检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Haozhe Ma Kuankuan Sima Thanh Vinh Vo Di Fu Tze-Yun Leong School of Computing National University of Singapore Singapore College of Design and Engineering National University of Singapore Singapore

Reward shaping is a promising approach to tackle the sparse-reward challenge of reinforcement learning by reconstructing more informative and dense rewards. This paper introduces a novel dual-agent reward shaping framework, composed of two synergistic agents: a policy agent to learn the optimal behavior and a reward agent to generate auxiliary reward signals. The proposed method operates as a self-learning approach, without reliance on expert knowledge or hand-crafted functions. By restructuring the rewards to capture future-oriented information, our framework effectively enhances the sample efficiency and convergence stability. Furthermore, the auxiliary reward signals facilitate the exploration of the environment in the early stage and the exploitation of the policy agent in the late stage, achieving a selfadaptive balance. We evaluate our framework on continuous control tasks with sparse and delayed rewards, demonstrating its robustness and superiority over existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Retail Logistics: Fine-Tuning 5G-Cyberphysical Vehicular Networks with AGSA-Driven Path Loss Models 2

Revolutionizing Retail Logistics: Fine-Tuning 5G-Cyberphysic...

引用

2nd International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2023

作者： Okafor, Kennedy Chinedu Adebisi, Bamidele Akande, A.O. Anoh, Kelvin Manchester Metropolitan University School of Engineering ManchesterM1 5GD United Kingdom Federal University of Technology School of Electrical Systems Engineering Technology Owerri Nigeria University of Chichester School of Engineering Computing and Design Bognor RegisPO21 1HR United Kingdom

ISBN: (纸本)9798350358834

Non-autonomous vehicles, like the MasterMover electric Tugs, find extensive application in specialised short-range communication settings such as UK's Tesco warehouses. Employing a resilient MasterMover setup, electromagnetic attenuation within the Cyberphysical vehicular infrastructure can be fine-tuned, thereby enhancing supply chain logistics for retail outlets. This study enhances an earlier conventional Agile Gravitational Search Algorithm (AGSA) with outdated path loss models. Through AGSA-driven path loss optimisation, subsequent regression analysis is employed to generate supervised labels for both observed and anticipated path loss behaviors. The findings are useful for new level 3-5 driverless cars operating at 5G/6G spectrum. © 2023 IEEE.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Quantum Secure Email Communication for Phishing Prevention

Quantum Secure Email Communication for Phishing Prevention

引用

IEEE Punecon

作者： Pankaj Chandre Palash Sontakke Rajkumar Patil Bhagyashree D Shendkar Dhanraj Dhotre Viresh Vanarote Department of Computer Science and Engineering MIT School of Computing MIT Art Design and Technology University Pune India Department of Information Technology MIT School of Computing MIT Art Design and Technology University Pune India

ISBN: (数字)9798331527822

ISBN: (纸本)9798331527839

The rise of sophisticated phishing attacks has necessitated stronger security measures for email communication, especially in sensitive environments. This paper proposes a Quantum Secure Email Communication Framework designed to prevent phishing by integrating Quantum Key Distribution (QKD) with traditional email security mechanisms. The framework leverages quantum keys to encrypt email communication, ensuring that only legitimate users with the correct quantum key can send and receive secure emails. The architecture also incorporates a Phishing Detection Engine that validates email content and sender information using quantum-encrypted keys, alerting users to potential phishing threats. The system operates through the secure exchange of quantum keys between the sender’s email server and the user via a QKD Channel, with quantum encryption applied to secure outgoing and incoming emails. In parallel, the phishing detection module analyses all email traffic for signs of malicious activity, using a QKD-based Email Validator to confirm the legitimacy of emails. This hybrid approach ensures both the privacy of communication and the proactive detection of phishing attempts, offering a robust defense mechanism in the increasingly hostile landscape of digital communication.

关键词： Privacy Phishing Prevention and mitigation Digital communication Real-time systems Electronic mail Quantum key distribution Encryption Servers Engines

来源：评论

学校读者我要写书评

暂无评论

Post-Quantum Cryptography: Securing Critical Infrastructure Against Emerging Quantum Threats

Post-Quantum Cryptography: Securing Critical Infrastructure ...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Pankaj Chandre Hyderali Hingoliwala Amit Uttarkar Bhagyashree D Shendkar Deepali Lokare Palash Sontakke Department of Computer Science and Engineering MIT School of Computing MIT Art Design and Technology University Pune India Department of Information Technology MIT School of Computing MIT Art Design and Technology University Pune India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

The rapid advancements in quantum computing pose significant threats to traditional cryptographic systems, which are foundational to securing modern digital infrastructure. Cryptosystems like RSA and ECC, currently relied upon for secure communications, are vulnerable to quantum attacks, necessitating the development of post-quantum cryptography (PQC). The proposed methodology in this paper focuses on safeguarding critical infrastructure from quantum-based cyberattacks by leveraging PQC. The framework integrates several key strategies: hybrid cryptography, which combines classical and post-quantum algorithms to ensure security even as quantum threats evolve; quantum key distribution (QKD), ensuring secure communication by detecting any interception attempts; and post-quantum algorithms designed to resist quantum computing capabilities. The methodology also includes a robust security layer with incident response and threat monitoring systems to detect anomalies and initiate rapid responses to potential attacks. This holistic approach secures vital sectors like healthcare, energy, and telecommunications by future-proofing cryptographic measures against quantum threats.

关键词： Quantum algorithm Medical services Resists Elliptic curve cryptography Critical infrastructure Quantum key distribution Telecommunications Encryption Monitoring Resilience

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient and Diverse Generative Model for Unconditional Human Motion Synthesis 24

Towards Efficient and Diverse Generative Model for Unconditi...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yu, Hua Liu, Weiming Bai, Jiapeng Gui, Xu Hou, Yaqing Ong, Yewsoon Zhang, Qiang Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education School of Computer Science and Technology Dalian University of Technology Dalian China College of Computer Science Zhejiang University Hangzhou China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China College of Computing and Data Science Nanyang Technological University Singapore Singapore Yonsei University Seoul Korea Republic of

ISBN: (纸本)9798400706868

Recent generative methods have revolutionized the way of human motion synthesis, such as Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), and Denoising Diffusion Probabilistic Models (DMs). These methods have gained significant attention in human motion fields. However, there are still challenges in unconditionally generating highly diverse human motions from a given distribution. To enhance the diversity of synthesized human motions, previous methods usually employ deep neural networks (DNNs) to train a transport map that transforms Gaussian noise distribution into real human motion distribution. According to Figalli's regularity theory, the optimal transport map computed by DNNs frequently exhibits discontinuities. This is due to the inherent limitation of DNNs in representing only continuous maps. Consequently, the generated human motions tend to heavily concentrate on densely populated regions of the data distribution, resulting in mode collapse or mode mixture. To address the issues, we propose an efficient method called MOOT for unconditional human motion synthesis. First, we utilize a reconstruction network based on GRU and transformer to map human motions to latent space. Next, we employ convex optimization to match the noise distribution with the latent space distribution of human motions through the Optimal Transport (OT) map. Then, we combine the extended OT map with the generator of reconstruction network to generate new human motions. Thereby overcoming the issues of mode collapse and mode mixture. MOOT generates a latent code distribution that is well-behaved and highly structured, providing a strong motion prior for various applications in the field of human motion. Through qualitative and quantitative experiments, MOOT achieves state-of-the-art results surpassing the latest methods, validating its superiority in unconditional human motion generation. © 2024 ACM.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

HDPlanner: Advancing Autonomous Deployments in Unknown Environments through Hierarchical Decision Networks

arXiv

引用

arXiv 2024年

作者： Liang, Jingsong Cao, Yuhong Ma, Yixiao Zhao, Hanqi Sartoretti, Guillaume The Department of Mechanical Engineering College of Design and Engineering National University of Singapore Singapore The School of Computing National University of Singapore Singapore

In this paper, we introduce HDPlanner, a deep reinforcement learning (DRL) based framework designed to tackle two core and challenging tasks for mobile robots: autonomous exploration and navigation, where the robot must optimize its trajectory adaptively to achieve the task objective through continuous interactions in unknown environments. Specifically, HDPlanner relies on novel hierarchical attention networks to empower the robot to reason about its belief across multiple spatial scales and sequence collaborative decisions, where our networks decompose long-term objectives into short-term informative task assignments and informative path plannings. We further propose a contrastive learning-based joint optimization to enhance the robustness of HDPlanner. We empirically demonstrate that HDPlanner significantly outperforms state-of-the-art conventional and learning-based baselines on an extensive set of simulations, including hundreds of test maps and large-scale, complex Gazebo environments. Notably, HDPlanner achieves real-time planning with travel distances reduced by up to 35.7 % compared to exploration benchmarks and by up to 16.5 % than navigation benchmarks. Furthermore, we validate our approach on hardware, where it generates high-quality, adaptive trajectories in both indoor and outdoor environments, highlighting its real-world applicability without additional training. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ECC:Edge Collaborative Caching Strategy for Differentiated Services Load-Balancing

引用

Computers, Materials & Continua 2021年第11期69卷 2045-2060页

作者： Fang Liu Zhenyuan Zhang Zunfu Wang Yuting Xing School of Design Hunan UniversityChangshaChina School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhouChina Department of Computing Imperial College LondonUK

Due to the explosion of network data traffic and IoT devices,edge servers are overloaded and slow to respond to the massive volume of online requests.A large number of studies have shown that edge caching can solve this problem *** paper proposes a distributed edge collaborative caching mechanism for Internet online request services *** solves the problem of large average access delay caused by unbalanced load of edge servers,meets users’differentiated service demands and improves user *** particular,the edge cache node selection algorithm is optimized,and a novel edge cache replacement strategy considering the differentiated user requests is *** mechanism can shorten the response time to a large number of user *** results show that,compared with the current advanced online edge caching algorithm,the proposed edge collaborative caching strategy in this paper can reduce the average response delay by 9%.It also increases the user utility by 4.5 times in differentiated service scenarios,and significantly reduces the time complexity of the edge caching algorithm.

关键词： Edge collaborative caching differentiated service cache replacement strategy load balancing

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Based Optimised Energy Management System for Microgrids 58

Artificial Intelligence-Based Optimised Energy Management Sy...

引用

58th International Universities Power engineering Conference, UPEC 2023

作者： Hussain, Muhammad Majid Nazir, Mian Hammad Akhtar, Muhammad Naveed Javed, Waqas Razaq, Abdul Pasha, Ahmad Hesham School of Engineering & Physical Sciences Heriot-Watt University Edinburgh United Kingdom University of South Wales Faculty of Computing Engineering & Science Cardiff United Kingdom Rachna College of Engineering & Technology Department of Electrical Engineering Gujranwala Pakistan James Watt School of Engineering University of Glasgow Glasgow United Kingdom School of Design and Informatics Abertay University Dundee United Kingdom

ISBN: (纸本)9798350316834

Electric power consistency is one of the essential variables in the social and economic growth of a smart city. In contrast, innovative energy sources and intelligent electricity networks are the primary components in making a city smart. This study describes an artificial neural network (ANN)- based controller for increasing power supply consistency by employing a dynamic voltage restorer. The optimisation approach particle swarm optimisation (PSO) is also discussed in this work, used to compute the maximum power point tracking (MPPT) of wind/photovoltaic hybrid power systems. The proposed PSO and ANN techniques can detect load, wind velocity, and solar irradiation fluctuations to optimise generating device power output, allowing hybrid power systems to function steadily, safely, and economically. This paper predicts and compares results with two cases using PSO and ANN to show the greater robustness and comparability of microgrid hybrid energies, namely photovoltaic and wind power. The simulation results show that the ANN-based controller with the PSO technique gives better performance as compared to the fuzzy controller. Further, the simulation results show that the converter can follow the hybrid system's maximum power point. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Frequency-Domain Assisted Fundus Image Enhancement Network Based on the Mamba Model 9

Frequency-Domain Assisted Fundus Image Enhancement Network B...

引用

9th IEEE International Conference on Progress in Informatics and computing, PIC 2024

作者： Luo, Bin Wen, Yang Ji, Jianhua Cao, Wenming Li, Ping Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing College of Electronic and Information Engineering Shenzhen China College of Electronic and Information Engineering Shenzhen University Shenzhen China The Hong Kong Polytechnic University Department of Computing and School of Design Hong Kong Hong Kong

ISBN: (纸本)9798350363203

Enhancing fundus images is crucial for early diagnosis and monitoring of retinal diseases. Although CNN and Transformer-based methods have made great progress, CNNs struggle with long-range dependencies, and Transformers face challenges with large model sizes and low computational efficiency. To address these issues, Selective Structured State-Space Models (SSMs) offer an efficient solution with linear complexity. However, standard Mamba models still suffer from local pixel information loss and channel redundancy, limiting their performance in fundus image enhancement. We propose MambaFE, which incorporates localized refinement and an advanced channel attention mechanism to resolve challenges such as pixel detail loss and excessive channel information. Considering that retinal structures play a vital role in fundus analysis, retaining these structures during the enhancement process is crucial. As retinal structures are predominantly located within the high-frequency components of fundus images, we introduce a frequency-guided approach to capture reliable representations of these features, ensuring improved retention of essential information during enhancement. Comprehensive experimental findings indicate that the proposed MambaFE outperforms contemporary fundus image enhancement techniques, significantly enhancing the quality of clinically low-quality and synthetically degraded fundus images, while offering robust support for real-world medical applications. © 2024 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Enhancing Urban Living - A Comprehensive Solution Using Machine Learning and IoT 4

Enhancing Urban Living - A Comprehensive Solution Using Mach...

引用

4th International Conference for Emerging Technology, INCET 2023

作者： Puranik, Atharva Ghanekar, Vishwanath Pangaonkar, Satyajit Gunjan, Reena Rokade, Prakash Avantika University School of Computer Science and Engineering Madhya Pradesh Ujjain India Design and Technology University MIT School of Computing MIT Art Maharashtra Pune India Cloud and Infrastructure Services Infosys Ltd Maharashtra Pune India

ISBN: (纸本)9798350335750

The urban population is increasing rapidly, leading to challenges in managing daily life activities such as transportation, healthcare, and accessing local services. The developed "At a Glance,"is a comprehensive mobile application and digital billboard that provides real-time solutions to several problems faced by city dwellers. The app uses machine learning and IoT to offer features such as real-time traffic monitoring, local news updates, resource people contacts, medical and health information, among others. It aims to promote sustainable living, reduce traffic congestion and air pollution, and make the city a better place to live. "At a Glance"uses various technologies such as Flutter, Firebase Realtime Database and Storage, TensorFlow, IoT, geolocator, geocoder, OpenStreetMaps, and Raspberry Pi. The app offers features such as traffic density monitoring, real-time weather updates, local news and event notifications, and a resource people directory. The app also uses machine learning algorithms to recommend relevant services and resources to users based on their preferences. "At a Glance"has the potential to revolutionize urban living by providing a one-stop solution for all daily life activities. The app can help people make informed decisions, save time and resources, and reduce their carbon footprint. The app's user-friendly interface and accessibility make it a promising solution for cities worldwide. © 2023 IEEE.

关键词： Carbon footprint

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：