检索结果-内蒙古大学图书馆

2nd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2023

作者： Topale, Ninaf Rajesh Usharani, Shola Gayathri Rajarajeswari, S. Depuru, Sivakumar Shola, Sivanaga Prasad Vellore Institue of Technology Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India School of Computing Mohan Babu University Dept of CSE Tirupati India Teladoc Health United States

ISBN: (纸本)9798350397635

The 21st century is dominated by artificial intelligence. AI is already dominating in medical domain like automated surgeries and medical chat bots. Healthcare is one of the important domains and it is continuously involved from technology point of view. Automation is one of the biggest challenges in this domain. AnuVaidya is trying to handle and work on this challenge. The AnuVaidya would basically resemble a prototype which would try to enhance and automate the communication between the patient and doctor. The AnuVaidya will work as a companion for doctor, it analyses the conversation between patient and doctor and predict the disease. There are some advance modes in AnuVaidya like dept.ness of anesthesia identification and classification. AnuVaidya will implement some inbuilt modules from scratch to increase time and accuracy. NLP will be helpful for deeply analyzing the conversation between doctor and patient. Deep learning would be useful for modern use cases like anesthesia dept. classification. AnuVaidya focus on accuracy and make the machine learning and deep learning more accurate for anethesia monitoring system of about 87%. Research limitations- Use of cloud computing in AnuVaidya. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Real-time Human Motion Tracking and Reconstruction using IMU Sensors

Real-time Human Motion Tracking and Reconstruction using IMU...

引用

2022 IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2022

作者： Chakravarthi, Bharatesh Prabhu Prasad, B.M. Chethana, B. Pavan Kumar, B.N. Chung-Ang University Virtual Environments Laboratory Seoul Korea Republic of Indian Institute of Information Technology Dept. of Computer Science and Engineering Dharwad India Centre for Product Design and Manufacturing Indian Institute of Science Bengaluru India

ISBN: (数字)9781665470872

ISBN: (纸本)9781665470872

Human body-strap-based, and sensor-mounted clothing-based easy-to-wear motion capture systems have generated a lot of interest and been thoroughly investigated in recentm times. Body movements are typically assessed using miniature inertial measurement unit (IMU) sensors. Based on body strap IMU sensors, this paper presents a system enabling real-time human motion monitoring and reconstruction. To track fullbody motions, the system utilizes a human-body kinematicsassured orientation and position estimation technique. A threedimensional (3D) humanoid model-based motion reconstruction module is included, letting people visualize human motions in real-time. Furthermore, We can edit the motion data that has already been captured and validate joint-segment kinematics. Finally, we utilize complicated yoga exercise movements to demonstrate the accuracy in terms of orientation estimation. © 2022 IEEE.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis for Air Quality Assessment and Evaluation: A Data Mining Approach 9

Statistical Analysis for Air Quality Assessment and Evaluati...

引用

9th IEEE International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2021

作者： Mangla, Monika Sharma, Nonita Mehta, Vaishali Mohanty, Sachi Nandan Saxena, Komal Tilak College of Engineering Dept. of Computer Engineering Lokmanya Navi Mumbai India Dr. B.R Ambedkar National Institute of Technology Dept. of Computer Science and Engg. Jalandhar India Dept. of Computer Science and Engineering Hyderabad India Amity Institute of Information Technology Amity University Uttar Pradesh India

ISBN: (纸本)9781665417037

In this era of the industrial revolution, air Pollution is emerging as the most concerning problem specifically in developing countries. This air pollution considers the escalation of several pollutants in the air like nitrogen oxides, sulfur dioxide, carbon dioxide, carbon monoxide and particulate matter (PM), CFCs (Chlorofluorocarbons), odors, and radioactive pollutants, etc. The rise of these pollutants in the air is putting a significant impact on the health of mankind and animals in the affected area. In this manuscript, the authors aim to analyze the quality of air in terms of SO2 and NO2 emissions. Further, an analysis is also made regarding the amount of PM in the air in terms of Reparable Suspended Particulate Matter (RSPM) and Suspended Particulate Matter (SPM). To perform this survey, the authors consider the air quality of various states in India. Among the various states considered for the survey, authors consider Chandigarh and Delhi for further analysis. © 2021 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Survey on the Design and Development of Indian Language Chatbots

Survey on the Design and Development of Indian Language Chat...

引用

2021 International Conference on Communication, Control and Information sciences, ICCISc 2021

作者： George, Athira Susan Muralikrishnan, Gowri Ninan, Leya Rachel Varrier, Pranav S. Dhanya, L.K. Mar Baselios College of Engineering and Technology Dept. of Computer Science and Engineering Kerala India

ISBN: (纸本)9781665412797

A chatbot is an intelligent system which can hold a conversation in real-Time with a human being using natural language. This paper describes a multitude of chatbots that communicate in Indian Languages. Extensive research has been done on chatbots in English before, but there is little study on Chatbots in Indian languages. This survey was conducted as a part of our project on an Intelligent Chatbot using Deep Reinforcement Learning. The paper is based on the firm belief that chatbots in Indian languages can be used to bridge the communication gap amongst Indian users. For the chatbot to work resourcefully, it needs to be provided vast logical resources. The peculiarities of natural language require special care, especially in the processing of synonyms, word forms, context, etc. This survey paper deeply studies the methodologies and behaviours of various Indian chatbots, and a comparison is drawn based on their accuracy. © 2021 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Exploring an Inter-Pausal Unit (IPU) based Approach for Indic End-to-End TTS Systems

arXiv

引用

arXiv 2024年

作者： Prakash, Anusha Murthy, Hema A. IITM Bengaluru India Dept of Computer Science & Engineering Indian Institute of Technology Madras Chennai India

Sentences in Indian languages are generally longer than those in English. Indian languages are also considered to be phrase-based, wherein semantically complete phrases are concatenated to make up sentences. Long utterances lead to poor training of models and result in poor prosody during synthesis. In this work, we explore an inter-pausal unit (IPU) based approach in the end-to-end (E2E) framework, focusing on synthesising conversational-style text. We consider both autoregressive Tacotron2 and non-autoregressive FastSpeech2 architectures in our study and perform experiments with three Indian languages, namely, Hindi, Tamil and Telugu. With the IPU-based Tacotron2 approach, we see a reduction in insertion and deletion errors in the synthesised audio, providing an alternative approach to the FastSpeech(2) network in terms of error reduction. The IPU-based approach requires less computational resources and produces prosodically richer synthesis compared to conventional sentence-based systems. © 2024, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Binary Classification using K-Nearest Neighbor Algorithm on FPGA 6

Binary Classification using K-Nearest Neighbor Algorithm on ...

引用

6th International Conference on computer, Communication, Chemical, Materials and Electronic engineering, IC4ME2 2021

作者： Sadad, Nahin Ul Afrin, Afsana Mondal, Md Nazrul Islam Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9781665406376

The K-Nearest Neighbor (K-NN) algorithm is one of the most widely used algorithms for machine learning applications. Using K-NN algorithm on massively large data requires high computation power. This high computation demand can not be met by traditional software-based approach using CPUs. Field Programmable Gate Array (FPGA) can be used to implement K-NN algorithm to achieve hardware acceleration. In this paper, we implemented K-NN on Xilinx FPGA using Verilog Hardware Description Language (HDL) by exploiting the raw hardware power. The result shows that our FPGA-based solution is on average 30 thousand times faster than traditional software-based solution on CPU. © 2021 IEEE.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Using NOMA Scheme for the Management of Interference and the Improvement of Performance in 5G Networks 13

Using NOMA Scheme for the Management of Interference and the...

引用

13th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2021

作者： Bouras, Christos Kokkinos, Vasileios Tzioumanis, Georgios University of Patras Computer Technology Institute and Press Diophantus' Computer Engineering and Informatics Dept. Patras Greece

ISBN: (纸本)9781665402194

The new generation of 5G networks, compared to 4G networks, is a very important example of change in achieving very high frequencies in the carrier with huge bandwidth, high densities with a huge number of antennas and improved quality of services, making effective interference management necessary. In this paper, we present the contribution of the Non-Orthogonal Multiple Access (NOMA) scheme to improving the performance of 5G networks. We refer to the technique of sequential interference cancellation applied to some NOMA formats, compare NOMA and Orthogonal Multiple Access (OMA) formats in terms of the capabilities they offer users and NOMA's significant contribution to Multiple-Input Multiple-Output (MIMO) technology and compare three basic NOMA formats in three different resource and user reporting scenarios. Finally, we present the results of the simulations of the above comparisons and analyze the contribution of each scheme to the improvement of the system performance. and copy;2021 IEEE. © 2021 IEEE computer Society. All rights reserved.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in IoT Data Streams Based on Long Short-Term Memory

Anomaly Detection in IoT Data Streams Based on Long Short-Te...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Hussein, Layth Mohan, M. Rajeswari, P. Gurupandi, D. Saranya, N. Naga The Islamic University College of Technical Engineering Department of Computers Techniques Engineering Najaf Iraq Nitte Meenakshi Institute of Technology Dept of Ise Bangalore India Karpagam Institute of Technology Department of Ece Coimbatore India Panimalar Engineering College Department of Ece Chennai India Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India

ISBN: (纸本)9798350360660

Nowadays, the swift growth of Ambient Intelligence (AmI) in Internet of Things (IoT), sensing devices have been generating many data streams in intelligent scenarios. The IoT deployment issues, complexity of systems is leading to abnormal behavior in data streams. Moreover, the dynamic and consecutive data streams generated in IoT systems leads to difficulty in determining anomaly detection. Therefore, this paper presents a Long Short-Term Memory (LSTM) and Sparse Autoencoder method for classification of data to determine anomaly behavior in IoT data streams. Firstly, a min-max normalization technique is employed to scale the input data for better results and Sparse Autoencoder utilizes sparsity penalty to capture relevant features. The LSTM network is employed for prediction tasks which leverages the ability to handle sequential IoT data streams and dropout layers are utilized to prevent overfitting. Finally, K-means clustering mechanism is used to establish an error threshold for anomaly detection. The performance of proposed LSTM and Sparse Autoencoder is evaluated on SKAB dataset which illustrated higher precision (0.824), recall (0.982) and f1 scores (0.847). The proposed method outperformed existing anomaly detection methods such as Neural Network (NN), Adaptable and Interpretable Framework for Anomaly Detection (AID). © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Bayesian Belief Network Analysis for SPAD System in Railways

Bayesian Belief Network Analysis for SPAD System in Railways

引用

Multimedia Processing, Communication & Information technology (MPCIT), International Conference on

作者： Manjunath Sargur Krishnamurthy Bommisetty Rahul Chandrahas Reddy Bondala M Vishnu Vardhan Reddy Magha Raghul G Ambika B J JP Morgan & Chase Co. Houston Texas USA Dept. of AI&ML BMS Institute of Technology and Management Bengaluru Dept. of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Karnataka

ISBN: (数字)9798350375466

ISBN: (纸本)9798350375473

Even with a powerful network of signaling and warning systems in the country, there have been many examples of trains crossing the red signal due to various factors, even today. These occurrences, known as Signal Passed At Danger (SPAD) events, could potentially result in severe consequences such as train derailments, train collisions, infrastructure collisions, and other dangerous events. Traditionally, these events have been analyzed using the Fault Tree Analysis (FTA) approach Bayesian Network (BN) is considered to be a better model to represent this situation when it comes to handling complexity. Bayesian Network allows for integration and includes systematic knowledge about the system, which helps to get a very flexible concise, and simple graphed representation. This study demonstrates applications of Bayesian Belief Networks (BBN) analysing and enlightening the Signal Passed at Danger (SPAD) system in railway processes. Execution of BBN offers more dynamic and flexible models compared to outmoded Fault Tree Analysis (FTA), struggling with complexity. BBN efficiently catches the inter dependencies between factors that are contributing to SPAD events, such as signal conditions, human errors, and mechanical issues. Over simulations and probability calculations using OpenMarkov software, Study revealed key intuitions, such as identifying highly risk apparatuses within SPAD system. The outcomes include enhanced risk calculation accuracy and recommendations for improving signal systems and safety protocols. These conclusions contribute to a safer and reliable railway structure, highlighting the success of BBN for complex, safety critical systems in real world applications.

关键词： Analytical models Systematics Rail transportation Software Bayes methods Safety Complexity theory Software reliability Single-photon avalanche diodes Fault trees

来源：评论

学校读者我要写书评

暂无评论

Implementation of Scalable Non-Recursive Merge Sort on FPGA 6

Implementation of Scalable Non-Recursive Merge Sort on FPGA

引用

6th International Conference on computer, Communication, Chemical, Materials and Electronic engineering, IC4ME2 2021

作者： Ul Sadad, Nahin Afrin, Afsana Mondal, Md Nazrul Islam Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9781665406376

Sorting is a classic algorithm that is fundamental building block of many algorithms. Many algorithms requiring high speed data processing nowadays are hardware accelerated using re-configurable architecture like Field Programming Gate Array (FPGA) which can outperform CPU architecture in terms of performance. Since sorting is computation-intensive operation in any algorithm, faster, efficient and scalable sorting algorithm is important to achieve hardware acceleration. In this paper, scalable non-recursive merge sort algorithm is implemented using FPGA and its performance is compared with performance of bubble sort. We found that merge sort on FPGA is 2 or more times faster than bubble sort on FPGA. © 2021 IEEE.

关键词： Sorting

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：