检索结果-内蒙古大学图书馆

4th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2023

作者： Kanthavel, R. Margala, Martin Siva Shankar, S. Chakrabarti, Prasun Dhaya, R. Chakrabarti, Tulika University of Louisiana Lafayette United States School of Computing and Informatics University of Louisiana Lafayette United States Department of CSE KG Reddy College of Engineering and Technology Chilkur Village Telangana Moinabad Mandal501504 India Baroda University Gujarat Vadodara391510 India School of Computing University of Louisiana Lafayetta United States Sir Padampat Singhania University Rajasthan Udaipur313601 India

ISBN: (纸本)9789819965854

Knee osteoarthritis (OA) has been a prevalent degenerative joint ailment that affects people all over the world. Because of the increased occurrence of knee OA, the accurate diagnosis of osteoarthritis at an early stage is a tough task. The osteoarthritis imaging such as conventional radiography, MRI, and ultrasound are the essential components to diagnose knee OA in its early stages. On the other hand, deep neural network (DNN) designs are extensively used in medical image examination for the accurate outcomes in terms of classification of OA diagnosis. Image segmentation, also known as pixel-level categorization, is the method of categorizing portions of an image that are composed of the exact same object class by means of partitioning images into multiple segments. But, the drawback identified from the lack of accuracy of the traditional approach can be overcome using deep learning method. Hence, this paper presents a deep learning-based semantic grey wolf optimization (GWO) threshold segmentation to detect the Osteoarthritis accurately at all stages. The two phases of stages involve in the proposed work which carries CT image normalization and histogram connection to enhance the image with accuracy. The comparative analysis has also been done with the existing methods using the evaluation parameters such as sensitivity, specificity, accuracy, MSE, PSNR, SSIM, and MAE for the accurate diagnosis of OA. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Combination of Boruta's Algorithm and Lasso Logistic Regression in Establishing Blood-Based Biomarkers for Alzheimer's Disease 5

Combination of Boruta's Algorithm and Lasso Logistic Regress...

引用

5th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2024

作者： Abdullah, Mohammad Nasir Wah, Yap Bee School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi Mara Tapah Campus Perak Tapah35400 Malaysia School of Information Technology Unitar International University Tierra Crest Jalan SS6/3 SS6 Selangor Petaling Jaya47301 Malaysia

ISBN: (纸本)9798331528553

Alzheimer's disease (AD) is the leading neurodegenerative disorder worldwide, significantly impacting morbidity, disability, and mortality rates. This study aims to enhance the early diagnosis of AD by identifying blood-based biomarkers using Boruta's algorithm and lasso logistic regression. The Gene Expression Omnibus (GEO) dataset GSE140829 identified 47,008 potential biomarkers, which preprocessing reduced to 22,372. Boruta's algorithm further narrowed these to 21 significant biomarkers. Lasso logistic regression was applied to this balanced dataset, resulting in six key biomarkers: CST7, DPAGT1, DZIP1, MOSC1, TACC3, and YDJC. The final model, validated with a C-index of 0.763, demonstrated good discriminative power and clinical utility. This research offers a robust method for predicting AD, potentially improving early diagnosis and guiding treatment decisions. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Utilizing Fine-Tuning ResNet-18 for Acute Leukemia Diagnosis from Blood Smear Images

Utilizing Fine-Tuning ResNet-18 for Acute Leukemia Diagnosis...

引用

technology Innovation and Its Applications (ICTIIA), International Conference on

作者： Triandes Sinaga Ade Candra Bedy Purnama Master of Informatics Engineering Faculty of Computer and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Informatics School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9798350351613

ISBN: (纸本)9798350351620

This study explores fine-tuning ResNet-18 to enhance the accuracy of acute leukemia diagnosis from blood smear images. Early detection is crucial for patient outcomes, but the application of ResNet-18 in this context has been underutilized. We propose fine-tuning ResNet-18 to increase diagnostic precision using datasets from RSUP Haji Adam Malik Medan and Università degli Studi di Milano Statale. The model achieved 99.12% accuracy on validation and test datasets, with excellent precision, recall, F1-score, and AUCROC. Comparative analysis with non-fine-tuned ResNet-18, VGG-16, and MobileNetV2 demonstrated the superiority and stability of fine-tuning, highlighting its importance in improving diagnostic model reliability.

关键词： Training Measurement Technological innovation Analytical models Accuracy Fluctuations Stability analysis Data models Blood Overfitting

来源：评论

学校读者我要写书评

暂无评论

A federated learning attack method based on edge collaboration via cloud

A federated learning attack method based on edge collaborati...

引用

作者： Yang, Jie Baker, Thar Gill, Sukhpal Singh Yang, Xiaochuan Han, Weifeng Li, Yuanzhang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computer Science Beijing Institute of Technology Beijing China School of Mechanical Manufacturing and Automation Engineer of China Railway Tunnel Bureau Group Co. Ltd Henan Zhengzhou China

Federated learning (FL) is widely used in edge-cloud collaborative training due to its distributed architecture and privacy-preserving properties without sharing local data. FLTrust, the most state-of-the-art FL defense method, is a federated learning defense system with trust guidance. However, we found that FLTrust is not very robust. Therefore, in the edge collaboration scenario, we mainly study the poisoning attack on the FLTrust defense system. Due to the aggregation rule, FLTrust, with trust guidance, the model updates of participants with a significant deviation from the root gradient direction will be eliminated, which makes the poisoning effect on the global model not obvious. To solve this problem, under the premise of not being deleted by the FLTrust aggregation rules, we construct malicious model updates that deviate from the trust gradient to the greatest extent to achieve model poisoning attacks. First, we utilize the rotation of high-dimensional vectors around axes to construct malicious vectors with fixed orientations. Second, the malicious vector is constructed by the gradient inversion method to achieve an efficient and fast attack. Finally, a method of optimizing random noise is used to construct a malicious vector with a fixed direction. Experimental results show that our attack method reduces the model accuracy by 20%, severely undermining the usability of the model. Attacks are also successful hundreds of times faster than the FLTrust adaptive attack method. © 2022 John Wiley & Sons Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Industry Recommendation for Undergraduate Internship using Decision Tree

Industry Recommendation for Undergraduate Internship using D...

引用

2022 IEEE International Conference on computing, ICOCO 2022

作者： Kamalbahrin, Intan Norsyafiqa Hanum, Haslizatul Mohamed Abdullah, Nur Atiqah Sia Adam, Noor Latiffah Kamal, Nor Ashikin Mohamad Bakar, Zainab Abu College of Computing Informatics and Media Universiti Teknologi Mara Selangor Shah Alam Malaysia Asia e University School of Science and Technology Selangor Malaysia

ISBN: (纸本)9781665489966

The process of matching student profiles to industry profiles is critical to ensuring that students are placed in industries that are a good fit for their program. Therefore, to solve this problem, a system is presented that will give suggestions on suitable industrial types and internship placement from companies in the suggested industry for undergraduate students. This project maps student profiles from seven computer science programs and seven industrial types. There are 284 sample profiles collected from undergraduate students of Universiti Teknologi MARA. The profiles are gathered from previous records of placement for internship training. A decision tree model is constructed based on the sample profiles. The student's Cumulative Grade Point Average (CGPA) and registered program are used as the main feature of industry recommendation. As a result, a web-based system for mapping students' profiles to industries' profiles has been developed. The application stores students' and industries' profiles and recommends suitable industries for each student's profile. © 2022 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Fog computing in Optical Access Networks: An Energy-efficient and Deadline-aware Task Scheduling Mechanism 13

Fog Computing in Optical Access Networks: An Energy-efficien...

引用

13th International Conference on Information technology in Asia, CITA 2023

作者： Ahmad, Fathiyah Haji Shah Newaz, S.H. Sankar, D.S. Ramlie, Rudy Nafi, Nazmus Shaker School of Computing and Informatics GadongBE1410 Brunei Kaist Institute for Information Technology Convergence Daejeon34141 Korea Republic of School of Applied Sciences and Mathematics GadongBE1410 Brunei Boeing Defence Australia AdelaideSA5111 Australia

ISBN: (纸本)9798350326208

Fog computing is paving the way for catering latency stringent applications (e.g., augmented reality and virtual reality) at the customer premises. Fog computing nodes are located between the end user devices and remote cloud. They are lightweight and small-scale storage and processing system deployed closer to the data source, allowing faster processing as well as providing privacy and security of the data. We have been witnessing a growing number of solutions that integrate Passive Optical Network (PON) with the fog computing. Along this research line, there are some solutions considering fog computing nodes are co-located with the Optical Line Terminal (OLT), the central intelligence of a PON system, and Optical Network Unit (ONU), a customer premises equipment. There are some solutions, on the other hand, that propose to embed computing and storage functionality within PON equipment itself. In this paper, we particularly focus on the later approach. Here, we propose an energy conserving solution for a PON system with fog computing enabled ONUs, i.e., the ONUs are equipped with additional computing and Storage Units (CSUs). Our solution aims at minimizing energy consumption of a PON system by keeping only the required number of CSUs active and allowing the ONUs to move into sleep mode (whenever possible) by taking into account task arrival rate and task completion deadline. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Predictive Classification of Covid-19: Assessing the Impact of Digital Technologies 7

Predictive Classification of Covid-19: Assessing the Impact ...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Kumar, Bonda Kiran Majumdar, Anurima Ismail, Saidatul Akmar Dixit, Rohit R Wahab, Hairani Ahsan, Md Hafizi KL School of Architecture KL Deemed to Be University Koneru Lakshmaiah Educational Foundation Andhra Pradesh Vaddeswaram India Guru Nanak Institute of Technology Department of Electronics and Communication Engineering India School of Information Science College of Computing Informatics & Mathematics Universiti Teknologi MARA Shah Alam Malaysia Siemens Healthineers India School of Information Science College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Universiti Malaysia Sabah Labuan Faculty of International Finance Malaysia

ISBN: (纸本)9798350340600

The recent severe outbreak of the disease has been linked to the COVID-19 virus. It is essential for healthcare professionals and individuals with the capacity to provide intensive care to offer clear explanations of this situation. To address this issue, the World Health Organization (WHO) has implemented several measures. The National Emergency Telecritical Care Network (NETCCN) has the capability to assess these actions using digital technologies. This section provides a comprehensive explanation of these developments, and NETCCN has put forth a recommendation. Version 2.0 of this digital health data will be made available;it will significantly enhance potential crises in the future. Artificial Intelligence (AI) is used in the suggested digital prediction approach to gather past data on the infection. Telemetry, sophisticated maintenance robotics, and monitoring intelligence may all be found with this technology. These may be created to incorporate data relevant to various infections. Health experts will coordinate all of these. To maintain sustained preparedness for emergency catastrophe protection, frequent testing should be conducted. © 2023 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Virtual IMU Data for Eating Detection with Wrist Sensors

On the Effectiveness of Virtual IMU Data for Eating Detectio...

引用

2022 ACM International Joint Conference on Pervasive and Ubiquitous computing and the 2022 ACM International Symposium on Wearable Computers, UbiComp/ISWC 2022

作者： Jain, Yash Kwon, Hyeokhyen Ploetz, Thomas School of Interactive Computing Georgia Institute of Technology AtlantaGA United States Department of Biomedical Informatics Emory University AtlantaGA United States

ISBN: (纸本)9781450394239

The successful training of human activity recognition (HAR) systems typically heavily depends on the availability of sufficient amounts of labeled sensor data. Unfortunately, obtaining large-scale labeled datasets is usually expensive and often limited by practical and / or privacy reasons. Recently, IMUTube was introduced to tackle this data scarcity problem through generating weakly-labeled, virtual IMU data from unconstrained video repositories, such as YouTube. IMUTube was demonstrated to be very effective at classifying locomotion or gym exercises that involve large movements of body parts. Yet, many important daily activities, such as eating, do not exhibit such substantial body (part) movements but are rather based on more subtle, fine-grained motions. This work explores the utility of IMUTube for such subtle motion activities with specific, exemplary application to eating detection. We found that-surprisingly-IMUTube is also very effective for this challenging HAR domain. Our experiment demonstrates that eating recognition systems benefit from virtual IMU data extracted from video datasets with significant improvements of recognition accuracy (increases of 8.4% and 5.9% F1-score absolute for both curated and in-the-wild video datasets, respectively relative to 71.5% F1-score of the baseline), which is encouraging for the broader use of systems like IMUTube. © 2022 Owner/Author.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Ingredient-Guided RGB-D Fusion Network for Nutritional Assessment

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 156-166页

作者： Feng, Zhihui Xiong, Hao Min, Weiqing Hou, Sujuan Duan, Huichuan Liu, Zhonghua Jiang, Shuqiang Shandong Normal University School of Information Science and Enginering Jinan250358 China Macquarie University Centre for Health Informatics Macquarie ParkNSW2109 Australia Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Zhejiang Ocean University School of Information Engineering Zhoushan316022 China

The nutritional value of agricultural products is an important indicator for evaluating their quality, which directly affects people's dietary choices and overall well-being. Nutritional assessment studies provide a scientific basis for the production, processing, and marketing of food by analyzing the nutrients they contain. Traditional methods often struggle with suboptimal accuracy and can be time consuming, as well as a shortage of professionals. The progress in artificial intelligence has revolutionized dietary health by offering more accessible methods for food nutritional assessment using vision-based approaches. However, existing vision-based methods using RGB images often face challenges due to varying lighting conditions, impacting the accuracy of nutritional assessment. An alternative is the RGB-D fusion method, which combines RGB images and depth maps. Yet, these methods typically rely on simple fusion techniques that do not ensure precise assessment. Additionally, current vision-based methods struggle to detect small components like oils and sugars on food surfaces, crucial for determining ingredient information and ensuring accurate nutritional assessment. In this pursuit, we propose a novel ingredient-guided RGB-D fusion network that integrates RGB images with depth maps and enables more reliable nutritional assessment guided by ingredient information. Specifically, the multifrequency bimodality fusion module is designed to leverage the correlation between the RGB image and the depth map within the frequency domain. Furthermore, the progressive-fusion module and ingredient-guided module leverage ingredient information to explore the potential correlation between ingredients and nutrients, thereby enhancing the guidance for nutritional assessment learning. We evaluate our approach on a variety of ablation settings on Nutrition5k, where it consistently outperforms state-of-the-art methods. © 2023 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

AI-Based Heart Disease and Brain Stroke Prediction Using Multi-modal Patient Data 1st

AI-Based Heart Disease and Brain Stroke Prediction Using Mu...

引用

1st Pan-African Conference on Artificial Intelligence, PanAfriCon AI 2022

作者： Simegn, Gizeaddis Lamesgin Degu, Mizanu Zelalem Biomedical Image Unit School of Biomedical Engineering Jimma Institute of Technology Jimma University Jimma Ethiopia AI and Biomedical Imaging Research Unit Jimma Institute of Technology Jimma University Jimma Ethiopia Faculty of Computing and Informatics Jimma Institute of Technology Jimma University Jimma Ethiopia

ISBN: (纸本)9783031313264

Heart disease and stroke are among the major causes of death and disabilities globally causing numerous social or economic difficulties. Neurological damage is the primary cause of most deaths following a stroke, with cardiovascular issues being the second leading cause. Research findings, both from clinical and experimental studies, indicate a cause-and-effect connection between damage to the brain and the development of heart disease. If left untreated at early stages, stroke, and heart disease can lead to death. Therefore, Early diagnosis and monitoring of these diseases are crucial for the reduction of morbidity and mortality. In this research electronic medical records of patients’ symptoms, body features, clinical laboratory test values, and brain images were used to analyze patterns, and train and validate different machine learning and deep learning models to predict heart disease and brain stroke. Three types of modules including machine learning-based heart disease, brain stroke prediction using clinical data, and a deep learning-based brain stroke prediction using brain MRI image data were designed and deployed into a user-friendly custom-made user interface. The heart disease and brain stroke prediction models were found to be 100% and 97.1% accurate in predicting heart disease and brain stroke, respectively, based on clinical and patient information, while the MRI image-based deep learning stroke prediction model was 96.67% accurate. Our experimental results suggest that the proposed systems may have the potential to impact clinical practice and become a decision support system for physicians to predict heart disease and brain stroke from a set of risk factors and laboratory tests improving diagnosis accuracy for better treatment planning. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

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：