检索结果-内蒙古大学图书馆

A Logical Evaluation of Predicting Immune System Strength by using Enhanced Deep Learning Strategy

A Logical Evaluation of Predicting Immune System Strength by...

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Malathi, K. Ramkumar, M. Ruby, E. D. Kanmani Santhi, G.B. Korde, Vivek Aljawawdeh, Hamzeh J. Saveetha University Department of Cse Chennai India Veltech Rangarajan Dr Sagunthala R & D Institute of Science & Technology Department of Ece Chennai India New Prince Shri Bhavani College of Engineering and Technology Department of Computer Science and Engineering Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa University Faculty of information technology Department of software engineering Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

The immune system plays a crucial role in defending the body against diseases, making it vital to develop models that can accurately predict immune system strength. This study presents an Enhanced Deep Learning Strategy (EDLS) designed to predict immune system strength based on immune-related biomarkers such as White Blood Cell (WBC) count and Immunoglobulins. A dataset consisting of 23,654 records with 12 features was collected from clinical sources. The data underwent comprehensive preprocessing, including noise reduction using a Median Filter, feature selection with Random Forest, and data fusion using Kalman Filters. The EDLS model integrates AutoEncoder for dimensionality reduction and Cascaded Long Short-Term Memory (LSTM) for capturing temporal dependencies. The proposed model outperforms nine traditional and advanced machine learning models, including Logistic Regression, Support Vector Machine (SVM), and Convolutional Neural Network (CNN), with an accuracy of 94.72%. Evaluation metrics such as Precision (92.01%), Recall (93.77%), and F1-Score (92.88%) highlight the model's effectiveness in predicting immune system strength. Feature importance analysis reveals that WBC count and Immunoglobulins are the most influential predictors. This study demonstrates the potential of EDLS for enhancing immune strength prediction, which can have significant implications for personalized healthcare and disease prevention. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Self-Reported Learning Strategies and Preferences in Health Informatics

Self-Reported Learning Strategies and Preferences in Health ...

引用

34th Medical Informatics Europe Conference, MIE 2024

作者： Rohani, Narjes Gallagher, Michael Gal, Kobi Banas, Kasia Manataki, Areti Usher institute University of Edinburgh United Kingdom Moray House School of Education and Sport University of Edinburgh United Kingdom School of Informatics University of Edinburgh United Kingdom Dept. of Software and Information Systems Engineering Ben-Gurion University Israel School of Computer Science University of St Andrews United Kingdom

ISBN: (纸本)9781643685335

Despite the proliferation of educational programmes in Health Informatics (HI) worldwide, there is limited knowledge regarding students' preferences and learning strategies in HI courses. To address this gap, we conducted a study to gather and analyse data from three HI courses. Employing the Motivated Strategies for Learning Questionnaire (MSLQ) and theories of deep and surface learning, we designed a questionnaire to collect data. The analysis of students' responses indicates that machine learning emerges as one of the most interesting topics, while certain topics such as data wrangling of genomics data were more challenging for students. Students expressed a preference for sequential learning. They exhibited multimodal tendencies regarding the type of learning resources, with tendency to prefer learning resources that have more visual contents. In all three courses, learners reported using deep learning strategy rather than surface learning, yet they appear to struggle with employing organisation, elaboration, and peer learning tactics. This study provides valuable insights into HI education, offering recommendations for educators, learners, and researchers to enhance HI education. © 2024 The Authors.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Designing Quantum-Safe Lattice-Based Multi-Authority CP-ABE Scheme for Blockchain-Enabled IoT-Based Consumer Healthcare Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Bagchi, Prithwi Bisht, Abhishek Das, Ashok Kumar Saxena, Neetesh Hossain, M. Shamim International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500 032 India Department of Computer Science and Engineering College of Informatics Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Cardiff University School of Computer Science and Informatics CardiffCF24 4AG United Kingdom King Saud University College of Computer and Information Sciences Department of Software Engineering Riyadh13273 Saudi Arabia

Despite edge computing reducing communication delays associated with cloud computing, privacy concerns remain a significant challenge when sharing data from edge-based consumer electronics (CE) or Internet-of-Things (IoT) devices. Ciphertext policy attribute-based encryption (CP-ABE) is a cryptographic tool that facilitates intricate and refined access control. It can deliver more flexible, secure, compact, and effective access control policies for the cloud data. In the case of a conventional CP-ABE scheme, the keys can only be issued and disseminated by a trusted central authority (CA). However, if the CA is compromised, the entire system becomes more susceptible to assaults or failures, which leads to a single-point failure. In this article, we propose a Ring-Learning with Errors (Ring-LWE)-based MA-CP-ABE scheme that is effectively resolved by the multi-authority CP-ABE (MA-CP-ABE), and it ensures the security against quantum attacks. The threshold secret sharing by Shamir and the Lagrange interpolation formula are applied in the key-generation and decryption procedures of the proposed scheme, which make it easier to segment and restore the private keys. The proposed scheme is implemented in the CE-enabled IoT-based smart healthcare applications using the blockchain technology as a secure storage. A detailed comparative study, security analysis and experimental results with the existing relevant schemes shows that the proposed scheme exhibits superior security and better efficiency as compared to other schemes, demonstrating its feasibility in practical IoT-based healthcare applications. © 2025 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Structural Cracks Segmentation Through Generative Image Synthesis 5

Enhancing Structural Cracks Segmentation Through Generative ...

引用

5th International Conference on Frontiers Technology of information and computer, ICFTIC 2023

作者： Liao, Yunping Zhang, Tao Yang, Yong Li, Boyi Li, Hui Yan, Qi Southwest University College of Computer and Information Science & College of Software Chongqing China Ministry of Natural Resources Chongqing Institute of Geology and Mineral Resources Technology Innovation Center of Geohazards Automatic Monitoring Chongqing China Chongqing University School of Civil Engineering Chongqing China

ISBN: (纸本)9798350309034

Using deep neural networks to detect cracks in architectural structures presents significant challenges due to the irregular and diverse nature of cracks, along with variations in lighting conditions and backgrounds. Moreover, the absence of a sufficient number of crack sample images can significantly impact the accuracy of crack detection. In this study, we propose a novel method to enhance the semantic segmentation accuracy of structural crack images. This is achieved by generating images and their corresponding masks. Our approach cleverly combines synthetic crack data generated through unconditional GAN-based methods with real-world data, addressing the issue of limited data availability. Additionally, we employ transformer-based architecture, specifically the SegFormer segmentation model, to assess our methodology. Experimental results demonstrate that the SegFormer small model, trained iteratively on this integrated dataset, achieved an impressive mIoU of 87.13%, marking a significant improvement over the 85.59% obtained on the original dataset. Our work demonstrates the power of generative techniques in computer vision tasks by offering a viable solution in the face of challenging data constraints, especially in the realm of cracks detection. © 2023 IEEE.

关键词： computer vision crack detection generative adversarial network image processing segmentation

来源：评论

学校读者我要写书评

暂无评论

End-to-End Rockfall Detection Based on DINO 3

End-to-End Rockfall Detection Based on DINO

引用

3rd Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum, AIBDF 2023

作者： Liao, Yunping Li, Shichao Yang, Yong Li, Boy Li, Hui Yan, Qi Technology Innovation Center of geohazards automatic monitoring Ministry of Natural Resources Chongqing Institute of Geology and Mineral Resources Chongqing China Southwest University College of Computer and Information Science College of Software Chongqing China School of Civil Engineering Chongqing University Chongqing China

ISBN: (纸本)9798400716362

In this paper, we utilized the DINO object detection model to achieve end-to-end deep learning-based rockfall detection. Rockfalls cause significant economic losses and casualties every year, and timely detection and response are crucial to prevent accidents and reduce human casualties. By detecting a small number of rockfall features in the early stages of a potential rockfall, this study analyzed the severity of the disaster and aimed to protect people’s lives and health by providing critical time to avoid disasters. In this paper, we annotated 2,201 images from 28 confirmed rockfall videos, of which 66.2% were primarily small targets according to the COCO dataset definition. By using the Transformer-based DINO model, we achieved an AP of 43.5%, which outperformed other excellent object detection models, especially in its ability to detect small targets. © 2023 Copyright held by the owner/author(s).

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

An Approach for Real Time computer User Action Monitoring

An Approach for Real Time Computer User Action Monitoring

引用

Advancements in Computing (ICAC), International Conference on

作者： Dulshan Alahakoon Tharindu Samarakoon Indika Wickramanayake Kushani Sakalasooriya Dharshana Kasthurirathna Anuradha Karunasena Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

computers play a significant part in the modern world. The rapid increase in computer use, especially after the COVID-19 pandemic, raised concerns about the potential negative impact on user health. Sitting posture, eye health, stress, and sleep are the most important factors when considering the health of daily computer users. It is more important to prevent issues from occurring than to find solutions once they have occurred. To address this issue, a Real-Time computer User Action Monitoring Approach is proposed that uses machine learning techniques to monitor and preserve user health effectively. Importantly, this solution leverages only the built-in webcam, eliminating the need for costly external equipment and ensuring affordability. The proposed solution consists of four key components: sitting posture detection and correction, eye tracking for eye health and comfort, stress detection and reduction techniques, and drowsiness detection for enhanced productivity and safety. This approach assists users in avoiding harmful behaviors, fosters healthful computer use by providing real-time feedback, and offers personalized recommendations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Life on land: An accurate centralized system for ensuring the safety and wellbeing of domestic and wild animals

TechRxiv

引用

TechRxiv 2023年

作者： Heshan, Adithya B.M. Wickramathilake, Shamilka K.W.D. Gunathilake, Dulmi W.M.P. Herath, Hiruni H.M.S. Samarasekara, Piyumika de Silva, Dilshan Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Sri Lanka Faculty of Computing Sri Lanka Institute of Information Technology Malabe Sri Lanka

The web application described above has the potential to make a significant contribution to the conservation of endangered wildlife and the responsible management of domestic animals. The application addresses a critical issue that has far-reaching implications for the health of ecosystems and the well-being of animals. By providing users with tools to track and manage animal populations, monitor their health and behavior, and implement conservation efforts, the application empowers individuals and organizations to take action and make a positive impact on the environment. In addition to its practical benefits, the web application also includes educational resources and supports community engagement to raise awareness about the importance of preserving biodiversity and protecting animal welfare. This holistic approach recognizes the complex and interconnected nature of conservation and management efforts, and highlights the need for collaboration and cooperation among stakeholders. The user-friendly interface of the application ensures that it is accessible to a wide range of users, including individuals with limited technical expertise. The ability to collaborate and share data also promotes transparency and accountability, which are essential for effective conservation and management efforts. Overall, this web application has the potential to be a valuable tool for those involved in animal conservation and management, and it offers hope for the protection of endangered wildlife and the responsible management of domestic animals. © 2023, CC BY.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Development of a Prediction System for Criminality and Suicidal in Sri Lanka

Development of a Prediction System for Criminality and Suici...

引用

Advancements in Computing (ICAC), International Conference on

作者： D.P.D. Ranasinghe R.D.T.S. Fernando D.G. Girambe D.M.H.K.D. Arambegama Bhagyanie Chathurika Dulani Jayasinghe Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

This research confronts the growing challenges of rising suicide rates and crime in Sri Lanka through a dual approach, harnessing advanced machine learning and time series analysis. The innovative methodology, merging “Feature Importance Weighting and Ensemble of Diverse Trees with the Random Forest Regressor,” achieves impressive accuracy of 93% for factors and 94% for methods. Additionally, the accuracy rates of 94% for education and 93% for occupationbased predictions enhance this comprehensive approach, offering a profound understanding of suicidal incidents and enabling precise prevention strategies. Simultaneously this study employs an ensemble of AutoRegressive Integrated Moving Average (ARIMA) models for crime prediction. This approach consistently attains high accuracy, often surpassing 90%, such as 96% and 97%. Utilizing multiple models enhances predictive accuracy and hotspot identification, granting law enforcement and policymakers flexibility to address enduring yearly hotspots and evolving dynamic hotspots. This research bridges the comprehension of suicide and crime dynamics in Sri Lanka, providing invaluable insights for evidence-based policies and targeted interventions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Transformer for Vibration Data Analysis: Case Study on CWRU Dataset 2

Anomaly Transformer for Vibration Data Analysis: Case Study ...

引用

2nd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2023

作者： Liao, Yunping Li, Hui Zhang, Liwen Yan, Qi Yang, Yong Li, Boyi Southwest University College of Computer and Information Science and College of Software Chongqing China Chongqing Institute of Geology and Mineral Resources Technology Innovation Center of Geohazards Automatic Monitoring Ministry of Natural Resources Chongqing China Chongqing University School of Civil Engineering Chongqing China

ISBN: (纸本)9798350331417

Time series anomaly detection has a wide range of applications in various fields of society, one of which is the detection of anomalies in vibration data. Abnormal vibration data often indicates the existence of potential disasters or abnormal operation of equipment, so timely detection and identification is important for the prevention of earthquakes and improvement of industrial production efficiency. In this paper, an unsupervised time series anomaly detection algorithm, Anomaly Transformer, is used to detect anomalies in CWRU vibration *** Transformer leverages the powerful characterization capabilities of the Transformer network and an improved anomaly attention mechanism to capture anomalies in the time series. Experimental results show that Anomaly Transformer exhibits excellent performance in the CWRU vibration dataset, achieving high precision and recall. In addition, Anomaly Transformer demonstrated a low false alarm rate, indicating its high accuracy in recognizing real anomalies. Future research can further explore the application of Anomaly Transformer in other domains with deeper optimization and extensions. © 2023 IEEE.

关键词： deep learning time series anomaly detection vibration data

来源：评论

学校读者我要写书评

暂无评论

HistoMind: AI-Based Historical Place Navigator

HistoMind: AI-Based Historical Place Navigator

引用

Advancements in Computing (ICAC), International Conference on

作者： Chathra Navoda Ranasinghe Kavindu Ushan Ranasinghe Niketh Munasighe Manul Priyaratne Buddika Harshanath Samantha Rajapakse Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka

This research addresses a critical gap in Sri Lanka's tourism infrastructure: the absence of a comprehensive smart location-based recommendation system with a route planner and a multilingual AI chatbot. To date, no integrated solution has been developed to cater to the diverse preferences of tourists, offer community-validated recommendations, and bridge language barriers. This research is pioneering the creation of these novel systems, with a clear focus on enhancing the tourism experience and supporting the country's economy. The smart recommendation system harmonizes various recommendation techniques, encompassing user preferences, community-approved choices, and hidden gems. By integrating these aspects, the system aims to provide tourists with personalized, community-endorsed recommendations while introducing them to unique destinations, thus addressing the existing void in Sri Lanka's tourism landscape. Furthermore, the AI-based multilingual chatbot tackles the language barrier head-on, enabling tourists to communicate effortlessly in their native language, a feature hitherto unavailable in the Sri Lankan tourism sector. This innovation aims to break down language barriers, making the country more accessible to a global audience. Through advanced methodologies and cutting-edge technology, this research strives to fill these critical gaps, promising a brighter future for Sri Lanka's tourism and its economic prosperity.

关键词：

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：