Martin Mladenov

A step counter service for Java-enabled devices using a built-in accelerometer

The presence of 3D acceleration sensors in mobile devices has already raised a new range of context-aware applications, in particular in the sports and wellness sector. In this paper, we present an accelerometer-based step counter middleware for J2ME-enabled smartphones to simplify the development of activity aware applications, creating an abstraction layer between the client and the signal processing algorithms and raw sensor access. The service provides information about the step count, stop detection and changes in the phones orientation, independently of the phones location on the human body. The software package runs natively on Symbian S60 phones, providing an interface to J2ME applications and has been validated experimentally on a Nokias N95 smartphone.

Discovering bits of place histories from people's activity traces

Events that happened in the past are important for understanding the ongoing processes, predicting future developments, and making informed decisions. Significant and/or interesting events tend to attract many people. Some people leave traces of their attendance in the form of computer-processable data, such as records in the databases of mobile phone operators or photos on photo sharing web sites. We developed a suite of visual analytics methods for reconstructing past events from these activity traces. Our tools combine geocomputations, interactive geovisualizations and statistical methods to enable integrated analysis of the spatial, temporal, and thematic components of the data, including numeric attributes and texts. We demonstrate the utility of our approach on two large real data sets, mobile phone calls in Milano during 9 days and flickr photos made on British Isles during 5 years.

Identifying Place Histories from Activity Traces with an Eye to Parameter Impact

Events that happened in the past are important for understanding the ongoing processes, predicting future developments, and making informed decisions. Important and/or interesting events tend to attract many people. Some people leave traces of their attendance in the form of computer-processable data, such as records in the databases of mobile phone operators or photos on photo sharing web sites. We developed a suite of visual analytics methods for reconstructing past events from these activity traces. Our tools combine geocomputations, interactive geovisualizations, and statistical methods to enable integrated analysis of the spatial, temporal, and thematic components of the data, including numeric attributes and texts. We also support interactive investigation of the sensitivity of the analysis results to the parameters used in the computations. For this purpose, statistical summaries of computation results obtained with different combinations of parameter values are visualized in a way facilitating comparisons. We demonstrate the utility of our approach on two large real data sets, mobile phone calls in Milano during 9 days and flickr photos made on British Isles during 5 years.

Extracting Events from Spatial Time Series

An important task in exploration of data about phenomena and processes that develop over time is detection of significant changes that happened to the studied phenomenon. Our research is focused on supporting detection of significant changes, called events, in multiple time series of numeric values. We developed a suite of visual analytics techniques that combines interactive visualizations on time-aware displays and maps with statistical event detection methods implemented in R. We demonstrate the utility of our approach using two large data sets.

Relational linear programming

Abstract We propose relational linear programming, a simple framework for combining linear programs (LPs) and logic programs. A relational linear program (RLP) is a declarative LP template defining the objective and the constraints through the logical concepts of objects, relations, and quantified variables. This allows one to express the LP objective and constraints relationally for a varying number of individuals and relations among them without enumerating them. Together with a logical knowledge base, effectively a logic program consisting of logical facts and rules, it induces a ground LP. This ground LP is solved using lifted linear programming. That is, symmetries within the ground LP are employed to reduce its dimensionality, if possible, and the reduced program is solved using any off-the-shelf LP solver. In contrast to mainstream LP template languages such as AMPL, which features a mixture of declarative and imperative programming styles, RLPs relational nature allows a more intuitive representation of optimization problems, in particular over relational domains. We illustrate this empirically by experiments on approximate inference in Markov logic networks using LP relaxations, on solving Markov decision processes, and on collective inference using LP support vector machines.

Pairwise Markov Logic

For many tasks in fields like computer vision, computational biology and information extraction, popular probabilistic inference methods have been devised mainly for propositional models that contain only unary and pairwise clique potentials. In contrast, statistical relational approaches typically do not restrict a model’s representational power and use high-order potentials to capture the rich structure of relational domains. This paper aims to bring both worlds closer together.

Fault monitoring and correction in a walking robot using LMS filters

In this paper we show how the design of robust robotic systems can profit from the emerging research field of organic computing by bringing together adaptive systems theory, controller design, and fault tolerance. In particular, we have evaluated in a case study of a hexapod walking robot the use of linear adaptive filters for the detection and correction of faults. Our analysis shows that linear filters can be applied for monitoring the system state and a simple threshold approach utilizing the weights of the adaptive filter can be exploited for fault detection. This even holds in the case of using additional adaptive filters for direct fault compensation in the controller loop. We present the case study and our experimental results which have been derived in a Matlab simulation.