Analysis of EnterpriseVoIP Traffic from aWire line IMS System

With the rapid development of telecommunication industry, the IP multimedia Subsystem (IMS) could very well be the panacea for most telecom operators. It is originally defined as the core network for 3G mobile systems by the 3rd Generation Partnership Project (3GPP), the more recent development is merging between fixed line network and wireless networkd This report researchs the characteristic of the IMS data and proposes an IMS characterization analysis. We captured the IMS traffic data with 10 tousands users for about 41 hours. By analyzing the characteristics of the IMS, we know that the most important application in the IMS is VoIP call. Then we use the tool designed by Tsinghua University & Ericsson Company to recognize the data, and the results we got can be used to build the traffic models. From the results of the traffic models, I will get some reasons and conclusion. The traffic model gives out the types of session and types of VoIP call. I bring into a concept—busy hour. This concept is very important because it can help us to know which period is the peak of the VoIP call. The busy hour is from 10:00 to 11:00 in the morning. I also bring into another concept—connection ratio. This concept is significant because it can evaluate whether the VoIP call is good when it use IMS network. By comparing the traffic model with other one’s models, we found the different results from them, both the accuracy and the busy hour. From the contract, we got the advantages of our traffic models.

Hand Gesture Detection & Recognition System

The project introduces an application using computer vision for Hand gesture recognition. A camera records a live video stream, from which a snapshot is taken with the help of interface. The system is trained for each type of count hand gestures (one, two, three, four, and five) at least once. After that a test gesture is given to it and the system tries to recognize it.A research was carried out on a number of algorithms that could best differentiate a hand gesture. It was found that the diagonal sum algorithm gave the highest accuracy rate. In the preprocessing phase, a self-developed algorithm removes the background of each training gesture. After that the image is converted into a binary image and the sums of all diagonal elements of the picture are taken. This sum helps us in differentiating and classifying different hand gestures.Previous systems have used data gloves or markers for input in the system. I have no such constraints for using the system. The user can give hand gestures in view of the camera naturally. A completely robust hand gesture recognition system is still under heavy research and development; the implemented system serves as an extendible foundation for future work.