Di Jin, Chenhang Sun, Zhiyi Yang, Ruifa Cao, Zhigang Zhang
The intermittent output of renewable energy and the load fluctuation bring many uncertainties to the integrated energy system. Therefore, this paper proposes a power probabilistic energy flow calculation method for integrated energy systems considering renewable energy output and load uncertainty. Firstly, the electricity-heat-gas integrated energy system's steady-state energy flow calculation model is constructed based on the energy hub model. On this basis, considering the uncertainty of renewable energy output and load, a probabilistic energy flow calculation method for integrated energy systems based on the Quasi-Monte Carlo simulation method is proposed for the probabilistic energy flow of electricity. Finally, the accuracy of the calculation method is verified by an example analysis.
{"title":"Power Probabilistic Energy Flow Calculation for Integrated Energy System Considering Uncertainties of Renewable Energy Output and Load","authors":"Di Jin, Chenhang Sun, Zhiyi Yang, Ruifa Cao, Zhigang Zhang","doi":"10.1145/3546000.3546031","DOIUrl":"https://doi.org/10.1145/3546000.3546031","url":null,"abstract":"The intermittent output of renewable energy and the load fluctuation bring many uncertainties to the integrated energy system. Therefore, this paper proposes a power probabilistic energy flow calculation method for integrated energy systems considering renewable energy output and load uncertainty. Firstly, the electricity-heat-gas integrated energy system's steady-state energy flow calculation model is constructed based on the energy hub model. On this basis, considering the uncertainty of renewable energy output and load, a probabilistic energy flow calculation method for integrated energy systems based on the Quasi-Monte Carlo simulation method is proposed for the probabilistic energy flow of electricity. Finally, the accuracy of the calculation method is verified by an example analysis.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121329679","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}
Zhongxin Du, Ye Qiu, Qingbin Yu, Yingjie Chen, Mengru Ma, Wei Ding
With the increasing use of driving recorder equipment, people need new methods for the analysis of vehicle trajectories. The extraction of road information from vehicle trajectory data is one of the focuses in the field of geographic information. In this paper, we proposed two vehicle trajectory extraction methods, a fast vehicle trajectory extraction method based on GPS points and a vehicle trajectory extraction method based on the field of view. First, we gave a problem definition for the video trajectory display method. Then we expounded on the field of view of the Geo-referenced video [1] and its related information. The first method connects the location points, and each segment of the trajectory line indicates the current driving direction of the vehicle. The other method introduces the concept of perspective on this basis. It not only shows the direction of the trajectory line but also extracts the perspective of keyframes to accurately describe the trajectory of the vehicle. Next, we used a time and distance-based spatiotemporal clustering algorithm to extract points and demonstrate them through experimental results. We visualized the extracted vehicle trajectories and displayed them on a map. Finally, we compared the efficiency and accuracy of the traditional vehicle trajectory extraction method and the two methods proposed in this paper. The results showed that the vehicle trajectory extraction methods proposed in this paper are superior to the traditional vehicle trajectory display method in accuracy.
{"title":"Road extraction method of vehicle trajectory data based on geo-referenced videos","authors":"Zhongxin Du, Ye Qiu, Qingbin Yu, Yingjie Chen, Mengru Ma, Wei Ding","doi":"10.1145/3546000.3546024","DOIUrl":"https://doi.org/10.1145/3546000.3546024","url":null,"abstract":"With the increasing use of driving recorder equipment, people need new methods for the analysis of vehicle trajectories. The extraction of road information from vehicle trajectory data is one of the focuses in the field of geographic information. In this paper, we proposed two vehicle trajectory extraction methods, a fast vehicle trajectory extraction method based on GPS points and a vehicle trajectory extraction method based on the field of view. First, we gave a problem definition for the video trajectory display method. Then we expounded on the field of view of the Geo-referenced video [1] and its related information. The first method connects the location points, and each segment of the trajectory line indicates the current driving direction of the vehicle. The other method introduces the concept of perspective on this basis. It not only shows the direction of the trajectory line but also extracts the perspective of keyframes to accurately describe the trajectory of the vehicle. Next, we used a time and distance-based spatiotemporal clustering algorithm to extract points and demonstrate them through experimental results. We visualized the extracted vehicle trajectories and displayed them on a map. Finally, we compared the efficiency and accuracy of the traditional vehicle trajectory extraction method and the two methods proposed in this paper. The results showed that the vehicle trajectory extraction methods proposed in this paper are superior to the traditional vehicle trajectory display method in accuracy.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116576488","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}
Li-Qin Kong, Zhiyuan Ren, Yan Zhou, Wei Ding, Ji-Hong Cheng
Pneumonia has always been the leading infectious disease leading to the death of children under five years old. X-ray images of the lungs have become the key to the diagnosis of this disease. If computer-aided medical diagnosis is used to automatically detect lung abnormalities, the accuracy of the diagnosis will be improved.This article aims to introduce a deep learning technology based on the combination of image segmentation and feature fusion, which can realize automatic diagnosis of patients with pneumonia in X-ray images. First, use residuals to achieve image segmentation to more accurately divide the lung area. Secondly, the Xception network is used to extract the in-depth features of the data, and the extracted features are passed to the LSTM model to detect the extracted features, and classify the two cases of pneumonia and no pneumonia. This research combines Pearson's feature selection ideas and fuses the correlation between the two loss functions. Experimental results show that the accuracy of this paper is 98%, and the accuracy of AUC is 99%. Compared with the existing technical methods, the accuracy of the model designed in this paper is greatly improved. The model we designed has achieved excellent. experimental results on the currently available data sets. I hope our research can help doctors in the detection of pneumonia in children.
{"title":"Research on Medical Image Classification Based on Image Segmentation and Feature Fusion","authors":"Li-Qin Kong, Zhiyuan Ren, Yan Zhou, Wei Ding, Ji-Hong Cheng","doi":"10.1145/3546000.3546023","DOIUrl":"https://doi.org/10.1145/3546000.3546023","url":null,"abstract":"Pneumonia has always been the leading infectious disease leading to the death of children under five years old. X-ray images of the lungs have become the key to the diagnosis of this disease. If computer-aided medical diagnosis is used to automatically detect lung abnormalities, the accuracy of the diagnosis will be improved.This article aims to introduce a deep learning technology based on the combination of image segmentation and feature fusion, which can realize automatic diagnosis of patients with pneumonia in X-ray images. First, use residuals to achieve image segmentation to more accurately divide the lung area. Secondly, the Xception network is used to extract the in-depth features of the data, and the extracted features are passed to the LSTM model to detect the extracted features, and classify the two cases of pneumonia and no pneumonia. This research combines Pearson's feature selection ideas and fuses the correlation between the two loss functions. Experimental results show that the accuracy of this paper is 98%, and the accuracy of AUC is 99%. Compared with the existing technical methods, the accuracy of the model designed in this paper is greatly improved. The model we designed has achieved excellent. experimental results on the currently available data sets. I hope our research can help doctors in the detection of pneumonia in children.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115042674","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}
Dandan Chen, Jin Li, Hongwei Liu, L. Ao, Qiushi Zhang
Alzheimer's disease (AD) is a most common and particularly complex neurodegenerative disease commonly characterized by a progressive decline in cognition and memory impairments. CSF Aß42 and tau levels have emerged as useful biomarkers for disease and Quantitative Traits (QTs) for genetic studies of AD. In this study, CSF Phosphorylated Tau (P-tau) were used both in genome-wide association studies (GWAS) and genome-wide interaction study (GWIS) as QTs. The GWAS results shows that genes identified by Total Tau (T-tau), also have been replicated on QTs of P-tau, and a new GWAS loci of rs157582 have been identified by GWAS of CSF P-tau. The three genes of APOE, APOC1, and TOMM40 identified by p-Tau in this GWAS are previously confirmed AD susceptibility genes, while our GWAS have replicated them. Therefore, we may argue that QTs of P-tau is more sensitive and more significant than tau. This also indirectly proves the view of P-tau may be a more specific marker than T-tau for AD. Furthermore, the results demonstrate that the data, phenotypes, quality control methods and GWAS method we used to be rationality and validity, which making the subsequent GWIS based on this data more meaningful. In GWIS, 8 pairs of SNPs showed significant interaction effects on the CSF P-tau (corrected p-value <0.05). These 8 pairs of SNPs revealed by GWIS codes from 8 novel genes. Among them, NAT1, ST18, CTNNA2 and IMMP2L have been reported as AD risk genes. NCKAP5, LHFPL3, PRLHR are related to schizophrenia (SCZ). And the gene of AOAH go unreported be related to AD or SCZ. All the work illustrates the plausibility of T-tau as QTs on our dataset, while we also found more significant SNPs by GWIS, which can be used as an effective supplement when AD risk loci cannot be identified by GWAS. The 8 pairs of SNP interactions findings warrant replication and can be used for the analysis of other complex diseases.
{"title":"Genome-Wide Association and Interaction Study on Quantitative Traits of CSF Phosphorylated Tau in ADNI cohort","authors":"Dandan Chen, Jin Li, Hongwei Liu, L. Ao, Qiushi Zhang","doi":"10.1145/3546000.3546008","DOIUrl":"https://doi.org/10.1145/3546000.3546008","url":null,"abstract":"Alzheimer's disease (AD) is a most common and particularly complex neurodegenerative disease commonly characterized by a progressive decline in cognition and memory impairments. CSF Aß42 and tau levels have emerged as useful biomarkers for disease and Quantitative Traits (QTs) for genetic studies of AD. In this study, CSF Phosphorylated Tau (P-tau) were used both in genome-wide association studies (GWAS) and genome-wide interaction study (GWIS) as QTs. The GWAS results shows that genes identified by Total Tau (T-tau), also have been replicated on QTs of P-tau, and a new GWAS loci of rs157582 have been identified by GWAS of CSF P-tau. The three genes of APOE, APOC1, and TOMM40 identified by p-Tau in this GWAS are previously confirmed AD susceptibility genes, while our GWAS have replicated them. Therefore, we may argue that QTs of P-tau is more sensitive and more significant than tau. This also indirectly proves the view of P-tau may be a more specific marker than T-tau for AD. Furthermore, the results demonstrate that the data, phenotypes, quality control methods and GWAS method we used to be rationality and validity, which making the subsequent GWIS based on this data more meaningful. In GWIS, 8 pairs of SNPs showed significant interaction effects on the CSF P-tau (corrected p-value <0.05). These 8 pairs of SNPs revealed by GWIS codes from 8 novel genes. Among them, NAT1, ST18, CTNNA2 and IMMP2L have been reported as AD risk genes. NCKAP5, LHFPL3, PRLHR are related to schizophrenia (SCZ). And the gene of AOAH go unreported be related to AD or SCZ. All the work illustrates the plausibility of T-tau as QTs on our dataset, while we also found more significant SNPs by GWIS, which can be used as an effective supplement when AD risk loci cannot be identified by GWAS. The 8 pairs of SNP interactions findings warrant replication and can be used for the analysis of other complex diseases.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128991630","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 problems that the ant colony routing algorithm is easy to form loops and its energy distribution is not uniform enough, an improved ant colony routing algorithm is proposed. The improved algorithm adds an ant identification combination item in the Hello packet, and stores it in the neighbor list of other nodes by broadcasting, which effectively weakens the loop effect. At the same time, the pheromone update formula is revised to improve the accuracy of pheromone update in multi-node areas and the energy difference factor is introduced, and the energy difference factor is used as the reference factor for the update of pheromone concentration, which improves the problem of uneven distribution of node energy and obtains a better balance of the energy of network nodes. The simulation results show that the improved algorithm can greatly improve the balance of node energy and the weakening of loop effects.
{"title":"An Energy Balance Ant Colony Routing Algorithm for WSN","authors":"Wei-hong Zhu, Lu-ying Xie","doi":"10.1145/3546000.3546006","DOIUrl":"https://doi.org/10.1145/3546000.3546006","url":null,"abstract":"Aiming at the problems that the ant colony routing algorithm is easy to form loops and its energy distribution is not uniform enough, an improved ant colony routing algorithm is proposed. The improved algorithm adds an ant identification combination item in the Hello packet, and stores it in the neighbor list of other nodes by broadcasting, which effectively weakens the loop effect. At the same time, the pheromone update formula is revised to improve the accuracy of pheromone update in multi-node areas and the energy difference factor is introduced, and the energy difference factor is used as the reference factor for the update of pheromone concentration, which improves the problem of uneven distribution of node energy and obtains a better balance of the energy of network nodes. The simulation results show that the improved algorithm can greatly improve the balance of node energy and the weakening of loop effects.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123405232","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 rapid development of the automobile industry, the trading volume of second-hand cars in our country has grown rapidly. However, with the continuous expansion of the second-hand car market, a scientific and reasonable evaluation system or unified standard has not yet been formed in the second-hand car market, which makes the second-hand car trading market lack credibility and restricts its development of the second-hand car trading market. Therefore, it is particularly important to establish a reasonable and perfect second-hand car valuation method. In this paper, GBDT, LightGBM, and XGBoost models are introduced into the field of the used car valuation, and by analyzing the influence of body infrastructure and vehicle conditions, a used car valuation model based on the fusion of GBDT, LightGBM, and XGBoost is constructed. Then it conducts in-depth analysis and research on the problem of used car valuation. At the same time, to verify the advantages and rationality of the model proposed in this paper, the used car valuation model based on the fusion of GBDT, LightGBM and XGBoost is compared and analyzed with random forest, KNN, linear regression, and other models. Finally, after verification, the proposed model based on GBDT, LightGBM, and XGBoost fusion can significantly improve the prediction accuracy, and under the self-defined model evaluation standard in this paper, the model recognition accuracy is up to 89%, which has good practical value.
{"title":"Research on used car valuation problem based on model fusion","authors":"Guozheng Liu, Haoxiang Chu, Ye Zhang, Huiling Shi","doi":"10.1145/3546000.3546009","DOIUrl":"https://doi.org/10.1145/3546000.3546009","url":null,"abstract":"In recent years, with the rapid development of the automobile industry, the trading volume of second-hand cars in our country has grown rapidly. However, with the continuous expansion of the second-hand car market, a scientific and reasonable evaluation system or unified standard has not yet been formed in the second-hand car market, which makes the second-hand car trading market lack credibility and restricts its development of the second-hand car trading market. Therefore, it is particularly important to establish a reasonable and perfect second-hand car valuation method. In this paper, GBDT, LightGBM, and XGBoost models are introduced into the field of the used car valuation, and by analyzing the influence of body infrastructure and vehicle conditions, a used car valuation model based on the fusion of GBDT, LightGBM, and XGBoost is constructed. Then it conducts in-depth analysis and research on the problem of used car valuation. At the same time, to verify the advantages and rationality of the model proposed in this paper, the used car valuation model based on the fusion of GBDT, LightGBM and XGBoost is compared and analyzed with random forest, KNN, linear regression, and other models. Finally, after verification, the proposed model based on GBDT, LightGBM, and XGBoost fusion can significantly improve the prediction accuracy, and under the self-defined model evaluation standard in this paper, the model recognition accuracy is up to 89%, which has good practical value.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121636379","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}
Due to the wide use of lithium batteries, the charging safety of lithium batteries in low temperature environment has become a matter of concern. This time, through the battery bench test verification of the battery pack charging control method in the low-temperature environment, it shows that this method can ensure the normal operation of the battery pack in the low-temperature environment, and the charged power is 93.2% of the rated capacity of the battery pack, which effectively ensures the charging safety of lithium battery in the low-temperature environment.
{"title":"Research on charging control of battery pack in low temperature environment","authors":"Chao Liu, R. Zang, Ying Xin, Yu Wang","doi":"10.1145/3546000.3546028","DOIUrl":"https://doi.org/10.1145/3546000.3546028","url":null,"abstract":"Due to the wide use of lithium batteries, the charging safety of lithium batteries in low temperature environment has become a matter of concern. This time, through the battery bench test verification of the battery pack charging control method in the low-temperature environment, it shows that this method can ensure the normal operation of the battery pack in the low-temperature environment, and the charged power is 93.2% of the rated capacity of the battery pack, which effectively ensures the charging safety of lithium battery in the low-temperature environment.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121879833","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}
Deep neural networks are widely used in various fields. However, due to the large scale of the latest deep neural networks, the research on the sparsity of deep neural networks is constantly carried out. The implementation of the sparse deep neural network on GPU can further accelerate the computing speed of a sparse deep neural network. The performance of the GPU code of the CUDA version is far superior to the CPU codes of the Matlab version, which confirms the great superiority of the sparse deep neural network implementation on GPU. And the GPU code of the CUDA version is up x1.61 faster than the CUSPARSE version when the deep neural network has 1024 neurons and the 1920 layers.
{"title":"Performance Optimization of Sparse Deep Neural Networks Based on GPU","authors":"Yucheng Shi, Long Ren","doi":"10.1145/3546000.3546011","DOIUrl":"https://doi.org/10.1145/3546000.3546011","url":null,"abstract":"Deep neural networks are widely used in various fields. However, due to the large scale of the latest deep neural networks, the research on the sparsity of deep neural networks is constantly carried out. The implementation of the sparse deep neural network on GPU can further accelerate the computing speed of a sparse deep neural network. The performance of the GPU code of the CUDA version is far superior to the CPU codes of the Matlab version, which confirms the great superiority of the sparse deep neural network implementation on GPU. And the GPU code of the CUDA version is up x1.61 faster than the CUSPARSE version when the deep neural network has 1024 neurons and the 1920 layers.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124121087","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}
Yingjie Chen, Mengru Ma, Qingbin Yu, Zhongxin Du, Wei Ding
With the increasing number of moving videos, anomaly detection of moving videos has become a popular data mining task in the field of intelligent transportation. Traditional road anomaly detection algorithms are hard to detect road bump outliers while the domestic platform has not yet applied road bump detection methods using the accelerometer and gyroscope data. For this, we proposed a road bump outlier detection algorithm (RBOD) and illustrated migration and the improvement of our algorithm for the domestic platforms. Our RBOD algorithm used a Kalman Filter-based method to solve the noise data problem of the accelerometer or gyroscope and selected the accelerometer or gyroscope data for outlier detection according to the sampling frequency. The experimental results show that our RBOD algorithm can detect moving things anomalies efficiently and accurately.
{"title":"Road Bump Outlier Detection of Moving Videos Based on Domestic Kylin Operating System","authors":"Yingjie Chen, Mengru Ma, Qingbin Yu, Zhongxin Du, Wei Ding","doi":"10.1145/3546000.3546021","DOIUrl":"https://doi.org/10.1145/3546000.3546021","url":null,"abstract":"With the increasing number of moving videos, anomaly detection of moving videos has become a popular data mining task in the field of intelligent transportation. Traditional road anomaly detection algorithms are hard to detect road bump outliers while the domestic platform has not yet applied road bump detection methods using the accelerometer and gyroscope data. For this, we proposed a road bump outlier detection algorithm (RBOD) and illustrated migration and the improvement of our algorithm for the domestic platforms. Our RBOD algorithm used a Kalman Filter-based method to solve the noise data problem of the accelerometer or gyroscope and selected the accelerometer or gyroscope data for outlier detection according to the sampling frequency. The experimental results show that our RBOD algorithm can detect moving things anomalies efficiently and accurately.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132903002","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}
Wei Ding, Qingbin Yu, Zhongxin Du, Mengru Ma, Yingjie Chen
The application of sensors enables mobile devices to generate amounts of content-aware data, such as trajectory, gyro, and video data. Moving video is an emerging new type of moving object that can provide a potential source for geo-referenced applications. Measuring the similarity of moving videos is widely used in traffic management, tourist recommendations, and location-based advertising. Our prior work proposed two similarity measures, the Largest Common View Subsequences can accurately calculate similar moving videos, and the View Vector Subsequences can fast calculate similar moving videos. In this paper, we proposed the searching top-k similar moving videos (K-SSMV). First, we give the problem definition of searching top-k similar moving videos. Then, we illustrated the strategy of searching for moving videos. Specifically, we sorted the video pairs by the most similar videos. Since the similar videos would be less than k, we first calculated the similarity of moving videos by the Largest Common View Subsequences algorithm, if the number of similar videos is less than k, we will adopt the View Vector Subsequences algorithm to compute the similarity of moving videos. Next, we mixed the candidate videos calculated by the Largest Common View Subsequences and the View Vector Subsequences algorithms, the searching top-k similar moving videos algorithm picked the top-k similar videos from candidate videos. Finally, we evaluated the performance of our proposed algorithms on the accuracy and computational cost. The experiments verified that our algorithms can efficiently search top-k similar moving videos.
{"title":"Searching Top-K Similar Moving Videos","authors":"Wei Ding, Qingbin Yu, Zhongxin Du, Mengru Ma, Yingjie Chen","doi":"10.1145/3546000.3546026","DOIUrl":"https://doi.org/10.1145/3546000.3546026","url":null,"abstract":"The application of sensors enables mobile devices to generate amounts of content-aware data, such as trajectory, gyro, and video data. Moving video is an emerging new type of moving object that can provide a potential source for geo-referenced applications. Measuring the similarity of moving videos is widely used in traffic management, tourist recommendations, and location-based advertising. Our prior work proposed two similarity measures, the Largest Common View Subsequences can accurately calculate similar moving videos, and the View Vector Subsequences can fast calculate similar moving videos. In this paper, we proposed the searching top-k similar moving videos (K-SSMV). First, we give the problem definition of searching top-k similar moving videos. Then, we illustrated the strategy of searching for moving videos. Specifically, we sorted the video pairs by the most similar videos. Since the similar videos would be less than k, we first calculated the similarity of moving videos by the Largest Common View Subsequences algorithm, if the number of similar videos is less than k, we will adopt the View Vector Subsequences algorithm to compute the similarity of moving videos. Next, we mixed the candidate videos calculated by the Largest Common View Subsequences and the View Vector Subsequences algorithms, the searching top-k similar moving videos algorithm picked the top-k similar videos from candidate videos. Finally, we evaluated the performance of our proposed algorithms on the accuracy and computational cost. The experiments verified that our algorithms can efficiently search top-k similar moving videos.","PeriodicalId":196955,"journal":{"name":"Proceedings of the 6th International Conference on High Performance Compilation, Computing and Communications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129628340","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：