检索结果-内蒙古大学图书馆

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： Karnam Akhil Tamma Bhuwan Vamsi Somaram Soujanya Kambhampati Kodanda Sai Harshitha Miryala Mounisha Nimma Srihitha Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad India Associate Software Engineer ServiceNow Hyderabad India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Today’s world data is about 80-90% unstructured, which makes it very complex to analyze, interpret and understand. Meaningful insights, patterns are hidden in the data, discovering knowledge and converting to structured form is important. It is also important to interpret in various forms and process the data. In this paper, we have presented an overview which includes various texts, their representation formats and finds Natural Language Processing (NLP), an essential component for interpreting the unstructured form. NLP components including its history, components, architecture, and challenges are well illustrated. Presented Research dives the evolution of NLP from rule-based systems to modern Deep Learning (DL) approaches. Key features and characteristics such as Natural Language Understanding (NLU), Natural Language Generation (NLG), and machine translation are discussed. The architectural framework of NLP systems is presented, furthermore, we address research and industrial challenges in NLP, emphasizing the need for robust methodologies, domain-specific changes, and ethical considerations.

关键词： Deep learning Ethics Component architectures Natural language generation Government Natural language processing Machine translation History

来源：评论

学校读者我要写书评

暂无评论

Color-Based Auto-Rickshaw Detection Using Convolutional Neural Networks for Intelligent Transportation Systems

Color-Based Auto-Rickshaw Detection Using Convolutional Neur...

引用

Information and Communication Technology (ICICT), International Conference on

作者： Md. Mehedi Hasan Nakib Aman Md Wadud Jahan Software Engineer I Developer Experience Hub Rajshahi Bangladesh Department of Computer Science and Engineering Pabna University of Science and Technology Pabna Bangladesh Department of Computer Science and Engineering Varendra University Rajshahi Bangladesh

ISBN: (数字)9798331508227

ISBN: (纸本)9798331508234

The investigation in this paper is centered on a new methodology for improving the effectiveness of intelligent transportation systems by identifying and distinguishing auto-rickshaws using Convolutional Neural Networks (CNN). The strategy proposed involves training a CNN model to automatically recognize and differentiate the colors of auto-rickshaws, which in turn significantly enhances the detection capabilities. Using hierarchical convolution feature models, the CNN algorithm independently extracts relevant features from images, thereby aiding in precise object detection. An assessment of the model's performance is conducted using a carefully selected dataset containing 1000 auto-rickshaw images, illustrating a high level of accuracy with minimal margin of error. This research makes a valuable contribution to the advancement of automated transport detection within the realm of traffic management. It presents a more streamlined and impactful methodology aimed at improving the overall efficiency and reliability of the system.

关键词： Training Accuracy Image color analysis Semantic segmentation Urban areas Transportation Streaming media Feature extraction Convolutional neural networks Reliability

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach to Identify Stroke based on Real-time Medical Data 1

A Comprehensive Approach to Identify Stroke based on Real-ti...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Maragatharajan, M. Shanmugapriya, S. Sudhan, M.B. Deeptha, R. Paramasivam, Sankar Muthu Vit Bhopal University School of Computing Science and Engineering Madhya Pradesh Kothrikalan India Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamilnadu Srivilliputhur India Srm Institute of Science and Technology Department of Computer Science and Engineering RamapuramTamilnadu Chennai India Srm Institute of Science and Technology Department of Information Technology RamapuramTamilnadu Chennai India Palo Alto Networks Inc Distinguished Software Engineer 3000 Tannery Way Santa ClaraCA United States

ISBN: (纸本)9798350372748

Strokes or cardiovascular disorders continue to be a major global health concern. Proactive intervention and timely detection greatly reduce the morbidity and death related to strokes. The goal of this research is to build a prediction model using machine learning techniques to assess a person's risk of stroke based on a variety of sociodemographic and health characteristics. The dataset used in this study consists of a large collection of medical records. It contains important details including age, gender, BMI, smoking habits, heart disease, hypertension, and the type of residential property. Using this information, a Decision Tree Classifier is trained to predict the likelihood of strokes, enabling early detection and customized treatment plans. A Decision Tree Classifier with a predetermined maximum depth is used in the proposed methodology's rigorous data preprocessing, which includes handling missing values, encoding categorical features, and developing models. Both the training and testing datasets are used to evaluate the model's performance using evaluation measures including accuracy, precision, and recall. The model's insights provide important characteristics that influence the prediction of stroke risk, assisting medical professionals in focused risk assessment and preventive intervention. The proposed method has the potential to improve healthcare practices by facilitating prompt interventions and personalized treatment for stroke risk individuals. The proposed model has resulted in 86.78% accuracy for this dataset by using the traditional machine learning algorithms. This work highlights the value of predictive modelling in the healthcare industry by demonstrating how it may improve early detection techniques and lessen the impact of strokes on public health. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Permutation Invariant Training for Paraphrase Identification 48

Permutation Invariant Training for Paraphrase Identification

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Bai, Jun Yin, Chuantao Hong, Hanhua Zhang, Jianfei Li, Chen Wang, Yanmeng Rong, Wenge Beihang University State Key Laboratory of Software Development Environment Beijing China Beihang University School of Computer Science and Engineering Beijing China Beihang University Sino-French Engineer School Beijing China Ping An Technology Beijing China

ISBN: (纸本)9781728163277

Identifying sentences sharing similar meanings is crucial to speech and text understandings. Although currently popular cross-encoder solutions with pre-trained language models as backbone have achieved remarkable performance, they suffer from the lack of the permutation invariance or symmetry that is one of the most important inductive biases to such task. To alleviate this issue, in this research we propose a permutation invariant training framework, in which a symmetry regularization is introduced during training that forces the model to produce the same predictions for input sentence pairs in both forward and backward directions. Empirical studies exhibit improved performance over competitive baselines. © 2023 IEEE.

关键词： Paraphrase Identification Permutation Invariance Symmetry Regularization

来源：评论

学校读者我要写书评

暂无评论

EfficientNet B7 based Deep Learning Technique for Adaptive Gait Recognition under Challenging Covariate Conditions

EfficientNet B7 based Deep Learning Technique for Adaptive G...

引用

Recent Progresses in science, engineering and Technology (ICRPSET), International Conference on

ISBN: (数字)9798331509477

ISBN: (纸本)9798331509484

Gait recognition is a crucial biometric tool for surveillance and security, but its effectiveness is hindered by factors like clothing, carried obj ects, and environmental conditions. This study introduces an adaptive framework that assigns weights to gait components to counter these issues. Using EfficientNet_B7, a deep learning technique, the framework reduces intra-class variations and improves recognition accuracy. The experimental results show a 98.7% accuracy rate, proving the method's robustness in various conditions. This advancement significantly enhances the reliability of gait recognition systems in real-world applications.

关键词： Deep learning YOLO Heart Adaptation models Accuracy Surveillance Clothing Robustness Security Gait recognition

来源：评论

学校读者我要写书评

暂无评论

A Framework Design of ML Classifier Algorithm for Retrieve the Information about the Drugs and its Quality 4

A Framework Design of ML Classifier Algorithm for Retrieve t...

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Meenakshi, M. Ruban, S. Nandhini, T.J. Loganayagi, S. Sayed, Raad Muhammed Hassan, Enas Al-Saidi, Imad Al-Din Hussein Saveetha University Saveetha School of Engineering Chennai Thandalam602117 India St Aloysius Deemed to Be University Department of Software Technology India Saveetha University Saveetha School of Engineering-SIMATS Department of Computer Science and Engineering chennai India Department of Computer Science and Engineering chennai tamil nadu thandalam602105 India Collage of Nursing National University of Science and Tqechnology dhi qar64001 Iraq Al-Farahidi University Baghdad Iraq Al-kunooze University College Computer Engineer Department basra Iraq

ISBN: (纸本)9798350360165

Every day, pharmaceutical firms have to do extensive product analyses. The same product is frequently registered more than once in several systems, each using unique properties. For these businesses, precise and high-quality information is crucial, especially considering the nature of the pharmaceuticals these goods contain. The hypothesis of this research project is that machine learning provides a workable way to effectively combine different data sources and match records pertaining to the same product. It is no longer feasible to match records by hand because of the extraordinarily large volume that has to be processed. In a large data context, this paper presents a framework for matching pharmacological records using machine learning approaches. The framework trains machine learning by utilising specified criteria for record matching. These models are then tested by forecasting matches between records that deviate from these preset guidelines. Lastly, by creating a huge variety of record combinations and forecasting matches based on them, the system mimics the production environment. The findings show that although the training datasets produce good results - the top model has an average accuracy of about 85% - the production environment has its own set of difficulties. In spite of this, matches that depart from established norms are effectively predicted by the framework. These results highlight how machine learning can be used to perform record matching tasks, as manual processing at this size is impossible. © 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

The Benefits of engineering Design Competitions

引用

IEEE Potentials 2021年第4期40卷 4-5页

作者： Schor, Dario Kakarountas, Thanos Software Engineer Magellan Aerospace Winnipeg Manitoba Canada Department of Computer Science and Biomedical Informatics University of Thessaly Fthiotida Lamia Greece

During student orientation week at the University of Manitoba, Dean Emeritus Doug Ruth used to tell incoming classes, “Don’t miss 50% of your education by attending 100% of your classes.” After a short pause, he would qualify that statement by encouraging students to take advantage of learning opportunities, like engineering design competitions, that are found outside the classroom. engineering design competitions complement the engineering curriculum by exposing students to complex and interdisciplinary projects that would otherwise not fit within a semester-long course. Such projects motivate participants to realize ideas, apply the knowledge acquired from university courses, and solve real-world engineering problems. This procedure helps students appreciate the tradeoffs of their design decisions in order to respect constraints and meet the specifications of a complex system. Moreover, such competitions provide practical experience as participants conceptualize, design, test, and iterate through the design flow steps needed to realize the desired results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digitized Paper Evaluation for Universities using Machine Learning Technique

Digitized Paper Evaluation for Universities using Machine Le...

引用

Emerging Technology (INCET), International Conference for

作者： Bipin Nair B J Spoorthi C Gokul Narayanan C Koushik K S Pranav Venkitesan Dept. of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru India Software engineer frontend Zenloop GMBH Berlin Germany

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Automating the assessment of handwritten university papers is a crucial advancement in today's digital era. This study focuses on leveraging Handwriting Text Recognition (HTR) and Machine Learning (ML) techniques to streamline the evaluation process. By extracting key features and automating the grading process, this research aims to enhance efficiency and accuracy. The project emphasizes two primary objectives: feature extraction and automated calculation to replace manual evaluation methods. By employing a 70:30 split and training on 1000 images, the system undergoes rigorous filtering, preprocessing, region of interest (ROI) identification, segmentation, and validation based on ground truth data. Despite challenges like strike-throughs, overlapping letters, and inconsistent ink, this initiative ultimately aims to overcome the limitations of traditional paper evaluation methods.

关键词： Training Accuracy Text recognition Refining Machine learning Manuals Streaming media

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Predict COVID-19 Through Cough Analysis Using CNN-BiDirectional LSTM

A Deep Learning Approach to Predict COVID-19 Through Cough A...

引用

2022 International Conference for Advancement in Technology, ICONAT 2022

作者： Bhanusree, Y. Sree Deeksha, B. Sohan, V. Ajay, D. Eshwar Sai Ram, M. VNR VJIET Department of CSE Hyderabad India Junior Programmer Trainee Cognizant Hyderabad India Support Engineer II Amazon Hyderabad India Software Engineer NCR Corporation Hyderabad India Maters of Computer Science CSU Fresno California United States

ISBN: (纸本)9781665425773

COVID-19 is deadly contagious and with new variants forming every day, people are at great risk. 29.9 million cases have been reported in India so far and the range goes up to 179 million cases worldwide. Due to the limited number of test centers and the ever-increasing cases, the equipment and the lab technicians are getting outnumbered. They are also at constant risk of getting infected. The scientists have been working on analyzing coughs using machine learning and this technology has been successful in analyzing different types of coughs and classifying them into respective categories. Using this, a deep learning model is created that analyses the recorded cough sample and classifies them into their respective category. A CNN-Bidirectional LSTM is used to create this model and run it on the Covid-sounds dataset provided by Cambridge University. The Covid-sounds dataset has both breathing and cough samples of positive, negative, and other respiratory diseases which might alter or cause cough. This data is pre-processed and used as cough samples for the model. This model has outperformed other models which used the same dataset. © 2022 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

ETHACA - A Container-Based Cyber Range for Research and Education 29

ETHACA - A Container-Based Cyber Range for Research and Educ...

引用

29th IEEE International Workshop on computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2024

作者： Chouliaras, Nestoras Kantzavelou, Ioanna Pantziou, Grammati Maglaras, Leandros Chouliara-Sidera, Panagiota Adamakos, Antonis Chalatsakos, Panagiotis University of West Attica Department of Informatics and Computer Engineering Athens Greece School of Computing Edinburgh Napier University EdinburghEH10 5DT United Kingdom University of Thessaly Department of Computer Science and Biomedical Infromatics Lamia Greece Senior Software Engineer at *** Athens Greece Open University of Cyprus Faculty of Pure and Applied Sciences Nicosia Cyprus

ISBN: (纸本)9798350377644

The advent of Industry 4.0 and the Industrial Internet of Things (IIoT) has revolutionized manufacturing and production systems, enhancing efficiency and communication through the integration of advanced technologies such as IoT devices and AI. However, this increased digitization has also led to heightened cybersecurity risks, with a notable rise in the frequency and complexity of cyber-attacks. Cyber Ranges emerges as a critical solution in addressing these challenges, offering a controlled environment for simulating cyber-attack scenarios, training cybersecurity teams, and developing robust defense strategies. The escalating demand for cybersecurity professionals has highlighted the crucial need for effective training solutions. This article presents an open-source Cyber Range constructed on container-based architecture, meticulously engineered for efficient operation with minimal resource consumption. In response to the scarcity of cybersecurity experts, this platform prioritizes extensive scalability and robust isolation between exercises, ensuring secure learning environments, and also integrates a complex developed exercise series aimed at strengthening cybersecurity learning experiences. These exercises encompass a variety of scenarios and challenges, catering to professionals at different skill levels. Each exercise replicates real-world cyber threats, offering practical, hands-on learning opportunities. Additionally, a comprehensive questionnaire accompanies these exercises, designed to gather feedback on participants' experiences. © 2024 IEEE.

关键词： Cyber attacks

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：