检索结果-内蒙古大学图书馆

6th IFIP TC 12 International conference on Intelligence Science, ICIS 2024

作者： Chen, Lin Chen, Xiaobo Shandong Technology and Business University Yantai264005 China

ISBN: (纸本)9783031712524

Driving fatigue has become a serious hidden danger to road traffic safety. Drivers in a fatigued state often have problems such as delayed reactions and lack of concentration, which increases the risk of traffic accidents. In fatigued driving, the brain activity of the driver undergoes a series of changes, such as a decrease in the frequency of brain waves and a decrease in the amplitude of electroencephalogram (EEG) signals. Therefore, we propose a novel Semi-supervised Label Propagation with Optimal Graph Learning (SOGL) model that for identifying the fatigue state of drivers. This model uses class information from a small amount of labeled EEG data to assist the learning of unlabeled data and uses soft projection matrix learning to handle non-linear data structures. In addition, we also introduce a partially labeled graph learning method that extracts potential data structure information through graph structure learning techniques to improve the robustness and generalization ability of the model. Experimental results show that the model has good performance on a driving fatigue dataset. © IFIP International Federation for Information processing 2025.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Practical Radar Sensing Using Two Stage Neural Network for Denoising OTFS signals

Practical Radar Sensing Using Two Stage Neural Network for D...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ashok S Kumar Sheetal Kalyani Department of Electrical Engineering Indian Institute of Technology Madras Chennai India

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Our objective is to derive the range and velocity of multiple targets from the delay-Doppler domain for radar sensing using orthogonal time frequency space (OTFS) signaling. Noise contamination affects the performance of OTFS signals in real-world environments, making radar sensing challenging. This work introduces a two-stage approach to tackle this issue. In the first stage, we use a generative adversarial network to denoise the corrupted OTFS samples, significantly improving data quality. Following this, the denoised signals are passed to a convolutional neural network model to predict the values of the velocities and ranges of multiple targets. The proposed two-stage approach can predict the range and velocity of multiple targets, even in very low signal-to-noise ratio scenarios, with high accuracy and outperforms existing methods.

关键词： Time-frequency analysis Spaceborne radar Noise reduction Neural networks Predictive models Generative adversarial networks Sensors Convolutional neural networks Speech processing signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning Technique with Meta-data-Featured Images Captured by Drone for Real-Time Victim Positioning in Flood-Affected Areas 19

Leveraging Deep Learning Technique with Meta-Data-Featured I...

引用

19th International conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Do, Trong Tuan Nguyen, Dinh Duy Ho, Xuan Hai Nguyen, Van Duc School of Electrical and Electronic Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9798331507817

Flooding has long been a major concern for nations frequently affected by natural disasters. The detection and localization of isolated victims for immediate temporary rescue have been a focal point for many researchers aiming to demonstrate the practical value of their solutions. However, accessing flood-affected areas poses significant challenges, as floods severely disrupt local transportation and damage infrastructure, rendering access nearly impossible. In such scenarios, the most feasible rescue approach is aerial intervention using Unmanned Aerial Vehicles (UAVs). Nevertheless, accurately detecting and localizing targets from a UAV’s perspective is a significant challenge. UAVs operate at various altitudes and speeds, resulting in motion blur of targets against densely populated backgrounds. Additionally, target localization is made difficult due to the limited contextual understanding of the surroundings. To address these challenges, we propose training the YOLOv10 model to enhance the detection of small objects, integrated with a GPS-based target localization system. Furthermore, to enable the practical, real-world application of this solution, we introduce a communication infrastructure that facilitates the timely and effective deployment of both the detection and localization models. Field experiments have yielded promising results, with the artificial intelligence model achieving an Average Precision (AP) between 85-95%, and the localization model processing targets at an impressive speed of under 1 ms. The combined detection and localization approach demonstrated a positioning error of only 7-9 meters. Moreover, integrating the AI model and the localization algorithm into a low-latency communication system has shown promising results, providing near-instantaneous outputs with delays ranging from 0.6 to 0.9 seconds from the moment a target enters the frame. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Exploring Prediction targets in Masked Pre-Training for Speech Foundation Models

Exploring Prediction Targets in Masked Pre-Training for Spee...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Li-Wei Chen Takuya Higuchi He Bai Ahmed Hussen Abdelaziz Shinji Watanabe Alexander Rudnicky Tatiana Likhomanenko Barry-John Theobald Zakaria Aldeneh Carnegie Mellon University Apple

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Speech foundation models, such as HuBERT and its variants, are pre-trained on large amounts of unlabeled speech data and then used for a range of downstream tasks. These models use a masked prediction objective, where the model learns to predict information about masked input segments from the unmasked context. The choice of prediction targets in this framework impacts their performance on downstream tasks. For instance, models pre-trained with targets that capture prosody learn representations suited for speaker-related tasks, while those pre-trained with targets that capture phonetics learn representations suited for content-related tasks. Moreover, prediction targets can differ in the level of detail they capture. Models pre-trained with targets that encode fine-grained acoustic features perform better on tasks like denoising, while those pre-trained with targets focused on higher-level abstractions are more effective for content-related tasks. Despite the importance of prediction targets, the design choices that affect them have not been thoroughly studied. This work explores the design choices and their impact on downstream task performance. Our results indicate that the commonly used design choices for HuBERT can be suboptimal. We propose approaches to create more informative prediction targets and demonstrate their effectiveness through improvements across various downstream tasks.

关键词： Foundation models Noise reduction Predictive models Phonetics signal processing Acoustics Speech processing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Decoupled Feature Matching for Few-shot Counting and Localization

Decoupled Feature Matching for Few-shot Counting and Localiz...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Chao Zhai Fan Zhang Wenyu Chen Malu Zhang Fan Li Xuanting Xie University of Electronic Science and Technology of China Chengdu China The Hong Kong University of Science and Technology Hong Kong SAR China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Few-shot counting (FSC) aims to train a generalized visual counting model that can count any novel category given a small number of support samples. Current prevalent approaches treat FSC as a feature-matching task, leveraging attention to aggregate information from all other query patches or supports for each query patch. However, we notice that this operation blends target features with non-target features, making it difficult for the model to differentiate between targets and non-targets, thereby impacting counting accuracy. To tackle this issue, we develop a Decoupled Feature Matching Module (DFMM), which decouples target and non-target regions and conducts self-aggregation within respective regions. Furthermore, we design a Consistency Alignment Loss (CAL) to facilitate discriminative ability between targets and non-targets across multiple scales. Besides, we adopt a localization paradigm for counting and propose an Anchor-based Assignment Strategy to stabilize the optimization process and improve counting accuracy. Experiments on FSC147 and CARPK demonstrate that our method can achieve performance on par with state-of-the-art methods. Qualitative and quantitative experiments both confirm the efficacy of our proposed components.

关键词： Location awareness Training Visualization Accuracy Aggregates signal processing Acoustics Power capacitors Speech processing Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Discrepancy Attack for Single Object Tracking

Multi-view Feature Discrepancy Attack for Single Object Trac...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Zhiheng Li Weng Zhimin Yuehuan Wang Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Adversarial attacks on single object tracking (SOT) have attracted increasing attention. However, most previous works have focused on adding small digital perturbations to tracking sequences, assuming access to the data, which makes these attacks impractical in real-world applications. Inspired by traditional military camouflage, we propose a texture pattern attack method with a similar implementation, called the Multi-View Feature Discrepancy Attack (MFDA). Unlike the consistent texture features of traditional camouflage, we iteratively optimize non-planar textures by obtaining gradients from the target model to enhance feature discrepancies across different viewpoints. Moreover, the model’s multi-scale features and heatmaps are utilized as targets for our feature-level and decision-level attacks, respectively. We apply texture patterns to controllable regions of vehicle models and conduct extensive attack experiments. The results show that our method significantly degrades the performance of state-of-the-art Siamese-based trackers, and also exhibits attack capability against ViT-based trackers.

关键词： Heating systems Target tracking Perturbation methods signal processing Acoustics Surface texture Object tracking Speech processing Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Learning adaptive detection and tracking collaborations with augmented UAV synthesis for accurate anti-UAV system

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 282卷

作者： Liu, Shihan Xu, Tianyang Zhu, Xue-Feng Wu, Xiao-Jun Kittler, Josef Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Peoples R China Univ Surrey Ctr Vis Speech & Signal Proc CVSSP Guildford GU2 7XH England

In recent years, Unmanned Aerial Vehicles (UAVs) have witnessed a significant use upsurge across various domains. However, their low cost and elusive size have raised significant security concerns. In particular, UAVs, imaged in the infrared mode, located in a cluttered background and being relatively small targets, pose formidable challenges. To this end, in this paper, we propose a novel approach for accurate UAVs perception. The core innovation lies in learning an adaptive detection and tracking collaboration mechanism, supported by a novel method of training data augmentation (ADTC). During the test phase, ADTC begins by leveraging the detector to identify the potential target candidates within the image frame. These candidates are then refined by an adaptive selection module, where a Kalman filter is deployed to model and predict the motion trajectory of each candidate. The best result of the predicted trajectories with the detected candidates is adopted as the output. The adaptive selection module filters out less confident objects, efficiently decreasing processing time. Furthermore, we construct a new dataset Anti-MUAV15 to evaluate the performance of ADTC in multipleUAV scenarios. Our approach has been rigorously evaluated through qualitative and quantitative experiments on the Anti-UAV, AntiUAV600 and Anti-MUAV15 datasets. The experimental results demonstrate that our method outperforms state-of-the-art anti-UAV solutions in terms of robustness and precision, without imposing additional computational burden. The code and dataset are available at https://***/Shihan0325/AntiMUAV15.

关键词： Anti-UAV system Object detection Visual tracking data augmentation

来源：评论

学校读者我要写书评

暂无评论

Stance Detection for Social Text: Inference-Enhanced Multi-Task Learning with Machine-Annotated Supervision

Stance Detection for Social Text: Inference-Enhanced Multi-T...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Qiankun Pi Jicang Lu Yepeng Sun Qinlong Fan Xukun Zhou Shouxin Shang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China School of Information Renmin University of China Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Stance detection, a natural language processing technique, captures user attitudes on controversial social media topics. However, the semantic ambiguity of social texts makes accurate stance determination challenging. Existing annotated data is often domain-specific, resulting in poor model generalization for unseen targets and cross-domain scenarios. To tackle this challenge, we introduce inference tasks related to stance detection as auxiliary tasks and use a multitask learning approach to improve the model’s understanding of textual semantics. Meanwhile, to alleviate the scarcity of annotated data, we use argumentation corpus with abundant resources as the source domain to train the basic stance detection model. We integrate this model with a large-scale framework to facilitate weakly supervised learning for machine annotation of unlabeled social texts, thereby boosting the model’s adaptability across different targets and domains. Experimental results on four Twitter datasets demonstrate that our method can significantly improve the model’s stance discriminative ability and generalization performance.

关键词： Adaptation models Weak supervision Social networking (online) Annotations Semantics Blogs Transfer learning signal processing data models Speech processing

来源：评论

学校读者我要写书评

暂无评论

TinyResNetDOA-DCS: A Tiny Residual Network for Direction-of-Arrival Estimation with Dual Channel Switched-element System 16

TinyResNetDOA-DCS: A Tiny Residual Network for Direction-of-...

引用

16th International conference on signal processing Systems, ICSPS 2024

作者： Si, Chengke Xu, Chen Hong, Yunhai Fan, Rong Institute of Electronic and Electrical Engineering Civil Aviation Flight University of China Chengdu641419 China

ISBN: (纸本)9781510689251

In conventional direction finding system with dual channel switched-element receiver, the direction-of-arrival (DOA) estimation just can be performed for single source, the accuracy of which deteriorates in the low signal-to-noise ratio case. In this paper, a tiny residual network for DOA estimation with dual channel switched-element system named TinyResNetDOA-DCS is proposed, in which the residual connections, squeeze-and-excitation block (SEBlock), cross stage partial (CSP) connections and DropBlock are employed. The proposed network has the merits of small parameter scale, low computational complexity, real-time of inference and strong generalization ability. As far as we know, it is the first time to estimate the DOA of sources based on neural network with dual channel switched-element system. With the data set formed by the angular spectra features with the minimum variance distortionless response estimator, the advantages of the proposed neural network are illustrated. Simulation results show that the accuracies of TinyResNetDOA-DCS outperform the counterparts in the case of single source with low signal-to-noise ratio. © 2025 SPIE.

关键词： signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Biodenoising: Animal Vocalization Denoising without Access to Clean data

Biodenoising: Animal Vocalization Denoising without Access t...

引用

2025 IEEE International conference on Acoustics, Speech, and signal processing, ICASSP 2025

作者： Miron, Marius Keen, Sara Liu, Jen-Yu Hoffman, Benjamin Hagiwara, Masato Pietquin, Olivier Effenberger, Felix Cusimano, Maddie Earth Species Project

ISBN: (纸本)9798350368741

Animal vocalization denoising is a task similar to human speech enhancement, which is relatively well-studied. In contrast to the latter, it comprises a higher diversity of sound production mechanisms and recording environments, and this higher diversity is a challenge for existing models. Adding to the challenge and in contrast to speech, we lack large and diverse datasets comprising clean vocalizations. As a solution we use as training data pseudo-clean targets, i.e. pre-denoised vocalizations, and segments of background noise without a vocalization. We propose a train set derived from bioacoustics datasets and repositories representing diverse species, acoustic environments, geographic regions. Additionally, we introduce a non-overlapping benchmark set comprising clean vocalizations from different taxa and noise samples. We show that that denoising models (demucs, CleanUNet) trained on pseudo-clean targets obtained with speech enhancement models achieve competitive results on the benchmarking set. We publish data, code, libraries, and demos at https://***/research/biodenoising. © 2025 IEEE.

关键词： bioacoustics datasets domain generalization

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：