检索结果-内蒙古大学图书馆

DiabetCare – A Classifier based Mobile Application for Predicting the Risk of Prediabetes Mellitus, Gestational Diabetes Mellitus and Type 2 Diabetes Mellitus

DiabetCare – A Classifier based Mobile Application for Pred...

引用

International Research Conference on Smart computing and Systems Engineering (SCSE)

作者： Nirmani Jayaprabha Pathiranage S.M.D. Asanka Sanjaya Suraweera Department of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350375688

ISBN: (纸本)9798350375695

Diabetes mellitus, commonly referred to as diabetes, poses a significant global public health challenge. According to the International Diabetes Federation, the number of people affected by this condition is projected to rise from 415 million to 642 million by 2040. This chronic ailment disrupts the body's ability to absorb glucose, making early risk prediction essential for diagnosis and prevention. This research aims to introduce an innovative AI-driven method for early risk assessment of three distinct types of diabetes. Utilizing medical data from the University of Kelaniya, two different ensemble learning techniques are implemented. These predictions will be accessible through an automated mobile application named "DiabetCare," enabling risk evaluation irrespective of age. The objective is to identify and manage diabetes in its early stages, thereby reducing potential future complications. The experimentation process encompassed the training of 12 machine learning base classifiers and three ensemble techniques for each component. Optimal parameters for each algorithm were determined using the random search cv hyper-parameter tuning method. Ultimately, the most effective base and ensemble models, based on evaluation metrics, were chosen for integration into the final product. In terms of predicting the risk of type 2 diabetes or prediabetes, the Random Forest classifier achieved perfect training accuracy (1.0000), a testing accuracy of 0.8715, an AUC-ROC score of 0.9811, and a Cohen’s Kappa of 0.8037. For forecasting the risk of gestational diabetes, the Stacking classifier attained a perfect training accuracy (1.0000), a testing accuracy of 0.9650, an AUC-ROC score of 0.9963, and a Cohen’s Kappa of 0.9288. The implementation of such a system holds immense potential within the field of diabetes medicine and can serve as a valuable validation tool for medical experts.

关键词： Training Biological system modeling Stacking Diabetes Mobile applications Ensemble learning Risk management

来源：评论

学校读者我要写书评

暂无评论

IoT Based Designing of Secure Data Storage System in Distributed Cloud System with Big Data using Cryptography Algorithm 11

IoT Based Designing of Secure Data Storage System in Distrib...

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Shukla, Ravi Shankar College of Computing and Informatics Saudi Electronic University Department of Computer Science Saudi Arabia

ISBN: (纸本)9781665487320

The cloud system plays a versatile role in the storage of vast data for future references. This includes the delivery of the computing sources that includes the servers with storage, various databases, networking system and software analysis. The web based services provides various usages in versatile forms. The cloud computing helps in numerous pathways for the web based service networks. The security of the data and the privacy constraints are the important aspects involved in the cloud computing techniques. This includes the safeguarding the sensitive data with higher precision. This is accompanied with the intelligent cryptographic algorithm to obtain secure data in the cloud system. This helps to save the data through several data processing applications accompanied with the cryptography algorithm. The cryptography algorithm are enabled to obtain encrypt data so that to have secure communication links in the networking system. This helps in the separation of data with the prescribed files in the distributed cloud networks. The operational time is secured by the classification of data in the form of data packets. © 2022 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

A Distributed Deep Learning Approach with Mobile Edge computing for Next Generation IoT Networks Security

A Distributed Deep Learning Approach with Mobile Edge Comput...

引用

2023 IEEE World Conference on Communication and computing, WCONF 2023

作者： Rathore, Shailendra Sharma, Pradip Kumar Rathore, Heena Abertay University Division of Cybersecurity School of Design and Informatics Scotland Dundee United Kingdom University of Aberdeen Department of Computing Science Aberdeen United Kingdom Texas State University Department of Computing Science TX United States

ISBN: (纸本)9798350311204

Along with recent development in Next Generation IoT, the Deep Learning (DL) has become a promising paradigm to perform various tasks such as computation and analysis. Many security researchers have proposed distributed DL supporting DL task at the IoT device level to deliver low latency and high accuracy. However, due to limited computing capabilities of IoT devices, distributed DL is failed to maintain Quality-of-service demand in practical IoT applications. To this end, BlockDeepEdge, a Blockchain-based Distributed DL with Mobile Edge computing (MEC) is proposed where MEC supports the lightweight IoT devices by delivering computing operations to them at the edge of the network. The blockchain provide a secure, decentralized and P2P interaction among IoT devices and MEC server to carryout distributed DL operation. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Security in Robot Operating Systems (ROS): Analytical Review Study 3

Security in Robot Operating Systems (ROS): Analytical Review...

引用

3rd International Conference on Distributed Sensing and Intelligent Systems, ICDSIS 2022

作者： Mokhamed, Takua Dakalbab, Fatima Mohamad Abbas, Sohail Talib, Manar Abu Department of Computer Science College of Computing and Informatics University of Sharjah United Arab Emirates

ISBN: (纸本)9781839538186

The Robotic Operating System (ROS) is a popular framework for robotics research and development. It's a system that provides hardware abstraction with low-level device management to handle communications and services. ROS is a distributed system, which allows various nodes in a network to communicate using a method such as message passing. When integrating systems using ROS, it is vital to consider the security and privacy of the data and information shared across ROS nodes, which is considered to be one of the most challenging aspects of ROS systems. The goal of this study is to examine the ROS architecture, primary components, and versions, as well as the types of vulnerabilities that might compromise the system. In order to achieve the CIA's three fundamental security criteria on a ROS-based platform, we categorized these vulnerabilities and looked into various security solutions proposed by researchers. We provide a comparative analysis of the ROS-related security solutions, the security threats and issues they addressed, the targeted architecture of the protection or defense system, the solution's evaluation methodology and the evaluation metric, and the limitations that might be viewed as unresolved issues for the future course of action. Finally, we look into future possibilities and open challenges to assist researchers to develop more secure and efficient ROS systems. © IET Conference Proceedings 2022.

关键词： Robot Operating System

来源：评论

学校读者我要写书评

暂无评论

Electrohysterogram Data Augmentation Using Generative Adversarial Network for Pregnancy Outcome Prediction

引用

IEEE Access 2025年 13卷 92468-92482页

作者： Cheema, Muhammad Omar Din, Zia Mohy Ud Imran, Azhar Khan, Fawad Salam Al-Rawi, Mahmood Basil A. El-Meligy, Mohammed Gul, Jahan Zeb Air University Department of Biomedical Engineering Islamabad44000 Pakistan Air University Faculty of Computing & AI Department of Creative Technologies Islamabad44000 Pakistan King Saud University College of Applied Medical Sciences Department of Optometry Riyadh Saudi Arabia Amman Arab University College of Computer Science and Informatics Amman Jordan Maynooth University Department of Electronic Engineering Ireland

There are many difficulties in managing and detecting preterm pregnancies, especially in the early stages. Analyzing electrohysterogram data, which show the electrical activity of uterine muscles, is a promising non-invasive method for classifying term and preterm pregnancies. However, the effectiveness of machine learning classifiers is hampered by the inherent class imbalance in datasets. In order to overcome this constraint, this study uses a Generative Adversarial Network to produce high-quality synthetic EHG data while maintaining the statistical properties of actual signals. By successfully reducing class imbalance, the enhanced dataset makes it possible for machine learning models to be trained with resilience. Real and synthetic features did not differ significantly, according to statistical validation using a t-test (p > 0.05). With this method, the Random Forest classifier obtained a ROC-AUC of 0.99 and a 10-fold cross-validation accuracy of 98%. The suggested GAN-based method’s simplicity and efficacy demonstrate its promise for resolving class imbalance and developing reliable classification systems for diagnostic applications. © 2013 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Neuro-Mimetic Developmental Architecture for Continual Learning through Self-Organizing Multimodal Perception Coordination

引用

IEEE Access 2025年 13卷 91625-91641页

作者： Dawood, Farhan Masuyama, Naoki Loo, Chu Kiong Iqra University Department of Computing & Technology Islamabad Pakistan Osaka Metropolitan University Graduate School of Informatics 1-1 Gakuen-cho Naka-ku Sakai-Shi Osaka599-8531 Japan University of Malaya Faculty of Computer Science and Information Technology Department of Artificial Intelligence Kuala Lumpur50603 Malaysia

Developing cognitive capabilities in autonomous agents stands as a challenging yet pivotal task. In order to construct cohesive representations and extract meaningful insights from the environment, the brain utilizes patterns from a variety of sensory inputs, including vision and sound. Furthermore, related sensory inputs can activate each other’s representations, highlighting the brain’s ability to associate and integrate information across different sensory channels – key to cognitive development and adaptive learning. Current learning methods often mirror the developmental process of infants, who enhance their cognition through guidance and exploration. These methods often struggle with issues such as catastrophic forgetting and stability-plasticity trade-offs. This study presents a novel brain-inspired hierarchical autonomous framework, Cognitive Deep Self-Organizing Neural Network (CDSN), designed to enable autonomous agents to acquire object concepts dynamically. The architecture includes dual parallel audio-visual information pathways, incorporating three layers based on a Topological Kernel CIM-based Adaptive Resonance Neural Network (TC-ART). The first layer, referred to as the receptive layer, learns and organizes visual attributes and object names autonomously in an unsupervised manner. Subsequently, the second layer, the concept layer, distills clustered results from the corresponding receptive layer to create succinct symbol representation. In a synchronized manner, visual and auditory concepts are combined concurrently in the third layer, the associative layer, to establish real-time associative connections between the modalities. Furthermore, this layer introduces a top-down response approach, allowing agents to independently retrieve associated modalities and adapt acquired knowledge in a hierarchical manner. Experimental evaluations conducted on object datasets demonstrate the proposed architecture’s efficacy in online learning and the association o

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Smartwatch-Based Gait Authentication Using Siamese LSTM Networks

Smartwatch-Based Gait Authentication Using Siamese LSTM Netw...

引用

International Conference on Information Technology Research (ICITR)

作者： Rumeth Randombage Nuwan Jayawardene Computing Department Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798331511425

ISBN: (纸本)9798331511432

Smartwatches have become a key component in wearable computing. These devices are tightly woven with the modern smartphone and the user themselves. However, smartwatches lack the ability to employ well-known biometric authentication techniques such as fingerprint scanning and facial recognition due to their physical space constraints and other challenges. Gait analysis is the study of walking patterns, and it is known to be a feasible authentication technique, especially using the accelerometer and gyroscope sensors within smartphones. This study explores the feasibility of a gait-based authentication scheme that uses accelerometer and gyroscope data from a commercially available smartwatch device. A novel approach of using Lightweight Siamese long-short term memory (LSTM) networks to identify unique features from two sets of sensor data is proposed for performing gait-based authentication. Furthermore, the computational costs of executing this type of authentication scheme are also explored with the proposed LSTM model architecture.

关键词： Accelerometers Filters Computational modeling Authentication Computer architecture Feature extraction Data models Sensors Gyroscopes Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Analyzing video footage from security cameras using the Amped FIVE professional tool specifically for the identification of vehicle license plates 4

Analyzing video footage from security cameras using the Ampe...

引用

4th International Conference on computing, Networking, Telecommunications and Engineering Sciences Applications, CoNTESA 2023

作者： Gvozdanovic, Misel Delija, Damir Tulicic, Domagoj Sirovatka, Goran Zagar, Marinko Bilic, Krunoslav Zagreb University of Applied Science Department of Informatics and Computing Zagreb Croatia University of Applied Sciences in Information Technology Department of Computer Systems and Networks Zagreb Croatia

ISBN: (纸本)9798350382754

This paper describes problems of improving security cameras' video footage for forensic investigation. When processing records, one encounters problems with low resolution, poor lighting, or excessive distance of a key object in an image or video. Using the Amped FIVE Professional tool, forensic scientists create videos and analyze and process the record itself using various filters. Record quality demands a choice of video filters. The use and selection of filters show the improvement of the record itself to the level to which useful information can be obtained in this case of vehicle license plates. The presented roadmap can be used as the base for further video forensic research. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Behavioural Characteristics and Cyberbullying Profiles among Malaysian Youngsters 1

Behavioural Characteristics and Cyberbullying Profiles among...

引用

1st International Visualization, informatics and Technology Conference, IVIT 2022

作者： Anwar, Rina Md. Din, Marina Md. Bakar, Asmidar Abu Abdul Latif, Aliza Rahim, Fiza Abdul Institute of Informatics and Computing Energy Kajang Selangor Malaysia Universiti Teknologi Malaysia Razak Faculty of Technology and Informatics Advanced Informatics Department Kuala Lumpur Malaysia

ISBN: (纸本)9781665486484

Cyberbullying is a variation of bullying that involves the use of technology to abuse others. This study examined the relationship between behavioural characteristics and cyberbullying profiles among youngsters. A total of 221 youngsters aged between 15-30 in Malaysia were surveyed, and their raw scores ran through statistical analysis. Findings show that the majority of the participants have never engaged in cyberbullying, but a few of them had experienced cyberbullying. Findings from the survey revealed that the percentages of female participants as cybervictims are higher (63.7%) than male participants (36.3%), while the percentages of male participants as bullies are higher (52.9%) than female participants (47.1%). The most prominent behaviour of cyberbullies is sending mean messages directly to cybervictims and the most prominent behaviour of cybervictims is being excluded from online groups. © 2022 IEEE.

关键词： Computer crime

来源：评论

学校读者我要写书评

暂无评论

Enhancing Brain Tumor Diagnosis: A Comparative Review of Systems with and without eXplainable AI

Enhancing Brain Tumor Diagnosis: A Comparative Review of Sys...

引用

Information Communication Technologies Conference (ICTC)

作者： Janidu Chathumina Krishnakripa Jayakumar Department of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350373523

ISBN: (纸本)9798350373530

Deep Learning (DL) and computer vision may be used to distinguish between various anatomical features in the human body. As technology has developed, several DL methods have been used to diagnose brain tumors and have shown promise in terms of early diagnosis. Nevertheless, due to their lack of explainability and state-of-the-art (SOTA) accuracy, a smooth integration of these technologies into clinical workflows raises issues. Existing literature reveals that certain studies have obtained SOTA performance by experimenting with cutting-edge technologies and where the model exhibits a black-box nature, several eXplainable Artificial Intelligence (XAI) techniques have been used to resolve their explainability issues. This review paper will include an overview of brain tumors, a review of the recent research publications that involve XAI, and which do not, along with the techniques used and their performances. A comparative analysis will be presented to gather ideas on the strengths and weaknesses while narrowing down the limitations to discover research gaps which need to be addressed. Finally, key findings from the review which will be followed by concluding remarks and a possible future scope will be included at the end.

关键词： Deep learning Computer vision Accuracy Reviews Explainable AI Closed box Brain modeling

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：