检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Arpitha, K. Lohith, H.R. Nemmadi, H.K. Sujan, K. Yashwanth, C.L. Dept. of Computer Science Engineering BGS Institute of Technology Adichunchanagiri University Mandya India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383867

One of the most serious illnesses that may impact the neurological system in humans is dementia, of which Parkinson' s disease is a major subtype. Patients with Parkinson' s disease have significant behavioural changes. The suggested system uses quantum computing and machine learning to build a speech signal-based method for Parkinson' s disease prediction. Four main machine learning methods are used in this prediction: Artificial Neural Networks, KNN, Decision Trees, and Naïve Bayes. Furthermore, different ensemble learning models are used to combine numerous models and improve the accuracy. An industry standard dataset from the UCI Machine Learning Repository is used to assess the model' s performance. Ensemble models have proven to outperform extremely efficient techniques like neural networks in terms of accuracy. A multi-layer perceptron, a very significant machine learning optimization technique, is incorporated into the suggested system. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Based Classification of Students' Algebraic Responses Using MathBERT Embeddings 5

A Machine Learning Based Classification of Students' Algebra...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Injeti, Anees Sajid Rupsica, G. Neha Reddy, G. Praneetha Balakrishnan, Roshni M. Pati, Peeta Basa Dept of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India

ISBN: (纸本)9798350361155

Conduction of assessments and analysing the students' knowledge is the most important part of any teaching learning process. Traditional manual grading of written mathematical solutions can be time-consuming and laborious, especially for a larger group of students. It takes lot of time and effort to correct these answer scripts. In order to evaluate students' open responses for algebraic inquiries automatically, this project explores the use of MathBERT embeddings, an advanced natural language processing technique with different machine learning classifiers. The model tries to classify the student's responses to either correct or wrong. XGBoost Classifier on the MathBERT embeddings exhibited the best accuracy for this model with 75.3% mean accuracy with standard deviation of 0.016. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Optimization of ARIA Block Cipher Implementation on RISC-V Systems through Instruction Extension 10

Optimization of ARIA Block Cipher Implementation on RISC-V S...

引用

10th International Conference on Platform Technology and Service, PlatCon 2024

作者： Yun, Dongwook Iqbal, Muhammad Kim, Howon Dept. of Computer Science&Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9798350367874

Cryptographic modules in Internet of Things (IoT) devices have had limited use, primarily to meet key requirements such as efficiency and lightweight. However, as IoT devices fulfill more complex roles and handle sensitive information, the need for efficient and lightweight cryptographic modules is increasing. However, traditional software- or hardware-based implementations to provide cryptographic modules result in a tradeoff between efficiency and lightweight. The emergence of the RISC-V architecture presents a new strategy to unify these distinct implementation approaches. RISC-V provides a modular Instruction Set Architecture (ISA) and support for user-extended instructions to enable the configuration of optimal system architectures. Therefore, a new cryptographic algorithm implementation method that integrates existing implementation methods can be presented. This paper presents various strategies for implementing ARIA block cipher, a Korean standard cryptographic algorithm, on a lightweight RISC-V system. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Advancing Healthcare Accessibility: Development of an AI-Driven Multimodal Chatbot 4

Advancing Healthcare Accessibility: Development of an AI-Dri...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Garimella, Bala Subrahmanyam Garlapati, Hari Sharan Choul, Sriharini Cherukuri, Rajesh Lanke, Pallavi B v Raju Institute of Technology Dept.Computer Science and Engineering Narsapur India

ISBN: (纸本)9798350349900

In today's rapidly evolving healthcare sector, the need for efficient and accessible medical assistance is more crucial than ever. With the advancements in Artificial intelligence (AI), healthcare chatbots have emerged as a promising solution to address this need. These chatbots are capable of providing personalized medical information, scheduling appointments, and offering support to patients, thereby enhancing healthcare accessibility and patient engagement. The purpose of this project is to develop an advanced AI-powered healthcare chatbot that builds upon existing technologies to bring significant improvements in patient interaction and healthcare delivery. By leveraging the capabilities of Natural Language Processing (NLP) algorithms and deep learning techniques, the project aims to enhance the chatbot's functionality by integrating multimodal interaction features, enabling users to interact via text, voice, etc and provide more accurate and relevant responses to user queries. Additionally, the project seeks to create a comprehensive patient portal where users can securely access their medical records, reports, appointments, and engage with the chatbot for personalized assistance. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Weighted butterfly optimization algorithm with intuitionistic fuzzy Gaussian function based adaptive-neuro fuzzy inference system for covid-19 prediction

引用

Materials Today: Proceedings 2022年 56卷 3317-3324页

作者： Sundaravadivel, T. Mahalakshmi, V. Dept. of Computer Science and Engineering Annamalai University Tamil Nadu India

Covid-19 cases are increasing each day, however none of the countries successfully came up with a proper approved vaccine. Studies suggest that the virus enters the body causing a respiratory infection post contact with a disease. Measures like screening and early diagnosis contribute towards the management of COVID- 19 thereby reducing the load of health care systems. Recent studies have provided promising methods that will be applicable for the current pandemic situation. The previous system designed a various Machine Learning (ML) algorithms such as Decision Tree (DT), Random Forest (RF), XGBoost, Gradient Boosting Machine (GBM) and Support Vector Machine (SVM) for predicting COVID-19 disease with symptoms. However, it does not produce satisfactory results in terms of true positive rate. And also, better optimization methods are required to enhance the precision rate with minimum execution time. To solve this problem the proposed system designed a Weighted Butterfly Optimization Algorithm (WBOA) with Intuitionistic fuzzy Gaussian function based Adaptive-Neuro Fuzzy Inference System (IFGF-ANFIS) classifier for predicting the magnitude of COVID- 19 disease. The principle aim of this method is to design an algorithm that could predict and assess the COVID-19 parameters. Initially, the dataset regarding COVID-19 is taken as an input and preprocessed. The parameters included are age, sex, history of fever, travel history, presence of cough and lung infection. Then the optimal features are selected by using Weighted Butterfly Optimization Algorithm (WBOA) to improve the classification accuracy. Based on the selected features, an Intuitionistic fuzzy Gaussian function based Adaptive-Neuro Fuzzy Inference System (IFGF-ANFIS) classifier is utilized for classifying the people having infection possibility. The studies conducted on this proposed system indicates that it is capable of producing better results than the other systems especially in terms of accuracy, precision,

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Modular Deep Reinforcement Learning: Enhancing Flexibility through Agent Splitting

Modular Deep Reinforcement Learning: Enhancing Flexibility t...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Tian, Chong Rawat, Danda B. Howard University Dept. of Electrical Engineering & Computer Science WashingtonDC United States

ISBN: (纸本)9798350362480

Deep reinforcement learning (DRL) has shown remarkable success in tackling complex tasks by learning representations directly from raw data. However, as DRL agents become increasingly sophisticated, they often face challenges in adapting to new tasks or environments due to their monolithic structure. In this paper, we prove that by decomposing the agent into modular components, we enable more efficient adaptation as well as more efficient than that of the singular DRL agent on tackling complex tasks. Overall, our work contributes to advancing the field of DRL by introducing a flexible and scalable framework for agent decomposition. By enabling the creation of modular agents, we empower DRL systems to efficiently adapt to changing environments, learn new tasks with minimal intervention, and achieve higher levels of performance and versatility. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Secure Fuzzy Keyword Search in Cloud Computing using Levenshtein Distance and Cryptographic Indexing 5

Secure Fuzzy Keyword Search in Cloud Computing using Levensh...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Jahnavi, M. Haritha, K. Gowtham, R.S.V. Rajgopal, Shinu M. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350389609

Growing usage of the cloud for computing, the necessity for safe and security storage and retrieval of information procedures has become important. This study provides a novel way to tackle the difficulty of searching across encrypted information in the cloud with supporting an inherent fuzzy in queries made by users. The purpose is to allow users to execute searches for keywords on their secure data saved in the cloud while maintaining the secrecy of the data. The approach we propose uses cryptographic methods, notably to secure the information before transferring it to the service. To support fuzzy searches for keywords, we apply approaches such as secure indexing building and similarity rating. This enables users to receive useful data regardless of whether their search request includes errors in spelling, typos, or small changes in the terms. The system structure makes sure a cloud server stays clueless to the details of the encrypted information and the queries used for searching. In addition, we incorporate safety measures to defend against illegal access and to preserve integrity of data throughout the searching process. Thorough tests and experiments, we show the speed as well as effectiveness of our strategy in the areas of search performance, processing overhead, and speed of response, not just enhancing the security of data provided by users but additionally provides an efficient method for safe and flexible retrieval of data in cloud-based systems of storage. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based approach for detection of Resource Depletion Attacks in 5G Networks 5

Deep Learning based approach for detection of Resource Deple...

引用

5th IEEE India Council International Subsections Conference, INDISCON 2024

作者： Sharma, M V Sri Shiva Shourya Tilak Venkata Sai, M. Sankaran, Sriram Amrita Vishwa Vidyapeetham Electronics and Computer Engineering Dept.of Electronics and Communications Kollam India Amrita Vishwa Vidyapeetham Center for Cybersecurity Systems and Networks Kollam India

ISBN: (纸本)9798350376753

Resource Depletion Attacks pose significant challenges to the stability and efficiency of 5G networks, with potential repercussions on service availability, network performance, and user experience. This problem is motivated by the need to understand the complexities of RDAs and their specific impact on the 5G Core networks, to develop effective countermeasures. First, we investigate the vulnerabilities of 5G networks, which make them susceptible to Resource Depletion Attacks. By identifying and analyzing these weaknesses, we aim to gain a comprehensive understanding of potential attack vectors. The problem of modelling and detecting Resource Depletion Attacks (RDA) on 5G Core, aiming to enhance their security and resilience against cyber threats is discussed in this paper. Our proposed attack model will incorporate essential 5G network elements, including base stations, user equipment, and core network components while integrating realistic traffic patterns and usage behaviours. Finally, a Deep learning-based mechanism will be evaluated to counter RDA on 5G Core. We incorporated two deep learning algorithms, specifically LSTM and GRU, which exhibited robust performance by achieving accuracies of 97.62 % and 99.07 %, respectively. The outcomes of our work will contribute to the development of resilient 5 G networks capable of withstanding sophisticated cyber threats, ensuring uninterrupted and secure communication and connectivity services by addressing the challenges posed by Resource Depletion Attacks. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Advancing Image Forgery Detection: A CNN-Based Approach 8

Advancing Image Forgery Detection: A CNN-Based Approach

引用

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Nalini, N. Rakshitha, Sai Nithyashree, H.V. Rakshitha, S.L. Shravan, Motamarri Sai Uttej, K Sai Nitte Meenakshi Institute of Technology Dept. of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798331505462

In the digital age, image forgery is a significant concern due to advanced editing tools. This study addresses the need for reliable forgery detection, focusing on copy-move, splicing, and retouching techniques. Using Convolutional Neural Networks (CNNs) known for learning hierarchical image features, the research developed a robust detection system. The CNN model, trained on a diverse dataset which has over 10,000+ images and it is split into test and train data for better classification results, detected subtle inconsistencies indicative of manipulation, achieving a peak accuracy of 94% over 50 training epochs. Test cases showed the system effectively detected forged images and identified forgery types, though it had shortcomings with invalid inputs. The CNN architecture employed convolutional and max-pooling layers with specific hyperparameters to enhance feature extraction. This paper offers a valuable tool for digital forensics experts, law enforcement, and journalists to ensure the authenticity of visual content. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Flex Sensor Data Analysis for Hand Rehabilitation using Wearable Glove 3

Flex Sensor Data Analysis for Hand Rehabilitation using Wear...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Thangam, S. Reddy, Anusha C. Varun, Ginnaram Hemasri, M. Virupaxappa Kumari, J. Jesy Janet Amrita Vishwa Vidyapeetham Amrita School of Computing Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350369083

Every day we encounter many people with unexpected situations where they suffer from many neuropathological diseases that cause a severe impact on the daily lives of individuals, especially about hand movements, thereby directly affecting the quality of their lives. Traditional methods often lack insights into personalized progress and optimal medication outcomes, which take longer to recover. We have designed an approach based on a novel concept using wearable technology to monitor and assess finger movements. The proposed solution of wearable device integrated flex sensor technology to enhance the rehabilitation process by providing real-time insights by the input of the flex sensors captured by the finger movements of the patients. By sensor data analysis, people get a chance to know their progress and the professionals gain accurate tracking of the progress so that they enhance identifying the areas of improvement and customize the treatment. This innovative approach to designing a wearable device serves as a helping aid to improve patient outcomes by categorizing the stages of improvement into Normal, Mild, and Severe Impairment for a better understanding and helps improve the rehabilitation experience. © 2024 IEEE.

关键词： Personalized medicine

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：