检索结果-内蒙古大学图书馆

3rd International Conference on Disruptive Technologies, ICDT 2025

作者： Chawla, Sachin Gupta, Deepa Pippal, Sanjeev Kumar Amity University Amity School of Engineering and Technology UP Greater Noida India Amity University Amity Institute of Information Technology UP Noida India G.L Bajaj Institute of Technology and Management Dept. Computer Science-Artificial Intelligence UP Greater Noida India

ISBN: (纸本)9798331519582

This review provides a broad overview of CNN architectures, focusing on the crucial building blocks and layered structures that form complete networks. It traces the evolution of CNNs, summarizing key publications and highlighting the diverse array of architectures that have emerged in recent years. While simplifying some technical details, the review maintains conceptual rigor to ensure a thorough understanding of CNN principles and development. This review serves as a valuable resource for those seeking to navigate the complexities of CNNs, offering insights into their operational principles, architectural innovations, and potential applications beyond the realm of computer Vision. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Improved Air Pollution Prediction: A Combined LSTM-SVR Approach

Federated Learning for Improved Air Pollution Prediction: A ...

引用

India Council International Subsections Conference (INDISCON), IEEE

作者： Satheesh Abimannan John A Saurabh Shukla Dhivyadharsini Satheesh Department of Computer Science and Engineering Amity University Maharashtra Mumbai India Department of Computer Science and Engineering Galgotias University Greater Noida UP India School of Computer Science and Engineering Vellore Institute of Technology Vellore India

In this research paper, we introduce a unique approach to predict air pollutant concentrations. The method involves combining two pre-existing models, LSTM and SVR, by utilizing federated learning. Our proposed model is evaluated based on air quality data gathered by the Taiwan Environmental Protection Agency (EPA). By using federated learning, we can create a global model that taps into the collective knowledge of all 70 data centers while safeguarding data privacy and security. This novel method has significant implications for addressing joint air pollution mitigation and environmental protection. Additionally, the research paper presents performance comparisons of various models across three locations in Taiwan. We demonstrate the efficiency of our FL-ALSTM and FL-SVR models in predicting air pollutant concentrations. Our findings show that the FL-ALSTM model outperforms other models, improving predictions of air pollution levels by more than 95%. Overall, our study underscores the potential of federated learning in advancing air pollution prediction and environmental sustain ability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cervical Cancer Classification using Multi-Scale, Multiple-Attention-based Deep Learning Approach

Cervical Cancer Classification using Multi-Scale, Multiple-A...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： Ritesh Maurya Suvidha Deshwal Lucky Rajput T Gopalakrishnan Raguru Jaya Krishna Amity Centre for Artificial Intelligence Amity University Noida India Amity School of Engineering & Technology Amity University Noida India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

Cervical cancer is a widely acknowledged health concern, especially in the areas lacking appropriate medical treatment. The early diagnosis and the explicit categorization of cervical lesions may bring about effective therapy and restrict the expansion of the disease. The novel approach proposed in this work employs a multi-scale, multi-attention based MobileNetV2 network for the categorisation of cervical cancer. The proposed model improves the efficiency of MobileNetV2, a lightweight convolutional neural network (CNN), by incorporating multiscale and multi-attention techniques to improve feature extraction capabilities and categorisation accuracy. By incorporating multiscale component, the suggested model can effectively detect features at different resolutions. Moreover, the integration of multi-attention mechanism allows the model to dynamically highlight salient features over multiple scales. The proposed method has been evaluated using single cell conventional Pap Smear images, exhibiting improved performance compared to existing approaches in terms of accuracy. The results suggest that the Multi-Scale, Multiple-Attention MobileNetV2-based network proves to be a useful tool for cervical cancer categorisation, offering potential interests for clinical diagnosis with an accuracy of 92.4

关键词： Deep learning Accuracy Image resolution Transfer learning Medical treatment Feature extraction Convolutional neural networks Lesions Cervical cancer Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

A protection and assurance version for E-authorities Web Services based totally on Cloudlet computing

A protection and assurance version for E-authorities Web Ser...

引用

2021 International Conference on Technological Advancements and Innovations, ICTAI 2021

作者： Singh, Devang Pratap Rajpoot, Subhadra Singh, Puneet Computer Science and Engineering Amity School of Engineering and Technology Greater Noida India Amity School of Engineering and Technology Department of Applied Sciences Greater Noida India Faculty of Communications Engineering Military College of Telecommunication Engineering Madhya Pradesh Mhow India

ISBN: (纸本)9781665420877

In the present scenario, Web Administration and cloud computing are the spine architecture of any e-authorities application due to its interoperable and robust nature. Web benefits that are kept up in Cloud computing bring in easy consideration in examination and industry as far as getting the conveyed Web administrations. Consequently, gaining more trust between the imparted Web administrations which has been continuously getting more accessible for Web administrations shoppers, executives, and Web specialist organizations particularly the e-government administrations. Likewise, the proposed architecture is handling the issues that emerge when Web administration purchasers are speaking with most of the e-legislative Web administrations are furnished through a depended on Cloud-based system that is not bound via any administrative authority. Furthermore, Cloudlet computing is used to quantify the supplier of Web benefits' reliability and compliance to the distributed strategy using input from the Web administration customer. © 2021 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

A Framework for Blockchain-Enabled Smart Contract Management System of Arms and Ammunition for Defence Industry

A Framework for Blockchain-Enabled Smart Contract Management...

引用

International Conference on Reliability, Infocom Technologies and Optimization (ICRITO) (Trends and Future Directions)

作者： Deepak Dhillon Ajay Kumar Vashist Diksha V Mariaprecilla Deepti Mehrotra Amity Institute of Defence Technology Amity University Noida India Department of Computer Science Banasthali Vidyapith Jaipur Rajasthan India Combat Vehicle Research and Development Establishment DRDO Chennai India Amity School of Engineering and Technology Amity University Noida India

ISBN: (数字)9798350350357

ISBN: (纸本)9798350350364

This paper presents an innovative solution, the Blockchain-Enabled Smart Contract- Based Management System for Arms & Ammunition, revolutionizing logistics within the Defence industry. Addressing prevalent challenges of transparency limitations and manual inefficiencies in existing systems, this framework represents a transformative approach. Leveraging blockchain technology and smart contracts, our framework offers real-time visibility, automated processes, and stringent compliance measures. The architectural design incorporates distinct layers including Blockchain Network, Smart Contracts, Data Management, User Interfaces, Integration, Security, and Governance. Smart contracts play a pivotal role by ensuring data accuracy and enabling immediate access to critical information. Scalability concerns are mitigated through optimized consensus algorithms and sharding, ensuring smooth expansion. An indepth analysis of blockchain platforms underscores the significance of platform selection, pivotal for security and operational efficiency. Real-world use cases illustrate the system's adaptability, spanning ammunition distribution to proactive maintenance scheduling, showcasing its resilience and versatility. In summary, our proposed system marks a monumental advancement in Defence industry logistics, offering unparalleled transparency, automation, and security. It sets a new standard for military operations by establishing a robust and responsive infrastructure. Ongoing developmental initiatives and global collaboration underscore a future-ready, secure, and adaptable Defence landscape.

关键词： Sharding Defense industry Scalability Smart contracts User interfaces Blockchains Security

来源：评论

学校读者我要写书评

暂无评论

Classification of Common Insects Using Transfer Learning and ResNet50

Classification of Common Insects Using Transfer Learning and...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Sakshi Chetan Sharma Jaydeep Kishore Vivek Bhardwaj Amity Institute of Information Technology Amity University Noida India upGrad Education Private Limited Bangalore India School of Computer Science and Engineering Manipal University Jaipur Jaipur India

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

The escalation of the global temperature and the pressure on the fields is at an all-time high. To feed the rising population, insecticides, and pesticides are likewise at an all-time high. With the growing temperature due to global warming and the increasing employment of pesticides to feed the people, one class of creatures suffers the direct hit: insects. On the other hand, the growing warmth leaves them vulnerable to death due to bad environmental circumstances. On the other hand, the increasing employment of pesticides extirpates innocuous insects with hazardous insects. There is a continual requirement to monitor the growth and condition of such insects to maintain the sustainability of the environmental system. However, accomplishing such a big work manually is not only impossible but fruitless, too, since few insects of various classes provide identical looks. To cope with such challenges related to this work, a transfer learning-based ResNet50 network is presented to automatically detect, categorize, and consequently track the insect populations to take future measures. The model obtains a recognition accuracy of 91.45%.

关键词： Hands Temperature sensors Insects Employment Transfer learning Pesticides Feeds Sustainable development Monitoring Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Fingerprint-Based Multifactor Authentication For Bank Transaction

Fingerprint-Based Multifactor Authentication For Bank Transa...

引用

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Mananjeet Kaur Shreya Kaistha Shubhani Aggarwal Ishan Budhiraja Rajat Chaudhary Abhay Bindle Department of Computer Science Engineering Amity University Punjab India School of Computer Science Engineering and Technology Bennett University Greater Noida Uttar Pradesh India Department of Electronics and Communication Engineering Maharishi Markandeshwar University Mullana Ambala Haryana India

ISBN: (数字)9798350391725

ISBN: (纸本)9798350391732

Robberies of ATMs have been on the rise in the last few years and are becoming a major concern for Banks and their customers. Currently, we operate ATMs using a PIN that can become a victim of theft, guessed, and can be hacked while the transaction is going on. This raises a question on the security of ATM transactions and requires new techniques and schemes that can offer a second level of protection. Considering these security concerns, we proposed a security check on the existing ATM systems. We authors have created two applications that present the new technique. Our banking application, called Fingerpay, works like traditional banking applications with an added feature where the user can enable the MFA (Multi-factor Authentication) through MPIN verification. In this case, a request for fingerprint authentication is prompted as a notification on the user’s registered mobile number. Upon successful authentication, the transaction is authorized and completed securely. The key contribution of this research lies in the formation of a secure and user-friendly MFA system for ATM transactions. By integrating fingerprint authentication with existing banking applications, users are prompted to verify their identity through a registered fingerprint scan during ATM transactions. This additional layer of authentication increases security by significantly reducing the risk of unauthorized access and fraudulent transactions. In addition, biometric authentication outperforms traditional methods, including increased accuracy, reliability, and resistance to identity theft or impersonation. In the end, this proposal will go a long way in resolving the problem of ATM transactions. Further, this report contains the introduction, design and implementation part of the proposed model.

关键词： Multi-factor authentication Authentication Banking Fingerprint recognition Telecommunications Pins Security Reliability Proposals Protection

来源：评论

学校读者我要写书评

暂无评论

Automated Diagnosis of Marigold Leaf Diseases using a Hybrid CNN-SVM Model

Automated Diagnosis of Marigold Leaf Diseases using a Hybrid...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： Deepak Banerjee Vinay Kukreja Vandana Sharma Vishal Jain Shanmugasundaram Hariharan Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Amity Institute of Information Technology Amity University Department of Computer Science and Engineering Sharda School of Engineering and Technology Sharda University Greater Noida UP India

For healthy yields of crops and to maintain food security, it is essential to identify and classify plant diseases. In this research, the aimed to create a convolutional neural network-based deep learning algorithm for accurately classifying various marigold leaf diseases. 2000 images of marigold leaves were included in the dataset, with 200 images for each of the ten groups. (nine diseases and one healthy leaf). Six layers of convolution, six maximum-pooling layers, and two fully linked layers with regularisation and ReLU function activation made up the suggested CNN model. The efficiency of the model was optimized through hyperparameter tuning. Using the Keras framework, the model was trained and evaluated on the preprocessed dataset, and its performance was assessed using metrics like precision, recall, F1-score, as well as accuracy. According to the findings, the developed model classified the various classes of marigold leaves with an overall accuracy of 92%, with precision, recall, as well as F1-score metrics varying from 50% to 71.79% depending on the class. The confusion matrix gave a thorough summary of how well the model did at identifying each of the various marigold leaf classes. The created model can be applied to the early discovery of diseases affecting marigold leaves, aiding in both disease containment and yield protection. This research also emphasizes how well deep learning models work at accurately identifying and categorizing various plant diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Cryptographic Encryption Technique for the Security Enhancement of Electronic Transactions

A Novel Cryptographic Encryption Technique for the Security ...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Grace Odette Boussi Himanshu Gupta Syed Akhter Hossain Fila Rudy J. J Amity Institute of Information Technology Amity University Noida India Computer Science and Engineering Department University of Liberal Arts City Bangladesh School of Engineering and Technology Sharda University Greater Noida India

Cybersecurity has been a trending topic for years now, different propositions, studies, and work have been suggested in various forms by other authors all over the world, but the impact of crime is still around us. In the present area, we cannot say that data is safe when it is hidden from an unauthorized person, but it is safe when the intruder cannot understand it, hence encryption is the suitable solution at the moment. Encryption is one of the techniques that we use to protect our data from unauthorized persons. In this technique, we do not stop the unauthorized person from accessing our information, but we made our data appear in an incomprehensive form to the intruder, only the person with the correct key can decrypt the encrypted message. Many encryption techniques are available, and the commonly used and modern ones are RSA, AES, and HAS, each of them is suitable for different scenarios and are all helpful for cyber security. In this paper, we will propose a framework that provides an additional layer of security for any sensitive information in general and those in the banking sector.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Wearable Device for Assistance of Alzheimer’s disease with computer Aided Diagnosis

引用

EAI Endorsed Transactions on Pervasive Health and technology 2024年 10卷

作者： Sarita Choudhury, Tanupriya Mukherjee, Saurabh Dutta, Chiranjit Sharma, Aviral Sar, Ayan Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Manesar Gurgaon122413 India Graphic Era Deemed to be University Uttarakhand Dehradun248002 India Department of Computer Science Banasthali Vidyapith Rajasthan 304022 India SRM Institute of Science and Technology Delhi NCR Campus Uttar Pradesh Ghaziabad201204 India Dehradun248007 India Dehradun248007 India

INTRODUCTION: Alzheimer’s disease (AD), which is also a pervasive form of dementia primarily common among the elderly, causes progressive brain damage, which might lead to memory loss, language impairment, with cognitive decline. This research proposed a solution that leveraged wearable technology's potential for computer-aided diagnosis. This wearable device, which looks like a pendant, integrates a panic button to notify the closed ones during an emergency. OBJECTIVES: The primary objective is to effectively scrutinise and implement the wearable device for computer-aided diagnosis in AD. Specifically, this device aims to provide timely alerts to family members during emergencies and other symptoms. METHODS: The proposed system is developed with the help of a microcontroller and integrates the Android Studio. This device, which resembles a pendant, contains a panic button that connects to a mobile application which receives notifications. RESULTS: The system successfully achieved its objectives by providing timely alerts with accurate cognitive support for AD patients. The wearable device developed along with the mobile application, with the help of a microcontroller and Android Studio, contributed to the overall well-being of patients with AD. CONCLUSION: This research introduced a very innovative and promising solution for improving the lives of individuals with AD through this wearable device and mobile application. By addressing these challenges, the system demonstrated its true potential for enhancing the quality of life for individuals with dementia. © 2024 Author et al., licensed to EAI.

关键词： Neurodegenerative diseases

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：