Optical Burst Switching - A New Paradigm

Enhanced packet routing queuing model in optical burst switching network using queue-based dynamic optical route scheduling

In hop-based burst-cluster transmission, multiple bursts are assembled simultaneously and sorted from the smallest number of hops to the largest one. By doing so, the burst loss probability for a large number of hops decreases, improving fairness. How- ever, in mesh networks, the amount of trac on each link is not necessarily the same, and hence degrades the performance of hop-based burst-cluster transmis- sion. In this paper, we propose dynamic burst or- dering to solve this problem. Here, each source node calculates the burst loss probability for each number of hops using ACK and NACK messages. Based on the calculated probabilities, the source node changes the order of bursts within a burst-cluster dynami- cally. It is expected that this method can improve local fairness for each source node. We evaluate the performance of the proposed method in tandem net- works by simulation. Numerical examples show that the proposed method is eective for improving fair- ness for each source node regardless of the amount of trac on each link.

/pdf/adaptive-burst-reordering-for-burst-cluster-transmission-to-2zg7w4j9td.pdf

Adaptive burst reordering for burst-cluster transmission to improve fairness in OBS networks

Rail transportation system remains one of the most cost effective and suited means of passenger and goods transportation for both long distance and suburban travel. Hence it is a critical task to ensure regular railway maintenance. This work explores the scope of detecting cracks and also pedestrians in the track by making use of deep learning and image recognition system. This task becomes very challenging as the cracks in the track are varying and the pedestrian can take wide range of poses. This system make use of a conventional Convolutional Neural Network (CNN) along with Support Vector Machine for recognition of crack defective from the dataset. SVM is the binary classifier used, while CNN was used as an automated feature extractor. The dataset was used to train and test the algorithm that was implemented in the proposed model. CNN’s receptive field aids in extracting the most recognizable aspects from these images automatically. The experimental findings show that the suggested framework is successful, with a recognition accuracy of 78% throughout the dataset and a template based lane detection method is used. Lane tracking is done with edge detection and the position of a region of interest in vanishing point in tack image is used for identifying the land departure. This detector on real time video with the region of interest selection and achieve in 23 fps. 

Real time railway track crack analysis using multi-level classification

Over the past decade, machine learning (ML) is being used as a new direction of innovation to transform optical communication systems. Due to the significant improvement and advancement in computing capabilities of ML techniques, it helps in issues related to optical communication and networking. In this chapter we describe numerous ML-based approaches to deal with various issues at physical and network layers. We also provide an outline of existing ML applications in optical communication systems with an emphasis on physical and network layer.

Machine Learning for Optical Communication to Solve Pervasive Issues of Internet of Things

The problem on loss free burst transmission has been well studied in Burst Switching Networks (BSN). There are number of approaches discussed for the performance development, but suffers to achieve higher performance. To overcome the issue, an burst rate based dynamic IO Queue management scheme has been presented. The method monitors the incoming burst traffic from more number of nodes and according to the rate of burst coming, the input output queue systems has been modified for their size. The burst in the queue system has been routed through available routes whenever identified. The method is capable of triggering the IO queue systems up and down according to the burst traffic. The proposed method improves the performance of burst switching networks.

Burst rate based optimized IO queue management for improved performance in Optical Burst Switching Networks

In India rail transportation engage a major pose in endow with the essential transportation to maintain necessities of a hastily emergent financial system. At present, India possesses the fourth major railway net in the globe. The majority of the viable transportation conceded out by the railway system and consequently, any difficulty in the equal has the capacity to induce major damage to the financial system. A method for evade trains from devastating and crash with threat on railways is making known. According to the improvement, the techniques comprise a safety vehicle that travels along a railway a head of a train failure follow on in mishap generally get extensive means exposure still when the railway is not at fault and give to rail transport, among the unaware public, an unjustified image of inefficiency often fuelling calls for immediate reforms. This paper is intended at serving the railway control apprehensive to make stronger and expand the surveyor equipment vital through recent protection supervision.

Advanced Automatic Detection of Cracks in Railway Tracks

In this manuscript the projected method overcome the drawback created by this current GPS, the alternate system of finding a human position. An alternating technique be term as IPS technique. Present GPS structure provide us the essential direct of people’s spot, although its most important problem is more difficult while the individual depart inside or if he enter consign which have an extremely deprived signal connectivity.

Advanced Determination of object location using IPS

This work proposed an approach for the simple detection and segmentation of human skin color based on user oriented and perceptually color models as RGB, YCbCr, HSV and CIELab. In image and video processing, human skin segmentation finds many applications including face recognition and nudity detection. The success of the human skin detection is purely depends on the exact demarcation of non-skin and skin pixels in the scene. It is very difficult to build up a unique approach for the identification and segmentation of human skin color. The color based approaches for the detection of human skin differentiate the color and luminance information still in the uncharacteristic illumination circumstances. The investigational outcome illustrates the effectiveness of color model based recognition of skin tone in color images.

S. Jagan Mohan Rao

Papers

Burst rate based optimized IO queue management for improved performance in Optical Burst Switching Networks

Advanced Automatic Detection of Cracks in Railway Tracks

Advanced Determination of object location using IPS

An Approach to Threshold Based Human Skin Color Recognition and Segmentation in Different Color Models