Helsinki Institute for Information Technology

About: Helsinki Institute for Information Technology is a facility organization based out in Espoo, Finland. It is known for research contribution in the topics: Population & Bayesian network. The organization has 630 authors who have published 1962 publications receiving 63426 citations.

Influence of landmark-based navigation instructions on user attention in indoor smart spaces

Abstract: Using landmark-based navigation instructions is widely considered to be the most effective strategy for presenting navigation instructions. Among other things, landmark-based instructions can reduce the user's cognitive load, increase confidence in navigation decisions and reduce the number of navigational errors. Their main disadvantage is that the user typically focuses considerable amount of attention on searching for landmark points, which easily results in poor awareness of the user's surroundings. In indoor spaces, this implies that landmark-based instructions can reduce the attention the user pays on advertisements and commercial displays, thus rendering the assistance commercially inviable. To better understand how landmark-based instructions influence the user's awareness of her surroundings, we conducted a user study with $20$ participants in a large national supermarket that investigated how the attention the user pays on her surroundings varies across two types of landmark-based instructions that vary in terms of their visual demand. The results indicate that an increase in the visual demand of landmark-based instructions does not necessarily improve the participant's recall of their surrounding environment and that this increase can cause a decrease in navigation efficiency. The results also indicate that participants generally pay little attention to their surroundings and are more likely to rationalize than to actually remember much from their surroundings. Implications of the findings on navigation assistants are discussed.

High density-focused uncertainty sampling for active learning over evolving stream data

Abstract: Data labeling is an expensive and time-consuming task, hence carefully choosing which labels to use for training a model is becoming increasingly important. In the active learning setting, a classifier is trained by querying labels from a small representative fraction of data. While many approaches exist for non-streaming scenarios, few works consider the challenges of the data stream setting. We propose a new active learning method for evolving data streams based on a combination of density and prediction uncertainty (DBALSTREAM). Our approach decides to label an instance or not, considering whether it lies in an high density partition of the data space. This allows focusing labelling efforts in the instance space where more data is concentrated; hence, the benefits of learning a more accurate classifier are expected to be higher. Instance density is approximated in an online manner by a sliding window mechanism, a standard technique for data streams. We compare our method with state-of-the-art active learning strategies over benchmark datasets. The experimental analysis demonstrates good predictive performance of the new approach.

Identifying Psychophysiological Correlates of Boredom and Negative Mood Induced during HCI.

Abstract: This paper presents work conducted towards the automatic recognition of negative emotions like boredom and frustration, induced due to the subject’s loss of interest during HCI. Focus was on the basic pre-requisite for the future development of systems utilizing an “affective loop”, namely effective recognition of the human affective state. Based on the concept of “repetition that causes loss of interest”, an experiment for the monitoring and analysis of biosignals during repetitive HCI tasks was deployed. During this experiment, subjects were asked to play a simple labyrinth-based 3D video game repeatedly, while biosignals from different modalities were monitored. Twenty one different subjects participated in the experiment, allowing for a rich biosignals database to be populated. Statistically significant correlations were identified between features extracted from two of the modalities used in the experiment (ECG and GSR) and the actual affective state of the subjects.

Experience Assessment and Design in the Analysis of Gameplay

Abstract: We report research on player modeling using psychophysiology and machine learning, conducted through interdisciplinary collaboration between researchers of computer science, psychology, and game design at Aalto University, Helsinki. First, we propose the Play Patterns And eXperience (PPAX) framework to connect three levels of game experience that previously had remained largely unconnected: game design patterns, the interplay of game context with player personality or tendencies, and state-of-the-art measures of experience (both subjective and non-subjective). Second, we describe our methodology for using machine learning to categorize game events to reveal corresponding patterns, culminating in an example experiment. We discuss the relation between automatically detected event clusters and game design patterns, and provide indications on how to incorporate personality profiles of players in the analysis. This novel interdisciplinary collaboration combines basic psychophysiology research with game design patterns and machine learning, and generates new knowledge about the interplay between game experience and design.

Global citation recommendation using knowledge graphs

Abstract: Scholarly search engines, reference management tools, and academic social networks enable modern researchers to organize their scientific libraries. Moreover, they often provide recommendations for scientific publications that might be of interest to researchers. Because of the exponentially increasing volume of publications, effective citation recommendation is of great importance to researchers, as it reduces the time and effort spent on retrieving, understanding, and selecting research papers. In this context, we address the problem of citation recommendation, i.e., the task of recommending citations for a new paper. Current research investigates this task in different settings, including cases where rich user metadata is available (e.g., user profile, publications, citations). This work focus on a setting where the user provides only the abstract of a new paper as input. Our proposed approach is to expand the semantic features of the given abstract using knowledge graphs – and, combine them with other features (e.g., indegree, recency) to fit a learning to rank model. This model is used to generate the citation recommendations. By evaluating on real data, we show that the expanded semantic features lead to improving the quality of the recommendations measured by nDCG@10.