检索结果-内蒙古大学图书馆

14th international Conference on Frontier Computing, FC 2024

作者： Yang, Hsuan-Che Chang, Wen-Chih Huang, Wei-Han Hsu, Chia-Hao Lin, Yen-Chen Li, Jie-Syuan Lee, Yun-Cheng Luo, Zeng-Sheng Department of Information Management Chihlee University of Technology New Taipei City220 Taiwan International Master Program of Information Technology and Applications National Ping-Tung University Ping-Tung Taiwan

ISBN: (纸本)9789819623945

The worldwide aging population has been on the rise due to the advancement of medical science and decreasing birth rates. Unfortunately, this has led to an increase in falls among the elderly, which has emerged as one of the top ten causes of death for elderly individuals in Taiwan. To address this issue, our study aims to leverage the widespread use of smartphones and smartwatches to detect and prevent falls in older adults. Our machine learning model is trained using the UMAFall dataset, which collects data on daily activities and falling actions through five sensing devices. We used Azure Machine Learning Studio to test six different machine learning algorithms to evaluate suitable algorithms. In the end, the Two-Class Decision Tree algorithm achieved the best results. In our next step, this method will be programmed with the TensorFlow Lite and train the model. This model will be integrated into Android-based apps that can be installed on smartphones. By continuously connecting the smartwatch and smartphone Apps, the accelerometer, gyroscope, and magnetometer in both devices can be compared and analyzed in real time using the TensorFlow Lite model, accurately determining the wearer's actions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Underwater Vision Enhancement: Adaptive White Balancing Combined with Nature-Inspired Algorithm Mechanisms

Underwater Vision Enhancement: Adaptive White Balancing Comb...

引用

Disruptive Technologies (ICDT), international Conference on

作者： Gunjan Verma Divya Sharma Sanjeev Kumar Urvashi Garima Saini Taruna Chopra Master of Computer Applications G.L. Bajaj Institute of Technology and Management Greater Noida India School of Computer Applications Manav Rachna International Institute of Research and Studies Faridabad India Information Technology IINTM Janakpuri Guru Gobind Singh Indraprastha University Delhi India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Underwater reconstructed images often suffer from color cast, low contrast, and reduced brightness due to absorption and scattering effects. Research has shown that underwater environments exhibit low-pass characteristics, leading to the loss of crucial image information and degradation in visual quality. Image enhancement techniques can help recover this lost information. Various underwater image enhancement methods have been proposed; however, existing approaches often introduce artefacts and produce unrealistic results. To address these challenges, we propose a novel adaptive white-balancing method specifically designed for underwater images. This method primarily focuses on correcting a color cast in underwater scenes. Following white balancing, both local and global contrast enhancements are applied to further improve image quality. The artificial bee colony algorithm is employed to significantly enhance contrast, while a Laplacian filter is used to refine local contrast. The proposed method effectively improves contrast and eliminates color cast, resulting in more natural-looking underwater images. Additionally, the integration of different algorithms enhances the quality of degraded images. Experimental results demonstrate that our method outperforms existing techniques, achieving the highest UIQM score (41.78 on RUIE, 44.82 on EUVP datasets) and the lowest BRISQUE score (2.8 on RUIE, 0.8 on EUVP), indicating superior contrast, color correction, and image naturalness.

关键词： Image quality Visualization Laplace equations Image resolution Image color analysis Lighting Scattering Image restoration Image enhancement Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Predict the Language Proficiency of Thai Students Studying in Taiwan 10

Using Machine Learning to Predict the Language Proficiency o...

引用

10th international Conference on Applied System Innovation, ICASI 2024

作者： Moocharoen, Charoenwat Chang, Wen-Chih National Pingtung University International Master Program in Information Technology and Applications Taiwan

ISBN: (纸本)9798350394924

Currently, there are students from Thailand who wish to study abroad. The researchers have chosen Taiwan as the focus. Among the students who come for further studies, there are those proficient in the English language and those who are not. Factors such as language readiness, financial preparedness, scholarship availability, and the university's reputation are crucial in the decision-making process for choosing an educational institution. Simultaneously, some students had the opportunity to study in Taiwan but, due to language unpreparedness, had to withdraw from their studies and return to their home country. The researchers emphasize the importance of language readiness among students. Data has been collected from 316 data including undergraduate, master's, doctoral, and language students of Thai students throughout Taiwan, and a model has been developed to predict the English language proficiency of Thai students. The goal is to create a model with the highest level of accuracy to produce reliable results. This model can be utilized by educational institutions to tailor their courses to match the language abilities of Thai students, thereby enhancing the overall learning experience. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enabling Smart Home Energy Management through Gesture-Based Control and IoT technology

Enabling Smart Home Energy Management through Gesture-Based ...

引用

2023 international Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2023

作者： Rambe, Khairul Hawani Ou, Chia-Ho International Master Program in Information Technology and Applications Sweden National Pingtung University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350324174

The Internet of Things (IoTs) have become ubiquitous in all aspects of public needs today. The application of IoT technology is crucial for promoting energy-saving behavior. This paper presents a control system used for smart home devices based on hand gesture control and Android applications. The hardware design uses the ESP32 microcontroller, which has an in-chip Wi-Fi module, making it very suitable for creating IoT application systems. The software was designed using the Arduino IDE, and the application display design was developed using Kodular Creator, which is used to control the lamps and switches. The experiment results show that the electrical equipment can be activated using the Android application with gesture sensors by waving down, up, left, and right. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

The Efficient Traffic Sign Detection and Recognition for Taiwan Road Using YOLO Model with Hybrid Dataset 9

The Efficient Traffic Sign Detection and Recognition for Tai...

引用

9th international Conference on Applied System Innovation, ICASI 2023

作者： Suwattanapunkul, Taweelap Wang, Lung-Jen National Pingtung University International Master Program in Information Technology and Applications Taiwan National Pingtung University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350398380

According to the trend of worldwide car sales have grown up, this cause may increase accidents on the road due to human error. The self-driverless car has been developed to solve this problem. One task of the self-driverless car is traffic sign detection and recognition (TSDR), which will help drivers notify the traffic sign installed on the road in advance. Taiwan roads have specific traffic signs, and no Taiwan traffic sign public dataset is available. In this paper, our proposed object detection method was experimentally performed using YOLOv5s6 and YOLOv8s models on three different datasets, as Tsinghua-Tencent 100K (TT100k), the self-created Taiwan traffic sign (TWTS), and the hybrid dataset, which combine the traffic scenes between TT100k and TWTS dataset. The output results from each dataset and each model, which is trained on the same parameter, will be compared to validate the proposed method. The experiment results' comparison of the hybrid dataset between YOLOv5s6 and YOLOv8s models display the results of the mAP@.5 is about 65% and 76.2%, respectively, which means the performance of the YOLOv8s is higher than the YOLOv5s6 when using hybrid dataset. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Key Factors for Unsubscribing from YouTube Channels: A Study of YouTubers in Taiwan 1

引用

13th international Conference on Frontier Computing, FC 2023

作者： Yang, Hsuan-Che Chang, Wen-Chih Department of Information Management Chihlee University of Technology New Taipei City220 Taiwan International Master Program of Information Technology and Applications National Pingtung University Pingtung City Taiwan

ISBN: (数字)9789819993420

ISBN: (纸本)9789819993413

YouTube has become a major advertisement media for industries. People watch TV shows, movie trailers, news and episodes, on-line shows streaming as well. When people want to purchase something, they can find some unboxing reviews, experiences shares, using instructions and services introductions on YouTube before making orders. Traveling guides and educational tutorials are also can be found on YouTube. Thousands of YouTube channels need channel’s subscribers directly or indirectly affect the revenue of channel owners. In addition to YouTube’s own profit from watching, the subscribers are also an important reference when manufacturers want to choose key opinion leaders (KOL) or internet celebrities to promote their products or services. Since, maintaining a stable growth of channel subscribers and reducing the occurrence of unsubscribing are the key issue that every YouTuber needs to understand urgently. In this study, we used a survey to understand subscribers and YouTubers on unsubscribing, and analyzed some key factors for unsubscribing. The data analyses include descriptive analysis, factor analysis, reliability analysis, t-test, one-way ANOVA, and Pearson’s correlation analysis. Through this study, people can understand key factors for unsubscribing reasons on YouTube platform and the priority of these factors. Whether there is special unsubscribe factors for different channel types and attributes. The key contribution of this study is: a questionnaire on key factors for unsubscribing on the YouTube platform was designed, and it could be utilized for further use in related studies in the future. We also summarize the responses and suggestions of we-media channel owners on the factors for unsubscribing. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

AI Prescription Recognition System 9

AI Prescription Recognition System

引用

9th international Conference on Orange technology, ICOT 2021

作者： Ou, Yang-Yen Wang, Hung-Min Lee, Tsung-Yen Tsai, An-Chao Wang, Jhing-Fa National Cheng Kung University Department of Electrical Engineering Tainan Taiwan National Pingtung University International Master Program in Information Technology and Applications Pingtung Taiwan

ISBN: (纸本)9781665478427

In order to improve the work efficiency of pharmacists, this work proposes a prescription recognition system. The prescription recognition system mainly consists of three parts, namely pre-processing, information extraction and post-processing. The pre-processing includes contrast enhancement of the input image, optical character recognition, and the merging and sorting of the characters after optical character recognition. In the information extraction part, we hybrid two different strategies, the rule-based method, and the deep learning-based method. Finally, post-processing corrects some common optical character recognition errors and performs format conversion on specific fields. On the user interface, we build a web application server with Django, which provides pharmacists to upload, edit, and manage prescriptions. In the deep-learning-based information extraction, the average F1-score reached 93.8%. In the experiment of the overall recognition system, we test 202 different prescriptions, and compare the three different information extraction strategies, which are rules-based method, deep-learning-based method, and hybrid method respectively. The hybrid method is improved in most fields, and the accuracy of all the fields in our system is greater than 93%. Finally, the system gets 4.38 point on the average opinion score. © 2021 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

EESRGAN: Efficient & Effective Super-Resolution Generative Adversarial Network

引用

IETE Technical Review (Institution of Electronics and Telecommunication Engineers, India) 2024年第2期41卷 200-211页

作者： Tsai, An-Chao Tsou, Cheng-Han Wang, Jhing-Fa International Master Program of Information Technology and Application National Pingtung University Pingtung900 Taiwan Department of Electrical Engineering National Cheng Kung University Tainan Taiwan

In Taiwan, traditional production equipment for the mainframe panels is imported from overseas, and the parameters are adjusted through the operation panel for automated manufacturing. However, these parameters are slightly different from those used in Taiwan, requiring manual recording of warning parameters to ensure quality control. Currently, the only way to capture the operation records of these machines is by manually recording the system panel information, which is a time-consuming and laborious process that is expensive for production line personnel. In this work, we use image recognition to capture and analyze data externally without damaging the machine. This research improves the ESRGAN network to restore the image details and textures of the mainframe panels. It also captures relevant data with Google OCR to convert panel images into parameter values. The captured results are combined with data analysis to provide more accurate standard mainframe panel information. Even under different interference source conditions, data extraction and analysis can still be carried out to output the text files, effectively assisting the production line in recording the machine panel parameters and reducing personnel’s workload. © 2024 IETE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Real Time Classification System of Black Soldier Fly Larva

Real Time Classification System of Black Soldier Fly Larva

引用

IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS)

作者： Chayanon Pookunngern An-Chao Tsai International Master Program in Information Technology and Applications National Pingtung University Taiwan

ISBN: (数字)9798350361704

ISBN: (纸本)9798350361711

Food waste presents a significant issue, contributing extensively to greenhouse gas emissions and climate change. When food waste decomposes in landfills, it generates methane, a greenhouse gas that is significantly derogation effective to the atmosphere than carbon dioxide. Additionally, the production, transportation, and disposal of food waste significantly contribute to global greenhouse gas emissions. This study explores an innovative approach to mitigate the environmental impact of food waste by using food scraps to create compost for animal feed, specifically utilizing the Black Soldier Fly Larva (BSFL). Accurate control of food quantity for various larval stages is essential, necessitating precise stage classification. This process is complex due to the larvae's similar and small color variations. In this paper, we introduce a mobile application designed to classify and detect the growth stages of BSFL, ranging from stage 1 to stage 4, which are high in protein and beneficial for animal feed, to stages 5 and 6, which are ideal for preparing pupae that can be used in skincare products. Our approach employs the YOLOv8 model for larval stage classification and detection, achieving an impressive mAP50-95 of 0.812, surpassing the performance of YOLOv7 (mAP50-95 of 0.781) and YOLOv5 (mAP50-95 of 0.789).

关键词： Food waste YOLO Waste management Wireless communication Accuracy Animals Transportation

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：