Search

With each passing day resolutions of still image/video cameras are on the rise. This amelioration in resolutions has the potential to extract useful information on the view opposite the photographed subjects from their reflecting parts. Especially important is the idea to capture images formed on the eyes of photographed people and animals. The motivation behind this research is to explore the forensic importance of the images/videos to especially analyze the reflections of the background of the camera. This analysis may include extraction/ detection/recognition of the objects in front of the subjects but on the back of the camera. In the national context such videos/photographs are not rare and, specifically speaking, an abductee’s video footage at a good resolution may give some important clues to the identity of the person who kidnapped him/her. Our aim would be to extract visual information formed in human eyes from still images as well as from video clips. After extraction, our next task would be to recognize the extracted visual information. Initially our experiments would be limited on characters’ extraction and recognition, including characters of different styles and font sizes (computerized) as well as hand written. Although varieties of Optical Character Recognition (OCR) tools are available for characters’ extraction and recognition but, the problem is that they only provide results for clear images (zoomed).

SYN flooding is one of the most challenging problems that many networks applications face, particularly those that are security-related. Disrupting a server's daily function and assigning it to other tasks leaves it a constantly busy server that processes little usable data. In this research, a comprehensive INDIGSOL approach is demonstrated that not only detects SYN flooding but also prevents the attacker(s) from making such attempts in the future. The designed approach has four modules such as node registration and validation, packet capturing, dynamic check system, and hook activation. The approach is further checked and compared with some state-of-the-art baselines on various parameters like detection time, response/processing time, and number of malicious packets detection. It is observed that INDIGSOL performed better than other baselines with an average accuracy of 99% malicious packet detection in six scenarios along with 13.4% faster detection time and 11.2% faster response/processing time. Overall, the provided solution is scalable, robust, and highly accurate that prevents SYN flooding in a timely manner.

Social network analysis has been increasingly employed to study patterns in diverse areas of disciplines such as crowd management, air passenger and freight transportation, business modelling and analysis, online social movements and bioinformatics. Over the years, human disease networks have been studied to analyze Human Disease, Genotype, and Phenotype networks. This study explores human Disease Network based on their symptoms by employing different social network analysis such as centrality measures of network, community detection, overlapping communities. We studied relationships of symptoms with diseases on meso-level in order to detect comorbidity pattern of communities in disease network. This help us to understand the underlying patterns of diseases based on symptoms and find out that how different disease communities are correlated by detecting overlapping communities.

The data mining methods have been extensively used in the process of decision making. The popularity of data mining methods is due to availability of high speed algorithms, processing and storage power of computers. The effective use of data mining methods help in mining datasets and taking better decisions. The data need to be preprocessed before applying data mining methods. Some datasets require little preparation like dealing with missing and redundant instances while some high-dimensional datasets require strong processing like dimensionality reduction. One of the techniques used for dimensionality reduction is feature selection. This study uses graph based centrality measure for feature selection. Graph based centrality measures are used for ranking features which is used for removing irrelevant attributes. After comparison of results with other approaches, it has been found that the proposed approach results in reduction of feature space without compromising accuracy. The results also shows that proposed approach performs better than some other feature selection approaches not only in terms of accuracy but also on the basis of larger reduction in feature space.