Lightweight and Efficient CSI-Based Human Activity Recognition via Bayesian Optimization-Guided Architecture Search and Structured Pruning by Sungkwan Youm, Sunghyun Go

“…Motivated by the need for accuracy and efficiency in resource-constrained environments, we combine Bayesian Optimization-based Neural Architecture Search (NAS) with a structured pruning algorithm. NAS identifies optimal network configurations, while pruning systematically removes redundant parameters, preserving accuracy. …”
Get full text

A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning by Qingming Hu, Xinjie Fu, Dandan Sun, Donghui Xu, Yanqi Guan

“…Secondly, the datasets and an adaptive learning rate reduction algorithm are utilized to train the model, and the lightweight network model is achieved through network pruning. …”
Get full text

Deformable Feature Fusion and Accurate Anchors Prediction for Lightweight SAR Ship Detector Based on Dynamic Hierarchical Model Pruning by Yue Guo, Shiqi Chen, Ronghui Zhan, Wei Wang, Jun Zhang

“…Finally, a magnitude-based dynamic hierarchical pruning algorithm is introduced to dynamically prune parameters across various network structures, thereby reducing the model’s parameters. …”
Get full text

Unveiling optimal SDG pathways: an innovative automated recommendation approach integrating graph pruning, intent graph, and attention mechanism by Qiang Wang, Zhihang Yu, Shu Wang, Yunqiang Zhu, Xiaoliang Dai, Zhiqiang Zou, Weiming Huang, Christophe Claramunt

“…However, traditional recommendation algorithms struggle with two key challenges: spatial heterogeneity and sparse historical interaction records between regions and SDPs. …”
Get full text

Improved printed circuit board defect detection scheme by Lufeng Bai, Wen Hao Xu

“…Compared to the original YOLOv8 algorithm, this algorithm improves the average accuracy on small targets by $$5.5\%$$ for mAP50.…”
Get full text

3D Printing Errors Detection During the Process by Florin-Bogdan MARIN, Mihaela MARIN

“…In this paper, a computer vision algorithm able to detect specific errors is proposed.…”
Get full text

Bridging Additive Manufacturing and Electronics Printing in the Age of AI by Jihua Chen, Yue Yuan, Qianshu Wang, Hanyu Wang, Rigoberto C. Advincula

“…In this age of ongoing AI revolution, the application of AI algorithms is discussed in terms of combining them with 3D printing and electronics printing for a future with automated optimization, sustainable design, and customizable and scalable manufacturing.…”
Get full text

ML-Based Materials Evaluation in 3D Printing by Izabela Rojek, Dariusz Mikołajewski, Krzysztof Galas, Jakub Kopowski

“…ML algorithms can analyze vast amounts of data from previous printing processes to predict the performance of different materials (including those used in multi-material printing) under different conditions. …”
Get full text

An Automated Digital Microfluidic System Based on Inkjet Printing by Wansheng Hu, Ming Cao, Lingni Liao, Yuanhong Liao, Yuhan He, Mengxiao Ma, Simao Wang, Yimin Guan

“…To address these issues, we have developed an automated, intelligent system based on inkjet printing. This system allows for precise control of droplet volume by adjusting algorithms, thereby enabling the formation of spheroids of varying sizes. …”
Get full text

Remaining Useful Life Prediction Method for Bearings Based on Pruned Exact Linear Time State Segmentation and Time–Frequency Diagram by Xu Wei, Jingjing Fan, Huahua Wang, Lulu Cai

“…To improve the accuracy and robustness of bearing remaining useful life (RUL) prediction, this paper proposes a bearing RUL prediction method based on PELT state segmentation and time–frequency analysis, incorporating the Informer model for time-series modeling. First, the PELT (Pruned Exact Linear Time) algorithm is used to segment the vibration signals over the full life cycle of the bearing, accurately identifying critical degradation states and optimizing the stage division of the degradation process. …”
Get full text

GYS-RT-DETR: A Lightweight Citrus Disease Detection Model Based on Integrated Adaptive Pruning and Dynamic Knowledge Distillation by Linlin Yang, Zhonghao Huang, Yi Huangfu, Rui Liu, Xuerui Wang, Zhiwei Pan, Jie Shi

“…Secondly, the model adopts two model optimization strategies: (1) The Group_taylor local pruning algorithm is used to reduce memory occupation and the number of computing parameters of the model. (2) The feature-logic knowledge distillation framework is proposed and adopted to solve the problem of information loss caused by the structural difference between teachers and students, and to ensure a good detection performance, while realizing the lightweight character of the model. …”
Get full text

Exploring the fresh and rheology properties of 3D printed concrete with fiber reinforced composites (3DP-FRC): a novel approach using machine learning techniques by Risul Islam Rasel, Md Minaz Hossain, Md Hasib Zubayer, Chaoqun Zhang

Subjects: Get full text

DVCW-YOLO for Printed Circuit Board Surface Defect Detection by Pei Shi, Yuyang Zhang, Yunqin Cao, Jiadong Sun, Deji Chen, Liang Kuang

“…The accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. …”
Get full text

Research on Lightweight Method of Insulator Target Detection Based on Improved SSD by Bing Zeng, Yu Zhou, Dilin He, Zhihao Zhou, Shitao Hao, Kexin Yi, Zhilong Li, Wenhua Zhang, Yunmin Xie

“…Furthermore, the channel pruning strategy is used to reduce the unimportant weight matrix of the model, and the knowledge distillation strategy is used to fine-adjust the network model after pruning, so as to ensure the detection accuracy. …”
Get full text

Generating Automatically Print/Scan Textures for Morphing Attack Detection Applications by Juan E. Tapia, Maximilian Russo, Christoph Busch

“…Currently, there are limited datasets available for training the MAD algorithm due to privacy concerns and the challenges of obtaining and processing a large number of printed and scanned images. …”
Get full text

Write-off of material values of state reserves with their further processing, utilization or destruction by Yu.М. Bilokon, O.V. Storozh, L.M. Shevchuk, V.М. Grytsun

“…The current law on state reserves provides for the procedure for actions with material values of state reserves, the release of which cannot be carried out due to the loss of their qualitative characteristics and/or the expiration of the shelf life (shelf life), such material values are subject to write-off with subsequent processing, disposal or destruction. …”
Get full text

The future of 3D printing in instrumented implantable polymer meta-stents by C. Brosseau, G. Nocchiero, J. Ville

“…Firstly, we examine the benefits of using 3D-printed polymer stents by comparing their characteristics with metallic devices. …”
Get full text

FlexSim-Simulated PCB Assembly Line Optimization Using Deep Q-Network by Jinhao Du, Jabir Mumtaz, Wenxi Zhao, Jian Huang

Subjects: “…printed circuit board…”
Get full text

Optimization of particle swarm for force uniformity of personalized 3D printed insoles by Zhao Jiali, Liu Jinhai, Liu Yuan

“…This study investigates the application of particle swarm optimization (PSO) algorithm in optimizing the force uniformity of personalized 3D-printed insoles, aiming to enhance the comfort and functionality of the insoles. …”
Get full text

Intrusion detection method for IoT in heterogeneous environment by LIU Jing, MU Zelin, LAI Yingxu

“…Subsequently, an innovative heterogeneous model aggregation algorithm was introduced, utilizing similarity-weighted coefficients for channel averaging, thereby effectively mitigating the adverse effects of Non-IID data during the model aggregation process. …”
Get full text