Yuncheng Sang, Han Huang, Shuangqing Ma, Shouwen Cai, Zhen Shi
∗We present some experienced improvements to YOLOv5s for mobile robot platforms that occupy many system resources and are difficult to meet the requirements of the actual application. Firstly, the FPN + PAN structure is redesigned to replace this complex structure into a dilated residual module with fewer parameters and calculations. The dilated residual module is composed of dilated residual blocks with different dilation rates stacked together. Secondly, we switch some convolution modules to improved Ghost modules in the backbone. The improved Ghost modules concatenate feature maps obtained by convolution with ones generated by a linear transformation. Then, the two parts of feature maps are shuffled to boost information fusion. The model is trained on the COCO dataset. In this paper, mAP_0.5 is 56.1%, mAP_0.5:0.95 is 35.7%, and the speed is 6.1% faster than YOLOv5s. The experimental results show that the method can further increase the inference speed to ensure detection accuracy. It can well solve the task of object detection on the mobile robot platform.
{"title":"Lightweight Object Detection Method for Mobile Robot Platform","authors":"Yuncheng Sang, Han Huang, Shuangqing Ma, Shouwen Cai, Zhen Shi","doi":"10.1145/3507548.3507550","DOIUrl":"https://doi.org/10.1145/3507548.3507550","url":null,"abstract":"∗We present some experienced improvements to YOLOv5s for mobile robot platforms that occupy many system resources and are difficult to meet the requirements of the actual application. Firstly, the FPN + PAN structure is redesigned to replace this complex structure into a dilated residual module with fewer parameters and calculations. The dilated residual module is composed of dilated residual blocks with different dilation rates stacked together. Secondly, we switch some convolution modules to improved Ghost modules in the backbone. The improved Ghost modules concatenate feature maps obtained by convolution with ones generated by a linear transformation. Then, the two parts of feature maps are shuffled to boost information fusion. The model is trained on the COCO dataset. In this paper, mAP_0.5 is 56.1%, mAP_0.5:0.95 is 35.7%, and the speed is 6.1% faster than YOLOv5s. The experimental results show that the method can further increase the inference speed to ensure detection accuracy. It can well solve the task of object detection on the mobile robot platform.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127593062","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}
In the deep texture image retrieval, to address the problem that the retrieval performance is affected by the lack of sufficiently large texture image dataset used for the effective training of deep neural network, a deep learning based texture dataset construction and texture image retrieval method is proposed in this paper. First, a large-scale texture image dataset containing rich texture information is constructed based on the DTD texture image dataset, and used as the source dataset for pre-training deep neural networks. To effectively characterize the information of the source texture dataset, a revised version of the VGG16 model, called ReV-VGG16, is adaptively designed. Then, the pre-trained ReV-VGG16 model is combined with the target texture image datasets for the transfer learning, and the probability values of the output from the classification layer of the model are used for the computation of the similarity measurement to achieve the retrieval of the target texture image dataset. Finally, the retrieval experiments are conducted on four typical texture image datasets, namely, VisTex, Brodatz, STex and ALOT. The experimental results show that our method outperforms the existing state-of-the-art texture image retrieval approaches in terms of the retrieval performance.
{"title":"Texture Dataset Construction and Texture Image Retrieval based on Deep Learning","authors":"Zhisheng Zhang, Huaijing Qu, Hengbin Wang, Jia Xu, Jiwei Wang, Yanan Wei","doi":"10.1145/3507548.3507564","DOIUrl":"https://doi.org/10.1145/3507548.3507564","url":null,"abstract":"In the deep texture image retrieval, to address the problem that the retrieval performance is affected by the lack of sufficiently large texture image dataset used for the effective training of deep neural network, a deep learning based texture dataset construction and texture image retrieval method is proposed in this paper. First, a large-scale texture image dataset containing rich texture information is constructed based on the DTD texture image dataset, and used as the source dataset for pre-training deep neural networks. To effectively characterize the information of the source texture dataset, a revised version of the VGG16 model, called ReV-VGG16, is adaptively designed. Then, the pre-trained ReV-VGG16 model is combined with the target texture image datasets for the transfer learning, and the probability values of the output from the classification layer of the model are used for the computation of the similarity measurement to achieve the retrieval of the target texture image dataset. Finally, the retrieval experiments are conducted on four typical texture image datasets, namely, VisTex, Brodatz, STex and ALOT. The experimental results show that our method outperforms the existing state-of-the-art texture image retrieval approaches in terms of the retrieval performance.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130991618","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}
Low-dimensional feature regression is a common problem in various disciplines, such as chemistry, kinetics, and medicine, etc. Most common solutions are based on machine learning, but as deep learning evolves, there is room for performance improvements. A few researchers have proposed deep learning-based solutions such as ResidualNet, GrowNet and EnsembleNet. The latter two methods are both boost methods, which are more suitable for shallow network, and the model performance is basically determined by the first model, with limited effect of subsequent boosting steps. We propose a method based on self-distillation and bagging, which selects the well-performing base model and distills several student models by appropriate regression distillation algorithm. Finally, the output of these student models is averaged as the final result. This integration method can be applied to any form of network. The method achieves good results in the CASP dataset, and the R2(Coefficient of Determination) of the model is improved from (0.65) to (0.70) in comparison with the best base model ResidualNet.
{"title":"Regression Algorithm Based on Self-Distillation and Ensemble Learning","authors":"Yaqi Li, Qiwen Dong, Gang Liu","doi":"10.1145/3507548.3507580","DOIUrl":"https://doi.org/10.1145/3507548.3507580","url":null,"abstract":"Low-dimensional feature regression is a common problem in various disciplines, such as chemistry, kinetics, and medicine, etc. Most common solutions are based on machine learning, but as deep learning evolves, there is room for performance improvements. A few researchers have proposed deep learning-based solutions such as ResidualNet, GrowNet and EnsembleNet. The latter two methods are both boost methods, which are more suitable for shallow network, and the model performance is basically determined by the first model, with limited effect of subsequent boosting steps. We propose a method based on self-distillation and bagging, which selects the well-performing base model and distills several student models by appropriate regression distillation algorithm. Finally, the output of these student models is averaged as the final result. This integration method can be applied to any form of network. The method achieves good results in the CASP dataset, and the R2(Coefficient of Determination) of the model is improved from (0.65) to (0.70) in comparison with the best base model ResidualNet.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128657555","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}
In recent years, with the continuous improvement of teaching informatization, online teaching or online and offline hybrid teaching has become the new normal of teaching in some schools. However, the biggest problem in online teaching is that it is difficult to predict students' academic performance. Therefore, it is necessary to design an effective method to predict students' academic performance more accurately. In this paper, a student academic level prediction method based on stacking model fusion is proposed. Logistic regression, random forest, XGBoost, and Naive Bayes are selected as base learners according to optimal fusion criteria and model properties. Furthermore, the structure and distribution of the features of the dataset are optimized by data preprocessing, feature coding, and feature selection, and the upper limit of the model expression is effectively raised. On this basis, according to the features of dataset and model performance, we select the appropriate model for model fusion, and further improve the prediction effect. Experiments are conducted on OULAD and xAPI datasets, and the results show that the prediction accuracy of the proposed method is better than that of traditional prediction methods. Finally, we analyze the factors that affect academic performance and give some specific suggestions.
{"title":"The Research of Predicting Student's Academic Performance Based on Educational Data","authors":"Yubo Zhang, Yanfang Liu","doi":"10.1145/3507548.3507578","DOIUrl":"https://doi.org/10.1145/3507548.3507578","url":null,"abstract":"In recent years, with the continuous improvement of teaching informatization, online teaching or online and offline hybrid teaching has become the new normal of teaching in some schools. However, the biggest problem in online teaching is that it is difficult to predict students' academic performance. Therefore, it is necessary to design an effective method to predict students' academic performance more accurately. In this paper, a student academic level prediction method based on stacking model fusion is proposed. Logistic regression, random forest, XGBoost, and Naive Bayes are selected as base learners according to optimal fusion criteria and model properties. Furthermore, the structure and distribution of the features of the dataset are optimized by data preprocessing, feature coding, and feature selection, and the upper limit of the model expression is effectively raised. On this basis, according to the features of dataset and model performance, we select the appropriate model for model fusion, and further improve the prediction effect. Experiments are conducted on OULAD and xAPI datasets, and the results show that the prediction accuracy of the proposed method is better than that of traditional prediction methods. Finally, we analyze the factors that affect academic performance and give some specific suggestions.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128727897","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}
In order to real time and accurately detect the action of human falling, combined with lightweight detection network, Kalman filter tracking, posture estimation network and spatiotemporal graph convolutional network, a joint algorithm for human fall detection in video is proposed. Firstly, the lightweight YOLOv3-Tiny algorithm is used to locate the frame of human in video, which can quickly detect the human-frame; among them, for the situation that the human body is likely to be missed in video, the Kalman filter tracking algorithm is integrated into the stage of target-detection and the accuracy of detecting is improved. Secondly, the human-frame detected or tracked in video is sent to the AlphaPose network to estimate the posture graph about human body. Finally, the spatiotemporal graph convolutional network is exploited to extract the spatiotemporal features of the human body, and eventually the result for classification is output. Experimental results show that the algorithm proposed in this paper, which is more appealing and successful than the other algorithm.
{"title":"Human Fall Detection Model with Lightweight Network and Tracking in Video","authors":"Xiaoli Ren, Yunjie Zhang, Yanrong Yang","doi":"10.1145/3507548.3507549","DOIUrl":"https://doi.org/10.1145/3507548.3507549","url":null,"abstract":"In order to real time and accurately detect the action of human falling, combined with lightweight detection network, Kalman filter tracking, posture estimation network and spatiotemporal graph convolutional network, a joint algorithm for human fall detection in video is proposed. Firstly, the lightweight YOLOv3-Tiny algorithm is used to locate the frame of human in video, which can quickly detect the human-frame; among them, for the situation that the human body is likely to be missed in video, the Kalman filter tracking algorithm is integrated into the stage of target-detection and the accuracy of detecting is improved. Secondly, the human-frame detected or tracked in video is sent to the AlphaPose network to estimate the posture graph about human body. Finally, the spatiotemporal graph convolutional network is exploited to extract the spatiotemporal features of the human body, and eventually the result for classification is output. Experimental results show that the algorithm proposed in this paper, which is more appealing and successful than the other algorithm.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121085950","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}
Lightweight object detection models have great application prospects in resource-restricted scenarios such as mobile and embedded devices, and have been a hot topic in the computer vision community. However, most existing lightweight object detection methods show poor detection accuracy. In this study, we put forward a lightweight objection detection model named Enhanced-YOLOv3-tiny to improve the detection accuracy and reduce the model complexity at the same time. In Enhanced-YOLOv3-tiny, we propose a new backbone named GhostDarkNet based on DarkNet53 and Ghost Module for decreasing the model parameters, which helps to get more representative features compared with YOLOv3-tiny. Furthermore, we put forward a new Multiscale Head, which adds three more heads and includes Ghost Module in each head to fuse multi-scale features. Experiments on the Priority Research Application dataset from the real scenes in driving show that the proposed Enhanced-YOLOv3-tiny outperforms the state-of-the-art YOLOv3-tiny by 8.4% improvement in AP metric and decreases parameters from 8.8M to 3.9M, demonstrating the application potentials of our proposed method in resource-constrained scenarios.
轻量级目标检测模型在移动和嵌入式设备等资源受限场景中具有很大的应用前景，一直是计算机视觉界的研究热点。然而，现有的大多数轻量化目标检测方法检测精度较差。在本研究中，我们提出了一种轻量级的目标检测模型Enhanced-YOLOv3-tiny，在提高检测精度的同时降低模型复杂度。在Enhanced-YOLOv3-tiny中，我们提出了一种基于DarkNet53和Ghost Module的新主干GhostDarkNet，以减少模型参数，从而获得比YOLOv3-tiny更具代表性的特征。在此基础上，我们提出了一种新的多尺度磁头，该磁头增加了3个磁头，并在每个磁头中加入Ghost Module以融合多尺度特征。在Priority Research Application真实驾驶场景数据集上的实验表明，本文提出的Enhanced-YOLOv3-tiny在AP度量上比最先进的YOLOv3-tiny提高了8.4%，并将参数从8.8M降至3.9M，证明了本文提出的方法在资源受限场景下的应用潜力。
{"title":"Enhanced Efficient YOLOv3-tiny for Object Detection","authors":"Huanqia Cai, Lele Xu, Lili Guo","doi":"10.1145/3507548.3507551","DOIUrl":"https://doi.org/10.1145/3507548.3507551","url":null,"abstract":"Lightweight object detection models have great application prospects in resource-restricted scenarios such as mobile and embedded devices, and have been a hot topic in the computer vision community. However, most existing lightweight object detection methods show poor detection accuracy. In this study, we put forward a lightweight objection detection model named Enhanced-YOLOv3-tiny to improve the detection accuracy and reduce the model complexity at the same time. In Enhanced-YOLOv3-tiny, we propose a new backbone named GhostDarkNet based on DarkNet53 and Ghost Module for decreasing the model parameters, which helps to get more representative features compared with YOLOv3-tiny. Furthermore, we put forward a new Multiscale Head, which adds three more heads and includes Ghost Module in each head to fuse multi-scale features. Experiments on the Priority Research Application dataset from the real scenes in driving show that the proposed Enhanced-YOLOv3-tiny outperforms the state-of-the-art YOLOv3-tiny by 8.4% improvement in AP metric and decreases parameters from 8.8M to 3.9M, demonstrating the application potentials of our proposed method in resource-constrained scenarios.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115587522","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}
Shuo Liu, Li-wen Xu, Jin-Rong Wang, Yan Sun, Zeran Qin
Anomaly detection is pivotal and challenging in artificial intelligence, which aims to determine whether a query sample comes from the same class, given a set of normal samples from a particular class. There are a plethora of anomaly detection methods based on generative models; however, these methods aim to make the reconstruction error of the training samples smaller or extract more information from the training samples. We believe that it is more important for anomaly detection to extract crucial representation from normal samples rather than more information, so we propose a semi-supervised method named LCR-GAN. We conducted extensive experiments on four image datasets and 15 tabular datasets to demonstrate the effectiveness of the proposed method. Meanwhile, we also carried out an anti-noise study to demonstrate the robustness of the proposed method.
{"title":"LCR-GAN: Learning Crucial Representation for Anomaly Detection","authors":"Shuo Liu, Li-wen Xu, Jin-Rong Wang, Yan Sun, Zeran Qin","doi":"10.1145/3507548.3508229","DOIUrl":"https://doi.org/10.1145/3507548.3508229","url":null,"abstract":"Anomaly detection is pivotal and challenging in artificial intelligence, which aims to determine whether a query sample comes from the same class, given a set of normal samples from a particular class. There are a plethora of anomaly detection methods based on generative models; however, these methods aim to make the reconstruction error of the training samples smaller or extract more information from the training samples. We believe that it is more important for anomaly detection to extract crucial representation from normal samples rather than more information, so we propose a semi-supervised method named LCR-GAN. We conducted extensive experiments on four image datasets and 15 tabular datasets to demonstrate the effectiveness of the proposed method. Meanwhile, we also carried out an anti-noise study to demonstrate the robustness of the proposed method.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127504005","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}
In recent years, the research of computer vision is popular. However, the image data that can be used for computer vision training is very limited, so it is necessary to find an effective method to expand the datasets based on the existing image data. In this paper, we study methods to collect more training data from existing datasets and compare detectors’ performance trained with datasets generated by different methods. One method is to perform sampling-based on statistical properties of feature descriptors. For every feature, the underlying assumption is that a probability density function (PDF) exists, such PDF is approximated with existing training examples and new training examples are sampled from the approximated PDF. The other method is simply to expand the existing datasets by flipping each training example along its symmetric axis. Locally Adaptive Regression Kernel (LARK) feature is used in this paper because it is robust against illumination changes and noise. Our experimental results demonstrate that an expanded training dataset is not always preferable, even if the expanded dataset includes all original training data.
{"title":"Sampling May Not Always Increase Detector Performance: A Study on Collecting Training Examples","authors":"Jun Liu, Shuang Lai","doi":"10.1145/3507548.3507568","DOIUrl":"https://doi.org/10.1145/3507548.3507568","url":null,"abstract":"In recent years, the research of computer vision is popular. However, the image data that can be used for computer vision training is very limited, so it is necessary to find an effective method to expand the datasets based on the existing image data. In this paper, we study methods to collect more training data from existing datasets and compare detectors’ performance trained with datasets generated by different methods. One method is to perform sampling-based on statistical properties of feature descriptors. For every feature, the underlying assumption is that a probability density function (PDF) exists, such PDF is approximated with existing training examples and new training examples are sampled from the approximated PDF. The other method is simply to expand the existing datasets by flipping each training example along its symmetric axis. Locally Adaptive Regression Kernel (LARK) feature is used in this paper because it is robust against illumination changes and noise. Our experimental results demonstrate that an expanded training dataset is not always preferable, even if the expanded dataset includes all original training data.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"45 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126277872","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}
This paper takes visitor experience as the center to study the specific strategies to enhance the digital display effect of the former residence Memorial Hall, in order to deal with the plight of its digital display development lag. Based on the theory of IPOP, this paper makes an empirical study of Tsou Jung Memorial Hall through questionnaire survey and field observation, this paper discusses the differences of four kinds of audience on the digital display of the former residence Memorial Hall. There are significant differences and correlations among the four kinds of experiences dimensions among the audiences with different preference types. Through the analysis of their internal relations, this paper explores the application possibility of IPOP theory in the digital display experience of museums, it provides a general plan for the evaluation of demonstration effect and the standard of technology application.
{"title":"Research on Digital Exhibition Design of Former Residence Memorial Hall based on IPOP Theory","authors":"Xia Wang, Zhengqing Jiang","doi":"10.1145/3507548.3507606","DOIUrl":"https://doi.org/10.1145/3507548.3507606","url":null,"abstract":"This paper takes visitor experience as the center to study the specific strategies to enhance the digital display effect of the former residence Memorial Hall, in order to deal with the plight of its digital display development lag. Based on the theory of IPOP, this paper makes an empirical study of Tsou Jung Memorial Hall through questionnaire survey and field observation, this paper discusses the differences of four kinds of audience on the digital display of the former residence Memorial Hall. There are significant differences and correlations among the four kinds of experiences dimensions among the audiences with different preference types. Through the analysis of their internal relations, this paper explores the application possibility of IPOP theory in the digital display experience of museums, it provides a general plan for the evaluation of demonstration effect and the standard of technology application.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130280681","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}
Aiming at the complex dependence of water quality data in space and time, we propose a GCN-Seq2Seq model for surface water quality prediction. The model uses Graph Convolutional Network (GCN) to capture the spatial feature of water quality monitoring sites, uses the sequence to sequence (Seq2Seq) model constructed by GRU to extract the temporal feature of the water quality data sequence, and predicts multi-step water quality time series. Experiments were carried out with data from 6 water quality monitoring stations in the Huangshui River and surrounding areas in Xining City, Qinghai Province from November 2020 to June 2021, and compared with the baseline model. experimental results show that the proposed model can effectively improve the accuracy of multi-step prediction of surface water quality.
针对地表水水质数据在空间和时间上的复杂依赖性，提出了一种用于地表水水质预测的GCN-Seq2Seq模型。该模型利用图卷积网络(Graph Convolutional Network, GCN)捕捉水质监测点的空间特征，利用GRU构建的序列到序列(sequence to sequence, Seq2Seq)模型提取水质数据序列的时间特征，并对多步水质时间序列进行预测。利用青海省西宁市湟水河及周边地区6个水质监测站2020年11月至2021年6月的数据进行实验，并与基线模型进行对比。实验结果表明，该模型能有效提高地表水水质多步预测的精度。
{"title":"GCN-Seq2Seq: A Spatio-Temporal feature-fused model for surface water quality prediction","authors":"Ying Chen, Ping Yang, Chengxu Ye, Zhikun Miao","doi":"10.1145/3507548.3507597","DOIUrl":"https://doi.org/10.1145/3507548.3507597","url":null,"abstract":"Aiming at the complex dependence of water quality data in space and time, we propose a GCN-Seq2Seq model for surface water quality prediction. The model uses Graph Convolutional Network (GCN) to capture the spatial feature of water quality monitoring sites, uses the sequence to sequence (Seq2Seq) model constructed by GRU to extract the temporal feature of the water quality data sequence, and predicts multi-step water quality time series. Experiments were carried out with data from 6 water quality monitoring stations in the Huangshui River and surrounding areas in Xining City, Qinghai Province from November 2020 to June 2021, and compared with the baseline model. experimental results show that the proposed model can effectively improve the accuracy of multi-step prediction of surface water quality.","PeriodicalId":414908,"journal":{"name":"Proceedings of the 2021 5th International Conference on Computer Science and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130873026","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：