检索结果-内蒙古大学图书馆

2023 International Seminar on Application for Technology of Information and Communication, iSemantic 2023

作者： Supriyanto, Catur Salam, Abu Zeniarja, Junta Wijaya, Adi Universitas Dian Nuswantoro Bachelor Program in Informatics Engineering Faculty of Computer Science Semarang Indonesia Universitas Indonesia Maju Department of Health Information Management Jakarta Indonesia

ISBN: (纸本)9798350339215

The field of dermatology faces considerable challenges when it comes to early detection of skin cancer. Our study focused on using different datasets, including original data, augmented data, and SMOTE oversampled data, to identify skin cancer. Our dataset consisted of images of skin lesions from the MNIST Skin Cancer dataset (HAM 10000), including samples of both cancerous and benign cases in the dataset. We employed data augmentation to expand the dataset's size and increase the diversity of skin lesion features. Furthermore, to tackle class imbalance in the dataset, we applied the SMOTE oversampling technique to generate synthetic samples for the under-represented group. With the original, augmented, and SMOTE oversampled datasets, we trained a Convolutional Neural Network (CNN) model. The performance of the model was evaluated using accuracy, recall, precision, and F1-score. The comparison between the results obtained from the original data, augmented data, and SMOTE oversampling data clearly revealed distinctions in performance. Our findings clearly demonstrate that employing data augmentation and SMOTE oversampling can significantly enhance the efficacy of skin cancer detection. © 2023 IEEE.

关键词： Neural network models

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 10

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

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Tu, Yu-Chen Wang, Hsuan-Chih Liu, Chien-Pin Hsieh, Chia-Yeh Chan, Chia-Tai National Yang Ming Chiao Tung University Department of Biomedical Engineering Taipei City112 Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City242062 Taiwan

ISBN: (纸本)9798350394924

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. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Reversible data hiding based on pixel segmentation and prediction for improving hiding capacity

引用

Signal, Image and Video Processing 2024年第6-7期18卷 5043-5059页

作者： Huang, Cheng-Ta Weng, Chi-Yao Zheng, Guo-Ting Weng, Hao-Yu International Bachelor Program in Informatics Yuan Ze University Taoyuan320315 Taiwan Department of Information Management Yuan Ze University Taoyuan320315 Taiwan Department of Computer Science and Information Engineering National Chiayi University Chiayi City600355 Taiwan Department of Computer Science and Artificial Intelligence National Pingtung University Pingtung900391 Taiwan Department of Computer Science and Information Engineering National Central University Taoyuan City320317 Taiwan

The idea of the traditional histogram shifting technique is to hide a message within the cover-image pixel distribution. However, the embedding capacity is limited by the peak point occurrences. To solve this problem, many reversible data hiding (RDH) techniques are developed to combine pixel prediction and histogram shifting to increase the embedding payload. In this paper, a RDH scheme based on chessboard prediction and pixel partitioning is proposed for enhancing the hiding payload. Pixel partitioning is used to separate a pixel into two parts: most significant bit and least significant bit. Then, the chessboard predictor is adopted to generate prediction errors and separate the pixels. Thereafter, histogram shifting is applied to embed the secret messages into prediction errors. Due to the high similarity of adjacent pixels in an image, the generated prediction errors are highly close to zero, resulting in a large embedding space. The experimental results indicate that the proposed method has superior performance in embedding capacity with acceptable image visual quality compared to existing schemes since it adopts the adaptive adjustment strategy to achieve this improved balance. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge Distillation 48

Prefallkd: Pre-Impact Fall Detection Via CNN-ViT Knowledge D...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Chi, Tin-Han Liu, Kai-Chun Hsieh, Chia-Yeh Tsao, Yu Chan, Chia-Tai National Yang Ming Chiao Tung University Department of Biomedical Engineering Taiwan Academia Sinica Research Center for Information Technology Innovation Taiwan Fu Jen Catholic University Bachelor's Program in Medical Informatics and Innovative Applications Taiwan

ISBN: (纸本)9781728163277

Fall accidents are critical issues in an aging and aged society. Recently, many researchers developed "pre-impact fall detection systems"using deep learning to support wearable-based fall protection systems for preventing severe injuries. However, most works only employed simple neural network models instead of complex models considering the usability in resource-constrained mobile devices and strict latency requirements. In this work, we propose a novel pre-impact fall detection via CNN-ViT knowledge distillation, namely PreFallKD, to strike a balance between detection performance and computational complexity. The proposed PreFallKD transfers the detection knowledge from the pre-trained teacher model (vision transformer) to the student model (lightweight convolutional neural networks). Additionally, we apply data augmentation techniques to tackle issues of data imbalance. We conduct the experiment on the KFall public dataset and compare PreFallKD with other state-of-the-art models. The experiment results show that PreFallKD could boost the student model during the testing phase and achieves reliable F1-score (92.66%) and lead time (551.3 ms). © 2023 IEEE.

关键词： Inertial measurement units Knowledge distillation Pre-impact fall detection Vision transformer Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Identification of Software Bugs by Analyzing Natural Language-Based Requirements Using Optimized Deep Learning Features

引用

Computers, Materials & Continua 2024年第3期78卷 4379-4397页

作者： Qazi Mazhar ul Haq Fahim Arif Khursheed Aurangzeb Noor ul Ain Javed Ali Khan Saddaf Rubab Muhammad Shahid Anwar Department of Computer Science and Engineering and International Bachelor’s Program in Informatics Yuan Ze UniversityZhongliTaoyuan320315Taiwan Department of Computer Science National University of PakistanRawalpindiPunjab46000Pakistan Department of Computer Software Engineering MCSNational University of Sciences and TechnologyIslamabad44000Pakistan Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Department of Computer Science School of PhysicsEngineering and Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Department of AI and Software Gachon UniversitySeongnam-SI13120South Korea

Software project outcomes heavily depend on natural language requirements,often causing diverse interpretations and issues like ambiguities and incomplete or faulty *** are exploring machine learning to predict software bugs,but a more precise and general approach is *** bug prediction is crucial for software evolution and user training,prompting an investigation into deep and ensemble learning ***,these studies are not generalized and efficient when extended to other ***,this paper proposed a hybrid approach combining multiple techniques to explore their effectiveness on bug identification *** methods involved feature selection,which is used to reduce the dimensionality and redundancy of features and select only the relevant ones;transfer learning is used to train and test the model on different datasets to analyze how much of the learning is passed to other datasets,and ensemble method is utilized to explore the increase in performance upon combining multiple classifiers in a *** National Aeronautics and Space Administration(NASA)and four Promise datasets are used in the study,showing an increase in the model’s performance by providing better Area Under the Receiver Operating Characteristic Curve(AUC-ROC)values when different classifiers were *** reveals that using an amalgam of techniques such as those used in this study,feature selection,transfer learning,and ensemble methods prove helpful in optimizing the software bug prediction models and providing high-performing,useful end mode.

关键词： Natural language processing software bug prediction transfer learning ensemble learning feature selection

来源：评论

学校读者我要写书评

暂无评论

Multi-Speaker Voice Cloning in Indonesian Using Sequence to Sequence Speech Synthesis

SSRN

引用

SSRN 2022年

作者： Awangga, Rolly Maulana Majesty, Dinda Applied Bachelor Program of Informatics Engineering Politeknik Pos Indonesia Bandung40151 Indonesia

Multi-Speaker Voice Cloning is a system that can produce various voices based on voice samples and text input. Voice cloning can be an alternative to get audio data quickly without recording, which requires a lot of time, cost, and effort. Sequence to Sequence Speech Synthesis produces sounds that are naturally similar to speech equivalent to the human voice. Sequence to Sequence Speech Synthesis is a technology for generating speech directly from the text, consisting of attention-based predictive network features. Multi-Speaker Voice Clone consists of speaker encoder, encoder-decoder, and vocoder models. Tacotron-2 as model encoder-decoder and WaveNet as a vocoder. The speaker encoder will produce a speaker embedding to recognize the sound from the speaker. Tacotron-2 will embed text into the mel scale spectrogram. WaveNet will synthesize the time domain waveform from the mel scale spectrogram and generate sound predictions based on the samples. This model uses a multi-speaker voice dataset in Indonesian. Combining the three models produces a value of 3.28 for speech naturalness and 1.94 for speech similarity. © 2022, The Authors. All rights reserved.

关键词： Cloning

来源：评论

学校读者我要写书评

暂无评论

YNote: A Novel Music Notation for Fine-Tuning LLMs in Music Generation

arXiv

引用

arXiv 2025年

作者： Lu, Shao-Chien Yeh, Chen-Chen Cho, Hui-Lin Hsu, Chun-Chieh Hsu, Tsai-Ling Wu, Cheng-Han Shih, Timothy K. Lin, Yu-Cheng Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan International Bachelor Program in Informatics Yuan Ze University Taoyuan Taiwan Department of Computer Science and Information Engineering National Central University Taoyuan Taiwan

The field of music generation using Large Language Models (LLMs) is evolving rapidly, yet existing music notation systems, such as MIDI, ABC Notation, and MusicXML, remain too complex for effective fine-tuning of LLMs. These formats are difficult for both machines and humans to interpret due to their variability and intricate structure. To address these challenges, we introduce YNote, a simplified music notation system that uses only four characters to represent a note and its pitch. YNote’s fixed format ensures consistency, making it easy to read and more suitable for fine-tuning LLMs. In our experiments, we fine-tuned GPT-2 (124M) on a YNote-encoded dataset and achieved BLEU and ROUGE scores of 0.883 and 0.766, respectively. With just two notes as prompts, the model was able to generate coherent and stylistically relevant music. We believe YNote offers a practical alternative to existing music notations for machine learning applications and has the potential to significantly enhance the quality of music generation using LLMs. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Fluid Intake Assessment Approaches for Fluid Intake Monitoring System

Biosensors

引用

Biosensors 2024年第1期14卷 14页

作者： Hsieh, Chia-Yeh Huang, Hsiang-Yun Chan, Chia-Tai Chiu, Li-Tzu Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City24205 Taiwan Department of Biomedical Engineering National Yang Ming Chiao Tung University Taipei City11221 Taiwan

Monitoring fluid intake is essential to help people manage their individual fluid intake behaviors and achieve adequate hydration. Previous studies of fluid intake assessment approaches based on inertial sensors can be categorized into wrist-worn-based and smart-container-based approaches. This study aims to analyze wrist-worn-based and smart-container-based fluid intake assessment approaches using inertial sensors. The comparison of these two approaches should be analyzed according to gesture recognition and volume estimation. In addition, the influence of the fill level and sip size information on the performance is explored in this study. The accuracy of gesture recognition with postprocessing is 92.89% and 91.8% for the wrist-worn-based approach and smart-container-based approach, respectively. For volume estimation, sip-size-dependent models can achieve better performance than general SVR models for both wrist-worn-based and smart-container-based approaches. The improvement of MAPE, MAD, and RMSE can reach over 50% except MAPE for small sip sizes. The results demonstrate that the sip size information and recognition performance are important for fluid intake assessment approaches. © 2023 by the authors.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Fall Detection Algorithm Using Ensemble Model of Coarse-fine CNN and GRU Networks

Deep Learning-based Fall Detection Algorithm Using Ensemble ...

引用

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Liu, Chien-Pin Li, Ju-Hsuan Chu, En-Ping Hsieh, Chia-Yeh Liu, Kai-Chun Chan, Chia-Tai Tsao, Yu National Yang Ming Chiao Tung University Department of Biomedical Engineering Taipei City112 Taiwan Fu Jen Catholic University Bachelor's Program in Medical Informatics and Innovative Applications New Taipei City242062 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei City115 Taiwan

ISBN: (纸本)9781665493840

Falls are the public health issue for the elderly all over the world since the fall-induced injuries are associated with a large amount of healthcare cost. Falls can cause serious injuries, even leading to death if the elderly suffers a 'long-lie.' Hence, a reliable fall detection (FD) system is required to provide an emergency alarm for first aid. Due to the advances in wearable device technology and artificial intelligence, some fall detection systems have been developed using machine learning and deep learning methods to analyze the signal collected from accelerometer and gyroscopes. In order to achieve better fall detection performance, an ensemble model that combines a coarse-fine convolutional neural network and gated recurrent unit is proposed in this study. The parallel structure design used in this model restores the different grains of spatial characteristics and capture temporal dependencies for feature representation. This study applies the FallAllD public dataset to validate the reliability of the proposed model, which achieves a recall, precision, and F-score of 92.54%, 96.13%, and 94.26%, respectively. The results demonstrate the reliability of the proposed ensemble model in discriminating falls from daily living activities and its superior performance compared to the state-of-the-art convolutional neural network long short-term memory (CNN-LSTM) for FD. © 2023 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Oversampling Methods on Deep Learning-Based Skin Cancer Classification

Performance Evaluation of Oversampling Methods on Deep Learn...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Catur Supriyanto Abu Salam Junta Zeniarja Adi Wijaya Bachelor Program in Informatics Engineering Faculty of Computer Science Universitas Dian Nuswantoro Semarang Indonesia Department of Health Information Management Universitas Indonesia Maju Jakarta Indonesia

The field of dermatology faces considerable challenges when it comes to early detection of skin cancer. Our study focused on using different datasets, including original data, augmented data, and SMOTE oversampled data, to identify skin cancer. Our dataset consisted of images of skin lesions from the MNIST Skin Cancer dataset (HAM 10000), including samples of both cancerous and benign cases in the dataset. We employed data augmentation to expand the dataset’s size and increase the diversity of skin lesion features. Furthermore, to tackle class imbalance in the dataset, we applied the SMOTE oversampling technique to generate synthetic samples for the under-represented group. With the original, augmented, and SMOTE oversampled datasets, we trained a Convolutional Neural Network (CNN) model. The performance of the model was evaluated using accuracy, recall, precision, and F1-score. The comparison between the results obtained from the original data, augmented data, and SMOTE oversampling data clearly revealed distinctions in performance. Our findings clearly demonstrate that employing data augmentation and SMOTE oversampling can significantly enhance the efficacy of skin cancer detection.

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：