检索结果-内蒙古大学图书馆

International Conference on informatics and Computing (ICIC)

作者： Armando Tirta Dwilaga Lintang Yuniar Banowosari Sudaryanto Aini Suri Talita Department of Information Technology Doctoral Program Gunadarma Information Technology University West Java Indonesia Department of Informatics Gunadarma University West Java Indonesia Department of Industrial Engineering and Management Gunadarma University West Java Indonesia Department of Information System Management Gunadarma University West Java Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Convolutional Neural Networks (CNN) have shown potential in tire defect classification, but challenges like image quality variations and model limitations persist. This Systematic Literature Review (SLR) employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology and a qualitative approach. It uses the Population, Intervention, Comparison, Outcome, and Context (PICOC) framework to analyze 30 articles from Google Scholar, published between 2018 and 2024 in Q1-Q4 journals. The review examines article distribution by publisher, evaluates the impact of key pre-training parameters (such as data split ratio, dropout rate, optimization algorithm, learning rate, and pre-trained models on CNN performance), and identifies challenges in defect classification. MDPI (Multidisciplinary Digital Publishing Institute) is the most frequent publisher, with the highest number of publications occurring in 2021. AlexNet and VGG16 are the most common models, and an 80:20 data split ratio, 0.5 dropout rate, and a 0.001 learning rate are frequently used. The Adam (Adaptive Momentum) optimization algorithm is widely adopted, but challenges remain in detecting small defects. Further improvements in CNN models, lighting techniques, and larger datasets are needed to enhance defect detection. This review highlights current trends and future research opportunities in tire quality measurement.

关键词： Image quality Adaptation models Current measurement Lighting Tires Data models Classification algorithms Convolutional neural networks Optimization Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

A Study of the Ecological Dynamics of Batumi, on the Black Sea Coast, Analyzing Environmental Factors and Their Impact

A Study of the Ecological Dynamics of Batumi, on the Black S...

引用

International Black Sea Conference on Communications and Networking (BlackSeaCom)

作者： Lily Petriashvili Irine Khomeriki Mzia Kiknadze Tamar Lominadze Nona Otkhozoria Dept. of Program Engineering Georgian Technical University Tbilisi Georgia Dept. of Interdisciplinary Informatics Georgian Technical University Tbilisi Georgia Dept. of Computer Engineering Georgian Technical University Tbilisi Georgia Dept. of Information Systems Georgian Technical University Tbilisi Georgia Dept. of Microprocessor and Measurement Systems Georgian Technical University Tbilisi Georgia

ISBN: (数字)9798350351859

ISBN: (纸本)9798350351866

This paper studies the complex ecological dynamics of Batumi on the Black Sea coast, through adetailed analysis of environmental factors and their impact. We use Business Intelligence (BI) methods to explore the complex interactions between natural and human impacts on the local ecosystems. By using data-focused approaches, including statistical analysis and predictive modeling, we aim to distinguish patterns and trends in ecological dynamics. This study aspires to make clear the complex relationships between environmental factors such as climate change, pollution levels, habitat degradation, and biodiversity loss, and their impacts on the coastal ecosystem of Batumi. Through this study, we aim to provide valuable information on sustainable management practices and conservation measures to protect the ecological integrity of this important coastal region.

关键词： Sea coast Pollution Statistical analysis Ecosystems Habitats Sea measurements Predictive models

来源：评论

学校读者我要写书评

暂无评论

The Combination of Foot Switch and Low-Cost IMU for a Wearable Mouse in Human-computer Interaction 12

The Combination of Foot Switch and Low-Cost IMU for a Wearab...

引用

12th International Conference on Information Technology and Electrical engineering, ICITEE 2020

作者： Widodo, Romy Budhi Jahja, Evans Giovanno, Yusuf Ma Chung University Ma Chung Human-Machine Interaction Research Center Informatics Engineering Study Program Malang Indonesia

ISBN: (纸本)9781728110974

A wearable mouse using upper arm movement/gesture is a promising pointing device that can be used by people with lower-arm disablement due to accident or prenatal disablement. The movement of the upper arm could be used to substitute the cursor movement. The use of an inertial measurement system is one way to capture the arm's movement in 3 dimensional spaces. The purposes of this study are the development of a new wearable mouse using the nine degree-of-freedom of inertial measurement unit and a foot switch for clicking action;and the evaluation of its performance on a specified level of difficulties. The device was evaluated by comparing the proposed device and a standard mouse. The performance indicators were throughput, movement time, comfort, and fatigue, based on Fitts' Law formula. The important finding is a significant (p © 2020 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning Models for Early Detection of Albuminuria Risk in Type-2 Diabetes Mellitus Patients

Supervised Learning Models for Early Detection of Albuminuri...

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Arief Purnama Muharram Dicky Levenus Tahapary Yeni Dwi Lestari Randy Sarayar Valerie Josephine Dirjayanto Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Metabolic Disorder Cardiovascular and Aging Research Center Faculty of Medicine Indonesia Medical Education and Research Institute Universitas Indonesia Jakarta Indonesia Ophthalmology Department Faculty of Medicine Cipto Mangunkusumo General Hospital Universitas Indonesia Jakarta Indonesia Faculty of Medicine Universitas Indonesia Jakarta Indonesia

Diabetes, especially T2DM, continues to be a significant health problem. One of the major concerns associated with diabetes is the development of its complications. Diabetic nephropathy, one of the chronic complication of diabetes, adversely affects the kidneys, leading to kidney damage. Diagnosing diabetic nephropathy involves considering various criteria, one of which is the presence of a pathologically significant quantity of albumin in urine, known as albuminuria. Thus, early prediction of albuminuria in diabetic patients holds the potential for timely preventive measures. This study aimed to develop a supervised learning model to predict the risk of developing albuminuria in T2DM patients. The selected supervised learning algorithms included Naive Bayes, Support Vector Machine (SVM), decision tree, random forest, AdaBoost, XGBoost, and Multi-Layer Perceptron (MLP). Our private dataset, comprising 184 entries of diabetes complications risk factors, was used to train the algorithms. It consisted of 10 attributes as features and 1 attribute as the target (albuminuria). Upon conducting the experiments, the MLP demonstrated superior performance compared to the other algorithms. It achieved accuracy and f1-score values as high as 0.74 and 0.75, respectively, making it suitable for screening purposes in predicting albuminuria in T2DM. Nonetheless, further studies are warranted to enhance the model's performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning Models for Early Detection of Albuminuria Risk in Type-2 Diabetes Mellitus Patients

arXiv

引用

arXiv 2023年

作者： Muharram, Arief Purnama Tahapary, Dicky Levenus Lestari, Yeni Dwi Sarayar, Randy Dirjayanto, Valerie Josephine Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Metabolic Disorder Cardiovascular and Aging Research Center Indonesia Medical Education and Research Institute Faculty of Medicine Universitas Indonesia Jakarta Indonesia Ophthalmology Department Faculty of Medicine Universitas Indonesia Cipto Mangunkusumo General Hospital Jakarta Indonesia Faculty of Medicine Universitas Indonesia Jakarta Indonesia

Diabetes, especially T2DM, continues to be a significant health problem. One of the major concerns associated with diabetes is the development of its complications. Diabetic nephropathy, one of the chronic complication of diabetes, adversely affects the kidneys, leading to kidney damage. Diagnosing diabetic nephropathy involves considering various criteria, one of which is the presence of a pathologically significant quantity of albumin in urine, known as albuminuria. Thus, early prediction of albuminuria in diabetic patients holds the potential for timely preventive measures. This study aimed to develop a supervised learning model to predict the risk of developing albuminuria in T2DM patients. The selected supervised learning algorithms included Naïve Bayes, Support Vector Machine (SVM), decision tree, random forest, AdaBoost, XGBoost, and Multi-Layer Perceptron (MLP). Our private dataset, comprising 184 entries of diabetes complications risk factors, was used to train the algorithms. It consisted of 10 attributes as features and 1 attribute as the target (albuminuria). Upon conducting the experiments, the MLP demonstrated superior performance compared to the other algorithms. It achieved accuracy and f1-score values as high as 0.74 and 0.75, respectively, making it suitable for screening purposes in predicting albuminuria in T2DM. Nonetheless, further studies are warranted to enhance the model’s performance. © 2023, CC BY-SA.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Brain Tumor Objects in Magnetic Resonance Imaging (MRI) Image using Connected Component Label Algorithm

Segmentation of Brain Tumor Objects in Magnetic Resonance Im...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Prasetyo Mimboro Andi Sunyoto Rizqi Sukma Kharisma Informatics Engineering Departement Postgraduate Program Universitas Amikom Yogyakarta PT Perkebunan Nusantara IV Yogyakarta Indonesia

ISBN: (纸本)9781665499705

Several techniques in computer vision can be used in object grouping, one of which is image segmentation. Segmentation is a field of computer vision that aims to group all pixels in an image into regions that have homogeneity in their characteristics. In this study, the segmentation technique will be carried out to partition objects in magnetic resonance image (MRI) images. Object segmentation uses a connected component labeling algorithm to classify regions or objects of brain tumors in MRI images. The dataset used in this study amounted to 80 images, of which 30 images contained meningioma brain tumor disease, 30 images with glioma brain tumor disease, and 20 images without indications of brain tumor disease. Based on tests conducted, the average accuracy obtained in detecting brain tumor objects is 96.66%.

关键词： Image segmentation Computer vision Mechatronics Magnetic resonance imaging Object segmentation Prediction algorithms Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep STI: Deep Stochastic Time-series Imputation on Electronic Health Records

Deep STI: Deep Stochastic Time-series Imputation on Electron...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Ming-Che Cheng Yi-Hsien Hsieh Te-Cheng Hsu Tung-Hung Su Che Lin Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Dept. of Internal Medicine Division of Gastroenterolgy and Hepatology National Taiwan University Hospital Taipei Taiwan Department of Electrical Engineering NTU Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan Smart Medicine and Health Informatics Program NTU Taipei Taiwan

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Electronic Health Records (EHRs) are a cornerstone of modern healthcare analytics, offering rich datasets for various disease analyses through advanced deep learning algorithms. However, the pervasive issue of missing values in EHRs significantly hampers the development and performance of these models. Addressing this challenge is crucial for enhancing clinical decision-making and patient care. Existing methods for handling missing data, ranging from simple imputation to more sophisticated approaches, often fall short of capturing the temporal dynamics inherent in EHRs. To bridge this gap, we introduce the Deep Stochastic Time-series Imputation (Deep STI) algorithm, an innovative end-to-end deep learning model that seamlessly integrates a sequence-to-sequence generative network with a prediction network. Deep STI is designed to leverage the observed time-series data in EHRs, learning to infer missing values from the temporal context with high accuracy. We evaluated Deep STI on the liver cancer data from the National Taiwan University Hospital (NTUH), Taiwan. Our results showed that Deep STI achieved better 5-year hepatocellular carcinoma predictions (19.21% in the area under the precision-recall curve) than extreme gradient boosting (18.15%) and Transformer (18.09%). The ablation study also illustrates the efficacy of our generative architecture design compared to regular imputations. This approach not only promises to improve the reliability of disease analysis in the presence of incomplete data but also sets a new standard for utilizing EHRs in predictive healthcare. Our work aims to advance the field of healthcare analytics and open new avenues for research in deep learning applications to EHRs.

关键词： Deep learning Time series analysis Stochastic processes Predictive models Transformers Imputation Reliability Electronic medical records Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Imbalance fault detection in BLDC motors through audio signals using the density of maxima and CNN

Imbalance fault detection in BLDC motors through audio signa...

引用

Brazilian Symposium on Computing System engineering (SBESC)

作者： Yuri C. Gouveia Alisson V. Brito Tiago P. Nascimento Jorge Gabriel Ramos Abel Lima Filho Graduate Program in Informatics Universidade Federal da Paraiba Joao Pessoa Brazil Laboratory of System Engineering and Robotics Universidade Federal da Paraiba Joao Pessoa Brazil Department of Physics Universidade Federal da Paraiba Joao Pessoa Brazil Department of Mechanical Engineering Universidade Federal da Paraiba Joao Pessoa Brazil

Unmanned Aerial Vehicles (UAVs), commonly known as drones, are increasingly used for various tasks. However, increased usage leads to more failures, posing risks to humans and the environment. This study identifies propeller imbalance faults in Brushless DC (BLDC) motors of UAVs. It compares two fault detection methodologies based on chaotic behavior: the alreadyknown CNN approach, and the SAC-DM+CNN approach. Both methods involve acquiring audio signals, generating spectrograms, and training a Convolutional Neural Network (CNN) model. Results show that the CNN approach achieves 98.18% accuracy, while the SAC-DM+CNN approach achieves 71.43% accuracy in classifying propeller balance faults.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cyber Security for Hoax News Detection with Similarity Algorithm

Cyber Security for Hoax News Detection with Similarity Algor...

引用

International Conference on informatics and Computing (ICIC)

作者： Sy.Yuliani Yakub David Agustriawan Irmawati Dinar Ajeng Kristiyanti Shahrin Sahib Mohd Faizal Abdollah Mohammed Nasser Al-Mhiqani Yusuf Durachman The Informatic Study Program Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Faculty of Information Communication Technology Universiti Teknikal Malaysia Melaka Melaka Malaysia Department of Cyber Security University of Huddersfield United Kingdom Department of Information System State Islamic University of Syarif Hidayatullah Jakarta Jakarta Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Hoax news is false information disseminated to deceive or mislead audiences, often with the aim of swaying opinions or creating confusion. The rise of social media has amplified the spread of hoax news, particularly in sensitive areas such as politics and health. In response to this growing issue, this paper proposes a Natural Language Processing (NLP) approach of detecting hoax news using the Smith-Waterman similarity algorithm. By comparing news content with a curated dataset of verified hoaxes, the system calculates a similarity score to assess the likelihood of the news being false. The results of this study show that news articles analyzed using the Smith-Waterman algorithm achieve a high accuracy, with a similarity score exceeding $93 \%$ for news inputs over 100 words. Furthermore, the proposed system demonstrates an efficient processing time, completing the analysis in approximately 6.57 seconds. These findings underscore the algorithm’s potential for real-time application in detecting fake news on social media and other digital platforms. This research aims not only to enhance the technical capabilities of hoax detection systems but also to foster greater media literacy and a more informed public.

关键词： Accuracy Social networking (online) Scalability Approximation algorithms Real-time systems Natural language processing Fake news informatics Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: A proposal for Internet of Smart Home Things based on BCI system to aid patients with amyotrophic lateral sclerosis

引用

Neural Computing and Applications 2024年第28期36卷 17761-17761页

作者： de Oliveira Júnior, Wilson G. de Oliveira, Juliana M. Munoz, Roberto de Albuquerque, Victor Hugo C. Graduate Program in Applied Informatics Laboratory of Bioinformatics University of Fortaleza Fortaleza Brazil School of Informatics Engineering Universidad de Valparaíso Valparaíso Chile

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：