Underground personnel detection and tracking using improved YOLOv7 and DeepSORT by Weiqiang FAN, Xuejin WANG, Yinghui ZHANG, Xiaoyu LI

“…Finally, the experimental validation of the proposed algorithm is carried out on the established downhole personnel video image dataset and the public dataset, and the results show that: the average detection accuracy of the improved YOLOv7 model is improved by 3.9% compared with that of the YOLOv7 model; the multi-target tracking accuracy of the improved DeepSORT algorithm reaches 74.9%, the tracking accuracy reaches 82.3%, and the speed reaches 24 FPS. …”
Get full text

Reconstruction of LDPC code check matrix based on random extraction at high bit error rate by Zhongyong WANG, Zhenghao LI, Kexian GONG, Peng SUN, Qingtao LI

“…In order to improve the performance of the sparse check matrix reconstruction algorithm of LDPC codes at high BER, an open set recognition algorithm of the check matrix with strong fault tolerance under the condition of sufficient and insufficient number of received code words was proposed.Firstly, a new code word space was constructed by randomly extracting part bits of the code words for many times.Gaussian elimination method was used to solve the dual vector and restore the check vector in a lower dimension.Secondly, using the check vector, the proportion of error-free code groups in the received data was continuously increased by using the methods of “eliminating error code words” or“flipping the lowest unreliable bits” for iterative processing.Simulation results show that the proposed algorithm is superior to comparison algorithm under different bit error rates, different code lengths, different code rates and different number of code words.For (648,324) LDPC codes in IEEE 802.11n protocol, when the number of received code words is sufficient, the reconstruction rate of check matrix can reach more than 95% under the condition of bit error rate of 0.003.When the number of received code words is insufficient (the number of code words is 450), the reconstruction rate of check matrix can reach more than 90% under the condition of bit error rate of 0.0015.…”
Get full text

An Adaptive Nonmonotone Line Search Technique for Solving Systems of Nonlinear Equations by Masoud Hatamian, Mahmoud Paripour, Farajollah Mohammadi Yaghoobi, Nasrin Karamikabir

“…We attempt to answer this question how to control the degree of the nonmonotonicity of line search rules in order to reach a more efficient algorithm? Therefore, we present a novel algorithm that can avoid the increase of unsuccessful iterations. …”
Get full text

Radio signal recognition based on image deep learning by Xin ZHOU, Xiaoxin HE, Changwen ZHENG

“…A technical idea was innovatively proposed that uses image deep learning to solve the problem of radio signal recognition.First,the radio signal was transformed into a two-dimensional picture,and the radio signal recognition problem was transformed into the object detection problem in the field of image recognition.Then,the advanced achievements about image recognition were used to improve the intelligence and ability of radio signal recognition in complex electromagnetic environment.Based on the proposed idea,a novel radio signal recognition algorithm named RadioImageDet was proposed.The experimental results show that the algorithm can effectively identify the waveform types and time/frequency coordinates of radio signals.After training and testing on the self-collected data set with 12 types and 4 740 samples,the accuracy reaches 86.04% and the mAP value reaches 77.72,while the detection time is only 33 ms on the medium configured desktop computer.…”
Get full text

Spectroscopic measurement of near-infrared soil pH parameters based on GhostNet-CBAM. by Jianguo Zhu, Wenjin Wang, Peng Tian

“…The results showed that the [Formula: see text] of the GhostNet-CBAM method could reach up to 0.9447, and the RMSE reached as low as 0.3267, and the scatter density plots of the predicted and true values further confirmed that the method could quickly and accurately obtain the soil pH parameters.…”
Get full text

Defect detection method of red globe grapes bunches based on near infrared camera imaging by GAO Sheng

“…The edges of the samples and the edges of the defective parts were first extracted by applying the Sobel algorithm to the NIR images （NIR）, and then the images were binarized by the adaptive thresholding algorithm to achieve the segmentation of the images. …”
Get full text

Research on the application of weighted-Laguerre-FDTD method with “unidirectional explicit” matrix in cylindrical structure by Dawei ZHU, Hailin CHEN, Zhongwen SHEN, Xiuling JIA, Zhen LI

“…To solve the shortcomings of FDTD algorithm in electromagnetic wave propagation in communication applications.A FDTD algorithm under “unidirectional explicit” matrix was constructed and applied to cylindrical structure.Firstly, a new coefficient matrix was established by the ideology of WCS and WLP.Secondly, the perturbation terms were introduced to form the initial value and iterative equations.Finally, the fields on the z axis were treated in special way.Numerical examples prove that the proposed algorithm is superior to the WCS-FDTD and WLP-FDTD in electromagnetic wave propagation.The best improvement efficiency is 83%, accuracy is 88%, and memory consumption is reduced by 44%.Meanwhile, comparing with the conventional FDTD algorithm, it can improve the efficiency of 7 time steps size and reduce the memory consumption by 53% without losing accuracy.Moreover, under the boundary truncation of the PML, the proposed algorithm also shows good electromagnetic wave energy absorption performance, which can reach below -60 dB.…”
Get full text

WTL-CNN: a news text classification method of convolutional neural network based on weighted word embedding by Weidong Zhao, Lin Zhu, Ming Wang, Xiliang Zhang, Jinming Zhang

“…Secondly, an improved TF-IDF algorithm is proposed to weight word vectors. The improved TF-IDF algorithm introduces LDA topic generation model to enhance the topic semantic information of TF-IDF values. …”
Get full text

Tennis action recognition and evaluation with inertial measurement unit and SVM by Jinxia Gao, Guodong Zhang

“…For amateur enthusiasts, the algorithm exhibited an average accuracy of 94.08 %. …”
Get full text

Assessment of a Smartphone-Based Neural Network Application for the Risk Assessment of Skin Lesions under Real-World Conditions by Teresa Maria Kränke, Philipp Efferl, Katharina Tripolt-Droschl, Rainer Hofmann-Wellenhof

“…The tested algorithm reached a sensitivity of 76.9% (CI 71.7%-81.5%) and a specificity of 80.9% (CI 78.5%-83.2%). …”
Get full text

Guaranteed convergence control for consensus of mobile sensor networks with dynamical topologies by Xiangshun Li, Cheng Lei, Lijing Dong, Sing-Kiong Nguang

“…In these scenarios, it is very important to reduce the power consumption as well as make sensors reach consensus as fast as possible. In this article, we propose a novel guaranteed convergence control algorithm to switch topologies of mobile sensors so that we can reduce power consumption in the sensor network and make the mobile sensors reach consensus with guaranteed convergence as well. …”
Get full text

Multicast resource allocation scheme considering source-coding characteristic in OFDM systems by XU Wen-jun, HE Zhi-qiang, NIU Kai, LIN Jia-ru, WU Wei-ling

“…Aiming to solve the problem that unicast or conventional multicast was incapable of make full use of the opening for wireless propagation in orthogonal frequency division multiplexing（OFDM） systems,a resource allocation scheme involving several multicast groups was proposed to maintain proportional fairness among groups.The proposed scheme consisted of subcarrier assignment algorithm and power allocation algorithm.The former was achieved by modi-fying the existing unicast subcarrier assignment algorithm,whilst optimal power allocation on condition that subcarrier assignment was determined was reached by the latter based on theoretically derived non-linear equations.Simulation re-sults show that the proposed scheme can ensure perfect fairness among different multicast groups,and remarkably out-performs conventional multicast in terms of rate-sum capacity.Combined with the low complexity,it is suitable for the application to voice/video multicast in actual wireless systems.…”
Get full text

Electricity Demand Projection Using a Path-Coefficient Analysis and BAG-SA Approach: A Case Study of China by Qunli Wu, Chenyang Peng

“…Results indicate that the proposed algorithm has higher precision and reliability than the coefficients optimized by other single-optimization methods, such as genetic algorithm, particle swarm optimization algorithm, or bat algorithm. …”
Get full text

A Method for Detecting Tomato Maturity Based on Deep Learning by Song Wang, Jianxia Xiang, Daqing Chen, Cong Zhang

“…The algorithm employs several technical means to improve detection accuracy and efficiency. …”
Get full text

Iraqi Stock Market Prediction Using Artificial Neural Network and Long Short-Term Memory by Sama Hayder Abdulhussein AlHakeem, Nashaat Jasim Al-Anber, Hayfaa Abdulzahra Atee, Mahmod Muhamad Amrir

“…In this paper, two models were proposed to predict the Iraqi stock markets index through the use of artificial neural networks (ANN) and a long short-term memory (LSTM) algorithm where Iraqi stock market data were used from 2017 to 2021 and good results were achieved in the prediction where the long short-term memory (LSTM) algorithm reached a mean square error (MSE) rate of as little as 0.0016 while the artificial neural network (ANN) algorithm reached error rate 0.0055. …”
Get full text

A Study of Corrosion-Grade Recognition on Metal Surfaces Based on Improved YOLOv8 Model by Hao Chen, Ying Cao, Shengxian Cao, Heng Piao

“…The experiments verify that the improved model is comprehensively leading in multi-dimensional indicators: the mAP reaches 96.3% and the F1 score reaches 93.6%, which is significantly better than mainstream models such as Faster R-CNN, and provides a reliable technical solution for the intelligent inspection of substation equipment.…”
Get full text

Intelligent garbage sorting truck system based on deep learning by Wang Hui, Jiang Chaogen

“…The experimental test results show that the average accuracy reaches 91.8%, the accuracy rate reaches 94.5%, and the recall rate reaches 89.03%.…”
Get full text

Design of a Novel UWB Omnidirectional Antenna Using Particle Swarm Optimization by Chengyang Yu, Tanghong Xu, Changjun Liu

“…Furthermore, the measured antenna polarization purity reaches about 20 dB at the communication C band. The PSO algorithm is a powerful candidate for microwave passive component design.…”
Get full text

Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning by Haomin Tang, Shu Liu, Yongxin Shi, Jin Wei, Juxiang Peng, Hongchao Feng

“…Among them, the dice of the semi-supervised algorithm adopted in this study reached 93.41 and 96.89% in maxillary and mandibular segmentation tasks, and the average error of landmark detection tasks reached 1.908 ± 1.166 mm, both of which were superior to the full-supervised algorithm with the same data volume annotation. …”
Get full text

Improving care pathways for children with severe illness through implementation of the ASPIRE mHealth primary ETAT package in Malawi. by Nicola Desmond, Marc Y R Henrion, Mtisunge Gondwe, Thomasena O'Byrne, Pui-Ying Iroh Tam, Deborah Nyirenda, Louisa Pollock, Maureen Daisy Majamanda, Martha Makwero, Marije Geldof, Queen Dube, Chimwemwe Phiri, Chimwemwe Banda, Rabson Kachala, Prof Robert S Heyderman, Clemens Masesa, Norman Lufesi, David G Lalloo

“…Implementation of ETAT through an mHealth algorithm documented successful referrals from primary to tertiary, but half of referred patients did not reach the tertiary site. …”
Get full text