检索结果-内蒙古大学图书馆

2nd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2023

作者： Zad, Ajay Jagannatha, S. Kumar, Manish Ajitha, S. Prakash, B.R. M S Ramaiah Institute of Technology Department of Masters of Computer Applications Bangalore India East Point College of Engineering Department of Computer Applications Bangalore India M S Ramaiah Institute of Technology Department of Master of Computer Applications Bangalore India Government First Grade College Department of Computer Science Karnataka Tumkur India

ISBN: (纸本)9798350314045

The mouse plays a very important role in interacting with laptop's and computer system, to perform necessary operations. In this paper, we are proposing a method to carry out mouse operations on the computer system without a physical mouse by utilizing voice commands and face-motion gestures. The system employs an internal webcam to detect facial gestures and an internal microphone to receive voice commands from the user. By employing a virtual mouse based on face gestures and natural language processing (NLP), we can accomplish all the fundamental functionalities of a mouse by issuing voice commands to the computer system. The system accepts these commands and executes corresponding mouse events such as "click,""right-click,""double-click,""scroll-up,""scroll-down,""minimize,"and "close."The mobility of the mouse cursor on the monitor is achieved through face motion gestures, enabling the cursor to move up, down, left, and right, respectively. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Deep Learning Techniques for Deepfake Detection: Evaluating Threats and Opportunities 15

Comparative Analysis of Deep Learning Techniques for Deepfak...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kadam, Maithili Milind Kate, Sakshi Sachin Chavare, Vaishnavi Bhoite, Sachin Department of Computer Science and Applications Dr. Vishwanath Karad MIT-World Peace University Pune India

ISBN: (纸本)9798331300579

Deepfake, a term combining "deep learning" and "fake," is a growing concern in various fields due to the ability to generate realistic images and visuals using advanced visual effects and AI algorithms. This study aims to critically analyze various deep learning approaches for deepfake detection, focusing on their performance, robustness, and adaptability. The re-search will evaluate techniques like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Generative Adversarial Networks (GANs), and The Convolutional Vision Transformer (CVT). The results will highlight the efficiency of ensemble modeling based on combined models, highlighting the strengths of multiple models. Additionally, the research undertakes a comprehensive literature review that analyzes several research works done by other researchers in field of deepfake detection. The research gaps demonstrate where further research and analysis is required, thereby revealing the weaknesses and unresolved challenges that face deepfake de-tection. © Grenze Scientific Society, 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Patterns of Widespread Structural Abnormalities in Autism Spectrum Disorder using Diffusion Tensor Imaging

Patterns of Widespread Structural Abnormalities in Autism Sp...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Bharti, Dilip Kumar Singh, Sanjay Kumar Kumar, Mukesh Kanaujia, Vishal Kumar Aeri, Manisha Abes Engineering College Computer Science And Engineering-Data Science Ghaziabad India Kashi Institute Of Technology Department Of Computer Science & Applications Mirzamurad U.P Varanasi India Graphic Era Hill University Computer Science And Engineering Uttarakhand Dehradun248002 India Abes Engineering College Computer Science And Engineering Data Science Department Ghaziabad India

ISBN: (纸本)9798350366846

Diffusion tensor imaging (DTI) is a neuroimaging approach that lets in for the visualization and quantification of the structural integrity of white depend fibers in the brain. In latest years, DTI has come to be an essential tool for investigating the underlying neurobiological mechanisms of autism spectrum sickness (ASD), a neurodevelopmental disorder characterized via problems in social communication and repetitive behaviors. Through the usage of DTI, researchers have identified good sized styles of structural abnormalities in the brains of individuals with ASD. these abnormalities encompass changes in the microstructure of white remember fibers, along with decreased fiber density, changes in fiber directionality, and decreased connectivity between mind areas. Additionally, there may be evidence of bizarre mind development in early formative years, with a few research finding that these structural variations are present even in very younger children with ASD. One constant finding in DTI studies of ASD is reduced white rely integrity inside the corpus callosum, a large fiber package deal that connects the two hemispheres of the mind. This abnormality has been connected to deficits in social communiqué and language in people with ASD, as well as difficulties in integrating records from distinctive brain areas. The results showed extensive structural abnormalities in people with ASD in comparison to TD individuals. © 2024 IEEE.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Empowering Education: Blockchain-Driven Decentralized Data Storage and Access of Academic Assets

Empowering Education: Blockchain-Driven Decentralized Data S...

引用

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

作者： Goyal, Kamakshi Keshav Shukre, Varsha Atul Godbole, Shruti Shirish Mulye, Vandana Dr.Vishwanath Karad MIT World Peace University Department of Computer Science & Applications Pune India

ISBN: (纸本)9798350385199

In recent years, the rapid heightening in technology has led to the convergence of various fields, resulting in cathartic applications across education sector. One such paradigm shift has been witnessed in the domain of Blockchain. The use of vast academic assets necessitates secure storage and shared access to diverse data owned by the various institutions and universities. This paper presents the innovative application of Blockchain technology with a focus on decentralized data access and storage for learning materials. Traditional centralized data storage models have problems with restricted accessibility, security breaches, and data manipulation. Blockchain provides an innovative solution which is safe, immutable environment for archiving and retrieving academic content. In order to increase storage capacity beyond Blockchain-only solutions, the paper suggests a distributed, decentralized storage application on the basis of Interplanetary File System (IPFS) and Hyperledger Fabric for Blockchain network traceability. The intent of using this approach is to secure and provide distributed access to the academic assets for maintaining the ledger in a tamper proof order. Smart contracts are used to automatically validate educational materials, guaranteeing their integrity and immutability. The Publish/Subscribe architectural design pattern is employed to streamline communication, while the Proof-of-Authority consensus mechanism is employed to enhance security. With an emphasis on accountability and transparency, the architecture facilitates the safe exchange of academic assets and credits owned by students. The advantages of a decentralized application (DApp) operating on a peer-to-peer network are covered, along with fraud prevention scenarios and the validation process. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Detection of Mango Leaves Disease using CSUBW based Residual Attention with EfficientNet 2

Detection of Mango Leaves Disease using CSUBW based Residual...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kumar V, Sunil Jyothi, A.P. Nagamani, H.S. Sumanth, S. Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ramaiah University of Applied Sciences Faculty of Engineering and Technology Department of Cse Bengaluru India Department of Computer Science Bengaluru India Department of Computer Science and Computer Applications Kolar India

ISBN: (纸本)9798350382952

Mangoes are one of the most popular fruits worldwide due to their taste and nutrition. Plant diseases may reduce plant quantity and quality. Disease management to improve crop quality and productivity requires early plant illness detection. Automation of plant disease detection reduces large farm surveillance. Since plants feed us, leaf problems must be diagnosed quickly and accurately. Our advanced learning method automatically detects leaf disease in several mango plant varieties. This study creates the RAM-EfficientNet, a novel illness classification network. The RAM block in EfficientNet extracts additional features and handles slight leaf lesion changes. Transfer learning was used to train EfficientNet on ImageNet to overcome the mango leaf disease sample size issue. The Cat Swarm Updated Black Widow Model (CSUBW), a hybrid optimization model, changes RAM-EfficientNet's weights to improve classification accuracy. Black Widow Optimization Algorithm (BWO) and Cat Swarm Optimization Algorithm (CSO) are combined to create the hybrid optimization model. The model's performance is then assessed to confirm its efficacy. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Advancement in Inflation Projection with AI Insights: A Case Study on India's Inflation Data 15

Advancement in Inflation Projection with AI Insights: A Case...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Bhoite, Sachin Panchal, Riddhi Shukre, Varsha Atul Department of Computer Science and Applications MIT World Peace University Dr. Vishwanath Karad Pune India

ISBN: (纸本)9798331300579

The study critically reviews the existing literature on inflation forecasting in India, emphasizing the limitations of traditional econometric models in capturing intricate relationships among macroeconomic variables influencing inflation. In response, Machine Learning (ML) and Deep Learning (DL) models are proposed for inflation forecasting, leveraging a dataset comprising Indian macroeconomic variables. The devised model undergoes training and testing through various ML and DL techniques, encompassing LR, K-NN, DT, SVM (Linear Kernel), SVM (RBF Kernel), NN, RF, GB, AdaBoost, and XGBoost. Comparative analysis against traditional econometric models demonstrates the superior predictive performance of the ML and DL model. Notably, the convolutional neural network model stands out as the most accurate forecasting techniques. This study also identifies key variables influencing inflation rates in India, including interest rates, exchange rates, and fuel prices. The results underscore the potential of ML and DL methods in enhancing inflation forecasting in India, utilizing the latest dataset collected through survey methods across diverse Indian cities. Furthermore, XGBoost emerges as the optimal classifier for predicting inflation in India. These findings hold significant implications for policymakers and central banks, offering valuable insights for informed decision-making and the formulation of effective monetary policies in the context of developing countries. © Grenze Scientific Society, 2024.

关键词： Inflation

来源：评论

学校读者我要写书评

暂无评论

Analysing weather conditions using Firebase

Analysing weather conditions using Firebase

引用

2023 International Conference on Green Energy, Computing and Intelligent Technology, GEn-CITy 2023

作者： Jha, Abhishek Lalan Ashraf, Azhar Verma, Sahil Kaur, Maninder Computer Science & Engineering Chandigarh University Gharuan India Department of Computer Science and Engineering Uttaranchal University Dehradun India Department of Computer Science and Applications Guru Gobind Singh College for Women Chandigarh India

ISBN: (纸本)9781839539596

Forecasting Weather to a specific time and location via the use of science and technology for its specific location from the 19th century, millions of humans have started predicting weather forecasting. This technology uses meteorology so that it predicts the weather for the future so that the response of the atmosphere can be recorded for the future purpose. Technology for predicting weather we use barometric pressure, in that which show the current weather condition and cloud cover for Sky condition this prediction model is based on the computer Based model show the records of a wide range of atmospheric will be recorded by having this technology for model prediction is pattern recognition, telecommunication model, performance knowledge, but its skill required the more in this technology for forecasting the chaotic character of the weather which is overpowered by the measurement error by this less accuracy the atmospheric dynamic model field to predicting the model which is already exist for forecasting. As a result, as the time gap between today and the predicted model for the forecast has a time gap so it leads to less accuracy, the range of forecasting prediction for selecting the most likely and accurate outcome in the model contest aid narrows free error in it. The most difficult challenge in the world is to predict the forecasting using the Meteorology virtual application for the most significant difficult Technology. In this paper, we are going to investigate data mining techniques and artificial neural networks, my research paper presents the service-oriented model that the architecture for the weather information system will be linked with the GPS system. Algorithms such as Artificial neural networks and Decision tree algorithms are going to use for prediction model for forecasting by gathering information on meteorological data collection of specific time can use for achieving accuracy therefore, this paper includes of classification of different rules f

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Conglomerate Energy Efficient Elgamal Encryption Based Data Aggregation Cryptosystems in Wireless Sensor Network

引用

International Journal of Engineering, Transactions B: applications 2022年第2期35卷 417-424页

作者： Babu, T.G. Jayalakshmi, V. Department of Computer Applications Vels Institute of Science Technology and Advanced Studies Pallavaram Chennai India

Wireless sensor networks (WSN) are growing rapidly since the pastdecade mainly due to its efficiency and Ad-Hoc feature. The data aggregation has been extensively employed in WSN that also impacton the data transferring between the sensor nodes. The security issues, data integrity and confidentiality become vital during the deployment of sensor network in a hostile environment. The entire network comprises of sensors, base stations, gateways and nodes which are connected for the purpose of digital transmission. Many existing works have been evolved to address the security issues in WSN butall focused only on basic security features but lack to obtain reliable and effective results in terms of parameters like energy consumption, packet delivery ratio, and computational cost. T his paper focussed on the primary research area of data aggregation and the mode of transmission in an energy efficientway without congestion. To obtain the objective, an integration of Conglomerate ElGamal energy efficient protocol has been employed and the performance of the proposed system are evaluated. Since the resource constraint nodes of the wireless sensor network requires less energy to cope up with limited battery power, the main purpose of the work is to build an efficient security mechanism that enhances the performance of the network with less energy, minimum delay, and maximum throughput. The performance parameters like packet delivery ratio, throughput, estimation of alive nodes and dead nodes for different rounds has been performed in the study. Furthermore, the effectiveness of the proposed system has been compared with state of artmet hods in terms of residual energy and depicted that deliberat es the superior performance of the presented framework. © 2022 Materials and Energy Research Center. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Cognitive Detection of Anomalies in Autonomous In-Vehicle Network Communication

Cognitive Detection of Anomalies in Autonomous In-Vehicle Ne...

引用

2024 International Conference on Advancements in Power, Communication and Intelligent Systems, APCI 2024

作者： Firasta, Suzen Srivastava, Yash Rahul Rao, Vidya Manipal Institute of Technology Manipal Academy of Higher Education Department of Data Science and Computer Applications Manipal India

ISBN: (纸本)9798350363289

The research addresses the critical issue of detecting anomalies in autonomous in-vehicle network communication, focusing on the vulnerability of infotainment systems to denial-of-service attacks. The aim is to explore and compare traditional Machine Learning (ML) and advanced Deep Learning (DL) models for the detection of DoS attacks within Controller Area Network (CAN) communications. By evaluating the performance of various ML and DL algorithms, including Decision Tree, Logistic Regression, RandomForest, Feed Forward Neural Networks, and LSTM architectures, the study aims to enhance intrusion detection capabilities in vehicular communication systems. The significance of the research lies in identifying the advantages of DL methods in capturing complex patterns and temporal dependencies within the CAN network, thus contributing to fortifying the security of automotive networks against evolving threats. The results demonstrate the efficacy of the proposed models in detecting and mitigating DoS attacks, with DL methods showing promise in automatic learning and adaptability to intricate network structures. This study provides valuable insights for future research endeavors aimed at enhancing the cybersecurity of autonomous vehicles. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

AI Enabled Convolutional Neural Networks to Detect Brain Tumors 1

引用

3rd International Conference on Universal Threats in Expert applications and Solutions, UNI-TEAS 2024

作者： Singh, Kamred Udham Kumar, Ankit Kumar, Gaurav Singh, Teekam Kothari, Paras Rao, Ankur School of Computing Graphic Era Hill University Dehradun India Department of Computer Engineering and Applications GLA University UP Mathura India Department of Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India Department of Computer Applications Geetanjali Institute of Technical Studies Rajasthan Udaipur India

ISBN: (数字)9789819738106

ISBN: (纸本)9789819738090

In the early stages of a person’s existence, it is common practice to screen for the presence of brain tumors. Nevertheless, in the current day, it has been improved using various AI computations. Along these same lines, in order to diagnose a patient with a brain tumor, we take into consideration the data of patients, such as MRI scans of the patient’s brain. Our main concern at this point is determining whether or not the tumor is present in the patient’s brain. For a patient to have a healthy lifespan, it is essential for the tumor to be identified at the earliest possible stage. During this phase of the project, we use a calculation called a convolutional neural network to determine the level of severity, which provides accurate results. The division of tumors is an essential and challenging task that falls within the purview of clinical image production. This is due to the fact that human-aided manual characterization might result in erroneous anticipations and discoveries. We proposed the use of a convolutional neural network as a means of differentiating cancers from 2D appealing resonance brain imaging (MRI). The exploratory study was carried out on a dataset that included tumors with a wide range of dimensions, localizations, configurations, and picture forces. Convolutional neural networks, which are built using Keras and Tensorflow, were chosen for usage by our team because, in comparison to regular neural networks, they provide a much-improved presentation. During the course of our investigation, CNN demonstrated an accuracy of 98.73%. Because of its great speculation capacity and quickness, the CNN design that was only recently developed has the potential to be employed as an effective decision-aid device for radiologists working in clinical diagnostics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

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：