检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Karthikeyan, M. Saravana Subramani, Ponnusamy Selvam, M. Panneer Sworna Kokila, M.L. Vijayalakshmi, R. Sundaravadivel, P. Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Department of Computer Science and Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Physics Chennai India Sona College of Technology Department of Electrical and Electronics Engineering Salem India School of Computing SRM Institute of Science and Technology Kattankulathur Faculty of Engineering and Technology Department of Computing Technologies Chennai India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798331505745

The rapid expansion of loT-based sensor networks has necessitated the development of efficient edge analytics frameworks to process vast amounts of data in real time while minimizing computational overhead. Deep learning-powered edge computing has emerged as a transformative approach, enhancing data processing capabilities at the network edge while addressing constraints related to latency, bandwidth, and energy consumption. This study introduces a novel algorithm, Lightweight AI Model Compression for Energy-Efficient IoT Edge Devices (LiteEdgeAI), designed to optimize deep learning models for resource-constrained edge environments. The proposed method employs quantization, pruning, and knowledge distillation techniques to achieve significant reductions in model size and computational complexity while maintaining high inference accuracy. To validate the efficiency of LiteEdgeAI, a comparative simulation analysis was conducted against existing state-of-the-art algorithms using key performance metrics such prediction accuracy, energy efficiency and computational complexity. Experimental results demonstrated that LiteEdgeAI outperformed baseline models. The findings highlight the potential of LiteEdgeAI in enabling scalable, low-power, and real-time edge intelligence for IoT-based sensor networks. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Strategies for Scalable and Heterogeneous VANET Network 5

Adaptive Strategies for Scalable and Heterogeneous VANET Net...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Thangam, S. Jha, Priyanshu Hawari, Jawed Sah, Nabin Kumar Jain, Nikunj Jesy Janet Kumari, J.J. Saleem Raja, A. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India College of Computing and Information Sciences University of Technology and Applied Sciences It Department Shinas Oman

ISBN: (纸本)9798350385649

Despite technological advancements, Vehicular Ad-hoc Networks (VANETs) continue to face challenges related to reliability and high-speed mobility. This study focuses on enhancing scalability, improving mobility, and addressing network heterogeneity in the context of data dissemination. Data dissemination involves the distribution or transmission of statistical data to users. Tools like NS3, SUMO utilizing OSM for realistic traffic simulations, MATLAB for Data Analysis and evaluation of various protocols like ADHOC, Dynamic Source Routing (DSR), Optimized Link State Routing Protocol (OLSR), Destination Sequenced Distance Vector Routing (DSDV). The research aimed to refine VANET simulations for effective decision making, as its primary objective data dissemination i.e. distribution or transmission of statistical data to users, forming the central focus of this investigation. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Chest X-Ray-Based Covid-19 Detection Using Preprocessing Techniques and Deep Learning Algorithms 7th

Chest X-Ray-Based Covid-19 Detection Using Preprocessing Tec...

引用

7th International Conference on Soft computing: Theories and Applications, SoCTA 2023

作者： Kurian, Thanu Thangam, S. Raja, A. Saleem Reddy, K. Lokeswar Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India IT Department College of Computing and Information Sciences University of Technology and Applied Sciences-Shinas Shinas Oman

ISBN: (纸本)9789819720880

Covid-19 is a transmissible infection identified in Wuhan, China, in December 2019 where more than million people were killed. When the contamination enters body, it contacts the mucous film that lies in your mouth, eyes, and nose. The virus entering a cell makes new disease parts making use of the cell and spreads infections by attacking nearest cells. Signs could begin one to fourteen days subsequent to presenting to the infection. Majority of them suffer with pneumonia, while a few suffer with extreme side effects like shortness of breath, headache, and fast heartbeat. Medical practitioners can see indications of respiratory infections on a chest X-ray. So, to detect if a person is suffering with Covid-19, the chest images help in the early analysis and the treatment of the patient. This study utilizes multiple datasets containing images of chest X-ray and makes use of preprocessing techniques like image augmentation, resizing, Contrast-Limited Adaptive Histogram Equalization (CLAHE) and trained using Deep learning algorithms like CNN, VGG-16, VGG-19, and AlexNet. CNN model with a maximum pooling layer and a flatten layer outperformed other algorithms when trained on image augmentation and normalization images and achieved accuracy of 0.98. Finally, integrating the best suitable model with web applications like Flask helps to reduce the burden on doctors and minimize the human error in Covid-19 detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A Comparative Exploration of Time Series Models for Wild Fire Prediction 4

A Comparative Exploration of Time Series Models for Wild Fir...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Sri Sowmya, V. Sasikala, D. Theetchenya, S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India Sona College of Technology Department of Computer Science and Engineering Salem India

ISBN: (纸本)9798350343670

Wildfires pose a great threat to human safety and property arising from both natural and human causes. According to a technical assessment by the Forest Survey of India more than 95% of fires are of anthropogenic origin. Wildfires erupt due to burning of fossils by local communities for crop rotation, camp fires without proper supervision etc. Climate change further elevates the risk by fostering dry conditions. Traditionally, wildfire prediction relied on statistical models and expert judgment. However, the emergence of Machine Learning (ML) and Deep Learning (DL) techniques has significantly improved the accuracy of forest fire prediction. The objective of this work is to prevent wildfires and save the ecosystem. In this work, LightGBM(Light Gradient Boosting Machine) and LSTM(Long Short-Term Memory) machine learning models are utilized to predict the forest fire. Both models exhibit high F1 scores of 97% and 95% accuracy in forest fire prediction, enabling the development of reliable prediction systems. The results of these ML-based models may aid in identifying highrisk areas, optimizing prevention measures, refining evacuation plans, and guiding firefighting efforts. © 2024 IEEE.

关键词： Deep Learning(DL) LightGBM LSTM Machine learning(ML) Wildfires

来源：评论

学校读者我要写书评

暂无评论

Pixel+ and Pixel++: Compact and Efficient Forward-Secure Multi-Signatures for PoS Blockchain Consensus 33

Pixel+ and Pixel++: Compact and Efficient Forward-Secure Mul...

引用

33rd USENIX Security Symposium, USENIX Security 2024

作者： Wei, Jianghong Tian, Guohua Wang, Ding Guo, Fuchun Susilo, Willy Chen, Xiaofeng Xidian University China State Key Laboratory of Mathematical Engineering and Advanced Computing China College of Cyber Science Nankai University China School of Computing and Information Technology University of Wollongong Australia

ISBN: (纸本)9781939133441

Multi-signature schemes have attracted considerable attention in recent years due to their popular applications in PoS blockchains. However, the use of general multi-signature schemes poses a critical threat to the security of PoS blockchains once signing keys get corrupted. That is, after an adversary obtains enough signing keys, it can break the immutable nature of PoS blockchains by forking the chain and modifying the history from some point in the past. Forward-secure multi-signature (FS-MS) schemes can overcome this issue by periodically updating signing keys. The only FS-MS construction currently available is Drijvers et al's Pixel, which builds on pairing groups and only achieves forward security at the time period level. In this work, we present new FS-MS constructions that either are free from pairing or capture forward security at the individual message level (i.e., fine-grained forward security). Our first construction Pixel+ works for a maximum number of time periods T. Pixel+ signatures consist of only one group element, and can be verified using two exponentiations. It is the first FS-MS from RSA assumption, and has 3.5x and 22.8x faster signing and verification than Pixel, respectively. Our second FS-MS construction Pixel++ is a pairing-based one. It immediately revokes the signing key's capacity of re-signing the message after creating a signature on this message, rather than at the end of the current time period. Thus, it provides more practical forward security than Pixel. On the other hand, Pixel++ is almost as efficient as Pixel in terms of signing and verification. Both Pixel+ and Pixel++ allow for non-interactive aggregation of signatures from independent signers and are proven to be secure in the random oracle model. In addition, they also support the aggregation of public keys, significantly reducing the storage overhead on PoS blockchains. We demonstrate how to integrate Pixel+ and Pixel++ into PoS blockchains. As a proof-of-concept, we prov

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

QoS CBSC: An Enhanced Metaheuristic Strategy on QoS-Cloud-based Service in Cloud 5

QoS CBSC: An Enhanced Metaheuristic Strategy on QoS-Cloud-ba...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Jesy Janet Kumari, J. Thangam, S. Saleem Raja, A. Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India College of Computing and Information Sciences University of Technology and Applied Sciences-Shinas It Department Oman

ISBN: (纸本)9798350385649

Due to the growing number of cloud users working on various cloud apps on specific infrastructure, resource allocation in cloud computing is implicitly difficult. Most resource allocation strategies currently in use focused on delivering efficiency determined by the workload of applications across many domains, such as business and scientific. Cloud service brokers compete strongly with one another to provide quality of service improvements based on the need, demand and the rapid growth of the services that are offered. Such conflict makes it difficult and complex to provide simple service selection and composition services in the cloud, this needs to be addressed to lighten the load on local resources. Because cloud-based services are too sophisticated and scalable, it is preferable to use an optimization strategy to choose the services that will meet the needs of the clients. To do this, a hybrid algorithm Modified Ant Colony System Cloud Services Composition (MACSCSC) is proposed to employ Ant Colony Optimization (ACO) incorporated with Genetic Algorithm (GA) to smoothly increase cloud-based services. When allocating cloud resources these meta-heuristic algorithms can achieve significantly better performance, lower costs and instances, better utilization of resources, and increased energy efficiency. The empirical findings on different real datasets have been demonstrated to show the improvements of the suggested method to overcome the drawbacks such as allocation of resources and high power consumption. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Smart Traffic Management in Green VANETs: Ant-Inspired Routing Strategies with Local Search Optimization

Smart Traffic Management in Green VANETs: Ant-Inspired Routi...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Thangam, S. Jahnavi, M. Chandana, K. Dheeraj, K. Janet Kumari, J Jesy Saleem Raja, A. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India University of Technology and Applied Sciences-Shinas College of Computing and Information Sciences It Department Oman

ISBN: (纸本)9798350309140

Green Vehicular Ad-hoc Networks (VANETs) are gaining significance in smart mobility because of growing concerns about the environment. The research introduces a novel method for managing traffic in such networks by combining ant-inspired routing methods with local search optimization approaches. The solution, which draws inspiration from the efficient path-finding abilities of ants, facilitates decentralized communication and sharing of traffic data among cars. It allows rapid adaptation to changing traffic circumstances and environmental elements. Local search optimization enhances routing decisions by considering the near vicinity of each vehicle. Extensive simulations demonstrate notable enhancements in traffic efficiency, decreased congestion, and improved energy conservation as compared to conventional routing methods. The suggested solutions also enhance the development of environmentally friendly and enduring transportation networks. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

OLBR: Optimization of Location-Based Routing Protocols in Vehicular Ad Hoc Networks

OLBR: Optimization of Location-Based Routing Protocols in Ve...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Thangam, S. Srikar Reddy, M. Vivek Ullas, Karthik Khadar Jilani, N. Abdul Venkatesh, K. Janet Kumari, J. Jesy Saleem Raja, A. Amrita School of Computing Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India University of Technology and Applied Sciences-Shinas College of Computing and Information Sciences It Department Oman

ISBN: (纸本)9798350309140

The proposed work employs ns-3, SUMO, and NetAnim to create geographical routing in vehicular ad hoc networks (VANETs). The research attempts to assess the performance of three well-known protocols AODV, DSDV, and OLSR in VANET settings. Utilizing SUMO's realistic mobility models and NS3's simulation capabilities, the project simulates node communication, protocol behaviour, and vehicle movement. The main purpose is to know how well various routing techniques work in dynamic vehicular situations. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Text Sentiment Analysis Based on Multi-Layer Bi-Directional LSTM with a Trapezoidal Structure

引用

Intelligent Automation & Soft computing 2023年第7期37卷 639-654页

作者： Zhengfang He Cristina E.Dumdumaya Ivy Kim D.Machica School of Intelligent Science and Engineering Yunnan Technology and Business UniversityKunming650000China College of Information and Computing University of Southeastern PhilippinesDavao CityDavao del SurPhilippines

Sentiment analysis,commonly called opinion mining or emotion artificial intelligence(AI),employs biometrics,computational linguistics,nat-ural language processing,and text analysis to systematically identify,extract,measure,and investigate affective states and subjective *** analy-sis algorithms include emotion lexicon,traditional machine learning,and deep *** the text sentiment analysis algorithm based on a neural network,multi-layer Bi-directional long short-term memory(LSTM)is widely used,but the parameter amount of this model is too ***,this paper proposes a Bi-directional LSTM with a trapezoidal structure *** design of the trapezoidal structure is derived from classic neural networks,such as LeNet-5 and *** classic models have trapezoidal-like structures,and these structures have achieved success in the field of deep *** are two benefits to using the Bi-directional LSTM with a trapezoidal *** is that compared with the single-layer configuration,using the of the multi-layer structure can better extract the high-dimensional features of the *** is that using the trapezoidal structure can reduce the model’s *** paper introduces the Bi-directional LSTM with a trapezoidal structure model in detail and uses Stanford sentiment treebank 2(STS-2)for *** can be seen from the experimental results that the trapezoidal structure model and the normal structure model have similar ***,the trapezoidal structure model parameters are 35.75%less than the normal structure model.

关键词： Text sentiment Bi-directional LSTM Trapezoidal structure

来源：评论

学校读者我要写书评

暂无评论

Gaussian Backbone-Based Spherical Evolutionary Algorithm with Cross-search for engineering Problems

引用

Journal of Bionic engineering 2024年第2期21卷 1055-1091页

作者： Yupeng Li Dong Zhao Ali Asghar Heidari Shuihua Wang Huiling Chen Yudong Zhang College of Computer Science and Technology Changchun Normal UniversityChangchun130032JilinChina School of Surveying and Geospatial Engineering College of EngineeringUniversity of TehranTehranIran School of Computing and Mathematical Sciences University of LeicesterLeicesterLE17RHUK Department of Biological Sciences Xi’an Jiaotong-Liverpool UniversitySuzhou215123JiangsuChina Key Laboratory of Intelligent Informatics for Safety and Emergency of Zhejiang Province Wenzhou UniversityWenzhou325035China School of Computer Science and Engineering Southeast UniversityNanjing210096China

In recent years,with the increasing demand for social production,engineering design problems have gradually become more and more *** novel and well-performing meta-heuristic algorithms have been studied and developed to cope with this *** them,the Spherical Evolutionary Algorithm(SE)is one of the classical representative methods that proposed in recent years with admirable optimization ***,it tends to stagnate prematurely to local optima in solving some specific ***,this paper proposes an SE variant integrating the Cross-search Mutation(CSM)and Gaussian Backbone Strategy(GBS),called *** this study,the CSM can enhance its social learning ability,which strengthens the utilization rate of SE on effective information;the GBS cooperates with the original rules of SE to further improve the convergence effect of *** objectively demonstrate the core advantages of CGSE,this paper designs a series of global optimization experiments based on IEEE CEC2017,and CGSE is used to solve six engineering design problems with *** final experimental results fully showcase that,compared with the existing well-known methods,CGSE has a very significant competitive advantage in global tasks and has certain practical value in real ***,the proposed CGSE is a promising and first-rate algorithm with good potential strength in the field of engineering design.

关键词： Meta-heuristic algorithms engineering optimization Spherical evolution algorithm Global optimization

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：