检索结果-内蒙古大学图书馆

iSeePlus : A cost effective smart assistance archetype based on deep learning model for visually impaired

JOURNAL OF INFORMATION & OPTIMIZATION SCIENCES 2020年第7期41卷 1741-1756页

作者： Virmani, Deepali Gupta, Charu Bamdev, Pakhi Jain, Prateek Guru Gobind Singh Indraprastha Univ Dept Comp Sci & Engn Bhagwan Parshuram Inst Technol Sect 17 New Delhi 110089 India

In this paper, a unique smart assistance aid, iSeePlus, for visually impaired people is presented. iSeePlus, as a prototype product, is equipped with smart glasses (iSee Glasses), a smart stick (iStick) and an android application which will be initially used to set up the device. The smart glasses are trained on proposed deep learning models to provide features like face detection and recognition, emotion detection and image captioning with a click of a specifically placed buttons on the device. The proposed prototype product also supports reading texts from images via Google Cloud Vision API and allows the user to send alert texts with his current location to the saved emergency contacts. The iStick is an integrated accessory that comes with iSeePlus which creates vibrations to alert the user of any incoming obstacle within the range of 25 cm. The android application will be used to set up the device at initial stages as it helps to add a database of known people and the emergency contacts. Presently, iSeePlus, has an accuracy of 98.03% on face detection and recognition model, FDREnet, 68.5% on emotion detection with ExpressNet and 65.7% on image captioning with CaptionMeNet BLUE-1: 65.7). With the help of iSeePlus, people suffering from visual impairment will now be able to do their day-to-day chores independently up to a significant degree.

关键词： Deep learning computer vision machine learning Android application Raspberry Pi3 Visual impairment Assistive technology Convolution neural network

来源：评论

学校读者我要写书评

暂无评论

A Review of Bigdata and machine learning Techniques in Healthcare

A Review of Bigdata and Machine Learning Techniques in Healt...

引用

international conference on Intelligent Sustainable Systems (ICISS)

作者： Sumati boyapati Srinivasa Rao Swarna Shweta Sharma Rashmi Agrawal IRIS Software INC Edison NJ Tata Consultancy Services Edision NJ MDSU Ajmer Ajmer India Faculty of Computer Application Manav Rachna International Institute of Research and Studies

ISBN: (数字)9781728170893

ISBN: (纸本)9781728170909

The study of big data by machine learning offers significant favorable circumstances for the assimilation and assessment of large amounts of complex medical services information. To adequately use machine learning devices in medical services, some constraints must be measured and key points must be measured, for example, its clinical use and ethics in the use of medical services. Favorable circumstances of machine learning incorporate adaptability and versatility contrasted and conventional biostatistical strategies, which makes it deployable for some errands, for example, hazard separation, finding and grouping, and endurance expectations. The health care services measure includes a lot of gigantic information that can be of various kinds and put in better places. The digitization of data, if appropriately dissected, prompts an expansion like cycles and administrations in the Healthcare area. In this specific situation, machine learning (ML) is the key empowering innovation to diminish the expenses of medical services extricating knowledge from information. The objective of ML is to improve a framework with no ceaseless human mediation. Medical Decision Support Systems (MDSS) are an additional incentive from one viewpoint by accelerating determination and care measures, then again decreasing the hour of clinical staff or concentrated learning.

关键词： Medical services machine learning Genomics Bioinformatics Big Data Medical diagnostic imaging Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Research and application of computer Artificial Intelligence Technology in Online learning System and Mobile Internet Terminal 2021

Research and Application of Computer Artificial Intelligence...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Weifeng Deng Lin Wang Hainan Vocational University of Science and Technology China

ISBN: (纸本)9781450385046

In order to overcome the poor application effect of the traditional English-led intelligent online learning system, a PIMS-based English-led intelligent online learning system is proposed. Based on the analysis of the current situation of the intelligent teaching system, the article designs an intelligent English learning platform system based on PIMS. This has further improved the English teaching model and completed the construction of the overall framework structure. The research also solicited the user's evaluation and feedback information on the expected function improvement, and the results showed that the function improvement design has considerable value for the new concept college English network teaching system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot learning on 3D Surface Defect Detection with PM Networks 2021

Few-Shot Learning on 3D Surface Defect Detection with PM Net...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Gao Chen Han Yu Linhua Jiang Huiliang Shang Fudan University China

ISBN: (纸本)9781450385046

machine learning has grown rapidly in recent years. The research and application of machine learning technology can be widely seen in many fields of science. As a result, various machine learning-based detection methods have been deployed in manufacturing lines. Compared with the traditional methods, machine learning methods improve the defect detection performance better. But there are still shortcomings such as the need for a large amount of data to train the classification model. We have developed and validated an Automatic Optical Inspection (AOI) system to detect surface defects based on 3D point cloud data. Our system can be divided into 4 main fundamental parts: Data Mapping, Defect Segmentation, Data Augmentation, and Few-shot learning. This system can effectively reduce the workload of data collection. The PM Networks we proposed in the Few-shot learning stage are evaluated on Omniglot. We also provide our dataset of the Tile surface to evaluate the system performance. Our algorithm obtains significant improvements over the mainstream models on these datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

machine learning Methods for Prediction of COVID-19 Patient Length of Stay: Using Texas PUDF Data

Machine Learning Methods for Prediction of COVID-19 Patient ...

引用

Electrical, computer, Communications and Mechatronics Engineering (ICECCME), international conference on

作者： Junyan Zhang Peter Yu A&M Rural and Community Health Institute Texas A&M University College Station US

Accurately predicting the length of stay (LOS) has significant benefits for hospitals’ resource utilization. It’s especially important for COVID-19 patients since it is a highly contagious disease, and it places significant strain on healthcare systems worldwide. In this paper, we used the Texas Public Use Data File (PUDF) inpatient discharge record, which is a state-level dataset that contains data from over 600 hospitals, to make predictions regarding LOS of COVID-19 patients. Our analysis included 224,152 (n) records covering a time span of six quarters from Q4 2020 to Q1 2022. In addition, seven features are chosen to predict LOS - age group, sex code, race, first payment source, type of admission, illness severity, and risk mortality. Various machine learning techniques were employed, including Gradient Boosting (GB), K-Nearest Neighbors (KNN), Support Vector machine (SVM), and Random Forest (RF). Using regression models, we identified the best parameters for each model and predicted the numerical LOS for each quarter. Additionally, the Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-Squared (R2) were calculated to evaluate the performance of each prediction. The results revealed notable performance differences among models. SVM performs the least MAE for 6 quarters, and GB performs the highest R-squared for 6 quarters. It also showed varying performance across different quarters, possibly due to dissimilarities in the data distribution. Q4 2020 and Q2 2021 has a relatively better performance, and the data is relatively concentrated compared to others. Q4 2021 has the least performance with a highly dispersed data distribution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

machine learning-Powered Real-Time Motion Detection System: A Review

Machine Learning-Powered Real-Time Motion Detection System: ...

引用

international conference on Innovative Mechanisms for Industry applications (ICIMIA)

作者： Naman Khurana Madhavi Bansal Ananya Thakur Velma Sai Varshitha Tannu Er. Kirat Kaur Computer Science & Engineering Chandigarh University Punjab India

Motion detection, a fundamental technology in computer vision, is crucial for a wide array of applications, including security,surveillance, gaming and robotics. OpenCV, the open-source computer Vision Library, has emerged as a versatile tool for developing robust and efficient motion detection systems. The article offers insights into the intricacies of motion detection using OpenCV, combining existing research findings with a unique perspective on this critical subject. It explores traditional and advanced techniques, highlights real-world applications and addresses persistent challenges in the field such as handling background clutter, adapting to changing lighting conditions, and achieving real-time processing. It presents a fundamental approach to motion detection, encompassing frame acquisition, frame differencing, thresholding, noise reduction, object tracking, and more, with a focus on the tools and technologies that can enhance these processes. The primary problem addressed in the article is the development of accurate, reliable, and real-time motion detection systems considering various challenges and objectives across different application domains. The provided references encompass a wide range of research in the field, contributing to a comprehensive understanding of motion detection. The article can serve as a valuable resource for individuals interested in motion detection and its integration with OpenCV, offering a foundation for readers to embark on their motion detection projects and foster innovation in this dynamic field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare Data Security through Blockchain-Enhanced IDPS and Multi-Layered Firewall System

Enhancing Healthcare Data Security through Blockchain-Enhanc...

引用

Advancement in Technology (ICONAT), international conference for

作者： Vishnu Kurnala Department of Computer Science and Engineering(AI&ML) Vardhaman College of Engineering

ISBN: (数字)9798350354171

ISBN: (纸本)9798350354188

This paper introduces a novel security framework to fortify healthcare data against cyber threats, incorporating blockchain technology and ledger tokenization within an integrated Intrusion Detection and Protection System (IDPS). Faced with escalating cybersecurity challenges, our approach merges traditional protection mechanisms with cutting-edge technologies to offer unparalleled data integrity and security. By leveraging blockchain for immutable data trails and enhancing IDPS with advanced machine learning techniques, our solution provides a robust defense against a range of cyber threats, including ransomware and data breaches. Extensive testing in simulated environments confirms the effectiveness of our system, suggesting it as a viable blueprint for future developments in healthcare cybersecurity. This study not only demonstrates the application of blockchain in enhancing data security but also sets the stage for further innovative practices in protecting sensitive healthcare information.

关键词： Firewalls (computing) Data integrity Intrusion detection Medical services machine learning Tokenization Blockchains Ransomware Protection Testing

来源：评论

学校读者我要写书评

暂无评论

Enzyme Function Classification using Protein Sequence Features and Random Forest

Enzyme Function Classification using Protein Sequence Featur...

引用

The 3rd international conference on Bioinformatics and Biomedical Engineering(iCBBE 2009)(第三届生物信息与生物医学工程国际会议)

作者： Chetan Kumar Gang Li Alok Choudhary Department of Electrical Engineering and Computer Science Northwestern University EvanstonILUSA

Enzymes are proteins that catalyze bio-chemical reactions in different ways and play important roles in metabolic pathways. The exponential rise in sequences of new enzymes has necessitated developing methods that accurately predict their function. To address this problem, approaches that cluster enzymes based on their sequence and structural similarity have been applied, but are known to fail for dissimilar proteins that perform the same function. In this paper, we present a machine learning approach to accurately predict the main function class of enzymes based on a unique set of 73 sequence-derived features. Our features can be extracted using freely available online tools. We used different multi-class classifiers to categorize enzyme protein sequences into one of the NC-IUBMB defined six main function classes. Amongst the classifiers, Random Forest reported the best results with an overall accuracy of 88％ and precision and recall in the range of 84％ to 93％ and 82％ to 93％ respectively. Our results compare favorably with existing methods, and in some cases report better performance. Random Forest has been proven to be a very efficient data mining algorithm. This paper is first in exploring their application to enzyme function prediction. The datasets can be accessed online at the location: .

关键词： enzyme function classificaiton machine learning multi-class random forest protein sequence features

来源：评论

学校读者我要写书评

暂无评论

Influence of Deepfake Terminology on Content-Emerging Threat Reduction

Influence of Deepfake Terminology on Content-Emerging Threat...

引用

international conference on Innovative Sustainable Computational Technologies (CISCT)

作者： Rajeev Tripathi Vinay Kumar Mishra Vivek Kumar Alok Singh Sengar Neeraj Kumar Pandey Amit Kumar Mishra Department of CAS School of Management Sciences Lucknow India Department of Computer Application Babu Banarasi Das University Lucknow India Department of CSE Teerthanker Mahaveer University Moradabad India Department of CSE IIMT University Meerut India School of Computing IIMT University Dehradun India Department of CSE Graphic Era Hill University Dehradun India

A significant development in the rapidly expanding fields of Deep and machine learning resulted in architectures that can create convincing synthetic content sometimes known as deepfakes. The danger arises when doctored photographs, films, and audios blur the distinction between fake and real content and are employed as weapons to inflict new levels of damage. This work analyzes the effectiveness of Big Data processing on operational parameters and focuses on data-dimensionality factors. It resolves big-data complications using DL and ML for decision-making mechanisms in the enterprise sectors and corporate sectors using in-depth analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Benefits of Applying machine learning to Real-Time Data Analysis

Analyzing the Benefits of Applying Machine Learning to Real-...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), international conference on

作者： Rakesh Kumar Yadav TR Mahesh Ajay Kumar R. Jayadurga A Vishal Gourav Sood Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Bangalore Karnataka India Department of Master of Business Administration Prince Shri Venkateshwara Padmavathy Engineering College Chennai Centre of Interdisciplinary Research in Bus iness and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

The application of device learning to actual-time data analysis has the potential to revolutionize the way businesses make decisions. With the capacity to procedure big volumes of data fast and correctly, system learning can provide insights that tell strategic decisions at the same time as promoting information-pushed choice making. This evaluation can assist agencies increase efficiency, lower expenses, and create a more aggressive area. By means of leveraging system learning to higher recognize patron behavior, operational operations, and traits in the market, organizations can create proactive procedures to assume customer wishes and capitalize on opportunities. This paper will discover the capacity advantages of making use of device studying to actual-time records analysis and talk how businesses can satisfactory leverage it. The paper can even speak exceptional varieties of device gaining knowledge of strategies and do not forget some problems businesses need to do not forget before integrating system gaining knowledge of into their records evaluation systems.

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：