检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Bongini, Pietro Mandelli, Sara Montibeller, Andrea Casu, Mirko Pontorno, Orazio Ragaglia, Claudio Vittorio Zanchetta, Luca Aquilina, Mattia Wani, Taiba Majid Guarnera, Luca Tondi, Benedetta Boato, Giulia Bestagini, Paolo Amerini, Irene De Natale, Francesco Battiato, Sebastiano Barni, Mauro University of Siena Department of Information Engineering an Mathematics Italy Politecnico di Milano Department of Electronics Informatics and Bioengineering Italy University of Trento Department of Information Engineering and Computer Science Italy University of Catania Department of Mathematics and Computer Science Italy Sapienza University of Rome Departement of Computer Control and Management Engineering Italy

Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available generative techniques, as well as the scarcity of high-quality open source datasets of diverse nature for this task, make training and benchmarking synthetic image source attribution models very challenging. WILD1 is a new in-the-Wild Image Linkage Dataset designed to provide a powerful training and benchmarking tool for synthetic image attribution models. The dataset is built out of a closed set of 10 popular commercial generators, which constitutes the training base of attribution models, and an open set of 10 additional generators, simulating a real-world in-the-wild scenario. Each generator is represented by 1,000 images, for a total of 10,000 images in the closed set and 10,000 images in the open set. Half of the images are post-processed with a wide range of operators. WILD allows benchmarking attribution models in a wide range of tasks, including closed and open set identification and verification, and robust attribution with respect to post-processing and adversarial attacks. Models trained on WILD are expected to benefit from the challenging scenario represented by the dataset itself. Moreover, an assessment of seven baseline methodologies on closed and open set attribution is presented, including robustness tests with respect to post-processing. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hide & Seek: Traffic Matrix Completion and Inference Using Hidden Information

Hide & Seek: Traffic Matrix Completion and Inference Using H...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Alessio Sacco Flavio Esposito Guido Marchetto Department of Control and Computer Engineering Politecnico di Torino Italy Department of Computer Science Saint Louis University USA

Traffic matrices are used for many network management operations, from planning to repairing. Despite years of research on the topic, their estimation and inference on the Internet are still challenging and error-prone. For example, missing values are unavoidable due to flaws in the measurement systems and possible failure in data collection systems. It is thus helpful for many network operators to recover the missing data from the partial direct measurements. Some existing matrix completion methods do not fully consider network traffic behavior and hidden traffic characteristics, showing the inability to adapt to multiple scenarios. Others instead make assumptions on the matrix structure that may be invalid or impractical, curtailing the applicability. In this paper, we propose Hide & Seek, a novel matrix completion and prediction algorithm based on a combination of generative autoencoders and Hidden Markov Models. We demonstrate with an extensive experimental evaluation on real-world datasets how our algorithm can accurately reconstruct missing values while predicting their short-term evolution.

关键词： Hidden Markov models Estimation Telecommunication traffic Data collection Prediction algorithms Inference algorithms Encoding

来源：评论

学校读者我要写书评

暂无评论

GLOBAL PATH PLANNING OF CLIMBING ROBOT FOR WELD QUALITY INSPECTION IN LARGE SCALE STORAGE TANKS

引用

International Journal of Robotics and Automation 2025年第3期40卷 242-253页

作者： Wang, Ruifeng Gu, Shichao Liu, Xiaoguang Zhang, Hao Xu, Zhihao Pan, Jia Zhou, Xuefeng Institute of Intelligent Manufacturing Guangdong Academy of Sciences Guangdong Key Laboratory of Modern Control Technology GuangDong Guangzhou510070 China School of Rail Transportation Wuyi University GuangDong Jiangmen529020 China School of Mechanical Automotive Engineering South China University of Technology Guangdong Guangzhou510006 China Department of Computer Science University of Hong Kong 999077 Hong Kong

Climbing robots are considered efficient solutions for conducting quality inspections of welds on large storage tanks. Nevertheless, planning the global shortest path along spatially complex cross distributed welds poses a significant challenge for climbing robots. This paper introduces a novel graph-based global shortest climbing path planning method, facilitating swift inspect all welds by the robot. The three-dimensional (3D) weld lines undergo conversion into a two-dimensional (2D) weighted connected graph using a 3D model equivalence mapping approach. The dimensionality-reduced connectivity map is required to be an Euler graph;otherwise, the adoption of the Floyd and KM algorithms is necessary to construct an undirected Euler graph with the minimum total weight. Subsequently, an Euler circuit is searched in the Euler graph, considering the presence of plus edges, through an improved Fleury algorithm to obtain the shortest global path for the climbing robot. The paper also introduces the idea of Euler graph segmentation to address the challenge of Euler circuits in large or symmetric models. Simulations are conducted to validate the effectiveness and performance of the proposed planners. The results demonstrate that our method effectively reduces the length global path and enhances inspection efficiency. © 2025 Acta Press. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Federated-Boosting: A Distributed and Dynamic Boosting-Powered Cyber-Attack Detection Scheme for Security and Privacy of Consumer IoT

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Khan, Izhar Ahmed Pi, Dechang Kamal, Shaharyar Alsuhaibani, Mohammed Alshammari, Bandar Mzel Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China University of Chile Department of Electrical Engineering Chile Qassim University College of Computer Department of Computer Science Buraydah Saudi Arabia Technology Control Company Riyadh Saudi Arabia

Consumer Internet of Things (CIoT) is an emerging technology that took the traditional consumer electronics to next level with smarter devices and higher connectivity. However, the rapid boom of this technology has captured a great deal of hacker's attention in the past decade. Due to resource restricted nature of CIoT devices and limited computational abilities, security professionals are unable to strengthen the security and privacy measures. Since the existing security methods suffers from data imbalance and overfitting issues, this paper proposes a distributed and dynamic weighted boosting method named Federated-Boosting for the accurate and timely detection of cyber-Attacks in CIoT. Specifically, a weighting strategy is designed to overcome the data imbalance issue by dynamically adjusting the weights of weaker class samples. Additionally, a regularized loss function is designed that helps in controlling the overfitting of the model and provide enhance performance and generalization. Finally, a time-based and performance-based dynamic aggregation scheme is designed using distributed training model that keeps the privacy of the CIoT devices intact to the local server. Extensive experiments on two real-world datasets validates the superior performance of Federated-Boosting model against state-of-The-Art detection models. © 1975-2011 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Handwritten Signature Recognition using Parallel CNNs and Transfer Learning for Forensics

Handwritten Signature Recognition using Parallel CNNs and Tr...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Jaouhar Fattahi Feriel Sghaier Mohamed Mejri Ridha Ghayoula Emil Pricop Baha Eddine Lakdher Department of Computer Science and Software Engineering Laval University Quebec Canada Carthage National Engineering School Carthage University Tunis Tunisia Faculty of Engineering University of Moncton Canada Computers & Electronics Department Automatic Control Petroleum-Gas University of Ploieşti Ploieşti Romania Faculty of Science University of Monastir Monastir Tunisia

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Handwritten signatures hold paramount importance in legal, financial, and administrative domains, necessitating the development of robust signature recognition tools for forensic applications. This paper introduces a handwritten signature recognition (HSR) model employing Parallel Convolutional Neural Networks (CNN) tailored for forensic endeavors. Utilizing the parallel processing capabilities of CNN, our proposed approach adeptly analyzes and extracts discriminative features from handwritten signature images to facilitate precise recognition. In addition, we leverage several transfer learning techniques by parallelizing proven pre-trained CNNs. Extensive experimentation validates the efficacy of our approach on a standard dataset, demonstrating high accuracy and resilience in signature recognition tasks. The proposed approach exhibits substantial promise in augmenting forensic investigations by automating signature verification processes, thereby bolstering fraud detection efforts and upholding the integrity of legal documentation.

关键词： Deep learning Handwriting recognition Forensics Face recognition Transfer learning Feature extraction Fraud Convolutional neural networks Standards Resilience

来源：评论

学校读者我要写书评

暂无评论

A markerless high resolution structural health monitoring framework for smart cities

A markerless high resolution structural health monitoring fr...

引用

2021 IEEE Technology and engineering Management Conference - Europe, TEMSCON-EUR 2021

作者： Chan, Christopher Chun Ki Chen, Chih-Cheng Delaney, Steven Ferworn, Alexander Chaoyang University of Technology Department of Information Management Taichung Taiwan Feng Chia University Department of Automatic Control Engineering Taichung Taiwan Ryerson University Department of Computer Science Toronto Canada

ISBN: (纸本)9781665440912

Our paper introduces a novel structural health monitoring (SHM) framework for preexisting surveillance camera video footage towards an automated structural engineering e-governance system in a smart city. We test our framework on a sample pole structure using a high-resolution camera and an off-the-shelf phone camera. A preliminary study suggests the efficacy of using the framework in monitoring noticeable degradation and aging in large structures in periodically captured images. Our framework is dissimilar to computer vision techniques in which deformation patterns are recognized;instead, our framework is purposed as a long term observation application in which large structures in public video surveillance footage is monitored for changes that may suggest signs of aging or degradation of a structure over a long period of time. We posit that this novel framework, with emerging technology and innovation, can pave the way to combine artificial intelligence and smart structural health monitoring techniques in a widespread, unprecedented way of ensuring safe public structures in smart cities. © 2021 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

A deep learning architecture for audience interest prediction of news topic on social media 24

A deep learning architecture for audience interest predictio...

引用

Advances in Database Technology - 24th International Conference on Extending Database Technology, EDBT 2021

作者： Truică, Ciprian-Octavian Apostol, Elena-Simona Stefu, Teodor Karras, Panagiotis Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania Department Computer Science Aarhus University Aarhus Denmark

ISBN: (纸本)9783893180844

Personalized social media offer communication opportunities that mass media could not afford, yet also raise novel challenges. A prime challenge arising from this shift in digital communication is to detect topics and events of interest. In this paper, we propose and deploy a novel Deep Learning architecture that predicts if a news topic becomes viral by analyzing social media diffusion and audience interest in current news events. The proposed solution: (i) analyzes news articles, (ii) extracts associated topics and events, (iii) matches the topics and events to filter and extract developing topics, (iv) extracts current events from Twitter and matches them to the filtered news topics, and (v) predicts audience interest in news topics using Twitter likes and retweets. We employ several feature engineering techniques to improve prediction by integrating user metadata into the training set. In our experiments, we correlate two datasets collected over several months in the same time period. The first dataset contains news articles collected from different news venues, while the second one contains tweets regarding the news. The experimental results from our real-world deployment prove that the proposed system achieves high accuracy when integrating influencers metadata and the day of the week. Thus, proving that the news topics virality prediction is improved under the assumptions that spreaders and the day of the week play a huge role in information diffusion. © 2021 Copyright held by the owner/author(s).

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Designing a Secure Smart Remote Patient Monitoring and Warning System using Big Data and Internet of Things Ecosystems 10

Designing a Secure Smart Remote Patient Monitoring and Warni...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Ramesh, S.P. Abdulwahid, Ali Hadi Anjum, Afsana Venkatesh, N. Singh, Rajesh Chakravarthi, M. Kalyan Amet University Department of Computer Science and Engineering Tamil Nadu Kanathur India Southern Technical University Engineering Technical College Department of Control and Automation Basra Iraq Jazan University Department of Information Technology and Security Jazan Saudi Arabia School of Computer Science and Artificial Intelligence Sr University Telangana Warangal India Uttaranchal Institute of Technology Uttaranchal University India School of Electronics Engineering VIT-AP University Amaravathi India

ISBN: (纸本)9789380544472

The demand on healthcare is growing as a result of the expanding global population, rising demands for successful treatment, and an underlying improvement in life quality. Consequently, healthcare remains one of the most significant social and economic problems in the world, necessitating the development of new and more sophisticated scientific and technological treatments.E-health services are provided via personalised healthcare systems to meet the medical and support needs of the ageing population. An important development in the Big Data age is the Internet of Things, which facilitates several real-time engineering solutions through improved services. Healthcare systems are now using analytics over IoT data streams as a stream of user data to find new information, forecast rapid recognition, and make decisions on life-threatening situations. In this study, researchers have carried out a thorough review of the hottest recent revolutionary technologies in bespoke healthcare systems, with a focus on hypervisor, cloud infrastructure, big data analytic, the Web of Things, and smartphone apps. In order to make early disease detection and diagnosis possible, it is important to develop a better healthcare system. We have examined these problems and suggested potential solutions while offering secure e-health services. The purpose of this study is to design a smart and secure remote monitoring and warning system using the latest emerging technologies in 21stcentury such as big data analytics and Internet of Things (IoT) ecosystems. In this study the researchers discussed a detailed research methodology to meet the outcomes of the reerach. All the relevant findings and analysis are explained in descriptive manner. Moreover, this study highlights the constantly expanding requirements for better medical systems in the present and offers potential directions for future research. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FROST: Fusion and Multimodal 3D Reconstruction of Icy Surfaces for Robotic Exploration

FROST: Fusion and Multimodal 3D Reconstruction of Icy Surfac...

引用

Computational Intelligence on engineering/Cyber Physical Systems Companion (CIES Companion), IEEE Symposium on

作者： Huy Xuan Pham Erdal Kayacan Department of Electrical and Computer Engineering Artificial Intelligence in Robotics Laboratory (Air Lab) Aarhus University Aarhus C Denmark Automatic Control Group (RAT) Paderborn University Paderborn Germany

ISBN: (数字)9798331508494

ISBN: (纸本)9798331508500

Three-dimensional (3D) reconstruction serves as a cornerstone in various robotic applications, playing critical roles in scene understanding and navigation. Traditionally, LiDAR has been instrumental in generating precise point clouds of the environment, providing essential data for these applications. However, the efficacy of LiDAR sensors is significantly hindered in challenging conditions, such as the presence of water or icy surfaces. The complex interplay between laser beams and icy or non-ideal surfaces can result in signal degradation, distortion, or even complete signal loss, adversely affecting the accuracy and reliability of the 3D reconstruction process. The reflective and refractive properties of ice, along with its variable surface conditions, present challenges that traditional LiDAR sensors struggle to address. This paper proposes a diverse dataset to facilitate a multimodal approach for reconstructing icy surfaces using various sensors. A preliminary study based on this dataset demonstrates the feasibility of combining the geometric surface obtained from consecutive LiDAR scans with reconstructed meshes from visual cameras. The integration of distinct data sources has the potential to improve the robustness of reconstruction algorithms in diverse scenarios. The dataset can be downloaded at https://***/records/13862009.

关键词： Point cloud compression Surface reconstruction Laser radar Three-dimensional displays Navigation Ice Robustness Laser beams Image reconstruction Surface treatment

来源：评论

学校读者我要写书评

暂无评论

ScCADE: A Superior Tool for Predicting Perturbation Responses in Single-Cell Gene Expression Using Contrastive Learning and Attention Mechanisms

ScCADE: A Superior Tool for Predicting Perturbation Response...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Ou, Jingfeng Li, Jiawei Xia, Zhiliang Dai, Shurui Ding, Yulian Guo, Yan Jiang, Limin Tang, Jijun Southern University of Science and Technology College of Engineering Shenzhen518055 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Miami Department of Public Health Sciences MiamiFL33136 United States

ISBN: (纸本)9798350386226

The advent of single-cell transcriptomics has revolutionized our ability to analyze cellular heterogeneity and dynamics at a fine resolution, yet covering the vast array of potential perturbations remains challenging due to biological variability. To address this, we propose scCADE, a novel computational approach utilizing contrastive learning and an attention mechanism to decouple gene expression signatures and predict cellular responses to perturbations. scCADE excels in predicting responses in cells to perturbations observed in other cells but not yet seen in the target cells. Through rigorous ablation studies and validation across three datasets involving drug and gene editing perturbations, scCADE consistently outperformed existing methods, underscoring its efficacy and potential to advance genomics and personalized medicine by accurately forecasting responses to novel perturbations. © 2024 IEEE.

关键词： Contrastive 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：