检索结果-内蒙古大学图书馆

ActivityMamba: A CNN-Mamba hybrid neural network for efficient human activity recognition

IEEE Transactions on Mobile computing 2025年

作者： Luo, Fei Li, Anna Jiang, Bin Khan, Salabat Wu, Kaishun Wang, Lu Great Bay University School of Computing and Information Technology Dongguan China Lancaster University School of Computing & Communications United Kingdom University of Petroleum College of Oceanography and Space Informatics Qingdao China Shenzhen University College of Computer Science and Software Engineering Shenzhen China Guangzhou China

Current research in human activity recognition primarily emphasizes enhancing accuracy, with limited exploration into computational efficiency and hardware compatibility. Recently, Mamba has sparked substantial interest within the realm of deep learning. Mamba is a hardware-aware algorithm enabling very efficient training and inference. Researchers are applying Mamba to various tasks, demonstrating significant promise in both language and vision tasks. It is worthwhile to investigate the use of Mamba for efficient human activity recognition. In this paper, we proposed a hybrid neural network that integrates CNN and visual Mamba, called ActivityMamba. The SE-Mamba block in ActivityMamba utilizes both CNN's local and Mamba's global context modeling while keeping computation and memory efficiency. We evaluated the ActivityMamba on five public benchmark datasets collected by using three different sensing techniques. ActivityMamba achieved higher performance than vision transformers, vision Mamba, and CNNs with fewer FLOPs and parameters. It sets a new SOTA on all five datasets, which are 91.78% OA and 89.13% F1 on the USC-HAD dataset, 99.19% OA and 98.64% F1 on the UT-HAR dataset, 99.82% OA and F1 on the DIAT dataset, 98.59% OA and 98.65% F1 on the UCI-HAR dataset, and 95.41% OA and 93.14% F1 on the UniMib dataset. Our work is the first to investigate the CNN-Mamba hybrid network for efficient human activity recognition. © 2002-2012 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

multiPI-TransBTS: A multi-path learning framework for brain tumor image segmentation based on multi-physical information

引用

Computers in Biology and Medicine 2025年 191卷 110148-110148页

作者： Zhu, Hongjun Huang, Jiaohang Chen, Kuo Ying, Xuehui Qian, Ying School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Engineering Research Center of Software Quality Assurance Testing and Assessment Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing University of Posts and Telecommunications Chongqing400065 China

Brain Tumor Segmentation (BraTS) plays a critical role in clinical diagnosis, treatment planning, and monitoring the progression of brain tumors. However, due to the variability in tumor appearance, size, and intensity across different MRI modalities, automated segmentation remains a challenging task. In this study, we propose a novel Transformer-based framework, multiPI-TransBTS, which integrates multi-physical information to enhance segmentation accuracy. The model leverages spatial information, semantic information, and multi-modal imaging data, addressing the inherent heterogeneity in brain tumor characteristics. The multiPI-TransBTS framework consists of an encoder, an Adaptive Feature Fusion (AFF) module, and a multi-source, multi-scale feature decoder. The encoder incorporates a multi-branch architecture to separately extract modality-specific features from different MRI sequences. The AFF module fuses information from multiple sources using channel-wise and element-wise attention, ensuring effective feature recalibration. The decoder combines both common and task-specific features through a Task-Specific Feature Introduction (TSFI) strategy, producing accurate segmentation outputs for Whole Tumor (WT), Tumor Core (TC), and Enhancing Tumor (ET) regions. Comprehensive evaluations on the BraTS2019 and BraTS2020 datasets demonstrate the superiority of multiPI-TransBTS over the state-of-the-art methods. The model consistently achieves better Dice coefficients, Hausdorff distances, and Sensitivity scores, highlighting its effectiveness in addressing the BraTS challenges. Our results also indicate the need for further exploration of the balance between precision and recall in the ET segmentation task. The proposed framework represents a significant advancement in BraTS, with potential implications for improving clinical outcomes for brain tumor patients. © 2025

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain

FreqSense: Universal and Low-Latency Adversarial Example Det...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yihuan Huang Yuanzhe Li Yanzhen Ren Weiping Tu Yuhong Yang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speaker recognition (SR) systems are particularly vulnerable to adversarial example (AE) attacks. To mitigate these attacks, AE detection systems are typically integrated into SR systems. To overcome the limitations of low detection accuracy, poor generalization, and high latency in existing schemes, this paper proposes FreqSense, an AE detection scheme based on frequency distribution features. FreqSense detects a variety of unknown AE attacks with low latency, and provides interpretability in its detection process. The basic idea of FreqSense is that AE typically introduce carefully designed noise in specific frequency bands that are associated with highly distinctive speaker identities. Therefore, leveraging the distributional variations in these frequency bands can effectively distinguish between AE and benign audio. FreqSense models frequency distribution features by integrating time-frequency transformation technology with a self-attention mechanism and employs a neural network-based classifier to distinguish between AE and benign audio. Experimental results show that FreqSense achieves an overall detection accuracy of 99.2%, surpassing state-of-the-art (SOTA) schemes by 27.2%. When confronting unknown AE attacks, FreqSense achieves a detection accuracy of 98.3% with a latency of just 0.0014 seconds.

关键词： Time-frequency analysis Accuracy Noise Speech recognition Feature extraction Acoustics Speaker recognition Low latency communication Speech processing

来源：评论

学校读者我要写书评

暂无评论

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smoke Detection

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yuhan Jiang Zhongyuan Wang Jie Hua Jinbi Liang Zengmin Xu National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10,724 images covering three common scenarios of air conditioner refrigerant leak: loading port, refrigerant extraction, and disassembly. All images are sourced from 656 video segments of real air conditioner recycling scenarios, captured by surveillance cameras deployed on an environmental company’s recycling production line. The annotations for the refrigerant leak smoke in the images are performed by industry experts to ensure high accuracy and consistency. To the best of our knowledge, ACRL-10K is the first dataset specifically designed for refrigerant leak smoke detection. Based on the ACRL-10K dataset, we present the performance of mainstream object detectors, including the YOLO series, as a baseline to conduct the following work: 1) preliminarily summarize the challenges of using the dataset for refrigerant leak smoke detection; 2) show the detection results of benchmark methods; and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the ACRL-10K dataset would hopefully advance research and applications in refrigerant leak early warning during air conditioner dismantling and recycling processes.

关键词： YOLO Image segmentation Accuracy Surveillance Loading Signal processing algorithms Production Detectors Cameras Recycling

来源：评论

学校读者我要写书评

暂无评论

SafeSlice: Enabling SLA-Compliant O-RAN Slicing via Safe Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Nagib, Ahmad M. Abou-Zeid, Hatem Hassanein, Hossam S. School of Computing Queen’s University Canada Department of Electrical and Software Engineering University of Calgary Canada Faculty of Computers and Artificial Intelligence Cairo University Egypt

Deep reinforcement learning (DRL)-based slicing policies have shown significant success in simulated environments but face challenges in physical systems such as open radio access networks (O-RANs) due to simulation-to-reality gaps. These policies often lack safety guarantees to ensure compliance with service level agreements (SLAs), such as the strict latency requirements of immersive applications. As a result, a deployed DRL slicing agent may make resource allocation (RA) decisions that degrade system performance, particularly in previously unseen scenarios. Real-world immersive applications require maintaining SLA constraints throughout deployment to prevent risky DRL exploration. In this paper, we propose SafeSlice to address both the cumulative (trajectory-wise) and instantaneous (state-wise) latency constraints of O-RAN slices. We incorporate the cumulative constraints by designing a sigmoid-based risk-sensitive reward function that reflects the slices’ latency requirements. Moreover, we build a supervised learning cost model as part of a safety layer that projects the slicing agent’s RA actions to the nearest safe actions, fulfilling instantaneous constraints. We conduct an exhaustive experiment that supports multiple services, including real virtual reality (VR) gaming traffic, to investigate the performance of SafeSlice under extreme and changing deployment conditions. SafeSlice achieves reductions of up to 83.23% in average cumulative latency, 93.24% in instantaneous latency violations, and 22.13% in resource consumption compared to the baselines. The results also indicate SafeSlice’s robustness to changing the threshold configurations of latency constraints, a vital deployment scenario that will be realized by the O-RAN paradigm to empower mobile network operators (MNOs). Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Zhang, Xiyue Xue, Xiaoyong Du, Xiaoning Xie, Xiaofei Liu, Yang Sun, Meng University of Oxford Department of Computer Science United Kingdom Peking University Department of Information and Computing Science School of Mathematical Science China Monash University Department of Software Systems and Cybersecurity Australia Singapore Management University School of Computing and Information Systems Singapore Nanyang Technological University School of Computer Science and Engineering Singapore

Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify dissimilarities between clients, identifying model deviations caused by backdoor injections. We also propose an iterative algorithm to progressively detect and exclude malicious clients as outliers based on these dissimilarity measurements. Evaluations across a range of benchmark tasks demonstrate that our approach outperforms state-of-the-art methods in detection accuracy and defense effectiveness. When deployed for runtime protection, our approach effectively eliminates backdoor injections with marginal overheads. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Semi-rPPG: Semi-Supervised Remote Physiological Measurement with Curriculum Pseudo-Labeling

arXiv

引用

arXiv 2025年

作者： Wu, Bingjie Yu, Zitong Xie, Yiping Liu, Wei Luo, Chaoqi Liu, Yong Goh, Rick Siow Mong Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen518060 China

Remote Photoplethysmography (rPPG) is a promising technique to monitor physiological signals such as heart rate from facial videos. However, the labeled facial videos in this research are challenging to collect. Current rPPG research is mainly based on several small public datasets collected in simple environments, which limits the generalization and scale of the AI models. Semi-supervised methods that leverage a small amount of labeled data and abundant unlabeled data can fill this gap for rPPG learning. In this study, a novel semi-supervised learning method named Semi-rPPG that combines curriculum pseudo-labeling and consistency regularization is proposed to extract intrinsic physiological features from unlabelled data without impairing the model from noises. Specifically, a curriculum pseudo-labeling strategy with signal-to-noise ratio (SNR) criteria is proposed to annotate the unlabelled data while adaptively filtering out the low-quality unlabelled data. Besides, a novel consistency regularization term for quasi-periodic signals is proposed through weak and strong augmented clips. To benefit the research on semi-supervised rPPG measurement, we establish a novel semi-supervised benchmark for rPPG learning through intra-dataset and cross-dataset evaluation on four public datasets. The proposed Semi-rPPG method achieves the best results compared with three classical semi-supervised methods under different protocols. Ablation studies are conducted to prove the effectiveness of the proposed methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Pattern recognition in programming to support the evaluation of Computational Thinking

Pattern recognition in programming to support the evaluation...

引用

IEEE World engineering Education Conference (EDUNINE)

作者： Steven Pacheco-Portuguez Antonio Gonzalez-Torres Lilliana Sancho-Chavarria Ignacio Trejos-Zelaya Jorge Monge-Fallas School of Computing Costa Rica Institute of Technology Cartago Costa Rica School of Computer Engineering Costa Rica Institute of Technology Cartago Costa Rica School of Software Engineering & School of Computing Universidad CENFOTEC & Costa Rica Institute of Technology San José & Cartago Costa Rica School of Mathematics Costa Rica Institute of Technology Cartago Costa Rica

ISBN: (数字)9798331542788

ISBN: (纸本)9798331542795

Computational thinking is a high-level skill that involves both critical and creative thinking. This research proposes an advanced method for analyzing source code to assess computational thinking skills in elementary school students. We present a large-scale approach that examines source code from various programming exercises using a generalized abstract syntax tree, enabling language-independent analysis. Clustering techniques are applied to identify different levels of computational thinking development in areas such as parallelism, data representation, abstraction and decomposition, control flow, and programming structure. The results of the automated assessment provide insights into students' computational thinking abilities across diverse populations, highlighting opportunities for improving the educational framework.

关键词： Codes Source coding Data visualization Syntactics Parallel processing Pattern recognition software measurement engineering education Programming profession

来源：评论

学校读者我要写书评

暂无评论

Multiscale Graph Transformer for Brain Disorder Diagnosis

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Shehzad, Ahsan Zhang, Dongyu Yu, Shuo Abid, Shagufta Kumar, Dinesh Kant Xia, Feng School of Software Technology Dalian University of Technology Dalian116620 China School of Foreign Languages School of Software Technology Dalian University of Technology Dalian116024 China School of Computer Science and Technology Dalian University of Technology Dalian116024 China School of Engineering RMIT University MelbourneVIC3000 Australia School of Computing Technologies RMIT University MelbourneVIC3000 Australia

—Multiscale brain networks are crucial for diagnosing brain disorders by revealing the hierarchical organization of brain function and connectivity. However, previous methods that explored multi-atlas approaches to model these networks often failed to represent this organization across multiple spatial and temporal scales, leading to limited representations and potentially inaccurate diagnoses. To address this issue, we propose the Multiscale Brain Graph Transformer (BrainMGT), which captures the hierarchical organization of brain connectivity at various spatial and temporal scales to improve the diagnosis of brain disorders. BrainMGT constructs multiscale brain networks that model spatial hierarchies, i.e. microscale, mesoscale, and macroscale, while preserving their modular structure. It also incorporates multiple temporal scales, i.e. fast, intermediate, and slow, for estimating connectivity, rather than relying on a single temporal scale from blood-oxygen-level-dependent (BOLD) signals. Using self-attention and cross-attention mechanisms, BrainMGT extracts and integrates features both within and between these scales, generating fine-coarse feature representations that improve diagnostic precision. We validated BrainMGT on three real-world functional magnetic resonance imaging (fMRI) datasets, and the results show that BrainMGT outperformed existing methods in diagnosing neurological disorders. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Magnetic resonance imaging

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：