Pub Date : 2023-06-01DOI: 10.1109/SMARTCOMP58114.2023.00018
Kuan-Chien Wang, J. Zhang, Jingquan Huang, Qi Li, Minmin Sun, Kazuya Sakai, Wei-Shinn Ku
With the growing consumption of online visual contents, there is an urgent need for video translation in order to reach a wider audience from around the world. However, the materials after direct translation and dubbing are unable to create a natural audio-visual experience since the translated speech and lip movement are often out of sync. To improve the viewing experience, an accurate automatic lip-movement synchronization generation system is necessary. To improve the accuracy and visual quality of speech to lip generation, this research proposes two techniques: Embedding Attention Mechanisms in Convolution Layers and Deploying SSIM as Loss Function in Visual Quality Discriminator. The proposed system as well as several other ones are tested on three audiovisual datasets. The results show that our proposed methods achieve superior performance over the state-of-the-art speech to lip synthesis on not only the accuracy but also the visual quality of audio-lip synchronization generation.
{"title":"CA-Wav2Lip: Coordinate Attention-based Speech To Lip Synthesis In The Wild","authors":"Kuan-Chien Wang, J. Zhang, Jingquan Huang, Qi Li, Minmin Sun, Kazuya Sakai, Wei-Shinn Ku","doi":"10.1109/SMARTCOMP58114.2023.00018","DOIUrl":"https://doi.org/10.1109/SMARTCOMP58114.2023.00018","url":null,"abstract":"With the growing consumption of online visual contents, there is an urgent need for video translation in order to reach a wider audience from around the world. However, the materials after direct translation and dubbing are unable to create a natural audio-visual experience since the translated speech and lip movement are often out of sync. To improve the viewing experience, an accurate automatic lip-movement synchronization generation system is necessary. To improve the accuracy and visual quality of speech to lip generation, this research proposes two techniques: Embedding Attention Mechanisms in Convolution Layers and Deploying SSIM as Loss Function in Visual Quality Discriminator. The proposed system as well as several other ones are tested on three audiovisual datasets. The results show that our proposed methods achieve superior performance over the state-of-the-art speech to lip synthesis on not only the accuracy but also the visual quality of audio-lip synchronization generation.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123384555","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 : 2023-06-01DOI: 10.1109/smartcomp58114.2023.00007
{"title":"SMARTCOMP 2023 Technical Program Committee","authors":"","doi":"10.1109/smartcomp58114.2023.00007","DOIUrl":"https://doi.org/10.1109/smartcomp58114.2023.00007","url":null,"abstract":"","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127622619","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 : 2023-06-01DOI: 10.1109/SMARTCOMP58114.2023.00067
Ghazal Alinezhad Noghre
Video anomaly detection is a significant problem in computer vision that aims to detect unusual or abnormal behaviors in video data that can be used to enhance public safety. Given the widespread deployment of cameras in public areas, video anomaly detection for public safety has become increasingly important in recent years. There are numerous applications, including but not limited to security, traffic monitoring, healthcare, and manufacturing, where video anomaly detection can be useful. However, anomaly detection in nature is an open-set problem that further complicates the task. Moreover, the definition of anomalous behavior may differ in various environments, adding to real-world anomaly detection challenges. On the other hand, addressing ethical issues and privacy concerns related to this task is also crucial. We aim to design an anomaly detection method that uses non-identifiable features such as pose, trajectory, and optical flow to avoid discrimination against distinct minority groups and safeguard the privacy of individuals.
{"title":"Privacy-preserving Real-world Video Anomaly Detection","authors":"Ghazal Alinezhad Noghre","doi":"10.1109/SMARTCOMP58114.2023.00067","DOIUrl":"https://doi.org/10.1109/SMARTCOMP58114.2023.00067","url":null,"abstract":"Video anomaly detection is a significant problem in computer vision that aims to detect unusual or abnormal behaviors in video data that can be used to enhance public safety. Given the widespread deployment of cameras in public areas, video anomaly detection for public safety has become increasingly important in recent years. There are numerous applications, including but not limited to security, traffic monitoring, healthcare, and manufacturing, where video anomaly detection can be useful. However, anomaly detection in nature is an open-set problem that further complicates the task. Moreover, the definition of anomalous behavior may differ in various environments, adding to real-world anomaly detection challenges. On the other hand, addressing ethical issues and privacy concerns related to this task is also crucial. We aim to design an anomaly detection method that uses non-identifiable features such as pose, trajectory, and optical flow to avoid discrimination against distinct minority groups and safeguard the privacy of individuals.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"87 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127996785","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 : 2023-06-01DOI: 10.1109/smartcomp58114.2023.00005
{"title":"Message from the General and TPC Co-Chairs","authors":"","doi":"10.1109/smartcomp58114.2023.00005","DOIUrl":"https://doi.org/10.1109/smartcomp58114.2023.00005","url":null,"abstract":"","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129020870","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 : 2023-06-01DOI: 10.1109/smartcomp58114.2023.00016
{"title":"SSC 2023 Message from Workshop Co-Chairs","authors":"","doi":"10.1109/smartcomp58114.2023.00016","DOIUrl":"https://doi.org/10.1109/smartcomp58114.2023.00016","url":null,"abstract":"","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130823177","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 : 2023-06-01DOI: 10.1109/SMARTCOMP58114.2023.00065
Mostafa Zaman
The escalating population growth and urbanization have led to a surge in the demand for smart cities. Nonetheless, handling and evaluating the vast data produced by Internet of Things (IoT) sensors requires significant effort. Therefore, implementing intelligent decision support systems is crucial for analyzing real-time data and optimizing city operations while tackling uncertain events. This study discusses the architectural flow diagram of a smart city decision support system that employs reinforcement learning techniques to enhance traffic management, minimize energy consumption, elevate public safety, and reduce risks in a constantly changing and unpredictable environment. This system comprises various components that work in tandem to provide customized real-time recommendations for a given situation. The capacity of the system to produce recommendations in real-time while taking into account the likelihood of various outcomes has the potential to enhance performance and facilitate more efficient decision-making in intricate settings. In general, this system will exhibit the capability to improve emergency response and public safety to a considerable extent in smart cities.
{"title":"A Model Based Decision Support System for Smart Cities","authors":"Mostafa Zaman","doi":"10.1109/SMARTCOMP58114.2023.00065","DOIUrl":"https://doi.org/10.1109/SMARTCOMP58114.2023.00065","url":null,"abstract":"The escalating population growth and urbanization have led to a surge in the demand for smart cities. Nonetheless, handling and evaluating the vast data produced by Internet of Things (IoT) sensors requires significant effort. Therefore, implementing intelligent decision support systems is crucial for analyzing real-time data and optimizing city operations while tackling uncertain events. This study discusses the architectural flow diagram of a smart city decision support system that employs reinforcement learning techniques to enhance traffic management, minimize energy consumption, elevate public safety, and reduce risks in a constantly changing and unpredictable environment. This system comprises various components that work in tandem to provide customized real-time recommendations for a given situation. The capacity of the system to produce recommendations in real-time while taking into account the likelihood of various outcomes has the potential to enhance performance and facilitate more efficient decision-making in intricate settings. In general, this system will exhibit the capability to improve emergency response and public safety to a considerable extent in smart cities.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116881000","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 : 2023-06-01DOI: 10.1109/SMARTCOMP58114.2023.00043
C. Cicconetti, M. Conti, E. Lella, Pietro Noviello, Gennaro Davide Paduanelli, Andrea Passarella, Elisabetta Storelli
In this demonstration, we showcase the realization of a prototype of an edge computing network, where the client and edge domains both host simulated Quantum Key Distribution devices, for a hospital use case. In particular, digital health applications using the Function-as-a-Service (FaaS) paradigm will invoke remote functions provided by an Apache OpenWhisk cluster deployed in the edge infrastructure, where the arguments and return value are encrypted using keys generated through an underlying simulated QKD point-to-point network. All the interactions in the control/management plane are handled through standard interfaces defined by the ETSI MEC and QKD industry study groups.
{"title":"A Prototype for QKD-secure Serverless Computing with ETSI MEC","authors":"C. Cicconetti, M. Conti, E. Lella, Pietro Noviello, Gennaro Davide Paduanelli, Andrea Passarella, Elisabetta Storelli","doi":"10.1109/SMARTCOMP58114.2023.00043","DOIUrl":"https://doi.org/10.1109/SMARTCOMP58114.2023.00043","url":null,"abstract":"In this demonstration, we showcase the realization of a prototype of an edge computing network, where the client and edge domains both host simulated Quantum Key Distribution devices, for a hospital use case. In particular, digital health applications using the Function-as-a-Service (FaaS) paradigm will invoke remote functions provided by an Apache OpenWhisk cluster deployed in the edge infrastructure, where the arguments and return value are encrypted using keys generated through an underlying simulated QKD point-to-point network. All the interactions in the control/management plane are handled through standard interfaces defined by the ETSI MEC and QKD industry study groups.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134271802","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 : 2023-06-01DOI: 10.1109/smartcomp58114.2023.00057
Raghav Mehrotra-Venkat, N. Dutt, J. Rousseau
Several recent studies, in the aftermath of Covid-19, point to dangers of social isolation that negatively impacts both mental and physical health especially amongst older adults. Isolation often leads to self-destructive behaviour such as drug and alcohol misuse deteriorating the quality of life and compounding health complications. Recent research has explored several technologies to detect the onset of isolation and to trigger interventions (e.g., nudge caregivers, etc.) to mitigate its impact. Such mechanisms span a range from using survey instruments, using biometrics to detect stress (an effect of isolation), and those using monitoring social interactions to detect loneliness amongst individuals. This paper studies biometric based and social interaction-based methods with the objective to understand their relative benefits/disadvantages and explores their combined usage to create a robust isolation detection mechanism. In particular, we explore the design of an integrated system based on both biometric (via wearables) and social interaction data (using call log analysis) to study their efficacy both individually and in combination.
{"title":"Robust Detection of Social Isolation in Older Adults by Combining Biometrics with Social Interaction Data","authors":"Raghav Mehrotra-Venkat, N. Dutt, J. Rousseau","doi":"10.1109/smartcomp58114.2023.00057","DOIUrl":"https://doi.org/10.1109/smartcomp58114.2023.00057","url":null,"abstract":"Several recent studies, in the aftermath of Covid-19, point to dangers of social isolation that negatively impacts both mental and physical health especially amongst older adults. Isolation often leads to self-destructive behaviour such as drug and alcohol misuse deteriorating the quality of life and compounding health complications. Recent research has explored several technologies to detect the onset of isolation and to trigger interventions (e.g., nudge caregivers, etc.) to mitigate its impact. Such mechanisms span a range from using survey instruments, using biometrics to detect stress (an effect of isolation), and those using monitoring social interactions to detect loneliness amongst individuals. This paper studies biometric based and social interaction-based methods with the objective to understand their relative benefits/disadvantages and explores their combined usage to create a robust isolation detection mechanism. In particular, we explore the design of an integrated system based on both biometric (via wearables) and social interaction data (using call log analysis) to study their efficacy both individually and in combination.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134022433","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 : 2023-06-01DOI: 10.1109/SMARTCOMP58114.2023.00086
Alex Howe, M. Papa
This paper evaluates the importance of feature exploration and engineering when applying machine learning for intrusion detection in OT (Operational Technology) networks. Data used consisted of raw network traffic captures from a simulated OT environment communicating over the Modbus/TCP protocol. Feature engineering efforts identified thirty eight attributes of interest at the different layers of the network stack. The Random Forest algorithm was used to analyze the importance of each feature for the detection of anomalous network behavior. Both supervised and unsupervised learning methods were evaluated including Random Forest, Support Vector Machines, K-Nearest Neighbors, K-Means Clustering, and Isolation Forest. Results indicate that statistical based features as well as features derived from the protocol and application layers contained information best suited for detecting anomalous OT behavior. Additionally, variable importance-based feature selection helped reduce complexity and improved detection rate when compared with models trained on the original high dimensional data. Random Forest and Support Vector Machines had the best detection performance but required a large amount of labeled data for training and validation. Notably, Isolation Forest shows potential for anomaly detection in OT networks as it requires no labeled data and produced promising results.
{"title":"Feature Engineering in Machine Learning-Based Intrusion Detection Systems for OT Networks","authors":"Alex Howe, M. Papa","doi":"10.1109/SMARTCOMP58114.2023.00086","DOIUrl":"https://doi.org/10.1109/SMARTCOMP58114.2023.00086","url":null,"abstract":"This paper evaluates the importance of feature exploration and engineering when applying machine learning for intrusion detection in OT (Operational Technology) networks. Data used consisted of raw network traffic captures from a simulated OT environment communicating over the Modbus/TCP protocol. Feature engineering efforts identified thirty eight attributes of interest at the different layers of the network stack. The Random Forest algorithm was used to analyze the importance of each feature for the detection of anomalous network behavior. Both supervised and unsupervised learning methods were evaluated including Random Forest, Support Vector Machines, K-Nearest Neighbors, K-Means Clustering, and Isolation Forest. Results indicate that statistical based features as well as features derived from the protocol and application layers contained information best suited for detecting anomalous OT behavior. Additionally, variable importance-based feature selection helped reduce complexity and improved detection rate when compared with models trained on the original high dimensional data. Random Forest and Support Vector Machines had the best detection performance but required a large amount of labeled data for training and validation. Notably, Isolation Forest shows potential for anomaly detection in OT networks as it requires no labeled data and produced promising results.","PeriodicalId":163556,"journal":{"name":"2023 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131951926","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：