检索结果-内蒙古大学图书馆

2nd International Conference on Trends in Electrical, Electronics and computer engineering, TEECCON 2023

作者： Lakshminarayanan, Arun Raj singh Rathna balaji, Inderpaal Hussain, sheik Taaha Jayaraman, Vaishnavi Anwar, Chintakunta shaik B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350339949

Detecting emotions in audio speech files is a significant challenge for machines, despite the natural skill of humans in this area. While computers excel at comprehending informational content, deciphering underlying emotions remains a formidable challenge. At this juncture, the speech Emotion Recognition system (sERs) emerges as an important component of the solution. To reliably categorize audio speech data into distinct emotional categories such as happiness, sorrow, anger, and neutrality, a specific model called sERs was developed. It has a wide range of potential uses, from healthcare to contact centers. In this study, the following Machine Learning models were utilized support Vector Machine (sVM), k-nearest neighbors (KNN), and Decision Tree (DT). These models yielded lower accuracy rates when categorizing emotions. Thus, to improve the accuracy rate three crucial audio features such as Mel, chroma, and MFCC are applied by the constructed sERs and analyzed by utilizing a grid search-b.s.d Multi-Layer Perceptron (MLP) classifier for accurate results. The proposed model produced 75.97% accuracy rate, which is quite remarkable. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Investigation on Real - Time Object Detection in Deep Learning 5

A Comprehensive Investigation on Real - Time Object Detectio...

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Rajeshkumar, M. Arun Raj, L. B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305449

Object Detection technique is extremely related among the computer Vision field. Object detection empowers detecting case in the perception of various objects from videos plus imagery as well as videos or pre-recordings video. This will find out the variety of individuality of imagery more willingly than the recognition of mechanism of objects and will provides a logical as well as perceptive of images in efficient manner deeply related to human vision works. Object detection has recognized with significant notice from researchers for the motive of its very close relationship with image detection. Machine learning algorithms interrelated to Convolutional Neural Networks (CNNs) has been currently investigated in a several times of real time object detection applications through the source of various articles. In this study, we have analyzed about various algorithm implemented in the concept of real-time object detection as well as importance and drawbacks of specific algorithm of the existing works in the form of a comparative table. The results of this investigation indicate that the machine learning algorithms are very successful in detecting the real time object. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Human Action Recognition with Ensembled DTW Loss Function in CNN LsTM Architecture 3rd

Enhanced Human Action Recognition with Ensembled DTW Loss Fu...

引用

3rd International Conference on sustainable Expert systems, ICsEs 2022

作者： Ram, D. Dinesh Muthukumaran, U. Fatima, N. sabiyath Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (纸本)9789811978739

Human action recognition is a concept that involves acquiring information b.s.d on the sequence of movements by the target. This recognition model is used to recognise elderly people's actions to monitor their anomalies and provide appropriate guidance as soon as possible to avoid further disaster. This algorithm involves refining HAR and provides precise decisions to predict any emergencies while handling elderly people. This algorithm uses Dynamic Time Warping as a loss function ensembled with mean absolute error in CNN LsTM neural network. DTW is used in the loss function to get a relationship between two sequences of actions considered as waves. This results in performing better at any speed of action as long as the sequence of movements for action remains the same. The variations in the change of the sequence of movements for action are further countered by mean absolute error to perform better in any variation of an action. Thus, it provides an accuracy of 75% for the taken dataset which is way more than the accuracy produced by DTW or MAE as a separate loss function. © 2023, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

simulator for swarm Feature selection Algorithms for Classification Problem 2

Simulator for Swarm Feature Selection Algorithms for Classif...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for social Innovation, IATMsI 2024

作者： Kulkarni, Mayuri Diwakar shahade, Makarand Deore, shailesh Khandekar, Nilesh bhavsar, Ishwari Garud, Jayesh Ahirrao, Kunal SVKM's Institute of Technology Dept. of Computer Engineering Dhule India SSVPS's B.S. Deore CoE Dept. of Computer Engineering Dhule India

ISBN: (纸本)9798350360523

swarm Intelligence (sI) algorithms address difficult optimization and decision-making issues using cues from collective behavior. These behaviors are inspired by social creatures like ants, bees, and birds. Using these creatures' behaviors algorithms have demonstrated amazing promise in several fields, such as distributed computing, robotics, and optimization. Assessing sI algorithms' performance under various conditions and scenarios is still a significant difficulty, though. We introduce a new swarm Intelligence Algorithm Performance Analysis simulator (sIAPAs) to tackle this issue. This proposed simulator introduces a novel approach to automating the process of selection for swarm Intelligence (sI) algorithms on datasets. The system empowers users to upload datasets into a specialized simulator, which then orchestrates a comparative analysis using a suite of sI algorithms. The simulator evaluates and selects the most suitable algorithm b.s.d on the dataset's characteristics and problem domain. This provides the optimal selected features by the respective algorithms b.s.d on measured parameters. © 2024 IEEE.

关键词： swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

system-75 - sWITCH sERVICEs sOFTWARE

引用

AT&T TECHNICAL JOURNAL 1985年第1期64卷 197-212页

作者： DENsMORE, W JAKUbEK, RJ MIRACLE, MJ sUN, JH All authors are members of AT&T Information Systems Laboratories an entity of AT&T Information Systems Inc. Wayne Densmore: B.S. (Electrical and Computer Engineering) 1975 Clarkson College of Technology M.S. (Electrical and Computer Engineering) 1976 Clarkson College of Technology AT&T Bell Laboratories 1976–1983 AT&T Information Systems Laboratories 1983—. Ray J. Jakubek: B.S. (Electrical Engineering) 1967 Manhattan College M.S. 1968 and Ph.D. (Electrical Engineering) 1973 New York University Bell Laboratories 1968–1982 Michael J. Miracle: B.S. (Electrical and Computer Engineering) 1979 University of Wisconsin M.S. (Electrical Engineering) 1980 Stanford University AT&T Bell Laboratories 1979–1982 John H. Sun: B.S. (Electrical Engineering) 1972 National Chiao-Tung University Taiwan M.S. (Computer Science) 1977 University of Connecticut Taiwan Telecom Research Laboratories 1974–1975 ACCO-Bristol Company 1978 Bell-Northern Research 1979 AT&T Bell Laboratories 1980–1982

The switch services software of system 75 provides the b.s.s for an extensible office communication system, supporting a wide variety of voice and data-switching services. This paper presents the software architecture of the system 75 switch services. The concepts of user, group, and process-per-call form its foundation. We introduce the architecture by stepping through a simple station-to-station phone call, and proceed to the derivation of a call model b.s.d on the topology of a call. This call model is realized as a layered set of cooperating processes that execute under the Oryx/Pecos Operating system on the system 75 switch processor. The software layers and processes are discussed and a call walk-through is used to illustrate the process interactions.

关键词： DIGITAL COMMUNICATION systems

来源：评论

学校读者我要写书评

暂无评论

Advanced Vehicle Detection Heads-Up Display with TensorFlow Lite 3rd

Advanced Vehicle Detection Heads-Up Display with TensorFlow ...

引用

3rd International Conference on sustainable Expert systems, ICsEs 2022

作者： Haris, K. Mohamed Fatima, N. sabiyath Albeez, syed Abdallah Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (纸本)9789811978739

The real-time heads-up display (HUD) will enable the human operator to have a new sense and perspective to driving. The proposed Heads-up display (HUD) detects vehicles, civilians, and obstacles by allowing the user to stay focused on driving. It has a navigator map to keep the user aware of their current location and helps to track their movement. It also tracks speed with an overlayed speedometer and offers fail-safe emergency protocol to alert the emergency contacts when a crash is detected. All these features are accessible by almost everyone who have access to a mobile device and is very cost-effective. The Heads-up display serves as an effective medium between the car and human operator. The operator can set any of the three models: ssD, YOLO v2 and v3 b.s.d on their device performance level. If it is a lower-end device, the ssD model performs faster and efficient. If it is a high-end device, the performance can be improved by using YOLO higher version models. © 2023, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Rob.s. Parkinson's Disease Recognition from MRI brain Images by Densely Multi-Dilated Densely Connected ResNet Model

A Robust Parkinson's Disease Recognition from MRI Brain Imag...

引用

2024 International Conference on Integrated Circuits, Communication, and Computing systems, ICIC3s 2024

作者： Arogia Victor Paul, M. shankar, sharmila B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350364088

Parkinson disease (PD) is a neurological ailment that can be treated that causes excruciating discomfort in the brain as well as problems with balance and dexterity. Physicians frequently employ experimental indicators, such as motorized and non-motor symptoms b.s.d on brain magnetic resonance imaging (MRI) pictures, to diagnose Parkinson's disease (PD) in a medical stage. Nevertheless, there are disparities in inter-variability because these medical evaluations heavily rely on skilled physicians. Thus, this work proposes a sophisticated deep learning (DL) method for precise brain MRI-b.s.d PD analysis. To improve the data eminence, Extended Unsharp Mask Filtering (Ex_UMF) is first used to the brain images. The suggested Multi-dilated Densely linked ResNet model (MD_DenseRNet) is then fed the preprocessed pictures to determine if the image is PD or normal. The Python platform processes and examines the generated method, and the simulation progresses using a publicly available PPMI datab.s.. A number of evaluation metrics, including computing time (CT), sensitivity, specificity, and precision, are looked at and linked to conventional research. The created MD_DenseRNet model achieved 98.87% accuracy, 97% precision, 98.1% recall, 96.9% specificity, and 0.15 ms CT in the experimental part. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Clustering models for data stream mining

Clustering models for data stream mining

引用

IUTAM symposium on the Dynamics of Extreme Events Influenced by Climate Change (2013)

作者： Mythily, R. banu, Aisha Raghunathan, shriram Department of Information Technology B.S. Abdur Rahman University Chennai India Department of Computer Science and Engineering B.S. Abdur Rahman University Chennai India

The scope of this research is to aggregate news contents that exists in data streams. A data stream may have several research issues. A user may only be interested in a subset of these research issues;there could be many different research issues from multiple streams, which discuss similar topic from different perspectives. A user may be interested in a topic but do not know how to collect all feeds related to this topic. The objective is to cluster all stories in the data streams into hierarchical structure for a better serve to the readers. The work utilizes segment wise distributional clustering that show the effectiveness of data streams. To better serve the news readers, advance data organization is highly desired. Once catching a glimpse of the topic, user can browse the returned hierarchy and find other stories/feeds talking about the same topic in the internet. The dynamically changing of stories needs to use the segment wise distributional clustering algorithm to have the capability to process information incrementally. © 2015 The Authors. Published by Elsevier b.V.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Prediction for bullish and bearish Trend in the Price of stocks Using PCA and LsTM 4th

Prediction for Bullish and Bearish Trend in the Price of Sto...

引用

4th International Conference on Communication and Intelligent systems, ICCIs 2022

作者： Mohanavel, Adithya Asmath Haseena, M.I. sabiyath Fatima, N. Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India

ISBN: (纸本)9789819920990

In the cutting-edge era, stock prediction is soaring to a new peak since the investors forsake risking the economy. so, they exhibit more interest in prognosticating the future value of the company or any product before they buy which reverberates in gain. stock prediction drastically increases the accuracy of prognosticating profit and loss by comparing the pattern with the previous data set. This paper deals with both technical and fundamental stock analysis. It uses a boolean-b.s.d algorithm for searching for any pattern match in the trend of the data with the historical data warehouse of stocks and if any, subsequently applying time series algorithms to predict the profit or loss behaviour of the pattern. It treats the technical data analysis in a way to improvise accuracy. The recorded data is fed into the hybrid algorithm which is the combination of five top-performing trading algorithms namely Exponential moving average, Relative strength index, Average directional index, standard deviation index, and On-balance volume. The result of technical and fundamental data analysis is then integrated to procure the overall profit percentage. The inter-day trading profit is acquired using technical data analysis and the intraday trading profit is reaped through fundamental data analysis. © 2023, The Author(s), under exclusive license to springer Nature singapore Pte Ltd.

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

smart Verification system for Media File Using blockchain 1

Smart Verification System for Media File Using Blockchain

引用

1st International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2022

作者： siddique, s. shireen Fatima, N. sabiyath B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781665497107

In this modern world where information is stored and shared in digital manner in the format of image, video, document privacy and authenticity of the data needs to be preserved which is not an easy task. It has become a major threat where data shared or stored can be tampered or manipulated with and it is very difficult to check for the same. The main principle behind this study is to provide a way to store data in secure manner with the ability to check its authenticity when the need arises. The proposed method integrates blockchain technology to the system which helps to add the media file to the system and store the 256-bit unique hash value generated through keccak-256 hashing algorithm into blockchain using Proof-of-Work protocol. The generated 256-bit hash is stored in blockchain is of immutable nature and it takes approximately 3.5-10-63 seconds to crack the 256-bit encryption. In cases where the need arises to check if the media file is tampered or manipulated it can be done by comparing hash of the media file against hash value that is stored in blockchain. If both hash values are exactly same then the media file is authentic and its integrity is preserved. © 2022 IEEE.

关键词： blockchain

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：