Kai Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kai Yang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Dongxiao Zhu
Wayne State University
2 shared publications - Hossein Badri
Department of Computer Science, Wayne State University, Detroit, USA
2 shared publications - Anoop Prakash
Wayne State University
1 shared publication - Daniel Grosu
Wayne State University
1 shared publication - Milad Zafar Nezhad
Department of Industrial and Systems Engineering Wayne State University 4815 Fourth Street 48202 Detroit MI USA
1 shared publication - Mohammad Hessam Olya
Department of of Computer Science Wayne State University Detroit USA
1 shared publication
Latest Publications
- 13 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 31 (4) , 909-922
Energy-Aware Application Placement in Mobile Edge Computing: A Stochastic Optimization Approach
The Quality of Service (QoS) in Mobile Edge Computing (MEC) systems is significantly dependent on the application offloading and placement decisions. Due to the movement of users in MEC networks, an optimal application placement might turn into the least efficient placement in few minutes. Thus, it is crucial to take the dynamics of the system into account when designing application placement mechanisms. On the other hand, energy consumption of servers is a significant component of the cost of services in MEC systems and must also be considered in the design of the mechanisms. In this paper, we model the problem of energy-aware application placement in edge computing systems as a multi-stage stochastic program. The objective is to maximize the QoS of the system while taking into account the limited energy budget of the edge servers. To solve the problem, we design a novel parallel Sample Average Approximation (SAA) algorithm. We conduct an extensive experimental analysis to evaluate the performance of the proposed algorithm using real-world trace data.
- 13 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 31 (4) , 909-922
Energy-Aware Application Placement in Mobile Edge Computing: A Stochastic Optimization Approach
The Quality of Service (QoS) in Mobile Edge Computing (MEC) systems is significantly dependent on the application offloading and placement decisions. Due to the movement of users in MEC networks, an optimal application placement might turn into the least efficient placement in few minutes. Thus, it is crucial to take the dynamics of the system into account when designing application placement mechanisms. On the other hand, energy consumption of servers is a significant component of the cost of services in MEC systems and must also be considered in the design of the mechanisms. In this paper, we model the problem of energy-aware application placement in edge computing systems as a multi-stage stochastic program. The objective is to maximize the QoS of the system while taking into account the limited energy budget of the edge servers. To solve the problem, we design a novel parallel Sample Average Approximation (SAA) algorithm. We conduct an extensive experimental analysis to evaluate the performance of the proposed algorithm using real-world trace data.
- Open Access
Multi-task Prediction of Patient Workload
Developing reliable workload predictive models can affect many aspects of clinical decision making procedure. The primary challenge in healthcare systems is handling the demand uncertainty over the time. This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment because of the need for continuous treatments over the time. Although some researchers focused on exploring the methods for workload prediction recently, few types of research mainly focused on forecasting a quantitative measure for the workload of healthcare providers. Also, among the mentioned studies most of them just focused on workload prediction within one facility. The drawback of the previous studies is the problem is not investigated for multiple facilities where the quality of provided service, the equipment, and resources used for provided service as well as the diagnosis and treatment procedures may differ even for patients with similar conditions. To tackle the mentioned issue, this paper suggests a framework for patient workload prediction by using patients data from VA facilities across the US. To capture the information of patients with similar attributes and make the prediction more accurate, a heuristic cluster based algorithm for single task learning as well as a multi task learning approach are developed in this research.
Open AccessMulti-task Prediction of Patient Workload
Developing reliable workload predictive models can affect many aspects of clinical decision making procedure. The primary challenge in healthcare systems is handling the demand uncertainty over the time. This issue becomes more critical for the healthcare facilities that provide service for chronic disease treatment because of the need for continuous treatments over the time. Although some researchers focused on exploring the methods for workload prediction recently, few types of research mainly focused on forecasting a quantitative measure for the workload of healthcare providers. Also, among the mentioned studies most of them just focused on workload prediction within one facility. The drawback of the previous studies is the problem is not investigated for multiple facilities where the quality of provided service, the equipment, and resources used for provided service as well as the diagnosis and treatment procedures may differ even for patients with similar conditions. To tackle the mentioned issue, this paper suggests a framework for patient workload prediction by using patients data from VA facilities across the US. To capture the information of patients with similar attributes and make the prediction more accurate, a heuristic cluster based algorithm for single task learning as well as a multi task learning approach are developed in this research.
- 25 September 2018
- Published by Elsevier in European Journal of Operational Research
- Vol. 273 (3) , 1016-1025
A Reliability-based Approach for Performance Optimization of Service Industries: An Application to Healthcare Systems
- 25 September 2018
- Published by Elsevier in European Journal of Operational Research
- Vol. 273 (3) , 1016-1025
A Reliability-based Approach for Performance Optimization of Service Industries: An Application to Healthcare Systems
- Open Access
A Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer
Survival analysis has been developed and applied in the number of areas including manufacturing, finance, economics and healthcare. In healthcare domain, usually clinical data are high-dimensional, sparse and complex and sometimes there exists few amount of time-to-event (labeled) instances. Therefore building an accurate survival model from electronic health records is challenging. With this motivation, we address this issue and provide a new survival analysis framework using deep learning and active learning with a novel sampling strategy. First, our approach provides better representation with lower dimensions from clinical features using labeled (time-to-event) and unlabeled (censored) instances and then actively trains the survival model by labeling the censored data using an oracle. As a clinical assistive tool, we introduce a simple effective treatment recommendation approach based on our survival model. In the experimental study, we apply our approach on SEER-Medicare data related to prostate cancer among African-Americans and white patients. The results indicate that our approach outperforms significantly than baseline models.
Open AccessA Deep Active Survival Analysis Approach for Precision Treatment Recommendations: Application of Prostate Cancer
Survival analysis has been developed and applied in the number of areas including manufacturing, finance, economics and healthcare. In healthcare domain, usually clinical data are high-dimensional, sparse and complex and sometimes there exists few amount of time-to-event (labeled) instances. Therefore building an accurate survival model from electronic health records is challenging. With this motivation, we address this issue and provide a new survival analysis framework using deep learning and active learning with a novel sampling strategy. First, our approach provides better representation with lower dimensions from clinical features using labeled (time-to-event) and unlabeled (censored) instances and then actively trains the survival model by labeling the censored data using an oracle. As a clinical assistive tool, we introduce a simple effective treatment recommendation approach based on our survival model. In the experimental study, we apply our approach on SEER-Medicare data related to prostate cancer among African-Americans and white patients. The results indicate that our approach outperforms significantly than baseline models.
- 26 October 2014
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 77 (5-8) , 847-860
Modeling and optimization of direct metal laser sintering process
- 26 October 2014
- Published by Springer Nature in The International Journal of Advanced Manufacturing Technology
- Vol. 77 (5-8) , 847-860
Modeling and optimization of direct metal laser sintering process