm was proposed to solved the multi-ground station cooperative task assignment strategy.Simulation experiments showed that when the task scale was large, the method had a gain of 12%~20% compared with the traditional algorithm in the diff erent scenarios mentioned.…”
Get full text

Multi-Ground Station Collaborative Measurement and Control Technology for Giant Constellation System by Yang LIU, Di ZHOU, Min SHENG, Jiandong LI, Shiguang HAO, Xiaotian ZHENG

“…Measurement and control technology is the key technology to ensure the effi cient operation, maintenance and management of the constellation system.In recent years, with the continuous expansion of the constellation scale, mega-constellation system has gradually formed, which makes the demand for constellation measurement and control show an explosive growth, which puts forward new requirements for the completion of the constellation system measurement and control tasks.Firstly, the constraints of the megaconstellation system measurement and control tasks and the equipment constraints of the ground measurement and control station were analyzed, and the problem modeling was given; Secondly, an interaction method of the ground station agent based on the learning planning segment was proposed, by introduced the constraint penalty operator and the multi-ground station joint the penalty operator was designed to optimized the objective function.Finally, a multi-ground station Agent reinforcement learning algorithm was proposed to solved the multi-ground station cooperative task assignment strategy.Simulation experiments showed that when the task scale was large, the method had a gain of 12%~20% compared with the traditional algorithm in the diff erent scenarios mentioned.…”
Get full text

Synthetic Text as Data: On Usefulness and Limitations by Seoyeon Choi, Jaein Sim, Guebin Choi

“…These findings suggest that GPT-generated text can function as a conditional training resource, with its effectiveness closely tied to the granularity of the classification task.…”
Get full text

Determining parameters of surface defects in the base metal of pipelines using results of complex diagnostics by N.V. Krysko, S.V. Skrynnikov, N.A. Shchipakov, D.M. Kozlov, A.G. Kusyy

Get full text

High-Performance Deployment Operational Data Analytics of Pre-Trained Multi-Label Classification Architectures with Differential-Evolution-Based Hyperparameter Optimization (AutoDE... by Teo Prica, Aleš Zamuda

“…This article presents a high-performance-computing differential-evolution-based hyperparameter optimization automated workflow (AutoDEHypO), which is deployed on a petascale supercomputer and utilizes multiple GPUs to execute a specialized fitness function for machine learning (ML). The workflow is designed for operational analytics of energy efficiency. …”
Get full text

Joint Resource Allocation for V2X Sensing and Communication Based on MADDPG by Zhiyong Zhong, Zhangyou Peng

Get full text

Smart Car Damage Assessment Using Enhanced YOLO Algorithm and Image Processing Techniques by Muhammad Remzy Syah Ramazhan, Alhadi Bustamam, Rinaldi Anwar Buyung

Get full text

Fault Diagnosis of Wind Turbine Gearbox Based on Mel Spectrogram and Improved ResNeXt50 Model by Xiaojuan Zhang, Feixiang Jia, Yayu Chen

“…In response to the problem of complex and variable loads on wind turbine gearbox bearing in working conditions, as well as the limited amount of sound data making fault identification difficult, this study focuses on sound signals and proposes an intelligent diagnostic method using deep learning. By adding the CBAM module in ResNeXt to enhance the model’s attention to important features and combining it with the Arcloss loss function to make the model learn more discriminative features, the generalization ability of the model is strengthened. …”
Get full text

Cooperative UAV clustering for fair coverage of communication regions by Jiehong Wu, Linpeng Gu, Zhongli Jia, Jinsong Wu

“…Under the premise of comprehensively considering the maximum coverage, we use a new energy efficiency function to minimize energy consumption, so as to extend the network lifetime of the UAVs cluster networks. …”
Get full text

Beam Coefficient Prediction for Antenna Arrays Using Physics-Aware Convolutional Neural Networks by Glendyn D. King, Md Asaduzzaman Towfiq, Ali C. Gurbuz, Bedri A. Cetiner

“…In addition to the classical mean squared error (MSE) loss for regression to true weights, a novel physics-aware loss function is designed to jointly force the PA-CNN to estimate true weight while generating physically consistent beam patterns. …”
Get full text

Explicitly Constrained Black-Box Optimization With Disconnected Feasible Domains Using Deep Generative Models by Naoki Sakamoto, Rei Sato, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto

Get full text

Enterprise fission path optimization and dynamic capability construction based on the soft actor-critic algorithm by Hengsheng Gu

“…Secondly, a multi-level reward function is designed that covers short-term financial and market indices. …”
Get full text

The Teacher–Assistant–Student Collaborative and Competitive Network for Brain Tumor Segmentation with Missing Modalities by Junjie Wang, Huanlan Kang, Tao Liu

“…Second, a competitive function is formulated to promote collaboration and competition between the student network and the teacher network. …”
Get full text

Joint Optimization of Task Completion Time and Energy Consumption in UAV-Enabled Mobile Edge Computing by Hanwen Zhang, Tao Chen, Bangbang Ren, Ruozhe Li, Hao Yuan

“…Then, a reinforcement learning method, LyraRD, is proposed to solve the PROP. …”
Get full text

Energy-Efficient Prediction of Carbon Deposition in DRM Processes Through Optimized Neural Network Modeling by Rui Fang, Tuo Zhou, Zhuangzhuang Xu, Xiannan Hu, Man Zhang, Hairui Yang

Get full text