Haris Supic

Autonomous creation of new situation cases in structured continuous domains

A case-based reasoning (CBR) system that continuously interacts with an environment must be able to autonomously create new situation cases based on its perception of the local environment in order to select the appropriate steps to achieve the current mission goal. Although many continuous problem domains seem appropriate for case-based reasoning, a general formal framework is still missing. This paper presents a step in the direction of developing such a formal model of autonomous creation of new situation cases. The model is based on the notion of the step for attentional shift. This notion allows us to define the representation scheme for situation cases. We have introduced two types of situation cases: contextual cases and action cases. The solution component of contextual cases, also called a contextual behavior routine, is used as a resource to direct the attention of the CBR system to the relevant aspects of the local environment. The solution component of action cases, also called an action behavior routine, is used to guide selection of manipulative steps. There are two key roles of steps for attentional shift in our model. The first one is that steps for attentional shift represent a description structure of situation cases. The second role is that steps for attentional shift represent an abstract representation of actions by which the CBR system moves the attention to the relevant aspects of a local environment.

An approach to design of time-aware recommender system based on changes in group user's preferences

Traditional recommender systems use collaborative filtering or content-based methods to recommend new items for users. New users and items are continuously updated to the system bringing changes in users preferences, as well as the additional context in form of temporal information. The continuous system updates change not just individual users preferences, but also group users preferences affecting prediction of ratings for individual users. In this work is presented improved user-based collaborative filtering algorithm using temporal contextual information. With difference to other approaches, we propose using weight function based on changes in the group users preferences over time that increases prediction accuracy of collaborative filtering prediction algorithm.

A compact color descriptor for image retrieval

The resource usage in Content-Based Image Retrieval is a frequently neglected issue. This paper describes a novel compact feature vector based on image color histograms in the HSL color space. The images are represented using only 10 bytes per image. It is shown that, in the context of Query-by-Example (QbE) usage scenarios, the method described achieves retrieval performance close to the state of the art image retrieval methods that use considerably more memory. It is also shown that the described method outperforms other methods with similar memory usage.

Issue of resource usage in content-based image retrieval algorithms

Content-based image retrieval (CBIR) is a field of active research for almost 20 years. This timeframe has seen several generations of hardware and corresponding changes in computer usage patterns. It is therefore prudent to periodically reevaluate known methods in the context of modern hardware and usage patterns. Overall the issue of resource usage in CBIR is somewhat neglected. In this paper some extremes in this area are benchmarked and results presented. Specifically, paper is focused on usage scenario of indexing a personal image collection.

Performance and quality assessment of R-tree based nearest neighbour search in the scalar field mapping technique

Energy efficiency became more relevant recently. This also includes the construction of energy efficient buildings in terms of heat conservation and dissipation. For analysing the energy efficiency several mapping algorithms are proposed that map indoor environments with added thermal information. Also, several algorithms that generate virtual 3D models are recently presented. One of the main parts of these algoritms are nearest neighbour searching techniques. There are several algorithms that enables the use of nearest neighbour (NN) search. In this paper we present the assessment of R-tree based NN queries in the problem of scalar field mapping that maps a measured temperatures onto reconstructed 3D-mesh of indoor environment. The mesh is reconstructed from the point cloud recorded with 3D laser scanner and thermal imaging camera. We present the performance analysis of the R-tree based NN search with different R-tree types. Also, we present the quality of the scalar field mapping produced with employed R-tree based NN search techniques.

An iterative approach in development of the student information system: Lessons learned

Iterative and incremental development (IID) is a staple of multiple software development methods, including Spiral development, Unified process and Agile development. However, a number of papers warn of possible pitfalls in application of this approach in examples of real-life development project. In this paper we will describe an (in our opinion) successful application of IID to a software project which is in everyday use and which has so far proven useful. In addition, we will attempt to draw some conclusions that may be of use for further research on software development methodology.

Temporal dynamics of changes in group user's preferences in recommender systems

Using contextual information in recommender systems is a subject of continuous improvement of rating prediction accuracy. Among others, information on temporal rating dynamics contain valuable data that establish foundation for discovering changes in both individual and group users preferences. Such changes can be caused by multiple factors such as changes of individual user interests, changes in item popularity or other hidden patterns or events. In this paper an improved user-based collaborative filtering algorithm is presented that utilizes changes of group users preferences over time. We also investigate temporal dynamics of changes in users preferences within different item categories and propose time weight function that improves prediction accuracy of recommender systems.

A Case-Based Approach to Intelligent Virtual Agent's Interaction Experience Representation

In this paper we describe a case-based representation of intelligent virtual agents interaction experience. This allows us to develop an approach to creation of IVAs by using case-based reasoning. We called this agent CBRIVA. We can define a CBRIVA as an entity that selects the next step based on previous interaction experience. A CBRIVAs interaction experience is represented in the form of the three types of cases: plan, contextual, and action cases.

Adaptation by Applying Behavior Routines and Motion Strategies in Autonomous Navigation

This paper presents our current efforts toward development of highlevel behavior routines and motion strategies for the stepwise case-based reasoning (SCBR) approach. The SCBR approach provides an appropriate architectural framework for autonomous navigation system in which situation cases are used to support the situation module, and route cases are used to support the high-level route planning module. In the SCBR approach, adaptation knowledge comes in the form of high-level behavior routines and motion strategies. The SCBR system determines next action based on an analysis of the generated view in terms of positions of relevant objects. Thus, higher-level case-based symbolic reasoning intervenes at the action selection points to determine which action vector is appropriate to control the SCBR system. In order to qualitatively evaluate the SCBR approach, we have developed a simulation environment. This simulation environment allows us to visually evaluate the progress of an SCBR system while it runs through a predefined virtual world.

Modeling Long-Term User Profile in Collaborative Filtering

Collaborative filtering methods are widely accepted and used for item recommendation in various applications and domains. Their simplicity and ability to provide recommendations without the need fo...