检索结果-内蒙古大学图书馆

Challenges with reinforcement learning in prosthesis

Materials Today: Proceedings 2022年 49卷 3133-3136页

作者： Deepali Salwan Shri Kant Himanshu Pareek Roopali Sharma Pt. Deen Dayal Upadhyaya National Institute for Physically Handicapped New Delhi India Research and Technology Development Centre Department of Computer Science School of Engineering and Technology Sharda University Greater Noida India M.Tech IIT Hyderabad India M.Tech Amity University India

Reinforcement Learning has work wonders in games like Atari and AlphaZero. Recent advancement in Deep Reinforcement Learning showcase it’s ability in the active Prosthesis as well. RL is being used widely to solve problems where Learning of the Agent in its own environment is as necessary as training the model beforehand. However, model developed, and successful in the gaming environment could still need to be tuned to be effective with Real Time devices such as Prosthetic Limb and other Real-World devices. In this article, main challenges are presented which we face while working on a Model Based and Model Free Reinforcement Learning in real world environment and suggesting an approach which would work uniformly on most of the Real Time scenarios. We observed the performance and noticed that there are couple of factors which needs to be taken care of in Real Time Applications which are not much though about in games and other online applications. We also compared the algorithms such as Policy Proximal Optimization (PPO) and Deep Deterministic Policy Gradient (DDPG) vs Model Based Policy search with Gaussian Processes and found out that a mix of Model-Based and Model-Free (MBMF) performed the best individually despite of all the challenges.

关键词： Reinforcement learning Artificial intelligence Deep learning Challenges Model-based Model-free Prosthesis OpenSim

来源：评论

学校读者我要写书评

暂无评论

从四方到立方:高性能太阳能电池的钙钛矿相结构演变

引用

Science Bulletin 2023年第2期68卷 141-145,M0003页

作者：魏旗梁昊 Yuki Haruta Makhsud Saidaminov 米启兮 Michael Saliba 崔光磊宁志军 School of Physical Science and Technology ShanghaiTech UniversityShanghai 201210China High Performance Computing Department National Supercomputing Center in ShenzhenShenzhen 200441China Department of Chemistry and Department of Electrical&Computer Engineering and Centre for Advanced Materials and Related Technologies(CAMTEC) University of VictoriaVictoria V8P 5C2Canada Institute for Photovoltaics University of StuttgartStuttgart 70569Germany Qingdao Industrial Energy Storage Research Institute Qingdao Institute of Bioenergy and Bioprocess TechnologyChinese Academy of SciencesQingdao 266101China

Crystal structure, which is generally determined by the composition, ionic radius and valence state of constituent elements, plays a significant role in the material’s fundamental properties such as optical, electronic, and mechanical characters. The manipulation of the crystal structure through compositional engineering, and understanding the relationship between crystal structure and properties are essential for the development of materials.

关键词：太阳能电池结构演变钙钛矿相

来源：评论

学校读者我要写书评

暂无评论

Observation of New Class of Bright Solitons: Tower and Volcano Solitons

Observation of New Class of Bright Solitons: Tower and Volca...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Michal Kwasny Urszula A. Laudyn Miroslaw Karpierz Marek Trippenbach David Hagan Demetrios Christodoulides Wieslaw Krolikowski Pawel S. Jung Faculty of Physics Warsaw University of Technology Warsaw Poland Faculty of Physics University of Warsaw Warsaw Poland CREOL The College of Optics and Photonics University of Central Florida Orlando Florida USA Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles California USA Laser Physics Centre Research School of Physics Australian National University Canberra Australia

We report the first experimental observation of a novel fundamental soliton class, termed Tower and Volcano solitons, in soft-matter systems characterized by nonlinear responses driven by competing nonlocal interactio... 详细信息

ISBN: (纸本)9798350369311

关键词： Phase modulation Poles and towers Refractive index Optical solitons Electro-optic modulators Optical variables control Volcanoes Optical refraction Optical modulation Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

DynBlock: dynamic data encryption with Toffoli gate for IoT

引用

Scientific Reports 2025年第1期15卷 1-28页

作者： Haq, Mubasher Shoukat, Ijaz Ali Naushad, Alamgir Jafri, Mohsin Raza Sandhu, Moid Khan, Abd Ullah Shin, Hyundong Department of Computing Riphah International University Faisalabad 38000 Pakistan Department of Computer Science National University of Sciences and Technology Balochistan Campus Quetta Pakistan Australian e-Health Research Centre (AEHRC) CSIRO Brisbane Australia Queensland University of Technology Brisbane Australia CQI Lab Department of Information and Electronics Convergence Engineering Kyung Hee University Yongin 17104 Gyeonggi South Korea

The emergence of 6G networks, coupled with the expansion of smart devices, necessitates robust and efficient cryptography solutions to ensure secure communication. However, the existing resource-constrained cryptography solutions that rely on static permutation, substitution methods, variable key sizes, and fixed block size are vulnerable to quantum computing-based cryptanalysis and side-channel attacks. To address these challenges, this paper proposes a lightweight dynamic block cipher (DynBlock) algorithm. DynBlock is specifically suitable for resource-limited devices, and features a dynamic block size (64-128 bits), which is adaptable to symmetric encryption key sizes. Additionally, DynBlock includes dynamic permutation and substitution layers that enhance confusion and diffusion properties, along with a novel substitution-permutation network (SPN) algorithm that eliminates conventional substitution- and permutation-boxes. DynBlock leverages Tofoli gates and XOR operations to reduce the number of computation operations required to achieve optimal throughput and energy efficiency. Security validation of DynBlock is performed considering various metrics, including an average key avalanche effect of 53.85%, average plain-text avalanche effect of 57.82%, differential cryptanalysis (), and cryptanalysis (). Performance is compared against various state-of-the-art schemes. We evaluate DynBlock with both 3 and 5 rounds to assess its security and computational efficiency. While the 5-round configuration offers stronger resistance to cryptanalytic attacks, the 3-round setup already delivers robust security, featuring high entropy and a strong avalanche effect, making it well-suited for resource-constrained environments. It is found that DynBlock significantly improves energy efficiency and throughput compared to its predecessors. Additionally, DynBlock demonstrates resistance to quantum computing-based attacks, improved side-channel attack resilience, and enhanced randomn

关键词： Dynamic block cipher IoT security Lightweight cryptography Substitution-permutation network (SPN) Toffoli gates

来源：评论

学校读者我要写书评

暂无评论

Redesign NAMD molecular dynamics non-bonded force-field on sunway manycore processor 21

Redesign NAMD molecular dynamics non-bonded force-field on s...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Chen, Junshi An, Hong Yan, Binghui Liang, Weihao Liu, Xin Department of Computer Science and Technology University of Science and Technology of China China National Research Center of Parallel Computer Engineering and Technology Beijing China

ISBN: (纸本)9781728120584

NAnoscale Molecular Dynamics (NAMD) is a parallel molecular dynamics application used to study the structure and dynamics of large biomolecular complexes, such as various types of viruses. In a biomolecular system, billions of time steps are required to understand the biological phenomena of interest. It requires enormous computing power to have a long-timescale observation of the molecule behavior of a large simulation system. NAMD meets this demand with thousands of state-of-the-art manycore processors. The Sunway Taihulight supercomputer is the number one computing system in the top 500 list of supercomputers in November 2017, with a peak performance of 125 PFlops and equipped with 40,960 SW26010 manycore processors. In this paper, we present various optimization techniques that enable the non-bonded force calculation, which is the most computation intensive and time-consuming part of NAMD, to achieve high performance on the SW26010 manycore processor. The optimizations include software cache design on local data memory, separated computing and storage cores, fine-grained inter-core data communication for fast force updating, and vectorization. © 2019 IEEE.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models

arXiv

引用

arXiv 2020年

作者： Zhang, Yufeng Pan, Jialu Liu, Wanwei Chen, Zhenbang Li, Kenli Wang, Ji Liu, Zhiming Wei, Hongmei College of Computer Science and Electronic Engineering Hunan University Changsha China College of Computer National University of Defense Technology Changsha China Centre for Research and Innovation in Software Engineering Southwest University Chongqing China National Research Center of Parallel Computer Engineering and Technology China

—Recent research has revealed that deep generative models including flow-based models and Variational Autoencoders may assign higher likelihoods to out-of-distribution (OOD) data than in-distribution (ID) data. However, we cannot sample OOD data from the model. This counterintuitive phenomenon has not been satisfactorily explained and brings obstacles to OOD detection with flow-based models. In this paper, we prove theorems to investigate the Kullback-Leibler divergence in flow-based model and give two explanations for the above phenomenon. Based on our theoretical analysis, we propose a new method KLODS to leverage KL divergence and local pixel dependence of representations to perform anomaly detection. Experimental results on prevalent benchmarks demonstrate the effectiveness and robustness of our method. For group anomaly detection, our method achieves 98.1% AUROC on average with a small batch size of 5. On the contrary, the baseline typicality test-based method only achieves 64.6% AUROC on average due to its failure on challenging problems. Our method also outperforms the state-of-the-art method by 9.1% AUROC. For point-wise anomaly detection, our method achieves 90.7% AUROC on average and outperforms the baseline by 5.2% AUROC. Besides, our method has the least notable failures and is the most robust one. Copyright © 2020, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of UAV-enabled backscatter wireless communication network 2

Performance analysis of UAV-enabled backscatter wireless com...

引用

2nd ACM MobiCom Workshop on Drone Assisted Wireless Communications for 5G and Beyond, DroneCom 2020

作者： Nagarajan, Deepan Jayakody, Dushantha Nalin K. Balakrishnan, Rebekka Department of ECE National Institute of Technology Tiruchirappalli India School of Computer Science and Robotics National Research Tomsk Polytechnic University Russia Centre for Telecommunication Research School of Engineering Sri Lanka Technological Campus Sri Lanka

ISBN: (纸本)9781450381055

Unmanned aerial vehicle (UAV) has been considered as a widespread technical solution in recent years to meet the explosive data and massive device connections demands. On the other hand, Backscatter communication (BackComm) also equally evolved as a potential candidate to realize future Internet-of-Things (IoT) networks. By deploying BackComm in UAV-enabled IoT system allows an efficient utilization of the network resources, especially, in remote areas and smart cities. In this paper, we investigate the performance of a UAVassisted multi-node BackComm network over generalized - shadowed fading channel. Closed-form expressions are derived to study the system performance through outage probability and average BER. Additionally, we obtain a simplified asymptotic expression in a high SNR regime, from which we gain insight into how the channel and system parameters affect the overall performance. Finally, simulation results are provided to validate the derived theoretical results. © 2020 Association for Computing Machinery.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient UAV Communications With Directional Antennas: Tilting Effect Modeling and Trajectory Optimization

引用

IEEE Transactions on Vehicular technology 2025年

作者： Dai, Xinhong Duo, Bin Yuan, Xiaojun Di Renzo, Marco National Key Laboratory of Wireless Communications The University of Electronic Science and Technology of China Chengdu611731 China Department of Communication Science and Engineering Fudan University Shanghai200433 China College of Computer Science and Cyber Security Chengdu University of Technology Chengdu610059 China Université Paris-Saclay Cnrs CentraleSupélec Laboratoire des Signaux et Systèmes 3 Rue Joliot-Curie Gif-sur-Yvette91192 France King's College London Centre for Telecommunications Research Department of Engineering LondonWC2R 2LS United Kingdom

Directional antennas have been widely used in UAV communications to improve the transmission efficiency. For a UAV mounted with directional antennas, its tilting effect has a crucial impact on the communication performance, which is however ignored in the related studies. In this paper, we first characterize the relationship between the tilting effect of the UAV and its flight status based on force analysis. Then, we investigate a UAV-enabled downlink communication system, where the UAV, equipped with a directional antenna, provides communication services to ground users (GUs). We formulate an energy efficiency (EE) maximization problem that optimizes the UAV trajectory under the consideration of the tilting effect. The formulated problem is challenging to solve due to the complicated expressions of the directional antenna radiation pattern and the adopted propulsion energy consumption model of the UAV. To tackle this, by utilizing the successive convex approximation technique, we propose an approximate antenna radiation pattern that serves as a convex lower bound of the original antenna gain, and develop an efficient algorithm to obtain a suboptimal solution. Simulation results show that the negative impact of the tilting effect on the EE can be efficiently mitigated and the UAV flight can be made more steady under the tilting effect. In addition, the proposed algorithm allows the UAV to achieve a substantially higher EE compared to the benchmark schemes. © 2025 IEEE.

关键词： Directional patterns (antenna)

来源：评论

学校读者我要写书评

暂无评论

Spatially Non-Stationary XL-MIMO Channel Estimation: A Three-Layer Generalized Approximate Message Passing Method

arXiv

引用

arXiv 2024年

作者： Tang, Anzheng Wang, Jun-Bo Pan, Yijin Zhang, Wence Chen, Yijian Yu, Hongkang de Lamare, Rodrigo C. The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The School of Computer Science and Communication Engineering Jiangsu University Zhenjiang212013 China The Wireless Product Research and Development Institute ZTE Corporation Shenzhen518057 China The Centre for Telecommunications Studies Pontifical Catholic University of Rio de Janeiro Rio de Janeiro22451-900 Brazil The School of Physics Engineering and Technology University of York YorkYO10 5DD United Kingdom

In this paper, the channel estimation problem for extremely large-scale multi-input multi-output (XL-MIMO) systems is investigated with the considerations of near-field (NF) spherical wavefront effects and spatially non-stationary (SnS) properties. Due to the diversity of SnS characteristics across different propagation paths, the concurrent channel estimation of multiple paths becomes intractable. To address this challenge, we propose a two-phase estimation scheme that decouples the problem into multiple subchannel estimation tasks. To solve these sub-tasks, we introduce a novel three-layer Bayesian inference scheme, exploiting the correlations and sparsity of the SnS subchannels in both the spatial and angular domains. Specifically, the first layer captures block sparsity in the angular domain, the second layer promotes SnS properties in the spatial domain, and the third layer effectively decouples each subchannel from the observed signal. To enable efficient Bayesian inference, we develop a three-layer generalized approximate message passing (TL-GAMP) algorithm that combines structured variational message passing with belief propagation rules. Simulation results validate the convergence and effectiveness of the proposed TL-GAMP algorithm, demonstrating its robustness across various channel environments, including NF-SnS, NF spatially stationary (NF-SS), and far-field spatially stationary (FF-SS) scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Channel estimation

来源：评论

学校读者我要写书评

暂无评论

Monaural Speech Enhancement Using a Multi-Branch Temporal Convolutional Network

SSRN

引用

SSRN 2022年

作者： Zhang, Qiquan Qian, Xinyuan Nicolson, Aaron Wang, Chenxu Paliwal, Kuldip K. Department of Electrical and Computer Engineering National University of Singapore Singapore Australian e-Health Research Centre CSIRO Australia School of Information and Electrical Engineering Harbin Institute of Technology Weihai264209 China Signal Processing Laboratory Griffith University BrisbaneQLD4160 Australia

Deep learning has achieved substantial improvement on single-channel speech enhancement. The performance of multi-layer perceptrons (MLPs)-based methods is limited by the ability to capture the long-term contextual information. The recurrent neural networks (RNNs), e.g., long short-term memory (LSTM) model, are able to capture the long-term temporal dependencies, but suffer from the high latency and the complex training process. Recently, temporal convolution networks (TCNs), employing 1-D dilated convolution and residual learning, achieves gained considerable success in speech enhancement. In this paper we propose a novel TCN model that employs multi-branch structure, called multi-branch TCN (MB-TCN), for monaural speech enhancement. The MB-TCN exploits split-transform-aggregate design, which is expected to obtain strong representational power with higher parameter efficiency. The MB-TCN model applies 1-D causal dilated CNN in each branch to expand receptive fields for capturing long-term temporal contextual information. Our extensive experimental investigation suggests that MB-TCNs outperform the residual LSTMs (ResLSTMs), TCNs, and the CNNs with dense aggregations (DenseNet) in terms of speech intelligibility and quality, while providing superior parameter efficiency. Furthermore, our proposed MB-TCN model demonstrates highly competitive performance to multiple state-of-the-art speech enhancement methods in terms of five widely used objective metrics. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：