检索结果-内蒙古大学图书馆

10th International Conference on Frontiers of Intelligent Computing: Theory and applications, FICTA 2022

作者： Dash, Satya Ranjan Roy, Saurav Mohanty, Jnyana Ranjan Meedeniya, Dulani Mishra, Manoj Ranjan School of Computer Applications KIIT University Odisha India School of Biotechnology KIIT University Odisha India Department of Computer Science and Engineering University of Moratuwa Sri Lanka India

ISBN: (纸本)9789811975233

Machine learning has opened a new era of effective and easy ways of data analysis in biological research. The use of high throughput data analysis tools and libraries facilitated cancer research among many other benefits. Breast cancer is one of the main reasons for mortality among women. Apart from traditional molecular detection, it is also necessary to find an alternate approach. With the advent of modern technology, clinicians and healthcare providers can improve diagnosis accuracy and detection. In this study, we use a simple layer-based deep learning approach to investigate the malignancy of breast cancer. Our finding includes shows over 97% accuracy with the ANN-based machine learning approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Enhanced Marathi Speech Recognition Facilitated by Grasshopper Optimisation-Based Recurrent Neural Network

引用

computer Systems science & engineering 2022年第11期43卷 439-454页

作者： Ravindra Parshuram Bachate Ashok Sharma Amar Singh Ayman AAly Abdulaziz HAlghtani Dac-Nhuong Le School of Computer Science and Engineering Lovely Professional UniversityPunjab144001India Department of Computer Science and IT University of JammuJammu and Kashmir180006India School of Computer Applications Lovely Professional UniversityPunjab144001India Department of Mechanical Engineering College of EngineeringTaif UniversityTaif21944Saudi Arabia School of Computer Science Duy Tan UniversityDanang550000Vietnam Institute of Research and Development Duy Tan UniversityDanang550000Vietnam

Communication is a significant part of being human and living in the *** kinds of languages and their variations are there;thus,one person can speak any language and cannot effectively communicate with one who speaks that language in a different *** application fields such as education,mobility,smart systems,security,and health care systems utilize the speech or voice recognition models ***,various studies are focused on the Arabic or Asian and English languages by ignoring other significant languages like Marathi that leads to the broader research motivations in regional *** is necessary to understand the speech recognition field,in which the major concentrated stages are feature extraction and *** paper emphasis developing a Speech Recognition model for the Marathi language by optimizing Recurrent Neural Network(RNN).Here,the preprocessing of the input signal is performed by smoothing and median *** preprocessing the feature extraction is carried out using MFCC and Spectral features to get precise features from the input Marathi Speech *** optimized RNN classifier is used for speech recognition after completing the feature extraction task,where the optimization of hidden neurons in RNN is performed by the Grasshopper Optimization Algorithm(GOA).Finally,the comparison with the conventional techniques has shown that the proposed model outperforms most competing models on a benchmark dataset.

关键词： Deep learning grasshopper optimization algorithm recurrent neural network speech recognition word error rate

来源：评论

学校读者我要写书评

暂无评论

Integration of Clinical and Imaging Data for Enhancing Oral Cancer Detection Using Deep Learning

Integration of Clinical and Imaging Data for Enhancing Oral ...

引用

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

作者： Shakila, M. Dhasaratham, M. Saranya, N. Naga Thotapalli, Aruna Telrandhe, S.V. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Tkr College of Engineering and Technology Department of Information Technology Hyderabad India Saveetha College of Liberal Arts & Science Simats Department of Computer Applications Chennai India Cvr College of Engineering Department of Information Technology Telangana Hyderabad India Guru Nanak Institute of Engineering & Technology Department of Etc Nagpur India

ISBN: (纸本)9798350360660

This study aims at unlocking the integration of clinical and imaging data using the deep learning model for enhancing the diagnosis of oral cancer cases. Therefore, for image analysis, in this paper proposed to major on CNNs while for clinical data, our Research used RNNs and hence came up with a unique architecture. The proposed model was trained on the patients' records and Histopathological Images Database from 5000 patients. As for the overall measure of accuracy of all of the constructed classifiers applying our integrated model the result was 94 %. Specificity achieved for the system was 7% while sensitivity was 93% for the oral cancer. 2%, sensitivity of 69.1%. This is an improvement of the previous methods that required either imaging or clinical data to obtain accuracy approximated at 85-90 percent. As a unique effectiveness factor of increasing the accuracy of oral cancer diagnosis, it is proposed to use an integration of clinical and imaging data through deep learning, which can also result in inclusion of the diagnosis at the early stages of the disease, thereby enhancing the prognosis of the illness. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Risk Modelling and Prediction of Financial Management Using FTL-CSGRU Approach 1

Risk Modelling and Prediction of Financial Management Using ...

引用

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Mothilal Nehru, G. Kudare, Roopali P. Karnawat, Amrita Tatia Rohini, J. Singh, Saurabh Nishant, Neerav SRM UNIVERSITY Faculty of Science & Humanities Department of computer Applications Chengalpattu India PCET's S B Patil Institute of Management Department of MBA Maharashtra Nigdi Pune India Indira School of Business Studies Tathawade Maharashtra Pune India Erode Sengunthar Engineering College Computer Science and Engineering Tamil Nadu Perundurai India Prestige Institute of Management and Research Department of Finance Indore India School of Engineering Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350371802

The need of building information technology is becoming more evident to those working in corporate financial management as the digital era arrives. An increasing number of modern societies are using enterprise resource planning (ERP) systems for their financial management needs. That way, companies can collect financial data in real-time and analyze it later. The steps of preprocessing, feature extraction, and training the model are all sequentially laid out. When it comes to statistical approaches used for data preprocessing, z-score normalization, decimal scaling, and min-max all offer very accurate results. You get the greatest results with MCML when you compare it to NCA, PCA, and Cluster-cluster LDA, the four approaches that comprise feature extraction. The suggested method employed an FTL-CSGRU strategy for model training. This method seems antiquated in comparison to the cutting-edge FTL and GRU. The statistics showed a significant improvement with an accuracy rating of 97.36%. © 2024 IEEE.

关键词： Enterprise resource planning

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling for Disease Progression in Chronic Conditions Using Machine Learning 6

Predictive Modeling for Disease Progression in Chronic Condi...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Umamaheswari, T.S. Dhaygude, Amol Dattatray Dewangan, Omprakash Krishnan, T. Yerpude, Poonam Swarnkar, Suman Kumar Jayagovind Harigopal Agarwal Agarsen College Department of Computer Applications Chennai India University of Washington Department of Data Science Seattle United States Kalinga University Department of CS & IT Chhattisgarh Raipur India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vijayawada India Indian Institute of Technology Department of Computer Science & Engineering Bhilai India Shri Shankaracharya Institute of Professional Management and Technology Department of Computer Science and Engineering Raipur India

ISBN: (纸本)9798350304480

Predictive modeling of disease progression in chronic conditions is a crucial task in healthcare, as it enables early identification and personalized intervention for patients at risk of adverse outcomes. In recent times, there has been a notable advancement in the field of machine learning techniques, which has demonstrated considerable potential in accurately forecasting the evolution of diseases. This development has proven to be highly beneficial for healthcare professionals, as it equips them with vital insights that can significantly enhance the management of patients. This research paper provides a thorough examination and comparative evaluation of different machine learning algorithms in the context of forecasting the course of diseases in chronic situations. We explore the use of diverse datasets containing longitudinal patient records, clinical variables, and disease-specific markers to train and evaluate predictive models. The study also investigates the impact of feature selection and data preprocessing techniques on the model's performance. Moreover, we assess the generalizability and robustness of the models across different chronic diseases to determine their potential for broader clinical applications. The results demonstrate that machine learning models can effectively predict disease progression, with certain algorithms outperforming others in specific scenarios. The research findings presented in this study offer significant contributions to the understanding and implementation of machine learning techniques for predicting disease development. The aforementioned realizations have the potential to be of substantial assistance to medical professionals in terms of making well-informed decisions, which will ultimately lead to better outcomes for patients. © 2023 IEEE.

关键词： Chronic conditions Clinical applications Clinical variables Data preprocessing Disease progression Feature selection Generalizability Healthcare Longitudinal patient records Machine learning Patient outcomes Predictive modeling

来源：评论

学校读者我要写书评

暂无评论

computer Vision-Hybrid Learning based on Multi Scale Dilated Convolution Module Mechanism Implemented for Object Detection 1

Computer Vision-Hybrid Learning based on Multi Scale Dilated...

引用

1st IEEE International Conference on Automation, Computing and Renewable Systems, ICACRS 2022

作者： Kalpanadevi, D. Kartheeban, K. Mayilvaganan, M. Bamaruckmani, P. Department of Computer Applications Kalasalingam Academy of Research and Education Krishnan Koil India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Krishnankoil India Department of Computer Science PSG College of Arts and Science Coimbatore India Department of Computer Science and Computer Applications Ayya Nadar Janaki Ammal College Sivakasi India

ISBN: (纸本)9781665460842

For smart traffic management and highway regulation, vehicle detection and statistics in highway surveillance video scenes are crucial. The massive installation of traffic surveillance cameras resulted in the collection of a sizable database of traffic video footage for analysis. In order to achieve the best detection from prediction, YOLOV3 (You Only Look Once) can be achieved in this study by including a multi-scale augmentation convolutional module technique. The first camera reads the licence plates of approaching vehicles before blockchain technology is used to store predictions in the cloud. It can display available parking spaces and be embedded in parking spaces. If there aren't any open spots, they are shown similarly. To make sure the automobile stays in the parking spot after it leaves the lot, a second camera scans the licence plate once again and matches it to the time of arrival. The size of vehicle objects varies substantially when viewed from this angle, and it is harder to spot small items that are off the road. It is crucial to successfully address the aforementioned issues and further apply them while dealing with complicated camera scenarios. This article concentrates on the aforementioned issue and offers a workable method so that the outcomes of vehicle detection can be used for tracking numerous objects and vehicle counts. The convolutional network's takes an input must be a fixed size, and its more complex structure necessitates lengthy training sessions and substantial resources. It extracts the feature points that need to be identified, compares them with the ORB algorithm, establishes road detection lines, and counts the number of moving vehicles and the volume of traffic. © 2022 IEEE

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Facial Feature Extraction with AI: An Innovative Approach

Revolutionizing Facial Feature Extraction with AI: An Innova...

引用

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： B. Lakshmi Jandhyam Lakshmi Alekhya K Parish Venkata Kumar B. Kishore K. Kamala Nyni K. Likhita Dept. of Computer Applications V.R. Siddhartha Engineering Dept of computer science and engineering V.R. Siddhartha Engineering College Department of Computer Applications V.R. Siddhartha Engineering College Department of Computer Applications

This paper provides a technique for detecting human faces & extracting their features based on segmentation of skin tone & facial structure. The system goes through several stages. The method first searches for regions where faces might be present by segmenting skin tone. After performing various morphological operations on skin, it uses aspect ratio of a face to find viable face blocks. face blocks are then used to extract additional features. Therefore, one may identify and validate a person's image using their face features by using this biometric attribute. To enhance facial recognition, numerous researchers have employed Support Vector Machine (SVM), Principal Component Analysis (PCA), a combination of SVM and PCA, PCA with an Artificial Neural Network, and even the conventional PCA-SVM. Due to PCA-ANN's limited dataset limitation, PCA-SVM is superior to PCA-ANN. To extract features, relative location & size are used. If algorithm is unable to identify even one feature in a prospective face block, it rejects face block.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securing Neural Network in the Cloud: A Systematic Approach of Cloud Security Based on ANN-SVM Model 4

Securing Neural Network in the Cloud: A Systematic Approach ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Arunarani, Ar Vijayagopal, V. Kartheesan, L. Dwivedi, Vijay Kumar Rajesh Kumar, A. Nishant, Neerav School of Computing College of Engineering Srm Institute of Science and Technology Department of Computational Intelligence Tamilnadu Chennai India Dr. M.G.R. Educational and Research Institute Faculty of Computer Applications Tamilnadu Chennai India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Vishwavidyalaya Engineering College Department of Mathematics Chhattisgarh Surguja India N.S.N. College of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Karur India School of Engineering Babu Banarasi Das University Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798331540364

Many services have made the transition to the cloud because of the increased reliability and efficiency of cloud computing. Due to their capacity to ease service access while also securing communications in the public network, the three-factor Mutual Authentication and Key Agreement (MAKA) protocols are seeing increased use in multi-server designs. A lack of formal security proof or high communication and computation costs makes the limited three-factor MAKA protocols that are currently available susceptible to a wide range of attacks. The proposed approach consists of three phases, which are preprocessing, feature selection, and model training. Text scheduling and normalization make up preprocessing. In feature selection, the PSO is an optimization method that uses a population-based approach to find optimal solutions. An ANN-SVM was employed throughout the model's training phase. With an average accuracy of 93.30%, the proposed technique surpasses ANN and SVM. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Grouping nodes based PBFT for Preventing Fake Educational Certificates Verification 25

Grouping nodes based PBFT for Preventing Fake Educational Ce...

引用

26th International Conference on Distributed Computing and Networking, ICDCN 2025

作者： Kumar, Amritesh Bhatia, Nitin Das, Debasis IDRP: IoT and Applications Indian Institute of Technology Jodhpur Rajasthan Jodhpur India Department of Electrical Engineering Indian Institute of Technology Jodhpur Rajasthan Jodhpur India Department of Computer Science and Engineering Indian Institute of Technology Jodhpur Rajasthan Jodhpur India

ISBN: (纸本)9798400710629

The traditional PBFT consensus mechanism in a blockchain network tolerating 33% node failure faces various challenges, including incorrect data verification, transaction communication complexity, and higher consensus delay in larger networks. In case of appending a block carrying the Educational Certificates (ECs) the impact of node error due to external attacks could lead to production of fake degrees in the system. To address the challenge of fraudulent degree verification, we propose a novel Grouping nodes-based Practical Byzantine Fault Tolerance (GnPBFT) consensus algorithm. We show that the GnPBFT algorithm gives higher probability to prevent fake certificate verification as compared to the PBFT in same network setting. Furthermore, we also show that our scheme is resilient against Sybil attack, with improved performance metrics such as 33% reduction in transaction overhead and 29% decrease in consensus latency. © 2025 Copyright held by the owner/author(s).

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Fine- Tuning Pre-trained Models for Aspect-Based Sentiment Analysis of Amazon Food Reviews

Fine- Tuning Pre-trained Models for Aspect-Based Sentiment A...

引用

2025 International Conference on computer, Electrical and Communication engineering, ICCECE 2025

作者： Sridhar, D. Manikandan, K.B. Padma Priya, R.S. Pradeepa, D. Vasumathi, B. Shankar, R. Alliane University Alliance College of Engineering and Design Central Campus Karnataka Bangalore India Hyderabad India Vignan's Foundation for Science Technology and Research Department of Information Technology and Computer Applications Guntur India Reva University School of Computer Science and Applications Bangalore India Brainware University Department of Computational Sciences West Bengal India Bharathiar University Research in Commerce Coimbatore India

ISBN: (纸本)9798331513894

The process of classifying consumer responses to a particular product review as neutral, negative, or positive is known as sentiment analysis. Product owners can utilize sentiment analysis for assistance in them decide whether to continue producing their product, increase production, or eliminate production altogether. As a result, they will gain a deeper comprehension of how customers feel about their products. The method used to determine the opinions expressed in the review regarding a specific feature or aspect of the product is called Aspect Based Sentiment Analysis, or ABSA. Numerous machine learning and natural language processing models are currently available for ABSA. The inability to precisely identify and categories the views expressed towards particular features is a major drawback of the aspect-based sentiment analysis (ABSA) techniques presently in usage for Amazon food assessment tasks. The Hybrid Contextual Aspect-Based Sentiment Analyzer (HCABSA), a hybridized framework for aspect-based sentiment analysis, is developed in this research to accurately assess the sentiment of Amazon food reviews through a number of processes. This research starts by collecting dataset for Amazon food reviews from Kaggle, preprocessing the data to eliminate noise and irrelevant information, and then using POS tagging to identify the specific aspects and sentiment words related to those aspects, which are nouns and adjectives in the review using the Lexicon based approach. In the following stage, the frequency-based candidate extraction method is utilized to pick the characteristics that are used to determine the product's internal and exterior features. The raw data is then transformed into features that the machine learning models can access using the Bag of Words feature extraction process. The Gradient Boosting Decision Tree technique is then used to categories the sentiment as either positive or negative. Using performance metrics like accuracy, precision, recall,

关键词： Decision trees

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：