Laser Radar System Based on Lightweight Diffractive Lens Receiver System by Jiajia Yin, Mengxia Hou, Bin Fan, Jiang Bian, Junfeng Du

“…Diffractive lens has advantages over traditional reflective lens, such as light weight, high folding compression ratio, high tolerance for surface figure error and low manufacturing costs. …”
Get full text

Study on Three-Dimensional Digital Expression and Robot Bending Method of Orthodontic Archwire by Jingang Jiang, Xuefeng Ma, Yongde Zhang, Biao Huo, Yi Liu

Get full text

Study of Hardness of Superhard Crystals by Topological Indices by Xiujun Zhang, Muhammad Naeem, Abdul Qudair Baig, Manzoor Ahmad Zahid

Get full text

Exploring Factors Contributing to Crash Injury Severity in the Rural-Urban Fringe of the Central City by Biao Wu, Xingyu Wang, Tuo Liu, Naibao Dong, Yun Li

Get full text

Privacy-preserving federated learning framework with irregular-majority users by Qianxin CHEN, Renwan BI, Jie LIN, Biao JIN, Jinbo XIONG

“…In response to the existing problems that the federated learning might lead to the reduction of aggregation efficiency by handing the majority of irregular users and the leak of parameter privacy by adopting plaintext communication, a framework of privacy-preserving robust federated learning was proposed for ensuring the robustness of the irregular user based on the designed security division protocol.PPRFL could enable the model and its related information to aggregate in ciphertext on the edge server facilitate users to calculate the model reliability locally for reducing the additional communication overhead caused by the adoption of the security multiplication protocol in conventional methods, apart from lowering the high computational overhead resulted from homomorphic encryption with outsourcing computing to two edge servers.Based on this, user could calculate the loss value of the model through jointly using the verification sets issued by the edge server and that held locally after parameter updating of the local model.Then the model reliability could be dynamically updated as the model weight together with the historic information of the loss value.Further, the model weight was scaled under the guidance of prior knowledge, and the ciphertext model and ciphertext weight information are sent to the edge server to aggregate and update the global model parameters, ensuring that global model changes are contributed by high-quality data users, and improving the convergence speed.Through the security analysis of the Hybrid Argument model, the demonstration shows that PPRFL can effectively protect the privacy of model parameters and intermediate interaction parameters including user reliability.The experimental results show that the PPRFL scheme could still achieve the accuracy of 92% when all the participants in the federated aggregation task are irregular users, with the convergence efficiency 1.4 times higher than that of the PPFDL.Besides, the PPRFL scheme could still reach the accuracy of 89% when training data possessed by 80% of the users in the federated aggregation task were noise data, with the convergence efficiency 2.3 times higher than that of the PPFDL.…”
Get full text

Macro-Micro Study on Mechanical Properties of Frozen Fine Sandstone Based on DEM Mathematical Model by Maoyan Ma, Min You, Shuguang Peng, Biao Zhang, Yuan Lin

Get full text

Multisignal VGG19 Network with Transposed Convolution for Rotating Machinery Fault Diagnosis Based on Deep Transfer Learning by Jianye Zhou, Xinyu Yang, Lin Zhang, Siyu Shao, Gangying Bian

“…To realize high-precision and high-efficiency machine fault diagnosis, a novel deep learning framework that combines transfer learning and transposed convolution is proposed. …”
Get full text

Pulmonary Langerhans Cell Histiocytosis Presenting as a Solitary Pulmonary Nodule on a Lung Cancer Screening CT by Hassan Baig, Sushilkumar Sonavane, Ian Makey, Jorge Mallea, Andras Khoor

Get full text

TOPOLOGY OPTIMIZATION DESIGN OF HIGH SPEED EMU GEARBOX by GAO Yang, QUE HongBo, BIAN Xiang, WEI YuZhou

Subjects: “…High-speed EMU gearbox…”
Get full text

Enhanced Light Response Performance of Ceria-Based Composites with Rich Oxygen Vacancy by Yanping Li, Xue Bian, Hui Dong, Hongtao Chang, Wenyuan Wu

“…The remarkable light response performance of Ce-O-S composites can be mainly attributed to the high proportion of oxygen vacancy. Moreover, the higher proportion of oxygen vacancies can be attributed to the doping of Ce (+3) and S (−2) in the lattice of CeO₂, and the synergistic effect of CeO₂, Ce₄O₄S₃, and Ce₂(SO₄)₃. …”
Get full text

In Vivo Distribution and Therapeutic Efficacy of Radioiodine-Labeled pH-Low Insertion Peptide Variant 3 in a Mouse Model of Breast Cancer by Min Zhang, Yue Xi, Hong Chen, Wangxi Hai, Biao Li

“…Extracellular acidity is a marker of highly aggressive breast cancer (BC). pH-low insertion peptides (pHLIPs) target the acidic tumor microenvironment. …”
Get full text

An Improved Stochastic Model for the Geodetic GNSS Receivers Under Ionospheric Scintillation at Low Latitudes by Xiaomin Luo, Yingzong Lin, Xiaolei Dai, Shaofeng Bian, Dezhong Chen

Get full text

Investigation of Traffic Loading Effects for Different Codes on Medium- and Small-Span Girder Bridges in China by Qingfei Gao, Biao Wu, Jun Li, Kemeng Cui, Chuang Xu

Get full text

Lightweight decentralized learning-based automatic modulation classification method by Jie YANG, Biao DONG, Xue FU, Yu WANG, Guan GUI

“…In order to solve the problems in centralized learning, a lightweight decentralized learning-based AMC method was proposed.By the proposed decentralized learning, a global model was trained through local training and model weight sharing, which made full use of the dataset of each communication nodes and avoided the user data leakage.The proposed lightweight network was stacked by a number of different lightweight neural network blocks with a relatively low space complexity and time complexity, and achieved a higher recognition accuracy compared with traditional DL models, which could effectively solve the problems of computing power and storage space limitation of edge devices and high communication overhead in decentralized learning based AMC method.The experimental results show that the classification accuracy of the proposed method is 62.41% based on RadioML.2016.10 A.Compared with centralized learning, the training efficiency is nearly 5 times higher with a slight classification accuracy loss (0.68%).In addition, the experimental results also prove that the deployment of lightweight models can effectively reduce communication overhead in decentralized learning.…”
Get full text

Heat Partition between the Friction Components in Multi-disc Clutch during Sliding by Xiong Cenbo, Ma Biao, Li Heyan, Zhang Fenglian, Zhu Li’an

Get full text

Biosynthesis of silver nanoparticles from macroalgae Hormophysa triquetra and investigation of its antibacterial activity and mechanism against pathogenic bacteria by Shazia Bibi, Mohammed H. Abu-Dieyeh, Mohammad A. Al-Ghouti

Get full text

BSG-WSL: BackScatter-guided weakly supervised learning for water mapping in SAR images by Kai Wang, Zhongle Ren, Biao Hou, Weibin Li, Licheng Jiao

“…In this article, a BackScatter-Guided Weakly Supervised Learning (BSG-WSL) framework based on image-level labels is proposed for water extraction with the requirement of high generalization and low labeling. …”
Get full text

Performance analysis of generalized orthogonal code index modulation system by Lina BIAN, Huizhen FENG, Xiaoping JIN, Weizhong LOU, Chongxiao QU

“…In order to improve the transmission efficiency of the code index modulation (CIM) system, a generalized orthogonal code index modulation (GQCIM) system with lower complexity was proposed, which was a single input single output (SISO) system.CIM system used spreading codes and constellation symbols to transmit information, but only activated two spreading code indexes and one modulation symbol.GQCIM system overcame the limitation of only activating one modulation symbol at a time in a novel way, at the same time, made full use of the orthogonality of modulation symbols, increased the spreading code index to transmit more additional information bits, and improved the transmission efficiency of the system.In addition, the theoretical performance of GQCIM system was analyzed and derived the upper bound of bit error rate performance.Then the performance of GQCIM was verified by Monte Carlo simulation, and the theoretical and simulation performance of GQCIM system was found to be consistent.And under the same transmission efficiency, the results show that the performance of GQCIM system is better than the same orthogonal modulation system, such as generalized code index modulation (GCIM) system, CIM system, code index modulation aided quadrature spatial modulation (CIM-QSM) system, code index modulation aided spatial modulation (CIM-SM) system, pulse index modulation (PIM) system.…”
Get full text

Anomaly Detection in Spatiotemporal Data from Fiber Optic Distributed Temperature Sensing for Outdoor Fire Monitoring by Haitao Bian, Xiaohan Luo, Zhichao Zhu, Xiaowei Zang, Yu Tian

“…Fiber Optic Distributed Temperature Sensing (FO-DTS), recognized for its high sensitivity and broad monitoring range, provides significant advantages in detecting outdoor fires. …”
Get full text

Laboratory Study on Core Fracturing Simulations for Wellbore Strengthening by Biao Ma, Xiaolin Pu, Zhengguo Zhao, Hao Wang, Wenxin Dong

Get full text