Browsing by Author "Hsieh, I-Ching"

Now showing 1 - 2 of 2

On the Classification of Mobile Broadband Applications
(2016)
Hsieh, I-Ching
;
Tung, Li-Ping
;
Lin, Bao-Shuh Paul
;
材料科學與工程學系
;
資訊工程學系
In the past decade, the Internet has been widely used in everyday life. Different types of mobile broadband applications are created and require an increasing amount of network resources. However, Internet service providers must maximize the use of these limited resources to provide users with different levels of quality of service. The first step toward traffic engineering is to perform traffic classification. In this work, we propose a classification method for identifying mobile applications executed at an early stage. We first collected traffic traces from a WiFi access point and then developed a hidden Markov model based on the packet size and transmission direction of the first 20 packets. In a series of our experiments, we evaluated the number of hidden states through 10-fold cross validation, and classified six types of mobile applications. The accuracy of the proposed method achieved 99.17%. In addition, we set specific threshold values for different application models and identified 91.33% of flows in the testing data set, which comprised unknown traffic flows. These experimental results demonstrate that our proposed method is effective for classifying Internet flows as well as unknown traffic in a real network.
The Design of Big Data Analytics for Testing & Measurement and Traffic Flow on an Experimental 4G/LTE Network
(2015)
Lin, Bao-Shuh
;
Tung, Li-Ping
;
Hsieh, I-Ching
;
Liu, Tsai-Hua
;
Chou, Shu-Yuan
BML(Broadband Mobile Lab.) at NCTU has been utilized to support the testing & measurement for communication and networking products. It also has proven to be able to develop applications and services in a campus scale experimental networking environment. In the meantime, ITRI in Taiwan is conducting a greater metropolitan (Hsinchu) scale experimental networking environment, called ITRINET under the MOEA national program to improve and speed up the 4G/LTE applications and services. The BML at NCTU will be integrated with ITRINET and merged to become its subnet. With the cloud-enabled 4G/LTE-based ITRINET, we have designed the system to conduct the big data analytics for testing&measurement data and for network traffic and management data through a real-time streaming computing software package, InfoSphere, run on a cloud server platform, Inventec Zion. The testing&measurement data is generated and collected through the industry-academia R&D services while the network traffic and management data is created and collected by engaged a variety of APP\'s on smart devices (SD). This paper addresses the system design methodology and issues related to the data analytics for an experimental network environment.