检索结果-内蒙古大学图书馆

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Agarwal, Shruti Gupta, Shagun Agarwal, Piyush Sharma, Garima Tripathi, Vikas Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9789380544472

Internet of Things (IoT) connects individual devices, software, and sensors over a network without misnomers of a public domain. It is a very common scenario in designing better low-cost enterprise solutions for smarter homes, cities, and healthcare. One key issue smart cities are dealing nowadays is car parking. It directly affects traffic congestion, costing people time and fuel. In this work, we solve the current problem by the implementation of an android application with the on-site deployment of an IoT module, where users can search for nearby parking spaces, reserve multiple slots according to their preference, and navigate to the selected location. Also, the application is capable of automatically notifying users of nearby parking locations in real time. Additionally, for efficient parking management, users will get an alert until the parking of a car is not done within the allotted boundaries. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Approach of Fog Computing and Edge Computing for Computing Resources Optimization Strategies 1

An Approach of Fog Computing and Edge Computing for Computin...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Upadhyay, Deepak Upadhyay, Abhay Gupta, Mridul Sharma, Kunj Bihari Yadav, Devansh Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India

ISBN: (纸本)9798350365016

This paper investigates optimization strategies for fog and edge computing systems, focusing on the key challenges of resource allocation, load balancing, latency minimization, and power efficiency. We analyze the results of the simulation study to determine the impact and potential of our strategies and find that the improvements achieved are small to moderate, varying between 1.75% and 2.95%. This knowledge demonstrates that system optimization requires small, gradual increments and that fog and edge computing are dynamic systems. Our results suggest that optimization based on integration and adaptability can produce a significant difference in the performance and reliability of distributed systems. © 2024 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Estimating Post-Synaptic Effects for Online Training of Feed-Forward SNNs

Estimating Post-Synaptic Effects for Online Training of Feed...

引用

2024 International Conference on Neuromorphic Systems, ICONS 2024

作者： Summe, Thomas M. Schaefer, Clemens JS Joshi, Siddharth University of Notre Dame Dept. of Computer Science and Engineering United States

ISBN: (纸本)9798350368659

Facilitating online learning in spiking neural networks (SNNs) is a key step in developing event-based models that can adapt to changing environments and learn from continuous data streams in real-time. Although forward-mode differentiation enables online learning, its computational requirements restrict scalability. This is typically addressed through approximations that limit learning in deep models. In this study, we propose Online Training with Postsynaptic Estimates (OTPE) for training feed-forward SNNs, which approximates Real-Time Recurrent Learning (RTRL) by incorporating temporal dynamics not captured by current approximations, such as Online Training Through Time (OTTT) and Online Spatio-Temporal Learning (OSTL). We show improved scaling for multi-layer networks using a novel approximation of temporal effects on the subsequent layer's activity. This approximation incurs minimal overhead in the time and space complexity compared to similar algorithms, and the calculation of temporal effects remains local to each layer. We characterize the learning performance of our proposed algorithms on multiple SNN model configurations for rate-based and time-based encoding. OTPE exhibits the highest directional alignment to exact gradients, calculated with backpropagation through time (BPTT), in deep networks and, on time-based encoding, outperforms other approximate methods. We also observe sizeable gains in average performance over similar algorithms in offline training of Spiking Heidelberg Digits with equivalent hyper-parameters (OTTT/OSTL - 70.5%;OTPE - 75.2%;BPTT - 78.1%). © 2024 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Image Retrieval Using Siamese Deep Neural Network and Hashing Technique 14

COVID-19 Image Retrieval Using Siamese Deep Neural Network a...

引用

14th International Conference on Information and Knowledge Technology, IKT 2023

作者： Boroujeni, Farsad Zamani Afshari, Doryaneh Hossien Mahmoodi, Fatemeh Science and Research Branch Dept. of Computer Engineering Tehran Iran Branch Dept. of Computer Engineering Isfahan Iran

ISBN: (纸本)9798350349412

Medical images are crucial for early diagnosis and are increasingly important in modern medicine. This study presents a medical image retrieval system using a Siamese neural network with 13 layers. The system uses the Minimum Redundancy Maximum Relevance (mRMR) technique to extract deep features from the Siamese, and then uses binary hashing to retrieve similar images using Hamming distance. The experimental results on Covid-19 dataset show that the proposed method improves lung image retrieval by over 6% compared to previous methods, achieving an average accuracy of 93.83% and 92.73% in 5 and 10 retrieved images, respectively. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

A systematic review of decentralized finance protocols

引用

International Journal of Intelligent Networks 2023年第1期4卷 171-181页

作者： Shah, Kaushal Lathiya, Dhruvil Lukhi, Naimish Parmar, Keyur Sanghvi, Harshal Dept. of Computer Science and Engineering Pandit Deendayal Energy University Gujarat Gandhinagar382007 India Dept. of Computer Science and Engineering Sardar Vallabhbhai National Institute of Technology Gujarat Surat395007 India Dept. of CEECS Florida Atlantic University Boca Raton United States

Decentralized finance (DeFi) has revolutionized the financial industry in recent years. Industries such as banking, insurance, and investment are experiencing a significant shift due to the growth of DeFi. The decentralized finance market is expanding exponentially, emphasizing the potential of digital currencies and decentralized platforms in providing an alternative to the traditional finance paradigm. It eliminates the need for costly intermediaries, reduces transaction fees, and increases accessibility to financial services for everyone, regardless of their geographic location or economic status. With the enormous increase in cryptocurrency investment, individuals and institutions have started to use DeFi. In this context, understanding the architecture and working mechanisms of different DeFi protocols becomes crucial in creating new and innovative products. This review paper explores various DeFi protocols, including derivatives, decentralized exchanges (DEX), lending and borrowing, asset management, and stablecoins. It analyses their internal structure and composability, providing insights into how these protocols can be combined to create new and innovative DeFi products and explore the potential of DeFi in providing an alternative to the traditional finance paradigm. © 2023 The Authors

关键词： Asset management

来源：评论

学校读者我要写书评

暂无评论

Joint Power and Channel Allocation in Fading Channels Using Deep Reinforcement Learning 2

Joint Power and Channel Allocation in Fading Channels Using ...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Upadhyay, Deepak Upadhyay, Abhay Gupta, Mridul Sharma, Kunj Bihari Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era deemed to be University Dept. of Electronics and Communication Engineering Dehradun India

ISBN: (纸本)9798331519056

This paper investigates joint power and channel allocation under fading communication channels using Deep Reinforcement Learning (DRL). To this end, we design a DRL to allocate dynamic resources with different network condition properly and achieve the spectral efficiency improvement while reducing latency to meet lower bound in cost function as well keeping target fairness. Results show that our DRL-based approach can achieve better spectrum efficiency and latency than traditional algorithms while at the same time, sustaining a higher value of fairness index. In addition, it is observed that the DRL method also offers both adaptability (with fast adaptation to network changes) and robustness in performance but at a higher computational expense. Our results illustrate that the DRL-based technique may serve as a strong, scalable candidate in future wireless systems up to several orders of magnitude better than existing resource allocation schemes. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Climate Change Prediction Dynamics Using Machine Learning Approach: A Review 1

Exploring Climate Change Prediction Dynamics Using Machine L...

引用

1st International Conference on Computing, sciences and Communications, ICCSC 2024

作者： Tiwari, Shashank Verma, Shikha Chauhan, Rosey Gupta, Neha Sharda Unviersity Dept. of Computer Science Gerater Noida India ABES Engineering College Dept. of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350353648

Climate refers to the long-term weather patterns of a region. Variations in the weather have a lot of implications on our daily lives. Explore the application of deep learning techniques in climate prediction and related fields. It focuses on Long Short-Term Memory (LSTM) models for forecasting air quality, greenhouse temperature control, and urban flood water accumulation using Gradient Boosted Decision Trees (GBDT). The analysis concludes that deep learning, particularly LSTM, offers promising accuracy for various climate-related predictions. Challenges such as data scarcity, non-stationarity, and high dimensionality are addressed, highlighting the need for advanced models to capture complex climate system dynamics and human influences. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Malware Exposed: An In-dept. Analysis of its Behavior and Threats 3

Malware Exposed: An In-Depth Analysis of its Behavior and Th...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Anand, Chinmay Korada, Shreya Raksha, S. Sundaram, B. Meenakshi Rajalakshmi, B. Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350322842

Any software that acts maliciously towards a user, device, or network is referred to as malware. Malware analysis consists of four fundamental processes that make use of a variety of technologies to comprehend operation and pinpoint areas for removal. In order to examine the behavior of the malware on the system, the second phase, known as Basic Dynamic analysis, is running the malware in a secure environment. Running malware in a Sandbox environment is a crucial step in the Basic Dynamic Analysis process. In order to determine which sandbox gives the greatest flexibility for running malware for research, this study will examine a variety of sandboxes. Based on the desired characteristics of a sandbox environment, a rubric was developed. Scalability, the capability to examine different file kinds, and the presence of sandbox detection evasion strategies are a few of the parameters taken into account. To do Basic Dynamic Analysis for malware analysis after examining some of the most well-known sandboxes, Norman Sandbox, GFI Sandbox, and Anubis. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Meta-Adaptation Goals: Leveraging Feedback Loop Requirements for Effective Self-Adaptation 5

Meta-Adaptation Goals: Leveraging Feedback Loop Requirements...

引用

5th IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion, ACSOS-C 2024

作者： Groner, Raffaela Caldas, Ricardo Diniz Wohlrab, Rebekka Chalmers | University of Gothenburg Dept. of Computer Science and Engineering Gothenburg Sweden

ISBN: (纸本)9798350389760

Self-∗ systems focus on optimizing systems regarding adaptation goals, e.g. availability, that relate to properties of the managed system. While these adaptation goals are important, the feedback loop must also be considered. It is problematic if systems adapt too often, make too time-consuming changes that involve insecure transition states, or react too slowly when planning adaptations. Current approaches do not allow to enforce requirements on the adaptation loop - including sensitivity, sta-bility, and transition states. When planning adaptations, those meta-adaptation goals need to be considered and potentially traded off against traditional adaptation goals. Such a tradeoff might entail, for instance, that it may be worth it to adapt a system less frequently, although the overall availability of the system could be higher with more adaptations. We propose to explicitly consider feedback loop requirements for self-adaptive systems. Concretely, we propose using machine learning to predict quality measures based on the state of the feedback loop and the managed system. This information is used to plan for better adaptations that consider the adaptation goals and the meta-adaptation goals of the feedback loop. The explicit representation of meta-adaptation goals and adaptation goals enables the optimization of adaptation strategies, tradeoff analysis, and evaluation of adaptations. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-Enhanced Image Restoration in Remote Sensing via Federated Learning 12

Privacy-Enhanced Image Restoration in Remote Sensing via Fed...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Jahanzeb Khan, M. Rath, Suman Zaib, Muhammad Hassan University of Nevada Reno Dept. of Computer Science and Engineering Reno United States Air University Dept. of Computer Science Islamabad Pakistan

ISBN: (纸本)9798350330366

This research addresses the dual challenges of image restoration quality and data privacy in optical remote sensing. Traditional restoration methods often fall short due to the complex nature of remote sensing images, and data privacy concerns further complicate the use of advanced techniques. By integrating the Deep Memory Connected Neural Network (DMCN) with the Data-Decoupled Federated Learning (DDFL) framework, our approach enables significant improvements in image restoration without requiring direct access to sensitive raw data. This method not only enhances data privacy by leveraging federated learning principles but also incorporates advanced techniques like Gaussian image denoising to maintain high restoration quality despite potential noise introduced by the federated process. The performance of the federated DMCN, particularly on the UCMERCED dataset, demonstrates minimal accuracy degradation, even in the presence of noise, while the strategic use of Downsampling Units within DMCN optimizes computational efficiency. Our comprehensive evaluations reveal the effectiveness of this approach in balancing data privacy with the need for high-quality image restoration, suggesting a promising direction for future advancements in remote sensing applications. © 2024 IEEE.

关键词： Image reconstruction

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：