Abstract- In this paper we present a new method to process sequences of system calls for anomaly intrusion detection. The key idea is to build a multi-layer model of program behaviours based on both hidden Markov models and enumerating methods for anomaly intrusion detection, which differs from the conventional single layer approach. Our experiments on Unix sendmail program have shown that the model is better in detecting anomalous behaviour of programs in terms of accuracy and response time. As we use the temporal characteristics in the model, it is suitable for online host-based intrusion detection systems in LAN environment.

this paper, new techniques are presented using Support Vector Machines (SVMs)

We describe a method for the reconstruction of a driven trajectory of a mobile robot if the begin and end states of the trajectory are known, and intermediate readings from odometry are available. Our method uses a Kalman filter to combine a forward and backward dead-reckoning trajectory. We show that our method is more reliable for long trajectories than just combining the dead-reckoning trajectories independently.

This paper describes a technique for on-line handwriting verification using Hidden Markov Models (HMMs). The handwriting is captured and digitized in real-time using a graphics tablet. The verification reliability of the technique is investigated using different forgery types. Additionally, a novel stand-alone security system is described which incorporates the verification technique. The results obtained from a database of almost 1000 handwriting samples from 47 writers include an error rate of 0.64 % when the potential forger does not know the genuine user's "password".

Abstract. Gesture is a natural expression form for humans, but its recognition is a similarly hard problem as speech recognition. In this paper, I present a real-time hand gesture recognition system, which identifies relevant parts in the continous sensor data stream, and classifies them to the most probable gesture. Instead of the usual button-based segmentation, I have created an automatic segmentation method, which makes the interface more natural. The results showed that the two different classifiers reach 97.4 % and 96 % accuracy on a personalized gesture set, and these results can be improved for certain gesture sets with the combination of the two algorithms. Furthermore, the system has great performance and low response time, so the user experience is much better than with previous gesture recognizers.

This paper gives a review of current state of the art in the development of robust and intelligent surveillance systems, going beyond traditional vision based framework to more advanced multi-modal framework. The goal of automated surveillance system is to assist the human operator in scene analysis and event classification by automatically detecting the objects and analyzing their behavior using computer vision, pattern recognition and signal processing techniques. This review addresses several advancements made in these fields while bringing out the fact that realizing a practical end to end surveillance system still remains a difficult task due to several challenges faced in a real world scenario. With the advancement in sensor and computing technology, it is now economically and technically feasible to adopt multi-camera and multi-modal framework to meet the need of efficient surveillance system in wide range of security applications like security guard for communities and important buildings, traffic surveillance in cities and military applications. Therefore our review includes significant discussion on multi-modal data fusion approach for robust operation. Finally we conclude with discussion on possible future research directions. Povzetek: Podan je pregled metod inteligentnega video nadzora. 1

This paper discusses the principles of making inferences about a user's context from location time-series. These principles have been implemented and embedded in a statistical model, used in a Sentient [1] Notification Service. This model makes estimates about the probability of a situation occurring in the future, based on users' locations and past behavior and using methods such as Bayesian inference [2] This information is then used by a Context-Aware Notification Service[10] to notify all registered users who are interested in the particular activity.

ISR develops, applies and teaches advanced methodologies of design and analysis to solve complex, hierarchical,

Learning genetic algorithm parameters

In this exercise the toolbox of Kevin Murphy was used [2].