检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhang, Wenqi Zhao, Kai Li, Peng Zhu, Xiao Shen, Yongliang Ma, Yanna Chen, Yingfeng Lu, Weiming College of Computer Science and Technology Zhejiang University China Netease Fuxi Robot Department China Institute of Software Chinese Academy of Sciences China College of Mechanical Engineering Zhejiang University of Technology China University of Shanghai for Science and Technology China University of Chinese Academy of Sciences Nanjing China

Reliable navigation systems have a wide range of applications in robotics and autonomous driving. Current approaches employ an open-loop process that converts sensor inputs directly into actions. However, these open-loop schemes are challenging to handle complex and dynamic real-world scenarios due to their poor generalization. Imitating human navigation, we add a reasoning process to convert actions back to internal latent states, forming a two-stage closed loop of perception, decision-making, and reasoning. Firstly, VAE-Enhanced Demonstration Learning endows the model with the understanding of basic navigation rules. Then, two dual processes in RL-Enhanced Interaction Learning generate reward feedback for each other and collectively enhance obstacle avoidance capability. The reasoning model can substantially promote generalization and robustness, and facilitate the deployment of the algorithm to real-world robots without elaborate transfers. Experiments show our method is more adaptable to novel scenarios compared with state-of-the-art approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

Using the Heterogeneous Network's Self-Adaptive Topological Structure for Drug-Protein Interaction Prediction

Using the Heterogeneous Network's Self-Adaptive Topological ...

引用

Communications and Information Technologies (GCCIT), Global Conference on

作者： Vikrant Sharma Niranjani B Baishakhi Debnath V. A. Mishra K. Yuvaraj Ansh Kataria Computer Science and Engineering Graphic Era Hill University Dehradun Uttarakhand India Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Business Administration Prince Shri Venkateshwara Padmavathy Engineering College Chennai School of Management - UG Management JAIN (Deemed to be University) Bangalore Karnataka Computer Engg. Vishwakarma Institute of Technology Pune India Department of Computer Science Karpagam Academy of Higher Education Coimbatore Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India

ISBN: (数字)9798350388916

ISBN: (纸本)9798350388923

The prediction of drug-protein interactions (DPIs) has been the subject of many robust computer approaches using graph neural networks (GNNs). The burden in laboratories and the costs associated with drug discovery and repurposing may be significantly decreased with its help. The unreported indications of many proteins and medications render their clinical activities unclear, nonetheless. Therefore, using the data that is currently available, it is challenging to construct a trustworthy drug-protein heterogeneous network that can characterize the interactions between medicines and proteins. We provide TAG, a DPI prediction approach that may self-adaptively alter the topological framework of the heterogeneous networks, as a solution to this challenge. Graph Neural Networks (GNNs) have recently gained a lot of interest due to their exceptional compatibility with viral proteins and pharmacological substances. Building such a model that accurately depicts the molecular structures of living molecules is, however, no easy feat. Also, newly created GNNs have been overfitting on Coronavirus datasets as they are still not widely used. Next, we propose a new model called Topology-enhanced Graph Neural Network using Multi-hop Gating Mechanism to fix those problems. Firstly, our model is able to learn more specific properties of proteins and chemicals. Conversely, we provide a novel gating approach for improving atom representation using non-neighbor data. In order to implement the drug-protein heterogeneous network, TAG sets up a representation learning module that is based on graph attention network. The network's topology may be fine-tuned in response to the training loss, and it can learn the connections between nodes using their properties. Lastly, TAG uses the embeddings of medicines and proteins to forecast the likelihood of their interactions. The experimental findings demonstrate that TAG is capable of significantly enhancing the network's topological structure. Across

关键词： Proteins Bridges Training Support vector machines Representation learning Network topology Spread spectrum communication Graph neural networks Heterogeneous networks Overfitting

来源：评论

学校读者我要写书评

暂无评论

Orbital angular momentum of spin electromagnetic wave

引用

Results in Physics 2024年 61卷

作者： Sun, Zhiwei Du, Mingzhu Guo, Zhenkun Xu, Ruolei Zhao, Junming Feng, Yijun School of Electronic Science and Engineering Nanjing University 210023 China School of Microelectronics and Communication Engineering Chongqing University 400044 China Shanghai Radio Equipment Research Institute Shanghai Academy of Spaceflight Technology 201109 China Department of Electrical and Computer Engineering National University of Singapore 117583 Singapore

Spin angular momentum (SAM) and Orbital angular momentum (OAM) are two distinct forms of electromagnetic angular momentum (AM). Generally, circularly-polarized (CP) wave is deemed as the typical form of spin wave, which carries SAM only. In this work, the OAM characteristic of spin wave is found after stating the CP wave into the cylindrical coordinate: the spin wave contains two components along r and ϕ directions, which carry both SAM and OAM. Based on the OAM character of spin wave, an electromagnetic waveform with SAM in the center and SAM-OAM beside is demonstrated. In addition, since spin wave carries OAM naturally, a spin–orbit coupling mechanism is performed, which demands no spin Pancharatnam–Berry phase nor any phase modulation structure. All the results have been experimentally verified. Our research can be utilized in the theoretical studies of rotational electromagnetic and may be potentially applied in metamaterial, information and quantum research areas. © 2024

关键词： Angular momentum Helical beam waves Polarization-phase Spatial-phase Spin-orbit coupling

来源：评论

学校读者我要写书评

暂无评论

Engineered Thermal Emittance for Infrared Camouflage Textiles with Radiative Cooling and Infrared Structural Colors

SSRN

引用

SSRN 2023年

作者： Huang, Xuemei Chen, Qixiang Huang, Jinhua Cheng, Jie Zhang, Jiaping Xu, Hua Song, Weijie Lu, Yuehui Zhejiang Provincial Engineering Research Center of Energy Optoelectronic Materials and Devices Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China University of Chinese Academy of Sciences Beijing100049 China School of Physical Science and Technology Ningbo University Ningbo315211 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China Research Center for Sensing Materials and Devices Zhejiang Lab Zhejiang Hangzhou311121 China

Infrared (IR) camouflage conceals objects by reducing their temperatures or thermal emittances within the mid-wave infrared (3-5 μm) and long-wave infrared (8-14 μm) atmospheric transparent windows. Concerning textiles for IR camouflage on human bodies, it is crucial to consider not only low thermal emittances but also factors such as thermal comfort, resistance to abrasion and washing, breathability, and even blending with the intricate IR background. In this study, we develop a spectrally-selective emission textile (SET) using a roll-to-roll (R2R) magnetron sputtering deposition process. The unique properties of the SET arise from asymmetric Fabry-Pérot cavity and surface impedance matching, resulting in the low emittance of 0.39 and 0.44 in the IR detection wavelength range of 3-5 and 8-14 μm, respectively. Additionally, it exhibits a high emittance of 0.79 in the undetectable range of 5-8 μm, which enhances thermal comfort through radiative cooling. To improve the SET’s resistance to abrasion and washing while maintaining breathability, we apply a highly IR-transparent polymer, styrene-ethylene-butylene-styrene (SEBS), to form a honeycomb pattern using a 3D-printed mask, producing a durable spectrally-selective emission textile (D-SET). The SEBS overcoating not only protects the IR camouflage textiles but also offers a versatile means of further engineering thermal emittance by controlling thicknesses, realizing a spatially-segmented emittance pattern with various IR structural colors, and ultimately achieving the IR-colorful spectrally-selective emission textile (IRC-SET). This work presents a novel approach to IR camouflage textiles, incorporating both spectral and spatial thermal emittance engineering through a combination of inorganic and organic building blocks. The scalability of manufacturing techniques, including R2R magnetron sputtering, spray coating, and blade coating, holds great promise for practical applications. © 2023, The Authors. All rights res

关键词： Infrared radiation

来源：评论

学校读者我要写书评

暂无评论

Towards Faster Fully Homomorphic Encryption Implementation with Integer and Floating-point Computing Power of GPUs

Towards Faster Fully Homomorphic Encryption Implementation w...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Guang Fan Fangyu Zheng Lipeng Wan Lili Gao Yuan Zhao Jiankuo Dong Yixuan Song Yuewu Wang Jingqiang Lin State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center Chinese Academy of Sciences Beijing China School of Cryptography University of Chinese Academy of Sciences Beijing China Department of Computer and Software Nanjing University of Information Science and Technology Nanjing China Ant Group Hangzhou China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Cyber Security University of Science and Technology of China Hefei China

Fully Homomorphic Encryption (FHE) allows computations on encrypted data without knowledge of the plaintext message and currently has been the focus of both academia and industry. However, the performance issue hinders its large-scale application, highlighting the urgent requirements of high-performance FHE *** noticing the tremendous potential of GPUs in the field of cryptographic acceleration, this paper comprehensively investigates how to convert the available computing resources residing in GPUs into FHE workhorses, and implement a full set of low-level and middle-level FHE primitives based on two arithmetic units (i.e., INT32 and FP64 units) with three types of data precision (i.e., INT32, INT64 and FP64). This paper gives a comprehensive evaluation and comparison based on each road-map. Our implementations of fundamental functions outperform the implementations on the same platform by 1.7× to 16.7×. Taking CKKS FHE schemes as a case study, our implementation of homomorphic multiplication achieves 3.2× speedup over the state-of-the-art GPU-based implementation, even considering the difference of platforms. The detailed evaluation and comparison of this paper would offer a vital reference for the follow-up work to choose appropriate underlying arithmetic units and important primitive optimizations in GPU-based FHE implementations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced IoT Intrusion Detection for Intelligent Homes using Optimized Cross-Contextual Transformers with a Dynamic City Game Framework

Advanced IoT Intrusion Detection for Intelligent Homes using...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Gurusigaamani Ayyanar Muthulingam Gulshan Dhasmana S. Purushothaman Sharath Honnaiah Bindu Ronald Manzoore Elahi M. Soudagar Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamil Nadu India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Electronics and Communication Sathyabama Institute of Science and Technology Chennai Tamil Nadu India Credit Acceptance Bangalore Karnataka India Faculty of Law Symbiosis Law School (SLS) Symbiosis International (Deemed University) (SIU) Pune Maharashtra India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

Ensuring data security against unauthorized access in smart homes is crucial, but implementing deep learning methods can be challenging due to potential issues such as accuracy loss, time complexity, and increased error rates. This study introduces a novel approach to address these challenges: the Securing Intelligent Home with a Transformer-Based IoT Intrusion Detection System (IDS) using an Optimized Cross-Contextual Point Running City Game Transformer Network (O2CPRCG-TransNet). This innovative method leverages advanced DL approaches to improve the security and reliability of Intelligent home environments. The study utilizes the IoT_bot dataset, which is pre-processed using the Grid-Constrained Data Purification Method (GCDP) to ensure high-quality input. The purified data is then optimized through the Giant Trevally Optimizer Algorithm (GTOA), which selects the most significant features to improve classification performance. Classification is performed using the O2CPRCG-TransNet architecture, which is specifically designed to address the complexities of Intelligent home security. To ensure secure data transmission, the system incorporates Somewhat Homomorphic Fuzzy-based Elliptic Curve Cryptography (SWH-FECC). Experimental results, obtained using the Python platform, demonstrate that the proposed approach achieves superior performance, with an accuracy of 98% and a recall of 0.993, compared to existing methods. These findings underscore the effectiveness of the proposed method and its potential for broader application in enhancing Intelligent home security.

关键词： Deep learning Accuracy Urban areas Intrusion detection Smart homes Games Transformers Elliptic curve cryptography Internet of Things Time complexity

来源：评论

学校读者我要写书评

暂无评论

Cell Manipulation Attack Against Onion Services

Cell Manipulation Attack Against Onion Services

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Jianjun Lin Yinliang Yue Yijing Zhang Xiaoyu Liu XiaoDu Yang Weilin Gai Bo Sun Chinese Academy of Sciences Institute of Information Engineering Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Zhongguancun Laboratory Beijing China Chinese Academy of Sciences Institute of Software Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China (CNCERT/CC) Beijing China

In this study, we proposed OREA-OS, a cell manipulation attack devised to compromise Onion Services. Through the manipulation of cells, two collaborating nodes within a circuit exchange information to unveil the anonymity of the targeted Onion Service. We conducted an analysis of existing de-anonymization scenarios and effectively addressed the associated challenges, thereby achieving successful de-anonymization of Onion Services. To assess the efficacy of our attacks, we conducted experiments on both private and public Tor networks. The experimental results validate the effectiveness of our approach, as we accomplished 100% accurate identification of the relationship between domain names and Internet Protocol addresses, with no false positives. Within our simulated private network, the recall rate neared 100 %. On the public Tor network, the de-anonymization rate (98.6 %) exceeded the successful download rate (98.2 %). Furthermore, 99.2 % of success attacks took less than 10 seconds to confirm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Feedback Residual Attention Network with Slanted Scarce Auto-Encoder and IoT Based Industrial Waste Water Treatment System for Effective Waste Management

Enhanced Feedback Residual Attention Network with Slanted Sc...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： K.V.S. Prasad T. Gavaskar G. Ravivarman P. Chinniah Sophia S Sathyakala S Department of Basic Sciences and Humanities GMR Institute of Technology Vizianagaram Andhra Pradesh India Department of Mechanical Engineering St. Joseph's College of Engineering Chennai Tamil Nadu India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Electronics and Communication Engineering ST. Joseph College of Engineering Kanchipuram Tamil Nadu India Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India Department of Management Studies Sona College of Technology Salem Tamil Nadu India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

In the last few decades, rapid industrialization has increased the problem of wastewater treatment and management because of the increasing complexity and toxicity of wastewater that is difficult to treat by any conventional approach. Commonly used waste water treatment systems are unable to treat a variety of pollutants because of deficiency of good classification and optimization processes which results in wastage of resources and harming the environment. Furthermore, existing systems are inflexible, and an ability to change the nature of treatment in real time is impossible, which is crucial for the timely and efficient delivery and adjustment of therapies. To overcome these challenges, there is a need for smart monitoring systems enabled by IoT and effective treatment processes utilizing machine learning for better waste management. This paper comes up with an IoT and Machine Learning based system for the treatment of industrial wastewater that uses an Enhanced Feedback Residual Attention Network with Slanted Scarce Autoencoder to achieve accuracy in pollutant classification and quantification. Fick's Law Optimization is incorporated for optimization which makes the treatment process more efficient by allowing the treatment to be applied only where necessary and in the right amounts. IoT sensors are also part of the system to ensure that the data is collected in real time and the waste is continuously monitored to allow quick reactions to changes in waste. The introduced approach attains higher accuracy as 99%.

关键词： Waste management Accuracy Autoencoders Machine learning Real-time systems Sensor systems Sensors Wastewater Wastewater treatment Optimization

来源：评论

学校读者我要写书评

暂无评论

Medical Protocols and AI-Driven Algorithms for Enhanced Monitoring of Cardiac Implantable Electronic Devices 19thth

Medical Protocols and AI-Driven Algorithms for Enhanced Mo...

引用

19th International Conference on computer Aided Systems Theory, EUROCAST 2024

作者： Kulbacki, Marek Segen, Jakub Chaczko, Zenon Kulbacki, Michal Nikodem, Jan Klempous, Ryszard Bąk, Artur Rozenblit, Jerzy Zyśko, Dorota Hrymniak, Bruno Jagielski, Dariusz Wroclaw University of Technology Wroclaw Poland Wroclaw University of Science and Technology Wroclaw Poland School of Electrical and Data Engineering University of Technology Sydney Ultimo Australia Department of Electrical and Computer Engineering University of Arizona Tucson United States Polish-Japanese Academy of Information Technology Warsaw Poland DIVE IN AI Wroclaw Poland Mathematical Institute University of Wroclaw Wroclaw Poland Center for Heart Diseases 4th Military Hospital Wroclaw Poland

ISBN: (纸本)9783031829598

Implantable cardioverter-defibrillators (ICDs) present several challenges regarding their detection, localization, and continuous monitoring within patients’ bodies. These challenges include maintaining the integrity of electrodes, preventing local tissue irritation, avoiding device displacement, and ensuring compatibility with MRI. Continuous monitoring is critical to ensure patient safety and the functional integrity of the devices. This paper systematically reviews approaches for the comprehensive monitoring of Cardiac Implantable Electronic Devices (CIEDs) over the past ten years, focusing on the CaRDIA-X procedure. We examine advanced protocols and integrated algorithms designed for this purpose. Specifically, we introduce the CaRDIA-X protocol, a manual method for identifying CIEDs based on the analysis of device patterns and the arrangement of elements on X-ray images. We compare this protocol with alternative detection methods, including artificial intelligence algorithms, and emphasize the field’s most significant studies and comprehensive comparative analyses. In conclusion, we propose improvements to the classic CaRDIA-X algorithm, focusing on automating the CaRDIA-X procedure, which holds significant potential for enhancing patient management and therapeutic efficacy. This integrated proposition offers a holistic perspective on CIED performance and potential issues. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic medical equipment

来源：评论

学校读者我要写书评

暂无评论

Skin-like cryogel electronics from suppressed-freezing tuned polymer amorphization

引用

Nature Communications 2023年第1期14卷 1-10页

作者： Zhang, Xiansheng Yan, Hongwei Xu, Chongzhi Dong, Xia Wang, Yu Fu, Aiping Li, Hao Lee, Jin Yong Zhang, Sheng Ni, Jiahua Gao, Min Wang, Jing Yu, Jinpeng Ge, Shuzhi Sam Jin, Ming Liang Wang, Lili Xia, Yanzhi State Key Laboratory of Bio-Fibers and Eco-Textiles College of Textiles and Clothing Qingdao University Qingdao 266071 China Institute for Future Shandong Key Laboratory of Industrial Control Technology School of Automation Qingdao University Qingdao 266071 China College of Materials Science and Engineering Qingdao University Qingdao 266071 China CAS Key Laboratory of Engineering Plastics Institute of Chemistry Chinese Academy of Sciences Beijing 100190 China Department of Chemistry SungKyunKwan University Suwon 16419 South Korea State Key Laboratory of Fluid Power and Mechatronic Systems College of Mechanical Engineering Zhejiang University Hangzhou 310027 China College of Biological Science and Medical Engineering Donghua University Shanghai 201620 China Institute of Environmental Engineering ETH Zürich Zürich 8093 Switzerland Department of Electrical and Computer Engineering National University of Singapore Singapore 117576 Singapore

The sole situation of semi-crystalline structure induced single performance remarkably limits the green cryogels in the application of soft devices due to uncontrolled freezing field. Here, a facile strategy for achieving multifunctionality of cryogels is proposed using total amorphization of polymer. Through precisely lowering the freezing point of precursor solutions with an antifreezing salt, the suppressed growth of ice is achieved, creating an unusually weak and homogenous aggregation of polymer chains upon freezing, thereby realizing the tunable amorphization of polymer and the coexistence of free and hydrogen bonding hydroxyl groups. Such multi-scale microstructures trigger the integrated properties of tissue-like ultrasoftness (Young’s modulus <10 kPa) yet stretchability, high transparency (~92%), self-adhesion, and instantaneous self-healing (<0.3 s) for cryogels, along with superior ionic-conductivity, antifreezing (−58 °C) and water-retention abilities, pushing the development of skin-like cryogel electronics. These concepts open an attractive branch for cryogels that adopt regulated crystallization behavior for on-demand functionalities. © 2023, Springer Nature Limited.

关键词： Gels and hydrogels Polymers

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：