Study on Lightweight Bridge Crack Detection Algorithm Based on YOLO11 by Xuwei Dong, Jiashuo Yuan, Jinpeng Dai

“…Additionally, the algorithm improves detection accuracy without increasing the model size. …”
Get full text

Application of evolutionary deep learning algorithm in construction engineering management system by Zhe Yang

“…By comparing with other classic deep learning models, we found that the optimized evolutionary deep learning algorithm model significantly improved the accuracy of classification training and testing. …”
Get full text

DS-YOLOv7: Dense Small Object Detection Algorithm for UAV by Tao Sun, Haonan Chen, Haiying Liu, Lixia Deng, Lida Liu, Shuang Li

“…The experimental verification on the public data set VisDrone2019 shows that mAP50 and mAP50-95 have increased by 4.3% and 3.3% respectively, F1 scores have increased by 3.81%, model volume has decreased by 23.3MB, parameters have decreased by 13 million, and the improved algorithm is more conducive to UAV deployment and dense small object detection.…”
Get full text

Athlete movement control training based on dynamic time warping algorithm by Luo Dai, Yueqiang Zhao

“…Subsequently, a quality assessment model for action completion is built based on an improved dynamic time-warping algorithm. …”
Get full text

Performance analysis and testing of personal influence algorithm in online social networks by Yong QUAN, Yan JIA, Liang ZHANG, Zheng ZHU, Bin ZHOU, Binxing FANG

“…Social influence is the key factor to drive information propagation in online social networks and can be modeled and analyzed with social networking data.As a kind of classical personal influence algorithm,two parallel implementation versions of a PageRank based method were introduced.Furthermore,extensive experiments were conducted on a large-scale real dataset to test the performance of these parallel methods in a distributed environment.The results demonstrate that the computational efficiency of the personal influence algorithm can be improved significantly in massive data sets by virtue of existing big data processing framework,and provide an empirical reference for the future research and optimization of the algorithm as well.…”
Get full text

Recommendation Algorithm of Web-Based Learning Resources considering Timeliness and Popularity by Xiaolu Han

“…The optimized learner evaluation matrix and similarity model are essential methods to deal with the challenges of “data sparsity” and “cold start” in the process of learning resource recommendation on the online learning platform. …”
Get full text

Research on Actuator Control System Based on Improved MPC by Qingjian Zhao, Qinghai Zhang, Shuang Zhao, Xiaoqian Zhang, Shilei Lu, Yang Guo, Liqiang Song, Zhengxu Zhao

“…The system uses an STM32 controller as the core processing unit, integrating high-precision position sensors to build a multi-level control architecture. An improved model predictive control algorithm is proposed, which introduces extended state observers and multi-objective optimization strategies to estimate system states and external disturbances in real-time, achieving precise disturbance compensation. …”
Get full text

A deep learning-based algorithm for the detection of personal protective equipment. by Bo Tong, Guan Li, Xiangli Bu, Yang Wang, Xingchen Yu

Get full text

CRASHWORTHINESS DESIGN AND OPTIMIZATION FOR COLLISION POST OF TRAIN by SHI YueQing, QIN RuiXian, CHEN BingZhi

“…In order to improve the crashworthiness of the collision post structure, the optimal cross-section configuration of the collision post was obtained based on the topology optimization method, and the impacting finite element model of the collision post was established in the explicit dynamics software Ls-Dyna. …”
Get full text

The Application of Kalman Filter Algorithm in Rail Transit Signal Safety Detection by Zhinong Miao, Qilong Liao

“…Firstly, the improved Kalman filter algorithm is used to denoise the signal to ensure the accuracy of signal transmission. …”
Get full text

Topology optimization of a cargo gripper design using the minimum effort principle by Gnezdilov S.G.

“…The study emphasizes accounting for varied load scenarios (e.g., sheet tilting) for future refinement. It confirms the algorithm’s effectiveness in simplifying models and highlights iterative refinement for rational topology. …”
Get full text

Computer-economical optimization method for solving inverse problems of determining electrophysical properties of objects in eddy current structroscopy by V. Ya. Halchenko, R. V. Trembovetska, V. V. Tychkov

“…Integration of multiple capabilities in the surrogate model that combine the advantages of high-performance computing and optimization algorithms in the factor space reduced by the Kernel PCA (Principal Component Analysis) method. …”
Get full text

IoT driven smart health monitoring for heart disease prediction using quantum kernel enhanced sardine diffusion and CNN by Dibas Kumar Hembram, Satya Narayan Tripathy, CH Narsimha Reddy, Debabrata Dansana, Quadri Noorulhasan Naveed, Shafat khan, Mohammed Kareemullah, Addisu Frinjo Emma

Get full text

Low error floor LT coding algorithm for unequal error protection by Xin SONG, Shuyan NI, Zhe ZHANG, Yurong LIAO, Tuofeng LEI

“…Conclusions: In this paper, a systematic unequal error protection LT coding scheme is designed, and a check degree distribution design model suitable for this scheme is constructed to solve the problem of high error floor existing in the conventional UEP-LT algorithm in the AWGN channel.The main idea of this scheme is to design fixed coding segments,rateless coding segments and systematic node segments and transmit them in sequence.The advantage of this scheme is that it can provide non-zero LLR information as early as possible for information nodes, and make the MIB and the LIB obtain different and flexibly adjustable average degrees.In addition,based on the extrinsic information transfer(EXIT)chart,the check degree distribution is designed for the fixed segment and the rateless segment,so that the MIB can obtain the optimal protection performance,and the convergence performance of the LIB can be improved as much as possible. …”
Get full text

A Linear Fitting Algorithm Based on Modified Random Sample Consensus by Yujin Min, Yun Tang, Hao Chen, Faquan Zhang

“…RANSAC is then used to fit the model parameters of the processed dataset. The optimal parameters for the linear model are obtained after multiple iterative processes. …”
Get full text

Barefoot Footprint Detection Algorithm Based on YOLOv8-StarNet by Yujie Shen, Xuemei Jiang, Yabin Zhao, Wenxin Xie

“…This study proposes an optimized footprint recognition model based on an enhanced StarNet architecture for biometric identification in the security, medical, and criminal investigation fields. …”
Get full text

Risk assessment and prevention in airport security assurance by integrating LSTM algorithm. by Yao Hu, Liguang Qiao, Feng Gu

“…It can be summarized that the algorithmic model has good accuracy and robustness. …”
Get full text

Elastic Optimization for Stragglers in Edge Federated Learning by Khadija Sultana, Khandakar Ahmed, Bruce Gu, Hua Wang

“…Then, we formulate an optimization problem to be solved at edge devices. We customize a benchmark algorithm, FedAvg, to obtain a new elastic optimization algorithm (FedEN) which is applied in local training of edge devices. …”
Get full text

Underwater object detection algorithm integrating image enhancement and deformable convolution by Lijia Guo, Xiangchun Liu, Dongsheng Ye, Xuebao He, Jianxin Xia, Wei Song

“…Finally, a dedicated detection head is added to further improve the model's ability to detect small objects. …”
Get full text

A Deep Learning-Based Algorithm for Ceramic Product Defect Detection by Junxiang Diao, Hua Wei, Yawei Zhou, Zhihua Diao

“…Additionally, an adaptive threshold method is proposed to improve the traditional Canny edge detection algorithm, significantly enhancing its accuracy in defect edge detection. …”
Get full text