检索结果-内蒙古大学图书馆

15th International Conference on Information and Communication Technology Convergence, ICTC 2024

作者： Shim, Hyoungsub Kang, Bongho Im, Haejung Jeon, Duhyun Kim, Seok-Min Chung-Ang University Seoul Department of Mechanical Engineering Seoul Korea Republic of Research and Development Center ICTK.LTD. Seoul Korea Republic of Chung-Ang University Department of Computer Scicne and Engineering Department of Mechanical Engineering Seoul Korea Republic of

ISBN: (纸本)9798350364637

This paper introduces qTrustNet VPN, a next-generation Virtual Private Network (VPN) designed to enhance security in the quantum era. With the rapid advancement of quantum computing, traditional encryption methods face obsolescence, necessitating more robust security solutions. qTrustNet VPN addresses this need by integrating the WireGuard protocol, known for its simplicity and high performance, with Post-Quantum Cryptography (PQC) algorithms developed by the National Institute of Standards and Technology (NIST). These PQC algorithms are designed to withstand the decryption capabilities of quantum computers, providing long-term security. © 2024 IEEE.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Mobile Memory Management System Based on User’s Application Usage Patterns

引用

computers, Materials & Continua 2021年第9期68卷 4031-4050页

作者： Jaehwan Lee Sangoh Park School of Computer Science and Engineering Chung-Ang UniversityDongjak-guSeoul06974Korea

Currently,the number of functions to improve user convenience in smartphone applications is *** addition,more mobile applications are being loaded into mobile operating system memory for faster launches,thus increasing the memory requirements for *** memory used by applications in mobile operating systems is managed using software;allocated memory is freed up by either considering the usage state of the application or terminating the least recently used(LRU)*** LRU-based memory management schemes do not consider the application launch frequency in a low memory situation,currently used mobile operating systems can lead to the termination of a frequently executed application,thereby increasing its relaunch *** study proposes a memory management system that can efficiently utilize the main memory space by analyzing the application usage *** proposed system reduces the application launch time by leaving the most frequently used or likely to be run applications in the main memory for as long as *** performance evaluation conducted utilizing actual smartphone usage records showed that the proposed memory management system increases the number of times the applications resume from the main memory compared with the conventional memory management system,and that the average application execution time is reduced by approximately 17%.

关键词： Mobile environment memory management machine learning neural nets user-centered design

来源：评论

学校读者我要写书评

暂无评论

Trustworthy and Explainable AI for Learning Analytics

Trustworthy and Explainable AI for Learning Analytics

引用

2024 Joint of International Conference on Learning Analytics and Knowledge Workshops, LAK-WS 2024

作者： Li, Min-Jia Li, Shun-Ting Yang, Albert C.M. Huang, Anna Y.Q. Yang, Stephen J.H. Department of Computer Science and Information Engineering National Central University Taiwan Department of Computer Science and Engineering National Chung Hsing University Taiwan

In recent years, there has been a surge of interest in combining artificial intelligence (AI) with education to enhance learning experiences. However, one major concern is the lack of transparency in AI models, which hinders our ability to understand their decision-making processes and establish trust in their outcomes. This study aims to address these challenges by focusing on the implications of explainable and trustworthy AI in education. The primary objective of this research is to improve trust and acceptance of AI systems in education by providing comprehensive explanations for model predictions. By doing so, it seeks to equip stakeholders with a better understanding of the decision-making process and increase their confidence in the outcomes. Additionally, the study highlights the importance of evaluation metrics in assessing the quality and effectiveness of explanations generated by explanation AI models. These metrics serve as vital tools for ensuring reliable system performance and upholding the fundamental principles necessary for building trustworthy AI. To accomplish these goals, the study utilizes the LBLS-467 dataset to predict high-risk students, employing both logistic regression and neural networks as AI models. Subsequently, explanation artificial intelligence techniques such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (Shapley Additive Explanations) are utilized to evaluate students' learning outcomes and provide explanations. Finally, six evaluation indicators are adopted to assess the accuracy and stability of these explanations. In conclusion, this study addresses the challenges associated with inconsistencies in explainable AI models within the field of education. It emphasizes the need for explainability and trust when applying AI systems in educational contexts. By providing comprehensive explanations and evaluation metrics, this research empowers education teams to make informed decisions and fosters a positive envir

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Disparity Computation With Low Intensity Quantization on Stereo Image Pairs

IEEE Transactions on Computational Imaging

引用

IEEE Transactions on Computational Imaging 2024年 10卷 318-328页

作者： Lin, Huei-Yung Hsu, Tsai-Yu National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan National Chung Cheng University Department of Electrical Engineering Minhsiung621301 Taiwan

From variate bit-rate stereo matching, it is observed that the image pair with a low intensity quantization level is still capable of providing good disparity maps. In this article, a mathematical model representing the level of disparity discontinuity is proposed to formulate the mismatching prediction based on the intensity quantization. It is used to derive the minimum quantization level for quality-assured stereo matching. Due to the high computational cost of stereo processing, the reduction of image data usage will benefit both network training and real-time inference. The formulation presented in this work is investigated extensively for various types of scenes for disparity computation. In the experiments, the feasibility of our approach is validated with Middlebury, KITTI 2015, and synthetic Scene Flow datasets. © 2015 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Abnormal Activity Detection and Classification of Bus Passengers with In-Vehicle Image Sensing

引用

IEEE Access 2024年 12卷 23057-23065页

作者： Lin, Huei-Yung Tseng, Chun-Han National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106 Taiwan National Chung Cheng University Department of Electrical Engineering Chiayi621 Taiwan

As the self-driving technology is getting mature for public transportation applications, the safety concern of onboard passengers has become an important issue. It is essential to identify inappropriate or hazardous behaviors of passengers for the vehicles without human operators. In this work, we propose a technique to detect and classify the abnormal activities of passengers in a bus environment. Different from the existing human activity classification algorithms, our approach reduces the occlusion and increases the recognition rate by acquiring images from an overhead vision system. To overcome the increased complexity on feature extraction and classification, an action recognition network for top-view images are proposed by incorporating both spatial and temporal information. An image dataset, BUS-HAR, is generated for practical application scenarios with bus passengers. Experiments using real-world scene images have demonstrated the feasibility of our technique compared to existing approaches. The codes and image dataset are made available publicly at https://***/richardkuo1999/passenger-action-recognition. © 2013 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Arbitrary style transfer system with split-and-transform scheme

引用

Multimedia Tools and Applications 2024年第23期83卷 62497-62517页

作者： Tu, Ching-Ting Lin, Hwei Jen Tsai, Yihjia Lin, Zi-Jun Department of Applied Mathematics National Chung Hsing University Taichung Taiwan Department of Computer Science and Information Engineering Tamkang University New Taipei Taiwan

For the subject of arbitrary image style transfer, there have been some proposed architectures that directly compute the transformation matrix of the whitening and coloring transformation (WCT) to obtain more satisfactory transformation results. However, calculating the transformation matrix of WCT is time-consuming. Li et al. trained a linear transformation module to generate a WCT transformation matrix for any pair of images, i.e., content image and style image, to avoid complex calculations and improves time efficiency. In this work, we introduce a flexible arbitrary image style transfer framework based on the LST, which uses deep neural networks to train a linear transformation matrix as the standard matrix for WCT. For the first part, inverse relationship between the Whitening matrix and the Coloring matrix w.r.t. the same image is enforced during the training of the linear transformation matrix, so that the resulting matrix will be more accurate and closer to the standard matrix of WCT. For the second part, a split-and-transform scheme is proposed. Unlike LST, which transforms the block of feature maps as a whole, the split-and-transform scheme divides the feature block into several smaller blocks and transforms them individually, so that the transformation is more localized, and the more the number of divided blocks, the more localized. In addition, the proposed split-and-transform scheme allows users to determine the number of divided blocks to flexibly control the locality of the transformations. Experimental results demonstrate the effectiveness and flexibility of the proposed framework by the high-quality stylized images and adjustable balance between globality and locality of transformations. The use of the split-and-transform scheme can reduce the computational time while preserving or even improving the stylization results. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Face frontalization GAN with self-supervised learning for pose-invariant facial recognition 11

Face frontalization GAN with self-supervised learning for po...

引用

11th International Conference on Soft Computing and Machine Intelligence, ISCMI 2024

作者： Alhlffee, Mahmood H.B. Chung Hua University College of Computer Science and Electrical Engineering Hsinchu Taiwan

ISBN: (纸本)9798331518127

Despite impressive milestones achieved by generative models such as Generative Adversarial Network (GAN) in synthesizing faces, maintaining face identity remains a major challenge for most face recognition system. In this paper, we propose a Self-supervised Face Frontalization GAN (SF-GAN), which produces a frontal face image from a profile image. We designed a profile method to preserve identity information and fine details in high-resolution that focus on pose feature space, which helps SF-GAN reconstruct high-frequency face texture details. SF-GAN switches key facial regions between the input image and its reconstructed version to produce more realistic images. Furthermore, we introduce an orthogonal constraint to our generator that penalizes redundant latent representations, resulting in a more diverse pose appearance details. While the discriminator is designed with a mechanism of facial awareness for each facial region to improve overall model performance. FaceNet and MTCNN are then used to extract correlated face features in order to determine the accuracy of face recognition. Our evaluations are based on the Multi-PIE and CAS-PEAL datasets. Results showed that SF-GAN achieved a better face quality visualization and rank-1 face identification. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Continual Learning for Multiple Modalities

arXiv

引用

arXiv 2025年

作者： Jin, Hyundong Kim, Eunwoo School of Computer Science and Engineering Chung-Ang University Korea Republic of

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were proposed under the assumption of learning a single modality (e.g., image) over time, which limits their applicability in scenarios involving multiple modalities. In this work, we propose a novel continual learning framework that accommodates multiple modalities (image, video, audio, depth, and text). We train a model to align various modalities with text, leveraging its rich semantic information. However, this increases the risk of forgetting previously learned knowledge, exacerbated by the differing input traits of each task. To alleviate the overwriting of the previous knowledge of modalities, we propose a method for aggregating knowledge within and across modalities. The aggregated knowledge is obtained by assimilating new information through self-regularization within each modality and associating knowledge between modalities by prioritizing contributions from relevant modalities. Furthermore, we propose a strategy that re-aligns the embeddings of modalities to resolve biased alignment between modalities. We evaluate the proposed method in a wide range of continual learning scenarios using multiple datasets with different modalities. Extensive experiments demonstrate that ours outperforms existing methods in the scenarios, regardless of whether the identity of the modality is given. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Personalized construction safety training system using conversational AI in virtual reality

引用

Automation in Construction 2025年 175卷

作者： Sabir, Aqsa Hussain, Rahat Pedro, Akeem Park, Chansik School of Computer Science and Engineering Chung-Ang University Seoul06974 Korea Republic of School of Architecture and Building Science Chung-Ang University Seoul06974 Korea Republic of

Training workers in safety protocols is crucial for mitigating job site hazards, yet traditional methods often fall short. This paper explores integrating virtual reality (VR) and large language models (LLMs) into iSafeTrainer, an AI-powered safety training system. The system allows trainees to engage with trade-specific content tailored to their expertise level in a third-person perspective in a non-immersive desktop virtual environment, eliminating the need for head-mounted displays. An experimental study evaluated the system through qualitative, survey-based assessments, focusing on user satisfaction, experience, engagement, guidance, and confidence. Results showed high satisfaction rates (>85 %) among novice users, with improved safety knowledge. Expert users suggested advanced scenarios, highlighting the system's potential for expansion. The modular architecture supports customization across various construction settings, ensuring adaptability for future improvements. © 2024

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Enhancing Personalized Learning with MBTI Forecasts and ChatGPT's Tailored Study Advice

Enhancing Personalized Learning with MBTI Forecasts and Chat...

引用

2024 Joint of International Conference on Learning Analytics and Knowledge Workshops, LAK-WS 2024

作者： Hsieh, Yi-Chun Yang, Albert C.M. Department of Computer Science and Information Engineering National Chung Hsing University Taiwan

Assessing students' learning behaviors has always been a focal point in the field of education. However, traditional assessment methods based solely on grades and learning behaviors often lack personalization, failing to truly understand the root of students' issues. Therefore, this study aims to address this problem by focusing on understanding students' Myers-Briggs Type Indicator (MBTI) personality types. It aims to provide personalized recommendations based on students' learning conditions and personality traits. Ultimately, it intends to suggest suitable study companions for students, enhancing both their learning motivation and efficiency. To achieve this goal, this study utilizes the LBLS467 Database to cluster students, conducts MBTI personality assessments using ChatGPT, offers study recommendations, and ultimately compares similarities to suggest suitable peers for group learning. This approach aims to aid students in their learning within the educational environment. © 2024 CEUR-WS. All rights reserved.

关键词： Students

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：