检索结果-内蒙古大学图书馆

Application of convolutional neural network for facial expression recognition 6

学校读者我要写书评

暂无评论

Application of convolutional neural network for facial expre...

6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020

作者： Clinton Atabansi, Chukwuemeka School of Electronic and Information Engineering Southwest University China No.2 Tiansheng Rd. Beibei District Chongqing400715 China Chongqing Key Laboratory of Nonlinear Circuit and Intelligent Information Processing Southwest University China No.2 Tiansheng Rd. Beibei District Chongqing400715 China

ISBN: (纸本)9781450388597

The recognition of people's expression has been a very difficult task for computers from the time of its invention and still continues to pose a lot of challenges to the modern day generation of computers. To solve this problem, Convolutional Neural Network (CNN) is used which involves the application of preprocessing, feature extraction, training technique, and testing modules/methods to determine facial expression recognition. These methods were tested on the Oulu-CASIA VIS dataset [1]. The results obtained classified images of people's facial expressions into six (6) distinct emotional classes, viz (anger, disgust, fear, happiness, sadness and surprise) showing an average accuracy of 98.99% and thus affirming that the application of the convolutional neural network (CNN) in facial expression recognition is efficient. © 2020 ACM.

关键词： Face recognition

Reversible Data Hiding Based on Improved Rhombus Prediction Method

学校读者我要写书评

暂无评论

Reversible Data Hiding Based on Improved Rhombus Prediction ...

International Conference on intelligent Control and information processing (ICICIP)

作者： Simi Lu Xiaofeng Liao Nankun Mu Jiahui Wu Junqing Le Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Electronic and Information Engineering Southwest University Chongqing P.R. China Computer Science Chongqing University Chongqing P. R. China

ISBN: (数字)9781728100159

ISBN: (纸本)9781728100166

Reversible data hiding(RDH) is a research hotspot in the field of information hiding. Among them, RDH based on histogram shift(HS) is a high performance algorithm. Accurate pixel prediction can reduce image distortion while maintaining high capacity. Therefore, this paper proposes an RDH algorithm based on the improved rhombus prediction method. Experiments show that the improved rhombus prediction method can predict pixels more accurately, and the generated prediction error histogram is more compact and clear. The proposed RDH algorithm has a higher embedding capacity and a lower distortion rate.

关键词： intelligent control information processing Airplanes

(Rectified Version) The Barzilai-Borwein Method for Distributed Optimization over Unbalanced Directed Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hu, Jinhui Chen, Xin Zheng, Lifeng Zhang, Ling Li, Huaqing Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China School of Big Data & Software Engineering Chongqing University Chongqing401331 PR China

This paper studies optimization problems over multi-agent systems, in which all agents cooperatively minimize a global objective function expressed as a sum of local cost functions. Each agent in the systems uses only local computation and communication in the overall process without leaking their private information. Based on the Barzilai-Borwein (BB) method and multi-consensus inner loops, a distributed algorithm with the availability of larger step-sizes and accelerated convergence, namely ADBB, is proposed. Moreover, owing to employing only row-stochastic weight matrices, ADBB can resolve the optimization problems over unbalanced directed networks without requiring the knowledge of neighbors’ out-degree for each agent. Via establishing contraction relationships between the consensus error, the optimality gap, and the gradient tracking error, ADBB is theoretically proved to converge linearly to the globally optimal solution. A real-world data set is used in simulations to validate the correctness of the theoretical analysis. Copyright © 2023, The Authors. All rights reserved.

关键词： Multi agent systems

Identifying strong stress and weak stress through blood volume pulse

学校读者我要写书评

暂无评论

Identifying strong stress and weak stress through blood volu...

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Jialan Xie Wanhui Wen Guangyuan Liu Chuanwu Chen Jie Zhang Hong Liu Chongqing Key Laboratory of Nonlinear Ciruits and Intelligent Processing Chongqing China School of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9781509034857

This paper explored the difference between weak stress (WS) and strong stress (SS) on the relative ejection period (REP) of the blood volume pulse (BVP). Features were extracted from the REP series to recognize WS and SS. The blood volume pulse data were acquired during the defense of 31 graduate students for their master's degree under the real stress environment. The result shows that, in the real stress situation, the features of REP have obtained a correct rate of 91.93% in distinguishing strong stress state and weak stress state.

关键词： Stress Data acquisition Blood Feature extraction Neural networks Time series analysis Wrist

Finite-Time Couple-Group Consensus for Fractional-Order Multi-Agent Systems with Coopetition Interactions

学校读者我要写书评

暂无评论

Finite-Time Couple-Group Consensus for Fractional-Order Mult...

Chinese Control and Decision Conference, CCDC

作者： Rong Wu Lianghao Ji Cuijuan Zhang Shasha Yang Xing Guo Huaqing Li Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Chongqing Key Laboratory of Nonlinear Circuits and Intelligence Information Processing College of Electronic and Information Engineering Southwest University Chongqing China

ISBN: (纸本)9781665478977

The problem of finite-time couple-group consensus for fractional-order multi-agent systems with weakly connected topology is investigated in this paper through pinning control. A new error variable based on cooperative and competitive interactions among agents is introduced to transform the fractional-order multi-agent system into a first-order multi-agent system and a novel group consensus protocol is designed for the transformed system. By applying the Lyapunov approach and matrix theory, several sufficient conditions are obtained to ensure the achievement of finite-time couple-group consensus of the system. In addition, the settling time is upper bounded by a definite value, which is independent of the initial states. Finally, the correctness and validity of our findings are verified through some numerical simulations.

关键词： Sufficient conditions Upper bound Transforms Numerical simulation Control systems Topology Consensus protocol

Distributed Online Private Learning of Convex Nondecomposable Objectives

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

In the machine learning domain, datasets share several new features, including distributed storage, high velocity, and privacy concerns, which naturally requires the development of distributed privacy-preserving algorithms. Moreover, nodes (e.g., learners, sensors, GPUs, mobiles, etc.) in the real networks usually process tasks in real time, which inevitably requires nodes to have online learning capabilities. Therefore, we deal with a general distributed constrained online learning problem with privacy over time-varying networks, where a class of nondecomposable objectives are considered. Under this setting, each node only controls a part of the global decision, and the goal of all nodes is to collaboratively minimize the global cost over a time horizon T while guarantees the security of the transmitted information. For such problems, we first design a novel generic algorithm framework, named as DPSDA, of differentially private distributed online learning using the Laplace mechanism and the stochastic variants of dual averaging method. Note that in the dual updates, all nodes of DPSDA employ the noise-corrupted gradients for more generality. Then, we propose two algorithms, named as DPSDA-C and DPSDA-PS, under this framework. In DPSDA-C, the nodes implement a circulation-based communication in the primal updates so as to alleviate the disagreements over time-varying undirected networks. In addition, for the extension to time-varying directed ones, the nodes implement the broadcast-based push-sum dynamics in DPSDA-PS, which can achieve average consensus over arbitrary directed networks. Theoretical results show that both algorithms attain an expected regret upper bound in O(√T) when the objective function is convex, which matches the best utility achievable by cutting-edge algorithms. Finally, numerous numerical experiments on both synthetic and real-world datasets verify the effectiveness of our algorithms. © 2022, CC BY.

关键词： Stochastic systems

Privacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Zhao, You Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

Distributed optimization is manifesting great potential in multiple fields, e.g., machine learning, control, and resource allocation. Existing decentralized optimization algorithms require sharing explicit state information among the agents, which raises the risk of private information leakage. To ensure privacy security, combining information security mechanisms, such as differential privacy and homomorphic encryption, with traditional decentralized optimization algorithms is a commonly used means. However, this would either sacrifice optimization accuracy or incur heavy computational burden. To overcome these shortcomings, we develop a novel privacy-preserving decentralized optimization algorithm, called PPSD, that combines gradient tracking with a state decomposition mechanism. Specifically, each agent decomposes its state associated with the gradient into two substates. One substate is used for interaction with neighboring agents, and the other substate containing private information acts only on the first substate and thus is entirely agnostic to other agents. For the strongly convex and smooth objective functions, PPSD attains a R-linear convergence rate. Moreover, the algorithm can preserve the agents’ private information from being leaked to honest-but-curious neighbors. Simulations further confirm the results. © 2023, CC BY.

关键词： Optimization

Loading Effects of the Human Body on An Ultrawideband Wearable Textile Antenna 12

学校读者我要写书评

暂无评论

Loading Effects of the Human Body on An Ultrawideband Wearab...

12th IEEE Asia-Pacific Conference on Antennas and Propagation, APCAP 2024

作者： Xu, Ziang Gao, Xiang Mao, Zhuzhang Tang, Wenfei Guo, Kun Beijing Institute of Technology School of Cyberspace Science and Technology Beijing100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing100081 China Beijing Institute of Technology School of Integrated Circuits and Electronics Beijing100081 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China

ISBN: (纸本)9798350351019

This paper presents an ultrawideband wearable textile antenna for emergency communication applications, and investigates the loading effects of the human body on radiation performance of the antenna. The proposed antenna has a measured operating bandwidth from 0.31 to 1.2 GHz and an average realized gain of 3.32 dBi in free space. Furthermore, the results show that the antenna gain can effectively be improved by properly adjusting the distance between the human body and the antenna. © 2024 IEEE.

关键词： Wearable antennas

Secrecy outage analysis of mixed RF-FSO downlink SWIPT systems

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Lei, Hongjiang Dai, Zhijun Park, Ki-Hong Lei, Weijia Pan, Gaofeng Alouini, Mohamed-Slim Chongqing Key Lab of Mobile Communications Technology Chongqing University of Posts and Telecommunications Chongqing400065 China Thuwal23955-6900 Saudi Arabia Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing Southwest University Chongqing400715

We analyze a secure dual-hop mixed radio frequency-free space optical (RF-FSO) downlink simultaneous wireless information and power transfer (SWIPT) systems. The FSO link and all RF links experience Gamma-Gamma, independent and identical Nakagami-mfading, *** analyze the effects of atmospheric turbulence, pointing error, detection technology, path loss, and energy harvesting on secrecy performance. Signal-to-noise ratios at both legitimate and illegitimate receivers are not independent since they are both simultaneously influenced by the FSO link. We derive the closedform expression of the secrecy outage probability (SOP) as well as the asymptotic result for SOP when signal-to-noise ratios at relay and legitimate destinations tend to infinity. Monte-Carlo simulations are performed to verify the accuracy of our analysis. The results show that the secrecy diversity order (SDO) depends on the fading parameter of the relay-destination link and the number of the destination's antennas. Additionally, the SDO also depends on the fading parameters, the pointing error parameter, and the detection type of the FSO link. Copyright © 2018, The Authors. All rights reserved.

关键词： Monte Carlo methods