Software for Graph Analysis and Visualization by M. I. Kolomeychenko, A. A. Zolotyh, I. V. Polyakov, A. M. Chepovskiy

Get full text

Rapid in-air ultrasound holography measurement and camera-in-the-loop generation using thermography by Zak Morgan, Youngjun Cho, Sriram Subramanian

“…Finally, we integrate this with holography algorithms to propose a camera-in-the-loop algorithm that employs real-time measurement, enabling targeted data acquisition and on-line training of acoustic holography algorithms. …”
Get full text

Design, analysis, and model fabrication of an industrial manipulator for quality control purposes using computer vision as a sorting mechanism by Muthair Saeed, Haris Imran, Liaquat Ali Khan, Kamran Nazir

“…This algorithm is also adaptable, as it can identify any object once it has been trained.…”
Get full text

Ray-Tracing-Based Modeling of Clad-Removed Step-Index Plastic Optical Fiber in Smart Textiles: Effect of Curvature in Plain Weave Fabric by Sun Hee Moon, Joon Seok Lee, In Hwan Sul

“…A half-cone-shaped jig was manufactured using 3D printing to give various curvature conditions to fibers. …”
Get full text

Denoising Graph Inference Network for Document-Level Relation Extraction by Hailin Wang, Ke Qin, Guiduo Duan, Guangchun Luo

“…Then, the Steiner tree algorithm extracts a mention-level denoised graph, Steiner Graph (SG), removing linguistically irrelevant words from the SDT-forest. …”
Get full text

LightCardiacNet: light-weight deep ensemble network with attention mechanism for cardiac sound classification by Suma K. V., Deepali B. Koppad, Dharini Raghavan, Manjunath P. R.

“…It is trained on the PASCAL Heart Challenge and CirCor DigiScope datasets. Static network pruning enhances model sparsity for real-time deployment. …”
Get full text

Visual information perception system of coal mine comprehensive excavation working face for edge computing terminal by Dongyang Zhao, Guoyong Su, Pengyu Wang

“…Firstly, the C3‐Fast feature extraction module, spatial pyramid pooling with cross‐stage partial connection (SPPCSPC) pooling module, bi‐directional feature pyramid network and lightweight decoupled detection head are used to optimize the YOLOv5s model, so as to construct the FSBD‐YOLOv5s multi‐object detection model. Secondly, the pruning and distillation algorithm is used to lighten the FSBD‐YOLOv5s model, and the model complexity is greatly reduced while maintaining the model detection accuracy. …”
Get full text

Two-stage deep reinforcement learning method for agile optical satellite scheduling problem by Zheng Liu, Wei Xiong, Zhuoya Jia, Chi Han

“…A neural network is designed as the observation scheduling network to determine observation actions for the sequenced tasks, which is well trained by the soft actor-critic algorithm. Finally, extensive experiments show that the proposed method, along with the designed mechanisms and strategy, is superior to comparison algorithms in terms of solution quality, generalization performance, and computation efficiency.…”
Get full text

MEL-YOLO: A Novel YOLO Network With Multi-Scale, Effective, and Lightweight Methods for Small Object Detection in Aerial Images by Yang Yang, Fangtao Feng, Guisuo Liu, Juxing Di

“…Furthermore, we explore the Soft-NMS algorithm to effectively mitigate small object occlusion and reduce missed detection. …”
Get full text

A machine learning-based recommendation framework for material extrusion fabricated triply periodic minimal surface lattice structures by Sajjad Hussain, Carman Ka Man Lee, Yung Po Tsang, Saad Waqar

“…This dataset was used to train both ML and DL algorithms. ML algorithms included Bayesian regression (BR), K-nearest neighbors (KNN), Random Forest (RF), Decision Tree (DT), and DL algorithm convolutional neural network (CNN). …”
Get full text

Programing mechanics in warp-knitted spacer materials with double inlay-jacquard systems by Zhang Yanting, Zhang Jing, Zhang Aijun, Liu Haisang, Chen Chaoyu, Jiang Gaoming

“…This researched programing method shows great potential in increasing design efficiency and decreasing chemicals consumption in printing.…”
Get full text

Machine Learning‐Enhanced Optimization for High‐Throughput Precision in Cellular Droplet Bioprinting by Jaemyung Shin, Ryan Kang, Kinam Hyun, Zhangkang Li, Hitendra Kumar, Kangsoo Kim, Simon S. Park, Keekyoung Kim

“…To address these obstacles, machine learning is employed to optimize five critical printing parameters (i.e., bioink viscosity, nozzle size, printing time, printing pressure, and cell concentration), and develop algorithms capable of immediate cellular droplet size prediction. …”
Get full text

Achieving Faster and Smarter Chest X-Ray Classification With Optimized CNNs by Hassen Louati, Ali Louati, Khalid Mansour, Elham Kariri

“…Finally, model compression through filter pruning, driven by evolutionary algorithms, trims redundant parameters to improve computational efficiency while preserving model accuracy. …”
Get full text

Sparse support path generation for multi-axis curved layer fused filament fabrication by Tak Yu Lau, Dong He, Yamin Li, Yihe Wang, Danjie Bi, Lulu Huang, Pengcheng Hu, Kai Tang

“…Currently, most support generation algorithms are for the conventional 2.5D printing, which are not applicable to multi-axis printing. …”
Get full text

YOLO-Ginseng: a detection method for ginseng fruit in natural agricultural environment by Zhedong Xie, Zhuang Yang, Chao Li, Zhen Zhang, Jiazhuo Jiang, Hongyu Guo

“…This addresses the detection challenges caused by occlusion or overlapping of ginseng fruits, significantly reducing the overall missed detection rate and improving the long-distance detection performance of ginseng fruits; Secondly, in order to maintain the balance between YOLO-Ginseng detection precision and speed, this study employs a mature channel pruning algorithm to compress the model.ResultsThe experimental results demonstrate that the compressed YOLO-Ginseng achieves an average precision of 95.6%, which is a 2.4% improvement compared to YOLOv5s and only a 0.2% decrease compared to the uncompressed version. …”
Get full text

Reliability-Based Topology Optimization Considering Overhang Constraints for Additive Manufacturing Design by Fahri Murat, Irfan Kaymaz, Abdullah Tahir Şensoy

“…In numerical experiments on the MBB beam, the AM-RBTO algorithm reduced 3D printing time by approximately 18.3% and improved structural performance by lowering the objective function value by 1.85% compared to conventional RBTO. …”
Get full text

New experimental techniques for fracture testing of highly deformable materials by E. Dall’Asta, V. Ghizzardi, R. Brighenti, E. Romeo, R. Roncella, A. Spagnoli

“…Thanks to the implemented algorithm based on a Semi-Global Matching (SGM) approach, it is possible to constraint the regularity of the displacement field in order to significantly improve the reliability of the evaluated strains, especially in highly deformable materials. …”
Get full text

A Novel Approach for Efficient Detection of Lotus Seedpod Maturity Using Compressed Models by Tao Tang, Min Jin, Gaohong Yu, Rui Feng, Bingliang Ye

“…To simplify the model and improve detection speed, a channel pruning algorithm was utilized for model compression. …”
Get full text

Model-Order Reduction of Multistage Cascaded Models for Digital Predistortion by Raul Criado, Wantao Li, William Thompson, Gabriel Montoro, Kevin Chuang, Pere L. Gilabert

“…To reduce the computational complexity of these multistage CC behavioral models, a model-order reduction technique based on a greedy algorithm is proposed. The advantages of employing CC DPD models with gradient descent parameter identification, as opposed to single-stage DPD models with least squares parameter identification, are extensively demonstrated and analyzed. …”
Get full text

Using reinforcement learning in genome assembly: in-depth analysis of a Q-learning assembler by Kleber Padovani, Rafael Cabral Borges, Roberto Xavier, André Carlos Carvalho, Anna Reali, Annie Chateau, Ronnie Alves, Ronnie Alves

“…We expand upon the previous approach found in the literature to solve this problem by carefully exploring the learning aspects of the proposed intelligent agent, which uses the Q-learning algorithm. We improved the reward system and optimized the exploration of the state space based on pruning and in collaboration with evolutionary computing (>300% improvement). …”
Get full text