Research on Channel Modeling and Communication Coverage of Wireless Sensor Networks in Barrier Area of Nuclear Power Plants by Zhi-Guang Deng, Qian Wu, Xin Lv, Bi-Wei Zhu, Mei-Qiong Xiang, Xue-Mei Wang, Jia-Liang Zhu

“…The simulation results show that the improved teaching and learning algorithm can optimize the network coverage of the obstacle area well, and under the four obstacle modules, 14 nodes can cover the whole area by more than 99%. …”
Get full text

Can Knowledge Distillation Enable Seismic Interpolation, Super-Resolution, and Denoising Simultaneously? by Benwen Zhang, Linrong Wang

“…In seismic data processing, interpolation, super-resolution, and denoising are three key issues to improve data quality. While deep learning methods have successfully addressed one or two of these tasks, simultaneously resolving all three within a single network faces difficulties. …”
Get full text

Development and application of a generalized fatigue driving monitoring system for open-pit mining vehicles: A case study in a myanmar copper mine by Tao Li, Baomeng Chang, Yan Sun, Yaodong Zhou, Bin Zhou, Lubin Zhang

“…Engineering practices yielding the following outcomes: (1) The Beidou positioning antenna demonstrated superior performance in the S&K mine, ensuring accurate vehicle tracking and minimal signal blind spots in challenging open-pit mining environments. (2) The GFDMS effectively identifies unsafe driving behaviors, including speeding, fatigue driving and irregular operations, providing real-time alerts to enhance safety. (3) A comprehensive analysis of system performance demonstrated its effectiveness, reducing traffic incident rates by over 70 % for mining dump trucks and auxiliary vehicles within a year while improving vehicle utilization and operational reliability. (4) Challenges in improving the GFDMS persist in areas such as environmental adaptability, algorithm generalization, and scalability. …”
Get full text

AHA: Design and Evaluation of Compute-Intensive Hardware Accelerators for AMD-Xilinx Zynq SoCs Using HLS IP Flow by David Berrazueta-Mena, Byron Navas

“…We outline criteria for selecting algorithms to improve speed and resource efficiency in HLS design. …”
Get full text

Breast cancer survival prediction using an automated mitosis detection pipeline by Nikolas Stathonikos, Marc Aubreville, Sjoerd deVries, Frauke Wilm, Christof A Bertram, Mitko Veta, Paul J vanDiest

“…Considering the potential of AI to improve reproducibility of MC between pathologists, we undertook the next validation step by evaluating the prognostic value of a fully automatic method to detect and count mitoses on whole slide images using a deep learning model. …”
Get full text

QoS Routing in Telecommunications Networks by N. I. Listopad, O. A. Lavshuk

“…The existing routing algorithms have been developed quite fully and, on the whole, function effectively if the optimization of the route selection is carried out according to one parameter. …”
Get full text

Deep knowledge tracing and cognitive load estimation for personalized learning path generation using neural network architecture by Chunyan Tong, Changhong Ren

“…A dual-objective optimization algorithm balances knowledge acquisition with cognitive load management to generate paths that maintain optimal challenge levels. …”
Get full text

Adaptive enhancement of shoulder x-ray images using tissue attenuation and type-II fuzzy sets. by Qifeng Liu, Yong Han, Lu Shen, Jialei Du, Marzia Hoque Tania

“…The method integrates automatic tissue attenuation techniques, which enhance the image contrast by removing non-essential tissue components while preserving important tissues and bones. Additionally, we apply an improved Type-II fuzzy set algorithm to further optimize image sharpness. …”
Get full text

Neural network compression for reinforcement learning tasks by Dmitry A. Ivanov, Denis A. Larionov, Oleg V. Maslennikov, Vladimir V. Voevodin

“…The use of sparsity and pruning for optimizing Neural Network inference, and particularly to improve energy efficiency, latency and throughput, is a standard technique. …”
Get full text

MUFFNet: lightweight dynamic underwater image enhancement network based on multi-scale frequency by Dechuan Kong, Dechuan Kong, Yandi Zhang, Xiaohu Zhao, Yanqiang Wang, Lei Cai

“…A Multi-Scale Joint Loss framework facilitates dynamic network optimization.ResultsExperimental results demonstrate that MUFFNet outperforms existing state-of-the-art models while consuming fewer computational resources and aligning enhanced images more closely with human visual perception.DiscussionThe enhanced images generated by MUFFNet exhibit better alignment with human visual perception, making it a promising solution for improving underwater robotic vision systems.…”
Get full text

PID Control and Input Shaping for Quadrotor UAV Stabilization and Payload Swing Reduction by Liyana Ramli, Izzuddin M. Lazim, Amalin Aisya Awi, Aina Syazwin Shukor

“…To enhance swing suppression, the input shaper parameters are optimized using the Particle Swarm Optimization (PSO) algorithm. …”
Get full text

A Full-Life-Cycle Modeling Framework for Cropland Abandonment Detection Based on Dense Time Series of Landsat-Derived Vegetation and Soil Fractions by Qiangqiang Sun, Zhijun You, Ping Zhang, Hao Wu, Zhonghai Yu, Lu Wang

“…Compared to the traditional yearly land cover-based approach (with an overall accuracy of 77.39%), this algorithm can overcome the propagation of classification errors (with product accuracy from 74.47% to 85.11%), especially in terms of improving the ability to capture changes at finer spatial scales. …”
Get full text

Intelligent Counterforce Allocation Method Using Multi-Agent Reinforcement Learning for Ground Operations by Kiwoong Park, Sangheun Shim

“…Modern military operations require commanders to make complex tactical decisions involving the effective allocation of multiple friendly forces to counter enemy threats while managing diverse streams of battlefield information. …”
Get full text

A Robust Hybrid MRAPID Controller Design for an Underactuated Nonlinear System With Parametric Uncertainty by Ahmed Abduljabbar Mahmood, Mohamed Abderrahim

“…The hybrid controller design is developed by combining the MRAPIDC design with controller gains applied to each output and incorporating the system adaptation error in a specific configuration. Optimal performance is achieved through parameter tuning via the social spider optimization (SSO) algorithm, and MIT (Massachusetts Institute of Technology) rule criteria are employed to ensure system stability. …”
Get full text

Traffic light detection and recognition based on deep learning for autonomous-rail rapid tram by XIONG Qunfang, LIN Jun, YUAN Xiwen, XU Yanghan, YUE Wei, LI Yuanzhengyu

“…This paper presents study efforts in this field through the application of a deep learning algorithm. Firstly, regions of interest (RoIs) for traffic lights were determined using high-precision map information to narrow the detection range and improve the detection speed. …”
Get full text

Development and Validation of a Discrete Element Simulation Model for Pressing Holes in Sowing Substrates by Hongmei Xia, Chuheng Deng, Teng Yang, Runxin Huang, Jianhua Ou, Lingjin Dong, Dewen Tao, Long Qi

“…A neural network model for predicting the angle of repose was constructed, and a genetic algorithm was applied to optimize the significant contact mechanical parameters. …”
Get full text

Embedded Hardware-Efficient FPGA Architecture for SVM Learning and Inference by B. B. Shabarinath, Muralidhar Pullakandam

“…While Sequential Minimal Optimization (SMO) has enhanced the efficiency of SVM training, traditional implementations still suffer from high computational cost. …”
Get full text

OR-FCOS: an enhanced fully convolutional one-stage approach for growth stage identification of Oudemansiella raphanipes by Runze Fang, Huamao Huang, Nuoyan Guo, Haichuan Wei, Shiyi Wang, Haiying Hu, Ming Liu

“…Channel pruning further reduces the decoder’s parameters, decreasing model size and computational requirements while maintaining precision. The enhanced algorithm achieved a mean average precision (mAP) of 89.4% ( $$\hbox {mAP}_{50}$$ ) and 78.3% ( $$\hbox {mAP}_{50:95}$$ ), while the number of model parameters was reduced to 9.9 M, the model size was reduced to 40.1 MB, and the number of floating point operations per second (FLOPs) was reduced to 31.2 G. …”
Get full text

Scalable Hyperspectral Enhancement via Patch-Wise Sparse Residual Learning: Insights from Super-Resolved EnMAP Data by Parth Naik, Rupsa Chakraborty, Sam Thiele, Richard Gloaguen

“…The spectral and spatial characteristics of the scene encoded in the dictionary enable reconstruction through a first-order optimization algorithm to ensure an efficient sparse representation. …”
Get full text

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning by Anis Elgabli

“…We provide a rigorous theoretical proof of convergence, showing that PP-QADMM converges to the optimal solution for convex problems while achieving a convergence rate comparable to standard ADMM, but with significantly lower communication and energy costs, and robust privacy protection. …”
Get full text