检索结果-内蒙古大学图书馆

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Wadhwa, Amit Arora, Neerja G. L. Bajaj Institute of Technology and Management Department of Computer Science and Engineering Greater Noida India Ajay Kumar Garg Engineering College Department of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350371055

With the advancement of technologies like cloud computing and Internet of things, there are enormous areas in which these can be utilized. One such domain is Smart City concept utilizing or based on the architecture of Internet of everything. In a smart city the distinguish concept is the utilization of internet of everything architecture to effectively manage the services provided to users. Moreover, integration of internet of everything with cloud computing architecture would provide a better ecosystem in the area of smart cities. Providing services to smart city users could pose certain challenges and security issues with the integration of cloud computing. As per previous studied literature there is scope for improving access and authentication-based security of services imparted to smart city users. In this work, initially the consolidation of internet of everything (IoE) and cloud computing in smart cities is put forward. Further, this work focusses upon issues and challenges encountered in leveraging IoE in smart city environments with analysis of existing techniques for authentication and access control of cloud-based services and later provides a proposed system focusing upon imparting access control and authentication-oriented security for services delivered over a cloud and IoE followed by its analysis. © 2024 IEEE.

关键词： Access Control Authentication Cloud Computing Services IOE (Internet of Everything) Smart Cities

来源：评论

学校读者我要写书评

暂无评论

Optimizing Gene Expression Analysis Using Clustering Algorithms 1

引用

5th International Conference on computer and Communication Technologies, IC3T 2023

作者： Bikku, Thulasi Ramu, J. Sekhar, J. Chandra Pratap, V. Krishna Pujari, Jeevana Jyothi Computer Science and Engineering Amrita School of Computing Amaravati Amrita Vishwa Vidyapeetham Andhra Pradesh Amaravati522503 India Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Database Systems School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632014 India

ISBN: (数字)9789819997077

ISBN: (纸本)9789819997060

Gene expression analysis plays a crucial role in understanding biological processes and diseases. However, the high-dimensional nature of gene expression data poses challenges for its analysis and interpretation. Clustering algorithms have been widely used for identifying patterns in gene expression data, but their effectiveness is limited by the choice of algorithm and parameters used. In this study, we propose an approach for optimizing gene expression analysis using clustering algorithms. Initially, a range of clustering techniques were assessed, encompassing K-means, hierarchical clustering, and DBSCAN. This assessment was conducted using gene expression information sourced from a publicly accessible database. Subsequently, various techniques for feature selection were employed. These techniques encompassed principal component analysis (PCA) as well as correlation-based feature selection (CFS). Their objective was twofold: to decrease the data's dimensionality and to enhance the effectiveness of the clustering process. From the study, we came to know that the combination of K-means clustering with PCA feature selection outperformed other methods in terms of clustering accuracy and stability. We also identified a set of genes that were consistently associated with different clusters, providing insights into the underlying biological processes. Overall, our study demonstrates the importance of careful algorithm and parameter selection for gene expression analysis and highlights the potential of clustering algorithms for identifying meaningful patterns in gene expression data. The suggested methodology entails merging DBSCAN with K-means clustering, which could be extended to diverse high-dimensional datasets for the enhancement of their analysis and comprehension. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

CASE: A Joint Traffic and Energy Optimization Framework Toward Grid Connected Green Future Networks

引用

IEEE Transactions on Network and Service Management 2024年第3期21卷 2888-2899页

作者： Balakrishnan, Ashutosh De, Swades Wang, Li-Chun Indian Institute of Technology Delhi Department of Electrical Engineering New Delhi110016 India National Yang Ming Chiao Tung University International College of Semiconductor Technology Hsinchu City300 Taiwan Indian Institute of Technology Delhi Department of Electrical Engineering The Bharti School of Telecommunication New Delhi110016 India National Yang Ming Chiao Tung University Department of Electrical and Computer Engineering Hsinchu City300 Taiwan

Renewable power provisioning of the base stations (BS) in addition to the traditional power grid connectivity presents an interesting prospect towards realizing green future network services. Designing such dual-powered systems is challenging due to the presence of space-time varying stochasticity in traffic and green energy harvest at each BS. These traffic and green energy imbalances result in non-optimal network green energy utilization and thus resulting in a higher grid energy purchase to the mobile operator. In this paper, we present a novel coverage adjustment and sharing of energy (CASE) framework that exploits the user traffic load and green energy availability imbalances across the networked BSs towards maximizing the operator profit and designing energy sustainable system. The profit maximization problem is formulated considering the networked BSs to have the flexibility of load aware coverage adjustment and green energy sharing capability among themselves, in addition to trading energy with the grid. The proposed CASE framework first leverages the spatio-temporal traffic and energy inhomogeneities and performs load management for maximizing user quality of service (QoS). The CASE strategy then distributes the residual energy imbalance across the BSs and maximizes the utilization of temporal green energy harvest across the BSs. The proposed strategy is compared with only coverage adjustment, only sharing of energy, and a benchmark without CASE based framework. Our simulation results indicate significant improvement in user QoS and operator profit, up to 18% and 39% respectively at high skewness scenario, in addition to fully utilizing the green energy potential in the network. 1932-4537 © 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

Custom Transformer-Based Approach for Enhanced Bengali Automatic Speech Recognition 1

Custom Transformer-Based Approach for Enhanced Bengali Autom...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Deepa, R. Jayalakshmi, V. Thilakavathy, P. Manikandan, G. Surendran, R. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Computer Science and Applications Ramapuram Chennai India Vels Institute of Science and Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Anna University St. Joseph's College of Engineering Department of Artificial Intelligence and Machine Learning Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350376517

ISBN: (纸本)9798350376517

Automated speech recognition (ASR) systems struggle with Bengali, which is the fifth most spoken language. Bengali has a varied morphology, many dialects, and limited high-quality annotated voice data. Traditional voice recognition techniques work well however struggle with Bengali phonetics and syntax. This method eliminates the need for large amounts of tagged data and the difficulties of differentiating sounds in different languages, both issues are addressed by this procedure. The research in this paper offers an Intellectual Bengali Speech Recognition System using Deep Learning Techniques (IBSRS-DLT). The model in this system uses transformer architecture and attention processes to manage Bengali speech pattern long-range dependencies. The IBSRS-DLT outperforms standard models in recognition accuracy using a pre-trained transformer model modified for phonetic and lexical correctness and fine-tuned on Bengali datasets. After training on a vast Bengali speech corpus, real-world datasets and rigorous simulations confirm the system. IBSRS-DLT can be used for automatic transcription, voice-controlled devices, and Bengali virtual assistants, such applications are efficient and accessible. The simulation showed a considerable boost in recognition speed and a decrease in keyword mistakes compared to current methods. This paper shows that deep learning can solve linguistic issues in ASR systems, enabling scalable regional language detection. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Security of SDN in 5G: A Hybrid Feature Selection Based Ensemble Machine Learning Framework for Classification of Cyber-Attacks

引用

SN computer science 2025年第3期6卷 1-16页

作者： Singh, Mahendra Pratap Haimashreelakshmi Singh, Virendra Pratap Gupta, Maanak Cyber Security Research Lab (CSRL) Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal Mangaluru 575025 India Department of Computer Science Tennessee Technological University Cookeville TN United States

In recent years, the adoption of 5G has significantly increased due to its numerous benefits, including high availability, lower latency, improved reliability, and high performance. To manage packet flow, 5G relies on Software-Defined Networking (SDN) that employs software controllers and Application Programming Interfaces (APIs) to route packets and communicate with the hardware, providing advantages like high efficiency, low cost, and dependability. However, due to centralized control, SDN controllers are vulnerable to various cyber-attacks, including Distributed Denial of Service (DDoS), Denial of Service (DoS), Password Brute Forcing, Web Attacks, etc. This paper proposes a framework that comprises a hybrid feature selection method and an ensemble machine learning model. The proposed ensemble model combines the strengths of three different machine learning (ML) classifiers to create a voting classifier for classifying traffic in SDN. Additionally, the optimal value for the hyperparameters of each classifier is obtained through hyperparameter tuning. Finally, the experimental analysis of the proposed model using the InSDN dataset shows 99.96% accuracy, highlighting the proposed model’s effectiveness in addressing the limitations of the existing approaches and detecting multiple attacks in the SDN context. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： 5G Hybrid feature selection Machine learning Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Approach for Double Security with Watermarking and Chaos Based Encryption for e-Healthcare Systems 4

Approach for Double Security with Watermarking and Chaos Bas...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Sharma, Suvita Rani Singh, Birmohan Kaur, Manpreet Singh, Harpreet Sant Longowal Institute of Engineering and Technology Department of Computer Science and Engineering Punjab Sangrur148106 India Sant Longowal Institute of Engineering and Technology Department of Electrical and Instrumentation Engineering Punjab Sangrur148106 India

ISBN: (纸本)9798350395914

Medical data of the patients includes sensitive information and needs security while transmit over the internet. The double security approach based on watermarking and encryption method has been purposed in this work to secure the patient information consisting personal information, clinical information, and diagnostic records along with the medical images. The watermarking method is introduced on the basis of the least significant bit (LSB) method that conceals the patient information in the LSB bit of the image to hide the information. As, the LSB bit of the image is consider as least informative bit. Thus, it reduces the loss of data in the image. Then, the watermarked image is secured using the hybrid encryption method based on the Self Adaptive Bald Eagle Search (SABES) optimization algorithm, multiple chaotic maps, and circular shift. Chaotic maps are employed in the proposed approach to increase randomness in the encrypted image and chaotic maps' parameters are optimized employing the SABES optimization method to increase the chaotic maps efficiency. The propounded approach is tested on different types of medical images i.e., Grayscale, RGB, and hyperspectral images having different modalities and sizes. The performance of the propounded approach has been analyzed utilizing the Normalized Correlation (NC), Peak Signal-to-Noise Ratio (PSNR), entropy, histogram, Number of Changing Pixel Rate (NPCR), Structural Similarity Measure (SSIM), and Unified Averaged Changed Intensity (UACI) test. The proposed approach performance shows that the medical information secure from different types of attacks. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Detecting influential nodes with topological structure via Graph Neural Network approach in social networks

引用

International Journal of Information technology (Singapore) 2023年第4期15卷 2233-2246页

作者： Bhattacharya, Riju Nagwani, Naresh Kumar Tripathi, Sarsij Department of Computer Science and Engineering National Institute of Technology Raipur GE Road Chhattisgarh Raipur 492010 India Department of Computer Science and Engineering Motilal Nehru National Institute of Technology Allahabad Uttar Pradesh Prayagraj 211004 India

Detecting influential nodes in complex social networks is crucial due to the enormous amount of data and the constantly changing behavior of existing topologies. Centrality-based and machine-learning approaches focus mostly on node topologies or feature values in their evaluation of nodes’ relevance. However, both network topologies and node attributes should be taken into account when determining the influential value of nodes. This research has proposed a deep learning model called Graph Convolutional Networks (GCN) to discover the significant nodes in graph-based large datasets. A deep learning framework for identifying influential nodes with structural centrality via Graph Convolutional Networks called DeepInfNode has been developed. The proposed approach measures up contextual information from Susceptible-Infected-Recovered (SIR) model trials to measure the rate of infection to develop node representations. In the experimental section, acquired experimental results indicate that the suggested model has a higher F1 and Area under the curve (AUC) value. The findings indicate that the strategy is both effective and precise in terms of suggesting new linkages. The proposed DeepInfNode model outperforms state-of-the-art approaches on a variety of publicly available standard graph datasets, achieving an increase in performance of up to 99.1% of accuracy. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Deep learning Graph Convolutional Network Influential nodes Susceptible Infected Recovered Topological features

来源：评论

学校读者我要写书评

暂无评论

Amalgamation of Transfer Learning and Explainable AI for Internet of Medical Things

引用

Recent Advances in computer science and Communications 2024年第4期17卷 40-53页

作者： Murugan, Ramalingam Paliwal, Manish Patibandla, Rama Seetha Maha Lakshmi Shah, Pooja Balaga, Tarakeswara Rao Gurrammagari, Deepti Raj Singaravelu, Parvathavarthini Yenduri, Gokul Jhaveri, Rutvij School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India School of Technology Pandit Deendayal Energy University Gujarat Gandhinagar India AP India Kallam Haranadhareddy Institute of Technology Andra Pradesh Guntur India Department of Computer Applications Kongu Engineering College Erode Perundurai India

The Internet of Medical Things (IoMT), a growing field, involves the interconnection of medical devices and data sources. It connects smart devices with data and optimizes patient data with real time insights and personalized solutions. It is mandatory to hold the development of IoMT and join the evolution of healthcare. This integration of Transfer Learning and Explainable AI for IoMT is considered to be an essential advancement in healthcare. By making use of knowledge transfer between medical domains, Transfer Learning enhances diagnostic accuracy while reducing data necessities. This makes IoMT applications more efficient which is considered to be a mandate in today’s healthcare. In addition, explainable AI techniques offer transparency and interpretability to AI driven medical decisions. This can foster trust among healthcare professionals and patients. This integration empowers personalized medicine, supports clinical decision making, and confirms the responsible handling of sensitive patient data. Therefore, this integration promises to revolutionize healthcare by merging the strengths of AI driven insights with the requirement for understandable, trustworthy, and adaptable systems in the IoMT ecosystem. © 2024 Bentham science Publishers.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Hierarchical Micro/Nano Surface Structures Induced by high Repetition rate femto-second Laser Pulses on Ti6Al4V in Ambient air

引用

Lasers in Manufacturing and Materials Processing 2023年第1期10卷 118-140页

作者： Munaswamy, Murugesh Sasaki, Koichi Samuel, Gl Manufacturing Engineering Section Department of Mechanical Engineering Indian Institute of Technology Chennai600 036 India Division of Applied Quantum Science and Engineering Hokkaido University Sapporo060-8628 Japan

Surface engineered components with micro/nano scale periodic surface structures are having a wide range of industrial applications, owing to their unique tribology enhancing characteristics. Generally, design and development of highly controlled sub micro-scale structures with intricate feature characteristics are highly challenging for the manufacturing industries, especially super alloys like titanium due to its inherent low thermal conductivity and higher chemical reactive property. This forms the major objective of the present research work emphasizing the methodology - hatching technique (dot and line) to create highly controlled micro/nano scale periodic surface structures. The recently widespread femtosecond pulsed laser processing can be an efficient alternative method for the usual industrial practice of generating periodic surface structures. Femtosecond pules hatch pitch was varied from 10 to 50 μm (with 250 pulses per spot), at higher repetition rates and scanning speeds of 200 to 500 kHz and 500 to 2000 mm/s respectively. The periodic surface structures analysed were found to be close to the wavelength (1030 nm) of incident pulsed laser, wherein the micro scale structures (in the range of 6 to 10 μm) were observed to be covered with nano scale structures. Furthermore, generated multiscale surface structures were observed to be having a higher degree of similarity to the Tetrodontophora Bielanensis, a European giant springtail skin structure, which revealed the possibility of achieving the concept of ‘Bio mimicking’ using this approach. Microdots, micro/nano columns, pillars, ripples, and cones are the various types of surface structures reported in the present research work. © 2022, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Surface roughness

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Implementation of Optimal Classification Algorithms for Credit Card Fraud Detection 2

Evaluation and Implementation of Optimal Classification Algo...

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Sampath Kini, K. Pushpakumar, R. Senthamil Selvan, R. Praveenkumar, G.D. Basi Reddy, A. Nitte Deemed To be University Department of Computer Science and Engineering Karkala India Vel Tech Rangarajan Dr.Sangunthala R&d Institute of Science and Technology Department of Information Technology Avadi India Annamacharya Institute of Technology and Sciences Department of Electronics and Communication Engineering Tirupati India Kongu Engineering College Department of Computer Technology Erode India School of Computing Mohan Babu University Department of Computer Science and Engineering Tirupati India

ISBN: (纸本)9798350364699

Nowadays, the credit card industry is more concerned about credit card fraud than any other problem. The main idea is to examine optional techniques used for fraud detection and to identify the different types of credit card fraud. Numerous strategies exist for lowering the prevalence of credit card fraud, each tailored to the specific threats faced by banks and the credit card industry. Credit card fraud prevention is the primary goal of implementing these measures. Existing methods have several unresolved issues that cause legitimate credit card customers to be mistakenly labelled as fraudulent. The amount of fraud in the financial sphere may be inferred from this paper's emphasis on integrating the best classification algorithm out of four distinct methods. © 2024 IEEE.

关键词： Credit card fraud faced by bank Financial sphere mistakenly labelled Primary Goal

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：