No abstract

Internet is being expanded because of the enhancement of today's networks and with these expansion different types of unauthorized activities building up to make the network vulnerable. Many researchers are working around the world to protect the systems from any kind of unauthorized access. In this study we have implemented an Intrusion Detection System based on K-Centroid Clustering and Genetic Algorithm to achieve a better detection rate and false positive rate. In our system training set is classified into different clusters based on K-Centroid clustering and then GA is performed to check each connection of the test set and finally result has been obtained for every specific connection. We have used both Kdd99Cup and NSLKDD dataset to get the experiment result of our system. Finally analyzing with those data we have got a decent detection rate in our implemented system.

Due to the domain shift between images and videos, standard object detectors trained on images usually do not perform well on videos. At the same time, it is difficult to directly train object detectors from video data due to the lack of labeled video datasets. In this paper, we consider the problem of localizing objects in weakly labeled videos. A video is weakly labeled if we know the presence/absence of an object in a video (or each frame), but we do not know the exact spatial location. In addition to weakly labeled videos, we assume access to a set of fully labeled images. We incorporate domain adaptation in our framework and adapt the information from the labeled images (source domain) to the weakly labeled videos (target domain). Our experimental results on standard benchmark datasets demonstrate the effectiveness of our proposed approach. Our work can be used for collecting large-scale video datasets for object detection.

No abstract

No abstract