检索结果-内蒙古大学图书馆

Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning

引用

IEEE Internet of Things Journal 2024年第12期11卷 21347-21358页

作者： Khan, Muhammad Waseem Obaidat, Mohammad S. Mahmood, Khalid Batool, Dania Badar, Hafiz Muhammad Sanaullah Aamir, Muhammad Gao, Wu Comsats University Islamabad Sahiwal Campus Department Of Computer Science Sahiwal57000 Pakistan Superior University Department Of Computer Science Lahore54000 Pakistan The University Of Jordan King Abdullah Ii School Of Information Technology Amman11942 Jordan University Of Science And Technology Beijing School Of Communication And Computing Engineering Beijing100083 China Amity University Amity School Of Engineering And Technology Uttar Pradesh Noida201301 India National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan University Of Palermo Department Of Engineering Palermo90133 Italy Emerson University Department Of Emerging Computing Technologies Multan60000 Pakistan Northwestern Polytechnical University Center For Bio-Inspired System-on-Chip School Of Computer Science Xi'an710060 China

Road damage detection (RDD) through computer vision and deep learning techniques can ensure the safety of vehicles and humans on the roads. Integrating unmanned aerial vehicles (UAVs) in RDD and infrastructure evaluation (IE) has also emerged as a key enabler, contributing significantly to data acquisition and real-time monitoring of road damages, such as potholes, cracks, and surface anomalies, facilitating proactive maintenance and improved road conditions. These UAVs are low-powered and resource-constrained devices that work autonomously to perform pattern detection and decision making leveraging tiny machine learning (Tiny ML) algorithms. These Tiny ML algorithms are designed to run on edge devices, IoT devices, UAVs, etc. In this study, the RDD2022 data set collected using UAVs and dashboard cameras of vehicles was utilized to train pure and mixed models that exhibit class instance imbalance in certain classes which is addressed by implementing data augmentation as a regularization technique. State-of-the-art two-stage detectors: Faster R-CNN ResNet101 and one-stage detectors: SSD MobileNet V1 FPN, YOLOv5, and Efficientdet D1 are employed. The results indicate that the two-stage detector achieved an impressive mean average precision (mAP) of 88.49% overall and 96.62% for focused classes. Notably, the state-of-the-art Efficientdet D1 approach achieved a competitive mAP of 86.47% overall and 95.12% for focused classes, with significantly lower computational cost. These findings highlight the potential of advanced object detection techniques, particularly Efficientdet D1, to enhance the accuracy and efficiency of RDD systems, thereby improving passenger safety and overall performance. © 2014 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Representation learning via an integrated autoencoder for unsupervised domain adaptation

引用

Frontiers of computer science 2023年第5期17卷 75-87页

作者： Yi ZHU Xindong WU Jipeng QIANG Yunhao YUAN Yun LI School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230601China

The purpose of unsupervised domain adaptation is to use the knowledge of the source domain whose data distribution is different from that of the target domain for promoting the learning task in the target *** key bottleneck in unsupervised domain adaptation is how to obtain higher-level and more abstract feature representations between source and target domains which can bridge the chasm of domain ***,deep learning methods based on autoencoder have achieved sound performance in representation learning,and many dual or serial autoencoderbased methods take different characteristics of data into consideration for improving the effectiveness of unsupervised domain ***,most existing methods of autoencoders just serially connect the features generated by different autoencoders,which pose challenges for the discriminative representation learning and fail to find the real cross-domain *** address this problem,we propose a novel representation learning method based on an integrated autoencoders for unsupervised domain adaptation,called *** capture the inter-and inner-domain features of the raw data,two different autoencoders,which are the marginalized autoencoder with maximum mean discrepancy(mAE)and convolutional autoencoder(CAE)respectively,are proposed to learn different feature *** higher-level features are obtained by these two different autoencoders,a sparse autoencoder is introduced to compact these inter-and inner-domain *** addition,a whitening layer is embedded for features processed before the mAE to reduce redundant features inside a local *** results demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.

关键词： unsupervised domain adaptation representation learning marginalized autoencoder convolutional autoen-coder sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Towards Better Accuracy-Efficiency Trade-Offs: Dynamic Activity Inference via Collaborative Learning From Various Width-Resolution Configurations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6723-6738页

作者： Qin, Lutong Zhang, Lei Li, Chengrun Song, Chaoda Cheng, Dongzhou Wang, Shuoyuan Wu, Hao Song, Aiguo Nanjing Normal University School of Electrical and Automation Engineering Nanjing210023 China Shanghai200240 China Case Western Reserve University Department of Computer and Data Sciences ClevelandOH44106 United States University of Macau Department of Computer and Information Science Taipa999078 China Yunnan University School of Information Science and Engineering Kunming650500 China Southeast University Department of Instrument Science and Engineering Nanjing210096 China

Recently, deep neural networks have triumphed over a large variety of human activity recognition (HAR) applications on resource-constrained mobile devices. However, most existing works are static and ignore the fact that the computational budget usually changes drastically across various devices, which prevent real-world HAR deployment. It still remains a major challenge: how to adaptively and instantly tradeoff accuracy and latency at runtime for on-device activity inference using time series sensor data? To address this issue, this article introduces a new collaborative learning scheme by training a set of subnetworks executed at varying network widths when fueled with different sensor input resolutions as data augmentation, which can instantly switch on-the-fly at different width-resolution configurations for flexible and dynamic activity inference under varying resource budgets. Particularly, it offers a promising performance-boosting solution by utilizing self-distillation to transfer the unique knowledge among multiple width-resolution configuration, which can capture stronger feature representations for activity recognition. Extensive experiments and ablation studies on three public HAR benchmark datasets validate the effectiveness and efficiency of our approach. A real implementation is evaluated on a mobile device. This discovery opens up the possibility to directly access accuracy-latency spectrum of deep learning models in versatile real-world HAR deployments. © 2020 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Generative Multimodal data Augmentation for Low-Resource Multimodal Named Entity Recognition 24

Generative Multimodal Data Augmentation for Low-Resource Mul...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Ziyan Yu, Jianfei Yang, Jia Wang, Wenya Yang, Li Xia, Rui School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Wee Kim Wee School of Communication and Information Nanyang Technological University Singapore

ISBN: (纸本)9798400706868

As an important task in multimodal information extraction, Multimodal Named Entity Recognition (MNER) has recently attracted considerable attention. One key challenge of MNER lies in the lack of sufficient fine-grained annotated data, especially in low-resource scenarios. Although data augmentation is a widely used technique to tackle the above issue, it is challenging to simultaneously generate synthetic text-image pairs and their corresponding high-quality entity annotations. In this work, we propose a novel Generative Multimodal data Augmentation (GMDA) framework for MNER, which contains two stages: Multimodal Text Generation and Multimodal Image Generation. Specifically, we first transform each annotated sentence into a linearized labeled sequence, and then train a Label-aware Multimodal Large Language Model (LMLLM) to generate the labeled sequence based on a label-aware prompt and its associated image. We further employ a Stable Diffusion model to generate the synthetic images that are semantically related to these sentences. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed GMDA framework, which consistently boosts the performance of several competitive methods for two subtasks of MNER in both full-supervision and low-resource settings. The low-resource dataset and source code are released at https://***/NUSTM/GMDA. © 2024 ACM.

关键词： data augmentation

来源：评论

学校读者我要写书评

暂无评论

Causal fMRI-Mamba: Causal State Space Model for Neural Decoding and Brain Task States Recognition

Causal fMRI-Mamba: Causal State Space Model for Neural Decod...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Deng, Weihao Han, Fei Ling, Qinghua Liu, Qing Han, Henry School of Computer Science and Communication Engineering JiangSu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China School of Computer Jiangsu University of Science and Technology China School of Electronic and Information Engineering West Anhui University China School of Engineering and Computer Science Baylor University United States

ISBN: (纸本)9798350368741

Deep learning advances neural decoding in functional magnetic resonance imaging (fMRI) tasks with convolution and attention-based methods. However, these methods struggle with capturing global spatiotemporal information due to high dimensionality, noise and inter-individual difference of fMRI, which also increase computational complexity and prior bias. To this end, a novel causal state space model, Causal fMRI-Mamba, is proposed for neural decoding and task state mapping. It effectively captures global spatiotemporal information via eliminating local redundancies and capturing long-distance dependencies. Meanwhile, a causal representation framework is designed to extract invariant high-order features and disentangle related causal features, enhancing model performance. Furthermore, a dense connection module is expanded to prevent significant causal information loss in hidden states of inter layers. On the HCP brain task state classification task, Causal fMRI-Mamba achieves better performance and generalization than comparison methods. © 2025 IEEE.

关键词： causal representation learning Neuro-decoding state space model task-based fMRI

来源：评论

学校读者我要写书评

暂无评论

Harnessing Large Language Models for Text-Rich Sequential Recommendation 24

Harnessing Large Language Models for Text-Rich Sequential Re...

引用

33rd ACM Web Conference, WWW 2024

作者： Zheng, Zhi Chao, WenShuo Qiu, Zhaopeng Zhu, Hengshu Xiong, Hui School of Data Science University of Science and Technology of China China Career Science Lab BOSS Zhipin China China China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400701719

Recent advances in Large Language Models (LLMs) have been changing the paradigm of Recommender Systems (RS). However, when items in the recommendation scenarios contain rich textual information, such as product descriptions in online shopping or news headlines on social media, LLMs require longer texts to comprehensively depict the historical user behavior sequence. This poses significant challenges to LLM-based recommenders, such as over-length limitations, extensive time and space overheads, and suboptimal model performance. To this end, in this paper, we design a novel framework for harnessing Large Language Models for Text-Rich Sequential Recommendation (LLM-TRSR). Specifically, we first propose to segment the user historical behaviors and subsequently employ an LLM-based summarizer for summarizing these user behavior blocks. Particularly, drawing inspiration from the successful application of Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) models in user modeling, we introduce two unique summarization techniques in this paper, respectively hierarchical summarization and recurrent summarization. Then, we construct a prompt text encompassing the user preference summary, recent user interactions, and candidate item information into an LLM-based recommender, which is subsequently fine-tuned using Supervised Fine-Tuning (SFT) techniques to yield our final recommendation model. We also use Low-Rank Adaptation (LoRA) for Parameter-Efficient Fine-Tuning (PEFT). We conduct experiments on two public datasets, and the results clearly demonstrate the effectiveness of our approach. © 2024 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Simulated Annealing BP Algorithm for Adaptive Temperature Setting 14th

A Simulated Annealing BP Algorithm for Adaptive Temperature ...

引用

14th International Symposium on Intelligence Computation and Applications, ISICA 2023

作者： Teng, Zi Liang, Zhixun Li, Yuanxiang Yi, Yunfei School of Mathematics and Statistics Central South University Hunan Changsha410083 China School of Big Data and Computer Hechi University Guangxi Yizhou546300 China School of Computer Science Wuhan University Hubei Wuhan430072 China

ISBN: (纸本)9789819743957

The backpropagation (BP) algorithm is so far, the most effective algorithm for neural network learning and training. This algorithm is based on the fast gradient descent method in optimization theory, which is essentially a deterministic local optimization algorithm. In this paper, for improving its local optimization, enhancing its global optimization potential ability is discussed by combining with the simulated annealing mechanism. The BP algorithm is utilized as the core component under the framework of simulated annealing algorithm, and the Metropolis criterion is used as the heuristic strategy. Integrating advantages of the BP algorithm and the simulated annealing algorithm, An adaptive simulated annealing based BP algorithm is designed. In this algorithm there two adaptive strategies, one is the setting of annealing temperature, and the other is the random perturbation of connection weight and bias value. The adaptive temperature setting can simultaneously reflect changes of the loss function value, and the adaptive perturbation is related to the network complexity and loss function value. By using the small batch gradient descent method used in machine learning commonly, the update of the annealing temperature is synchronized with the input sample batch, which follows up the search state of the algorithm running. The perturbed renewal of those parameters of the neural network is based on the current network configuration to avoid blind random perturbation. The algorithm is tested with the Fashion-MNIST and CIFAR-10 datasets, which are widely used in the current deep learning research field. The classification and recognition accuracies of the algorithm exceed 99% both. These results are better than the best results reported currently for the two datasets. In addition, the adaptive BP algorithm is repeated 30 times with these two datasets respectively. The statistical analysis results show the robustness and stability of the algorithm. © The Author(s), under

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Model for Heterogeneous dataset Analysis - Application to Winter Wheat Crop Yield Prediction 8th

A Deep Learning Model for Heterogeneous Dataset Analysis - A...

引用

8th International Conference on Information, Communication and Computing Technology, ICICCT 2023

作者： Bansal, Yogesh Lillis, David Kechadi, M.-Tahar School of Computer Science University College Dublin Dublin Ireland Insight Centre for Data Analytics Dublin Ireland

ISBN: (纸本)9783031438370

Western countries rely heavily on wheat, and yield prediction is crucial. Time-series deep learning models, such as Long Short Term Memory (LSTM), have already been explored and applied to yield prediction. Existing literature reports that they perform better than traditional Machine Learning (ML) models. However, the existing LSTM cannot handle heterogeneous datasets (a combination of data that varies and remains static with time). In this paper, we propose an efficient deep learning model that can deal with heterogeneous datasets. We developed the system architecture and applied it to the real-world dataset in the digital agriculture area. We showed that it outperformed the existing ML models. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Method of Advanced Persistent Threat data Processing Based on Ensemble Learning 9

A Method of Advanced Persistent Threat Data Processing Based...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Wang, Xuelong Zheng, Xin Tu, Yang School of Computer Science Xi'an Shiyou University Shaanxi Xi'an China Xi'an Shiyou University Internet data center Shaanxi Xi'an China

ISBN: (纸本)9798350376548

Finding the features with the highest correlation degree in the source APT data from network security devices is essential for preprocessing the data in order to train models that will increase the accuracy of APT attack classification. The preprocessing, cleaning, and feature transformation of the dataset are the first steps in the application of data mining techniques in this work. VarianceThreshold is ultimately chosen for feature selection to create the optimal feature subset after a range of feature selection techniques are used for experimental comparison. The best feature subset is then used to compare and evaluate several machine learning algorithms, and by integrating ensemble learning methods, the VT-stacking model is recommended. The experimental results demonstrate that the VT-stacking model developed in this paper achieves 97.3% accuracy in categorizing APT assaults after preprocessing the APT data. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Generative Forgery Image Detection Based on Diffusion Reconstruction Loss and Frequency Domain Feature 11

Generative Forgery Image Detection Based on Diffusion Recons...

引用

11th IEEE International Conference on Behavioural and Social Computing, BESC 2024

作者： Hu, Xinyang Haihong, E. Liu, Jianhua Hu, Tianyi Qiao, Xiaodong Ding, Junpeng Huang, Jiayu School of Computer Science Beijing University of Posts and Telecommunications Beijing China Beijing Wanfang Data Co. Ltd. Beijing China

ISBN: (纸本)9798331531904

Since the advent of generative models such as Generative Adversarial Networks (GANs), image generation techniques have made significant progress in the field of digital image processing. However, the development of these techniques has also brought about challenges in research integrity, especially the growing problem of forged images in research papers. Currently, there are no mature research results related to the generation of forged image detection in the field of research integrity detection. Existing detection techniques are difficult to adapt to the rapidly evolving image generation models, especially when dealing with research paper images that have a single structure and are quickly learned by the generation models. Existing methods fail to effectively identify high-quality forged images produced by advanced generative models, which poses a severe threat to scientific integrity. In this study, we propose a new detection method that combines diffusion reconfiguration loss and frequency-domain features to identify and differentiate generative forged images from fundamental scientific research images. We developed a technique to detect frequency-domain artifacts specific to generated images using frequency-domain analysis and combined it with image reconstruction error features of the diffusion model to enhance the accuracy and robustness of detection. Through testing on a newly constructed public dataset, our method shows superior performance in effectively identifying forged images produced by multiple generative models. © 2024 IEEE.

关键词： Generative adversarial networks

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：