检索结果-内蒙古大学图书馆

Integrated Circuits, Communication, and Computing systems (ICIC3s), International Conference on

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

ISBN: (数字)9798350364088

ISBN: (纸本)9798350364095

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.

关键词： Accuracy sensitivity Parkinson's disease Computed tomography Magnetic resonance imaging Computational modeling Medical services

来源：评论

学校读者我要写书评

暂无评论

引用

5th International Conference on Intelligent Computing and Applications, ICICA 2019

作者： Karthick, s. Yuvaraj, N. Rajakumari, P. Anitha Raja, R. Arshath Department of Computer Science and Engineering SRM Institute of Science and Technology DelhiNCR Campus Ghaziabad India Department of Computer Science and Engineering St. Peters Institute of Higher Education and Research ChennaiTamil Nadu India Department of Electronics and Communication Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology ChennaiTamil Nadu India

ISBN: (纸本)9789811555657

Many attempts are made to resolve the clustering problem over categorical dataset through the process of clustering ensemble. However, the conventional techniques failed to generate proper data portioning to cluster the data due to the presence of incomplete information. Hence, this paper uses a modified cluster ensemble similarity framework to cluster the relevant categorical datasets, and a weight-b.s.d similarity approach has been proposed to work with type II full-space and subspace ensembles that involve random-k and fixed-k techniques. The centroid selection is initiated using swarm-b.s.d bio-inspired optimization method or swarm-b.s.d similarity ensemble clustering (WsE). Finally, Division Reminder Hashing (DRH) technique is used to determine the weights of the cluster using similarity measurement. This technique helped in eliminating the null and duplicate datasets. The measurement for testing includes Adjusted Rand (AR), Normalized Mutual Information (NMI), and Classification Accuracy (CA). The performance of the proposed technique is tested over University of California Irvine (UCI) dataset, and the results proved that the proposed technique provides better clustering using Type-2 and Type-3 ensemble. © 2021, springer Nature singapore Pte Ltd.

关键词： swarm intelligence

来源：评论

学校读者我要写书评

暂无评论

P systems b.s.d on sticker operations

P systems based on sticker operations

引用

6th International Conference on bio-Inspired Computing: Theories and Applications, bIC-TA 2011

作者： Masilamani, V. Venkatesan, A.s. Prasanna Thomas, D.G. Department of Computer Science and Engineering IIITD and M Kancheepuram Chennai - 600 036 India Department of Mathematics B.S. Abdur Rahman University Chennai - 600 048 India Department of Mathematics Madras Christian College Chennai - 600 059 India

ISBN: (纸本)9780769545141

sticker systems, a computability model introduced by L. Kari et al. (1998) are language generating devices b.s.d on the sticker operation. In this paper, a theoretical study about a new class of P system b.s.d on the sticker operation has been presented. such a system has double stranded sequences with sticky ends as objects and sticker operations as evolution rules in its regions. We compare the language generated by this system with regular languages. © 2011 IEEE.

关键词： Formal languages

来源：评论

学校读者我要写书评

暂无评论

An intelligent approach for reasoning the stories using case b.s.d reasoning and rule b.s.d reasoning

An intelligent approach for reasoning the stories using case...

引用

International Conference on Intelligent Agent & Multi-Agent systems (IAMA)

作者： A. Jaya G.V. Uma Faculty of Computer Science & Engineering B.S. Abdur Rahman Crescent Engineering College Chennai India Faculty of Computer Science &Engineering Anna University Chennai India

Reasoning is the cognitive process of analyzing for certain conclusion, beliefs. because of sixth sense, the human beings can analyze the facts and derive the conclusion from it. In the artificial intelligence era, to make the computer system to analyze and reason the facts and derive the conclusion is very difficult to perform. The reasoner algorithm helps to reason the stories for the dynamic construction of new stories with help of ontology. Ontology is a formal explicit shared conceptualization for anything that exists in the world. Ontology helps to check the semantic consistency b.s.d on the domain knowledge acquired. This paper focuses on the intelligent approach for reasoning the stories.

关键词： Ontologies sections Artificial intelligence computer science Character generation Humans Educational institutions Animals birds Cities and towns

来源：评论

学校读者我要写书评

暂无评论

Enhancing speech Emotional Recognition through a Multi-Layer Perceptron Model

Enhancing Speech Emotional Recognition through a Multi-Layer...

引用

Trends in Electrical, Electronics, computer engineering Conference (TEECCON)

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An effective assessment of knowledge sharing and E-learning portals

引用

International Journal of Web-b.s.d Learning and Teaching Technologies 2015年第2期10卷 1-12页

作者： subramanian, D. Venkata Geetha, Angelina shankar, P. Department of Computer Science and Engineering Saveetha University Tamilnadu India Department of Computer Science and Engineering B.S. Abdur Rahman University Tamilnadu India Saveetha University Tamilnadu India

In recent years, most of the companies have increasingly realized the importance of the knowledge sharing portal and E-Learning portals to provide competitive knowledge for their employees. The knowledge stored in these portals varies from technical, process and project knowledge functional or domain specific knowledge to face the competitiveness among other companies or organizations, especially in industrialized countries. More than three-fourths of organizations have focused on their investment in technology and process trends that encourage user collaboration through Knowledge sharing and e-Learning Portals. There are many number of challenges in evaluating the effectiveness of the E-Learning Portals and Knowledge Portals. The primary goal of this paper is to illustrate how a domain independent multi-dimensional metric model and metric datab.s. can be built to assess the effectiveness of the Web b.s.d Knowledge and E-Learning Portals. Copyright © 2015, IGI Global.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of a Handwritten Digit Recognition Using CNN-WOA

Performance Analysis of a Handwritten Digit Recognition Usin...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： s. Nandhini Devi N. sabiyath Fatima Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science & Technology Chennai TanilNadu India

Handwritten Digit Recognition (HDR) techniques are acquiring favor in academia and b.s.ness. because of their complex and irregular patterns, handwritten texts are difficult to recognize. Word retrieval in limited-resource scripts is complex and time-consuming. Randomizing samples and increasing the size of training datasets enhance deep learning and neural network, models. HDR techniques heavily rely on manually-programmed key point information. The writing styles and dimensions of the input sample make numerical identification and categorization difficult. This work circumvents these limitations by employing a CNN model and an effective HDR scheme. HDR enhances the classification accuracy of the MNIsT dataset. The Gaussian filter and the Convolution algorithm polish the numbers. CNN-WOA is indicated as the model because the Algorithm for Whale Optimization Algorithm (WOA) fine-tunes CNN parameters. Using accuracy, precision, recall, specificity, AUC, F1-score, and false positive rate, simulation outcomes of the CNN-WOA model are compared to state-of-the-art techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ILAPP: An Efficient Design of sign Language Recognition system using Intelligent Learning Assisted Prediction Principles

ILAPP: An Efficient Design of Sign Language Recognition Syst...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and smart Electrical systems, ICsEs 2023

作者： Radha, K. Harikrishnan, R. Niresh Kumar, s. Hubert Mary, L. Rajendran, N. Dr.Mahalingam College of Engineering and Technology Department of CSE Coimbatore Pollachi India S.A. Engineering College Department of ECE Chennai India St. Joseph's College of Engineering Department of Computer Science and Engineering Chennai India Jeppiaar Institute of Technology Department of ECE Chennai India B.S. AbdurRahman Crescent Institute of Science and Technology Department of Information Technology Chennai Vandalur India

ISBN: (纸本)9798350319200

In this study, we introduce ILAPP (Intelligent Learning Assisted Prediction Principles), an innovative design for a sign Language Recognition system. ILAPP harnesses the power of Convolutional Neural Networks (CNN) for efficient feature extraction and employs the renowned LeNet-5 Model for rob.s. classification. sign language recognition is a critical technology that bridges communication gaps for individuals with hearing impairments. Our system, ILAPP, offers an efficient and effective solution to this challenge. The core of ILAPP lies in its utilization of CNNs to extract essential features from sign language images, capturing intricate patterns and nuances crucial for accurate classification. The LeNet-5 Model is employed for classification, benefiting from its proven capabilities in image recognition tasks. Our research focuses on enhancing the accuracy and efficiency of sign language recognition, aiming to provide a practical tool for the deaf and hard-of-hearing community. ILAPP represents a significant advancement in this field, and its promising results underscore its potential for real-world applications. This study showcases the fusion of intelligent learning principles with state-of-the-art models, highlighting the importance of leveraging AI in addressing accessibility and communication *** our study, the proposed model demonstrates an impressive accuracy rate of 98.23% when compared to existing models. This high accuracy rate signifies the exceptional performance and effectiveness of our model in sign language recognition. © 2023 IEEE.

关键词： Convolutional Neural Networks (CNN) Intelligent Learning Assisted Prediction Principles

来源：评论

学校读者我要写书评

暂无评论

Prediction and Classification of Handwritten Digits using DRNN-WOA model with Radiomics Features

Prediction and Classification of Handwritten Digits using DR...

引用

International Conference on Power, Energy, Control and Transmission systems (ICPECTs)

作者： s. Nandhini Devi N. sabiyath Fatima Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science & Technology Chennai Tamil Nadu India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508852

Words in handwriting are notoriously difficult to identify and distinguish because of their complex and irregular shapes. Word retrieval is a challenging and time-consuming process in low-resource scripts. To get the most out of deep learning and neural network models, it is necessary to employ large amount trained datasets and present randomness into the existing structure. Existing HDR methods rely primarily on hand-coded key points data. The wide variety of writing styles, as well as size fluctuations in the input sample, make accurate recognition and categorization of numerals to be a difficult task. To overcome these constraints, this research work introduces a Deep-Recurrent (DRNN) Neural Network model and provides an effective and efficient HDR system. before considering pre-processing to enhance prediction and classification accuracy, HDR is applied to the MNIsT and DIDA datasets. both the Convolution algorithms and the Gaussian filters are used to refine the digits. The DRNN model receives the extracted features called Radiomics as input. since the Whale Optimization Algorithm (WOA) is used to fine-tune the DRNN's parameters, the suggested type is called DRNN-WOA. Accuracy, recall, F1- score, specificity, AUC, precision, and false positive rate are some metrics used to compare the proposed DRNN-WOA model.

关键词： Accuracy Neural networks Training data Predictive models Prediction algorithms Feature extraction Data models Classification algorithms Testing Radiomics

来源：评论

学校读者我要写书评

暂无评论

Risk Prediction in Financial Transactions Using IoT big Data Analytics

Risk Prediction in Financial Transactions Using IoT Big Data...

引用

Electronics and sustainable Communication systems (ICEsC), 2020 International Conference on

作者： P. Chidambaranathan V. MuthuPriya Department of Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

The Internet of Things is a network of appliances and other items that can communicate and distribute data; as a result, Internet of Things are equipped with actuators, sensors, microelectronics, software, and connections. IoT devices, to put simply, share data over wired or wireless networks. Inventions of IoT have endless possibilities that can make a huge difference in the world. IoT is having the most effect on b.s.ness since has altered not just how various corporate processes are conducted, but also how the economy is managed. big data and IoT help optimize operations, reducing costs, enhancing productivity and improving lives. Globally, financial institutions and banks are coming up with fresh, creative approaches to quickly assimilate big data analytics for every step of the process in with the intention of maximizing efficiency. Numerous previous studies mostly concentrate on risk assessment along with big data analytics together in the banking industry; nevertheless, might not particularly address the difficulties posed by cross-border transactions. The purpose of the proposed study is to close this gap by focusing on the particulars and bringing up the approach of big data analytics for risk assessment in cross-border transactions.

关键词： Industries Technological innovation Reviews Wireless networks banking big Data software sensors Internet of Things Risk management

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：