检索结果-内蒙古大学图书馆

2nd International Conference on Next-Generation Computing and Information systems, ICNGCIS 2023

作者： Mathukiya, Deep Kumar, Yogesh Koul, Apeksha Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gandhinagar India Punjabi University Punjab Patiala India

ISBN: (纸本)9781032738659

Currently, Diabetes is a prevalent issue worldwide, affecting millions of people. The detection machinery for this disease is only available at healthcare centers, so individuals with diabetes are only aware of their condition when they visit and undergo a checkup. Prolonged diabetes can lead to various complications like heart disorders, kidney disease, nerve damage, and diabetic retinopathy. However, the risk can be reduced if the disease at its early stage is predicted. By utilizing a deep learning approach, this model can easily determine if an individual is diabetic or not. The aim of the research is to develop machine learning model that can identify diabetic people on the basis of their clinical data. The machine learning algorithms utilized in this study include Naive Bayes (NB), k-nearest neighbor (KNN), Stochastic Gradient Descent (SGD), Decision tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR). We have implemented efficient pre-processing techniques to detect as well as handle missing/ NAN and duplicate values and later trained our models with the cleaned dataset. During execution, we found that Random Forest as well as Decision Tree performed well for both diabetic and non-diabetic class by computing 100% and 99% accuracy respectively. © 2025 The Author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Review of Segmentation and Recognition Techniques for Indian Sign Language using Machine Learning and computer Vision 10

A Review of Segmentation and Recognition Techniques for Indi...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Kumari, Subhangi Tarlue, Ernest Diallo, Aissatou Chhabra, Megha Mishra, Gouri Shankar Goyal, Mayank Kumar School of Engineering and Technology Sharda University Department of Computer Science and Applications Greater Noida India

ISBN: (纸本)9789380544472

Indian Sign Language (ISL) is a complex and diverse language used by the deaf and hard-of-hearing community in India. ISL recognition and segmentation have been active areas of research in recent years due to the growing demand for assistive technologies for this population. In this review paper, we provide an overview of the various techniques used for ISL recognition and segmentation using machine learning and computer vision. We begin by discussing the challenges involved in ISL recognition and segmentation, such as the variations in sign language gestures, lighting conditions, and background noise. We then review the literature on various techniques used for ISL recognition. We analyze the strengths and limitations of each technique, comparing their accuracy, speed, and robustness against various factors. Finally, we present the recent advancements and future directions for ISL recognition and segmentation © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Audio Deepfake Detection Using Deep Learning 12

Audio Deepfake Detection Using Deep Learning

引用

12th International Conference on system Modeling and Advancement in Research Trends, SMART 2023

作者： Anagha, R. Arya, A. Narayan, V. Hari Abhishek, S. Anjali, T. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350369861

The capacity to identify real audio recordings from their modified counterparts is essential in the age of sophisticated digital manipulation for maintaining security and trust in a vari- ety of applications, from media forensics to voice authentication systems. This research aims to create a deep learning model that can distinguish between authentic and altered audio files, with an emphasis on identifying audio deepfakes. The study uses Mel spectrogram representations and data augmentation techniques to effectively extract features from the ASV spoof 2019 dataset and train models. Convolutional neural networks (CNNs) comprising a number of layers, including convolutional, pooling, batch normalization, ReLU activation, dropout, global average pooling, and a dense classification layer are used as the foundation of the design. The Adam optimizer is used to optimize the model once it has been trained using binary cross-entropy loss, and a variety of metrics, such as accuracy, F1 score, ROC curve, and AUC, are used to track its performance. By making it easier to identify audio deepfakes, this project will ultimately increase the security and integrity of audio data in the digital world. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Deep Structured Learning for Cross-Site Scripting Attacks

AI-Driven Deep Structured Learning for Cross-Site Scripting ...

引用

2023 IEEE International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2023

作者： Abhishek, S. Ravindran, Rahulkrishnan Anjali, T. Shriamrut Amrita School of Computing Department of Computer Science and Engineering Amritapuri India VMware Inc India

ISBN: (纸本)9798350397208

A substantial danger of attacks from numerous sources, with varying intensity and sophistication, is posed by the worldwide nature of online applications. A code injection attack known as cross-site scripting (XSS) occurs on the client side or via web browsers. Cross-Site Scripting (XSS), a severe attack that may be used to change a user's or an organization's data, is typical in online applications. This paper suggests a hybrid convolutional neural network (CNN) and machine learning (ML) framework for quickly and effectively identifying the XSS attacks to enhance the security. According to the simulation findings, the proposed model is more effective than the existing detection techniques. It generates results for XSS attack categorization that are more than 99.9% correct and is exceptionally resistant to XSS attack. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Wearable Physiological IoT system with Neural Network to Detect an Individual IT Professional's Stress / Emotion in Working Environments 7

Wearable Physiological IoT System with Neural Network to Det...

引用

7th International Conference on Intelligent Computing and Control systems, ICICCS 2023

作者： Devi, V.Anusuya Pradeepaj, T.Sam Achyuth, N.Sai Nagarajan, R. Raj, R.Rahul Krishna, B.Navneetha School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Krishnankovil India

ISBN: (纸本)9798350397253

Stress in the workplace has a major impact on people's lives. IT industries are pushing the boundaries by introducing cutting-edge technologies and products but the high levels of stress among IT professionals remains as a concerning issue. Research has shown that stress can have an adverse effect on cognitive performance and physical health. This research study presents a novel neural network based wearable physiological IoT system to detect the stress and emotion levels of individual IT professionals in working environments. The proposed system is composed of a wearable device, mobile application, and neural network. The wearable device is equipped with three physiological sensors, namely heart rate, skin temperature, and electromyography (EMG) sensor. The mobile application collects the sensed data from the wearable device and then sends it to the neural network for analysis. The neural network is designed to detect the individual's stress and emotion levels based on the sensed physiological data. In addition, the mobile application provides the user with visual feedback and can be used to set goals and track progress. The proposed system is evaluated through a user study in an IT professional work environment. The results show that the system has the capability to detect the individual's stress and emotion levels with an accuracy rate of 91.6%. In order to minimize the potential risks of stress and its related effects, it is important to recognize these emotions and take appropriate steps to alleviate them. This work presents a system that can detect stress using facial analysis, a pulse oximeter, and temperature sensors. A camera is used to capture the person's front view. The proposed system utilizes a Convolutional Neural Network (CNN) Algorithm to analyze an individual's facial expression in an image frame and determine their stress level. A prototype was developed to detect if someone is under stress based on their heart rate and blood pressure variations.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimal Ship Route Search Based on Multi-Objective Genetic Algorithm 14

Optimal Ship Route Search Based on Multi-Objective Genetic A...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Ashwin, R. Ilamparithi Yaazharasu, C.R. Ramana, Pavan Teja Shilpa, Paladugu Jeyakumar, G. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

Optimization of ship routing depends on several parameters such as ship and cargo characteristics, environmental factors, topography, international navigation rules and crew comfort, etc. Ship route optimization is an essential problem for ship operators to reduce fuel consumption and voyage duration. This work presents an algorithm to plan safe and optimal routes for ships moving inaccessible areas and with unlimited traffic direction. The route obtained is optimized with multiple objectives which makes it more unique and optimal. An evolutionary algorithm is used to create numerous locally optimal routes, and a parallel genetic algorithm is used to construct a final route by optimizing a set of said routes. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Investigate the efficiency of incompressible flow simulations on CPUs and GPUs with BSAMR

Investigate the efficiency of incompressible flow simulation...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Liu, Dewen He, Shuai Cheng, Haoran Zeng, Yadong School of Civil Engineering Southwest Jiaotong University Chengdu611756 China School of Civil Engineering Northwestern Polytechnical University Xi’an710129 China Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48104 United States Department of Computer Science University of Texas at Austin AustinTX78712 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Adaptive mesh refinement (AMR) is a classical technique about local refinement in space where needed, thus effectively reducing computational costs for HPC-based physics simulations. Although AMR has been used for many years, little reproducible research discusses the impact of software-based parameters on block-structured AMR (BSAMR) efficiency and how to choose them. This article primarily does parametric studies to investigate the computational efficiency of incompressible flows on a block-structured adaptive mesh. The parameters include refining block size, refining frequency, maximum level, and cycling method. A new projection skipping (PS) method is proposed, which brings insights about when and where the projections on coarser levels are safe to be omitted. We conduct extensive tests on different CPUs/GPUs for various 2D/3D incompressible flow cases, including bubble, RT instability, Taylor Green vortex, etc. Several valuable empirical conclusions are obtained to help guide simulations with BSAMR. Codes and all profiling data are available on GitHub. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Privacy Enhanced Mobile User Authentication Method Using Motion Sensors

引用

computer Modeling in engineering & sciences 2024年第3期138卷 3013-3032页

作者： Chunlin Xiong Zhengqiu Weng Jia Liu Liang Gu Fayez Alqahtani Amr Gafar Pradip Kumar Sharma Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518052China Sangfor Technologies Inc. Shenzhen518055China School of Data Science and Artificial Intelligence Wenzhou University of TechnologyWenzhou325035China College of Computer Science&Technology Zhejiang University of TechnologyHangzhou310023China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Math&Computer Science Department Faculty of ScienceMenofia UniversityShebin El-KomEgypt Computing Science Department University of AberdeenAberdeenUK

With the development of hardware devices and the upgrading of smartphones,a large number of users save privacy-related information in mobile devices,mainly smartphones,which puts forward higher demands on the protection of mobile users’privacy *** present,mobile user authenticationmethods based on humancomputer interaction have been extensively studied due to their advantages of high precision and non-perception,but there are still shortcomings such as low data collection efficiency,untrustworthy participating nodes,and lack of *** this end,this paper proposes a privacy-enhanced mobile user authentication method with motion sensors,which mainly includes:(1)Construct a smart contract-based private chain and federated learning to improve the data collection efficiency of mobile user authentication,reduce the probability of the model being bypassed by attackers,and reduce the overhead of data centralized processing and the risk of privacy leakage;(2)Use certificateless encryption to realize the authentication of the device to ensure the credibility of the client nodes participating in the calculation;(3)Combine Variational Mode Decomposition(VMD)and Long Short-TermMemory(LSTM)to analyze and model the motion sensor data of mobile devices to improve the accuracy of model *** experimental results on the real environment dataset of 1513 people show that themethod proposed in this paper can effectively resist poisoning attacks while ensuring the accuracy and efficiency of mobile user authentication.

关键词： Mobile authentication blockchain federated learning smart contract certificateless encryption VMD LSTM

来源：评论

学校读者我要写书评

暂无评论

Exploring ChatGPT for Email Content Compression and Summarization 4

Exploring ChatGPT for Email Content Compression and Summariz...

引用

4th International Conference on Communication, Computing and Industry 6.0, C216 2023

作者： Bhuvaneswari, R. Tharaniesh, P.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India

ISBN: (纸本)9798350327328

In our daily lives, email communication is essential, yet monitoring the voluminous amount of emails can be time-consuming. The goal of email summarizing techniques is to quickly and accurately summarize email content in order to increase productivity and efficiency. In this study, we investigate the use of ChatGPT, a cutting-edge language model, for email synthesis. We offer a fresh strategy to take advantage of ChatGPT's conversational features for summarization while optimizing it on a big dataset of email discussions. Our tests show that ChatGPT-based email summarization outperforms other approaches in terms of performance. The generated summaries provide a clear and succinct summary of the email content that successfully captures the important details. To assess the value and user satisfaction of the summaries produced by ChatGPT, we also perform user studies. According to the findings, ChatGPT-based email summarizing has potential as an efficient and convenient method for controlling email overload. This work demonstrates the potential of conversational language models in tackling the difficulties of email management and advances email summarizing approaches. © 2023 IEEE.

关键词： Electronic mail

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Integrated Software Defined Networking Architecture for Congestion Control 2

Machine Learning Integrated Software Defined Networking Arch...

引用

2nd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2023

作者： Sha, Akhbar Madhan, S. Neemkar, Sandeep Varma, Vanapala Bharath Chandra Nair, Lekha S. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Amritapuri India

ISBN: (纸本)9798350347456

Data center networks rely upon the excellent throughput of the network to ensure data transfer happens at incredible speeds. Many factors can determine the network's throughput, such as the design, routing mechanism, and congestion control model. The introduction of the cloud made it more challenging as high traffic can happen and disrupt the data transfer for the cloud applications;this is a challenge in hosting cloud services and applications. The introduction of Software Defined Networking (SDN) made it possible to program the networks and thus provide scope for enhancing the congestion control mechanisms. Separating the control plane from the data plane helps in independence and extracting and processing the data from different perspectives. This paper proposes a Machine Learning approach implementable in an SDN context that helps reduce congestion control by learning data transfer patterns. We propose a modified version of SDN in which an additional layer is implemented above the control plane called ML plane. ML plane takes care of the trend learning in the network that guides the control plane for better decisions. In this paper, we exhibit the architecture of ML plane for the purpose of congestion control in busy networks. © 2023 IEEE.

关键词： Software defined networking

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：