检索结果-内蒙古大学图书馆

2025 International Conference on Advancement in Data Science, E-learning and Information System, ICADEIS 2025

作者： Saveria, Hygea Gunawan, Putu Harry Informatics School of Computing Telkom University Bandung Indonesia

ISBN: (纸本)9798331513320

Stunting is a condition where a child's height significantly falls below the average for their age, primarily due to prolonged malnutrition and inadequate nutrient intake. This condition poses long-term challenges, affecting both physical growth and cognitive development. This study focuses on developing a predictive model using the C4.5 Decision Tree algorithm to classify the stunting status of children under five. The dataset comprises nutritional status data of toddlers collected from the Berastagi Health Center. Incorporating attributes such as gender, birth weight and height, age in months, weight, height, and the height-to-age ratio. The model aims to enhance the accuracy of stunting classification to support targeted prevention and treatment strategies. When compared to Naive Bayes, the Decision Tree C4.5 demonstrated superior performance, achieving an F1 score and average accuracy of 86%. This reflects a robust balance between precision and recall, underscoring its reliability in identifying children at risk of stunting. The research highlights the critical role of data-driven methodologies in public health. With its high accuracy, the model serves as a promising tool for healthcare providers, enabling more effective interventions to reduce stunting prevalence and improve nutritional outcomes among children under five years of age. © 2025 IEEE.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

MH-HMR:Human mesh recovery from monocular images via multi-hypothesis learning

引用

CAAI Transactions on Intelligence Technology 2024年第5期9卷 1263-1274页

作者： Haibiao Xuan Jinsong Zhang Yu-Kun Lai Kun Li College of Intelligence and Computing Tianjin UniversityTianjinChina School of Computer Science and Informatics Cardiff UniversityCardiffUK

Recovering 3D human meshes from monocular images is an inherently ill-posed and challenging task due to depth ambiguity,joint occlusion,and ***,most existing approaches do not model such uncertainties,typically yielding a single reconstruction for one *** contrast,the ambiguity of the reconstruction is embraced and the problem is considered as an inverse problem for which multiple feasible solutions *** address these issues,the authors propose a multi-hypothesis approach,multi-hypothesis human mesh recovery(MH-HMR),to efficiently model the multi-hypothesis representation and build strong relationships among the hypothetical ***,the task is decomposed into three stages:(1)generating a reasonable set of initial recovery results(i.e.,multiple hypotheses)given a single colour image;(2)modelling intra-hypothesis refinement to enhance every single-hypothesis feature;and(3)establishing inter-hypothesis communication and regressing the final human ***,the authors take further advantage of multiple hypotheses and the recovery process to achieve human mesh recovery from multiple uncalibrated *** with state-of-the-art methods,the MH-HMR approach achieves superior performance and recovers more accurate human meshes on challenging benchmark datasets,such as Human3.6M and 3DPW,while demonstrating the effectiveness across a variety of *** code will be publicly available at https://***/faculty/likun/projects/MH-HMR.

关键词： 3-D computer vision human reconstraction

来源：评论

学校读者我要写书评

暂无评论

An Examination of Harmonizing Multi-Vendor Cardiac MRI Data for Vendor-Neutral Image Segmentation 5

An Examination of Harmonizing Multi-Vendor Cardiac MRI Data ...

引用

5th International Conference on Advanced Research in computing, ICARC 2025

作者： Mohideen, Hamdaan Ayoob, Mohamed Nettasinghe, Oshan Sylvester, Vithushan Bowala, Helmini Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331530983

Vendor-specific scanner hardware, software, and image acquisition protocols can introduce systematic biases into MRI scans. This introduces non-biological artifacts which introduce variations across MRI images from different vendors. Further, we ratified such non-biological variances by conducting a discrepancy study on the MnMs-2 Cardiac MRI dataset. Data harmonization is the process of combining datasets from different sources while removing unwanted variations that are not caused by biological differences. This is important because it allows researchers to increase the understanding of biological differences in data, while mitigating vendor-specific biases. We used a domain adaptation methodology (which is a data harmonization method) on the dataset to unlearn domain (or vendor) specific biases by introducing a confusion loss to confuse the encoder. Furthermore, we introduced a 3D segmentation model to this method to capture spatial information. This method demonstrates the performance on the main task (segmentation) and compares the domain predictor, before and after unlearning. This shows the magnitude of mitigating vendor-specific biases of the model. In addition to the model architecture performance, we documented the discrepancy study between inter-vendor model performance to demonstrate the magnitude of impact in which vendor-specific, and non-biological variations of MRI scans can affect the model. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Age Prediction Based on User Faces Using Convolutional Neural Network Methods for Content Restrictions on Application Platforms 7

Age Prediction Based on User Faces Using Convolutional Neura...

引用

7th International Conference on Data Science and Its Applications, ICoDSA 2024

作者： MacHdi, Muhammad Irham Naufal Al Wirayuda, Tjokorda Agung Budi School of Computing Telkom University Informatics Bandung Indonesia

ISBN: (纸本)9798350365351

Children's development is significantly influenced by their environment, including the media they consume. In Indonesia, many children watch films that exceed their age-appropriate ratings due to the ease of accessing content without age verification on various platforms. To address this issue, this study develops a content restriction system that predicts users' ages based on facial images using a Convolutional Neural Network (CNN) with MobileNetV2 architecture. This architecture is selected for its efficiency in extracting complex features from images while maintaining fast processing speeds. The CNN model is trained using the UTKFace dataset, which includes a diverse range of ages, genders, and ethnicities, ensuring robustness and accuracy. The trained model is integrated into a mobile film application that scans users' faces and predicts their ages when they select a film. If the predicted age is appropriate for the film's rating, access is granted. Otherwise, a warning is issued, and access is denied. This system aims to protect children from inappropriate content, fostering a safer media consumption environment. The study also compares the performance of MobileNetV2 with Xception, highlighting that MobileNetV2 achieved a comparable Mean Absolute Error (MAE) with a minimal difference of 1.3 years while having a significantly smaller model size of 4.6 MB compared to Xception's 41.8 MB. This demonstrates the advantages of MobileNetV2 in terms of both performance and application size. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Ontology-based Conversational Recommender System for Tablet Products 9

Ontology-based Conversational Recommender System for Tablet ...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Dwipayana, Gisella Vania Baizal, Z.K.A. Telkom University Informatics School of Computing Bandung Indonesia

ISBN: (纸本)9798350394474

Technological developments have caused many electronic products to circulate in various circles of society, one of which is tablets. Tablets have various technical specifications which are often difficult to understand for the public, making it challenging for them to determine what they need based on those technical specifications. Therefore, a tablet conversational recommender system (CRS) based on product functional requirements is needed to educate users through conversational interaction. Some previous works have developed CRS framework based on functional requirements. In this paper, we utilize that framework and propose an ontology to build a CRS in tablet domain. The CRS interacts with users to gather their preferences regarding product functional requirements (e.g. a user needs a tablet to edit photos), then it recommends tablet products that meet those functional requirements. On the other hand, ontology is used to map functional requirements to the technical specifications of tablet products. This system is evaluated using accuracy metrics (performance-based evaluation) and user satisfaction evaluation. The evaluation results showed that the system achieves a recommendation accuracy of 95.36% with positive user satisfaction feedback. These results show that the system is effective in providing tablet product recommendations based on user functional requirements. © 2024 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of Computer Science Students' Performance Based on Core Foundational Courses using Ensemble Machine Learning Methods 12

Analysis and Prediction of Computer Science Students' Perfor...

引用

12th IEEE International Conference on Intelligent Systems, IS 2024

作者： Mayeku, Betty Kilwake, Juma Mamai, Ambrose Osala Wamasebu, Eve Khatundi School of Computing and Informatics Kibabii University Bungoma Kenya

ISBN: (纸本)9798350350982

As the surge toward a technology-driven and dependent society increases, the demand for technology oriented workforce particularly computer science continues to rise. However, the concern that continues to persist in a number of higher institutions of learning is the low graduation rates and poor performance in computer science programs. This study, carried out in a Kenyan public university attempted to extend the understanding on the performance of computer science students The study aimed at examining whether performance in early foundational core courses had any influence on the final graduation score (through final accumulative score) among computer science students using ensemble machine learning methods. The study specifically employed Random Forest and XGBoost ensemble methods. The results showed the Random forest regression model having a prediction power of 83.20% while XGBoost had a slightly improved prediction power of 84.6%. The results also revealed better model performance when using only years 1 and 2 core courses as compared to using years 1 to 3 core courses. This is an indicator that foundational core courses are good predictors of student academic performance in computer science programs. This work in progress is part of a preliminary study aimed at addressing the challenge of low graduation rates and poor performance in computer science programs. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Parameter-efficient fine-tuning of pre-trained code models for just-in-time defect prediction

引用

Neural computing and Applications 2024年第27期36卷 16911-16940页

作者： Abu Talib, Manar Bou Nassif, Ali Azzeh, Mohammad Alesh, Yaser Afadar, Yaman Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Computer Engineering College of Computing and Informatics Sharjah United Arab Emirates King Hussein School for Computing Sciences Princess Sumaya University for Technology Amman Jordan

Software engineering workflows use version control systems to track changes and handle merge cases from multiple contributors. This has introduced challenges to testing because it is impractical to test whole codebases to ensure each change is defect-free, and it is not enough to test changed files alone. Just-in-time software defect prediction (JIT-SDP) systems have been proposed to solve this by predicting the likelihood that a code change is defective. Numerous techniques have been studied to build such JIT software defect prediction models, but the power of pre-trained code transformer language models in this task has been underexplored. These models have achieved human-level performance in code understanding and software engineering tasks. Inspired by that, we modeled the problem of change defect prediction as a text classification task utilizing these pre-trained models. We have investigated this idea on a recently published dataset, ApacheJIT, consisting of 44k commits. We concatenated the changed lines in each commit as one string and augmented it with the commit message and static code metrics. Parameter-efficient fine-tuning was performed for 4 chosen pre-trained models, JavaBERT, CodeBERT, CodeT5, and CodeReviewer, with either partially frozen layers or low-rank adaptation (LoRA). Additionally, experiments with the Local, Sparse, and Global (LSG) attention variants were conducted to handle long commits efficiently, which reduces memory consumption. As far as the authors are aware, this is the first investigation into the abilities of pre-trained code models to detect defective changes in the ApacheJIT dataset. Our results show that proper fine-tuning improves the defect prediction performance of the chosen models in the F1 scores. CodeBERT and CodeReviewer achieved a 10% and 12% increase in the F1 score over the best baseline models, JITGNN and JITLine, when commit messages and code metrics are included. Our approach sheds more light on the abilities of l

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

FlexiSecure - AI-Powered Fraud Detection with Real-Time Alerts and Customizable Security 5

FlexiSecure - AI-Powered Fraud Detection with Real-Time Aler...

引用

5th International Conference on Advanced Research in computing, ICARC 2025

作者： Mumthas, Nooha Informatics Institute of Technology School of Computing Colombo Sri Lanka

ISBN: (纸本)9798331530983

The rapid expansion of online financial transactions has escalated the risk of fraud, posing significant challenges for banks and financial institutions, particularly in Sri Lanka. Traditional rule-based fraud detection systems often find it challenging to balance speed and accuracy, rendering them less effective against advanced and evolving fraud schemes. This study proposes a hybrid machine learning model combining decision trees and neural networks to enhance fraud detection performance. The model incorporates advanced preprocessing techniques, including feature scaling and outlier detection, to improve data quality. It employs supervised learning to achieve high accuracy and adapt to emerging fraud patterns. Additionally, explainable AI (XAI) is incorporated to ensure transparency in detection outcomes, where the user would be entrusted to make the final decision on the transaction, thereby fostering user trust and compliance with regulations in the financial sector. The model is designed to process large volumes of transactions efficiently, which demonstrates its scalability and suitability for high-volume banking environments. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Music: A Review of Artificial Intelligence in Jazz Reharmonization 5

Transforming Music: A Review of Artificial Intelligence in J...

引用

5th International Conference on Advanced Research in computing, ICARC 2025

作者： Jayasinghe, Sachindu Bhareti, Kushan Institute of Technology School of Computing Informatics Colombo Sri Lanka

ISBN: (纸本)9798331530983

Jazz reharmonization is a complex musical technique that improves harmonic frameworks by inventive chord progressions, augmenting the depth and emotional resonance of pieces. This paper examines the use of artificial intelligence, namely transformer networks, in the automation of jazz reharmonization, ensuring melodic coherence and artistic fidelity. This review compiles current research to highlight essential approaches, including early rule-based systems, neural networks, and advanced transformer models while emphasizing their benefits and limits. Particular emphasis is placed on the difficulties associated with dataset preparation, assessment measures, and the adaptation of AI systems to the intricacies of jazz harmony. The evaluation, via a critical examination of previous studies, identifies areas for enhancement, including real-time applications, multi-modal data integration, and cross-genre adaptation. The insights provided seek to direct future research and position transformers as a revolutionary instrument in computational musicology. This document is an extensive reference for scholars and professionals investigating the convergence of artificial intelligence and jazz music. © 2025 IEEE.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s Disease Prediction Using Spectrograms and Deep Belief Networks 14

Parkinson’s Disease Prediction Using Spectrograms and Deep ...

引用

14th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2025

作者： Sandeep, C.S. Margala, Martin School of Computing and Informatics University of Louisiana at Lafayette United States

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531935

This research presents a way to forecast Parkinson's disease in the early stages by means of spectrogram investigation and deep belief networks (DBNs). The aforesaid way concentrates on the use of spectrograms in order to get the best results and the extraction of innovative features and patterns from the signal of the speech or motor, which is indicative of Parkinson's disease. By using DBNs, which is a resilient deep learning mechanism, the system has the good feature of learning deep representations of the data, which makes the detection and classification accurate. The coupling of spectrograms with DBNs gives the model perspective to notice even the less severe differences in the input signals which are often missed out by traditional methods. The outlined aggregate demonstrates a prologue to a system that would be an accurate and automated solution to the problem, which in the end could be a help to healthcare professionals in a timely procurement of intervention and treatment. The proposed model makes clear the the ability of advanced machine learning techniques to solve hard neurological disorders and enhance patient outcomes. © 2025 IEEE.

关键词： Neurodegenerative diseases

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：