Proceedings of IEEE International Computer Performance and Dependability Symposium
Programmability, reliability, and scalability are system requirements that are essential to retai... more Programmability, reliability, and scalability are system requirements that are essential to retaining or establishing the high ground in the new world order for telecommunications solutions. For telephony systems to be successful in the next century, they must deliver “fifth-generation software flexibility” that enables interoperability while satisfying these 3 key requirements to give customers the applications they need, when they need
Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effe... more Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effect on the global economy and health. COVID-19 cases have been rapidly increasing, with no sign of stopping. As a result, test kits and accurate detection models are in short supply. Early identification of COVID-19 patients will help decrease the infection rate. Thus, developing an automatic algorithm that enables the early detection of COVID-19 is essential. Moreover, patient data are sensitive, and they must be protected to prevent malicious attackers from revealing information through model updates and reconstruction. In this study, we presented a higher privacy-preserving federated learning system for COVID-19 detection without sharing data among data owners. First, we constructed a federated learning system using chest X-ray images and symptom information. The purpose is to develop a decentralized model across multiple hospitals without sharing data. We found that adding the spatial...
Determining the price movement of stocks is a challenging problem to solve because of factors suc... more Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock’s historical time series data into a candlestick chart to elucidate patterns in the stock’s movement. Finally, we integrated the stock’s sentiment features and its candlestick chart to predict the...
Network slicing is a promising technology that network operators can deploy the services by slice... more Network slicing is a promising technology that network operators can deploy the services by slices with heterogeneous quality of service (QoS) requirements. However, an orchestrator for network operation with efficient slice resource provisioning algorithms is essential. This work stands on Internet service provider (ISP) to design an orchestrator analyzing the critical influencing factors, namely access control, scheduling, and resource migration, to systematically evolve a sustainable network. The scalability and flexibility of resources are jointly considered. The resource management problem is formulated as a mixed-integer programming (MIP) problem. A solution approach based on Lagrangian relaxation (LR) is proposed for the orchestrator to make decisions to satisfy the high QoS applications. It can investigate the resources required for access control within a cost-efficient resource pool and consider allocating or migrating resources efficiently in each network slice. For high ...
A combined edge and core cloud computing environment is a novel solution in 5G network slices. Th... more A combined edge and core cloud computing environment is a novel solution in 5G network slices. The clients’ high availability requirement is a challenge because it limits the possible admission control in front of the edge cloud. This work proposes an orchestrator with a mathematical programming model in a global viewpoint to solve resource management problems and satisfying the clients’ high availability requirements. The proposed Lagrangian relaxation-based approach is adopted to solve the problems at a near-optimal level for increasing the system revenue. A promising and straightforward resource management approach and several experimental cases are used to evaluate the efficiency and effectiveness. Preliminary results are presented as performance evaluations to verify the proposed approach’s suitability for edge and core cloud computing environments. The proposed orchestrator significantly enables the network slicing services and efficiently enhances the clients’ satisfaction of...
2017 IEEE 22nd Pacific Rim International Symposium on Dependable Computing (PRDC), 2017
Differential privacy is a recent notion of data privacy protection, which does not matter even wh... more Differential privacy is a recent notion of data privacy protection, which does not matter even when an attacker has arbitrary background knowledge in advance. Consequently, it is viewed as a reliable protection mechanism for sensitive information. Differential privacy introduces Laplace noise to hide the true value in a dataset while preserving statistic properties. However, the large amount of Laplace noise added into a dataset is typically defined by the discursive scale parameter of the Laplace distribution. The privacy parameter ε in differential privacy is with theoretical interpretation, but the implication on the risk of data disclosure (called RoD for short) in practice has not yet been studied. Moreover, choosing appropriate value for ε is not an easy task since it impacts the level of privacy in a dataset significantly. In this paper, we define and evaluate the RoD in a dataset with either numerical or binary attributes for numerical or counting queries with multiple attri...
2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), 2017
Differential privacy (DP) is a popular technique for protecting individual privacy and at the sam... more Differential privacy (DP) is a popular technique for protecting individual privacy and at the same for releasing data for public use. However, very few research efforts are devoted to the balance between the corresponding risk of data disclosure (RoD) and data utility. In this paper, we propose data-driven approaches for differentially private data release to evaluate RoD, and offer algorithms to evaluate whether the differentially private synthetic dataset has sufficient privacy. In addition to the privacy, the utility of the synthetic dataset is an important metric for differentially private data release. Thus, we also propose the data-driven algorithm via curve fitting to measure and predict the error of the statistical result incurred by random noise added to the original dataset. Finally, we present an algorithm for choosing appropriate privacy budget E with the balance between the privacy and utility.
As the IoT ecosystem becoming more and more mature, hardware and software vendors are trying crea... more As the IoT ecosystem becoming more and more mature, hardware and software vendors are trying create new value by connecting all kinds of devices together via IoT. IoT devices are usually equipped with sensors to collect data, and the data collected are transmitted over the air via different kinds of wireless connection. To extract the value of the data collected, the data owner may choose to seek for third-party help on data analysis, or even of the data to the public for more insight. In this scenario it is important to protect the released data from privacy leakage. Here we propose that differential privacy, as a de-identification technique, can be a useful approach to add privacy protection to the data released, as well as to prevent the collected from intercepted and decoded during over-the-air transmission. A way to increase the accuracy of the count queries performed on the edge cases in a synthetic database is also presented in this research.
2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), 2017
Cloud computing services provide flexible computing and storage resources to process large amount... more Cloud computing services provide flexible computing and storage resources to process large amount of datasets. In-memory techniques keep the frequently used data into faster and more expensive storage media for improving performance of data processing services. Data prefetching aims to move data to low-latency storage media to meet requirements of performance. However, existing mechanisms do not consider how to benefit the data processing applications which do not frequently access the same datasets. Another problem is how to reclaim memory resources without affecting other running applications. In this paper, we provide a Scheduling-Aware Data Prefetching (SADP) mechanism for data processing services in a cloud data center. The SADP includes data prefetching and data eviction mechanisms. It firstly evicts the data from memory to release resources for hosting other data blocks, and then it caches the data that will be used in near future. Finally, real-testbed experiments are perfor...
This paper studies the conditions under which peer-to-peer (P2P) technology may be benecial in pr... more This paper studies the conditions under which peer-to-peer (P2P) technology may be benecial in providing IPTV ser-vices over typical network architectures. It has two major contributions. First, we contrast two network models used to study the performance of such a system: a commonly used logical \Internet as a cloud " model and a \physical " model that re ects the characteristics of the underlying network. Speci cally, we show that the cloud model overlooks impor-tant architectural aspects of the network and may drastically overstate the benets of P2P technology by a factor of 3 or more. Second, we provide a cost-benet analysis of P2P video content delivery focusing on the prot trade-os for dierent pricing/incentive models rather than purely on ca-pacity maximization. In particular, we nd that under high volume of video demand, a P2P built-in incentive model per-forms better than any other model for both high-denition and standard-denition media, while the usage-based mod...
2017 International Conference on Fuzzy Theory and Its Applications (iFUZZY)
This paper presents a fuzzy state monitoring system for a machine tool spindle motor, which inclu... more This paper presents a fuzzy state monitoring system for a machine tool spindle motor, which includes the statistical characteristics of the dynamic speed. Therefore, we use statistical methods for vibration signal mining, and find the corresponding actual speed value from the spectrum. Then the statistical properties of each machine state are defined from the distribution of significant indexes, and the rules of fuzzy inference system. The experimental results show that the proposed strategy not only effectively identifies the different states of the spindle motor, but also has the adaptability under the frequency conversion.
2020 International Conference on System Science and Engineering (ICSSE), 2020
This research aims to propose a signal fusion-based artificial neural network algorithm for fault... more This research aims to propose a signal fusion-based artificial neural network algorithm for fault diagnosis of rotating machinery. Firstly, the fused signal becomes the running track, and then it is scaled up to grasp the subtle features. However, after calculating the weights, the characteristic distribution of each operating state is obtained. In this way, the fused signal has more prominent characteristics. The experimental results show that pattern recognition networks and feedforward networks have relatively stable and excellent performance. In different cases, the accuracy is maintained at 94~100 %, and the calculation cost is 1~25 seconds. In future research, more system parameters and optimization of the algorithm are considered. It is expected that the robustness of the algorithm will be improved.
2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)
This talk summarizes the genesis of software aging and rejuvenation as presented in the handbook ... more This talk summarizes the genesis of software aging and rejuvenation as presented in the handbook of software aging and rejuvenation. It also lays out possible future directions to reflect the content of the concluding chapter of the handbook.
2019 International Conference on Advanced Mechatronic Systems (ICAMechS)
This article focuses on embedded vision systems and their automation and intelligent technology r... more This article focuses on embedded vision systems and their automation and intelligent technology research, such as illumination, focal length, and surface roughness analysis. In illuminance, YCbCr color space conversion is used to obtain the contrast of brightness, and it becomes the basis for judging the illuminance state. In the focal length, the frequency domain space conversion is used to perform the spectral convolution operation, and it becomes the basis for judging the focal length state. In the surface roughness, the result of the spectral convolution operation becomes the input of the fuzzy C-means clustering algorithm and helps the fuzzy inference system (2 input -1 output) to establish the membership function and rule base. From the inference results of the fuzzy inference system, it is known that the surface roughness can be divided into three categories to obtain an accuracy of 91.67 %, and only five data are misjudged. At the same time, we hope that the low-cost embedded vision system can help the industry upgrade.
2017 IEEE 7th International Symposium on Cloud and Service Computing (SC2)
In the era of Industry 4.0 we seek to create a smart factory environment in which everything is c... more In the era of Industry 4.0 we seek to create a smart factory environment in which everything is connected and well coordinated. Smart factories will also be connected to cloud service and/or all kinds of partners outside the boundary of the factory to achieve even better efficiency. However network connectivity also brings threats along with the promise of better efficiency, and makes Smart factories more vulnerable to intruders. There were already security incidents such as Iran's nuclear facilities' infection by the Stuxnet virus and German's steel mill destroyed by hackers in 2014. To protect smart factories from such threats traditional means of intrusion detection on the Internet could be used, but we must also refine them and have them adapted to the context of Industry 4.0. For example, network traffic in a smart factory might be more uniformed and predictable compared to the traffic on the Internet, but one should tolerate much less anomaly as the traffic is usually mission critical, and will cause much more loss once intrusion happens. The most widely used signature-based intrusion detection systems come with a large library of signatures that contains known attack have been proved to be very useful, but without the ability to detect unknown attack. We turn to supervised data mining algorithms to detect intrusions, which will help us to detect intrusions with similar properties with known attacks but not necessarily fully match the signatures in the library. In this study a simulated smart factory environment was built and a series of attacks were implemented. Neural network and decision trees were used to classify the traffic generated from this simulated environment. From the experiments we conclude that for the data set we used, decision tree performed better than neural network for detecting intrusion as it provides better accuracy, lower false negative rate and faster model building time.
Proceedings of IEEE International Computer Performance and Dependability Symposium
Programmability, reliability, and scalability are system requirements that are essential to retai... more Programmability, reliability, and scalability are system requirements that are essential to retaining or establishing the high ground in the new world order for telecommunications solutions. For telephony systems to be successful in the next century, they must deliver “fifth-generation software flexibility” that enables interoperability while satisfying these 3 key requirements to give customers the applications they need, when they need
Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effe... more Coronavirus (COVID-19) has created an unprecedented global crisis because of its detrimental effect on the global economy and health. COVID-19 cases have been rapidly increasing, with no sign of stopping. As a result, test kits and accurate detection models are in short supply. Early identification of COVID-19 patients will help decrease the infection rate. Thus, developing an automatic algorithm that enables the early detection of COVID-19 is essential. Moreover, patient data are sensitive, and they must be protected to prevent malicious attackers from revealing information through model updates and reconstruction. In this study, we presented a higher privacy-preserving federated learning system for COVID-19 detection without sharing data among data owners. First, we constructed a federated learning system using chest X-ray images and symptom information. The purpose is to develop a decentralized model across multiple hospitals without sharing data. We found that adding the spatial...
Determining the price movement of stocks is a challenging problem to solve because of factors suc... more Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock’s historical time series data into a candlestick chart to elucidate patterns in the stock’s movement. Finally, we integrated the stock’s sentiment features and its candlestick chart to predict the...
Network slicing is a promising technology that network operators can deploy the services by slice... more Network slicing is a promising technology that network operators can deploy the services by slices with heterogeneous quality of service (QoS) requirements. However, an orchestrator for network operation with efficient slice resource provisioning algorithms is essential. This work stands on Internet service provider (ISP) to design an orchestrator analyzing the critical influencing factors, namely access control, scheduling, and resource migration, to systematically evolve a sustainable network. The scalability and flexibility of resources are jointly considered. The resource management problem is formulated as a mixed-integer programming (MIP) problem. A solution approach based on Lagrangian relaxation (LR) is proposed for the orchestrator to make decisions to satisfy the high QoS applications. It can investigate the resources required for access control within a cost-efficient resource pool and consider allocating or migrating resources efficiently in each network slice. For high ...
A combined edge and core cloud computing environment is a novel solution in 5G network slices. Th... more A combined edge and core cloud computing environment is a novel solution in 5G network slices. The clients’ high availability requirement is a challenge because it limits the possible admission control in front of the edge cloud. This work proposes an orchestrator with a mathematical programming model in a global viewpoint to solve resource management problems and satisfying the clients’ high availability requirements. The proposed Lagrangian relaxation-based approach is adopted to solve the problems at a near-optimal level for increasing the system revenue. A promising and straightforward resource management approach and several experimental cases are used to evaluate the efficiency and effectiveness. Preliminary results are presented as performance evaluations to verify the proposed approach’s suitability for edge and core cloud computing environments. The proposed orchestrator significantly enables the network slicing services and efficiently enhances the clients’ satisfaction of...
2017 IEEE 22nd Pacific Rim International Symposium on Dependable Computing (PRDC), 2017
Differential privacy is a recent notion of data privacy protection, which does not matter even wh... more Differential privacy is a recent notion of data privacy protection, which does not matter even when an attacker has arbitrary background knowledge in advance. Consequently, it is viewed as a reliable protection mechanism for sensitive information. Differential privacy introduces Laplace noise to hide the true value in a dataset while preserving statistic properties. However, the large amount of Laplace noise added into a dataset is typically defined by the discursive scale parameter of the Laplace distribution. The privacy parameter ε in differential privacy is with theoretical interpretation, but the implication on the risk of data disclosure (called RoD for short) in practice has not yet been studied. Moreover, choosing appropriate value for ε is not an easy task since it impacts the level of privacy in a dataset significantly. In this paper, we define and evaluate the RoD in a dataset with either numerical or binary attributes for numerical or counting queries with multiple attri...
2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), 2017
Differential privacy (DP) is a popular technique for protecting individual privacy and at the sam... more Differential privacy (DP) is a popular technique for protecting individual privacy and at the same for releasing data for public use. However, very few research efforts are devoted to the balance between the corresponding risk of data disclosure (RoD) and data utility. In this paper, we propose data-driven approaches for differentially private data release to evaluate RoD, and offer algorithms to evaluate whether the differentially private synthetic dataset has sufficient privacy. In addition to the privacy, the utility of the synthetic dataset is an important metric for differentially private data release. Thus, we also propose the data-driven algorithm via curve fitting to measure and predict the error of the statistical result incurred by random noise added to the original dataset. Finally, we present an algorithm for choosing appropriate privacy budget E with the balance between the privacy and utility.
As the IoT ecosystem becoming more and more mature, hardware and software vendors are trying crea... more As the IoT ecosystem becoming more and more mature, hardware and software vendors are trying create new value by connecting all kinds of devices together via IoT. IoT devices are usually equipped with sensors to collect data, and the data collected are transmitted over the air via different kinds of wireless connection. To extract the value of the data collected, the data owner may choose to seek for third-party help on data analysis, or even of the data to the public for more insight. In this scenario it is important to protect the released data from privacy leakage. Here we propose that differential privacy, as a de-identification technique, can be a useful approach to add privacy protection to the data released, as well as to prevent the collected from intercepted and decoded during over-the-air transmission. A way to increase the accuracy of the count queries performed on the edge cases in a synthetic database is also presented in this research.
2017 IEEE 31st International Conference on Advanced Information Networking and Applications (AINA), 2017
Cloud computing services provide flexible computing and storage resources to process large amount... more Cloud computing services provide flexible computing and storage resources to process large amount of datasets. In-memory techniques keep the frequently used data into faster and more expensive storage media for improving performance of data processing services. Data prefetching aims to move data to low-latency storage media to meet requirements of performance. However, existing mechanisms do not consider how to benefit the data processing applications which do not frequently access the same datasets. Another problem is how to reclaim memory resources without affecting other running applications. In this paper, we provide a Scheduling-Aware Data Prefetching (SADP) mechanism for data processing services in a cloud data center. The SADP includes data prefetching and data eviction mechanisms. It firstly evicts the data from memory to release resources for hosting other data blocks, and then it caches the data that will be used in near future. Finally, real-testbed experiments are perfor...
This paper studies the conditions under which peer-to-peer (P2P) technology may be benecial in pr... more This paper studies the conditions under which peer-to-peer (P2P) technology may be benecial in providing IPTV ser-vices over typical network architectures. It has two major contributions. First, we contrast two network models used to study the performance of such a system: a commonly used logical \Internet as a cloud " model and a \physical " model that re ects the characteristics of the underlying network. Speci cally, we show that the cloud model overlooks impor-tant architectural aspects of the network and may drastically overstate the benets of P2P technology by a factor of 3 or more. Second, we provide a cost-benet analysis of P2P video content delivery focusing on the prot trade-os for dierent pricing/incentive models rather than purely on ca-pacity maximization. In particular, we nd that under high volume of video demand, a P2P built-in incentive model per-forms better than any other model for both high-denition and standard-denition media, while the usage-based mod...
2017 International Conference on Fuzzy Theory and Its Applications (iFUZZY)
This paper presents a fuzzy state monitoring system for a machine tool spindle motor, which inclu... more This paper presents a fuzzy state monitoring system for a machine tool spindle motor, which includes the statistical characteristics of the dynamic speed. Therefore, we use statistical methods for vibration signal mining, and find the corresponding actual speed value from the spectrum. Then the statistical properties of each machine state are defined from the distribution of significant indexes, and the rules of fuzzy inference system. The experimental results show that the proposed strategy not only effectively identifies the different states of the spindle motor, but also has the adaptability under the frequency conversion.
2020 International Conference on System Science and Engineering (ICSSE), 2020
This research aims to propose a signal fusion-based artificial neural network algorithm for fault... more This research aims to propose a signal fusion-based artificial neural network algorithm for fault diagnosis of rotating machinery. Firstly, the fused signal becomes the running track, and then it is scaled up to grasp the subtle features. However, after calculating the weights, the characteristic distribution of each operating state is obtained. In this way, the fused signal has more prominent characteristics. The experimental results show that pattern recognition networks and feedforward networks have relatively stable and excellent performance. In different cases, the accuracy is maintained at 94~100 %, and the calculation cost is 1~25 seconds. In future research, more system parameters and optimization of the algorithm are considered. It is expected that the robustness of the algorithm will be improved.
2020 IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW)
This talk summarizes the genesis of software aging and rejuvenation as presented in the handbook ... more This talk summarizes the genesis of software aging and rejuvenation as presented in the handbook of software aging and rejuvenation. It also lays out possible future directions to reflect the content of the concluding chapter of the handbook.
2019 International Conference on Advanced Mechatronic Systems (ICAMechS)
This article focuses on embedded vision systems and their automation and intelligent technology r... more This article focuses on embedded vision systems and their automation and intelligent technology research, such as illumination, focal length, and surface roughness analysis. In illuminance, YCbCr color space conversion is used to obtain the contrast of brightness, and it becomes the basis for judging the illuminance state. In the focal length, the frequency domain space conversion is used to perform the spectral convolution operation, and it becomes the basis for judging the focal length state. In the surface roughness, the result of the spectral convolution operation becomes the input of the fuzzy C-means clustering algorithm and helps the fuzzy inference system (2 input -1 output) to establish the membership function and rule base. From the inference results of the fuzzy inference system, it is known that the surface roughness can be divided into three categories to obtain an accuracy of 91.67 %, and only five data are misjudged. At the same time, we hope that the low-cost embedded vision system can help the industry upgrade.
2017 IEEE 7th International Symposium on Cloud and Service Computing (SC2)
In the era of Industry 4.0 we seek to create a smart factory environment in which everything is c... more In the era of Industry 4.0 we seek to create a smart factory environment in which everything is connected and well coordinated. Smart factories will also be connected to cloud service and/or all kinds of partners outside the boundary of the factory to achieve even better efficiency. However network connectivity also brings threats along with the promise of better efficiency, and makes Smart factories more vulnerable to intruders. There were already security incidents such as Iran's nuclear facilities' infection by the Stuxnet virus and German's steel mill destroyed by hackers in 2014. To protect smart factories from such threats traditional means of intrusion detection on the Internet could be used, but we must also refine them and have them adapted to the context of Industry 4.0. For example, network traffic in a smart factory might be more uniformed and predictable compared to the traffic on the Internet, but one should tolerate much less anomaly as the traffic is usually mission critical, and will cause much more loss once intrusion happens. The most widely used signature-based intrusion detection systems come with a large library of signatures that contains known attack have been proved to be very useful, but without the ability to detect unknown attack. We turn to supervised data mining algorithms to detect intrusions, which will help us to detect intrusions with similar properties with known attacks but not necessarily fully match the signatures in the library. In this study a simulated smart factory environment was built and a series of attacks were implemented. Neural network and decision trees were used to classify the traffic generated from this simulated environment. From the experiments we conclude that for the data set we used, decision tree performed better than neural network for detecting intrusion as it provides better accuracy, lower false negative rate and faster model building time.
Uploads
Papers