Yuexin Wu

The implementation and application of the internet of things platform based on the REST architecture

The internet of things and Services is a rapidly growing concept that illustrates that the ever increasing amount of physical items of our daily life which become addressable through a network could be made more easily manageable and usable through the use of Services. This paper describes an innovative web service architecture, dedicated to the Internet of Things (IoT). My main concern is to illustrates why and how to use REST architecture to structure an IoT platform.

A Learning Spectrum Hole Prediction Model for Cognitive Radio Systems

In this paper, we present a new spectrum-hole prediction model for cognitive radio (CR) systems based on the IEEE 802.11 wireless local areas networks. We have also analyzed the distribution of interval between two consecutive packets (ITCP) based on a simple two-user network. For multiuser networks, we have investigated the distribution of ITCP and study its characteristics using Bayesian inference. The effectiveness of the presented prediction model is validated by MATLAB simulation programs.

A scalable Internet of Things Lean Data provision architecture based on ontology

The paper proposes a data management platform with an open architecture for converting huge amount of various and cluttered data into Lean Data, which provides customer-expected service and can be then encapsulated as service packages to be used by different application developers. Ontology is used to provide a unified way for data flow description and semantic data storage to achieve a unified understanding among different layers and modules. A case study for routing optimization in the industry of intelligent transportation is illustrated to show how the platform works, and he potential business value of such platform is also indicated in this paper.

Data Prediction for Public Events in Professional Domains Based on Improved RNN- LSTM

The traditional data services of prediction for emergency or non-periodic events usually cannot generate satisfying result or fulfill the correct prediction purpose. However, these events are influenced by external causes, which mean certain a priori information of these events generally can be collected through the Internet. This paper studied the above problems and proposed an improved model—LSTM (Long Short-term Memory) dynamic prediction and a priori information sequence generation model by combining RNN-LSTM and public events a priori information. In prediction tasks, the model is qualified for determining trends, and its accuracy also is validated. This model generates a better performance and prediction results than the previous one. Using a priori information can increase the accuracy of prediction; LSTM can better adapt to the changes of time sequence; LSTM can be widely applied to the same type of prediction tasks, and other prediction tasks related to time sequence.

Research on Spectrum Hole Distribution for Cognitive Radio Systems

In this paper, we at first studied the distribution of the interval between two consecutive packets (ITCP) for two-user networks. We then extend our interest to multi-user networks by using fitting curves to approximate the distribution of the ITCP. Next, based on the above observation, we present a new spectrum hole prediction model for the IEEE 802.11 standards based cognitive radio (CR) local areas networks. The effectiveness of the presented prediction model was thereafter validated by using NS-2 and MATLAB simulation programs. Simulation results showed that when adopting the proposed spectrum hole prediction model, CR systems can largely reduce the number of collisions with licensed users.