Showing papers by "Alexander Artikis published in 2021"

A probabilistic interval-based event calculus for activity recognition

Abstract: Activity recognition refers to the detection of temporal combinations of ‘low-level’ or ‘short-term’ activities on sensor data. Various types of uncertainty exist in activity recognition systems and this often leads to erroneous detection. Typically, the frameworks aiming to handle uncertainty compute the probability of the occurrence of activities at each time-point. We extend this approach by defining the probability of a maximal interval and the credibility rate for such intervals. We then propose a linear-time algorithm for computing all probabilistic temporal intervals of a given dataset. We evaluate the proposed approach using a benchmark activity recognition dataset, and outline the conditions in which our approach outperforms time-point-based recognition.

Composite Maritime Event Recognition

Abstract: Composite maritime event recognition systems support maritime situational awareness as they allow for the real-time detection of dangerous, suspicious and illegal vessel activities To illustrate the use of such systems, we motivate and present a series of composite maritime event patterns in a formal language For effective recognition, the presented maritime patterns have been developed in close collaboration with domain experts, and evaluated with the use of real-world Automatic Identification System (AIS) datasets

Parallel Model Exploration for Tumor Treatment Simulations.

Abstract: Computational systems and methods are being applied to solve biological problems for many years. Incorporating methods of this kind in the research for cancer treatment and related drug discovery in particular, is shown to be challenging due to the complexity and the dynamic nature of the related factors. Usually, there are two objectives in such settings; first to calibrate the simulators so as to reproduce real-world cases, and second, to search for specific values of the parameter space concerning effective drug treatments. We combine a multi-scale simulator for tumor cell growth and a Genetic Algorithm (GA) as a heuristic search method for finding good parameter configurations in reasonable time. The two modules are integrated into a single workflow that can be executed in a parallel manner on high performance computing infrastructures, since large-scale computational and storage capabilities are necessary in this domain. After using the GA for calibration, our goal is to explore different drug delivery schemes. Among these schemes, we aim to find those that minimize tumor cell size and the probability of emergence of drug resistant cells in the future. Results from experiments on high performance computing infrastructure illustrate the effectiveness and timeliness of the approach.

Complex event forecasting with prediction suffix trees

Abstract: Complex event recognition (CER) systems have become popular in the past two decades due to their ability to “instantly” detect patterns on real-time streams of events. However, there is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of complex event forecasting (CEF). Our framework combines two formalisms: (a) symbolic automata which are used to encode complex event patterns and (b) prediction suffix trees which can provide a succinct probabilistic description of an automaton’s behavior. We compare our proposed approach against state-of-the-art methods and show its advantage in terms of accuracy and efficiency. In particular, prediction suffix trees, being variable-order Markov models, have the ability to capture long-term dependencies in a stream by remembering only those past sequences that are informative enough. We also discuss how CEF solutions should be best evaluated on the quality of their forecasts.

Online Learning Probabilistic Event Calculus Theories in Answer Set Programming.

Abstract: Complex Event Recognition (CER) systems detect event occurrences in streaming time-stamped input using predefined event patterns. Logic-based approaches are of special interest in CER, since, via Statistical Relational AI, they combine uncertainty-resilient reasoning with time and change, with machine learning, thus alleviating the cost of manual event pattern authoring. We present a system based on Answer Set Programming (ASP), capable of probabilistic reasoning with complex event patterns in the form of weighted rules in the Event Calculus, whose structure and weights are learnt online. We compare our ASP-based implementation with a Markov Logic-based one and with a number of state-of-the-art batch learning algorithms on CER datasets for activity recognition, maritime surveillance and fleet management. Our results demonstrate the superiority of our novel approach, both in terms of efficiency and predictive performance. This paper is under consideration for publication in Theory and Practice of Logic Programming (TPLP).

Dagstuhl Seminar on the Foundations of Composite Event Recognition

Abstract: Composite event recognition (CER) is concerned with continuously matching patterns in streams of 'event' data over (geographically) distributed sources. This paper reports the results of the Dagstuhl Seminar "Foundations of Composite Event Recognition" held in 2020.

Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report.

Abstract: Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. However, there is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting (CEF). Our framework combines two formalisms: a) symbolic automata which are used to encode complex event patterns; and b) prediction suffix trees which can provide a succinct probabilistic description of an automaton's behavior. We compare our proposed approach against state-of-the-art methods and show its advantage in terms of accuracy and efficiency. In particular, prediction suffix trees, being variable-order Markov models, have the ability to capture long-term dependencies in a stream by remembering only those past sequences that are informative enough. Our experimental results demonstrate the benefits, in terms of accuracy, of being able to capture such long-term dependencies. This is achieved by increasing the order of our model beyond what is possible with full-order Markov models that need to perform an exhaustive enumeration of all possible past sequences of a given order. We also discuss extensively how CEF solutions should be best evaluated on the quality of their forecasts.

Symbolic Register Automata for Complex Event Recognition and Forecasting.

Abstract: We propose an automaton model which is a combination of symbolic and register automata, i.e., we enrich symbolic automata with memory. We call such automata Symbolic Register Automata (SRA). SRA extend the expressive power of symbolic automata, by allowing Boolean formulas to be applied not only to the last element read from the input string, but to multiple elements, stored in their registers. SRA also extend register automata, by allowing arbitrary Boolean formulas, besides equality predicates. We study the closure properties of SRA under union, intersection, concatenation, Kleene closure, complement and determinization and show that SRA, contrary to symbolic automata, are not in general closed under complement and they are not determinizable. However, they are closed under these operations when a window operator, quintessential in Complex Event Recognition, is used. We show how SRA can be used in Complex Event Recognition in order to detect patterns upon streams of events, using our framework that provides declarative and compositional semantics, and that allows for a systematic treatment of such automata. We also show how the behavior of SRA, as they consume streams of events, can be given a probabilistic description with the help of prediction suffix trees. This allows us to go one step beyond Complex Event Recognition to Complex Event Forecasting, where, besides detecting complex patterns, we can also efficiently forecast their occurrence.