检索结果-内蒙古大学图书馆

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Annamalai, J. Arjun Sneha, S. Sharon Ashokkumar, C. Srm Institute of Science and Technology School of Computing College of Engineering and Technology Department of Computing Technologies Chennai Kattankulathur603203 India

ISBN: (纸本)9798350353068

Traditional video search engines often rely on tags or manual annotations for content retrieval, limiting the accuracy and efficiency of search results. Moreover, keyword-centric searches may not adeptly capture the nuanced and intricate queries users pose when seeking specific video content. The envisioned video search system integrates machine learning and natural language processing components to enable efficient and effective video retrieval based on user queries. The pipeline includes video processing employing Vision Transformer with GPT-2 (ViT-GPT2) architecture to analyze intricate details within video frames, Speech-to-Text (STT) models for transcribing spoken content, and the combination of transcriptions with video captions to form textual descriptions. These descriptions are then embedded using BERT, a transformer-based model, to grasp contextual relationships. Semantic matching is achieved through deep learning models, and a ranking mechanism based on similarity scores facilitates efficient retrieval. Leveraging datasets such as the MSR-VTT dataset, spanning visual recognition domains, contributes to the evaluation and training of the system's components. The system's efficacy is evaluated using metrics such as precision, recall, F1-score, and ranking metrics, with datasets spanning visual recognition, speech transcription, and semantic similarity domains. The comprehensive evaluation approach ensures the robustness and relevance of the video search system, aligning with user expectations and real-world use cases. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Image Fusion Based on NSCT and Sparse Representation for Remote Sensing Data

引用

Computer Systems science & engineering 2023年第9期46卷 3439-3455页

作者： N.A.Lawrance T.S.Shiny Angel Department of Computational Intelligence School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyChengalpattu603203India

The practice of integrating images from two or more sensors collected from the same area or object is known as image *** goal is to extract more spatial and spectral information from the resulting fused image than from the component *** images must be fused to improve the spatial and spectral quality of both panchromatic and multispectral *** study provides a novel picture fusion technique that employs L0 smoothening Filter,Non-subsampled Contour let Transform(NSCT)and Sparse Representation(SR)followed by the Max absolute rule(MAR).The fusion approach is as follows:first,the multispectral and panchromatic images are divided into lower and higher frequency components using the L0 smoothing *** comes the fusion process,which uses an approach that combines NSCT and SR to fuse low frequency ***,the Max-absolute fusion rule is used to merge high frequency ***,the final image is obtained through the disintegration of fused low and high frequency *** terms of correlation coefficient,Entropy,spatial frequency,and fusion mutual information,our method outperforms other methods in terms of image quality enhancement and visual evaluation.

关键词： Remote sensing multispectral image pan chromatic image L0 smoothening filter non-sub sampled contourlet transform sparse representation

来源：评论

学校读者我要写书评

暂无评论

Secure Credit or Debit Card Transaction Using Alert messages and OTP to prevent phishing attacks 3

Secure Credit or Debit Card Transaction Using Alert messages...

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Parvesh Indervati Kumari, Sonia Kumar, Kartik Gupta, Gorakh Rajakumar, P. School of Computing Science & Engineering Galgotias University UP India

ISBN: (纸本)9798350336238

In the digital world, the utilization of online transactions using credit and debit cards is growing every day. However, credit or debit (CD) card fraud is one of the prime challenges confronted by customers and bankers. The financial databases are stored at various cloud servers and these types of fraud make a huge loss in the financial systems as well as security concerns in the cloud. The cloud platform provides efficient and uninterrupted access to banking databases. There are distinct security initiatives that were taken to prevent fraudulent transactions, but still, hackers try different techniques to compromise the customer's account. Currently, for online Card payments, an OTP has been sent to the customer's phone number and email-id of a customer for security during the transaction. In this article, we introduce a new approach by sending an alert message before the OTP to the card owner whenever the credit or debit card number is entered by the customer or hacker for an online transaction. © 2023 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Cricket Performance Analysis System Using Machine Learning Techniques 5

Cricket Performance Analysis System Using Machine Learning T...

引用

5th International Conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Mishra, Suraj Garg, Animesh Batra, Vansh Saxena, Devansh Om Gouthaman, P. School of Computing College of Engineering and Technology SRM Institute of Science and Technology Department of Networking and Communications 603203 India School of Computing SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications India

ISBN: (纸本)9798331530013

The Cricket Performance Analysis System based on big data tools, like Hadoop and Apache Spark, gives realtime deep insights into performances from players and teams and conditions in matches based on large-scale cricket match data. It scales up speedily and finds patterns using distributed computing capabilities of Spark, which makes it possible to take decisions around performance improvements and strategies. The system applies a set of machine learning techniques including K-means clustering, Logistic Regression, and Random Forest classifiers to be used for the analysis of player performance metrics and match outcomes. Thus, through the conversion of raw data into actionable insights, teams can improve their strategies, make better improvements in performance, and thus gain an upper hand against other competing professional cricket teams. As a result, teams are best positioned to make adjustments in good time and direct finer tactics toward further enhancement of overall performance. © 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

Speech Emotion Recognition Using Machine Learning 3

Speech Emotion Recognition Using Machine Learning

引用

3rd International Conference on Innovative Practices in Technology and Management, ICIPTM 2023

作者： Kumar, Aman Kumar, Vivek Rajakumar, P. School of Computing Science & Engineering Galgotias University UP India

ISBN: (纸本)9798350336238

In the field of human-computer interaction, identifying the emotions conveyed in a person's speech is a challenge that is both incredibly fascinating and challenging. Recent times have seen a significant uptick in people's interest in this topic. In the subject of speech emotion recognition, a wide variety of techniques have been applied in order to extract emotions from signals. These techniques include a number of well-known speech analysis and classification strategies. This paper provides an overview of the deep learning technique, which is based on a simple algorithm based on feature extraction and model creation that recognizes emotion. In the traditional method of speech emotion recognition, features are first extracted from the speech signals, then the features themselves are picked, collectively known as the selection module, and then the emotions are recognized. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Automated Parking Monitoring Using Geo-Tagged UAV Images

Vision-Based Automated Parking Monitoring Using Geo-Tagged U...

引用

2024 International Conference on Green Energy, computing and Sustainable Technology, GECOST 2024

作者： Lai, Chung Yi Jo, Hudyjaya Siswoyo Lai, Chean Hung Dunn, Michelle Swinburne University of Technology Sarawak Campus Faculty of Engineering Computing and Science Kuching Malaysia School of Science Computing and Engineering Technologies Swinburne University of Technology Hawthorn Campus Melbourne Australia

ISBN: (纸本)9798350357905

This paper proposes an automated solution for parking monitoring using geo-tagged UAV (Unmanned Aerial Vehicle) images. The parking monitoring system utilizes a UAV to patrol the parking lot. The UAV captures video footage that contains geolocation information. Geo-tagged images are extracted from the video footage and processed using the YOLOv8 object detection algorithm to recognize occupied and vacant parking spaces. The license plates of the parked vehicles in the occupied parking space are extracted using EasyOCR and stored in a database. Each parking space is labeled with a unique ID with its date, time, geolocation data, and occupancy status to facilitate integrated digital parking solutions for both the users and parking operators. © 2024 IEEE.

关键词： License plates (automobile)

来源：评论

学校读者我要写书评

暂无评论

Driver Somnolence Detection System Using Machine Learning Tools 5

Driver Somnolence Detection System Using Machine Learning To...

引用

5th IEEE International Conference on Advances in computing, Communication Control and Networking, ICAC3N 2023

作者： Gupta, Akrati Partheeban, N. Rajakumar, P. Pravesh Kumar, Saurabh Kumar, Rachit Galgotias University School Of Computing Science & Engineering UP India

ISBN: (纸本)9798350330861

A reliable mode of conveyance is essential in today's society. Anyone behind the vehicle is susceptible to having an accident. Several circumstances, such as fatigue, illness, or lengthy travel, may contribute to this phenomenon. Getting insufficient sleep or being subjected to other forms of injustice increases the likelihood of being involved in an accident. Accidents on the road are frequently the result of drivers who are drowsy or too exhausted to pay attention. Due to this, the annual global accident toll is significantly higher than it would be otherwise. Multiple automobile collisions have occurred in various areas of the world over the past several years. The road is heavily traveled at all hours of the day and night. Everyone experiences drowsiness after a lengthy voyage, which is a decent indicator of how exhausted one is. Don't get behind the wheel if you haven't had sufficient rest. Therefore, it is essential for drivers to be able to recognize the signs of exhaustion so they can take the necessary precautions to safeguard themselves and others on the road. This paper's major goal is to create a system that can recognize driver weariness. This model employs specialized algorithms to evaluate the driver's ocular health in realtime based on images captured in-car, eradicating the need for the driver to draw over. The driver could care less if there are alternative ways to attain the same objective;he is unaffected by this particular strategy. If you want to determine whether someone is fatigued, simply observe the 'stopping score' of the pupils. If the score exceeds a certain threshold, the individual is considered drowsy. © 2023 IEEE.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

Multi-Factor Authentication System With ID Card Credentials For Secure Transactions 14

Multi-Factor Authentication System With ID Card Credentials ...

引用

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

作者： Vasudev, R. Harini, N. Neethu, M.R. Amrita Vishwa Vidyapeetham Amrita School of Computing Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

A physical document that can be utilized to validate a person's identity is known as ID card, usually comes in standard size same as that of credit cards (3.370 inch height and 2.125 inch width).The machine readable identification information within ID card is the primary means of controlling individual access to everything starting from employee areas to special lounges. Transparency level of identification information within the document (ID card) varies from organization to organization. Some uses visible credentials like Barcodes and QR codes while others use RFIDs. Impersonation and the MFA- SYSTEM represents two distinct phases of the project. Former gives a clear-cut idea on how an impersonation attack is carried out by using methods in image processing, computer vision for extracting the visible features and decoding the information from the images or videos recorded using smartphones or surveillance cameras. SURF and SIFT are initially extracted, FLANN for feature mapping and Homography estimation using RANSAC algorithms. Latter one is making a multifactor authentication system that can improve the security of the ID card credentials. The proposed system in phase 1 can is able to successfully locate the position of barcodes and QR codes within the image and successfully decode information within the QR code, phase two helps to solve some of the challenges in authentication like shoulder surfing, securing data in MongoDB, accuracy during storing and retrieval from database etc © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Insights: A Survey on Innovative Approach for Lung Cancer Prediction Utilizing Machine Learning and Deep Learning Methods 3

AI-Driven Insights: A Survey on Innovative Approach for Lung...

引用

3rd International Conference on Automation, computing and Renewable Systems, ICACRS 2024

作者： Bhargav, A. Lakshmi Ashokkumar, C. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science & Technology Kattankulathur Chennai603203 India

ISBN: (纸本)9798331532420

The lungs are vital for exchanging oxygen and carbon dioxide, providing oxygen to cells for energy production, and removing waste carbon dioxide from the *** also help filter and protect the body from harmful particles and pathogens in the *** lung function is essential for overall health and *** cancer ranks as the second most common cause of cancer-related fatalities *** emphasizes the challenge of early detection due to the lack of symptoms in the initial *** contributes to a high mortality rate compared to other lung *** identification and precise prediction of lung cancer serves as vital for improving patient outcomes. Machine learning (ML) techniques have shown great promise in revolutionizing lung cancer prediction by leveraging various data sources such as medical images, clinical data, and genomic information. This paper presents a review of lung cancer prediction using ML, DL, and AI *** classification of lung cancer through medical imaging is essential for physicians to determine appropriate treatment options, ultimately aiming to reduce cancer *** goal is to compare the performance and accuracy of convolutional neural networks (CNNs), Random forest algorithm, ensemble extreme boosting (XGBoost) algorithm,Support Vector Machine (SVM), AdaBoost classification model (ADB-C), Long Short-Term Memory Networks (LSTM), incremental multiple resolution residual network (iMRRN) models while also providing explanations for their predictions. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security: A Hybrid Encryption Algorithm for Effective Key Generation 2

Enhancing Security: A Hybrid Encryption Algorithm for Effect...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, computing, and Communications Systems, ICMACC 2024

作者： Jacob, Jeevan John Kiran, P.S. Shenoy, Jaigovind B Basavaraju, Sagar Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350366570

The abstract Data security is of most importance, in the present day- the introduction of high-level wireless communication channels has led to generation and transfer of massive amounts of data. Data security must keep up with it. Data breach may cause disastrous outcomes. Previously, hardware security modules (HSM) were used to perform cryptographic actions- storing keys and for authentication. This is no longer feasible as HSMs are physical devices and become inconvenient to carry around all the time. The unavailability of HSM poses a serious security threat (for cryptographic keys). This paper aims at a novel software solution that compensates for hardware. As the algorithm focuses on securing keys used for encryption. It may be referred to as key security scheme (KSS). The paper proposes a way to generate keys instead of storing it and assumes performing of cryptographic actions on the available hardware in the system. The proposed method can secure data, both in transit and while at rest. © 2024 IEEE.

关键词： Encryption algorithms

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：