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.

Enhancing the stability and efficiency of spectral ordering with partial supervision and feature selection

Abstract: Several studies have demonstrated the prospects of spectral ordering for data mining. One successful application is seriation of paleontological findings, i.e. ordering the sites of excavation, using data on mammal co-occurrences only. However, spectral ordering ignores the background knowledge that is naturally present in the domain: paleontologists can derive the ages of the sites within some accuracy. On the other hand, the age information is uncertain, so the best approach would be to combine the background knowledge with the information on mammal co-occurrences. Motivated by this kind of partial supervision we propose a novel semi-supervised spectral ordering algorithm that modifies the Laplacian matrix such that domain knowledge is taken into account. Also, it performs feature selection by discarding features that contribute most to the unwanted variability of the data in bootstrap sampling. Moreover, we demonstrate the effectiveness of the proposed framework on the seriation of Usenet newsgroup messages, where the task is to find out the underlying flow of discussion. The theoretical properties of our algorithm are thoroughly analyzed and it is demonstrated that the proposed framework enhances the stability of the spectral ordering output and induces computational gains.

Algorithms and Data Structures for Sequence Analysis in the Pan-Genomic Era

Abstract: The advent of Next-Generation Sequencing brought new challenges for biological sequence analysis: larger volumes of sequencing data, a proliferation of research projects relying on genomic analysis, and the materialization of rich genomic databases, to name a few. A recent example of the latter, gnomeAD, contains more than 15,000 whole human genomes from unrelated individuals. Today a pressing challenge is how to leverage the full potential of such pan-genomic collections. Among the many biological sequencing processes that rely on computation methods, this thesis is motivated by variation calling and haplotyping. Variation calling is the process of characterizing an individual’s genome by identifying how it differs from a reference genome. The standard approach is to first obtain a set of small DNA fragments – called reads – from a biological sample. Genetic variants in the individual’s genome are detected by analyzing the alignment of these reads to the reference. A related procedure is haplotype phasing. Sexual organisms have their genome organized in two sets of chromosomes, with equivalent functions. Each set is inherited from the mother and the father respectively, and its elements are called haplotypes. The haplotype phasing problem is, once genetic variants are discovered, to attribute them to either of the haplotypes. The first part of this thesis incrementally builds a novel pipeline for variant calling. We propose to replace the single reference model by a pan-genomic

Discrete Component Analysis

Abstract: This article presents a unified theory for analysis of components in discrete data, and compares the methods with techniques such as independent component analysis, non-negative matrix factorisation and latent Dirichlet allocation. The main families of algorithms discussed are a variational approximation, Gibbs sampling, and Rao-Blackwellised Gibbs sampling. Applications are presented for voting records from the United States Senate for 2003, and for the Reuters-21578 newswire collection.

Facing with Collaborative Robots: The Subjective Experience in Senior and Younger Workers.

Abstract: In the past few years, collaborative robots (i.e., cobots) have been largely adopted within industrial manufacturing. Although robots can support companies and workers in carrying out complex activ...

Tell me Something My Friends do not Know: Diversity Maximization in Social Networks

Abstract: Social media have a great potential to improve information dissemination in our society, yet, they have been held accountable for a number of undesirable effects, such as polarization and filter bubbles. It is thus important to understand these negative phenomena and develop methods to combat them. In this paper we propose a novel approach to address the problem of breaking filter bubbles in social media. We do so by aiming to maximize the diversity of the information exposed to connected social-media users. We formulate the problem of maximizing the diversity of exposure as a quadratic-knapsack problem. We show that the proposed diversity-maximization problem is inapproximable, and thus, we resort to polynomial non-approximable algorithms, inspired by solutions developed for the quadratic knapsack problem, as well as scalable greedy heuristics. We complement our algorithms with instance-specific upper bounds, which are used to provide empirical approximation guarantees for the given problem instances. Our experimental evaluation shows that a proposed greedy algorithm followed by randomized local search is the algorithm of choice given its quality-vs.-efficiency trade-off.