检索结果-内蒙古大学图书馆

International Conference on Inventive Computing and Informatics (ICICI)

作者： M Udhayakumar Titus Issac J Sebastian Terance Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798350373295

ISBN: (纸本)9798350373301

The communication between differently challenged persons especially deaf and mute persons to a common man is challenging. The research work proposes to investigate various deep learning models to enhance communication between the deaf and persons who may not know sign language. The work uses computer vision technology for real-time hand gesture identification and natural language processing to produce coherent and understandable words This article investigates the feasibility of applying deep learning techniques like convolutional neural networks, xgboost and random forest to recognize hand gestures in real-time. The models are trained on a dataset of hand gestures and are investigated to identify hand gestures in real-time. The model can recognize a wide range of hand motions, from simple ones like pointing and waving to complex ones involving several fingers. The system creates sentences that are consistent with the hand gesture's intended meaning once it has been identified. Based on established rules and grammar suggestions, the model tries to generate appropriate sentences while taking the context of the conversation into account. The proposed work would be highly beneficial to researchers and target audiences who have trouble expressing themselves in a quick, efficient way to communicate.

关键词： Deep learning Sign language Target recognition Computational modeling Oral communication Real-time systems Natural language processing

来源：评论

学校读者我要写书评

暂无评论

An efficient deep learning with a big data-based cotton plant monitoring system

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 145-151页

作者： Stephen, Ancy Arumugam, Punitha Arumugam, Chandrasekar Department of Artificial Intelligence and Machine Learning St. Joseph’s College of Engineering OMR Kamaraj Nagar Semmancheri Tamil Nadu Chennai India Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram India Department of Computer Science and Engineering St. Joseph’s College of Engineering OMR Kamaraj Nagar Semmancheri Tamil Nadu Chennai 600119 India

In Agriculture, plant monitoring plays an important role from seedling to harvesting which helps farmers achieve a good yield. This paper focuses on building bigdata based cotton plant monitoring system. To build this system, the plant images are collected from the agricultural field with an Android mobile App. The collected data are labeled using a web-based feature labeling application. After applying the pre-trained Deep-learning (DL) classification algorithm to the labeled images, the farmers benefited from the subsequent information. This paper discusses different pre-trained Convolutional Neural Network (CNN) architectures such as ResNet18, GoogLeNet, InceptionV3, and MobileNetV3 Large used to monitor the health of the cotton plant. In plant health monitoring, the classification and identification accuracy are improved with better feature extraction. In comparison with other methods employed in this paper, MobileNetV3Large provides high accuracy. The proposed model classifies 11 different cotton plant regions which are boll, bud, crown, flower, land, leaf, stem, unhealthy leaf, weed, young boll, and young leaf. The MobileNetV3Large model offers an accuracy, specificity, and precision value of 93.9%, 96.12%, and 97.48% when evaluated using the images obtained from smartphones. The smart application developed also provides information to the framers regarding harvesting and yield. The proposed model is determined in real-world applications to identify whether a plant sprouted is a cotton plant or a weed. Next, it can also identify the health condition of the cotton plant and can predict the type of disease identified. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Cotton plant image Deep learning Labelling Plant monitoring

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep learning Cloud Intrusion Detection

Hybrid Deep Learning Cloud Intrusion Detection

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： Lokanayaki Karnan S. B. Mahalakshmi Thirunavukkarasu V Department of Computer Science Christ University Bangalore Karnataka India Department of Artificial Intelligence & Machine Learning Coimbatore Institute of Technology Coimbatore Tamil Nadu

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

The scalability and flexibility that cloud computing provides, organisations can readily adapt their resources to meet demand without having to make significant upfront expenditures in hardware infrastructure. Three main types of computing services are provided to people worldwide via the Internet. Increased performance and resource access are two benefits that come with using cloud computing, but there is also an increased chance of attack. As a result of this research, intrusion detection systems that can process massive amounts of data packets, analyse them, and produce reports using knowledge and behaviour analysis were created. Convolution Neural Network Algorithm encrypts data as it's being transmitted end-to-end and is stored in the cloud, providing an extra degree of security. Data protection in the cloud is improved by intrusion detection. This study uses a model to show how data is encrypted and decrypted, of an algorithm and describes the defences against attacks. When assessing the performance of the suggested system, it's critical to consider the time and memory needed to encrypt and decrypt big text files. Additionally, the security of the cloud has been investigated and contrasted with various encoding techniques now in use.

关键词： Cloud computing Scalability Neural networks Intrusion detection Signal processing algorithms Authentication Hardware

来源：评论

学校读者我要写书评

暂无评论

A Vision Based Approach for Real Time Detection of Proximity Hazards around Open Wells: An Application in Open Well Safety Monitoring

A Vision Based Approach for Real Time Detection of Proximity...

引用

Engineering Informatics, IEEE

作者： Aravind Naik Sandeep Bhat Daya Naik Department of Computer Science and Engg Srinivas Institute of Technology Mangaluru India Department of Artificial Intelligence and Machine Learning Srinivas Institute of Technology Mangaluru India

ISBN: (数字)9798331505776

ISBN: (纸本)9798331505783

Open wells are a major hazard in India’s rural and urban settings, especially for youngsters and unwary adults. The absence of safety barriers surrounding wells frequently causes mishaps, which can occasionally be fatal. This study suggests a brand-new, reasonably priced, vision-based solution that uses a CCTV camera to identify people approaching a well and sound an alarm when they get too close. The system draws boundary boxes and determines the distance between the well and the person using object detection methods to precisely detect and classify both. Accidents may be avoided if an automated alert is set off if the distance between the person and the well drops below a certain level. This method is trained using custom YOLOv8 models for well detection and a pre trained model for person detection. This paper emphasizes the system’s importance in the context of countries like India, where safety infrastructure around wells is often insufficient, and accidental falls are a common hazard.

关键词： machine vision Object detection Cameras Hazards Real-time systems Informatics Monitoring Accidents

来源：评论

学校读者我要写书评

暂无评论

FSRT: Facial Scene Representation Transformer for Face Reenactment from Factorized Appearance, Head-pose, and Facial Expression Features

arXiv

引用

arXiv 2024年

作者： Rochow, Andre Schwarz, Max Behnke, Sven Autonomous Intelligent Systems - Computer Science Institute VI and Center for Robotics University of Bonn Germany Lamarr Institute for Machine Learning and Artificial Intelligence Germany

The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image, which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame, which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder, which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance, head pose, and facial expressions. Thus, they are perfectly suited for cross-reenactment. In contrast to most related work, our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.1 Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Weed plant in Farm and Removing using Unmanned Ground Vehicle 7

Detection of Weed plant in Farm and Removing using Unmanned ...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Sandeep Telkar, R. Yakkundimath, Rajesh Thomas, Likewin Kl, Thara Shivamogga and Visvesveraya Technological University Pes Institute of Technology and Management Department of Artificial Intelligence & Machine Learning Karnataka Belagavi590018 India Hubbali and Visvesveraya Technological University Kle Institute of Technology Department of Computer Science & Engineering Karnataka Belagavi590018 India

ISBN: (纸本)9798350341485

India's agriculture sector has contributed greatly to the country's economic expansion. Therefore, reducing expenses and raising crop productivity are essential. In a country like India, where there are hundreds of fields, weeds are always growing there. Weeds and crops fight for space, water, food, nutrients, and other resources, which reduces agricultural output. Currently, one of agriculture's most difficult duties is weed control. Herbicide hand spraying is one of the most popular weed management techniques. However, this strategy has a number of shortcomings. Because manual labor is costly, an automated weed management system may be economically viable. There is currently no technology available that can be utilized in the field in real time to autonomously control in-row weeds, despite repeated attempts. Weed control has become more important as food grain production has increased per person. The suggested system makes an effort to provide a robotic, computer vision-based Unmanned Ground Vehicle (UGV) for real-time weed management in row crops in order to address the aforementioned issues. This tool can recognize weeds and remove them gently without endangering the environment. It would be ideal to achieve crop contact without the involvement of humans using IoT, machine learning, and picture analysis. © 2023 IEEE.

关键词： Ground vehicles

来源：评论

学校读者我要写书评

暂无评论

Deep learning-Based Dynamic Scheduling for Semiconductor Manufacturing with High Uncertainty of Automated Material Handling System Capability 2

Deep Learning-Based Dynamic Scheduling for Semiconductor Man...

引用

2nd International Conference on Data science and Information System, ICDSIS 2024

作者： Dineshkumar, R. Al-Attabi, Kassem Kumar, Komuravelly Sudheer Madhura, G.K. Sharma, Jaya Saveetha Institute Of Medical And Technical Sciences Saveetha University Saveetha School Of Engineering Department Of Ece Chennai India The Islamic University College Of Technical Engineering Department Of Computers Techniques Engineering Najaf Iraq Sr University School Of Computer Science & Artificial Intelligence Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Artificial Intelligence And Machine Learning Bengaluru India Gitam University Department Of Cse Bengaluru India

ISBN: (纸本)9798350381665

To improve the dynamic responsiveness and production efficiency of manufacturing workshops to personalized orders, a multi-agent manufacturing system. However, the previous methods cannot work well in a changeable workshop environment when encountering a large number of stochastic disturbances of orders and resources. Develop a robust scheduling approach for dynamic workshop environments, effectively managing stochastic disturbances in orders and resources to optimize production efficiency and minimize disruptions. Dynamic scheduling approach for semiconductor manufacturing using Proximal Policy Optimization (PPO) and Autoencoder (AE) for feature extraction, defining state space to capture task and production attributes. Action space design employs dispatching rules for operation selection, while the reward function adapts production to demand, trained in action and state phases. Autoencoders compress high-dimensional input data into a lower-dimensional latent space while preserving important features. The obtained results demonstrate that the proposed method achieves better performance Delivery Data Rate (DDR) of 41.20 %, Mean Cycle Time (MCT) of 51.66%, Mean of 12.85%, and Execution time of 5.07s. These results ensure superior dynamic scheduling performance compared to other existing methods, such as Dynamic Scheduling Using Flexible Job Shop Scheduling problem (FJSP), and Multiple-DynamicScheduling-Rule (MDSR). © 2024 IEEE.

关键词： Production efficiency

来源：评论

学校读者我要写书评

暂无评论

An Effective Web Scripting Algorithm for Real Time Data Processing

An Effective Web Scripting Algorithm for Real Time Data Proc...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： Harini. S J. Praveenchandar Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

There are various online web sites available nowadays. People are using online web sites for shopping etc. So take a particular website to scrape the data present in it. Choose *** to fetch the price of the product and display it according to the user's feed. Reach that website and the price of the product may changes according to the seasons, festivals, or some special events. So it fetches the price of the current date and provide it to the user's feed. Additionally, the date and time for the particular product is included. Here BeautifulSoup and pyspark are used. Here they use scraping tactics, specifically, in the realm of online advertising. In order to do this, this study suggests a collaborative filtering-based Web advertising system that makes use of Web scraping to identify the most pertinent ads for a generic Web page. Scrapers are especially interested in converting unstructured material and storing it in organized databases. Web scraping is a software method that gathers data from websites by using appropriate web browsers or low-level Hyper Text Transfer Protocol (HTTP) to mimic human exploration of the World Wide Web 1. It is closely associated with web indexing, which extracts information from the web using bots that have been designed by humans. The primary goal of Web Scraping is to convert unstructured data-typically in HTML format-into structured data that can be stored and handled in a centralized database 1. This technique is frequently utilized for a number of different tasks, including pricing comparison, mashups or mix-ups of webpages, weather prediction information, webpage integration, and webpage interface change detection. Some of the challenges are IP Blocking and Rate limiting, Dynamic content Loading, etc.

关键词： Databases Heuristic algorithms Web pages Weather forecasting Web sites Feeds Data mining

来源：评论

学校读者我要写书评

暂无评论

Detection of pulmonary embolism with improved Xception architecture

Detection of pulmonary embolism with improved Xception archi...

引用

International Conference on AI and the Digital Economy (CADE 2024)

作者： Getzi Jeba Leelipushpam Paulraj P. Joyce Beryl Princess Immanuel Johnraja Jebadurai S. Celshia Division of Computer Science and Engineering Karunya Institute of Technology and Sciences India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences India

ISBN: (数字)9781837241842

The blocking of arteries in the lungs through blood clots is known as pulmonary embolism. This blood vessel block usually originates in the legs and travels to the lungs causing fatal damage. An imaging test called Computed Tomography (CT) pulmonary angiography scans the lungs for blood clots. The preferred method for identifying pulmonary embolism is CT pulmonary angiography. Manual examination by radiologists increases the workload, consumes more time and also requires experience for correct examination. The objective of this paper is to propose an improved Xception architecture based on Convolutional Neural Networks. The existing architecture is improvised by replacing the Relu activation function with the Swish activation function. This improves the feature extraction of the algorithm thereby improving efficiency in terms of loss and accuracy. The algorithm has been trained and tested using the standard RSNA-STR Pulmonary Embolism CT Dataset. It is evident from the experimental results that our model achieves an improvement of 3.4% and 1.4% in terms of accuracy and loss respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Protecting Medical Image Transmission: Color Secret Sharing Protocol for Enhanced Security

Protecting Medical Image Transmission: Color Secret Sharing ...

引用

2024 International Conference on artificial intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Maram, Balajee Sai, Manikonda Srinivasa Sesha Vanniappan, Malathy Srinivas, T. Aditya Sai Nagaraju, Pamarthi Prasan, U.D. School of Computer Science and Artificial Intelligence SR University Telangana Warangal506371 India KKR & KSR Institute of Technology and Sciences Department of Information Technology Guntur India SR University Department of Electronics and Communication Engineering Telengana Warangal India Jayaprakash Naryan College of Engineering Artificial Intelligence and Machine Learning Mahabubnagar India Department of CSE Bhimavaram India Aditya Institute of Technology and Management Andhra Pradesh Tekkali India

ISBN: (纸本)9798331517953

The safety in the transmission of medical images cannot be compromised in the digital age, as the information contained is very sensitive. This paper presents a new approach to providing security for medical image transmission using the Color Secret Sharing protocol. This is ensured by the proposed approach of dividing the medical image into many shares, each of which is encoded with independent color information, to ensure that the restoration of the original image can be done only if all the shares are combined. Thus, the risk related to unauthorized access and data breaching is much reduced during the transmission process. Security analysis and experimental validation are provided that demonstrate that the compared methods tend to efficiently resist attacks. This study embeds CSS into medical imaging systems to solve the secure and trustworthy solution on the confidentiality, integrity, and availability of patient data in healthcare communications. © 2024 IEEE.

关键词： Color Secret Sharing Cryptography Healthcare Data Protection Image Encryption Medical Image Security Secure Transmission

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：