检索结果-内蒙古大学图书馆

Innovation in technology (INOCON), IEEE International Conference for

作者： Shivam Singla Vijay Kumar Bohat Manav Aggarwal Yatin Mehta Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

Single Image Super-Resolution (SISR) aims to generate high-resolution (HR) images from the low-resolution (LR) input images. Deep learning techniques have significantly improved the HR outputs. These techniques primarily use the Mean Squared Error (MSE) Loss function for training purposes which considers pixels and doesn’t take into account the structural information, textures, luminance, and contrast. These features play a crucial role in determining the perceptual quality of the image. Structural Similarity Index Metric (SSIM) can be manipulated to be used as a loss function that gives bright and well-structured HR images. However, this technique sometimes produces blurry and noisy HR outputs. To address this, a Hybrid Perceptual Structural and Pixel-wise Residual (HyPSPR) loss function approach has been introduced. This regularisation technique balances both factors. The Perceptual Structural (PS) Factor improves the structural information, textures, luminance, and contrast, while the Pixel-wise Residual (PR) Factor improves the encoded pixel-level information. A denoising and sharpening block in the model architecture has also been added to reduce the gaussian noise in the output.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Image Analysis for E-Healthcare Systems using Multi-Biometric Recognition Model

Image Analysis for E-Healthcare Systems using Multi-Biometri...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Bansal, Naman Arora, Pranav Sharma, Deepak Kumar Gupta, Koyel Datta Kuntala, Chandana Netaji Subhas Institute of Technology University of Delhi Department of Instrumentation and Control Engineering New Delhi India Indira Gandhi Delhi Technical University for Women Department of Information Technology New Delhi India Maharaja Surajmal Institute of Technology Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9798350396485

With the dawn of e-Healthcare systems, Medical Record Management has become an important research problem. The storage and organization of medical records have made relatively little progress in a world of constantly emerging new technologies and continuous innovation. Many hospitals keep the records on paper, which raises many challenges, including but not limited to a significant amount of time for searching and retrieving a specific record, high maintenance costs, lack of backup, and limited security. Although the inclusion of technology has made this task far more efficient and secure, there is still much that can be done to improve it. This paper proposes a double index-based approach for mapping medical records directly to a patient's biometrics which would take advantage of the uniqueness of biometrics to identify a patient. The proposed multi-biometric model achieves an accuracy of 97% and an F 1 score of 0.9814. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Trustful Payment System for Crowdfunding using Blockchain

A Trustful Payment System for Crowdfunding using Blockchain

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Kumar, Kiran Vashist, Rahul Vashist, Prem Chand G. L. Bajaj Institute of Technology and Management Department of Information Technology Greater Noida India Netaji Subhas Institute of Technology Electronics and Communication Engineering New Delhi India

ISBN: (纸本)9798350322309

Ideas lead to innovation which benefits the society. Innovation is a way of advancing, evolving, and improving our way of living. It is also a method of growing our economy. But to bring these ideas into reality, a huge capital investment is required. Sometimes, the person himself is capable of funding the project. Other times, when he's not capable of funding his project, he may resort to other methods of raising money. One of these successful methods include crowd funding. Crowdfunding refers to the use of small amounts of capital from a large number of individuals to finance a new business venture. In exchange for their investment, the contributors get certain rewards. These rewards may include profits or some other *** can be done through various platforms like social media. There are also some specific websites that focus on the idea of crowdfunding. These crowdfunding websites include crowdfunding platforms like Kickstarter, GoFundMe, Experiment, Fundly. But with the rising popularity of these investment based crowdfunding websites, there is also a rise in the cases of scam via these websites where the people don't get any reward in exchange for their *** issue with the traditional payment systems is that noticeable transaction fee is levied on payment via these payment methods. Our main goal is to create an intermediate network between the communities and the project idea for the scam-proof arrangement. The issue with the transaction fee would also be resolved to some extent. We proposed to do this by using Ethereum Smart Contracts-Blockchain instead of the traditional payment methods. This would result in considerable decrease in the scams and make it a trustworthy payment system and would attract more audience. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning: A Comprehensive Overview and Analysis

Quantum Machine Learning: A Comprehensive Overview and Analy...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Shreshtha Misra Poonam Rani Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The emerging field of Quantum Machine learning (QML), which offers noticeably faster processing speed, is the result of the merger of Quantum Computing (QC) and Machine Learning (ML). Superposition and Entanglement are the fundamental concepts of QC, which increases computational scalability. This comprehensive overview examines QML foundations, algorithms, applications, and challenges of QML. When applied to the Cleveland Heart Disease Dataset, the Quantum Support Vector Classifier (QSVC) achieves an accuracy of 0.75 whereas the Variational Quantum Classifier (VQC) yields an accuracy of 0.62, thus showing that QSVC outperforms VQC. The main issue in QML that calls for effort and investment is noise. QML has the potential to advance technology and has its application in a variety of domains.

关键词： Heart Machine learning algorithms Accuracy Noise Software algorithms Machine learning Vectors Classification algorithms Diseases Software engineering

来源：评论

学校读者我要写书评

暂无评论

Towards WRSN Security: Probabilistic Approach for Malicious Node Identification

Towards WRSN Security: Probabilistic Approach for Malicious ...

引用

Australasian Telecommunication Networks and Applications Conference, ATNAC

作者： Ayush Verma Tanuj Chandela Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9798350379112

ISBN: (纸本)9798350379129

The advancement of Wireless Power Transfer (WPT) has led to the widespread adoption of Wireless Rechargeable Sensor Nodes (WRSN s) for distributed reporting, making these networks attractive targets for adversaries seeking to disrupt their functionality. Numerous solutions have been proposed, such as machine learning, cryptography, and verification protocols. However, these methods are typically designed for Wireless Sensor Networks (WSNs) and may not be suitable for resource-constrained rechargeable sensor nodes. In this paper, we focus on preventing malicious nodes from establishing legitimate connections with normal nodes in WRSN, which can severely disrupt the network. We propose a sensor node registration mechanism with multiple Cuckoo Filter-based verification and malicious node isolation. We also employ MinHashing, k-shingling, and Jaccard similarity techniques at the Mobile Charger for effectively detecting Replicated nodes and fake connections. We also perform a comprehensive performance analysis of our approach, demonstrating its efficiency in detecting and mitigating false nodes.

关键词： Wireless communication Wireless sensor networks Filters Protocols Network topology Wireless power transfer Probabilistic logic Performance analysis Communication system security Testing

来源：评论

学校读者我要写书评

暂无评论

A Multilayered Trusted and Secure Surveillance with Frame Encoding, ML, and Hashgraph

A Multilayered Trusted and Secure Surveillance with Frame En...

引用

International Conference on Wireless Networks and Mobile Communications (WINCOM)

作者： Ayush Verma Tanuj Chandela Geetanjali Rathee Abhinav Tomar Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9798350377866

ISBN: (纸本)9798350377873

In today's interconnected society, ensuring the safety and security of the public is crucial for protecting individuals from threats posed by criminals. Equally important is safeguarding individuals' privacy, which requires the development of a robust mechanism capable of withstanding attacks while remaining efficient. Surveillance cameras, such as Closed-Circuit Television (CCTV), have become essential tools in this endeavour. These cameras capture extensive visual data, often processed and stored on remote, centralized cloud servers. However, these methods have several shortcomings and are vulnerable to numerous security and privacy breaches. Various solutions have been proposed to address these challenges, each focusing solely on specific aspects of the system. However, none of them have comprehensively addressed the complete mechanism and discussed its resilience against various cyber threats. This paper proposes a secure and trusted decentralized surveillance mechanism utilizing hashgraph for faster, scalable, and secure consensus. The framework aims to defend against attacks such as DDoS and Sybil Attacks and ensures tamperproof logging of all events securely. For rapid identification, we employ I-frame generation from camera footage and a two-stage detection process: one at the camera end using the MobileNetV3-small model to forward necessary keyframes, and another on a private cloud-based analyzer. To safeguard individuals' privacy and ensure secure I-frame transmission while preventing attacks such as Known-plaintext and Replay attacks, we implement an XORing mechanism alongside AES (Advanced Encryption Standard) for I-frames.

关键词： Visualization TV Surveillance Wireless networks Scalability Cameras Security

来源：评论

学校读者我要写书评

暂无评论

De-Fence: LoRa based Hop-to-Hop Communication 2022

De-Fence: LoRa based Hop-to-Hop Communication

引用

14th International Conference on Contemporary Computing, IC3 2022

作者： Chaudhary, Anav Talwar, Maanas Goel, Avil Singal, Gaurav Kushwaha, Riti Department of Computer Science Engineering Netaji Subhas University of Technology Delhi India Department of Computer Science Engineering Bennett University Greater Noida India

ISBN: (纸本)9781450396752

The need for a low-power reliable form of communication is ever-present in a multitude of fields. Our paper aims to develop and explore a security-oriented application of LoRa-based hop-to-hop communication, which provides low-power, large-scale, and long-range solutions to our current safety needs. It utilizes all the components of an IoT-based implementation, in to develop a network, which consists of different types of nodes. It takes input from the external environment through sensors, transports it via several intermediate nodes, using an effective routing algorithm, and provides output through the means of an actuator. The system achieved henceforth is highly scalable, reliable, portable, cheap, and easy to maintain, and provides a fresh outlook on the contemporary need of modernizing the security infrastructure using a growing non-cellular form of communication, LoRa technology. © 2022 ACM.

关键词： Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Levy Flight Based Fire Hawk Optimizer

Levy Flight Based Fire Hawk Optimizer

引用

IEEE Region 10 Symposium

作者： Daksh Baweja Archit Jain Aditya Bhandari Vijay Kumar Bohat Department of Computer Science and Engineering Netaji Subhas University of Technology New Delhi India

ISBN: (数字)9798350364866

ISBN: (纸本)9798350364873

This paper introduces the Levy Flight based Fire Hawk Optimizer (LFHO), an enhanced variant of the Fire Hawk Optimizer (FHO). The idea for LFHO emerged from observing the limitations in the original FHO, notably its re-stricted exploration capability and its tendency to get trapped in local optima, leading to sub-optimal solutions. Our motivation was to overcome these limitations and enhance the algorithm's performance in multifaceted problems. LFHO incorporates a random walk mechanism to inject stochasticity into the search process, thus broadening the exploration scope and mitigating premature convergence issues. Additionally, the introduction of dual global best solutions facilitates a more comprehensive exploration of the solution space, while a dynamic re-initialization mechanism for global best solutions ensures adaptability to evolving search landscapes. Furthermore, a refined nearest function enhances navigation towards promising solutions with greater accuracy and efficiency. The LFHO algorithm's performance is evaluated on CEC(Congress on Evolutionary Computation) 2014 benchmark functions, demonstrating significant improvements over the original FHO in addressing complex optimization tasks.

关键词： Accuracy Navigation Heuristic algorithms Evolutionary computation Benchmark testing Performance analysis Optimization Standards IEEE Regions Convergence

来源：评论

学校读者我要写书评

暂无评论

A survey of tools for social network analysis

引用

International Journal of Web engineering and technology 2021年第3期16卷 189-216页

作者： Rani, Poonam Shokeen, Jyoti Department of Computer Engineering Netaji Subhas University of Technology Delhi India Department of CSE University Institute of Engineering and Technology Maharshi Dayanand University Haryana Rohtak India

Social networking sites contain large amounts of data about users and their relationship with each other. This data is huge, noisy and unstructured, due to which it is necessary to mine the data to extract useful information. To interpret various network features and analyse the results visually or numerically, there are many tools for social network analysis and visualisation. The selection of a suitable tool to perform a specific work is an arduous task. This paper discusses various tools used in the analysis of social networks. It also gives a brief overview of few popular languages for social network analysis. We give a comprehensive comparison of social network analysis tools based on different parameters. We also perform experiments on these tools to evaluate their computational speed and scalability. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Consumer Electronics Data Auditing Scheme Toward Cloud-Edge Distributed and Resilient Machine Learning

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 2244-2256页

作者： Li, Yi Shen, Jian Vijayakumar, Pandi Lai, Chin-Feng Sivaraman, Audithan Sharma, Pradip Kumar Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China University College of Engineering Tindivanam Anna University Chennai Department of Computer Science and Engineering Tindivanam604001 India National Cheng Kung University Department of Engineering Science Tainan701 Taiwan Netaji Subhas University of Technology Department of Information Technology New Delhi110078 India University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

Distributed and resilient machine learning (DRML) endues next-generation consumer electronics with AI function. Intuitively, AI provides innovative, humanized, convenient applications based on the data extended by next-generation consumer electronics. Cloud-edge computing is an ideal undertaken architecture of DRML due to its distributed property. However, as one of the core elements driving AI applications, data could be lost or corrupted owing to damaged electronics, unstable communication, and even cloud providers' malicious behavior. It is essential to ensure the data integrity of next-generation electronics before AI applications. To this end, we proposed a privacy-protection distributed data auditing scheme for cloud-edge DRML. An efficient data integrity verification method that only uses algebraic operation is constructed. Then, Function Secret Share (FSS) extends the data integrity verification method to protect consumer privacy. Besides, a consensus for data auditing results is designed among the edge servers. Finally, we present an abundance of theoretical analyses and experimental findings to substantiate and validate the efficiency and effectiveness of our proposed scheme. © 1975-2011 IEEE.

关键词： Edge computing

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：