检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wu, Xiuen Wang, Tao Cai, Yuanzheng Liang, Lingyu Papageorgiou, George Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China SYSTEMA Research Center European University Cyprus Nicosia Cyprus

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians' future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multistage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method. Copyright © 2024, The Authors. All rights reserved.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Real-Time AIoT for UAV Antenna Interference Detection via Edge-Cloud Collaboration

arXiv

引用

arXiv 2024年

作者： Dong, Jun Cheng, Jintao Wu, Jin Zhang, Chengxi Zhao, Shunyi Tang, Xiaoyu School of Data Science and Engineering Xingzhi College South China Normal University Shanwei516600 China School of Physics South China Normal University Guangzhou510006 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Key Laboratory of Advanced Control for Light Industry Processes Ministry of Education Jiangnan University Wuxi214122 China School of Electronics and Information Engineering Xingzhi College South China Normal University Shanwei516600 China

In the fifth-generation (5G) era, eliminating communication interference sources is crucial for maintaining network performance. Interference often originates from unauthorized or malfunctioning antennas, and radio monitoring agencies must address numerous sources of such antennas annually. Unmanned aerial vehicles (UAVs) can improve inspection efficiency. However, the data transmission delay in the existing cloud-only (CO) artificial intelligence (AI) mode fails to meet the low latency requirements for real-time performance. Therefore, we propose a computer vision-based AI of Things (AIoT) system to detect antenna interference sources for UAVs. The system adopts an optimized edge-cloud collaboration (ECC+) mode, combining a keyframe selection algorithm (KSA), focusing on reducing end-to-end latency (E2EL) and ensuring reliable data transmission, which aligns with the core principles of ultra-reliable low-latency communication (URLLC). At the core of our approach is an end-to-end antenna localization scheme based on the tracking-by-detection (TBD) paradigm, including a detector (EdgeAnt) and a tracker (AntSort). EdgeAnt achieves state-of-the-art (SOTA) performance with a mean average precision (mAP) of 42.1% on our custom antenna interference source dataset, requiring only 3 million parameters and 14.7 GFLOPs. On the COCO dataset, EdgeAnt achieves 38.9% mAP with 5.4 GFLOPs. We deployed EdgeAnt on Jetson Xavier NX (TRT) and Raspberry Pi 4B (NCNN), achieving real-time inference speeds of 21.1 (1088) and 4.8 (640) frames per second (FPS), respectively. Compared with CO mode, the ECC+ mode reduces E2EL by 88.9%, increases accuracy by 28.2%. Additionally, the system offers excellent scalability for coordinated multiple UAVs inspections. The detector code is publicly available at https://***/SCNURISLAB/EdgeAnt. Copyright © 2024, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An Unstructured data Representation Enhanced Model for Postoperative Risk Prediction 21

An Unstructured Data Representation Enhanced Model for Posto...

引用

21st Chinese National Conference on Computational Linguistic, CCL 2022

作者： Wang, Yaqiang Yang, Xiao Hao, Xuechao Shu, Hongping Chen, Guo Zhu, Tao College of Software Engineering Chengdu University of Information Technology China Institute for Data Science and Engineering Chengdu University of Information Technology China Sichuan Key Laboratory of Software Automatic Generation and Intelligent Service China Department of Anesthesiology Sichuan University China

Postoperative risk prediction has a positive effect on clinical resource planning, emergency plan preparation and reducing postoperative risk and mortality. Postoperative risk prediction is mainly based on patient's basic information, laboratory tests, vital signs and other structured data, while the value of unstructured preoperative diagnosis with rich semantic information remains to be verified. Aiming at attempting this problem, an unstructured data representation enhanced postoperative risk prediction model is proposed in this paper. The model utilizes self-attention to fuse structured data with preoperative diagnosis. Through comparing with the commonly used statistical machine learning models and the state-of-the-art deep neural networks, the proposed model has not only better prediction performance, but also better interpretability. © 2022 China National Conference on Computational Linguistics Published under Creative Commons Attribution 4.0 International License.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Dstf: Enhancing Traffic Flow Prediction with a Diversified Spatio-Temporal Feature Extraction Model

SSRN

引用

SSRN 2024年

作者： Wang, Xing Wang, Xiaojun Zou, Fumin Liao, Lyuchao Jin, Biao Zeng, Ruihao Fujian Normal University College of Computer and Cyber Security China Fujian Normal University Digital Fujian Institute of Big Data Security Technology China Fujian University of Technology Fujian Key Laboratory of Automotive Electronic and Electrical Drive Technology China The University of Sydney School of Civil Engineering Sydney Australia

Traffic flow prediction stands as a pivotal focus within urban intelligent transportation systems, holding significant importance in enhancing road transport efficiency and ameliorating urban traffic conditions. However, due to the intricate nature of traffic patterns, predicting traffic flow poses profound challenges. To fully exploit the spatio-temporal features of traffic flow and enhance prediction precision, this paper proposes a diversified spatio-temporal feature extraction model (DSTF). This model extracts multiple spatio-temporal dependencies, thereby effectively enhancing its capability to improve the accuracy of traffic flow *** the spatial dimension, we construct two perspectives: geographical neighborhood and semantic similarity. Then we introduce geometric graph convolution networks (Geom-GCN) to capture local spatial dependencies within these viewpoints, aiming to comprehensively capture the complex and diverse spatial correlations within the urban road network. Subsequently, we utilize a spatial attention mechanism to capture dynamic global spatial dependencies, facilitating the learning of the global spatial structural patterns of urban traffic *** the time dimension, we employ the gated convolution-enhanced Res2Net architecture to capture time dependencies across various scales. This design ensures the model's capability to address both short-term and long-term time dependencies effectively. In addition to the aforementioned modules, our model utilizes a dynamic spatio-temporal synchronous aggregation module to extract spatio-temporal features simultaneously, enabling the capture of spatio-temporal correlations in traffic ***, we conduct experiments based on four real-world traffic datasets, namely PEMS03, PEMS04, PEMS07, and PEMS08, to validate the effectiveness of the proposed method. The results demonstrate that the proposed model outperforms the state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhicheng Chen Shibo Feng Zhong Zhang Xi Xiao Xingyu Gao Peilin Zhao Shenzhen International Graduate School Tsinghua University and Tencent AI Lab School of Computer Science and Engineering Nanyang Technological University Tencent AI Lab Shenzhen International Graduate School Tsinghua University and Key Laboratory of Data Protection and Intelligent Management (Sichuan University) Ministry of Education Institute of Microelectronics Chinese Academy of Sciences

ISBN: (纸本)9798331314385

The superior generation capabilities of Denoised Diffusion Probabilistic Models (DDPMs) have been effectively showcased across a multitude of domains. Recently, the application of DDPMs has extended to time series generation tasks, where they have significantly outperformed other deep generative models, often by a substantial margin. However, we have discovered two main challenges with these methods: 1) the inference time is excessively long; 2) there is potential for improvement in the quality of the generated time series. In this paper, we propose a method based on discrete token modeling technique called Similarity-driven Discrete Transformer (SDformer). Specifically, SDformer utilizes a similarity-driven vector quantization method for learning high-quality discrete token representations of time series, followed by a discrete Transformer for data distribution modeling at the token level. Comprehensive experiments show that our method significantly outperforms competing approaches in terms of the generated time series quality while also ensuring a short inference time. Furthermore, without requiring retraining, SDformer can be directly applied to predictive tasks and still achieve commendable results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Enhanced Perception and Attention-Driven Person Re-Identification

Research on Enhanced Perception and Attention-Driven Person ...

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Cancan Wu Dong Li Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan Hubei China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

When matching similarity among pedestrians in images, pedestrian re-identification algorithms are often disturbed by occlusions. A typical tactic is to improve the robustness of occlusion features in the model. However, this approach neglects the noise introduced by other pedestrians in the image, leading to limited learning of relevant information between images. To address these issues, this paper introduces a pedestrian re-identification model that leverages perception-enhanced and attention mechanisms. By enhancing the perception of non-pedestrian noise and erasing non-pedestrian features, we then employ a cross-attention mechanism to subtly embed global and local features for finer feature recognition. Finally, through context attention, we learn the interaction between pedestrian images to improve re-identification accuracy. Results from studies performed on the Market-1501, CUHK03-D, and Duke-ReID datasets indicate that the suggested model surpasses leading contemporary models regarding Rank-1 scores and mean Average Precision (mAP), while maintaining good robustness.

关键词： Pedestrians Accuracy Attention mechanisms Computational modeling Noise knowledge discovery Robustness Noise measurement Identification of persons Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Steel Surface Defect Detection Based on Improved YOLOv8

Steel Surface Defect Detection Based on Improved YOLOv8

引用

International Conference on Fuzzy Systems and knowledge Discovery (FSKD)

作者： Jichen Zhang Zhi Zhang College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan Hubei China Big Data Science and Engineering Research Institute Wuhan University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350356328

ISBN: (纸本)9798350356335

There are some defects on the surface of steel that are difficult to detect, so we propose an improved algorithm based on YOLOv8 for detecting defects that are difficult to be detected. This improvement includes the introduction of an SPD module to minimize the problem of information loss due to downsampling; the addition of a small object detection head combined with EMA attention to further enhance the detection capabilities for small targets; the use of BiFPN to replace the original PANet, applying different weights to different features to strengthen feature fusion. Experiments were conducted on the NEU-DET dataset, and the algorithm improved mAP to 80.2%, an improvement of 3.9% over the baseline model.

关键词： Convolution Computational modeling Object detection Feature extraction knowledge discovery Steel data mining Background noise Defect detection Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

Research on Ornamental Fish Recognition Base on Improved Shufflenet V2 Network

Research on Ornamental Fish Recognition Base on Improved Shu...

引用

Big data & Artificial Intelligence & Software engineering (ICBASE), International Conference on

作者： Xingyun Zhang Hongming Chen Longqing Zhang Qian Chen Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China School of Computer Science Guangdong University of Science and Technology Dongguan China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China

With the advancement of computer vision technology, fish recognition plays a crucial role in various fields such as aquaculture processing and disseminating fish knowledge. In this study, we propose an enhanced and lightweight fish recognition algorithm to accomplish fish classification recognition with limited data samples. Based on the ShuffleNet V2 network, we incorporate Transfer Learning and the SE attention mechanism. Additionally, we replace the ReLu activation function with the AM-Softmax activation function. Comparative evaluations are conducted against Resnet50, MobileNet V2, MobileNet V3, and the original ShuffleNet V2 network model. Our experimental findings demonstrate that the proposed algorithm outperforms the aforementioned models, resulting in recognition accuracy improvements of 16.01%, 19.05%, 15.04%, and 14.44% respectively. The final recognition accuracy achieved is 97.20%, successfully attaining the desired outcome.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MagLive: Robust Voice Liveness Detection on Smartphones Using Magnetic Pattern Changes

arXiv

引用

arXiv 2024年

作者： Sun, Xiping Chen, Jing Wu, Cong He, Kun Xu, Haozhe Feng, Yebo Du, Ruiying Chen, Xianhao Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan430072 China Rizhao Institute of Information Technology Wuhan University Rizhao276800 China School of Computer Science and Engineering Nanyang Technological University Singapore Collaborative Innovation Center of Geospatial Technology Wuhan430079 China The Department of Electrical and Electronic Engineering HKU Musketeers Foundation Institute of Data Science University of Hong Kong Pok Fu Lam Hong Kong

Voice authentication has been widely used on smartphones. However, it remains vulnerable to spoofing attacks, where the attacker replays recorded voice samples from authentic humans using loudspeakers to bypass the voice authentication system. In this paper, we present MagLive, a robust voice liveness detection scheme designed for smartphones to mitigate such spoofing attacks. MagLive leverages the differences in magnetic pattern changes generated by different speakers (i.e., humans or loudspeakers) when speaking for liveness detection, which are captured by the built-in magnetometer on smartphones. To extract effective and robust magnetic features, MagLive utilizes a TF-CNN-SAF model as the feature extractor, which includes a time-frequency convolutional neural network (TF-CNN) combined with a self-attention-based fusion (SAF) model. Supervised contrastive learning is then employed to achieve user-irrelevance, device-irrelevance, and content-irrelevance. MagLive imposes no additional burden on users and does not rely on active sensing or specialized hardware. We conducted comprehensive experiments with various settings to evaluate the security and robustness of MagLive. Our results demonstrate that MagLive effectively distinguishes between humans and attackers (i.e., loudspeakers), achieving an average balanced accuracy (BAC) of 99.01% and an equal error rate (EER) of 0.77%. Copyright © 2024, The Authors. All rights reserved.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

arXiv

引用

arXiv 2024年

作者： Ye, Maoyuan Zhang, Jing Liu, Juhua Liu, Chenyu Yin, Baocai Liu, Cong Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China IFLYTEK Research IFLYTEK CO. LTD. China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue 639798 Singapore

The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset. Subsequently, with these complete labels, we launch the end-to-end trainable Hi-SAM based on the TS architecture with a customized hierarchical mask decoder. During inference, Hi-SAM offers both automatic mask generation (AMG) mode and promptable segmentation (PS) mode. In the AMG mode, Hi-SAM segments pixel-level text foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing. As for the PS mode, Hi-SAM provides word, text-line, and paragraph masks with a single point click. Experimental results show the state-of-the-art performance of our TS model: 84.86% fgIOU on Total-Text and 88.96% fgIOU on TextSeg for pixel-level text segmentation. Moreover, compared to the previous specialist for joint hierarchical detection and layout analysis on HierText, Hi-SAM achieves significant improvements: 4.73% PQ and 5.39% F1 on the text-line level, 5.49% PQ and 7.39% F1 on the paragraph level layout analysis, requiring 20× fewer training epochs. The code is available at Hi-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Masks

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：