检索结果-内蒙古大学图书馆

13th International Conference on information Technology in Medicine and Education, ITME 2023

作者： Chen, Jinjian Li, Zuoyong Lai, Taotao Xie, Huosheng College of Computer and Data Science Fuzhou University Fuzhou350108 China College of Computer and Control Engineering Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China

ISBN: (纸本)9798350319156

Establishing dense correspondences between semantically similar images is a challenging task. Cost aggregation is a crucial step in finding correct dense correspondences, with the goal of optimizing the initial correlation map thereby removing the ambiguity of the correspondences. Current approaches use transformer architectures for cost aggregation, which lack local priors to adequately capture the local information contained in the correlation map. We propose to incorporate peripheral position coding into the transformer to explore the local information to obtain the matching set and call it the Peripheral Transformer Matcher (PTM). This coding technique partitions the overall receptive field of the self-attention mechanism into diverse peripheral regions, each with its own set of weights. By doing this, the proposed PTM gets a specific local prior by adding an inductive bias to the transformer models and making the initial correlation map less confusing. In addition, a local self-attention module is used to enhance the image features and obtain an enhanced initial correlation map. Comparisons of the experimental results with baselines on public datasets demonstrate the effectiveness of the proposed PTM. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年 27卷 3716-3728页

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： information leakage

来源：评论

学校读者我要写书评

暂无评论

Edge Intelligence Based Garbage Classification Detection Method 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Zhu, Ruijia Liu, Yiwen Gao, Yanxia Shi, Yuanquan Peng, Xiaoning School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

To address the problem that the classification and cleaning of garbage in city streets is always ineffective nowadays, the paper proposes a garbage detection method based on edge intelligence. The edge intelligence not only reduces the computational load of the cloud and speeds up the data transmission, but also greatly reduces the data transmission cost. First, images of city streets are collected and uploaded to the edge device via mobile devices in various locations in the city. Then, the edge server is used to temporarily store the image information, and the PeleeNet model deployed on it is used to identify and classify various kinds of garbage, and then visualize the information of each street. Finally, the street garbage information is transmitted to the cloud, which provides a detailed picture of the city’s garbage situation and facilitates city management. In this paper, the PeleeNet model is compared with ResNet, DenseNet and MobileNet models. The results show that the edge devices equipped with PeleeNet model not only have the fastest computation speed and the highest accuracy, but also occupy the least memory. It is fully demonstrated that the method studied in the paper can be applied to the problem of litter detection in urban streets. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Prediction for Surface Subsidence of Shield Construction in Water-Rich Sand Egg Stratum Based on Edge Intelligence 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Gao, Yanxia Liu, Yiwen Mi, Chunqiao Tang, Pengju Shi, Yuanquan School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

The refinement and intelligent control of shield tunneling is the development trend of modern tunnel construction technology. In order to better predict and control the surface subsidence caused by shield excavation, this paper takes the shield construction of Luoyang Metro Line 2 from Longmen Station to Longmen Avenue Station as the background, and proposes a method based on edge intelligence for shield construction in water-rich sand egg strata. Methods for predicting land subsidence. First, low latency and faster data processing are achieved by collecting a large amount of data containing dynamic information about geological conditions and surrounding environments during the shield tunneling process;then using the iFogSim simulator to create different configurations;second, establishing support A surface subsidence model based on vector regression was established, and the model was deployed on the edge equipment;finally, the model was evaluated using the monitoring data of surface subsidence of the water-rich sand egg formation in Luoyang area. The research results show that the edge computing-based system has lower latency and higher processing speed than only deploying cloud data centers. After Pearson-related parameter tuning and model comparison training with Linear as the kernel function, the mean square error of the predicted value and the collected value of the surface subsidence is better than the other two kernel functions. The method proposed in this paper can provide real-time prediction service for large-scale surface subsidence prediction caused by shield construction, and is more practical. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Course Homework Metaverse Based on Extended Reality Under Edge Computing 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Fu, Jinrong Liu, Yiwen Yan, Haobo Gao, Yanxia Xiao, Jianhua School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

The metaverse originated from science fiction at first, but it gradually came into reality with the continuous power of technology. Aiming at the problems of course work in Chinese universities, such as its function is weakened or suppressed, its form is too abstract, and it lacks elaborate design, this paper proposes a design method of course work meta-universe based on extended reality under edge computing. XR technology is used to realize the interactive immersion of the coursework meta-universe, in order to improve students’ learning enthusiasm and ability to solve abstract problems. Based on the international perspective, this paper systematically combs and analyzes the integration architecture, application scenarios and future trends of the meta-universe education application based on Edge computing (MEC). Four key processes are described: teacher-student interaction, data collection, data feedback and comprehensive evaluation. In order to promote the application of the metaverse in the field of education to provide mirror. The validity of the method is illustrated by the data. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Highly Accurate Dynamic Gesture Recognition Method Based on Edge Intelligence 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Changkai, Lu Yiwen, Liu Yanxia, Gao Yuanquan, Shi Xiaoning, Peng School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

In recent years, gestures have been widely used in many fields. For example, human-computer interaction, virtual reality, gesture translation, etc. The reason for its rapid development is due to the emergence of deep learning and artificial intelligence under today’s society. Due to dynamic gestural interactions, such large intelligent models are often characterized by many parameters, large sample size, frequent parameter updates, and high communication volume. Based on this feature, we propose a cloud-based edge design architecture approach for gesture recognition based on an improved YOLOv5 network model optimization by changing different gestures, background interference, which uses a 21-layer model for the neural network. With the use of edge intelligence, the computational accuracy can be improved by 10.6% over the traditional YOLOv5 with a MAP value of 93.3%. The final recall rate is also improved by 3.6%. The parameter model is only 43.6% of the original one. This shows the practicality and operability of using edge computing as a technique in gesture recognition, as well as the small improvement cost and obvious effect. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Rethinking Distribution Alignment for Inter-class Fairness 1

引用

1st International Conference on Artificial Intelligence Security and Privacy, AIS and P 2023

作者： Ye, Jinhuang Wu, Jiawei Li, Zuoyong Zheng, Xianghan College of Computer and Big Data Fuzhou University Fuzhou350108 China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518107 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China

ISBN: (数字)9789819997886

ISBN: (纸本)9789819997879

Semi-supervised learning (SSL) is a successful paradigm that can use unlabelled data to alleviate the labelling cost problem in supervised learning. However, the excellent performance brought by SSL does not transfer well to the task of class imbalance. The reason is that the class bias of pseudo-labelling further misleads the decision boundary. To solve this problem, we propose a new plug-and-play approach to handle the class imbalance problem based on a theoretical extension and analysis of distribution alignment. The method, called Basis Transformation Based Distribution Alignment (BTDA), efficiently aligns class distributions while taking into account inter-class *** implements the basis transformation through a learnable transfer matrix, thereby reducing the performance loss caused by pseudo-labelling biases. Extensive experiments show that our proposed BTDA approach can significantly improve performance in class imbalance tasks in terms of both accuracy and recall metrics when integrated with advanced SSL algorithms. Although the idea of BTDA is not complex, it can show advanced performance on datasets such as CIFAR and SVHN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

LSTM-based Pedestrian Trajectory Prediction Model under the General Direction Mechanism: DIR-LSTM 3

LSTM-based Pedestrian Trajectory Prediction Model under the ...

引用

3rd International Conference on Electronic informationTechnology and Smart Agriculture, ICEITSA 2023

作者： Luo, Junyuan Fu, Qiongfang Xiao, Jianhua Xiao, Hongbo Liao, Jiyong School of Computer Science and Engineering Huaihua University Hunan Huaihua China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing Application in Hunan Province Universities Hunan Huaihua China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9798400716775

Accurate prediction of future traffic flow trends is essential to solve urban transportation problems. However, traffic flow prediction faces great challenges due to the multimodal nature of pedestrian behavior and the complexity of the traffic environment. Although a large number of studies have been conducted to investigate these issues in depth, there are still some limitations. In order to address these challenges more effectively, we propose a pedestrian trajectory prediction model based on long-short-term memory networks (LSTMs): the DIR-LSTM. The model introduces an innovative generalized direction mechanism and a self-attention mechanism, which captures pedestrian movement patterns more comprehensively and accurately by predicting overall directional movements first and then gradually subdividing them into individual directions of movement. The DIR-LSTM is designed to address the challenges posed by the diversity of pedestrian behaviors and the complexity of urban environments. To validate the state-of-the-art of the model, we conducted experiments using the publicly available ETH [10] and UCY [9] datasets. The experiments demonstrate that DIR-LSTM performs better in terms of accuracy compared to other models, providing a more reliable prediction tool for future urban traffic management. © 2023 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Based User Scheduling for Real-Time Multimedia Tasks in Edge Devices 1

引用

3rd EAI International Conference on Edge Computing and IoT, EAI ICECI 2022

作者： Wen, Wenkan Liu, Yiwen Gao, Yanxia Zhu, Zhirong Shi, Yuanquan Peng, Xiaoning School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

Edge networks are highly volatile and the quality of device communication and computational resources change not only over time but also according to the movement of users. Current federation learning suffers from poor device network state and failure of devices to upload models in a timely manner. To address these problems, an intelligent scheduling mechanism that uses the predicted device state based on device information to select the appropriate device for federated learning is proposed in this paper. By focusing on information such as communication quality, computational resources, and location information, the information of edge devices is collected to analyze and predict the device network and computing resources to further analyze the state of devices in depth. Experiments are conducted on real datasets, and the experimental results show that the proposed scheduling method can make the global model fit faster than without the algorithm, which significantly improves the training efficiency of federated learning. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Machine learning

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：