检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Chen, Hong Zhang, Yipeng Wu, Simin Wang, Xin Duan, Xuguang Zhou, Yuwei Zhu, Wenwu Department of Computer Science and Technology Tsinghua University China Beijing National Research Center for Information Science and Technology China Lanzhou University China

Subject-driven text-to-image generation aims to generate customized images of the given subject based on the text descriptions, which has drawn increasing attention. Existing methods mainly resort to finetuning a pretrained generative model, where the identity-relevant information (e.g., the boy) and the identity-irrelevant information (e.g., the background or the pose of the boy) are entangled in the latent embedding space. However, the highly entangled latent embedding may lead to the failure of subject-driven text-to-image generation as follows: (i) the identity-irrelevant information hidden in the entangled embedding may dominate the generation process, resulting in the generated images heavily dependent on the irrelevant information while ignoring the given text descriptions;(ii) the identity-relevant information carried in the entangled embedding can not be appropriately preserved, resulting in identity change of the subject in the generated images. To tackle the problems, we propose DisenBooth, an identity-preserving disentangled tuning framework for subject-driven text-to-image generation. Specifically, DisenBooth finetunes the pretrained diffusion model in the denoising process. Different from previous works that utilize an entangled embedding to denoise each image, DisenBooth instead utilizes disentangled embeddings to respectively preserve the subject identity and capture the identity-irrelevant information. We further design the novel weak denoising and contrastive embedding auxiliary tuning objectives to achieve the disentanglement. Extensive experiments show that our proposed DisenBooth framework outperforms baseline models for subject-driven text-to-image generation with the identity-preserved embedding. Additionally, by combining the identity-preserved embedding and identity-irrelevant embedding, DisenBooth demonstrates more generation flexibility and controllability. © 2024 12th International Conference on Learning Representations, ICLR 2024. All ri

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Towards Atomic Scale Quantum Dots in Silicon: An Ultra-Efficient and Robust Subtractor Using Proposed P-Shaped Pattern

引用

IEEE Transactions on Nanotechnology 2024年 23卷 482-489页

作者： Rasmi, Hadi Mosleh, Mohammad Navimipour, Nima Jafari Kheyrandish, Mohammad Dezful Branch Islamic Azad University Department of Computer Engineering Dezful313 Iran Kadir Has University Department of Computer Engineering Faculty of Engineering and Natural Sciences Istanbul34083 Turkey National Yunlin University of Science and Technology Future Technology Research Center Yunlin Douliou64002 Taiwan Western Caspian University Research Center of High Technologies and Innovative Engineering Baku Azerbaijan

Today, Complementary Metal-Oxide-Semiconductor (CMOS) technology faces critical challenges, such as power consumption and current leakage at the nanoscale. Therefore, Atomic Silicon Dangling Bond (ASDB) technology has been proposed as one of the best candidates to replace CMOS technology;due to its high-speed switching and low power consumption. Among the most important issues in ASDB nanotechnology, output stability and robustness against possible faults may be focused. This paper first introduces a novel P-shaped pattern in ASDB, for designing stable and robust primitive logic gates, including AND, NAND, OR, NOR and XOR. Then, two combinational circuits, half-subtractor and full-subtractor, are proposed by the proposed ASDB gates. The simulation results show high output stability as well as adequate robustness, against various defects obtained by the proposed designs;on average, they have improvements of more than 56% and 62%, against DB omission defects and extra cell deposition defects;respectively. Also, the results of the investigations show that the proposed circuits have been improved by 65%, 21% and 2%, in terms of occupied area, energy and occurrence, respectively;compared to the previous works. © 2002-2012 IEEE.

关键词： Silicon

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding in Shared Images Based on Syndrome Decoding and Homomorphism

引用

IEEE Transactions on Cloud Computing 2023年第3期11卷 3085-3098页

作者： Xiong, Lizhi Han, Xiao Yang, Ching-Nung Zhang, Xinpeng Nanjing University of Information Science and Technology School of Computer Science Jiangsu Nanjing210044 China Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education CICAEET Jiangsu Nanjing210044 China National Dong Hwa University Department of Computer Science & Information Engineering Hualien974 Taiwan Fudan University School of Computer Science Shanghai200433 China

Reversible Data Hiding in Encrypted Images (RDHEI) has drawn increasing concern in multimedia cloud computing scenarios. It embeds secret message into the encrypted carrier while preserving the confidentiality of the image. However, most RDHEI schemes have only one hider and one image carrier which are not efficient for the distributed system with multiple participants. Moreover, if the stego-image is lost, the cover image and the embedded data cannot be restored. To solve above issues, this paper proposes Reversible Data Hiding in Shared Images based on syndrome decoding and homomorphism (RDHSI). In RDHSI, the cover image and secret data are distributed using secret sharing. Multiple data hiders embed shared data into the shared images based on the Syndrome Decoding of Hamming codes and the additive homomorphism of the polynomial. On the receiver side, the lossless cover image and secret data are obtained. The reversibility and privacy preserving of the cover image, the complete extraction of secret data, and the fault-tolerance of the proposed schemes are achieved. The experimental results show that PSNR of the marked image is above 54 dB at the embedding rate of 0.43 bpp. In order to improve the payload of secret data, the Modified RDHSI is further proposed. Generally, the proposed schemes are secure, effective and fault-tolerant. © 2013 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Adaptive finite-time command-filtered backstepping sliding mode control for stabilization of a disturbed rotary-inverted-pendulum with experimental validation

引用

JVC/Journal of Vibration and Control 2023年第5-6期29卷 1431-1446页

作者： Mofid, Omid Alattas, Khalid A Mobayen, Saleh Vu, Mai The Bouteraa, Yassine Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia School of Intelligent Mechatronics Engineering Sejong University Seoul Korea Republic of Department of Computer Engineering College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Al-Kharj Saudi Arabia University of Sfax Sfax3038 Tunisia

In this paper, the finite-time stabilization of the disturbed and uncertain rotary-inverted-pendulum system is studied based on the adaptive backstepping sliding mode control procedure. For this purpose, first of all, the dynamical equation of the rotary-inverted-pendulum system is obtained in the state-space form in the existence of external disturbances and model uncertainties with unknown bound. Afterward, a novel command filter is defined to enhance the control strategy by consideration of a virtual control input. Therefore, the differential signal is replaced by the output of the command filter to reduce the complicated computing in the control process. Hence, the finite-time convergence of the sliding surface to the origin is attested by using the backstepping sliding mode control scheme according to the Lyapunov theory. Besides, the unknown upper bound of the exterior perturbation and uncertainty is approximated providing the adaptive control technique. Finally, simulations and experimental results are done to demonstrate the impression and proficiency of the suggested method. © The Author(s) 2022.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Adaptive Indoor People-Counting System Based on Edge AI Computing

引用

IEEE Transactions on Emerging Topics in Computational Intelligence 2024年第1期8卷 255-263页

作者： Yen, Mao-Hsu Lin, Bor-Shyh Kuo, Yu-Lun Lee, I-Jung Lin, Bor-Shing National Taiwan Ocean University Department of Computer Science and Engineering Keelung City202301 Taiwan National Yang Ming Chiao Tung University Institute of Imaging and Biomedical Photonics Tainan71150 Taiwan Chi Mei Medical Center Department of Medical Research Tainan71004 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan National Taipei University College of Electrical Engineering and Computer Science New Taipei City237303 Taiwan

Since the outbreak of COVID-19 in 2019, people counting in confined spaces has become essential for controlling the flow of people and reducing viral spread. Many people-counting systems use a fisheye lens to achieve a wide viewing range. However, the images captured with a fisheye lens can have different sizes and deformations due to different camera heights, which consequently affects the accuracy of people counting. In this study, a Raspberry Pi 4 development board attached to a fisheye lens was used to construct an edge computing platform for people counting by using artificial intelligence. A modified You Only Look Once (YOLO) model, which has three output layers and a spatial pyramid pooling module, is proposed to recognize people in images captured at various heights. For efficiently running this deep learning model on the proposed edge computing platform, a TensorFlow Lite framework was used to reduce the model size. The final experimental results indicated that the mean average error and mean squared error of the modified tiny version of the YOLO v4 model were 0.249 and 0.292, respectively, and the detection speed of the platform was 2 frames per second. The results indicate that the proposed edge computing platform can efficiently and accurately count the number of people. Because the proposed system uses edge computing, it can effectively solve personal privacy and transmission bandwidth problems. © 2017 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Digital Classification within Information Systems 29

Digital Classification within Information Systems

引用

29th Annual Americas Conference on Information Systems: Diving into Uncharted Waters, AMCIS 2023

作者： Gerber, Aurona Department of Computer Science University of the Western Cape CAIR the Center for AI Research South Africa

ISBN: (纸本)9781713893592

Digitization creates digital artefacts that represent physical objects but with augmented and novel characteristics. The ways in which we interact with these digital artefacts necessarily change, including the way we classify them. Classification is the fundamental human activity of grouping, naming, and describing objects to make sense of the world. Classification is therefore fundamental to research as it underpins theory. In this paper we introduce classification and the role of classification as background, followed by an analysis of the way in which classification is adopted within Information Systems (IS). The results of this analysis indicate that IS research adopted the classical classification approaches even though often not explicitly stated. We then analyze digital classification and results indicate that, even though digital classification is classification, existing classification approaches, and by extension, IS classification literature, does not support digital classification sufficiently despite the need due to contemporary and digitized socio-technical developments. Finally, classical classification is contrasted with digital classification requirements of digital classification regarding key characteristics, purpose, and approach. The comparison also includes suggestions that indicate how existing classification approaches could be extended. © 2023 29th Annual Americas Conference on Information Systems, AMCIS 2023. All rights reserved.

关键词： Classification in IS Digital Classification Taxonomy Typology

来源：评论

学校读者我要写书评

暂无评论

Adventures in data analysis: a systematic review of Deep Learning techniques for pattern recognition in cyber-physical-social systems

引用

Multimedia Tools and Applications 2024年第8期83卷 22909-22973页

作者： Amiri, Zahra Heidari, Arash Navimipour, Nima Jafari Unal, Mehmet Mousavi, Ali Department of Computer Engineering Tabriz Branch Islamic Azad University Tabriz Iran Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has Universitesi Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou64002 Taiwan Department of Computer Engineering Nisantasi Universitesi Istanbul Turkey Islamic Azad University Sanandaj Branch Sanandaj Iran

Machine Learning (ML) and Deep Learning (DL) have achieved high success in many textual, auditory, medical imaging, and visual recognition patterns. Concerning the importance of ML/DL in recognizing patterns due to its high accuracy, many researchers argued for many solutions for improving pattern recognition performance using ML/DL methods. Due to the importance of the required intelligent pattern recognition of machines needed in image processing and the outstanding role of big data in generating state-of-the-art modern and classical approaches to pattern recognition, we conducted a thorough Systematic Literature Review (SLR) about DL approaches for big data pattern recognition. Therefore, we have discussed different research issues and possible paths in which the abovementioned techniques might help materialize the pattern recognition notion. Similarly, we have classified 60 of the most cutting-edge articles put forward pattern recognition issues into ten categories based on the DL/ML method used: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Generative Adversarial Network (GAN), Autoencoder (AE), Ensemble Learning (EL), Reinforcement Learning (RL), Random Forest (RF), Multilayer Perception (MLP), Long-Short Term Memory (LSTM), and hybrid methods. SLR method has been used to investigate each one in terms of influential properties such as the main idea, advantages, disadvantages, strategies, simulation environment, datasets, and security issues. The results indicate most of the articles were published in 2021. Moreover, some important parameters such as accuracy, adaptability, fault tolerance, security, scalability, and flexibility were involved in these investigations. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Cluster-preserving sampling algorithm for large-scale graphs

引用

science China(Information sciences) 2023年第1期66卷 60-76页

作者： Jianpeng ZHANG Hongchang CHEN Dingjiu YU Yulong PEI Yingjun DENG National Digital Switching System E&T Research Center Information Engineering University Network Systems Department of the Strategic Support Force School of Computer Science and Technology Eindhoven University of Technology Center for Applied Mathematics Tianjin University

Graph sampling is a very effective method to deal with scalability issues when analyzing largescale graphs. Lots of sampling algorithms have been proposed, and sampling qualities have been quantified using explicit properties(e.g., degree distribution) of the sample. However, the existing sampling techniques are inadequate for the current sampling task: sampling the clustering structure, which is a crucial property of the current networks. In this paper, using different expansion strategies, two novel top-leader sampling methods(i.e., TLS-e and TLS-i) are proposed to obtain representative samples, and they are capable of effectively preserving the clustering structure. The rationale behind them is to select top-leader nodes of most clusters into the sample and then heuristically incorporate peripheral nodes into the sample using specific expansion strategies. Extensive experiments are conducted to investigate how well sampling techniques preserve the clustering structure of graphs. Our empirical results show that the proposed sampling algorithms can preserve the population's clustering structure well and provide feasible solutions to sample the clustering structure from large-scale graphs.

关键词： graph sampling clustering structure top-leader nodes expansion strategies large-scale graphs

来源：评论

学校读者我要写书评

暂无评论

Gate-Attention and Dual-End Enhancement Mechanism for Multi-Label Text Classification

引用

computers, Materials & Continua 2023年第11期77卷 1779-1793页

作者： Jieren Cheng Xiaolong Chen Wenghang Xu Shuai Hua Zhu Tang Victor S.Sheng School of Computer Science and Technology Hainan UniversityHaikou570228China Hainan Blockchain Technology Engineering Research Center Hainan UniversityHaikou570228China School of Cyberspace Security Hainan UniversityHaikou570228China Department of Computer Science Texas Tech UniversityLubbock79409USA

In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative *** studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical *** contrast,these endogenous insights naturally align with the classification *** our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention *** mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the ***,to address the intricate task of mining label correlations,we propose a Dual-end enhancement *** mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory *** conducted an extensive battery of experiments on the AAPD and RCV1-2 *** experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement *** final model unequivocally outperforms the baseline model,attesting to its *** findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.

关键词： Multi-label text classification feature extraction label distribution information sequence generation

来源：评论

学校读者我要写书评

暂无评论

Cuckoo Search-Optimized Deep CNN for Enhanced Cyber Security in IoT Networks

引用

computers, Materials & Continua 2024年第12期81卷 4109-4124页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413TaiwanChina Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057MaharashtraIndia Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413TaiwanChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon Management Department College of Business AdministrationPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Science Faculty of ScienceNorthern Border UniversityArar91431Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks seriously threaten information privacy and security within the Internet of Things(IoT)*** phishing attack detection solutions have been developed for IoT;however,many of these are either not optimally efficient or lack the lightweight characteristics needed for practical *** paper proposes and optimizes a lightweight deep-learning model for phishing attack *** model employs a two-fold optimization approach:first,it utilizes the analysis of the variance(ANOVA)F-test to select the optimal features for phishing detection,and second,it applies the Cuckoo Search algorithm to tune the hyperparameters(learning rate and dropout rate)of the deep learning ***,our model is trained in only five epochs,making it more lightweight than other deep learning(DL)and machine learning(ML)*** proposed model achieved a phishing detection accuracy of 91%,with a precision of 92%for the’normal’class and 91%for the‘attack’***,the model’s recall and F1-score are 91%for both *** also compared our approach with traditional DL/ML models and past literature,demonstrating that our model is more *** study enhances the security of sensitive information and IoT devices by offering a novel and effective approach to phishing detection.

关键词： Deep learning phishing Cuckoo Search cable news network(CNN) IoT ANOVA F-test

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：