检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Signal Processing and Advance Research in Computing, SPARC 2024

作者： Atre, Anshul Singh, Kamlesh Kumar Chaurasia, Brijesh Kumar Amity University Amity School of Engineering & Technology Department of Computer Science & Engineering UP Lucknow India Amity University Amity School of Engineering & Technology Department of Electronics Communications and Engineering UP Lucknow India Pranveer Singh Institute of Technology Department of Computer Science & Engineering Kanpur India

ISBN: (纸本)9798350385199

Effective network communication is essential in the current digital era, and cloud computing (CC) and the Internet of Things (IoT) are significant aspects of daily life. Accelerating and lowering the latency of data transfers to the cloud for processing, analysis, and storage is the aim of cloud computing. IoT integration and job scheduling are the two most challenging issues in the multi-cloud computing environment because of the diverse and numerous IoT devices. The significant objectives of cloud computing-based IoT optimization are to reduce the total time needed to complete all input operations, determine which resources are required for the Message Queuing Telemetry Transport (MQTT), and other crucial protocols used in this work to display delay and evaluate the performance of different jobs at different IoT nodes and bit counts. Results and analysis show the viability of cloudSim is successfully achieved with the use of delayed quality of communication of jobs for different nodes. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Object Detection in Bad Weather Conditions using Deep Learning Models 14

An Analysis of Object Detection in Bad Weather Conditions us...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Verma, Janvi Verma, Harsh Raheja, Supriya Computer Science Engineering Amity School of Engineering and Technology Amity University Noida India

ISBN: (纸本)9798350344837

Object detection, a task, in the field of computer vision faces obstacles when dealing with weather conditions such as fog, rain, snow, and low light situations. This paper provides an overview of advancements in the realm of object detection under challenging weather conditions. It delves into groundbreaking research that utilizes learning techniques adjustments to frameworks and the significance of datasets. This paper proposed the YOLOv5 model to detect the object in bad weather conditions. The paper presents the comparison between the YOLOv5 model presented in literature and the proposed YOLOv5 model in terms of accuracy, precision, recall and F1-score. The evaluation results prove the better performance of our proposed model. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Interpretation of Sign Language Using Machine Learning 2

Interpretation of Sign Language Using Machine Learning

引用

2nd International Conference Computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Srivastava, Palak Hazela, Bramah Singh, Shikha Asthana, Pallavi Pandey, Deependra Singh, Kamlesh Kumar Singh, Vineet Amity University Amity School of Engineering & Technology Department of Computer Science Engineering Uttar Pradesh India Amity University Amity School of Engineering & Technology Department of Electronics & Communication Engineering Uttar Pradesh India

ISBN: (纸本)9798350364699

Sign language detection using machine learning has emerged as a crucial area of research aimed at bridging communication barriers between individuals with hearing impairments and the broader community. This paper explores the application of machine learning techniques for the automatic recognition and interpretation of sign language gestures. A systematic review of existing methodologies, including traditional machine learning approaches and recent advancements in deep learning architectures, reveals key challenges such as variability in signing styles, regional dialects, and real-time processing requirements. To address these challenges, we propose a novel approach that leverages convolutional neural networks (CNNs) and long short-term memory (LSTM) models, which have demonstrated significant improvements in accuracy and generalization across diverse datasets. Our experimental results show the efficacy of these models on benchmark sign language datasets, achieving high levels of accuracy and robustness in real-world conditions. Furthermore, this study discusses the potential societal impacts of sign language detection systems in education, healthcare, and everyday communication, emphasizing the role of technological innovation in fostering inclusivity. By advancing machine learning methodologies, we contribute to the development of accessible communication solutions for individuals with hearing impairments. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Reliability in Mobile Ad Hoc Networks (MANETs) Through the K-AOMDV Routing Protocol to Mitigate Black Hole Attacks

引用

SN computer science 2024年第2期5卷 263页

作者： Kaushik, Sheetal Tripathi, Khushboo Gupta, Rashmi Mahajan, Prerna Amity School of Engineering and Technology Amity University Haryana Gurugram 122413 India Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Haryana Gurugram 122413 India IITM Janakpuri New Delhi India

A Mobile Ad Hoc Network (MANET) is a self-organize assemblage of mobile nodes without the use of pre-existing infrastructure. They face challenges of security, routing efficiency, and network stability due to dynamic topology and limited resources. The Black Hole Attack on MANETs is a critical concern, affecting communication reliability. This malicious activity involves a node falsely advertising the shortest route to the destination, leading data packets to be routed into a “black hole” where they are dropped and causing severe disruptions. This research focuses on the Ad Hoc On-Demand Multi-Path Distance Vector Routing (AOMDV) protocol, which is preferred for its improved efficiency compared to a single-path routing protocol in MANETs. We observe, investigate, and estimate wireless ad-hoc network route optimization by reducing packet hops between nodes. We suggested a novel strategy in this paper, the K-AOMDV protocol that uses K-means clustering to prevent routing misbehavior. The efficiency of the proposed K-AOMDV (KNN-Ad-hoc on demand multi-path distance vector) routing protocol is calculated using supervised machine learning approach to predict optimal routes with delay and attacks. By employing multiple paths and dynamic route discovery, it ensures robust data delivery even in the presence of malicious nodes. This protocol’s adaptability and multi-path nature effectively minimize the effects of Black Hole Attacks, bolstering the MANETs security. Proposed algorithm has a high accuracy rate of 0.99%, 80% true positives, and 80% recall. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Black hole attack K-AOMDV K-nearest neighbors Machine learning MANET Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics in Sports: Using Machine Learning to Forecast Outcomes and Medal Tally Trends at the 2024 Summer Olympics 4

Predictive Analytics in Sports: Using Machine Learning to Fo...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Moolchandani, Jhankar Chole, Vikrant Sahu, Santosh Kumar, Rahul Shukla, Anshita Kumar, Ashok Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350387490

This paper focuses on using machine learning approaches in predicting the medal projections and analyzing the medal distribution pattern in the 2024 Summer Olympics. Due to the availability of a large number of variables both at the individual athlete level and the country level as well as event specific measures, various statistical models are trained to predict the number of medals and unearthing traits that are associated with success in Olympics. The evaluation of the predictions of the models is done using linear regression and random forest along with support vector classifier, as well as artificial neural network classifiers. Using the research findings, it becomes evident that predictive analytics has the capacity of offering a better understanding of the performance of sport teams and formulation of strategies for future competition events. As is observed from the above findings the random forest model sampled the highest accuracy of 99. 034 percent in the general set out of the four models;thus, it is recommended ideal for complicated set data investigations Based on the results of the experiments, it is clearly observed that the random forest has the highest accuracy of 99. 034. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of IoT and Blockchain Technologies in Enhancing Security and Efficiency in Healthcare Systems 4

Comparative Analysis of IoT and Blockchain Technologies in E...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Kumar, Ashok Shukla, Anshita Thada, Vikas Chole, Vikrant Moolchandani, Jhankar Sahu, Santosh Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350387490

This paper presents an extensive comparison of the IoT and blockchain technologies in the improvement of security, privacy, and interoperability, as well as energy efficiency in healthcare systems. This is because IoT allows for constant tracking and gathering of data from medical devices and this enhances the welfare of the patients as well as the management of the health facilities. However, this has exposed the Internet of Things (loT) technology with multiple risks in data security and privacy since it uses wireless communication and has limited computational power. Such issues can be addressed through the use of blockchain technology because of its distributed and tamper proof ledger. This research work presents a case of how the integration of IoT with blockchain will lead to a middle of the two worlds, where IoT will be useful for handling real time data while blockchain will handle the issue of security. The study concludes that the integration of blockchains with the IoT offers superior results than the individual implementations in several aspects, thus offering a more secure, efficient, and interoperable environment for today's healthcare applications. Possible future work includes improving the integration of these technologies to minimize the energy consumption, improve the scalability of the system and establish feasible implementation models in actual health care systems. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deceptive Plastic: Unveiling the World of Financial Fraud 6

Deceptive Plastic: Unveiling the World of Financial Fraud

引用

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Singh, Shikha Hazela, Bramah Asthana, Pallavi Barnwal, Shagun Srivastava, Garima Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow India Department of Electronic and Communication Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow India

As human society is developing, so is electronic commerce and with that the use of credit card are increasing. And along with this growth, as people prefer to shop using credit cards in both mode of payments, the possibility of fraud and fraud of credit card is also on rise. The criminals may steal the card physically, but more frequently, they use digital ways to obtain the credit card details along with the personal information linked to it in order to engage in illicit actions. There is a lot of overlap between credit card fraud and identity theft. Indeed, credit card theft is one of the most common forms of identity theft. In these cases, the personal information of victims is stolen to somehow get access to cards by registering a new account without the owner's knowledge and certainly it is a form of cyberattack as well as data breach and is offensive crime. This behavior is both identity fraud and credit card fraud. In this study, we employ a CAT Boost, ADA Boost, LIGHT GRADIENT BOOSTING and CONVOLUTIONAL NEURAL NETWORK model to simulate the process of credit card transaction processing and display how it can be applied to the spot of such frauds. The dataset inspection method, factor determination, and techniques used for detection have a significant influence on the demonstration of fraud detection in credit card transactions. The accuracy for models can be determined by finding precision, recall, f1score, accuracy values but to compare the models, we will take ROC AUC Score into account. So, the ROC AUC Score of CAT BOOST, ADA BOOST, LIGHT GRADIENT BOOSTING and CONVOLUTIONAL NEURAL NETWORK model are 92.44, 79.74, 93.34, 95.25 respectively. And CONVOLUTIONAL NEURAL NETWORK is best among four with 95.25 ROC Score. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of Human Activity from Video Streaming Smartphone Data Using Intensified VGG16

引用

International Journal of engineering, Transactions B: Applications 2025年第6期38卷 1340-1352页

作者： Yadav, R.K. Daniel, A. Semwal, V.B. Department of Computer Science and Engineering Amity University Gwalior India Data Science and Engineering Manipal University Jaipur India Department of Computer Science and Engineering Maulana Azad National Institute Technology Bhopal India

Human activity recognition (HAR) techniques pick out and interpret human behaviors and actions by analyzing data gathered from various sensor devices. HAR aims to recognize and automatically categorize human activities using patterns and attributes taken from sensor data. HAR is complex in implementing the algorithm for a self-recorded dataset, including challenges such as age variation, wearing different clothes, environment and surface, the direction of the smartphone camera, and many more. The paper aims to propose a VGG16 deep learning framework including an activation function and different optimizers for classifying human activity from the real-time captured dataset;further, we compare the evaluated results with existing results. The proposed methods achieved 99.88% accuracy with excellent precision, recall, and F_measure values. Comparing the evaluated result with existing outcomes over the WISDM and UCI-HAR datasets. The new things in the article are a self-captured dataset of various aged male, female, and healthy volunteers to perform seven activities. Furthermore, this research uses Tensor Processing Units (TPU) available on Kaggle to improve classification accuracy while reducing error rates and speeding up execution. ©2025 The author(s).

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Predicting Student Academic Performance using Machine Learning: Analyzing Socio-Economic and Personal Factors from Secondary Education in Portugal 4

Predicting Student Academic Performance using Machine Learni...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Sahu, Santosh Kumar, Ashok Kumar, Rahul Shukla, Anshita Chole, Vikrant Moolchandani, Jhankar Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Madhya Pradesh Gwalior India

ISBN: (纸本)9798350387490

This paper aims to predict student academic performance using machine learning algorithms by analyzing socioeconomic and personal factors from secondary education in Portugal. The study utilizes a dataset containing demographics, family background, educational support, extra-curricular activities, and academic records to evaluate their impact on students' success in Mathematics and Portuguese courses. Machine learning models such as Logistic Regression, Decision Trees, and Random Forests were employed to analyze the data. The Random Forest model outperformed others with an accuracy of 85 %, indicating significant potential in predicting student performance using the selected features. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Bayesian-Enhanced EEG Signal Analysis for Epileptic Seizure Recognition: A 1D-CNN LSTM Approach 11

Bayesian-Enhanced EEG Signal Analysis for Epileptic Seizure ...

引用

11th International Conference on Reliability, Infocom Technologies and Optimization, ICRITO 2024

作者： Jain, Mantra Bhardwaj, Harshit Srivastav, Ansh Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Uttar Pradesh Noida India

ISBN: (纸本)9798350350357

The intricate neurological condition known as epilepsy, which is common across the world, presents consid-erable difficulties in accurately identifying and differentiating between non-epileptic and epileptic activity using electroen-cephalograms (EEGs). To customize successful therapies, it is essential to accurately identify the kinds of epileptic activity. Since epilepsy affects about 50 million people worldwide according to latest update of WHO and is typified by spontaneous seizures, early identification and prediction are vital in enabling people to minimize possible harm. The current seizure prediction methods lacks, with particular emphasis on their limited performance on small training datasets and their disregard for time-series data. To identify small patterns in EEG data, this study combines cutting edge technologies, like Long Short-Term Memory (LSTM) and 1D-CNN (Convolutional Neural Network) leveraging data from five hundred patients acquired from the UCI Machine Learning Repository. To optimize the 1D-CNN LSTM architec-ture and hyper-parameters, Bayesian optimization is employed, allowing for efficient exploration of the parameter space. It's effectiveness is not only limited to enhancing the performance metrics of a particular model but also minimizing the computing power required for fine tuning. The research evaluates the effectiveness of the 1D-CNN LSTM-based model, showcasing its potential as a reliable tool for automated epilepsy detection with accuracy of 99.47% (100%), average sensitivity of 99.45%, and average specificity of 99.57%. This approach, emphasizes the significance of anticipating seizures in advance, attempts to provide epileptics the tools they need to control and avoid seizures in advance, so ultimately enhancing their quality of life for patients. © 2024 IEEE.

关键词： Quality control

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：