检索结果-内蒙古大学图书馆

International Conference on Telecommunication Systems, Services, and Applications (TSSA)

作者： Vidya Ikawati Didin Saepudin Bambang Susanto Ahmad Munandar Hardy Purnama Nurba Ary Setijadi Prihatmanto Doctoral Program of School of Electrical and Informatics Engineering Institute of Technology Bandung Bandung Indonesia Universitas Sangga Buana Bandung Indonesia Department of Electrical Engineering Faculty of Engineering Universitas Sangga Buana Bandung Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia

Health Service, also referred to as Health Care System, plays a pivotal role in maintaining and enhancing health by preventing illnesses and injuries. In this context, electronic health records are essential for both inpatients and outpatients, serving as a crucial tool for healthcare providers and policymakers. However, the potential of these records extends beyond individual care to support broader health policy and research initiatives. Personal Smart Health Care, an individual-based digital health technology, bridges the gap between personal health management and medical records, enabling comprehensive healthcare improvements. Smart healthcare, driven by technologies like IoT, mobile applications, cloud computing, big data, 5G, artificial intelligence, and biotechnology, offers a holistic approach to healthcare, emphasizing diagnosis, treatment, disease prevention, risk monitoring, and virtual assistance. An intelligent framework for smart healthcare includes four layers: the instrumentation layer, information system layer, business intelligence layer, and gamification layer, each contributing to enhanced patient outcomes, streamlined processes, and improved patient care. The gamification layer incentivizes healthy behaviors and fosters patient engagement, especially in healthcare scenarios. This comprehensive framework underscores the transformative potential of smart healthcare, where technology-driven solutions can revolutionize the healthcare landscape, improving patient care, health management, and the overall well-being of individuals and populations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulating Dependence in Networks Using Topological Data Analysis

arXiv

引用

arXiv 2022年

作者： Bourakna, Anass El Yaagoubi Chung, Moo K. Ombao, Hernando Statistics Program CEMSE Division Saudi Arabia Department of Biostatistics & Medical Informatics University of Wisconsin–Madison United States

Topological data analysis (TDA) approaches are becoming increasingly popular for studying the dependence patterns in multivariate time series data. In particular, various dependence patterns in brain networks may be linked to specific tasks and cognitive processes, which can be altered by various neurological and cognitive impairments such as Alzheimer’s and Parkinson’s diseases, as well as attention deficit hyperactivity disorder (ADHD). Because there is no ground-truth with known dependence patterns in real brain signals, testing new TDA methods on multivariate time series is still a challenge. Simulations are crucial for evaluating the performance of proposed TDA methods and testing procedures as well as for creating computation-based confidence intervals. To our knowledge, there are no methods that simulate multivariate time series data with specific and manually imposed connectivity patterns. In this paper we present a novel approach to simulate multivariate time series with specific number of cycles/holes in its dependence network. Furthermore, we also provide a procedure for generating higher dimensional topological features. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectrum analysis

来源：评论

学校读者我要写书评

暂无评论

MIXTURE OF EXPERTS MADE PERSONALIZED: FEDERATED PROMPT LEARNING FOR VISION-LANGUAGE MODELS

arXiv

引用

arXiv 2024年

作者： Luo, Jun Chen, Chen Wu, Shandong Intelligent Systems Program University of Pittsburgh PittsburghPA15213 United States Intelligent Systems Program Department of Radiology Department of Biomedical Informatics Department of Bioengineering University of Pittsburgh PittsburghPA15213 United States Center for Research in Computer Vision University of Central Florida OrlandoFL32816 United States

Federated prompt learning benefits federated learning with CLIP-like Vision-Language Model’s (VLM’s) robust representation learning ability through prompt learning. However, current federated prompt learning methods are habitually restricted to the traditional FL paradigm, where the participating clients are generally only allowed to download a single globally aggregated model from the server. While justifiable for training full-sized models under federated settings, in this work, we argue that this paradigm is ill-suited for lightweight prompts. By facilitating the clients to download multiple pre-aggregated prompts as fixed non-local experts, we propose Personalized Federated Mixture of Adaptive Prompts (pFedMoAP), a novel FL framework that personalizes the prompt learning process through the lens of Mixture of Experts (MoE). pFedMoAP implements a local attention-based gating network that learns to generate enhanced text features for better alignment with local image data, benefiting from both local and downloaded non-local adaptive prompt experts. Extensive experiments on 9 datasets under various federated settings demonstrate the efficacy of the proposed pFedMoAP algorithm. The code is available at https://***/ljaiverson/pFedMoAP. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Data Instrumentation for Stunting Analysis in Physical-Cyber Architecture 17

Advanced Data Instrumentation for Stunting Analysis in Physi...

引用

17th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2023

作者： Nugraha, Daniel Nurtam, M. Riza Mistialustina, Hartuti Saepudin, Didin Surjono, Welly Prihatmanto, Ary Setijadi Institut Teknologi Bandung Doctoral Program of School of Electrical Engineering and Infomatics Bandung Indonesia Universitas Widya Dharma Pontianak Kalimantan Barat Indonesia Universitas Sangga Buana Faculty of Engineering Electrical Engineering Department Bandung Indonesia Universitas Sangga Buana Bandung Indonesia Institut Teknologi Bandung School of Electical Engineering and Informatics Bandung Indonesia

ISBN: (纸本)9798350309164

In Indonesia, stunting is a serious problem that has drawn a lot of attention from the government. This study offers a novel strategy for preventing stunting by combining the 5-Desk Model used in integrated health posts (Posyandu) with the Cyber-Physical System (CPS) architecture. Chronic malnutrition and childhood diseases can cause stunting, which can result in long-Term health issues and cognitive deficits. Despite advancements, it still poses a serious threat to almost every Indonesian province. For the purpose of gathering data in Posyandu, such as registration, growth measurement, recording, counseling, and health services, the 5-Desk Model provides an organized framework. This promotes the well being of the community and gives healthcare professionals the ability to thoroughly monitor important health indicators. This strategy is improved with CPS integration, which results in a four-layered, comprehensive system that includes gamification, business intelligence, information systems, and instrumentation. To maximize efforts to avoid stunting, this architecture facilitates accurate monitoring, real-Time data collecting, data analysis, and stakeholder communication. This study imagines a data-driven future for Indonesian stunting prevention, where cooperation, technology, and data are combined to address this pressing problem and safeguard the future prospects and wellbeing of Indonesia's youth. Implementing this goal and expanding stunting prevention initiatives will be the main goals of future research. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Identifying Physical Unclonable Functions Using Classifier Algorithms

Identifying Physical Unclonable Functions Using Classifier A...

引用

Latin America Congress on Computational Intelligence (LA-CCI)

作者： Caio B. Viana Carlos J. M. Araújo Danilo R. B. de Araújo Post Graduated Program in Applied Informatics Federal Rural University of Pernambuco (UFRPE) Recife Brazil Department of Computing (DC) Federal Rural University of Pernambuco (UFRPE) Recife Brazil

Industrial IoT systems are constantly increasing security to mitigate failures and unallowed access. Nowadays, enterprise systems can handle large amounts of sensitive information that can be received from hundreds of tiny devices such as sensors, fog devices, gateways, etc. However, the lower processing capacity associated with tiny devices due to manufacturing decisions has contributed to their lack of defensive measures and hardware security support. Those devices performance usually restricts advanced software security usage and results in several vulnerabilities in the device’s authentication. RFID tags have been used in the IoT industry to create a variety of applications for identification, authentication, or even virtual proof of reality, but RFID tags are still susceptible to serious attacks since fake RFID devices or other attacks are trying to find ways of bypassing the security. In this paper, 5 (five) machine learning algorithms have been used to classify a dataset of read-time operations from blocks in Mifare RFID and fake tags, aiming to identify different behaviors between dataset’s variables, which can be used for a Physical Unclonable Functions (PUF). According to our results, K-Nearest Neighbor (KNN) offered the best performance for the considered problem. The KNN obtained a root mean squared error equal to 0.058 and an mean absolute error equal to 0.003. The obtained results indicate that operation times have variables inherent to the manufacturing process and this can be useful for future identity management schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benchmarking mortality risk prediction from electrocardiograms

arXiv

引用

arXiv 2024年

作者： Lukyanenko, Platon Mayourian, Joshua Liu, Mingxuan Triedman, John K. Ghelani, Sunil J. La Cava, William G. Computational Health Informatics Program Boston Children’s Hospital United States Department of Cardiology Boston Children’s Hospital United States Harvard Medical School United States National University of Singapore Singapore

Several recent high-impact studies leverage large hospital-owned electrocardiographic (ECG) databases to model and predict patient mortality. MIMIC-IV, released September 2023, is the first comparable public dataset and includes 800,000 ECGs from a U.S. hospital system. Previously, the largest public ECG dataset was Code-15, containing 345,000 ECGs collected during routine care in Brazil. These datasets now provide an excellent resource for a broader audience to explore ECG survival modeling. Here, we benchmark survival model performance on Code-15 and MIMIC-IV with two neural network architectures, compare four deep survival modeling approaches to Cox regressions trained on classifier outputs, and evaluate performance at one to ten years. Our results yield AUROC and concordance scores comparable to past work (circa 0.8) and reasonable AUPRC scores (MIMIC-IV: 0.4-0.5, Code-15: 0.05-0.13) considering the fraction of ECG samples linked to a mortality (MIMIC-IV: 27%, Code-15: 4%). When evaluating models on the opposite dataset, AUROC and concordance values drop by 0.1-0.15, which may be due to cohort differences. All code and results are made public. Copyright © 2024, The Authors. All rights reserved.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Use of an Expert System to Diagnose and Provide Solutions for Pests and Diseases in Hydroponic Mustard Plants Using Certainty Factor and Forward Chaining Methods

Use of an Expert System to Diagnose and Provide Solutions fo...

引用

Science and Information Technology in Smart Administration (ICSINTESA), International Conference of

作者： Mahesa Bayu Baihaqi Aris Puji Widodo Ferry Jie Master of Information System Study Program Diponegoro University Central Java Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Central Java Indonesia School of Business and Law Edith Cowan University Australia

ISBN: (数字)9798350376111

ISBN: (纸本)9798350376128

Mustard greens are a vegetable that is very popular with people, especially hydroponic mustard greens, which appear fresher. However, like other vegetables, mustard greens grown hydroponically are also susceptible to pests and diseases, which can cause the vegetables to lose their freshness and may even result in crop failure. This condition can cause losses for mustard greens farmers in running their businesses. This research proposes an information system that represents the expertise of hydroponic mustard greens farmers in diagnosing pests and diseases in mustard plants as well as solutions to overcome them. This is to make it easier for novice growers and anyone interested in learning about diseases or pests that impact hydroponic mustard greens. The expert system developed is web-based and functions as a user consultation medium in relation to mustard pests and diseases using the forward chaining and certainy factor method to explain the decision tree procedure for mustard plant disease symptoms. With this expert system, farmers do not need to look for people who can explain the problems they face. We found that there were 10 types of pests and diseases and 29 symptoms in the hydroponic mustard plants reviewed in this research.

关键词： Plant diseases Plants (biology) Hydroponics Expert systems Information technology Faces Diseases Business Information systems Farming

来源：评论

学校读者我要写书评

暂无评论

A VAE-Based Data Augmentation Method for Fall Detection System using Wearable Sensor

A VAE-Based Data Augmentation Method for Fall Detection Syst...

引用

International Conference on Applied System Innovation (ICASI)

作者： Yu-Chen Tu Hsuan-Chih Wang Chien-Pin Liu Chia-Yeh Hsieh Chia-Tai Chan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei City Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City Taiwan

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

Fall incidents among the elderly represent a significant global concern, often resulting in physical injuries and psychological distress. It is crucial to develop reliable fall detection systems which are capable of identifying fall events immediately and triggering alerts for assistance. However, real-world fall occurrences are infrequent, leading to a highly imbalanced class situation. Training a model with imbalanced datasets may result in biased models with poor performance in fall detection. To address this challenge, various techniques such as data transformation and Synthetic Minority Oversampling Technique (SMOTE) have been proposed. However, these methods are constrained by issues such as limitations in input data size or sensitivity to outliers. Compared to other methods, variational autoencoder (VAE) can generate data with a similar probability distribution to the original input data while constraining the latent representation in a Gaussian distribution. This study proposes a VAE-based data augmentation method for wearable-based fall detection system. The proposed method is validated on the FallAllD public dataset, achieving a F-score of 99.46%. The performance has been increased by 2.21%. The results demonstrate the effectiveness of VAE-based data augmentation technique in enhancing fall detection systems and its superior performance compared with other traditional data augmentation methods.

关键词： Training Technological innovation Sensitivity Psychology Data augmentation Probability distribution Reliability

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory Networks for Predicting LQ45 Index Trends in Infrastructure Stocks*

Long Short-Term Memory Networks for Predicting LQ45 Index Tr...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： C. Maximiliano E. E. Surbakti R. Winantyo Jantianus M. Vasty W. Istiono Department of Informatics Universitas Multimedia Nusantara Tangerang Banten Indonesia Department of Electrical Engineering Universitas Multimedia Nusantara Tangerang Banten Indonesia Banking and Accounting Program Politenik Negri Medan Medan North Sumatra Indonesia

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

The capital market plays a crucial role in the nation’s economy by serving as a platform for trading long-term financial products. Among the securities, stock is favored by investors due to their high potential for profitability. With the advancement of technology, to minimize the risks associated with stocks, the utilization of technical analysis using the long short-term memory (LSTM) algorithm has become increasingly prevalent. Investors show keen interest in the LQ45 index, which comprises 45 stocks characterized by high liquidity and capitalization. The infrastructure sector within the index, including “***,” “***,” “***” and “***,” is particularly attractive due to its promising outlook, steady growth, and government backing. Hence, the utilization of the LSTM algorithm for forecasting the stock prices of the infrastructure sector within the LQ45 index aims to offer a competitive edge to investors in the stock market. Based on tests with 36 parameter combinations for each stock, highly accurate forecasting was achieved on each stock model with MAPE values below $10 \%$. The *** stock model stood out with a MAPE of $1.43 \%$ and an RMSE of 78.16031. It utilized 64 neurons on two hidden layers, a batch size of 32, and a dropout rate of 0.2.

关键词： Training Accuracy Neurons Predictive models Transformers Indexes Forecasting Long short term memory Tuning Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Unitig-centered pan-genome machine learning approach for predicting antibiotic resistance and discovering novel resistance genes in bacterial strains

引用

Computational and Structural Biotechnology Journal 2024年 23卷 1864-1876页

作者： Do, Duyen Thi Yang, Ming-Ren Vo, Tran Nam Son Le, Nguyen Quoc Khanh Wu, Yu-Wei Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan Department of Electrical Engineering National Taiwan University of Science and Technology Taipei Taiwan Department of Business Administration College of Management Lunghwa University of Science and Technology Taoyuan City Taiwan Professional Master Program in Artificial Intelligence in Medicine College of Medicine Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan TMU Research Center for Digestive Medicine Taipei Medical University Taipei Taiwan

In current genomic research, the widely used methods for predicting antimicrobial resistance (AMR) often rely on prior knowledge of known AMR genes or reference genomes. However, these methods have limitations, potentially resulting in imprecise predictions owing to incomplete coverage of AMR mechanisms and genetic variations. To overcome these limitations, we propose a pan-genome-based machine learning approach to advance our understanding of AMR gene repertoires and uncover possible feature sets for precise AMR classification. By building compacted de Brujin graphs (cDBGs) from thousands of genomes and collecting the presence/absence patterns of unique sequences (unitigs) for Pseudomonas aeruginosa, we determined that using machine learning models on unitig-centered pan-genomes showed significant promise for accurately predicting the antibiotic resistance or susceptibility of microbial strains. Applying a feature-selection-based machine learning algorithm led to satisfactory predictive performance for the training dataset (with an area under the receiver operating characteristic curve (AUC) of > 0.929) and an independent validation dataset (AUC, approximately 0.77). Furthermore, the selected unitigs revealed previously unidentified resistance genes, allowing for the expansion of the resistance gene repertoire to those that have not previously been described in the literature on antibiotic resistance. These results demonstrate that our proposed unitig-based pan-genome feature set was effective in constructing machine learning predictors that could accurately identify AMR pathogens. Gene sets extracted using this approach may offer valuable insights into expanding known AMR genes and forming new hypotheses to uncover the underlying mechanisms of bacterial AMR. © 2024 The Authors

关键词： Genes

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：