检索结果-内蒙古大学图书馆

BAN: A Universal Paradigm for Cross-Scene Classification Under Noisy Annotations From RGB and Hyperspectral Remote Sensing Images

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Chen, Wentang Wen, Yibin Zheng, Juepeng Huang, Jianxi Fu, Haohuan Sun Yat-sen University School of Artificial Intelligence Zhuhai519082 China Zhejiang University State Key Laboratory of Fluid Power and Mechatronic Systems Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering Robotics Institute Hangzhou310027 China Southwest Jiaotong University Faculty of Geosciences and Engineering Chengdu610032 China China Agricultural University College of Land Science and Technology Beijing100107 China Ministry of Agriculture and Rural Affairs Key Laboratory of Remote Sensing for Agri-Hazards Beijing100125 China Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518071 China Tsinghua University Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System Science Beijing100190 China National Supercomputer Center in Shenzhen Shenzhen518071 China

While domain adaptation (DA) methods have made significant strides in remote sensing community, most current works assume that the source domain labels are accurate. However, limited emphasis has been placed on the scenario where source data are mislabeled with noisy annotations, which is more common in real applications and referred to as noisy DA (NDA). This article formulates remote sensing cross-scene classification on NDA scenarios and proposes a novel network called bilateral adaptation network (BAN), which consists of two parts: 1) forward learning (FL), which utilizes a model learning from the noisy source domain and transfers knowledge to target domain;and 2) backward learning (BL), which utilizes a dual model to acquire knowledge from the target domain and transfer it to source domain. We conduct two parts alternately and adopt a symmetrical Kullback-Leibler (KL) loss to align predictions of the model and its dual model in the same domain. This interactive strategy is able to explore bilateral relationships between domains, implicitly reducing label noise in the source domain. In addition, BAN could serve as a universal paradigm to not only improve the existing NDA methods but also enhance recent DA approaches. Comprehensive evaluations on three publicly available RGB-band remote sensing datasets and two hyperspectral datasets validate the superior effectiveness of our proposed BAN. BAN improves the average accuracy by 6.70%-15.70% on RGB datasets and overall accuracy (OA) by 1.36%-3.14% on hyperspectral datasets with flip-20% noise compared to other state-of-the-art DA and NDA approaches. Promising results indicate the potential of our approach in tackling more general and practical problems with noisy source domain. © 2025 IEEE.

关键词： Contrastive Learning

Teleoperation of Humanoid Robots: A Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Darvish, Kourosh Penco, Luigi Ramos, Joao Cisneros, Rafael Pratt, Jerry Yoshida, Eiichi Ivaldi, Serena Pucci, Daniele Artificial and Mechanical Intelligence Center for Robotics and Intelligent Systems Istituto Italiano di Tecnologia Genoa Italy Florida Institute for Human and Machine Cognition 40 S Alcaniz St PensacolaFL32502 United States Department of Mechanical Science and Engineering University of Illinois at Urbana-Champaign United States Department of Information Technology and Human Factors Tsukuba Japan Inria Loria Université de Lorraine CNRS Nancy France Department of Applied Electronics Faculty of Advanced Engineering Tokyo University of Science Japan

Teleoperation of humanoid robots enables the integration of the cognitive skills and domain expertise of humans with the physical capabilities of humanoid robots. The operational versatility of humanoid robots makes them the ideal platform for a wide range of applications when teleoperating in a remote environment. However, the complexity of humanoid robots imposes challenges for teleoperation, particularly in unstructured dynamic environments with limited communication. Many advancements have been achieved in the last decades in this area, but a comprehensive overview is still missing. This survey paper gives an extensive overview of humanoid robot teleoperation, presenting the general architecture of a teleoperation system and analyzing the different components. We also discuss different aspects of the topic, including technological and methodological advances, as well as potential applications. A web-based version of the paper can be found at https://***/. © 2023, CC BY.

关键词： Remote control

MPTA-Net: Multi-Scale Perception Network with Triple-View Attention for Polyp Segmentation

学校读者我要写书评

暂无评论

MPTA-Net: Multi-Scale Perception Network with Triple-View At...

Neural Networks, Information and Communication engineering (NNICE), International Conference on

作者： Zhihong Chen Lisha Yao Yue Liu Bingjiang Qiu Chu Han Haoyang Tang Yujia Du Zaiyi Liu Gang Fang Institute of Computing Science and Technology Guangzhou University Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou China School of Medicine South China University of Technology Guangzhou China Department of Radiology Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China School of Information Engineering Jiangxi College of Applied Technology Ganzhou China Guangdong Cardiovascular Institute Guangdong Provincial People’s Hospital Guangdong Academy of Sciences Guangzhou China Medical Research Institute Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences) Southern Medical University Guangzhou China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China

Accurate segmentation of polyps in endoscopic images is pivotal for the early detection and diagnosis of colorectal cancer (CRC). Nonetheless, the varied appearance of polyp foregrounds and the intricate background interference significantly diminish the efficacy of pixel-level predictions. To address this issue, we propose a multi-scale perception network with triple-view attention (MPTA-Net) for polyp segmentation. The model primarily revolves around two core principles. The first integrates multiscale spatial information into the network's hierarchical encoding process to better preserve detailed polyp semantic information. The second introduces a triple-view attention mechanism that analyzes feature maps from three distinct perspectives to focus on and localize semantically relevant areas, thereby enhancing segmentation accuracy. Experimental results reveal that the proposed model outperforms existing mainstream segmentation models, effectively addressing under-segmentation, over-segmentation, and edge blurriness issues in polyp segmentation, thereby achieving better identification of challenging areas.

关键词：

Enhanced dysarthria detection in cerebral palsy and ALS patients using WaveNet and CNN-BiLSTM models: A comparative study with model interpretability

学校读者我要写书评

暂无评论

Biomedical Signal Processing and Control 2025年 110卷

作者： Esraa Hassan Abeer Saber Tarek Abd El-Hafeez T. Medhat Mahmoud Y. Shams Department of Machine Learning and Information Retrieval Faculty of Artificial Intelligence Kafrelsheikh University Kafr El-Sheikh 33516 Egypt Information Technology Dept. Faculty of Computers and Artificial Intelligence Damietta University Damietta 34517 Egypt Computer Science Unit Deraya University El-Minia 61765 Egypt Department of Computer Science Faculty of Science Minia University El-Minia 61519 Egypt Department of Electrical Engineering Faculty of Engineering Kafrelsheikh University Kafr El-Sheikh 33516 Egypt

Dysarthria, a motor speech disorder commonly associated with neurological conditions such as cerebral palsy and ALS, poses significant challenges for early diagnosis and intervention. Traditional diagnostic methods often rely on subjective assessments, leading to delays in effective treatment. Recent advances in machine learning and deep learning offer promising avenues for automated dysarthria detection, enabling faster and more reliable assessments. However, these approaches often face challenges in handling diverse languages and operating efficiently on resource-constrained devices. In this study, we leverage the TORGO database with cerebral palsy, ALS, or control subjects, along with a Russian-voice dataset, to explore automated dysarthria classification. We evaluate the performance of machine learning models, including Random Forest Classifier and XGBClassifier, in comparison with state-of-the-art deep learning architectures such as CNN-LSTM. Building upon these findings, we suggest an enhanced WaveNet-based model specifically optimized to capture the temporal characteristics of audio signals across large and diverse datasets. To address real-world challenges, we introduce a Real-Time Adaptation Framework, enabling efficient and accurate dysarthria detection even on resource-constrained devices. Additionally, explainability enhancements using SHAP values and Grad-CAM techniques are integrated, providing insights into the model’s decision-making process and improving its reliability for clinical applications. The suggested WaveNet-based model demonstrates exceptional performance, achieving precision, recall, and F-score values of 0.92040, 0.91979, and 0.91965, respectively, alongside a Matthews Correlation Coefficient (MCC) of 0.89320, outperforming other models. These results highlight the potential of our approach for rapid and reliable dysarthria detection, particularly in multilingual and resource-limited settings. By combining explainability and real-time c

关键词： Audio classification Dysarthria Signals WaveNet

Neural Brain: A Neuroscience-inspired Framework for Embodied Agents

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Jian Shi, Xiongtao Nguyen, Thai Duy Zhang, Haitian Zhang, Tianxiang Sun, Wei Li, Yanjie Vasilakos, Athanasios V. Iacca, Giovanni Khan, Arshad Ali Kumar, Arvind Cho, Jae Won Mian, Ajmal Xie, Lihua Cambria, Erik Wang, Lin School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Robotics Hunan University China School of Intelligence Science and Engineering Harbin Institute of Technology Shenzhen China Department of Information and Communication Technology University of Agder Norway Department of Information Engineering and Computer Science University of Trento Italy Elm Company London United Kingdom Division of Computational Science and Technology KTH Royal Institute of Technology Sweden School of Artificial Intelligence and Data Science Sejong University Korea Republic of Department of Computer Science the University of Western Australia Australia College of Computing and Data Science Nanyang Technological University Singapore

The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments. Despite advancements in pattern recognition and symbolic reasoning, current AI systems, such as large language models, remain disembodied, unable to physically engage with the world. This limitation has driven the rise of embodied AI, where autonomous agents, such as humanoid robots, must navigate and manipulate unstructured environments with human-like adaptability. At the core of this challenge lies the concept of Neural Brain, a central intelligence system designed to drive embodied agents with human-like adaptability. A Neural Brain must seamlessly integrate multimodal sensing and perception with cognitive capabilities. Achieving this also requires an adaptive memory system and energy-efficient hardware-software co-design, enabling real-time action in dynamic environments. This paper introduces a unified framework for the Neural Brain of embodied agents, addressing two fundamental challenges: (1) defining the core components of Neural Brain and (2) bridging the gap between static AI models and the dynamic adaptability required for real-world deployment. To this end, we propose a biologically inspired architecture that integrates multimodal active sensing, perception-cognition-action function, neuroplasticity-based memory storage and updating, and neuromorphic hardware/software optimization. Furthermore, we also review the latest research on embodied agents across these four aspects and analyze the gap between current AI systems and human intelligence. By synthesizing insights from neuroscience, we outline a roadmap towards the development of generalizable, autonomous agents capable of human-level intelligence in real-world scenarios. Our project page is at Neural-Brain-for-Embodied-Agents. Copyright © 2025, The Authors. All rights reserved.

关键词： Anthropomorphic robots

Forecasting Airlines Customer Demand: A Comparative Analysis of Time Series Models

学校读者我要写书评

暂无评论

Forecasting Airlines Customer Demand: A Comparative Analysis...

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Diaa Salama AbdElminaam Mariam Mohamed Abouelwafa Ahmed Ehab Ibrahim Amira Alaa Saber Laith Abualigah Faculty of Computer Science Misr International University Cairo Egypt Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Computer Science Department Al al-Bayt University Mafraq Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan MEU Research Unit Middle East University Amman Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya Malaysia

The airline industry is renowned for employing sophisticated strategies, making accurate customer demand fore-casting essential for operational planning and resource allocation. Revenue management systems heavily rely on precise passenger demand forecasts. This research paper consists of two main parts. Firstly, it compares and evaluates the performance of different time series models, namely SARIMA, ARIMA, and auto-regression, for forecasting airline customer demand. These forecasting methods are applied using features such as month, number of passengers, international flights, and total number of flights. Secondly, the models are tested on pattern analysis, including level, seasonality, and trend, and the evaluation metrics are assessed. The outcomes of this study contribute to the existing knowledge on forecasting airline customer demand, offering valuable insights for optimizing operational planning and resource allocation in the airline industry. The comparative analysis of forecasting models provides practical guidance for airlines to select the most suitable model for their specific requirements. The evaluation metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), R-squared $\left(\mathbf{R}^2\right)$ , and Mean Absolute Percentage Error (MAPE), clearly indicate the superior performance of the SARIMA methodology in terms of forecast bias. The experimental results demonstrate that SARIMA models incorporating seasonality patterns achieve the best forecasting outcomes. Keywords: Revenue management, accurate forecasts, evaluation matrix, time series algorithms

关键词：

Robust-MBDL: A Robust Multi-branch Deep Learning Based Model for Remaining Useful Life Prediction and Operational Condition Identification of Rotating Machines

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tran, Khoa Vu, Hai-Canh Pham, Lam Boudaoud, Nassim University of Science and Technology The University of Danang 54 Nguyen Luong Bang Hoa Khanh Bac Lien chieu Da Nang Danang550000 Viet Nam Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial Intelligence Van Lang University Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City70000 Viet Nam AIT Austrian Institute of Technology GmbH Giefinggasse 4 1210 Wien Vienna1210 Austria Roberval Laboratory Department of Mechanical Engineering University of Technology of Compiègne Rue Roger Couttolenc Compiègne60200 France

In this paper, a Robust Multi-branch Deep learning-based system for remaining useful life (RUL) prediction and Operating Condition (OC) identification of rotating machines is proposed. In particular, the proposed system comprises main components: (1) an LSTM-Autoencoder to denoise the vibration data;(2) a feature extraction to generate time-domain, frequency-domain, and time-frequency based features from the denoised data;(3) a novel and robust multi-branch deep learning network architecture to exploit the multiple features. The performance of our proposed system was evaluated and compared to the state-of-the-art systems on two benchmark datasets of XJTU-SY and PRONOSTIA. The experimental results prove that our proposed system outperforms the state-of-the-art systems and presents potential for real-life applications on bearing machines. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

Efficient congestion-aware routing in MANETs using quantum self-attention and optimized siamese network

学校读者我要写书评

暂无评论

Expert Systems with Applications 2025年 291卷

作者： Rajagopal Reka Bade Rebecca Murugavelu Mathivanan Muthusamy Rameshkumar Department of Artificial Intelligence & Data Science Mahendra College of Engineering Salem Campus Salem 636106 India Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Affiliated University - JNTUH Hyderabad India Department of Electronics and Communication Engineering Salem College of Engineering and Technology Salem India Department of Computer Science and Engineering Paavai Engineering College Namakkal Tamilnadu India

Mobile Ad Hoc Networks (MANETs) are dynamic, self-configuring wireless networks that frequently undergo topology changes, making them highly susceptible to link errors, congestion, and excessive energy consumption. Existing routing protocols struggle with real-time congestion detection and efficient path selection, leading to higher packet loss and increased network overhead. To address these challenges, this study proposes an adaptive Quantum Self-Attention-based Triple Pseudo Siamese Network (QSA-TPSN) with the Walrus Optimizer (WO) for congestion-aware and energy-efficient routing in MANETs. The QSA module enhances congestion detection by prioritizing stable, high-quality routes, reducing retransmissions by 25%. The TPSN framework learns congestion patterns and dynamically refines routing decisions to minimize delay. Meanwhile, the WO optimizer optimally selects paths based on real-time congestion and energy metrics, ensuring load balancing and efficient resource utilization. The QSA-TPSN-WO model is evaluated against CLEE, CL-QAERP, ESCL-PSO, and ANN-based routing approaches using packet delivery ratio (PDR), delay, throughput, energy consumption, and packet drop rate as performance metrics. Experimental results confirm that QSA-TPSN-WO achieves a 99.4% PDR, reduces packet loss by 28%, decreases energy consumption by 30%, and improves throughput by 15% compared to state-of-the-art methods. These findings demonstrate that QSA-TPSN-WO significantly enhances routing stability, congestion control, and energy efficiency, making it a robust solution for MANET environments.

关键词：

STAR-RIS Enabled ISAC Systems: Joint Rate Splitting and Beamforming Optimization

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yuan Zhang, Ruichen Jiang, Ruihong Zhu, Yongdong Hu, Huimin Ni, Qiang Fei, Zesong Niyato, Dusit The Research Center for Space Computing System Zhejiang Laboratory Hangzhou311100 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Communications and Information Engineering The School of Artificial Intelligence Xi’an University of Posts and Telecommunications Xi’an710121 China The School of Computing and Communications Lancaster University LancasterLA1 4WA United Kingdom The School of Information and Electronics Beijing Institute of Technology Beijing100081 China

This paper delves into an integrated sensing and communication (ISAC) system bolstered by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). Within this system, a base station (BS) is equipped with communication and radar capabilities, enabling it to communicate with ground terminals (GTs) and concurrently probe for echo signals from a target of interest. Moreover, to manage interference and improve communication quality, the rate splitting multiple access (RSMA) scheme is incorporated into the system. The signal-to-interference-plus-noise ratio (SINR) of the received sensing echo signals is a measure of sensing performance. We formulate a joint optimization problem of common rates, transmit beamforming at the BS, and passive beamforming vectors of the STAR-RIS. The objective is to maximize sensing SINR while guaranteeing the communication rate requirements for each GT. We present an iterative algorithm to address the non-convex problem by invoking Dinkelbach’s transform, semidefinite relaxation (SDR), majorization-minimization, and sequential rank-one constraint relaxation (SROCR) theories. Simulation results manifest that the performance of the studied ISAC network enhanced by the STAR-RIS and RSMA surpasses other benchmarks considerably. The results evidently indicate the superior performance improvement of the ISAC system with the proposed RSMA-based transmission strategy design and the dynamic optimization of both transmission and reflection beamforming at STAR-RIS. © 2024, CC BY.

关键词： Signal to noise ratio