检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Huang, Qihan Zhang, Jing Zeng, Zuanyang He, Ding Ye, Xiucai Chen, Yi School of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science University of Tsukuba Tsukuba Japan Department of Computer and Information Security Management Fujian Police College Fuzhou China

Mobile Crowd-Sensing (MCS) is a distributed data fusion system that leverages multiple data sources to improve the performance. By incorporating data from numerous individuals, MCS can provide more accurate, comprehensive, and valuable information than any single source could offer alone. As an essential application in MCS, intelligent transportation system deploys a large number of Transport Mode Inference (TMI) models. However, tens of thousands of trajectories are utilized for TMI model training, which will bring the risk of privacy disclosure. Existing solutions cannot address the privacy concerns of trajectories in MCS. In order to achieve the secure distributed architecture for eliminating such concerns in collaboration, a Federated Learning-based Transport Mode Inference Model with Privacy-Preserving data Fusion (PPDF-FedTMI) is proposed in this paper. Firstly, federated learning is utilized in the TMI model to solve the isolated data islands problem of MCS systems. Subsequently, a fuzzy fusion algorithm based on the fuzzy clustering of label information is proposed to train models stably and effectively under non-IID distributed datasets. Furthermore, a privacy-preserving joint training method applying local differential privacy is designed to enhance the gradient privacy, which can prevent attackers from deriving the original through the gradient. Finally, the experimental results demonstrate that PPDF-FedTMI can provide higher accuracy of mode inference and effective privacy-preserving compared to other models. © 2023, The Authors. All rights reserved.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

Predicting the Impacts of the Environment on the Probability and Severity of Electrical Injuries by AIML

Predicting the Impacts of the Environment on the Probability...

引用

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Deshmukh, Araddhana Arvind Kumar, K Parish Venkata Kumar, B.Anjanee Patro, Pramoda Singh, Pavitar Parkash Ashokkumar, N. Marathwada Mitra Mandal College of Engineering Department of Artificial Intelligence and Data Science Pune India Department of Computer Applications Vijayawada India Dadi Institute of Engineering and Technology Electronics and Communication Engineering Visakhapatnam India Koneru Lakshmaiah Education Foundation Department of Mathematics Hyderabad India Lovely Professional University Department of Management Phagwara India Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Department of Ece Tirupati India

ISBN: (纸本)9798350317060

The acceleration of global warming and environmental degradation has been attributed to industrial growth and fossil fuel utilization. Consequently, this phenomenon has resulted in a rise in the frequency and intensity of natural disasters. Due to their predominantly outdoor installation, generators are subject to significant impacts. The occurrence of natural disasters has led to an increase in accidents associated with electrical equipment. This paper analyses statistical data on electrical fires, electric shock accidents, and electricity-related accidents caused by climate change in domestic settings to determine the associated risk *** this study, we propose a risk assessment model for electrical fires, explicitly focusing on every month. Our approach involves analysing data on electrical hazards in different regional areas, particularly metropolitan cities, considering climatic conditions such as temperature and humidity. Additionally, we aim to evaluate the accident risk rating associated with natural disasters, specifically those related to low and high-voltage equipment. In this study, a risk analysis model has been developed to assess electrical hazards in different regions and equipment types. The model presented herein serves as a foundational predictive tool. Hence, offering electrical security amenities in the forthcoming period is feasible by giving a risk estimation map delineating potential dangers specific to each geographical area and wiring category via web platforms or mobile applications utilizing the investigation data provided. Additionally, it is imperative to enhance the resilience and dependability of electrical components as a proactive measure against electrocute ions resulting from climate change-induced emergencies. © 2023 IEEE.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

HMLM: An Intelligent Artificial Intelligence Assisted Strategy to Identify UPI Frauds Based on Hybrid Markov Learning Methodology

HMLM: An Intelligent Artificial Intelligence Assisted Strate...

引用

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

作者： Bharath, S. Prasad, G. Lakshmi Vara Sujatha, V. Hemajothi, S. Mani, D. Sharada Merlin, N.R. Gladiss Rajalakshmi Institute of Technology Department of Ece Chennai India Qis College of Engineering and Technology Department of Aimlds Vengamukkapalem AndhraPradesh Ongole India S.A. Engineering College Department of Master of Computer Applications Chennai India Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Department of Ece Chennai India Qis College of Engineering and Technology Department of Aimlds Vengamukkapalem Andhra Pradesh Ongole India R.M.K. Engineering College Department of Artificial Intelligence and Data Science Chennai India

ISBN: (纸本)9798331543617

The proliferation of Unified Payments Interface (UPI) transactions in the digital age has considerably improved financial inclusion, but it has also increased the vulnerability to fraud. This manuscript introduces a novel approach that employs Artificial Intelligence (AI) to detect UPI frauds. The approach is based on deep learning and is referred to as the Hybrid Markov Learning Methodology (HMLM). To evaluate the suggested system, it is cross-checked against the traditional Hidden Markov Model (HMM). Our approach combines the benefits of modern artificial intelligence methods with Markov models to improve the accuracy of fraud detection. Combining deep learning algorithms with probabilistic state transitions allows the hybrid Markov Learning Methodology to dynamically analyze transaction patterns and behaviors. By modeling both historical and real-time transaction data, our approach improves the identification of unusual activity and fraud patterns that conventional algorithms may ignore. From experimental data, we prove our approach minimizes false positives and improves the rate for fraud detection against the current options available. Our work advances the current state of fraud detection systems using more flexible and robust fraud detection systems, thus enabling security and confidence in UPI transactions. © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Accessible Authentication Using Keyword Search through Homomorphic Encryption 1

Accessible Authentication Using Keyword Search through Homom...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Vekariya, Vipul Manjunath, R. Gill, Jasmeen Gopianand, M. Kumar, Avneesh Jha, Amaresh Parul University Department of CSE PIET Gujarat Vadodara India Department of Data Science & Mathamatics Bangalore India RIMT University Department of CSE Godindgarh Mandi India PSNA College of Engineering and Technology Department of Computer Applications Dindigul India Galgotias University Department of Computer Application Uttar Pradesh Greater Noida India School of Modern Media UPES Dehradun India

ISBN: (纸本)9781665456876

data storage presents substantial issues due to concerns about data security and privacy. In this study, we provide a search-based, interoperable, verified public key cryptography system. The searchability is significantly improved by our recommended method, which allows the cloud servers to create invert crypto indexes while needing a query trap and leveraging asymmetric cryptography developed by van Vries, Miller, Showing different, and Vaikuntanathan. Contrarily, the recommended method offers a brand-new permitted dataset built on the inversion decryption scheme and shows how it may be used to evaluate the thoroughness and correctness of serps. Additionally, using the provided method, many users may do encrypted searches on cryptography. Finally, it is shown that the offered technique is secure utilizing the approximate-GCD problem. The experiment's results showed that the proposed technique had less computational complexity than the methods currently in use. © 2022 IEEE.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Lateralizing Seizure Onset Zone Through Interictal Sleep Scalp EEG High-Frequency Oscillations

Lateralizing Seizure Onset Zone Through Interictal Sleep Sca...

引用

International Joint Conference on computer science and Software Engineering (JCSSE)

作者： Dhruva P Achar Karunakar A Kotegar Kurupath Radhakrishnan Dept. of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Department of Neurosciences AVITIS Institute of Medical Sciences Nemmara Palakkad Kerala India

ISBN: (数字)9798350381764

ISBN: (纸本)9798350381771

Epilepsy, a neurological disorder impacting an estimated 50 million people globally, sees about 30% of patients developing drug-resistant epilepsy (DRE). For these patients, surgery emerges as a more promising option for achieving seizure freedom. The precise delineation of the Epileptogenic Zone (EZ) is crucial for considering a patient as a surgical candidate, with the Seizure Onset Zone (SOZ) considered the most reliable estimate of the EZ. In this retrospective study, we analysed interictal sleep electroencephalography (EEG) data from 5 patients to evaluate the rate of High-Frequency Oscillations (HFOs) in the 80-250 Hz range. Our objective was to explore whether regions exhibiting a higher incidence of HFO rates correlated with those diagnosed as the SOZ based on patient reports. Additionally, we computed the asymmetry index to examine whether the heightened HFO rate lateralizes to the hemisphere where the seizure occurs. Our results revealed a precise correlation between elevated HFO rates in a region and the specified SOZ as per the report in 4 out of 5 patients. Furthermore, the asymmetry index consistently lateralized to the same hemisphere causing seizure as specified in the report a cross all 5 patients. This implies that the analysis of HFOs can provide valuable assistance to clinicians in accurately identifying the hemisphere responsible for seizures.

关键词： Correlation Sleep Scalp Epilepsy Surgery Hafnium oxide Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks (GANs) in the Wild: applications, Challenges, and Future Prospects

Generative Adversarial Networks (GANs) in the Wild: Applicat...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Rakesh Kumar Pooja Chaudhary Shilpi Gupta Manoj Singhal Department of Computer Engineering & Applications GLA University Mathura UP India Department of CSE (Data Science) Raj Kumar Goel Institute of Technology Ghaziabad UP India Department of Computer Science & Engineering Meerut Institute of Technology Meerut UP India Department of Information Technology GL Bajaj Institute of Technology & Management Greater Noida UP India

Generative adverse Networks (GANs) have become increasingly famous for a variety of tasks in picture and audio processing, especially unsupervised getting to know. GANs encompass components, a “generator” and a “discriminator,” that are skilled adversarial. The generator is tasked with producing a pattern of statistics, and the discriminator is tasked with figuring out whether the information is “actual” or “fake.” The generator “learns” through trial and mistakes as it attempts to create samples that appear practical to the discriminator. Through the antagonistic schooling manner, the generator can create more accurate “fake” records while the discriminator can emerge as better at distinguishing between “actual” and “faux” records. GANs have been applied to various duties, which include picture era, textual content to photosynthesis, photo-to-image translation, and automatic music composition. Recent tries have been made to apply GANs to extra complicated obligations in the wild, including self-reliant use and drug discovery. GANs have inspired an ever-developing quantity of industries because of their potential to generate sensible facts with minimal human input.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Federated Learning in the Era of Privacy Preservation: A Comprehensive Review and Future Directions

Federated Learning in the Era of Privacy Preservation: A Com...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Kushagra Kulshreshtha Bhawna Goel Hoshiyar Singh Kanyal Vikas Singhal Department of Computer Engineering & Applications GLA University Mathura UP India Department of CSE (Data Science) Raj Kumar Goel Institute of Technology Ghaziabad UP India Department of Computer Science & Engineering ABES Institute of Technology Ghaziabad UP India Department of Information Technology Greater Noida Institute of Technology Greater Noida UP India

Federated studying is a disbursed system learning method that lets a set of dispensed users, or clients, collaboratively learn a shared predictive model without sharing any statistics. Through taking part in the model education method, every purchaser contributes to the development of a worldwide, predictive model without sacrificing its very own information privacy. This privateness renovation may be achieved through various techniques, which include differential privateness, cozy multi-celebration computation, and information obfuscation. In this way, model schooling isn't always a task exclusively for centralized facts creditors, but as an alternative, a large-scale collaboration amongst multiple entities with disparate hobbies and facts silos. In the technology of privacy protection, federated studying represents a powerful tool that enables the construction of predictive fashions that might be knowledgeable by means of various information resources at the same time as retaining the integrity and privateness of the individual statistics units.

关键词：

来源：评论

学校读者我要写书评

暂无评论

From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第07期PP卷 PP页

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Zhou, Huiyu Felsberg, Michael Tao, Dacheng Li, Xuelong University of York Department of Computer Science United Kingdom University of Leicester School of Computing and Mathematical Sciences United Kingdom Linkoping University Computer Vision Laboratory Sweden Nanyang Technological University College of Computing & Data Science Singapore China Northwestern Polytechnical University Key Laboratory of Intelligent Interaction and Applications Ministry of Industry and Information Technology Xi'an China

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion. © 1979-2012 IEEE.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

Text Classification on Tweets predicting the Mental Illness using Natural Language Processing and Machine Learning Classifiers

Text Classification on Tweets predicting the Mental Illness ...

引用

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： A. Vijayalakshmi T. N. Aruna Divya. N V J Chakravarthy M. Seenivasan Department of Data Science Dwaraka Doss Goverdhan Doss Vaishnav College Chennai India Department of Computer Applications Dr. MGR Educational and Research Institute Chennai Maduravoyal India Department of Mathematics CDOE Annamalai University Tamil Nadu India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

In the 21st Century, people’s are investing additional occasions on social media reflecting their feelings by means of the languages(text). The modern inquire about is looking at whether people's conventional dialect gives a great flag for anticipating the event of mental ailment. Dialect tests (Tweets) were assembled from the social media site, with tweets utilized to portray different sorts of mental condition. As hypothesized, tweets taken from the client can be utilized to separate a assortment of mental sicknesses (ADHD, uneasiness, bipolar clutter, and sadness). At last, models prepared on tweets particular in expressions showing disorder-specific side effects, while models instructed to foresee mental states particular in words, showing the sorts of choices prescient of mental ailment. This paper points to appear an NLP spaCy and the machine learning classifiers to anticipate mental sickness on tweets by categorizing the content and gets the exactness of 99.25% in NLP - spaCy and 96.71% in ML Irregular Timberland & XGBoost Demonstrate.

关键词： Social networking (online) Text categorization Machine learning Natural language processing Information and communication technology Clutter

来源：评论

学校读者我要写书评

暂无评论

Intelligent Energy Management for Electric Vehicles: Fuzzy Logic and Neural Network Integration

Intelligent Energy Management for Electric Vehicles: Fuzzy L...

引用

International Conference on Advanced Computing and Communication Systems (ICACCS)

作者： T Thirumalaikumari D Lita Princy S Uma R Sadaieswaran P Malathi N Legapriyadharshini Department of Computer Science Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of Master of Computer Applications Meenakshi College of Engineering Chennai Tamil Nadu India Department of Computer Science Engineering Dhanalakshmi Srinivasan College of Engineering and Technology Mahabalipuram Tamil Nadu India Department of Computer Applications Tagore College of arts and science Chromepet Chennai India Department of Data Analytics Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India Department of Computer Application Saveetha College of Liberal Arts and Sciences SIMATS Deemed to be University Chennai Tamil Nadu India

ISBN: (数字)9798350384369

ISBN: (纸本)9798350384376

This study suggests a novel methodology for intelligent energy management in electric vehicles (EVs) through the integration of neural networks and fuzzy logic. Achieving enhanced energy efficiency for electric vehicles is a critical concern that is tackled in this research through the integration of neural networks' decision-making and pattern recognition functionalities with fuzzy logic's adaptability and learning capabilities. The proposed method seeks to optimize energy consumption, enhance overall performance, and extend driving range. The integrated system is subjected to rigorous testing using a meticulously planned experimental setup and simulation environment, which enables it to surpass the performance of more conventional approaches to energy management. The results emphasize the potential of the novel methodology to improve environmentally sustainable transportation options and propel the development of electric vehicle technology. This study not only offers valuable insights into efficient energy management but also establishes the groundwork for subsequent developments in the domain.

关键词： Fuzzy logic Roads Neural networks Transportation Propulsion Electric vehicles Energy efficiency Pollution measurement Energy management systems Testing

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：