检索结果-内蒙古大学图书馆

International Journal of Systematic Innovation 2024年第2期8卷 58-69页

作者： Ch, Ravikumar Sridevi, Mulagundla Ramchander, M. Ramesh, Vankudoth Kumar, Vadapally Praveen Department of Artificial Intelligence &Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Computer Science and Engineering CVR College of Engineering Hyderabad 501510 India Department of Computer Applications Chaitanya Bharathi Institute of Technology Hyderabad 500075 India Department of Emerging Technologies CVR College of Engineering Hyderabad 500039 India

In the contemporary digital realm, the utilization of online services has surged, facilitated by the seamless integration of deep learning technology, which is paramount in applications demanding precision and efficiency. A pivotal use case in this context is online handwritten signature verification, where the need for exceptional accuracy is indisputable. This paper introduces ‘Signa-Deep, ’ an innovative approach designed to address the challenge of online signature verification and the determination of an individual’s authorization status. The study explores a range of methodologies, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), GoogleNet, and MobileNet, to discern the authenticity of signatures and affirm the identity of the signatory. The results of our proposed method are promising, showcasing its potential to significantly enhance the security of digital transactions and identity verification processes. In summary, ‘Signa-Deep’ harnesses deep learning technology to bolster the accuracy and reliability of online signature verification, thereby contributing to the overall robustness of digital interactions and identity validation processes. © (2024), (Society of Sytematic Innovation). All rights reserved.

关键词： Authorization Status Deep Learning Digital Transactions Security Identity Authentication Online Signature Verification

来源：评论

学校读者我要写书评

暂无评论

Code word Based Bi-Server Authentication and Key Exchange Encryption Technique 1

Code word Based Bi-Server Authentication and Key Exchange En...

引用

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Thangarasan, T. Karthikeyan, V. Arunkumar, G. Arul Prakash, A. Keerthana, R. Gouthami, Kamsala Madanapalle Institute of Technology & Science Department of Computer Science & Engineering AndhraPradesh Madanapalle India Vel Tech Rangarajan Dr Sagunthala R & D Institute of Science and Technology Department of Computer Science & Engineering Tamilnadu Chennai India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Tamilandu Chennai India K.S.R.College of Engineering Department of Computer Science and Engineering Tamilnadu Tiruchengode India

ISBN: (纸本)9798350328042

The data transfer and communication happening between the client and server or the source to destination should be made in some secure way. It must be protected and authenticated. the passwords related to that all will be stored in a centralized database. The majority of codeword-based user authentication systems assume complete reliance in the authentication server, this refers to the location where centralized databases store passwords in plain text or easily inferred code verification information. System defenses against server-side offline dictionary attacks are nonexistent. In the event that insiders or outsiders hack the authentication server, all user code words become public. which could have severe legal and financial ramifications for a business. A codeword-based client authentication and confidential key exchange system using cutting-edge bi-server architecture serves as the answer to the aforementioned problems. The sever providing the front-end service communicates directly with users in this setup;the control server remains in the background. The proposed system provides security against the offline dictionary attacks that can happen from any of the servers. The proposed work has been implemented by using java and netbeans IDE 6.1. © 2023 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Classification of Complex-Valued Radar Data using Semi-Supervised Learning: a Case Study 49

Classification of Complex-Valued Radar Data using Semi-Super...

引用

49th Euromicro Conference on Software engineering and Advanced Applications, SEAA 2023

作者： Fredriksson, Teodor Bosch, Jan Olsson, Helena Holmstrom Chalmers University of Technology Department of Computer Science and Engineering Gothenburg Sweden Malmö University Department of Computer Science and Media Technology Malmö Sweden

ISBN: (纸本)9798350342352

In recent years, the interest in applying machine learning (ML) and deep learning (DL) has been increasing due to their ability to learn to predict and find structure in data. The most common approach of ML and DL is supervised learning. Supervised learning requires the input data to be labeled. However, as reported by many industries, such as the embedded systems domain, fully labeled datasets are difficult to obtain since data labeling is manually intensive. This paper uses a semi-supervised learning approach on real-world Pulse-Doppler data obtained from our industry collaborator Saab to address this challenge. We took inspiration from the FixMatch algorithm. To investigate whether unlabeled data can help improve classification accuracy, we compare FixMatch to a supervised baseline. We use five different settings for the number of available labels per class label to investigate how many labeled instances and how much manual effort is required for optimal accuracy. Bayesian Linear Regression is used to analyze the results. The results show that FixMatch can reach a higher accuracy than the supervised baseline. Furthermore, FixMatch requires more computation time but will help reduce manual effort. In addition, FixMatch will not underfit or overfit. Thanks to this study, practitioners know the benefits of utilizing FixMatch and when it is safe to use to improve a supervised baseline in the industry. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Community Detection in Social Media Networks with a Multi-Algorithmic Approach

Fast and Accurate Community Detection in Social Media Networ...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Pabitha, P. Petchiammal, G. Eswari Anna University Department of Computer Technology MIT Campu Chromepet600044 India Knowledge Institute of Technology Department of Computer Science and Engineering Salem637504 India

ISBN: (纸本)9798331543617

Community detection is an essential technique for uncovering structural patterns in complex networks, such as social, biological, and information networks. In this paper to explore a hybrid approach to community detection by combining the label propagation algorithm and leiden algorithm. Although LPA is well known for its computational effectiveness in large- scale networks, because of its reliance on local label propagation, it frequently results in unstable and fractured communities. High- quality community structures are produced by the Leiden algorithm, which is more computationally expensive than the Louvain method but ensures well-connected communities by optimising modularity. Our goal in combining these two approaches is to take use of LPA's speed for quick community discovery and the Leiden algorithm's refinement powers for increased accuracy and stability. Large or dynamic networks where both real-time speed and community quality are crucial are best suited for the suggested hybrid method. The combination of these algorithms yields more cohesive and modular communities than either one working alone, as evidenced by experimental results on synthetic social network data. The method is a useful tool for large- scale network analysis because it strikes a balance between the necessity for strong and significant community structures and computational efficiency. © 2024 IEEE.

关键词： Community detection Label propagation leidens Louvain

来源：评论

学校读者我要写书评

暂无评论

Real-time Obesity and Heart Disease Monitoring with IoT and Deep Learning

Real-time Obesity and Heart Disease Monitoring with IoT and ...

引用

2024 International Conference on Smart Devices, ICSD 2024

作者： Singh, Jagendra Govindaraju, P. Kumar, Vinish Yamsani, Nagendar Umamaheswari, J. Munagala, Madhu Bennett University School of Computer Science Engineering & Technology Greater Noida India K S R Institute for Engineering and Technology Department of Electronics and Communication Engineering Tiruchengode India Raj Kumar Goel Institute of Technology Department of Computer Science Engineering Ghaziabad India SR University School of Computer Science and Artificial Intelligence Warangal India Brainware University Department of Computer Science Kolkata India Koneru Lakshmaiah Education Foundation Department of of English Vaddeswaram India

ISBN: (纸本)9798350394412

The accelerating spread of junk food consumption is progressively putting the younger generations at risk of obesity. The concept of health prioritization is deeply rooted in the development of nurturing and general welfare in society. The job has further become more complex by the glaring statistics of people across the globe who are fighting obesity. The World Health Organization (WHO) puts a staggering estimate that approximately 1 billion people across the globe suffer from obesity-related issues, a statistic heavy in terms of impact primarily because obesity greatly affects one's health but also holds fatal risks. Diagnosing the early stages of obesity can just be simple and prevent one from being obese;however, several obstacles stand in the way of its early diagnosis. Symptoms or signs that one is in the trajectory of suffering from obesity generally go unnoticed by the individual, and the availability of specialists to diagnose such risks persistently on time is not always possible. In this regard, the current paper shall showcase an application hitherto unknown using cloud-based diagnosis, in collaboration with machine learning through Secure Access Internet of Things to predict obesity-related risks without having to depend on glaring physical parameter indicators - in this regard, redefining how such information could be sourced even without the need of regularly visiting health professional people. To ensure the best possible health predictability from this machine learning, we gathered and plotted the datasets consisting of obese and overweight people. Other than machine learning, we use a Secure Access IoT sensor network. This allows for real-time monitoring and diagnosis, making early detection achievable. Consequently, this system paves the way for mitigating and substantially reducing the complications associated with obesity. © 2024 IEEE.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Detecting Data Manipulation in Electric Vehicle Charging Stations Using Machine Learning Algorithm 5

Detecting Data Manipulation in Electric Vehicle Charging Sta...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Akhila, Jannavarapu Vani Bhargavi, Maridu Manikanta, Mondem Lakshmi, Srigakolapu Sai Mithra, Nagulapati Phanindra Raja Vignan's Foundation for Science Technology and Research Department of Computer Science And Engineering Vadlamudi AP Guntur India

ISBN: (纸本)9798331530013

A vehicle that functions purely on electricity, as opposed to normal gasoline or diesel automobiles, is known as an electric vehicle (EV). Electric vehicles are becoming extremely popular. EVs come equipped with a built-in connection that allows for features like remote control via smartphone apps, over-the-air software upgrades, and navigation. Smart charging stations are available for electric vehicles (EVs) and are capable of utilizing energy consumption and cost data to improve charging times through communication with the car. However, there are cyber security problems nowadays everywhere. Monthly pricing is one option for charging at electric charging stations. False Data Injection Attacks are a frequent form of attack in which hackers alter data to their benefit. We are developing a machine learning algorithm to identify the site of the deceptive data injection in order to solve this issue. Random Forest Algorithms, RBF kernel, linear kernel, polynomial kernel, and Support Vector Machine were utilized for training and assessing the outcomes. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Multiband Slotted Crescent-shaped Patch Antenna for K-band Satellite and mmWave Communications

引用

IEIE Transactions on Smart Processing and Computing 2022年第3期11卷 213-221页

作者： Hossain, Md Najmul Paul, Liton Chandra Rahim, Md Abdur Shin, Jungpil Department of Electrical Electronic and Communication Engineering Faculty of Engineering and Technology Pabna University of Science and Technology Pabna6600 Bangladesh Department of Computer Science and Engineering Faculty of Engineering and Technology Pabna University of Science and Technology Pabna6600 Bangladesh School of Computer Science and Engineering The University of Aizu Aizuwakamatsu Fukushima965-8580 Japan

In this paper, a multiband miniaturized crescent-shaped patch antenna with circular slots is presented for ultra-wideband applications. The proposed antenna is constructed on a Flame Retardant 4 (FR-4) dielectric substrate. Next-generation wireless communication systems, such as beyond 5G (B5G) and 6G mobile communication systems require a wider bandwidth and higher data rates. The overall size of the proposed antenna is 11.4 mm3 operating in the frequency range of 17.73 GHz to 26.04 GHz and 29.6 GHz to 31.02 GHz for satellite communications and radar systems, respectively, as well as 35.40 GHz to 38.65 GHz for future mmWave B5G mobile applications. These frequency ranges usually fall into the K-band and mmWave frequency spectrums. Simulation results demonstrate that the peak gain of the proposed antenna is 4.68 dB, which is obtained at 25 GHz. © 2022 The Institute of Electronics and Information Engineers.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Optimizing Vanet Communications: A Bibliometric Analysis of Energy-Efficient Strategies with Deep Learning

Optimizing Vanet Communications: A Bibliometric Analysis of ...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Suganya, R. Prakash, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Kattankulathur India Srm Institute of Science and Technology Department of Computing Technologies Tamilnadu Kattankulathur India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

Vehicular Ad Hoc Networks (VANETs) are important for intelligent transportation systems, permitting vehicles to communicate with one another and nearby infrastructure in order to enhance road safety, traffic management and infotainment services. But the VANET communication is a high energy consumption technology, which may become a big challenge of large-scale power efficiency being in some real scenarios where huge number vehicles are needed to implement such V2I or V2V services sustaining. This paper conducts a analysis of different transmission stratagems for energy-efficient communication strategies among vehicles in VANETs, along with the focus to incorporate deep learning accelerators into an optimized architecture framework for enhancing communication processes. The paper presents an overview of VANET architecture and communication protocols, and then reviews the techniques to save energy in a VANET including efficient mechanisms for Transmission Power Control (TPC), some energy-aware routing protocols, as well as data aggregation realizations. Next, the paper introduces deep learning models that can adaptively optimize VANET transmission by forecasting network states and updating strategies on-the-fly. This analysis emphasizes hybrid solutions where deep learning is combined with traditional communication strategies to improve the energy efficiency apparent on a system level. Finally addresses the current challenges in the field and the need for advanced AI-driven techniques. This bibliometric analysis provides a comprehensive overview of energy-efficient communication strategies in VANETs, offering insights into how deep learning can contribute to the development of more sustainable vehicular 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

Improving Security and Performance of Databases Through Single Cache System 4

Improving Security and Performance of Databases Through Sing...

引用

4th International Conference on Blockchain technology and Information Security, ICBCTIS 2024

作者： Ul Haq, Ikram Khan, Salabat Khan, Mansoor Tamsal, Saher School of Computer Science and Technology Southwest University of Science and Technology Mianyang China School of Computer and Information Engineering Qilu Institute of Technology Jinan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China University of Agriculture Department of Computer Science Faisalabad Pakistan

ISBN: (纸本)9798331528324

In today's world, connectivity and performance-driven technology are rapidly advancing each year, and new platforms and mechanisms are being utilized to enhance the security and performance of databases and cloud computing, which are trending in the global market. This examination focused on customer information security in cloud computing, i.e., information stockpiling security issues and how to control unapproved access to data by proposing access control;valuable measures were characterized subsequently, and an entrance control show was prescribed. Cloud computing can be described as an innovation that depends on the web and the sharing of resources. It has an adaptable foundation that customers can use with much of a stretch. With its wide event relationship, there are numerous obstacles to continuing with cloud computing because of security issues, mostly considering customer data security. The proposed study helped hesitant clients sensibly continue forward in the cloud while understanding the dangers of cloud computing. The research objective is to examine the security techniques employed in cloud technology to improve its performance by utilizing data mining within a unified cache system. We will apply the Apriori algorithm as a proposed solution to be used in a single cache while considering the security measures in the cloud. The study expects to apply this method to all cloud providers and vendors by entering data into a single cache mechanism that can be extended into different components and implemented using SPSS modelers to improve the security of the database. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

DRL-Based UAV Path Planning for Coverage Hole Avoidance: Energy Consumption and Outage Time Minimization Trade-Offs

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 4194-4205页

作者： Jafari, Bahareh Hasna, Mazen Pishro-Nik, Hossein Zorba, Nizar Khattab, Tamer Saeedi, Hamid Qatar University Department of Electrical Engineering Doha Qatar University of Massachusetts Department of Electrical and Computer Engineering AmherstMA01003 United States University of Doha for Science and Technology College of Engineering and Technology Doha Qatar

Coverage holes pose critical challenges to reliability of wireless networks and their quality of service (QoS) and therefore should be avoided in the coverage design. In this paper, we address this issue through the deployment of unmanned aerial vehicles (UAVs) as mobile base stations, and we propose specific UAV path planning. A point is said to be in a coverage hole if the coverage probability for that point is below a certain threshold, e.g., 90%. This definition is more suitable for applications such as surveillance or sensor networks. In this paper, we target applications such as wireless communications for which QoS requirement allow only for short time disconnections, i.e., minimal outage time. As such, in addition to avoiding coverage holes, we should also make the outage time as small as possible. By deploying a deep reinforcement learning algorithm, we find optimal UAV paths based on the two families of trajectories: spiral and oval curves, to tackle different design considerations and constraints, in terms of QoS, energy consumption and coverage hole avoidance. We show that for a typical point on the cell, there is a trade-off between minimizing the maximum outage time length and consumed mechanical energy. Our observations indicate that such a trade-off is more pronounced for spiral trajectories compared to oval trajectories, but both of them are useful depending on the QoS and energy constraints imposed by the system. © 2020 IEEE.

关键词： Energy utilization

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：