Sung Goo Yoo

Packet Loss Rate Prediction Using the Sparse Basis Prediction Model

The quality of multimedia communicated through the Internet is highly sensitive to packet loss. In this letter, we develop a time-series prediction model for the end-to-end packet loss rate (PLR). The estimate of the PLR is needed in several transmission control mechanisms such as the TCP-friendly congestion control mechanism for UDP traffic. In addition, it is needed to estimate the amount of redundancy for the forward error correction (FEC) mechanism. An accurate prediction would therefore be very valuable. We used a relatively novel prediction model called sparse basis prediction model. It is an adaptive nonlinear prediction approach, whereby a very large dictionary of possible inputs are extracted from the time series (for example, through moving averages, some nonlinear transformations, etc.). Only few of the very best inputs among the dictionary are selected and are combined linearly. An algorithm adaptively updates the input selection (as well as updates the weights) each time a new time sample arrives in a computationally efficient way. Simulation experiments indicate significantly better prediction performance for the sparse basis approach, as compared to other traditional nonlinear approaches

Neural network modeling of transmission rate control factor for multimedia transmission using the internet

This study proposes a prediction model which functions by estimating the bandwidth of the Internet over the time period used for data transmission, that is the RTT (Round Trip Time) and PLR (Packet Loss Rate), which are the most important factors to consider for transmission rate control. The prediction model improves the number of valid transmitted packets by predicting the one-step-ahead transmission rate control factors. A method of prediction modeling was developed using a neural network, which makes it possible to model a nonlinear system and the LMBP algorithm was used to training the neural networks. RTT and PLR data was collected by the TFRC transmission method, which is a kind of adaptive transmission control based on UDP, and used as the training data for the neural network prediction model. Through the training of the neural network, the prediction model can predict the RTT and PLR after one step. It can also be seen that the error in the predicted values is small. This result shows that the congestion situation of the Internet can be predicted by the proposed prediction model. In addition, it shows that it is possible to implement a mechanism, which allows for a substantial amount of data to be transmitted, while actively coping with a congestion situation.

Round Trip Time Prediction Using the Symbolic Function Network Approach

In this paper, we develop a novel approach to model the Internet round trip time using a recently proposed symbolic type neural network model called symbolic function network. The developed predictor is shown to have good generalization performance and simple representation compared to the multilayer perceptron based predictors.

Development of predictive TFRC with neural network

As Internet real-time multimedia applications increase, the bandwidth available to TCP connections is stifled by UDP traffic, which results in the performance of overall system to be extremely deteriorated. Therefore, developing a new transmission protocol is necessary. The TCP-friendly algorithm is an example satisfying this necessity. The TCP-Friendly Rate Control (TFRC) is an UDP-based protocol that controls the transmission rate based on the variables such as RTT and PLR. In the conventional data transmission processing, the transmission rate is determined by the RTT and PLR of the previous transmission period. If the one-step ahead predicted values of RTT and PLR are used to determine the transmission rate, the performance of network will be improved significantly. This paper proposes a predictive TFRC protocol with one-step ahead RTT and PLR. A multi-layer perceptron neural network is used as the prediction model, and the Levenberg-Marquardt algorithm is used as a training algorithm. The values of RTT and PLR were collected using UDP protocol in the real system used for NN modeling. The performance of the predictive TFRC was evaluated by the share of Internet bandwidth with various protocols in terms of the packet transmission rate. The extensive experiment of the suggested system in real system was performed and proves its advantages.

Neural network prediction model for a real-time data transmission

Both the real-time transmission and the amount of valid transmitted data are important factors in real-time multimedia transmission through the Internet. They are mainly affected by the channel bandwidth, delay time, and packet loss. In this paper, we propose a predictive rate control system for data transmission, which is designed to improve the number of valid transmitted packets for the transmission of real-time multimedia over the Internet. The one-step-ahead round-trip delay time and packet loss are predicted using a prediction algorithm and then these predicted values are used to determine the transmission rate. A real-time multimedia transmission system was implemented using a TCP-friendly algorithm, in order to obtain the measurement data needed for the proposed system. Neural network modeling was performed using the collected data, which consisted of the round-trip time (RTT) delay and packet loss rate (PLR). In addition, the performance of the neural network prediction model was verified through a validation process. The transmission rate was determined from the values of RTT delay and PLR, and a data transmission test for an actual system was performed using this transmission rate. The experiment results show that the algorithm proposed in this study increases the number of valid packets compared with the TCP-friendly algorithm.

Adaptive wave variables for bilateral teleoperation using neural networks

Abstract Stability and transparency determine the performance of bilateral teleoperation systems. Previous studies on passivity-based control focused on stability such that the results of the study are robust in terms of the time delay issue. But there are not sufficient studies on performance analysis based on environmental elements related to transparency. This paper suggests an adaptive wave transformation system where stability is secured by controlling characteristic impedance in the existing wave variables system adaptively according to time delay and environmental elements and simultaneously ensuring a proper dynamic performance depending on external force. Neural network was utilized to design the system that enables controlling the characteristic impedance depending on external factors such as time delay and comparison with the existing wave variables.

Bilateral Teleoperation Control with Varying Time Delay Using Optimal Passive Scheme

This paper presents a passive control scheme for a force reflecting bilateral teleoperation system via the Internet. To improve the stability and performance of the system, the host and client must be coupled dynamically via the network and Internet technology provides a convenient way to develop an integrated teleoperation system. However, as use of Internet increases, congestion situation of network increased and transmission time and packet loss increased accordingly. This can make system unstable at remote control. In this paper, we present an optimal passive control scheme for a force reflecting bilateral teleoperation system via the Internet and we investigated how a varying time delay affects the stability of a teleoperation system. A new approach based on an optimal passive control scheme was designed for the system. The simulation results and the tracking performance of the implemented system are presented in this paper.

Self-positioning of a mobile robot using a vision system and image overlay with VRML

The research described a method for localizing a mobile robot in the working environment using a vision system and VRML. The robot identifies landmarks in the environment and carries out the self-positioning. The image-processing and neural network pattern matching techniques were employed to recognize landmarks placed in a robot working environment. The robot self-positioning using vision system was based on the well-known localization algorithm. After self-positioning, the 2D scene of the vision is overlaid with the VRML scene. How to realize the self-positioning was described. Also the result of overlapping between the 2D scene and VRML scene was shown. In addition, the advantage expected from overlapping both scenes described.