• Publications
  • Influence
Concinnity: A Generic Platform for Big Sensor Data Applications
TLDR
Concinnity takes sensor data from collection to final product via a cloud-based data repository and easy-to-use workflow system and supports rapid development of applications built on sensor data using data fusion and the integration and composition of models to form novel workflows. Expand
Building a cloud-based platform for personal health sensor data management
TLDR
This paper proposes a cloud-based platform for health sensor data management, named Wiki-Health, which will provide a potential solution for storing, tagging, retrieving, analysing, comparing and searching health Sensor data. Expand
Building a generic platform for big sensor data application
TLDR
A sensor data platform “Concinnity” is provided which can take sensor data from collection to final product via a data repository and workflow system to enable rapid development of applications built on sensor data using data fusion and the integration and composition of models to form novel workflows. Expand
Wiki-Health: A Big Data Platform for Health Sensor Data Management
Quickly evolving modern technologies such as cloud computing, Internet of things, and intelligent data analysis have created great opportunities for better living. The authors visualize the roleExpand
Multi-Tenant Machine Learning Platform Based on Kubernetes
TLDR
A flexible and scalable machine learning architecture based on Kubernetes that can support simultaneous use by huge numbers of users and the implementation of several important features that are designed to simplify the entire modeling lifecycle for machine learning developers are described. Expand
Multi-platform data collection for public service with Pay-by-Data
TLDR
The Pay-by-data model is extended, which is an explicit data-service exchange protocol, and a system framework to support large-scale public service is proposed. Expand
Application of Temperature Prediction Model Based on LSTNet in Telecommunication Room
TLDR
A temperature prediction model based on the Long- and Short-term Time-series network (LSTNet) and a mechanism for the automatic model update that is triggered when the accuracy of the prediction model is reduced or when the telecommunications room equipment is replaced is proposed. Expand
A Comparison of Machine Learning Algorithms for Automatic Cloud Resource Scaling on a Multi-Tenant Platform
TLDR
Several machine-learning-based predictive algorithms are compared to build models based on the information of the system used to predict future usage demands to save over 80% cloud resource consumption compared to the rule-based method. Expand
Anomaly Detection of Storage Battery Based on Isolation Forest and Hyperparameter Tuning
TLDR
A single-model method based on isolation forest and hyperparameter tuning is proposed for detecting abnormal batteries and Experimental results show that the proposed method is efficient in offline situations. Expand