检索结果-内蒙古大学图书馆

Recent Advances in science and engineering technology (ICRASET), International Conference on

作者： Ramakrishna Hegde S Shivashankara S M Soumyasri M T Thirthe Gowda Y N Mahadeva Prasad C S Tejeshwini Computer Science and Engg. Vidyavardaka College of Engineering Affiliated to Visvesvaraya Technological University Mysuru India Computer Science and Engg. KR Pete Krishna Govt. Engg. College Krishnarajapet India Dept. of Computer Applications Vidya Vikas Institute of Engineering and Technology Mysuru India Computer Science and Engineering Government Engineering College Hassan India Dept. of AI and DS MIT Thandavapura Mysuru India Information Science and Engineering Vidya Vikas Institute of Engineering and Technology Mysore India

ISBN: (数字)9798350388602

ISBN: (纸本)9798350388619

Among the nonverbal forms of communication techniques utilized in sign language is hand signals. People who are deaf or hard of hearing or speech frequently utilize it. They struggle to communicate with others or with each other. Numerous manufacturers worldwide have produced a variety of sign language systems, however they are inefficient and incompatible with one another in terms of cost. Our works objective is to develop a deaf communication system. There are two sections to this project. (1)Sign language conversion from the audio messages (2) Converting pictures and videos into speech or text. In the first section we will examine, audio is taken as input, the recorded spoken message is converted into text, and Hindi Sign language graphics or GIFs are displayed. The hearing and the deaf can communicate more easily when this method is used. In the second group, we gather the photographs, use CNN to train them, and display the outcomes.

关键词： Hands Graphics Sign language Translation Databases Auditory system Assistive technologies Real-time systems Usability Videos

来源：评论

学校读者我要写书评

暂无评论

Smart BAT - Smart Budget Analyzer and Tracker

Smart BAT - Smart Budget Analyzer and Tracker

引用

Advanced Computing Technologies and Applications (ICACTA), International Conference on

作者： Sahil Shelke Manish Shingre Sahaya Lebisha Shainila Shaikh Dept. Of Computer Engineering Don Bosco Institute Of Technology Mumbai India

Maintaining your daily expenses manually by entering all the details of the items purchased can often feel like an intimidating task. This research discusses the difficulties in budget tracking and suggests a fresh budget tracking program to simplify difficulties such as maintaining the expenses manually using pen and paper, spreadsheet or a diary. Departing from these traditional manual approaches the authors have proposed an innovative solution for this tedious task. In this research paper, we have proposed an automated system that combines Optical Character Recognition and Machine Learning to tackle the challenges associated with transforming physical bills into digital format. The key feature of the application includes optical character recognition which will scan the bill and extract all the items present on the bill and automatically categorize the items into various categories where the item belongs. The application also provides some additional features such as future expense prediction and a detailed report generation. In this study, authors emphasizes the significance of effective budget tracking in the modern world and offers a creative solution by creating a user-centered budget tracking application. We hope that by meeting the needs of the average customer and providing a flawless experience, our application can considerably enhance people’s financial well-being.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Roads: U-Turn Accident Prevention System

Smart Roads: U-Turn Accident Prevention System

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Neena Johnson J Ancy Jenifer Aanya Khan Akhila Jyothi Dept. of Computer Science and Engineering Karunya Institute Of Technology and Sciences Coimbatore India Karunya Institute Of Technology and Sciences Coimbatore India

When discussing statistics of everyday road accidents in India, a very large contributing factor is accidents in hilly areas due to hairpin bends. These blind turns are highly dangerous and may more often than not result in fatal accidents. The low visibility results in the driver being extremely vulnerable to head-on collisions. Coming up with a preventive measure to this perilous situation is the prime focus of this paper. The proposed system in this paper is to, warn drivers of other vehicles at hairpin curves to avoid accidents involving human lives. This system is designed to allow residents and tourists to drive safely by warning them of blind corners and u-turns and reducing the possibility of accidents. This paper intends to reduce the chances of head-on collisions by implementing an accident prevention system. A prevention system, although new, should be comprehensible for a new user, to solve this issue, an existing system has been integrated with the proposed idea.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ChatGPT: Information Retrieval from Image using Robotic Process Automation and OCR

ChatGPT: Information Retrieval from Image using Robotic Proc...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Ganeshayya Shidaganti R Sanjana K Shubeeksh V.R. Monish Raman Valmeeki Thakshith Dept. of Computer Science and Engineering M.S. Ramaiah Institute of Technology Bangalore Karnataka India

ChatGPT hit 1M users in just 5 days once it went public, the leading companies such as Facebook, Instagram, Spotify, Netflix took several months to years to achieve this mark. As a result of the conversational AI Chabot being hailed as a technological revolution, ChatGPT has emerged as one of the year’s most popular buzzwords. This research study intends to initiate interaction with ChatGPT more convenient to users by using user sent WhatsApp images containing text as input by converting it into text-based prompt which is accepted by ChatGPT and provide the user with the response generated by ChatGPT. This is achieved by integrating RPA to automate an in-dept. examination of images for information discovery using OCR to extract text and ChatGpt to retrieve information. This research study also focuses on providing a quick response to the user by comparing images with previous users’ inputs and sending the same response in case there is repetition of images which increases efficiency in terms of computation resources too. The proposed solution is designed to provide a quick suitable response to the user inscribed text in the image.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Whale Optimization Algorithm and Optimized Long Short-Term Memory for DDoS Cyber Security Threat 3

Improved Whale Optimization Algorithm and Optimized Long Sho...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pillai, Sanjaikanth E. Vadakkethil Somanathan Polimetla, Kiran Velpula, Srikanth Kumar Pareek, Piyush Sontakke, Dipti School Of Electrical Engineering And Computer Science University Of North Dakota Grand Forks United States Adobe Inc Dept. Of Information Technology AustinTX United States Sr University Department Of Electrical And Electronics Engineering Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml And Ipr Cell Bengaluru India Capgemini Inc United States

ISBN: (纸本)9798350318609

The Distributed Denial of Service (DDoS) attacks is a critical cyber security threat that blocks the services for users and leads to important damage for reputation and effective customers. The existing methods provides low classification accuracy due to irrelevant features in classification performance. The Improved Whale Optimization Algorithm (IWOA) is proposed for the selecting of relevant features which improved the classification performance. The selected features are detected and classified by Optimized Long Short-Term Memory (OLSTM) that provided high detection rate of DDoS attacks. The one-hot encoding and min-max normalization techniques are used in the data pre-processing stage to improve the performance of classification. The CIC-DDoS 2019 dataset are used for evaluating the proposed method. The IWOA-OLSTM method attained highest accuracy 97.12%, precision 96.74%, recall 96.27%. f1-score 96.54% and DR 93.26% on CIC-DDoS 2019 dataset which is effective than Convolutional Neural Network (CNN) - Bidirectional Long Short-Term Memory (BiLSTM) and CNN-LSTM. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Rethinking Functional Brain Connectome Analysis: Do Graph Deep Learning Models Help?

arXiv

引用

arXiv 2025年

作者： Han, Keqi Su, Yao He, Lifang Zhan, Liang Plis, Sergey Calhoun, Vince Yang, Carl Dept. of Computer Science Emory University AtlantaGA United States Dept. of Computer Science Worcester Polytechnic Institute WorcesterMA United States Dept. of Computer Science and Engineering Lehigh University BethlehemPA United States Dept. of Electrical and Computer Engineering Univ. of Pittsburgh PittsburghPA United States TReNDS Center GSU Georgia Tech Emory University AtlantaGA United States

Functional brain connectome is crucial for deciphering the neural mechanisms underlying cognitive functions and neurological disorders. Graph deep learning models have recently gained tremendous popularity in this field. However, their actual effectiveness in modeling the brain connectome remains unclear. In this study, we re-examine graph deep learning models based on four large-scale neuroimaging studies encompassing diverse cognitive and clinical outcomes. Surprisingly, we find that the message aggregation mechanism, a hallmark of graph deep learning models, does not help with predictive performance as typically assumed, but rather consistently degrades it. To address this issue, we propose a hybrid model combining a linear model with a graph attention network through dual pathways, achieving robust predictions and enhanced interpretability by revealing both localized and global neural connectivity patterns. Our findings urge caution in adopting complex deep learning models for functional brain connectome analysis, emphasizing the need for rigorous experimental designs to establish tangible performance gains and perhaps more importantly, to pursue improvements in model interpretability. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cancer Detection System

Intelligent Cancer Detection System

引用

2021 International Conference on Intelligent Technologies, CONIT 2021

作者： Das, Utpol Kanti Sikder, Juel Salma, Umme Anwar, A M Shahed Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati Bangladesh Bangladesh University Dept. of Computer Science and Engineering Dhaka Bangladesh Rangamati Science and Technology University Dept. of IT Section Rangamati Bangladesh

ISBN: (纸本)9781728185835

Histopathology and MRI produce different types of images and a single procedure to detect cancerous cells from both of them is considered tedious and time-consuming. Therefore, this study proposes a strategy that can perform segmentation, classification and detection over numerous categories of cancer cells. This experimentation demands the preprocessing to intensify the cells' pictorial characteristic and to segment the intended cancerous cell k-means algorithm applied. The Convolutional Neural Network (CNN) classifier being considered as the best method classifying the test image using the feature extraction method on the filtered cell. Considering the system detects cancer, different morphological operations are applied on the extracted cancer region, and finally, we calculated the percentage of the cancerous area. The MATLAB environment has been used on Histopathology and MRI images of the infected cell from various authentic datasets of various cancers mainly Brain, Breast, Leukemia and Lung cancer. The proposed arrangements of methods give improved accuracy as compared to the other existing methods. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Study on Classification of Desiccated Fruits Using Transfer Learning Models

A Comprehensive Study on Classification of Desiccated Fruits...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： Asha Gowda Karegowda Virupakshaiah H K Poornima D Leena Rani A Dept of MCA Siddaganga Institute of Technology Tumkur Karnataka Dept. of Computer Science. MS Ramaiah College of Arts Science & Commerce Banglore Karnataka Dept of Computer Science Seshadripuram College Tumkur Karnataka

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Desiccated fruit and nuts are super foods that are superior to other foods. It provides a lot of vitality in the form of nutrients, vitamins, minerals, and proteins in even tiny quantities and also boosts our immunity. Desiccated fruit has been highly prized for its sweet flavor, nutritional content and prolonged shelf life. Primary dataset are used, contains 2000 images of 9 types. Five transfer learning techniques were used to address this issue as well as to reduce training time and increase classification performance. Desiccated fruit are categorised using VGG16, Xception, MobileNet, InceptionV3, and InceptionResnet. Results are compared with Convolutional Neural Network (CNN) basic model. The MobileNet model beat all other pre-trained models in terms of accuracy, achieving 99.42 % and 100 % training and validation with only 5 epochs. VGG16 also resulted in similar accuracy with a thin difference of less than 0.06 accuracy.

关键词： Training Proteins Accuracy Transfer learning Process control Quality control Smart systems Robustness Convolutional neural networks Sorting

来源：评论

学校读者我要写书评

暂无评论

Implications of continual learning for lesion of the skin categorizing and detection

Implications of continual learning for lesion of the skin ca...

引用

Advances in Computational Intelligence and Communication (ICACIC), International Conference on

作者： V.Auxilia Osvin Nancy V Rajasekar Meenakshi S Arya Dept. of Computer Science and Engineering College of Engineering and Technology SRM Institute of science and Technology Chennai India Institute of Transportation IOWA state University United States

Development of techniques that can gradually learn from new samples is now important due to the growing number of data. Training a network with new data poses challenges, including the phenomenon known as "catastrophic forgetting." This occurs when a network's performance on previously learned data drops as it tries to learn from new instances. To address the issue of catastrophic forgetting, the article includes a powerful approach known as experience replay. Investigations are conducted on different datasets to analyze the impact of catastrophic forgetting. The technique is compared against various approaches, including individual training, mutual training, and fine-tuning. When compared to the fine-tuning approach, the model using experience replay retains knowledge from the previous dataset, leading to a 13% increase in accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Textual Video Summaries using Modified Bi-Modal Transformer and Whisper Model

Generating Textual Video Summaries using Modified Bi-Modal T...

引用

Advanced Computing Technologies and Applications (ICACTA), International Conference on

作者： Siddhesh Madkaikar Vipul Belhekar Yash Dharmadhikari Amiya Kumar Tripathy Dept. Of Computer Engineering Don Bosco Institute Of Technology Mumbai India

Online video material availability has grown significantly over the past few years, making it challenging for viewers to consume and process information effectively. Video summaries written in text form have shown to be a helpful technique for solving this problem. The key aspects of a video can be accurately and briefly summarised by utilizing methods like video summarising and natural language processing. The purpose of the model is to display a short textual summary of the video to the user before the user watches the complete video. It is frequently difficult and time-consuming for students to locate a suitable educational video. It is occasionally seen on video streaming platforms such as YouTube that the title and the content of the video are not precisely the same. So the model will generate a textual summary of the video and the user can read the summary and get to know about the content of the video. Also, this approach to summarizing videos is helpful in other tasks like video content moderation and could also enable visually-impaired people to consume video material and improve their quality of life.

关键词：

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：