检索结果-内蒙古大学图书馆

Efficient fault-tolerant quantum dialogue protocols based on dictionary encoding without decoy photons

Quantum Information Processing 2024年第1期23卷 1-22页

作者： Chang, Chen-Yu Lin, Jason Department of Computer Science and Engineering National Chung Hsing University No. 145 Xingda Rd. South District Taichung40227 Taiwan

This paper proposes two efficient block transmission and two efficient two-step transmission quantum dialogue (QD) protocols that are robust against collective-dephasing and collective-rotation noises, respectively. To counter collective noise, the carriers used to carry the message must correspond to the decoherence-free states under this collective noise. In addition to carrying messages, these quantum states and their combinations are used to ensure the security of transmission and prevent message distortion. In quantum communications, decoy photons are often used to detect eavesdroppers and always account for half of the total number of qubits, which is a burden on scarce quantum resources. Due to quantum state disclosure, the decoy photons used for inspection can no longer be utilized for transmission. Therefore, a dictionary is employed as an encoding mechanism to achieve self-checking without revealing these states. This approach enables photons to detect eavesdroppers while concurrently carrying keys. The proposed QD protocols can eliminate the consumption of decoy photons, significantly improve the qubit efficiency, and conduct security analysis to ensure that there is no information leakage. Two transmission modes with the same efficiency can be selected according to the noisy environment and time windows. © 2024, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

Ensemble-Based Brain Tissue Segmentation in CT Scans 24

Ensemble-Based Brain Tissue Segmentation in CT Scans

引用

11th International Conference on Biomedical and Bioinformatics engineering, ICBBE 2024

作者： Chiang, Wei-Chuan Mou, Tsung-Li Lai, Tsai-Hsing Shen, chung-Yi Liu, Wei-Min National Chung Cheng University Chiayi Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan

ISBN: (纸本)9798400718274

Computed Tomography is an important tool for diagnosing brain-related trauma or acute events, and brain tissue segmentation is a critical step in this task. In this study, we attempt to explore the performance of CT brain tissue segmentation using extended structures based on bagging and stacking in ensemble learning. We compared some base-learner models (UNet, UNet-2022, Swin-UNETR, and DeepLabv3+) in different combinations using union or intersection model fusion strategies within the ensemble structures. The experimental results showed that our bagging-based ensemble structure with the combination of UNet-2022 and Swin-UNETR using the intersection-based fusion strategy performed the best across multiple metrics. This approach achieves a Dice Similarity Coefficient score of 0.988. This study demonstrates that using intersection or union-based fusion strategies in ensemble learning improves the accuracy and stability of brain tissue segmentation in CT. It shows the potential for future development as an effective tool to assist physicians in diagnosis. Copyright © 2024 held by the owner/author(s).

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A novel data hiding scheme based on multidimensional reference tensors

引用

Multimedia Tools and Applications 2024年第9期83卷 25695-25712页

作者： Lin, Jason Liu, Kuan-Hung Lin, Cih-Lian Department of Computer Science and Engineering National Chung Hsing University No. 145 Xingda Rd. South District Taichung40227 Taiwan

The protection of transmitted messages from being eavesdropped on the internet by a third party has always been an important research topic. The image steganography, which utilizes natural images to hide secret messages, is a widely used approach. The security of image steganography depends primarily on the undetectability of the transmitted stego-images. However, very few methods can handle customized adjustments to both the security level and embedding capacity simultaneously. Therefore, this study proposes a novel data hiding scheme utilizing a multidimensional reference tensor (MRT) with N dimensions and a side length of M to achieve these adjustments. The proposed method can freely adjust the embedding capacity from 1 bit per pixel (bpp) to 8 bpp, reduce the overall memory usage by up to nearly 99% based on a scalable index encoding (SIE) technique, and customize the level of security by simply altering the number of dimensions or the side length while maintaining a balance between the embedding capacity and visual imperceptibility. Based on experimental results, we demonstrated that the method could achieve a peak signal-to-noise ratio (PSNR) of 46.38 dB with an embedding capacity of 2 bpp, which is equivalent to the performance of state-of-the-art methods. Furthermore, compared with existing steganographic methods, the embedded message through the MRT is less susceptible to hacking owing to the factorial number of solutions for the MRT, which in this case is M to the power of N. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Provable Data Possession with Outsourced Tag Generation for AI-Driven E-Commerce

引用

computers, Materials & Continua 2025年第5期83卷 2719-2734页

作者： Yi Li Wenying Zheng Yu-Sheng Su Meiqin Tang School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science and Technology(School of Artificial Intelligence) Zhejiang Sci-Tech UniversityHangzhou310018China Department of Computer Science and Information Engineering National Chung Cheng UniversityChiayi621301TaiwanChina Advanced Institute of Manufacturing with High-tech Innovations National Chung Cheng UniversityChiayi621301TaiwanChina Department of Computer Science and Engineering Taiwan Ocean UniversityKeelung202301TaiwanChina School of Integrated Circuits Wuxi Vocational College of Science and TechnologyWuxi214028China

AI applications have become ubiquitous,bringing significant convenience to various *** e-commerce,AI can enhance product recommendations for individuals and provide businesses with more accurate predictions for market strategy ***,if the data used for AI applications is damaged or lost,it will inevitably affect the effectiveness of these AI ***,it is essential to verify the integrity of e-commerce *** existing Provable Data Possession(PDP)protocols can verify the integrity of cloud data,they are not suitable for e-commerce scenarios due to the limited computational capabilities of edge servers,which cannot handle the high computational overhead of generating homomorphic verification tags in *** address this issue,we propose PDP with Outsourced Tag Generation for AI-driven e-commerce,which outsources the computation of homomorphic verification tags to cloud servers while introducing a lightweight verification method to ensure that the tags match the uploaded ***,the proposed scheme supports dynamic operations such as adding,deleting,and modifying data,enhancing its ***,experiments show that the additional computational overhead introduced by outsourcing homomorphic verification tags is acceptable compared to the original PDP.

关键词： Provable data possession data auditing cloud computing e-commerce bloom filter

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Firefly with Dynamic Multi-swarm Particle Swarm Optimization for WSN Deployment

引用

Journal of Internet Technology 2023年第4期24卷 825-836页

作者： Chang, Wei-Yan Soma, Prathibha Chen, Huan Chang, Hsuan Tsai, Chun-Wei Department of Computer Science and Engineering National Chung Hsing University Taiwan Department of Information Technology Sri Sai Ram Engineering College India Department of Computer Science and Engineering National Sun Yat-Sen University Taiwan

Enhancing the coverage area of the sensing range with the limiting resource is a critical problem in the wireless sensor network (WSN). Mobile sensors are patched coverage holes and they also have limited energy to move in large distances. Several recent studies indicated the metaheuristic algorithms can find an acceptable deployed solution in a reasonable time, especially the PSO-based algorithm. However, the speeds of convergence of most PSO-based algorithms are too fast which will lead to the premature problem to degrade the quality of deployed performance in WSN. A hybrid metaheuristic combined with dynamic multi-swarm particle swarm optimization and firefly algorithm will be presented in this paper to find an acceptable deployed solution with the maximum coverage rate and minimum energy consumption via static and mobile sensors. Moreover, a novel switch search mechanism between sub-swarms will also be presented for the proposed algorithm to avoid fall into local optimal in early convergence process. The simulation results show that the proposed method can obtain better solutions than other PSO-based deployment algorithms compared in this paper in terms of coverage rate and energy consumption. © 2023 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Double DQN for Chip-Level Synthesis of Paper-Based Digital Microfluidic Biochips

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2024年第8期43卷 2465-2478页

作者： Li, Katherine Shu-Min Wu, Fang-Chi Li, Jian-De Wang, Sying-Jyan National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan National Chung Hsing University Department of Computer Science and Engineering Taichung402 Taiwan Realtek Semiconductor Corporation Corporate Technology Center Hsinchu300 Taiwan

Digital microfluidic biochips (DMFBs) can effectively reduce the cost of biochemical analysis and improve experimental efficiency, as they are easy to carry, use fewer reagent samples and have high precision. Paper-based DMFBs (PB-DMFBs) are a branch of microfluidic biochips. This technology prints ink containing carbon nanotubes on special paper to form electrodes and control wire, so the manufacturing cost and time required are far less than the traditional digital microfluidic chip, in which droplets move between two control layers. However, the chip-level synthesis of PB-DMFBs becomes more challenging because all circuits of PB-DMFBs are printed on a single paper layer. Furthermore, current PB-DMFB designs must address various issues, including fabrication cost, reliability, and safety. Therefore, a more flexible method for the chip-level synthesis of PB-DMFBs is needed. In this article, we propose a chip-level synthesis method of PB-DMFBs based on reinforcement learning. Double deep Q -learning networks (Double DQN) are suitable for agents to select actions and estimate actions, and then obtain optimized comprehensive results. Experimental results demonstrate that the proposed method is not only effective and efficient for chip-level synthesis but also scalable to applications with high reliability and safety requirements. © 1982-2012 IEEE.

关键词： Electrodes

来源：评论

学校读者我要写书评

暂无评论

Constructing an AI Compiler for ARM Cortex-M Devices

引用

computer Systems science & engineering 2023年第7期46卷 999-1019页

作者： Rong-Guey Chang Tam-Van Hoang Department of Computer Science and Information Engineering National Chung Cheng UniversityChia-YiTaiwan

The diversity of software and hardware forces programmers to spend a great deal of time optimizing their source code,which often requires specific treatment for each *** problem becomes critical on embedded devices,where computational and memory resources are strictly *** play an essential role in deploying source code on a target device through the *** this work,a novel backend for the Open Neural Network Compiler(ONNC)is proposed,which exploits machine learning to optimize code for the ARM Cortex-M *** backend requires minimal changes to Open Neural Network Exchange(ONNX)*** novel optimization techniques are also incorporated in the backend,such as quantizing the ONNX model’s weight and automatically tuning the dimensions of operators in *** performance of the proposed framework is evaluated for two applications:handwritten digit recognition on the Modified National Institute of Standards and Technology(MNIST)dataset and model,and image classification on the Canadian Institute For Advanced Research and 10(CIFAR-10)dataset with the AlexNet-Light *** system achieves 98.90%and 90.55%accuracy for handwritten digit recognition and image classification,***,the proposed architecture is significantly more lightweight than other state-of-theart models in terms of both computation time and generated source code *** the system perspective,this work provides a novel approach to deploying direct computations from the available ONNX models to target devices by optimizing compilers while maintaining high efficiency in accuracy performance.

关键词： Open neural network compiler backend ARM Cortex-M device handwritten digit recognition image classification

来源：评论

学校读者我要写书评

暂无评论

CALANet: cheap all-layer aggregation for human activity recognition 24

CALANet: cheap all-layer aggregation for human activity reco...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jaegyun Park Dae-Won Kim Jaesung Lee School of Computer Science and Engineering Chung-Ang University Republic of Korea Department of Artificial Intelligence Chung-Ang University Republic of Korea

ISBN: (纸本)9798331314385

With the steady growth of sensing technology and wearable devices, sensor-based human activity recognition has become essential in widespread applications, such as healthcare monitoring and fitness tracking, where accurate and real-time systems are required. To achieve real-time response, recent studies have focused on lightweight neural network models. Specifically, they designed the network architectures by restricting the number of layers shallowly or connections of each layer. However, these approaches suffer from limited accuracy because the classifier only uses the features at the last layer. In this study, we propose a cheap all-layer aggregation network, CALANet, for accuracy improvement while maintaining the efficiency of existing real-time HAR models. Specifically, CALANet allows the classifier to aggregate the features for all layers, resulting in a performance gain. In addition, this work proves that the theoretical computation cost of CALANet is equivalent to that of conventional networks. Evaluated on seven publicly available datasets, CALANet outperformed existing methods, achieving state-of-the-art performance. The source codes of the CALANet are publicly available at https://***/jgpark92/CALANet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Imperceptible adversarial attack via spectral sensitivity of human visual system

引用

Multimedia Tools and Applications 2024年第20期83卷 59291-59315页

作者： Chiang, Chen-Kuo Lin, Ying-Dar Hwang, Ren-Hung Lin, Po-Ching Chang, Shih-Ya Li, Hao-Ting National Chung Cheng University Chiayi62130 Taiwan Computer Science National Yang Ming Chiao Tung University Hsinchu300093 Taiwan College of Artificial Intelligence National Yang Ming Chiao Tung University Tainan71150 Taiwan Computer Science and Information Engineering National Chung Cheng University Chiayi62130 Taiwan

Adversarial attacks reveals that deep neural networks are vulnerable to adversarial examples. Intuitively, adversarial examples with more perturbations result in a strong attack, leading to a lower recognition accuracy. However, increasing perturbations also causes visually noticeable changes in the images. In order to address the problem on how to improve the attack strength while maintaining the visual perception quality, an imperceptible adversarial attack via spectral sensitivity of the human visual system is proposed. Based on the analysis of human visual system, the proposed method allows more perturbations as attack information and re-distributes perturbations into pixels where the changes are imperceptible to human eyes. Therefore, it presents better Accuracy under Attack(AuA) than existing attack methods whereas the image quality can be maintained to the similar level as other methods. Experimental results demonstrate that our method improves the attack strength of existing adversarial attack methods by adding 3% to 23% while mostly maintaining the visual quality of SSIM lower than 0.05. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

From 5-Stars to Real Insight: Geospatial Detection of Campaigned Reviews with Google Maps and Mobility Data 28th

From 5-Stars to Real Insight: Geospatial Detection of Campai...

引用

28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023

作者： Hung, Ying-Zhe Wang, Ming-Hung Hsiung, Pao-Ann Department of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan

ISBN: (纸本)9789819717132

In recent years, online review platforms have become increasingly popular, and many consumers rely on these platforms to search for restaurants before dining. However, some restaurants start long-term or short-term campaigns to boost their ratings and attract more customers to dine there. This behavior affects consumer decision-making and seriously undermines the fairness of the consumption market. Most existing research has primarily focused on the direction of reviews. In this study, we take the restaurant's perspective and propose a method to detect whether restaurants host campaigns. We introduce a series of features based on the overall restaurant information. To enhance the performance of our detection, we employ five different models and conduct a comprehensive evaluation. The experimental results from Google review data suggest that our method performs well in identifying restaurant campaigns. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning

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：