Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things最新文献_第8页

Human Activity Classification Based on Data Analysis and Feature Extraction 基于数据分析和特征提取的人类活动分类

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603915

Qiao Liang, Cheng Hu, Haiyan Huang

引用次数: 0

Open Set Domain Adaptation with Zero-shot Learning on Graph 图上零点学习的开集域自适应

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603854

Xinyue Zhang, Xu Yang, Zhiyong Liu

{"title":"Open Set Domain Adaptation with Zero-shot Learning on Graph","authors":"Xinyue Zhang, Xu Yang, Zhiyong Liu","doi":"10.1145/3603781.3603854","DOIUrl":"https://doi.org/10.1145/3603781.3603854","url":null,"abstract":"Open set domain adaptation focuses on transferring the information from a richly labeled domain called source domain to a scarcely labeled domain called target domain, while classifying the unseen target samples as one unknown class in an unsupervised way. Compared with the close set domain adaptation, where the source domain and the target domain share the same class space, the classification of the unknown class makes it easy to adapt to the real environment. Particularly, after the recognition of the unknown samples, the model can either ask for manually labeling or further develop the classification ability of the unknown classes based on pre-stored knowledge. Inspired by this idea, we propose a model for open set domain adaptation with zero-shot learning on the unknown classes in this paper. We utilize adversarial learning to align the two domains while rejecting the unknown classes. Then the knowledge graph is introduced to generate the classifiers for the unknown classes with the employment of the graph convolution network (GCN). Thus the classification ability of the source domain is transferred to the target domain, and the model can distinguish the unknown classes in detail with prior knowledge. We evaluate our model on digits datasets and the result shows superior performance.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116112444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Few-shot Object Counting and Detection with Query-Guided Attention 基于查询引导注意力的小镜头目标计数和检测

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603865

Yuhao Lin

{"title":"Few-shot Object Counting and Detection with Query-Guided Attention","authors":"Yuhao Lin","doi":"10.1145/3603781.3603865","DOIUrl":"https://doi.org/10.1145/3603781.3603865","url":null,"abstract":"The focus of this paper is on Few-Shot Counting and Detection (FSCD), a task that involves counting and localizing target objects based on a few exemplar bounding boxes. In particular, we address two major challenges in developing a FSCD model: the high cost of bounding box labeling and the large variations in object appearance. To mitigate the former issue, we propose a neighbor distance-aware mechanism for generating pseudo bounding boxes. This mechanism utilizes neighboring objects as context to estimate the location and size of the target object without requiring training. To address the challenge of appearance variation, we introduce a novel query-guided attention module that enhances the visual features of the search image by employing multi-head cross attention with query features. The module is designed to encourage attentive inspection of the search image by directing the model to focus more on regions that share similarities with the target objects. We integrate the query-guided attention module into the Faster-RCNN object detection model, resulting in a new few-shot object detector named Counting-RCNN. The proposed approach outperforms the state-of-the-art method on a large-scale FSCD147 dataset, achieving 0.60 MAE, 5.36 RMSE, and 13.01% AP50 improvement.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121850759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Timed Calculus with Mobility for Wireless Networks 无线网络中具有移动性的时间演算

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603896

Wanling Xie, Huibiao Zhu, Xi Wu

引用次数: 0

Speech emotion recognition algorithm based on bimodality and attention mechanism 基于双峰和注意机制的语音情感识别算法

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603919

Huangshui Hu, Hongyu Sun, Peisong Xie, Nanhao Shen, Mei Han

引用次数: 0

Towards Effective Crowd-Assisted Similarity Retrieval of Large Cursive Chinese Calligraphic Character Images 基于群体辅助的大型草书汉字图像相似度检索

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603853

Haohong Li, Zhuang Yi, Yujia Ge, Tao Lou

引用次数: 0

Research and design of distributed testing framework for 5G network 5G网络分布式测试框架的研究与设计

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603878

Yugang He, Fengli Wang, Qian Sun, Lin Tian, Yuanyuan Wang

引用次数: 0

Complementary Disentangling and Dynamic Graph Convolution for Skeleton Based Action Recognition 基于骨架的动作识别的互补解缠和动态图卷积

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603866

Kemin Shi, Lin Xu

{"title":"Complementary Disentangling and Dynamic Graph Convolution for Skeleton Based Action Recognition","authors":"Kemin Shi, Lin Xu","doi":"10.1145/3603781.3603866","DOIUrl":"https://doi.org/10.1145/3603781.3603866","url":null,"abstract":"In this study, we introduce a novel skeleton-based action recognition approach, the Complementary Disentangling and Dynamic Graph Convolution Network (CDD-GCN). This method combines multi-scale graph convolution and multi-head self-attention to model human body structure and motion characteristics. We employ a complementary disentangle neighbor-hoods method to generate multi-scale graphs, which eliminates the redundant dependency on nearby nodes when receiving information from distant nodes while maximally preserving the structural features of the human skeleton. In accordance with the characteristics of human skeletal sequences, we improve the self-attention mechanism by introducing temporal pooling, semantic information, graph importance tuning matrix, and high-probability graph dropout into the dynamic graph generation process, achieving more effective action connections with lower computational complexity. We integrate the self-attention mechanism with the graph convolution process at the feature level, enabling independent learning and better performance of both, and modify the multi-head feature aggregation method of self-attention to be consistent with the graph convolution process, facilitating smoother subsequent fusion. Experimental results demonstrate that the CDD-GCN achieves the state-of-the-art performance on two large-scale datasets, NTU RGB+D 60 and 120, exemplified by a 92.7% accuracy on the cross-subject benchmark of NTU RGB+D 60, while maintaining low computational costs.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"341 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124215059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ring Oscillator based on Integer Dynamic Programming 基于整数动态规划的环形振荡器

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603899

Siyuan Cheng, Xiafei Yang, Congrui Bai, Honglei Zhou, Junshuo Ai

{"title":"Ring Oscillator based on Integer Dynamic Programming","authors":"Siyuan Cheng, Xiafei Yang, Congrui Bai, Honglei Zhou, Junshuo Ai","doi":"10.1145/3603781.3603899","DOIUrl":"https://doi.org/10.1145/3603781.3603899","url":null,"abstract":"As electronic products are updated, chips need to be constantly optimized for design, and the ring oscillator is one of the essential structures. By studying the oscillator area, power consumption and other elements, the best design solution to meet the relevant performance is investigated. It plays a role in promoting the development of chip industry. In this paper, we first model the frequency and area of the ring oscillator to design it. The optimal size is obtained, and then the power consumption is optimized for the design. The relationship between the energy consumption of the ring oscillator and the size and number of inverters is first analyzed by the energy consumption principle, and then an integer programming dynamic model is further developed. Finally, the concept of multiple wafers is introduced to optimize the chip stitching. This allows more ring oscillators to be placed on the last chip position with minimum power consumption. In this paper, the optimization is performed using the Condor algorithm to obtain the optimal design solution in terms of area and power consumption. The results show that the optimal design solution is 3 inverters with 101 nm gate length, 115 nm NMOS gate width, 120 nm PMOS gate width, and 3406018 number of ring oscillators on the last chip. CCS Concepts:Hardware∼ Integrated circuits∼ Semiconductor memory∼ Static memory","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129033736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on Predictive Model Technology for Student Academic Development Based on Machine Learning 基于机器学习的学生学业发展预测模型技术研究

Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things Pub Date : 2023-05-26 DOI: 10.1145/3603781.3603922

Yajuan Zhang, Nan Hu, Ru Jing, Letao Ren

{"title":"Research on Predictive Model Technology for Student Academic Development Based on Machine Learning","authors":"Yajuan Zhang, Nan Hu, Ru Jing, Letao Ren","doi":"10.1145/3603781.3603922","DOIUrl":"https://doi.org/10.1145/3603781.3603922","url":null,"abstract":"Student performance management is a pretty significant part of campus service construction in colleges, there are many students who fail or even delay their graduation because of their low grades every year. If we can provide warning for students' grades and realize academic support early, we can reduce the failure rate and delayed graduation rate, improve the quality of campus services and enhance the level of school management. In this paper, a machine learning based student performance prediction model is established. Through mathematical analysis, seven kinds of easily accessible prediction parameters for schools are selected after comprehensive examination, and two classical machine learning prediction algorithms, KNN and random forest, are built to solve the problem. After substitution into the data set for training, better prediction results were achieved. As the amount of student data and data dimensions received by the school increase, the accuracy and generalization ability of the model will be continuously improved to finally realize the prediction model of student performance based on big data.","PeriodicalId":391180,"journal":{"name":"Proceedings of the 2023 4th International Conference on Computing, Networks and Internet of Things","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129243037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0