检索结果-内蒙古大学图书馆

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

A pseudo-labelled ensemble inference for fast and efficient real field photovoltaic system's power prediction

引用

Optik 2023年第1期287卷

作者： Dhingra, Bhavya Tyagi, Shivam Verma, Aryan Tomar, Anuradha Rani, Poonam Department of Electrical Engineering Netaji Subhas University of Technology Dwarka Delhi110078 India Department of Computer Science Netaji Subhas University of Technology Dwarka Delhi110078 India Department of Instrumentation and Control Engineering Netaji Subhas University of TechnologyDwarka Delhi110078 India

Clean energy solutions like solar power plants have been at the forefront of the collaborative global efforts of the world towards the sustainable development of society. This research paper explores the use of machine learning in predicting photovoltaic (PV) power generation. An accurate and reliable prediction of solar power generation is crucial for the efficient integration of clean energy solutions into the existing power grid. The most common approach for PV forecasting is the statistical approach, which captures the local weather, seasonal, and geographical effects on the PV system but has limited accuracy due to limited data. The physical approach uses complex physical models to simulate solar radiation and predict energy output, but it is time-consuming and unsuitable for short-term forecasting. This study proposed a 3-stage machine learning architecture that uses pseudo labelling to increase accuracy and efficiency in predicting power generated by PV modules. The architecture uses a light gradient boosting machine (LGBM) and Cuda random forest (cuRF) together, which improved the model performance and achieved a high accuracy score of 99.98% R2. This study addresses missing data points and improves accuracy using imputation and weighted ensemble techniques with a year's worth of institutional data. The proposed model outperforms other models tested in this study. © 2023

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Similarity-Based Movie Recommendation Using Bag-of-Words Model

Feature Extraction and Similarity-Based Movie Recommendation...

引用

International Conference on Smart Systems and Wireless Communication, SSWC 2024

作者： Raj, Swati Dutta, Jhalak Bandopadhyay, Saikat Prasad, Rajesh Department of Computer Science and Engineering Christ University Bengaluru India Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Artificial Intelligence and Machine Learning Netaji Subhash Engineering College Kolkata India Department of Computer Science and Engineering MIT Art Design and Technology University Pune India

ISBN: (纸本)9789819613472

Recommender systems have become pervasive in guiding users through a lot of choices available in today’s digital landscape. This paper presents a content-based recommender system focused specifically for movie recommendations, offering a viable alternative to collaborative filtering methods. Unlike collaborative filtering, which relies on user ratings and demographic data, the proposed system operates without such prerequisites, making it particularly advantageous in scenarios with limited user engagement. By leveraging content attributes such as title, genre, cast, and crew, the system identifies similarities between movies and recommends those akin to a user’s preferences. Through innovative preprocessing techniques and feature extraction methodologies, the system transforms textual descriptions into numerical vectors, enabling efficient recommendation generation. The proposed model contributes to addressing critical challenges inherent in collaborative filtering, including the cold start problem, data sparsity, and popularity bias. Furthermore, it underscores the broad applicability of recommender systems across various domains and emphasizes the continuous evolution of interface designs and algorithms within the research community. Overall, the proposed content-based recommender system offers a promising solution for delivering personalized movie recommendations while advancing the state of the art in recommendation technology. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bag-of-words Cosine similarity Filtering system Recommender system TF-IDF

来源：评论

学校读者我要写书评

暂无评论

Deep and Machine Learning for monitoring groundwater levels and hydrological changes using GRACE and SENTINEL-1 for the Ganga River basin

Deep and Machine Learning for monitoring groundwater levels ...

引用

2024 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024

作者： Galodha, Abhinav Sai, Kayithi Naga Lall, Brejesh Ahammad, Shaikh Ziauddin Anees, Sanya New Delhi India Indian Institute of Technology Iit Delhi Bachelor of Engineering Department of Mechanical Engineering New Delhi India Indian Institute of Technology Iit Delhi Department of Electrical Engineering New Delhi India Indian Institute of Technology Iit Delhi Department of Biochemical Engineering And Biotechnology New Delhi India Netaji Subhas University of Technology Department of Electronics And Communication Engineering New Delhi India

ISBN: (纸本)9798350389678

Accurate estimating groundwater levels in river basins is paramount for hydro-geological research and sustainable water resource management. This research presents a deep-learning approach for accurate groundwater level estimates in the Ganga River Basin. Our method leverages the transformative potential of Vision Transformers (ViT) and their variants, with an emphasis on the Swin-Transformer variant enhanced with Normalization Attention Modules (NAMs), by utilizing the combined band information of Sentinel-1 synthetic aperture radar (SAR) and GRACE satellite data. We have assembled an extensive dataset and trained with computer vision to tackle the Ganga River basin's particular difficulties. Cutting-edge Vision Transformers showed great promise in groundwater level estimation, with the model based on Swin-Transformer NAM achieving an exceptional Mean Absolute Error (MAE) of 1.2. The basin and beyond will benefit greatly from this study's significant advancement of sustainable groundwater level and utilization practices. © 2024 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

High Voltage Gain Bidirectional DC-DC Converters for Supercapacitor Assisted Electric Vehicles: A Review

CPSS Transactions on Power Electronics and Applications

引用

CPSS Transactions on Power Electronics and Applications 2022年第4期7卷 386-398页

作者： Singh, Ankit Kumar Mishra, Anjanee Kumar Gupta, Krishna Kumar Siwakoti, Yam P. Netaji Subhas University of Technology Department of Electrical Engineering Delhi110078 India India Thapar Institute of Engineering and Technology Department of Electrical and Instrumentation Engineering Patiala147001 India School of Electrical and Data Engineering University of Technology Sydney SydneyNSW2007 Australia

Integration of supercapacitor alongwith battery in electric vehicles (EVs) improves the life cycle of the battery. Additionally, supercapacitor supplies or absorbs a large amount of instantaneous power during sudden demand such as acceleration or regenerative braking operation, hence also improve the dynamics of the internal power system. However, a major challenge with supercapacitor is that its terminal voltage is low and varies in a wide range during charging and discharging operation. Thus, a high voltage conversion ratio based bidirectional DC-DC converters are required to connect the lower supercapacitor voltage to higher DC-link voltage. The steep voltage conversion ratio with continuous gain based bidirectional DC-DC converters are an integral part of such applications. Various high gain converters exist in the literature such as isolated, non-isolated, cascaded, switched, flying capacitor, and coupled inductor based DC-DC converters, however all these converters have some limitations in context to high gain/high power applications. Therefore, to understand the development of next-generation high voltage gain bidirectional DC-DC converter, this paper focus to comprehensively review and classify various bidirectional step-up DC-DC converters based on their characteristics and voltage-boosting techniques. Further, practical suitability of the reviewed converters and future research directions in switched capacitor converters in context to EVs are also discussed in detail. © 2017 CPSS.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Reinforcement Learning Based Approach for Vehicle Routing Problem 1

引用

2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022

作者： Singh, Jagdeep Dhurandher, Sanjay Kumar Woungang, Isaac Ngatched, Telex Magloire N. Department of Computer Science and Engineering Sant Longowal Institute of Engineering and Technology Longowal India Department of Information Technology Netaji Subhas University of Technology New Delhi India Department of Computer Science Toronto Metropolitan University Toronto Canada Faculty of Engineering and Applied Science Grenfell Campus Memorial University St. John’s Canada

ISBN: (数字)9783031252716

ISBN: (纸本)9783031252709

Multi-Vehicle routing to service consumers in dynamic and unpredictable surroundings such as congested urban areas is a difficult operation that needs robust and flexible planning. Value iteration networks hold promise for planning vehicle routing problems. Conventional approaches aren’t usually constructed for real-life settings, and they are too slow to be useful in real time. In comparison, the Vehicle Routing Problem with Value Iteration Network (VRP-VIN) offers a neural network model based on graphs that can execute multi-agent routing in a highly dispersed but connected graph with constantly fluctuating traffic conditions using learned value iteration. Furthermore, the model’s communication module allows vehicles to work better in a cooperative manner online and can easily adapt to changes. A virtual environment is constructed to simulate real-world mapping by self-driving vehicles with uncertain traffic circumstances and minimal edge coverage. This method beats standard solutions based on overall cost and run time. Experiments show that the model achieves a total cost difference of 3% when compared with a state-of-art solver having global information. Also, after being trained with only 2 agents on networks with 25 nodes, can easily generalize to a scenario having additional agents (or nodes). © 2023, ICST institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Temperature and strain rate dependent tensile behavior of polycrystalline nanocopper under dynamic loading

引用

Materials Today: Proceedings 2022年 62卷 44-48页

作者： Kumar, Rajat Panwar, Vinay Gupta, Mahesh Kumar Mechanical Engineering Department Netaji Subhas University of Technology New Delhi Dwarka110078 India Department of Mechanical Engineering SRM Institute of Science and Technology Delhi-NCR Campus Modinagar GhaziabadUP201204 India

In this work, thermomechanical response of polycrystalline nanocopper has been studied using molecular dynamic simulation in equilibrium conditions. The behavioral change of polycrystalline nanocopper has been studied at different strain rates i.e., 5 × 108 s−1, 1 × 109 s−1, 5 × 109 s−1, 1 × 1010 s−1 and 5 × 1010 s−1. The response of copper with increasing discrete temperatures from 100 K to 500 K, at steps of 100 K each, has also been analyzed. Embedded Atom Method (EAM) potential is used which governs the interaction amongst atoms and helps in finding out the positions of atoms using Newton's second law of motion. Results have shown the dependency of Young's modulus, yield strength, ultimate strength on strain rate and temperature. It has been observed that when the strain rate is increased, Young's modulus also increases along with the increase in yield strength and ultimate strength. The Young's modulus, yield strength, and ultimate strength show inverse relation with the increase in temperature. The results provide a base for further investigation of polycrystalline nanomaterials with effects of other parameters. The study may also be helpful for the researchers to predict the mechanical behavior of a polycrystalline nanomaterial under varying strain rate and temperature during its synthesis via bottom-up approach or surface modification. © 2022

关键词： Strain rate

来源：评论

学校读者我要写书评

暂无评论

Framework for Personalized Chronic Pain Management:Harnessing AI and Personality Insights for Effective Care

引用

Journal of Artificial Intelligence and technology 2024年第2期4卷 132-144页

作者： Akshi Kumar Rahul Seewal Dipika Jain Ravleen Kaur Department of Computing Goldsmiths University of LondonLondonUK Chelsea and Westminster Hospital and East Kent Hospital NHS Find Trust UK MyPain■ UK Department of Computer Science&Engineering Delhi Technological UniversityNew DelhiIndia Department of Computer Science&Engineering Netaji Subhas University of TechnologyNew DelhiIndia

This paper introduces a cutting-edge framework for personalized chronic pain management,leveraging the power of artificial intelligence(AI)and personality *** explores the intricate relationship between personality traits and pain perception,expression,and management,identifying key correlations that influence an individual’s experience of *** integrating personality psychology with AI-driven personality assessment,this framework offers a novel approach to tailoring chronic pain management strategies for each patient’s unique personality *** highlights the relevance of well-established personality theories such as the Big Five and the Myers-Briggs Type Indicator(MBTI)in shaping personalized pain management ***,the paper introduces multimodal AI-driven personality assessment,emphasizing the ethical considerations and data collection processes necessary for its *** illustrative case studies,the paper exemplifies how this framework can lead to more effective and patient-centered pain relief,ultimately enhancing overall *** conclusion,the paper positions the need of an“AI-Powered Holistic Pain Management Initiative”which has the potential to transform chronic pain management by providing personalized,data-driven solutions and create a multifaceted research impact influencing clinical practice,patient outcomes,healthcare policy,and the broader scientific community’s understanding of personalized medicine and AI-driven interventions.

关键词： artificial intelligence health informatics pain personality traits

来源：评论

学校读者我要写书评

暂无评论

Investigation on aluminum based surface composite through FSP using metal (Fe-Sn-Mn) and ceramic (SiC) reinforcements

引用

Materials Today: Proceedings 2022年 62卷 251-254页

作者： Dwivedi, Pooja Maheshwari, Sachin Noor Siddiquee, Arshad Division of Manufacturing Processes and Automation Engineering Netaji Subhas Institute of Technology New Delhi 110078 India Department of Mechanical Engineering Jamia Millia Islamia New Delhi 110025 India

In the present study, the surface composite was fabricated via friction stir processing on AA5083 using mixture of Fe powder, SiC, Sn and Mn powder. Microstructural characterization with the help of bead geometry and micro-hardness analysis were performed to study the various zones of the processed samples. L4 orthogonal array from the Taguchi method is used for analysis. Improvement in microstructure and hardness is achieved at a rotational speed of 900 rpm, traverse speed of 50 mm/min and 24 mm shoulder diameter. Grain size is varying from one zone to another and enhanced properties are obtained because of grain refinement after friction stir processing. © 2022

关键词： Silicon carbide

来源：评论

学校读者我要写书评

暂无评论

A Novel Computational Model for Hardware-Level Security of Cloud Databases in Public Clouds 6

A Novel Computational Model for Hardware-Level Security of C...

引用

6th International Conference on Information Systems and computer Networks, ISCON 2023

作者： Yadav, Arun Kumar Bharti, Rajendra Kumar Raw, Ram Shringar VMSB-Uttarakhand Technical University Uttarakhand Dehradun India Itm University Department of Csa MP Gwalior India Bipin Tripathi Kumaon Institute of Technology Department of Computer Science and Engineering Uttarakhand Dwarahat India Netaji Subhas University of Technology East Campus Department of Computer Science and Engineering Delhi India

ISBN: (纸本)9798350346961

Today, all cloud-based social media applications are data-intensive, and the large amounts of data they generate are managed on the public cloud, which compromises user data security and privacy. Many government and nongovernment organizations that manage users' sensitive and personal data do not choose to use the public cloud to administer their databases because of the numerous security risks it has. However, these organizations are jeopardizing the performance of the application by handling the user's data on the private cloud. Without jeopardizing user data security and privacy or application performance, a security solution will encourage these organizations to manage their databases on the public cloud. This paper presents an L-PNR computational model for the hardware-level security of cloud databases in a multi-tenant public cloud environment. The L-PNR model's performance has been simulated and evaluated using VMware vCenter Simulator. According to experimental findings, the proposed model outperforms the current models THR-RS, LR-MU, DDPA, and DSRBACA in terms of performance and security. The suggested L-PNR model may be used by cloud service providers (CSPs) to offer data security over the public cloud, where organizations can affordably manage their sensitive data.. © 2023 IEEE.

关键词： Sensitive data

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：