检索结果-内蒙古大学图书馆

14th International Conference on Frontier Computing, FC 2024

作者： Chang, Ya-Fen Chang, Wen-Ting Tai, Wei-Liang Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung Taiwan

ISBN: (纸本)9789819623945

Vehicle-to-grid (V2G) technology supporting bidirectional power transfer allows electric vehicles (EVs) to contribute and consume energy bidirectionally. Because the specific properties and requirements of V2G, Khan et al. proposed a key agreement scheme for the V2G system to ensure the security of communication between a vehicle user and the grid server. However, after analyzing Khan et al.’s scheme, we find that it suffers from some flaws such that it cannot ensure anonymity, resist impersonation attack, man-in-the-middle attack and denial-of-service attack, and work as expected. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Meteorological Prediction Using Cloud's Images 12

Meteorological Prediction Using Cloud's Images

引用

12th International Electrical engineering Congress, iEECON 2024

作者： Ongkittikul, Surachai Jundang, Nattapong Panyokaew, Thanayut Department Of Computer Engineering Mahanakorn Institute Of Innovation Faculty Of Engineering And Technology Mahanakorn University Of Technology Bangkok Thailand Mahanakorn University Of Technology Engineering Program In Computer Engineering And Artificial Intelligence Faculty Of Engineering And Technology Bangkok Thailand

ISBN: (纸本)9798350383591

This paper uses YOLO deep learning to create a predict system for Meteorological Service for Air Navigation with a total of 5 types of forecast results: BKN, CAVOK, FEW, OVER and SCT. Indicative information for evaluating the image is observing the nature of the clouds arranged together and comparing them to quantities in the sky using the unit of measurement 'okta', which is divided into 8 parts of the image. Therefore, the nature of using deep learning in the article is to teach deep learning to recognize various image characteristics both during the day and at night in order to use the results of the forecast to inform the weather conditions in the sky. The process in this article consists of 3 steps: The first step is to train the data with images with different characteristics from the 5 data types. The next step is to test the accuracy of the weights generated from the training and training steps. The final step is to use water values to create a decision-making system for users. From the experiment, private dataset in this paper, more than 2500 images were used to participate in the experiment. The results of the experiment found that the average results of precision, recall, mAP50, and mAP50-95 could be measured at 84.7%, 92.1%, 95.7%, and 95.3%, respectively. © 2024 IEEE.

关键词： Air navigation

来源：评论

学校读者我要写书评

暂无评论

Reconfigurable Hardware Accelerator of Morphological Image Processor 3

Reconfigurable Hardware Accelerator of Morphological Image P...

引用

3rd IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2023

作者： Lin, Ming-Yi Hsieh, Sheng-Hsien Chen, Ching-Han Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan Bachelor's Program in Artificial Intelligence and Mechatronics National Pingtung University of Science and Technology Pingtung Taiwan

ISBN: (纸本)9798350333862

Researchers emphasize the importance of hardware accelerators for mathematical morphology. If there are any issues, the hardware architecture may need to be redesigned. Thus, we propose a novel, reconfigurable hardware architecture with pipeline techniques for acceleration. With the order control register, there is no need to modify the architecture even if different results are expected. Furthermore, the hardware architecture caters to specific purposes instead of requiring a purpose-built hardware design. © 2023 IEEE.

关键词： Reconfigurable hardware

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

Vision-Based Drug Classification System Using Transfer Learning Approach 9

Vision-Based Drug Classification System Using Transfer Learn...

引用

9th International Conference on Business and Industrial Research, ICBIR 2024

作者： Laohakijvitoon, Patpon Nilwong, Sivapong Thai-Nichi Institute of Technology Master of Engineering Program in Engineering Technology Bangkok Thailand Thai-Nichi Institute of Technology Department of Computer Engineering and Artificial Intelligence Bangkok Thailand

ISBN: (纸本)9798350383010

Dispensing generic drugs instead of original drugs from pharmacies may cause adverse drug events to patients. It is difficult to separate between generic drugs and originals due to their similarities, except for imprints on the tablets. In this paper, a vision-based medicine tablets classification system using Convolutional Neural Networks (CNN) with a transfer learning approach is proposed. The proposed classification system aims to helps its user distinguish between the original drugs and generic drugs based on imprints on the medicine tablets. Multiple CNN models are created and tested as the classifier for the drug classification system. Three well-known CNN models are chosen as base models for creating CNNs with the transfer learning, including VGG16, Inception-V3, and ResNet50-V2. The developed CNN models are tested with images of medicine tablet taken from smartphones. Results from the experiments are evaluated through accuracies, precisions, recalls, and F-1 scores. Experimental results show satisfying performances of the proposed system in classifying original drugs and generic drugs using visual information. © 2024 IEEE.

关键词： convolutional neural network deep learning image classification Medicine tablet transfer learning

来源：评论

学校读者我要写书评

暂无评论

Unlocking the potential of RNN and CNN models for accurate rehabilitation exercise classification on multi-datasets

引用

Multimedia Tools and Applications 2025年第3期84卷 1261-1301页

作者： Zaher, Moamen Ghoneim, Amr S. Abdelhamid, Laila Atia, Ayman Software Engineering Program Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Computer Science Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Information System Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Cairo Ain Helwan11795 Egypt Giza October12451 Egypt

Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesses and improving overall health. However, a notable global challenge stems from the shortage of professional physiotherapists, particularly acute in some developing countries, where the ratio can be as low as one physiotherapist per 100,000 individuals. To address these challenges and elevate patient care, the field of physical rehabilitation is progressively integrating computer Vision and Human Activity Recognition (HAR) techniques. Numerous research efforts aim to explore methodologies that assist in rehabilitation exercises and evaluate patient movements, which is crucial as incorrect exercises can potentially worsen conditions. This study investigates applying various deep-learning models for classifying exercises using the benchmark KIMORE and UI-PRMD datasets. Employing Bi-LSTM, LSTM, CNN, and CNN-LSTM, alongside a Random Search for architectural design and Hyper-parameter tuning, our investigation reveals the (CNN) model as the top performer. After applying cross-validation, the technique achieves remarkable mean testing accuracy rates of 93.08% on the KIMORE dataset and 99.7% on the UI-PRMD dataset. This marks a slight improvement of 0.75% and 0.1%, respectively, compared to previous techniques. In addition, expanding beyond exercise classification, this study explores the KIMORE dataset’s utility for disease identification, where the (CNN) model consistently demonstrates an outstanding accuracy of 89.87%, indicating its promising role in both exercises and disease identification within the context of physical rehabilitation. © The Author(s) 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Compact Model Build Upon Dynamic Weighting artificial Neural Network Approach for Complementary Field Effect Transistors

引用

IEEE Transactions on Electron Devices 2024年第1期71卷 246-253页

作者： Butola, Rajat Li, Yiming Kola, Sekhar Reddy National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation The Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program The Institute of Communications Engineering the Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

In this work, a dynamic weighting-artificial neural network (DW-ANN) methodology is presented for quick and automated compact model (CM) generation. It takes advantage of both TCAD simulations for high accuracy and SPICE simulations for cost-effectiveness. This methodology is developed for gate-all-around (GAA) silicon (Si) nanosheet (NS) complementary field effect transistor (CFET), a potential candidate for future CMOS technology due to its innate properties. The critical process variation (PV) sources that severely degrade the CFET performance are estimated using DW-ANN. It reduces the computation cost and predicts the effects of PV sources with less than 1% error. Furthermore, a compact DW-ANN-based Verilog-A model has been developed that captures the dc as well as transient behavior accurately for circuit-level analysis. CFET-based circuits such as inverter, 6T-static random access memory (SRAM), and ring oscillator (RO) are characterized and implemented using DW-ANN-based CM. The overall average error of the model is reported as less than 2%. Therefore, the proposed device and circuit modeling approach provides a feasible solution for the rapid compact modeling of new emerging devices with good convergence and high accuracy. © 1963-2012 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

3D Geometric Shape Assembly via Efficient Point Cloud Matching 41

3D Geometric Shape Assembly via Efficient Point Cloud Matchi...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Lee, Nahyuk Min, Juhong Lee, Junha Kim, Seungwook Lee, Kanghee Park, Jaesik Cho, Minsu Department of Computer Science and Engineering POSTECH Pohang Korea Republic of Graduate School of Artificial Intelligence POSTECH Pohang Korea Republic of Department of Computer Science and Engineering Seoul National University Seoul Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Learning to assemble geometric shapes into a larger target structure is a pivotal task in various practical applications. In this work, we tackle this problem by establishing local correspondences between point clouds of part shapes in both coarse- and fine-levels. To this end, we introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts while incurring low costs in memory and compute. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad and demonstrate its superior performance and efficiency compared to state-of-the-art methods. Project page: https://***/pmtr. Copyright 2024 by the author(s)

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

An Improved of Enhancements of a User Authentication Scheme

引用

International Journal of Network Security 2023年第3期25卷 508-514页

作者： Hwang, Min-Shiang Li, Hou-Wen Yang, Cheng-Ying Department of Computer Science Information Engineering Asia University Taiwan The Ph.D. Program in Artificial Intelligence Asia University Taiwan Department of Computer Science University of Taipei Taiwan

With the rapid development of the Internet, telemedicine information systems (TLS) appear more and more around us. Nevertheless, the security of patient’s medical infor-mation remains one of the most critical factors for the widespread adoption of TLS. Recently, Liu et al. pro-posed an improved three-factor authentication scheme. Through the BAN logic verification, their scheme is se-cure. However, the user needs to remember the long random number, which is impractical. In addition, their scheme could not withstand the fake smart card attack and a difficult-to-remember random number. In this ar-ticle, we will improve their scheme for practicality and security. © (2023), All Rights Reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Adversarial Environment Design via Regret-Guided Diffusion Models 38

Adversarial Environment Design via Regret-Guided Diffusion M...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chung, Hojun Lee, Junseo Kim, Minsoo Kim, Dohyeong Oh, Songhwai Interdisciplinary Program in Artificial Intelligence ASRI Seoul National University Korea Republic of Department of Electrical and Computer Engineering ASRI Seoul National University Korea Republic of

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments. Project page: https://***/projects/ADD. © 2024 Neural information processing systems foundation. All rights reserved.

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：