检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Manikanta, K. Lavanya Shyam, N. Saraswathi, S. Sathyabama Institute Of Science And Technology Department Of Computer Science And Engineering India Sathyabama Institute Of Science And Technology India

ISBN: (纸本)9798350364828

To bridge the communication gap between deaf people and non-sign language users, the research project Real-Time Hand Gesture Recognition and Sentence Generation for Deaf and Non-Verbal Communication was created. The proposed system makes use of computer vision technology for real-time hand gesture identification and natural language processing to produce coherent and understandable words. In order to recognize hand gestures in real-time, the study employs deep learning techniques like convolutional neural networks (CNNs) and recurrent neural networks (RNNs). These models are trained on a dataset of hand gestures and are able to accurately classify different hand gestures in real-time. The system 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. Natural language processing techniques are utilized to convert the recognized hand signal into understandable speech. Based on established rules and grammar suggestions, the program generates appropriate sentences while taking the context of the conversation into account. The proposed device may change communication for nonverbal and deaf individuals who have trouble expressing themselves. It gives these populations and the rest of society a quick, efficient way to communicate. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Large Language Model Based Document Query Solution Using Vector Databases

Large Language Model Based Document Query Solution Using Vec...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Rochan, A. Sowmya, P. Daniel, D. Anand Joseph Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

The world is moving towards a digital landscape where industries are starting to face great challenges in managing and extracting meaningful insights from vast volumes of unstructured data contained in documents such as PDFs, EPUBs and many more. Leveraging the advancements in Large Language Models, this paper presents a helpful approach to address the challenge using a document query solution using LLMs and the efficiency of vector databases. The proposed system presents a way for users to interact with documents and converse with it, allowing users to draw insights and information from the document in a new light and in a new way, facilitating intuitive interaction and information extraction for employees of companies across various industries. The system makes use of LLMs capabilities to interpret and generate responses similar to humans, while vector databases provide efficient data storage and retrieval. This integration enables users to extract insights and information from documents in novel ways, transforming data-driven decision-making processes. By delivering a more intuitive and appealing approach to interact with documents, the proposed approach has the potential to significantly enhance the productivity and effectiveness of data-driven decision-making processes, ultimately boosting innovation and growth across industries. © 2024 IEEE.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Transparency and Trust in Organ Donation through Blockchain technology 7

Transparency and Trust in Organ Donation through Blockchain ...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Bharti, Anshika Kumari, Megha Jacob, T. Prem Sathyabama Institute of Science And Technology Department of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350359299

This research investigates the transformative potential of blockchain technology in addressing the ethical challenge surrounding organ donation. The scarcity of transplantable organs underscores the need for innovative solutions that improve transparency and trust in the organ allocation process. This article investigates the potential of blockchain technology for increasing transparency and confidence in the organ donation process. Transparency, performance, reliability, security, tracking and traceability, and encryption processes are all key areas of concern. In addition, the book is language-edited to improve clarity and remove personal pronouns. Furthermore, this study tackles security issues by giving verifiable proof and covers the important blockchain principles that reduce security risks. It also elaborates on how blockchain ensures data security and immutability, as well as a conceptual examination of research gaps and potential remedies. Finally, this research study develops a clear problem description to assist the investigation. This research involves a comprehensive literature review to analyze current obstacles and moral issues in organ donation. This study investigates existing applications of blockchain in healthcare and adapt insights to propose a conceptual framework for organ donation systems. This study critically examines the potential benefits, risks, and ethical implications of integrating blockchain technology into organ transplantation processes. © 2024 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

An Efficient Unsupervised Learning Approach for Detecting Anomaly in Cloud

引用

computer Systems science & engineering 2023年第4期45卷 149-166页

作者： P.Sherubha S.P.Sasirekha A.Dinesh Kumar Anguraj J.Vakula Rani Raju Anitha S.Phani Praveen R.Hariharan Krishnan Department of Information Technology Karpagam College of EngineeringCoimbatoreTamilnaduIndia Department of Computer Science and Engineering Karpagam Academy of Higher EducationCoimbatoreTamilnaduIndia Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationAndhra PradeshIndia Department of MCA CMR Institute of TechnologyBengaluruKarnatakaIndia Department of Computer Science and Engineering Prasad V.Potluri Siddhartha Institute of TechnologyAndhra PradeshIndia Department of Computer Science and Engineering Residency CollegeChennaiIndia

The Cloud system shows its growing functionalities in various industrial *** safety towards data transfer seems to be a threat where Network Intrusion Detection System(NIDS)is measured as an essential element to fulfill ***,Machine Learning(ML)approaches have been used for the construction of intellectual *** IDS are based on ML techniques either as unsupervised or *** supervised learning,NIDS is based on labeled data where it reduces the efficiency of the reduced model to identify attack ***,the unsupervised model fails to provide a satisfactory ***,to boost the functionality of unsupervised learning,an effectual auto-encoder is applied for feature selection to select good ***,the Naïve Bayes classifier is used for classification *** approach exposes the finest generalization ability to train the *** unlabelled data is also used for adoption towards data ***,redundant and noisy samples over the dataset are *** validate the robustness and efficiency of NIDS,the anticipated model is tested over the NSL-KDD *** experimental outcomes demonstrate that the anticipated approach attains superior accuracy with 93%,which is higher compared to J48,AB tree,Random Forest(RF),Regression Tree(RT),Multi-Layer Perceptrons(MLP),Support Vector Machine(SVM),and ***,False Alarm Rate(FAR)and True Positive Rate(TPR)of Naive Bayes(NB)is 0.3 and 0.99,*** compared to prevailing techniques,the anticipated approach also delivers promising outcomes.

关键词： Network intrusion detection system feature selection auto-encoder support vector machine(SVM) anomaly

来源：评论

学校读者我要写书评

暂无评论

A Deep-Siamese CNN-based Approach for Identifying Mycosphaerella Coffeeicola Disease in Coffee Foliage 8

A Deep-Siamese CNN-based Approach for Identifying Mycosphaer...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Selvanarayanan, Raveena Rajendran, Surendran Jayaraman, Venkatesh Sathish Kumar, P.J. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350367904

Mycosphaerella Coffeeicola (Black Spot Disease) is the most destructive disease in coffee leaves and affects global production. Diseased coffee leaves can adversely affect coffee quality, discolor, distort, or rot the coffee leaves, and impair the coffee beans' cherry, taste, and aroma. The disease can also affect the quality of the coffee beans, leading to lower market value. The management of the Coffee Production department of India controls the disease through a combination of cultural practices, chemical control, and the use of resistant coffee varieties. In the existing work, using single-layer perceptron was trained and validated with 100 epochs to obtain an accuracy of 9 5. 7 1 %. In the piece above of work, an infected leaf is accurately diagnosed using deep learning-based models by employing the Deep-Siamese-based CNN Approach, recognized by a deep Siamese Neural network architecture which is also called a Twin Neural network with high illness recognition precision and simplified hyper-parameters to maximize description capacity while avoiding overfitting concerns, using a network with high sickness detection precision and minimal hyper-parameters. The prototype was tested in the lab on natural plants for known sickness instances, and the results matched the model validation datasets. When compared to several deep-learning models, the suggested structure attained an accuracy of 9 6. 8 9 %. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing CCTV Violence Detection: A Comparative Study of Deep Learning Models for Violence Detection in Surveillance Videos 8

Enhancing CCTV Violence Detection: A Comparative Study of De...

引用

8th IEEE International Conference on Information and Communication technology, CICT 2024

作者： Rodrigues, Kenneth Dsouza, Glen Phansopkar, Omkar Bide, Pramod Sardar Patel Institute of Technology Department of Computer Science and Engineering Mumbai India Sardar Patel Institute of Technology Department of Computer Engineering Mumbai India

ISBN: (纸本)9798331531539

With the large number of CCTV cameras located worldwide, ensuring people's safety has become much easier. Despite this, it is impossible to keep track of 100s of CCTV cameras simultaneously. Therefore, deep learning methods of violence detection from surveillance footage have been proposed to reduce human intervention. This solution presents a comparison of the performance of three-dimensional (3D) Convolutional Neural Networks (CNNs), VGG networks, and MobileNet models combined with Long Short-Term Memory (LSTM) units and Multi-Stream Networks to detect violence in CCTV video footage, providing a comprehensive analysis of these models based on accuracy, hardware requirements, and other performance metrics essential to real-world applications. The majority of the existing systems are trained on violent footage from sports or movies, the models in this solution are trained on a combination of datasets consisting of CCTV footage which provides an accurate representation of real-world surveillance footage, thus improving model accuracy. Existing research does not study the effect of combining very deep CNN models like VGG with advanced techniques like multi-stream models. This solution explores the impact of integrating such models to create a more robust solution. All the models proposed and evaluated have produced accurate results and are capable of identifying violence based on surveillance footage, with an accuracy of up to 98.46%. Unlike other solutions that do not take into account the memory and prediction time of different models, this solution identifies the ideal model depending on the available resources and infrastructure, helping make a decision based on real-world requirements. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Real Time Medicinal Plant Identification & Classification Using Random Forest Algorithm 10

Real Time Medicinal Plant Identification & Classification Us...

引用

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

作者： Nidhya, R. Imambee, K. Geethanjali, M. Anusha, M. Lakshmi Vyshnavi, I. Madanapalle Institute of Technology & Science Department of Computer Science & Engineering Angallu India

ISBN: (纸本)9798350353068

In recognition of their therapeutic qualities, medicinal plants have been used for millennia, greatly influencing traditional medical systems all over the world. But classifying and identifying these plant species by hand can be laborious and prone to mistakes. In this study, we suggest a unique method for identifying and detecting species of medicinal plants using machine learning techniques specifically, Random Forest. As part of the method we used, we gathered a broad dataset with pictures of eighty distinct kinds of medicinal plants. Preprocessing methods are used to standardize characteristics and improve image quality. Next, the Random Forest method is used for classification, taking advantage of its capacity to manage intricate datasets and yield comprehensible outcomes. The outcomes of the experiments show how well the suggested method works for correctly identifying and identifying medicinal plant species. The model demonstrates its promise for practical applications in domains including pharmacology, botany, and traditional medicine by achieving a high level of classification accuracy of 98%. Additionally, because of the Random Forest algorithm's interpretability, researchers may get insights into the factors that influence categorization judgments, which helps them better understand the traits that set distinct plant species apart. © 2024 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Segmenting Stenotic Regions from Coronary Angiograms using Mask Region-based Convolutional Neural Network 5

Segmenting Stenotic Regions from Coronary Angiograms using M...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Velvizhi, R. Ankayarkanni, B. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350389609

Coronary artery disease (CAD) is the primary cause of mortality and a key driver of healthcare expenses globally. Accurately segmenting stenotic regions from coronary angiograms is decisive in identifying and treating cardiovascular diseases. However, it is a challenging task for medical professionals to use X-ray Coronary Angiogram (XCA) due to the reduced signal quality, the existence of obstructive contextual elements, and various types of noise. Furthermore, handcrafted segmentation is arduous, laborious, and prone to inconsistencies and human errors. In this context, this research aim to develop an automatic stenosis segmentation system using a deep network. Initially, the input image is processed by Gaussian filters and the improved angiogram is filtered by Hessian-based Vessel Filtering (HVF) technique to increase the clarity of vascular components in the angiogram images. This study identifies the branch points (BP) in the angiograms based on the eigenvalues of the Hessian matrix. The proposed model employ a Mask Region-based Convolutional Neural Network (Mask R-CNN) to provide precise pixel-wise masks for every detected stenosis. The proposed Mask R-CNN includes (i) ResNet50 as the backbone network to extract significant attributes;(ii) Region Proposal Network (RPN) to identify possible Regions of Interest (RoIs) that may have stenosis;(iii) RoI Align to ensure precise alignment of the RoIs for improved mask prediction;and (iv) a mask branch to create a pixel-level segmentation mask for each RoI. The effectiveness of the model is assessed by applying an open-access ARCADE Phase 1 (Automatic Region-based CAD diagnostics using XCA images) dataset. The Mask R-CNN model achieves better results with 97.8% dice score, 92.9% sensitivity, and 96.6% specificity. Besides, it provides reduced standard deviation (SD) in the segmentation task with a 0.8% dice score, 1.0% sensitivity, and 1.0% specificity. These results shows that the Mask R-CNN model provides more relia

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Classification Using CT Scan Images Through Deep Learning And CNN Based Model

Lung Cancer Classification Using CT Scan Images Through Deep...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Karthikeyan, Nithesh Kumar Ali, Sharuksha Syed Vishnu Sekhar, R. Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

Lung cancer stands as a formidable and prevalent threat, necessitating urgent attention to early diagnosis and precise treatment to mitigate its high fatality rates. In this context, the utilization of computed tomography (CT) scans, particularly in conjunction with advanced deep learning algorithms, emerges as a powerful strategy for effective lung cancer identification. This study introduces a specialized Convolutional Neural Network (CNN) framework meticulously designed for the early detection of lung cancer through the analysis of CT scan images. Through rigorous comparative analyses with alternative models, our research highlights the CNN's superior performance, marking a substantial improvement over conventional diagnostic technique. The results accentuate the efficacy of our proposed deep learning model, solidifying its position as a more robust and potent diagnostic tool compared to prevailing approaches for the early identification of lung cancer. Future research avenues may explore the integration of larger and more diverse datasets, ensuring the model's robustness and applicability across varied clinical scenarios, ultimately advancing the landscape of lung cancer diagnostics towards improved patient outcomes and healthcare practices. © 2024 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Access Control in E Health Care Records Employing Mobile Cloud Computing Model and Big Data Analytics 1

Access Control in E Health Care Records Employing Mobile Clo...

引用

1st IEEE International Conference on Computing and Data science, ICCDS 2024

作者： Saisree, Yerramaddu Lalitha, Nomula Reddy Felix, A. Yovan Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365337

Cloud service providers are currently storing large volumes of data on cloud. This requires verification mechanisms often employing cryptography by third party auditors. However, ensuring the security and privacy of e-health systems poses a significant challenge. To overcome this challenge, researchers are focusing on building a robust public auditing system. This privacy preserving protocol focuses on privacy preservation allowing third party auditors to evaluate out sourced data without accessing the content. The key to this approach is implementation of batch auditing that enables simultaneous tasks to be processed by trusted third party auditors. The proposed system provides scalable, flexible and efficient public auditing capabilities enhancing the levels of security of e-healthcare systems. The external auditors promote trust and privacy in cloud-based healthcare systems. The integration of mobile devices and cloud computing provides a vast range of opportunities for healthcare management. This innovation provides a way to meet the evolving changes of cloud-based healthcare data management. © 2024 IEEE.

关键词： Mobile cloud computing

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：