Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00250
Po-Chih Chen, Chih-Hung Chang, Yu-Wei Chan, Yin-Te Tsai, W. Chu
Falls are consistently the top cause of death among seniors. At a time when the global population is getting older and fewer births. The shortage of nursing staff seriously affects the health care of the elderly. If information and communication technology can be used, automatic detection and identification the elderly fall, we believe it can reduce the injury of the elderly due to falls. This paper proposes a method different from the previous wearable sensing device, which is based on the displacement of human relative positional parameters in the image to identify the occurrence of human fall. We implemented a system based on OpenPose and combined with the deep learning neural network model LSTM with time series, the image recognition is carried out, the human joint parameters of human posture falling and falling in the image are captured, and the identified parameters are simply filtered, and then the filtered parameters are used for model training.
{"title":"An Approach to Real-Time Fall Detection based on OpenPose and LSTM","authors":"Po-Chih Chen, Chih-Hung Chang, Yu-Wei Chan, Yin-Te Tsai, W. Chu","doi":"10.1109/COMPSAC54236.2022.00250","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00250","url":null,"abstract":"Falls are consistently the top cause of death among seniors. At a time when the global population is getting older and fewer births. The shortage of nursing staff seriously affects the health care of the elderly. If information and communication technology can be used, automatic detection and identification the elderly fall, we believe it can reduce the injury of the elderly due to falls. This paper proposes a method different from the previous wearable sensing device, which is based on the displacement of human relative positional parameters in the image to identify the occurrence of human fall. We implemented a system based on OpenPose and combined with the deep learning neural network model LSTM with time series, the image recognition is carried out, the human joint parameters of human posture falling and falling in the image are captured, and the identified parameters are simply filtered, and then the filtered parameters are used for model training.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129701651","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00105
Mengxi Zhou, R. Ramnath
In this paper, we present a nuanced exploration of deep-learning techniques (DL) for extracting structural infor-mation from document images generated from the digitization of business processes. The driving example presented is the extraction of columns and rows of tables using a simple stacked CNN architecture and a combination of ensemble techniques. In addition, the component models of the ensemble are diversified by training on datasets created by applying a “semantics-preserving” transformation on the base dataset. This “semantics-preserving” transformation also aims to alleviate hard recognition in certain noisy images commonly encountered in practice. Our experiments demonstrate how DL techniques can be applied and innovatively combined to measurably improve the accuracy of structure extraction.
{"title":"A Structure-Focused Deep Learning Approach for Table Recognition from Document Images","authors":"Mengxi Zhou, R. Ramnath","doi":"10.1109/COMPSAC54236.2022.00105","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00105","url":null,"abstract":"In this paper, we present a nuanced exploration of deep-learning techniques (DL) for extracting structural infor-mation from document images generated from the digitization of business processes. The driving example presented is the extraction of columns and rows of tables using a simple stacked CNN architecture and a combination of ensemble techniques. In addition, the component models of the ensemble are diversified by training on datasets created by applying a “semantics-preserving” transformation on the base dataset. This “semantics-preserving” transformation also aims to alleviate hard recognition in certain noisy images commonly encountered in practice. Our experiments demonstrate how DL techniques can be applied and innovatively combined to measurably improve the accuracy of structure extraction.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130421875","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00222
Jagan Moahan Reddy Danda, Kumar Priyansh, H. Shahriar, Hisham M. Haddad, A. Cuzzocrea, Nazmus Sakib
Predictive analytics is gaining momentum in health-care since the adoption of electronic health record (EHR) system in hospitals. In particular, machine learning models are built using the critical care EHR data and the information provided during the ICU admissions to predict the mortality of patients admitted in ICU. As per the MIMIC-IV dataset, the survival rate of patients admitted in ICU is found to be 89.76%. This paper proposes a hybrid prediction technique that uses Random Forest and XGBoost for predicting the mortality rate. The proposed techniques performed well in predicting mortality rate despite the class imbalance problem of the dataset. The experiments conducted on MIMIC-IV dataset yields prediction accuracy of 89.72%.
{"title":"Predicting Mortality Rate based on Comprehensive Features of Intensive Care Unit Patients","authors":"Jagan Moahan Reddy Danda, Kumar Priyansh, H. Shahriar, Hisham M. Haddad, A. Cuzzocrea, Nazmus Sakib","doi":"10.1109/COMPSAC54236.2022.00222","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00222","url":null,"abstract":"Predictive analytics is gaining momentum in health-care since the adoption of electronic health record (EHR) system in hospitals. In particular, machine learning models are built using the critical care EHR data and the information provided during the ICU admissions to predict the mortality of patients admitted in ICU. As per the MIMIC-IV dataset, the survival rate of patients admitted in ICU is found to be 89.76%. This paper proposes a hybrid prediction technique that uses Random Forest and XGBoost for predicting the mortality rate. The proposed techniques performed well in predicting mortality rate despite the class imbalance problem of the dataset. The experiments conducted on MIMIC-IV dataset yields prediction accuracy of 89.72%.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124175142","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00246
Sad Rafik, P. Lachat, N. Bennani, V. Rehn-Sonigo
The omnipresence of services offered by diverse applications leads customers to share more and more personal data, among which some are sensitive. Dishonest entities perform inference attacks by querying non-sensitive data in order to deduce the stored sensitive data. Detecting those attacks is still an open problem in a setting where a dishonest entity has access to distinct data controllers' databases containing data collected from the same customer. This problem has been addressed considering a centralized detection system. However, this approach is limited because of this centralized nature where the system protects the customers' privacy at the expense of the data controllers' privacy. Hence, we propose in this article the description of a distributed architecture to detect inference attacks in a multi-database context, while preserving the privacy of both the applications and the customers.
{"title":"Towards a Distributed Inference Detection System in a Multi-Database Context","authors":"Sad Rafik, P. Lachat, N. Bennani, V. Rehn-Sonigo","doi":"10.1109/COMPSAC54236.2022.00246","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00246","url":null,"abstract":"The omnipresence of services offered by diverse applications leads customers to share more and more personal data, among which some are sensitive. Dishonest entities perform inference attacks by querying non-sensitive data in order to deduce the stored sensitive data. Detecting those attacks is still an open problem in a setting where a dishonest entity has access to distinct data controllers' databases containing data collected from the same customer. This problem has been addressed considering a centralized detection system. However, this approach is limited because of this centralized nature where the system protects the customers' privacy at the expense of the data controllers' privacy. Hence, we propose in this article the description of a distributed architecture to detect inference attacks in a multi-database context, while preserving the privacy of both the applications and the customers.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121491639","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00187
Keisuke Hamamoto, Huimin Lu, Yujie Li, Tohru Kamiya, Y. Nakatoh, S. Serikawa
In recent years, robots have been used not only in factories. However, most robots currently used in such places can only perform the actions programmed to perform in a predefined space. For robots to become widespread in the future, not only in factories, distribution warehouses, and other places but also in homes and other environments where robots receive complex commands and their surroundings are constantly being updated, it is necessary to make robots intelligent. Therefore, this study proposed a deep learning grasp position estimation model using depth images to achieve intelligence in pick-and-place. This study used only depth images as the training data to build the deep learning model. Some previous studies have used RGB images and depth images. However, in this study, we used only depth images as training data because we expect the inference to be based on the object's shape, independent of the color information of the object. By performing inference based on the target object's shape, the deep learning model is expected to minimize the need for re-training when the target object package changes in the production line since it is not dependent on the RGB image. In this study, we propose a deep learning model that focuses on the stacked encoder-decoder structure of the Stacked Hourglass Network. We compared the proposed method with the baseline method in the same evaluation metrics and a real robot, which shows higher accuracy than other methods in previous studies.
{"title":"Grasp Position Estimation from Depth Image Using Stacked Hourglass Network Structure","authors":"Keisuke Hamamoto, Huimin Lu, Yujie Li, Tohru Kamiya, Y. Nakatoh, S. Serikawa","doi":"10.1109/COMPSAC54236.2022.00187","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00187","url":null,"abstract":"In recent years, robots have been used not only in factories. However, most robots currently used in such places can only perform the actions programmed to perform in a predefined space. For robots to become widespread in the future, not only in factories, distribution warehouses, and other places but also in homes and other environments where robots receive complex commands and their surroundings are constantly being updated, it is necessary to make robots intelligent. Therefore, this study proposed a deep learning grasp position estimation model using depth images to achieve intelligence in pick-and-place. This study used only depth images as the training data to build the deep learning model. Some previous studies have used RGB images and depth images. However, in this study, we used only depth images as training data because we expect the inference to be based on the object's shape, independent of the color information of the object. By performing inference based on the target object's shape, the deep learning model is expected to minimize the need for re-training when the target object package changes in the production line since it is not dependent on the RGB image. In this study, we propose a deep learning model that focuses on the stacked encoder-decoder structure of the Stacked Hourglass Network. We compared the proposed method with the baseline method in the same evaluation metrics and a real robot, which shows higher accuracy than other methods in previous studies.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121523912","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00138
Pei Li, Jiaqi Yin, Huibiao Zhu, Lili Xiao, M. Popovic
Transactional memory is designed for developing parallel programs and improving the efficiency of parallel pro-grams. PSTM (python software transactional memory) mainly supports multi-core parallel programs based on the python language. In order to better adapt to the developing requirements of distributed concurrent programs and enhance the safety of the system, DPSTM (distributed python software transactional memory) was developed. Compared with PSTM, DPSTM has the advantages of higher operating efficiency and stronger fault tolerance. In this paper, we apply CSP (Communicating Sequential Processes) to formally analyze the components of DPSTM v2 architecture, the data exchange process between components, and two different transaction processing modes. We use the model checker PAT (Process Analysis Toolkit) to model the DPSTM v2 architecture and verify eight properties, including deadlock freedom, ACI (atomicity, isolation, and consistency), sequential consistency, data server availability, read tolerance, and crash tolerance. The verification results show that the DPSTM v2 archi-tecture can guarantee all of the above properties. In particular, the normal operation of the system can be maintained when some of the data servers are crashed, ensuring the safety of a distributed system.
{"title":"Formal Analysis and Verification of DPSTM v2 Architecture Using CSP","authors":"Pei Li, Jiaqi Yin, Huibiao Zhu, Lili Xiao, M. Popovic","doi":"10.1109/COMPSAC54236.2022.00138","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00138","url":null,"abstract":"Transactional memory is designed for developing parallel programs and improving the efficiency of parallel pro-grams. PSTM (python software transactional memory) mainly supports multi-core parallel programs based on the python language. In order to better adapt to the developing requirements of distributed concurrent programs and enhance the safety of the system, DPSTM (distributed python software transactional memory) was developed. Compared with PSTM, DPSTM has the advantages of higher operating efficiency and stronger fault tolerance. In this paper, we apply CSP (Communicating Sequential Processes) to formally analyze the components of DPSTM v2 architecture, the data exchange process between components, and two different transaction processing modes. We use the model checker PAT (Process Analysis Toolkit) to model the DPSTM v2 architecture and verify eight properties, including deadlock freedom, ACI (atomicity, isolation, and consistency), sequential consistency, data server availability, read tolerance, and crash tolerance. The verification results show that the DPSTM v2 archi-tecture can guarantee all of the above properties. In particular, the normal operation of the system can be maintained when some of the data servers are crashed, ensuring the safety of a distributed system.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121665634","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00168
Beverly Abadines Quon, J. Gaudiot
Many works focus on optimizing machine learning models during their training phase, but fail to account how these models adapt into their model-serving phase once they are deployed into real world applications. In this phase models must process through streams of data that can evolve over time and distort the relationship between incoming data, causing concept drift. This paper proposes leveraging the advantages of emerging features stores in order to improve concept drift detection on unlabeled, dynamic data streams across multiple models. Firstly, we introduce Drift Detection on Distributed Datasets (QuaD), which combines classical drift detectors to make use of labeled and unlabeled data, and create local context (i.e. per live model) and global context (i.e. across multiple models). Secondly, we propose using feature store entities, SHAP values, and Collaborative Filtering (CF) to augment unlabeled data across multiple models. To the best of our knowledge, QuaD is the first work that examines the collective behavior of concept drift across multiple models and discerns associations between models that may share a susceptibility in a dynamic setting. QuaD uses a combination of performance-based and data distribution-based drift detectors and CF to capture varying types of concept drifts for labeled and unlabeled data streams and is modeled around the data abstraction provided by emerging feature stores.
{"title":"Concept drift detection for distributed multi-model machine learning systems","authors":"Beverly Abadines Quon, J. Gaudiot","doi":"10.1109/COMPSAC54236.2022.00168","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00168","url":null,"abstract":"Many works focus on optimizing machine learning models during their training phase, but fail to account how these models adapt into their model-serving phase once they are deployed into real world applications. In this phase models must process through streams of data that can evolve over time and distort the relationship between incoming data, causing concept drift. This paper proposes leveraging the advantages of emerging features stores in order to improve concept drift detection on unlabeled, dynamic data streams across multiple models. Firstly, we introduce Drift Detection on Distributed Datasets (QuaD), which combines classical drift detectors to make use of labeled and unlabeled data, and create local context (i.e. per live model) and global context (i.e. across multiple models). Secondly, we propose using feature store entities, SHAP values, and Collaborative Filtering (CF) to augment unlabeled data across multiple models. To the best of our knowledge, QuaD is the first work that examines the collective behavior of concept drift across multiple models and discerns associations between models that may share a susceptibility in a dynamic setting. QuaD uses a combination of performance-based and data distribution-based drift detectors and CF to capture varying types of concept drifts for labeled and unlabeled data streams and is modeled around the data abstraction provided by emerging feature stores.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124334679","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00179
Sonam Ramchand, Tariq Mahmood
The rise in big technologies has been demanding different concepts and practices for data exploitation; among them data lake is a recently emerged concept that is meant to deal with the heterogeneous data. Data lakes have been residing in the big data era since 2010, but there has not been any systematic review yet over data lake implementation. In this research survey, we conduct a review and provide a road map to researcher that elaborates what has happened to data lakes till now. We aim to give understanding for basic concept of data lakes and propose a novel data lake definition that could best describe the concept based on the literature review. One of the main problem while implementing data lake is deciding the technologies to use, this study covers technologies that can potentially be used for data lake implementation. Furthermore, data lake architectures and their variants are discussed in detail. Moreover, we analyze current state, challenges, pros and cons of the data lake. This study is all in one place for researchers who try to understand data lake concept, architectures, technologies, approaches, current state and challenges.
{"title":"Big data architectures for data lakes: A systematic literature review","authors":"Sonam Ramchand, Tariq Mahmood","doi":"10.1109/COMPSAC54236.2022.00179","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00179","url":null,"abstract":"The rise in big technologies has been demanding different concepts and practices for data exploitation; among them data lake is a recently emerged concept that is meant to deal with the heterogeneous data. Data lakes have been residing in the big data era since 2010, but there has not been any systematic review yet over data lake implementation. In this research survey, we conduct a review and provide a road map to researcher that elaborates what has happened to data lakes till now. We aim to give understanding for basic concept of data lakes and propose a novel data lake definition that could best describe the concept based on the literature review. One of the main problem while implementing data lake is deciding the technologies to use, this study covers technologies that can potentially be used for data lake implementation. Furthermore, data lake architectures and their variants are discussed in detail. Moreover, we analyze current state, challenges, pros and cons of the data lake. This study is all in one place for researchers who try to understand data lake concept, architectures, technologies, approaches, current state and challenges.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124421949","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00109
A. Kattepur, S. David
Data-center network configurations are crucial in ensuring end-to-end differentiated service performance within 5G. Data-center networks encom-pass two domains: (i) the fat-tree networking fabric with leaf, spine and super-spine layers (ii) data-center server nodes with container and workload placement policies. These have traditionally been managed within silos with context and configurations driven within each domain. In this work, we examine the effect of configuration changes in one domain and its effect on the other. We develop Madelyn, a multi-domain multi-agent rein-forcement learning framework for data-center networks that can propose network-aware, virtual network function placement. This framework takes into account the data-center fabric wights, drop rates, capacities, load balancing and traffic shaping. It also considers the network function pod placements based on affinity / anti-affinity rules, node capacities and taints/tolerations. Using this multi-agent framework, we provide network aware scheduling policies for differentiated network function virtualization services running on Kubernetes pods within data-center networks. The results are demonstrated over a real traffic dataset collected over Ericsson's testbed networks.
{"title":"Madelyn: Multi-Domain Multi-Agent Reinforcement Learning for Data-center Networks","authors":"A. Kattepur, S. David","doi":"10.1109/COMPSAC54236.2022.00109","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00109","url":null,"abstract":"Data-center network configurations are crucial in ensuring end-to-end differentiated service performance within 5G. Data-center networks encom-pass two domains: (i) the fat-tree networking fabric with leaf, spine and super-spine layers (ii) data-center server nodes with container and workload placement policies. These have traditionally been managed within silos with context and configurations driven within each domain. In this work, we examine the effect of configuration changes in one domain and its effect on the other. We develop Madelyn, a multi-domain multi-agent rein-forcement learning framework for data-center networks that can propose network-aware, virtual network function placement. This framework takes into account the data-center fabric wights, drop rates, capacities, load balancing and traffic shaping. It also considers the network function pod placements based on affinity / anti-affinity rules, node capacities and taints/tolerations. Using this multi-agent framework, we provide network aware scheduling policies for differentiated network function virtualization services running on Kubernetes pods within data-center networks. The results are demonstrated over a real traffic dataset collected over Ericsson's testbed networks.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124098264","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}
Pub Date : 2022-06-01DOI: 10.1109/COMPSAC54236.2022.00150
Kisoo Kim, Hyunju Kim, Dongman Lee
Activity Segmentation, dividing a continuous sensor stream into a set of activity segments, is a crucial pre-process in Human Activity Recognition (HAR) and it is required to be done in real-time for real-world smart services. Existing single-user activity segmentation schemes fail to correctly detect transition points due to concurrent and overlapping events from multiple users in case of Multi-user Collaborative Activity Recognition (MCAR). In this paper, we propose a novel scheme for activity segmentation for MCAR that expresses complex events and the correlations between them. For this, the proposed scheme first creates an event stream from a sensor stream and defines event sets in terms of time windows. For each time window, two types of correlations for every event pair are calculated: duration correlation and history correlation. After calculating event correlation, the change score of a time window is measured by comparing the calculated correlation values with those of the preceding windows. Then, the proposed scheme elects as an activity transition point a time window whose change score exceeds the transition threshold. We evaluate the proposed method on two multi-user collaborative activity datasets and experiment results show that the proposed scheme achieves better segmentation performance than existing approaches.
{"title":"A Correlation-based Real-time Segmentation Scheme for Multi-user Collaborative Activities","authors":"Kisoo Kim, Hyunju Kim, Dongman Lee","doi":"10.1109/COMPSAC54236.2022.00150","DOIUrl":"https://doi.org/10.1109/COMPSAC54236.2022.00150","url":null,"abstract":"Activity Segmentation, dividing a continuous sensor stream into a set of activity segments, is a crucial pre-process in Human Activity Recognition (HAR) and it is required to be done in real-time for real-world smart services. Existing single-user activity segmentation schemes fail to correctly detect transition points due to concurrent and overlapping events from multiple users in case of Multi-user Collaborative Activity Recognition (MCAR). In this paper, we propose a novel scheme for activity segmentation for MCAR that expresses complex events and the correlations between them. For this, the proposed scheme first creates an event stream from a sensor stream and defines event sets in terms of time windows. For each time window, two types of correlations for every event pair are calculated: duration correlation and history correlation. After calculating event correlation, the change score of a time window is measured by comparing the calculated correlation values with those of the preceding windows. Then, the proposed scheme elects as an activity transition point a time window whose change score exceeds the transition threshold. We evaluate the proposed method on two multi-user collaborative activity datasets and experiment results show that the proposed scheme achieves better segmentation performance than existing approaches.","PeriodicalId":330838,"journal":{"name":"2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126549218","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：