检索结果-内蒙古大学图书馆

Self-Supervised Hyperbolic Spectro-Temporal Graph Convolution Network for Early 3D Behavior Prediction

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Liu, Peng Lai, Qin Li, Haibo Zhao, Chong Wang, Qicong Meng, Hongying Xiamen University Department of Computer Science and Technology School of Informatics Xiamen361102 China Brunel University London Department of Electronic and Electrical Engineering UxbridgeUB8 3PH United Kingdom

3D human behavior is a highly nonlinear spatiotemporal interaction process. Therefore, early behavior prediction is a challenging task, especially prediction with low observation rates in unsupervised mode. To this end, we propose a novel self-supervised early 3D behavior prediction frame-work that learns graph structures on hyperbolic manifold. Firstly, we employ the sequence construction of multi-dynamic key information to enlarge the key details of spatio-temporal behavior sequences, addressing the high redundancy between frames of spatio-temporal interaction. Secondly, for capturing dependencies among long-distance joints, we explore a unique graph Laplacian on hyperbolic manifold to perceive the subtle local difference within frames. Finally, we leverage the learned spatio-temporal features under different observation rates for progressive contrast, forming self-supervised signals. This facilitates the extraction of more discriminative global and local spatio-temporal information from early behavior sequences in unsupervised mode. Extensive experiments on three behavior datasets have demonstrated the superiority of our approach at low to medium observation rates. © 2016 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

``Impressively Scary:' Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications 25

``Impressively Scary:' Exploring User Perceptions and Reacti...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Jack West Bengisu Cagiltay Shirley Zhang Jingjie Li Kassem Fawaz Suman Banerjee Department of Computer Sciences University of Wisconsin-Madison Madison Wisconsin USA School of Informatics University of Edinburgh Edinburgh United Kingdom Electrical and Computer Engineering University of Wisconsin-Madison Madison Wisconsin USA

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on the Communication of UAVs with Charging and Control Stations

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer Science and Communications 2025年

作者： Chalkiadaki, Aikaterini Milidonis, Athanasios Mourgelas, Christos Voyiatzis, Ioannis Department of Informatics and Computer Engineering University of West Attica Ag. Spyridonos Str.Athens Egaleo12243 Greece

Unmanned Aerial Vehicles (UAVs) have a history of over a century of deployment, but in recent decades, they have progressed at a staggering rate. Nowadays, UAVs are used by a large number of civil and military applications. The communication functionality of a UAV with external systems for control and charging is strongly connected with evolving technologies and services. This leads to an increased number of alternatives when designing UAV communications. This review presents the information needed for choosing an efficient communication system between UAVs and two important elements, the Ground Control Station (GCS) and the Charging Station (CS). GCS is responsible for monitoring and controlling the UAV’s units, while CS is used for the formal charging of the UAV. This study aimed at collecting, classifying, and evaluating all of the necessary information in order to obtain the final decision about the kind of communication that is most efficient for a target UAV application. The features of the telemetry open-source protocols are presented for the UAV-GCS communication and evaluated according to the needs of the most significant application domains. Communication between UAVs and CSs is classified depending on the existence of an intermediate server and analyzed considering telemetry protocols and application domains. Communication algorithms are evaluated in terms of time and energy efficiency. Lastly, for the most significant application domains, the most suitable algorithms are matched. © 2024 Bentham Science Publishers.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Utilization of Distribution System Flexibility for Enhanced TSO-DSO Interoperability: A Novel Machine Learning-Based Optimal Power Flow Approach

arXiv

引用

arXiv 2025年

作者： Dindar, Burak Saner, Can Berk Çakmak, Hüseyin K. Hagenmeyer, Veit Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Karlsruhe76131 Germany Department of Electrical and Computer Engineering National University of Singapore Singapore117581 Singapore

Due to the transformation of the power system, the effective use of flexibility from the distribution system (DS) is becoming crucial for efficient network management. Leveraging this flexibility requires interoperability among stakeholders, including Transmission System Operators (TSOs) and Distribution System Operators (DSOs). However, data privacy concerns among stakeholders present significant challenges for utilizing this flexibility effectively. To address these challenges, we propose a machine learning (ML)-based method in which the technical constraints of the DSs are represented by ML models trained exclusively on non-sensitive data. Using these models, the TSO can solve the optimal power flow (OPF) problem and directly determine the dispatch of flexibility-providing units (FPUs)—in our case, distributed generators (DGs)-in a single round of communication. To achieve this, we introduce a novel neural network (NN) architecture specifically designed to efficiently represent the feasible region of the DSs, ensuring computational effectiveness. Furthermore, we incorporate various PQ charts rather than idealized ones, demonstrating that the proposed method is adaptable to a wide range of FPU characteristics. To assess the effectiveness of the proposed method, we benchmark it against the standard AC-OPF on multiple DSs with meshed connections and multiple points of common coupling (PCCs) with varying voltage magnitudes. The numerical results indicate that the proposed method achieves performant results while prioritizing data privacy. Additionally, since this method directly determines the dispatch of FPUs, it eliminates the need for an additional disaggregation step. By representing the DSs technical constraints through ML models trained exclusively on nonsensitive data, the transfer of sensitive information between stakeholders is prevented. Consequently, even if reverse engineering is applied to these ML models, no sensitive data can be extracted. This allows

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Silent Speech Interfaces: Non-Invasive Neuromuscular Signal Processing for Assistive Communication

Silent Speech Interfaces: Non-Invasive Neuromuscular Signal ...

引用

AI in Cybersecurity (ICAIC), International Conference on

作者： Sallar Khan Khawaja Usman Ali Ali Raza Ali Qadri Maisam Rizvi School of Informatics and Cybersecurity Technological University Dublin Dublin Ireland Department of Computer Science & Information Technology Sir Syed University of Engineering and Technology Karachi Pakistan

ISBN: (数字)9798331518882

ISBN: (纸本)9798331518899

Our research demonstrates a discrete speech system that empowers those afflicted with speech impairments to convey ideas by internally articulating words without producing audible sound. This method harnesses the minimal movements involved in articulation, making it less arduous than conventional vocalization, especially for individuals facing communication challenges. Silent Speech Interfaces (SSIs) form the foundation of our research, enabling the decoding of neuromuscular signals associated with internal speech articulation to facilitate non-invasive and effective communication for individuals with speech impairments. This research entails the utilization of a multi-electrode configuration to capture subtle, low-voltage electrical signals positioned on the surface area of the subject’s neck. These signals emerge as a consequence of neural activation within the speech articulator muscles, signifying the internal articulation of words within the oral cavity, accompanied by minimal physical movement. Subsequent to signal acquisition, a comprehensive analysis of the data is conducted using a biosensing board (Cyton), facilitated by the implementation of the OpenBCI GUI interface and visualization via Python plotting tools.

关键词： Training Vocabulary Accuracy Neuromuscular Speech recognition Speech enhancement Biosensors Artificial intelligence Usability Standards

来源：评论

学校读者我要写书评

暂无评论

Exploring Energy Landscapes for Minimal Counterfactual Explanations: Applications in Cybersecurity and Beyond

arXiv

引用

arXiv 2025年

作者： Evangelatos, Spyridon Veroni, Eleni Efthymiou, Vasilis Nikolopoulos, Christos Papadopoulos, Georgios Th. Sarigiannidis, Panagiotis Research & Innovation Development Department Netcompany-Intrasoft S.A. Luxembourg Department of Electronic Engineering Hellenic Mediterranean University Greece Department of Informatics and Telematics Harokopio University of Athens Greece Department of Electrical and Computer Engineering University of Western Macedonia Greece

Counterfactual explanations have emerged as a prominent method in Explainable Artificial Intelligence (XAI), providing intuitive and actionable insights into Machine Learning model decisions. In contrast to other traditional feature attribution methods that assess the importance of input variables, counterfactual explanations focus on identifying the minimal changes required to alter a model’s prediction, offering a "what-if" analysis that is close to human reasoning. In the context of XAI, counterfactuals enhance transparency, trustworthiness and fairness, offering explanations that are not just interpretable but directly applicable in the decision-making processes. In this paper, we present a novel framework that integrates perturbation theory and statistical mechanics to generate minimal counterfactual explanations in explainable AI. We employ a local Taylor expansion of a Machine Learning model’s predictive function and reformulate the counterfactual search as an energy minimization problem over a complex landscape. In sequence, we model the probability of candidate perturbations leveraging the Boltzmann distribution and use simulated annealing for iterative refinement. Our approach systematically identifies the smallest modifications required to change a model’s prediction while maintaining plausibility. Experimental results on benchmark datasets for cybersecurity in Internet of Things environments, demonstrate that our method provides actionable, interpretable counterfactuals and offers deeper insights into model sensitivity and decision boundaries in high-dimensional spaces. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Adaptive Filter for Head Tracking in Augmented Reality (AR)-based Flight Simulators

引用

IEEE Transactions on computers 2025年

作者： Nwobodo, Onyeka J. Kuaban, Godlove Suila Nkemeni, Valery Wereszczynski, Kamil Cyran, Krzysztof A. Silesian University of Technology Department of Computer Graphics Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Gliwice Poland Polish Academy of Sciences Institute of Theoretical and Applied Informatics Poland University of Buea Laboratory of Electrical Engineering and Computing Faculty of Engineering and Technology Buea Cameroon

This paper presents a novel approach for head tracking in augmented reality (AR) flight simulators using an adaptive fusion of Kalman and particle filters. This fusion dynamically balances the strengths of both algorithms, leveraging Kalman filters for computational efficiency and particle filters for handling non-linearities based on real-time factors such as sensor noise and head movement patterns. Our method demonstrates superior tracking precision and reduced latency, making it particularly effective for immersive pilot training in AR-based flight simulations. While focused on flight simulation, our approach holds high potential for broader applications in other AR and virtual reality (VR) environments where precise, real-time head tracking is crucial. These results provide actionable design guidance for developers optimizing tracking systems in environments that require fast response times and high accuracy. Future extensions of this research could explore the generalization of our approach across diverse AR applications, including human-computer interaction (HCI), medical simulations, and gaming. © 1968-2012 IEEE.

关键词： Flight simulators

来源：评论

学校读者我要写书评

暂无评论

Variational Weighted p−q Regularization for Hyperspectral Image Restoration Under Mixed Noise

引用

IET Image Processing 2025年第1期19卷

作者： Aetesam, Hazique Prasath, V. B. Surya Department of Computer Science and Engineering Birla Institute of Technology Mesra Bihar Patna India Division of Biomedical Informatics Cincinnati Children's Hospital Medical Center CincinnatiOH United States Department of Pediatrics University of Cincinnati College of Medicine CincinnatiOH United States Department of Biomedical Informatics University of Cincinnati CincinnatiOH United States Department of Computer Science University of Cincinnati CincinnatiOH United States

In this paper, we propose to use weighted (Formula presented.) -norm for approximating the solution of general (Formula presented.) -norm regularization problem for recovering hyperspectral images (HSI) corrupted by a mixture of Gaussian-impulse noise. As a special case of (Formula presented.), we design an optimization framework to accommodate the combined effect of different noise sources. An initial impulse noise pre-detection phase decouples the raw noisy HSI data into impulse and Gaussian corrupted pixels. Gaussian corrupted pixels are handled by data-fidelity term in (Formula presented.) while impulse corrupted pixels possess more Laplacian like behavior;modeled using (Formula presented.). Solutions of problems involving (Formula presented.) in data fidelity and regularization terms complicate the optimization process but are less sensitive to the outlier pixels. On the other hand, the least square solutions for the data misfit are computationally efficient but generates solutions which are quite sensitive to the outlier pixels;which is the characteristic of impulse corrupted pixels. Therefore, in this paper, we decouple the set of pixels into two distinct parts;handled using two separate data fidelity terms. Total variation (TV) is used on the Casorati matrix representation of the input data to exploit similarity along both spatial and spectral dimensions. The resulting optimization problem is reformulated as iteratively reweighted least square for the general (Formula presented.) -norm problem for (Formula presented.) for data fidelity terms and (Formula presented.) for the TV regularization term. Experiments conducted over synthetically corrupted HSI data and images obtained from real HSI sensors confirm the suitability of the proposed weighted norm optimization framework (WNOF) over a wide range of degradation scenarios. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

On the Rate-Exponent Region of Integrated Sensing and Communications With Variable-Length Coding

arXiv

引用

arXiv 2025年

作者： Papoutsidakis, Ioannis Alexandropoulos, George C. Department of Informatics and Telecommunications National and Kapodistrian University of Athens Panepistimiopolis Ilissia Athens15784 Greece Department of Electrical and Computer Engineering University of Illinois ChicagoIL60601 United States

This paper considers the achievable rate-exponent region of integrated sensing and communication systems in the presence of variable-length coding with feedback. This scheme is fundamentally different from earlier studies, as the coding methods that utilize feedback impose different constraints on the codewords. The focus herein is specifically on the Gaussian channel, where three achievable regions are analytically derived and numerically evaluated. In contrast to a setting without feedback, we show that a trade-off exists between the operations of sensing and communications. Copyright © 2025, The Authors. All rights reserved.

关键词： Codes (symbols)

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：