Quantcast
Channel: HIIT News
Viewing all 73 articles
Browse latest View live

Women need role models in information technology and information about the benefits of the technology

0
0

The Helsinki Institute for Information Technology (HIIT) arranged a film evening in the premises of the software company Futurice in May. HIIT showed the American documentary film ‘Code Debugging the Gender Gap’, which focuses on programming, gender and minorities.

- Gender is a highly charged subject. Cultural differences were the most important issue highlighted in the panel discussion following the screening. This is because the film mainly examines the subject from the American perspective. However, the matter is not so clear-cut in Finland either and we too must pay attention to how woman employees are treated, says Matti Nelimarkka from HIIT, explaining the background to the event.

There are already gender gaps during basic education. Studies show that the feeling of computer incompetence is more common among girls than among boys. Boys do not feel so strongly about the matter even if their skills were at the same level.

- I took part in a mathematics competition in which one girl and me were among the finalists. Among the top finalists, the ratio between girls and boys was one to nine, explains 14-year-old Victor Branea, who is doing his work practice at HIIT.

According to the documentary film, the amount of IT work and the demand for programmers is increasing every year and it is impossible to meet the growing need without also recruiting women to the tasks. The importance of role models was underlined in the film and during the panel discussion. Women are needed as role models so that more girls would be willing to work in the IT sector.

- Women are often considered as strangers who are unable to master such tasks as programming and they must often work hard in order to show that they are real professionals, explains Marjo Kauppinen, the only woman professor at the Department of Computer Science, Aalto University.

The panelists also expressed the view that people writing the job advertisements for the IT sector should ensure that the advertisements appeal to women.

- A recruitment advertisement often contains a technology-oriented list of the technology skills required for the job. Women have a different perspective and they give priority to the benefits achieved through technology. If the job advertisements were more than just lists of technological skills, there would be more applicants, both women and men, who are interested in changing the world with the help of technology, adds Kauppinen.

Studies show that men are by nature able to pick the human content from information technology whereas for women information technology is first and foremost a matter of technology.

Reference: Papastergiou, M. (2008). Are Computer Science and Information Technology still masculine fields? High school students’ perceptions and career choices. Computers & Education, 51(2), 594–608. http://doi.org/10.1016/j.compedu.2007.06.009

 

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Matti Nelimarkka

20 Postdoctoral Researcher and Research Fellow Positions in ICT (Helsinki, Finland)

0
0

Aalto University and University of Helsinki, the two leading universities in Finland within computer science and information technology, are looking for excellent researchers in several areas of ICT.

Positions are available in the following areas:

  • HIIT Research Programme on Computational Inference, Professors Samuel Kaski, Jukka Corander, Petri Myllymäki, Antti Oulasvirta, Matti Pirinen, Aki Vehtari
  • HIIT Research Programme on Foundations of Computational Health, Professors Juho Rousu, Veli Mäkinen, Tero Aittokallio, Aristides Gionis, Keijo Heljanko, Jari Saramäki
  • HIIT Research Brogramme on Building Trust in Secure Computing Systems, Professors Tuomas Aura, N. Asokan, Valtteri Niemi, Stavros Tripakis, Sasu Tarkoma
  • HIIT Research Programme on Augmented Research, Professors Giulio Jacucci, Samuel Kaski, Petri Myllymäki, Aristides Gionis, Sasu Tarkoma, Niklas Rava
  • Information Retrieval, Human-Computer Interaction HCI, Machine Learning, Professor Giulio Jacucci
  • Adaptive and immersive environments for augmented social interaction, Professor Giulio Jacucci
  • Complex Systems Computation, Professor Petri Myllymäki
  • Internet of Things, Professor Mario Di Francesco
  • Creative software: automated text generation, adaptive software architectures, Professor Hannu Toivonen
  • Machine Learning and Adaptive User Interfaces, Professors Antti Oulasvirta, Jukka Corander,  Samuel Kaski
  • Probabilistic Machine Learning, Professor  Samuel Kaski
  • Probabilistic machine learning for precision medicine and data-driven healthcare, Professor Samuel Kaski
  • Machine learning for high-dimensional and structured data, Professors Hiroshi Mamitsuka, Samuel Kaski
  • Solver technology for answer-set programming, Professor Ilkka Niemelä, Dr. Tomi Janhunen
  • High-throughput bioinformatics and regulatory genomics, Professor Harri Lähdesmäki
  • Probabilistic modeling for biomedicine and personalised medicine, Professor Harri Lähdesmäki

For the full call text and information about the application process, please visit here.
 
The deadline for sending the application is September 30, 2016, at 2pm Finnish time.

Add to highlights: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Petri Myllymäki

HIIT scientists present the most advanced GWAS method for bacteria to date

0
0

A HIIT-wide team led by professor Jukka Corander included several scientists from both UH and Aalto with a joint mission to create the most advanced and computationally best scalable method for genome-wide association (GWAS) studies in bacteria. The team had a close collaboration with the Pathogen Genomics Group at the Wellcome Trust Sanger Institute where GWAS is an important step towards unraveling the secrets behind evolution and success of numerous major human pathogens from large-scale population genomic data. The new method, SEER, was published in Nature Communications on September 16 and it is already rapidly gaining worldwide popularity among microbiologists. Since SEER is scalable to even tens of thousands of bacterial genome sequences, it will open a totally new era in bacterial GWAS. Details of the method can be found at http://www.nature.com/articles/ncomms12797

Add to highlights: 
Banner image: 
Importance: 
Very important
Show in: 
HIIT news
Contact person: 
Jukka Corander

HIIT participated to the 10th International Workshop on Machine Learning in Systems Biology

0
0
10th International Workshop on Machine Learning in Systems Biology
September 3-4 2016, World Forum, The Hague

The tenth edition of MLSB was organized as a two-day satellite meeting before ECCB2016, the European Conference on Computational Biology (September 5-7, 2016) by Dick de Ridder and Aalt-Jan van Dijk (Wageningen University, The Netherlands) and Juho Rousu and Harri Lähdesmäki (Aalto University, Finland) at the World Forum in The Huage. The workshop was generously sponsored by contributions from NWO Exact Sciences, the Helsinki Institute of Information Technology (HIIT) and five companies: BaseClear, Bayer, Enza Zaden, Philips and RijkZwaan.

 

Introduction

Biology is rapidly turning into an information science, thanks to enormous advances in the ability to observe the molecular properties of cells, organs and individuals. This wealth of data allows us to model molecular systems at an unprecedented level of detail and to start to understand the underlying biological mechanisms. This field of systems biology creates a huge need for methods from machine learning, which find statistical dependencies and patterns in these large-scale datasets and that use them to establish models of complex molecular systems. MLSB, a series of workshops, is a scientific forum for the exchange between researchers from Systems Biology and Machine Learning, to promote the exchange of ideas, interactions and collaborations between these communities.
 
Programme
 
The programme contained four keynote talks by internationally recognized top scientists in the field:
  • Prof. Lodewyk Wessels, The Delft Bioinformatics Lab, Delft University of Technology, The Netherlands
  • Prof. Jukka Corander, Department of Mathematics and Statistics, University of Helsinki, Finland
  • Prof. Yvan Saeys, VIB Inflammation Research Center, Ghent University, Belgium
  • Prof. Ziv Bar-Joseph, School of Computer Science Carnegie--Mellon University, USA
 
Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Juho Rousu

Giant leap in ABC inference scalability

0
0

HIIT scientists Michael Gutmann and Corander published a machine learning based ABC inference approach in the Journal of Machine Learning Research. Their method (BOLFI) is based on Bayesian optimization with Gaussian processes and is generally applicable to simulator models with intractable likelihoods. Without sacrificing accuracy, BOLFI speeds up posterior computation by 3-4 orders of magnitude compared with the state-of-the-art sequential Monte Carlo algorithms. It is expected to become a new standard in ABC inference, paving way for a multitude of new applications where the earlier methods have been too expensive computationally. Details of the method can be found in the article: Bayesian Optimization for Likelihood-Free Inference of Simulator-Based Statistical Models. Michael U. Gutmann, Jukka Corander; 17(125):1−47, 2016. http://jmlr.csail.mit.edu/papers/v17/15-017.html

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Jukka Corander

Regression modelling reconstructs weather forecasts for the past from animal teeth

0
0

Research data was collected from Kenyan national parks over the past 60 years, combined with traits of the teeth of herbivorous mammals.

In the new study, the annual rainfall and average temperatures in the national parks are inferred from the teeth of herbivorous mammals. Such reverse engineering opens up new opportunities for interpreting fossil records. The results were recently published in the journal PNAS.

Exact data on the number and geographical spread of the animals in Kenya’s national parks have been collected over the course of the past 60 years. The data used for the modelling in this study include the mammals in Kenya's 13 national parks, dental traits, and rainfall, temperature and the amount of vegetation.

“We computed the average dental traits for each area and related them in relation to environmental factors using regression models. The model’s generalizability was tested, and the predictability of individual environmental factors was compared,” explains researcher Indrė Žliobaitė, who was responsible for the modelling.

The research shows that features in animal teeth are particularly good at detecting where the weather has been unfavorable for the species in question. Such weather conditions include long dry periods, heavy rains or exceptionally low temperatures – anything that could result in the animal’s primary food source becoming unavailable, forcing the animals to turn to less preferred plants to survive.

The researchers were particularly interested in why animals were absent from a particular geographical area.

“African national parks frequently endure poor years, which seem to prevent the establishment of permanent populations of certain animals. Animals live where the conditions allow them to live and reproduce over the span of decades or centuries,” says Mikael Fortelius, professor of evolutionary paleontology at the University of Helsinki.

“We would be able to go millions of years past and see what the weather conditions were like back then, and that we have actually done in another research article published earlier this year in The Royal Society Publishing including the temperature curves of the past millions of years”, adds Žliobaitė.

The role of a computer scientist in studies like this is to deal with high-dimensional datasets and make the estimates, as evolutionary paleontologists make the analysis and interpretations based on the estimates. This work follows the collaboration between professor of evolutionary paleontology Mikael Fortelius in the University of Helsinki and professor Heikki Mannila from the Aalto University Department of Computer Science, now the President of the Academy of Finland, started about 10 years ago.

PNAS.org: Herbivore teeth predict climatic limits in Kenyan ecosystems: Indrė Žliobaitė, Janne Rinne, Anikó B. Tóth, Michael Mechenich, Liping Liu, Anna K. Behrensmeyer and Mikael Fortelius

The Royal Society Publishing: An ecometric analysis of the fossil mammal record of the Turkana Basin: Mikael Fortelius, Indrė Žliobaitė, Ferhat Kaya, Faysal Bibi, René Bobe, Louise Leakey, Meave Leakey, David Patterson, Janina Rannikko and Lars Werdelin

Further information:

Indrė Žliobaitė
Researcher
Department of Computer Science and HIIT, Aalto University
Department of Geosciences and Geography, University of Helsinki
indre.zliobaite@aalto.fi

Mikael Fortelius
Professor of Evolutionary Paleontology
Department of Geosciences and Geography
University of Helsinki
mikael.fortelius@helsinki.fi

Watch the video

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Indrė Žliobaitė

Model checking verifies the correctness of nuclear power plant safety systems

0
0

The study utilises model checking to address the insufficiencies of testing and simulation in the verification of safety systems.

The object of Jussi Lahtinen’s dissertation was to find a more formal and mathematical approach to system verification and to develop model checking practices that are suitable for the nuclear industry. The traditional system verification methods, such as testing and simulation, do not have enough coverage to address the increasing digitalisation of safety automation systems.

Nuclear power plants have large safety systems in place that encompass multiple safety functions, such as the emergency diesel generator control system. In one of the techniques now developed, the system is divided into modules, and an algorithm is used for pinpointing the subset of modules that verifies the correctness of the system,’ says Lahtinen, explaining the practical implementation of the study.

At the architecture level, hardware failures in the microcircuits used for computing a number of functions, for example, are of pronounced significance. An individual software failure, on the other hand, is not all that safety-critical, given that the plant has a number of independent software-based safety systems in place.

Model checking is a highly effective method for finding latent design errors that may also be strange or unusual. Unlike testing or simulation, model checking is capable of achieving complete sequential coverage with respect to the requirement being examined,’ Lahtinen adds.

In the concluding phase of the dissertation, a method to support the structure-based testing of the function block diagrams used in the design of software-based systems was created. The method generates tests based on the structure of the function block diagram that describes the functioning of the safety automation system.

According to the feedback received from Fortum, the process of model checking as such may reveal errors that are easily ignored in testing. The comprehensive checking is also capable of analysing events over a very short time span,’ Lahtinen adds.

The results of the dissertation work have already been used in practical assignments for the Radiation and Nuclear Safety Authority concerning the Olkiluoto 3 project, for Fortum concerning the automation renewal of the Loviisa nuclear power plant, and for Fennovoima concerning the functional architecture of the foreseen Hanhikivi nuclear power plant. Further study on the integration of model checking with probabilistic risk analysis is already underway.

The dissertation work related to the study was supervised at the Aalto University Department of Computer Science by Professor Keijo Heljanko, and it was carried out at the VTT Technical Research Centre of Finland. A substantial part of the study was funded by the Finnish nuclear power plant safety research programme SAFIR. Model checking has been studied on a constant basis since 2007, and it is a very demanding method computationally.

More information:

Jussi Lahtinen
VTT
jussi.lahtinen@vtt.fi
+3580 400 519 798

Keijo Heljanko
Professor
Department of Computer Science
keijo.heljanko@aalto.fi
+358 50 430 0771

Doctoral dissertation:  Model Checking Large Nuclear Power Plant Safety System Design

Defence of dissertation

 

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Keijo Heljanko

Preethi Lahoti feels very privileged to be part of the Data Mining research group

0
0

Honours programme student Preethi Lahoti conducts research in graph mining and social-networks analysis.

Exceptionally qualified Master’s students have joined the honours programme in computer science. Altogether 15 Master’s students from all over the world will have hands-on experience in the actual computer science research. Majority of the honours programme students are specialized in the machine learning, data mining and probabilistic modelling research area.

Preethi Lahoti feels very privileged to be part of the Data Mining research group led by professor Aristides Gionis for the second year already. She conducts research in graph mining and social-networks analysis.

“We have undergoing research with Aristides Gionis and Gianmarco De Francisci Morales, as we study the problem of finding topic experts in large graphs. This research is part of a Tekes project on managing personal data”, describes Lahoti.

Lahoti had a research internship at Nokia Bell Labs in Dublin during the summer of 2016. She conducted research in Data analytics team in text mining, focused on designing efficient algorithms for computing text similarity measures. Results of the research were accepted as a paper “Efficient Set Intersection for Text Similarity Measures” in a top algorithms conference, ALENEX 2017.

“We also submitted a patent for a device for guided discovery of people with similar interests. The patent of the device is currently in the process of filing”, adds Lahoti.

Lahoti has been actively been involved in the social media, for instance in Quora she answers questions related to machine learning and studies at Aalto University. Lahoti also participated in womENcourage 2016 conference, intended to encourage women in computing, and she also acts as a teaching assistant for the machine learning and data mining students.

Oleksii Abramenko and Ivan Baranov from Ukraine, Shishir Bhattarai from Nepal, Mustafa Celikok from Turkey, Kunal Ghosh and Preethi Lahoti from India, Alexandru Mara from both Spain and Romania, Van Linh Nguyen from Vietnam and Siddhart Ramchandran from India all study different aspects of machine learning, data mining and probabilistic modelling.

Rinu Boney from India specializes in computer vision, Rory How from the UK studies cloud computing, Xiaoxiao Ma from China participates in game research, Hannu Seppänen from Finland looks into the digital disruption of the industry, and Rajagopalan Ranganathan from India together with Manish Thapa from Nepal are part of the secure systems research group.

More information:

Honours programme

Honours programme student Alexandru Mara is learning signals from huge network graphs

Van Linh Nguyen has joined the honours programme in computer science

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Aristides Gionis

EEG reveals information essential to users

0
0

For the first time, information retrieval is possible with the help of EEG interpreted with machine learning.

In a study conducted by the Helsinki Institute for Information Technology (HIIT) and the Centre of Excellence in Computational Inference (COIN), laboratory test subjects read the introductions of Wikipedia articles of their own choice. During the reading session, the test subjects’ EEG was recorded, and the readings were then used to model which key words the subjects found interesting.

 

‘The aim was to study if EEG can be used to identify the words relevant to a test subject, to predict a subject's search intentions and to use this information to recommend new relevant and interesting documents to the subject. There are millions of documents in the English Wikipedia, so the recommendation accuracy was studied against this vast but controllable corpus’, says HIIT researcher Tuukka Ruotsalo.

Due to the noise in brain signals, machine learning was used for modelling, so that relevance and interest could be identified by learning the EEG responses. With the help of machine learning methods, it was possible to identify informative words, so they were also useful in the information retrieval application.

‘Information overload is a part of everyday life, and it is impossible to react to all the information we see. And according to this study, we don’t need to; EEG responses measured from brain signals can be used to predict a user’s reactions and intent', tells HIIT researcher Manuel Eugster.

Based on the study, brain signals could be used to successfully predict other Wikipedia content that would interest the user.

‘Applying the method in real information retrieval situations seems promising based on the research findings. Nowadays, we use a lot of our working time searching for information, and there is much room in making knowledge work more effective, but practical applications still need more work. The main goal of this study was to show that this kind of new thing was possible in the first place’, tells Professor at the Department of Computer Science and Director of COIN Samuel Kaski.

‘It is possible that, in the future, EEG sensors can be worn comfortably. This way, machines could assist humans by automatically observing, marking and gathering relevant information by monitoring EEG responses’, adds Ruotsalo.

The study was carried out in cooperation by the Helsinki Institute for Information Technology (HIIT), which is jointly run by Aalto University and the University of Helsinki, and the Centre of Excellence in Computational Inference (COIN). The study has been funded by the EU, the Academy of Finland as a part of the COIN study on machine learning and advanced interfaces, and the Revolution of Knowledge Work project by Tekes.

See the video:

Further information:

Researcher Tuukka Ruotsalo
Aalto University, University of Helsinki, HIIT
+358 50 566 1400
tuukka.ruotsalo@aalto.fi

Professor Samuel Kaski
Aalto University
+358 50 305 8694
samuel.kaski@aalto.fi

Article

HIIT augmented research
Tekes Re:Know
EU:n MindSee project
Department of Computer Science
HIIT
The Centre of Excellence in Computational Inference (COIN)

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Tuukka Ruotsalo, Samuel Kaski

Machine Learning Coffee Seminar

0
0

Starting January 9, Helsinki region machine learning researchers will start our week by an exciting machine learning talk and discussion over coffee before and after the talk. The talks will start 9:15, with coffee served from 9:00. http://www.hiit.fi/mlseminar

The first talk is by Erkki Oja, "Unsupervised Machine Learning for Matrix Decomposition" on Jan 9 at 9:15 in Seminar room T6, Konemiehentie 2, Otaniemi.

 

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
samuel.kaski@aalto.fi

ELFI: Engine for Likelihood-Free Inference

0
0

HIIT researchers have developed an engine for likelihood-free inference (ELFI), a Python framework for simulator-based statistics, which is useful in Bayesian inference when the likelihood function is difficult to evaluate or unknown. Press release

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
henri.vuollekoski@aalto.fi

A new mutation mechanism was found in human and bacterial genomes

0
0

An international research team has found a new replacement mechanism that causes mutations in both humans and bacteria. The mechanism can cause several changes to a short stretch of DNA simultaneously. The research was conducted by observing fragments of DNA sequence that contained plenty of mutations.

‘In order to find out how common the new mutation mechanism is, genome data was analysed using computational bioinformatics and by mining the massive genome data related to the mutation event’, tells researcher Pekka Marttinen from the Department of Computer Science.

The changes in the activity of the bacteria caused by mutation were verified by for example gauging protein production and its changes. The experimentally observed changes in the bacteria's genome could not be explained by any known mechanism.

Antibiotics and radiation accelerated mutation

The research observed that for example UV irradiation increases the frequency of mutation, sometimes even 7000-fold. On the other hand, antibiotics caused the changes to occur 600 times faster than normal. Generally, the disruption of a cell's sustenance mechanisms seems to affect the frequency of mutation.

‘The research shows that the DNA of bacteria can change even if the new fragments do not fit the original DNA stretch perfectly. According to the research, this can potentially help bacteria become resistant to antibiotics and vaccines’, describes Professor Pål Jarle Johnsen from the Norwegian Arctic University.

‘Because the new type of mutations cause several changes to the DNA simultaneously, they can quickly change the activity of a whole gene. The birth mechanism has to be researched more, so that we get an understanding of the mechanism's significance in evolution, for example of the mutation's possible role in cancer. Cancer cells contained a remarkable abundance of changes caused by the mutation event which could be caused by the general weakening of the cells’ maintenance  mechanisms during cancer’, Marttinen adds.

In addition to Aalto's bioinformatics researchers, the research team consisted of medicine, microbiology, genetics and epidemiology researchers from Norway, Denmark, Germany and the United States. The research has been recently published in Proceedings of the National Academy of the United States of America.

Article (pnas.org)

More information:

Academy researcher Pekka Marttinen
Aalto University, Department of Computer Science
tel. +358 44 303 0349
pekka.marttinen@aalto.fi

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news

Discovering the evolution of Burkholderia pseudomallei, a dangerous tropical soil bacterium

0
0

A HIIT research team led by professor Jukka Corander collaborated with the pathogen genomics group at Wellcome Trust Sanger Institute to unearth the evolution of Burkholderia pseudomallei, a notorius soil bacterium causing serious human infections in tropics. Contrary to previous understanding, the genomic analyses revealed that the origin of B. pseudomallei isolates on the American continent is in Africa, dating back to the peak period of slave trade. Transfer of humans, plants and animals seeded the bacterium population on the new continent, providing it with an ample opportunity to expand its ecological range. B. pseudomallei infections result in an estimated number of 165,000 cases of human melioidosis annually and its virulence repertoire causes a considerable number of disease manifestations, ranging from liver abscesses to encephalitis. The computational genomics method developed recently as a collaboration between HIIT and Sanger Institute led to the discovery of genetic determinants of B. pseudomallei induced encephalitis, which occurs only in Australia. Results were published in Nature Microbiology: http://www.nature.com/articles/nmicrobiol2016263 

Add to highlights: 
Banner image: 
Importance: 
Important
Show in: 
HIIT news
Contact person: 
Jukka Corander

Election candidates engage in battles also in social media

0
0
In the recent work on "Working the fields of big data: Using big-data-augmented online ethnography to study candidate–candidate interaction at election time" published in Journal of Information Technology & Politics, Salla-Maaria Laaksonen, Matti Nelimarkka, Mari Tuokko, Mari Marttila, Arto Kekkonen and Mikko Vili explore how ethnography can be used to support computational data analysis, developing a novel observation that candidates engage in candidate-candidate interaction and even battles in social media.
 
 
Based on an extensive online material, researchers showed that social media interaction between the candidates of different parties can be aggressive and have an accusing tone. They gathered data on the social media activity of the candidates of the parliamentary election in spring 2015 and combined the online ethnographic observations made during the election campaign with a computational big data analysis. The total amount of data gathered was 1.2 million individual posts or comments. The recently published article focused on candidates’ conversations on Facebook walls, of which a sample of 137 000 messages were analysed.
 
‘When we were making ethnographic observations, we noticed that the candidates also commented on each other’s posts a lot, but there is little knowledge about the structure of such conversations between candidates in the social media,’ says Matti Nelimarkka, Researcher at the Aalto University Department of Computer Science and Helsinki Institute for Information Technology HIIT.
‘Something that really stood out was the way the candidates kept sniping at their rivals. Candidates were as if in a virtual name-calling competition that reminds you of the rap battles in hip hop,’ says Salla-Maaria Laaksonen, who conducts research on the online public space at the University of Helsinki.
They examined the phenomenon by studying the emotional content or sentiment of the messages with the help of computational text analysis. When candidates of the same party interacted on Facebook, the interaction was mainly positive. The interaction between candidates of different parties, on the other hand, more often had a negative tone. These messages highlighted the rivals’ errors, bad behaviour or incorrect statements. The intention seemed to be to slander the rivals, make oneself look better on the expense of the opponent, or even shame the other candidate or the candidate’s party.
‘A dialogue between candidates of different parties often followed when the criticised candidate started to defend himself or herself. Often, the messages also travelled from one media to another. For example, the conversation about a topic that had been brought up in a blog, in a news article, on television, in advertising or in a separate event was continued in the social media,’ continues Nelimarkka.

A continuous election panel

Although there was very little communication between candidates in the entire material consisting of one million messages, the arguing between candidates seemed to attract an audience. Sniping attracted more likes than a neutral discussion on Facebook, and candidates were active in responding to the accusations that were made.
‘Perhaps it was easier for candidates to ignore a question raised by a voter than a message from a rival accusing them of something. However, these verbal battles in which candidates have a go at each other are one proof of how social media changes campaigning for elections: online arenas form a large continuous election panel in which candidates try to beat rivalling candidates and opinions,’ says Laaksonen.
According to the researchers, this analysis highlights the need to combine qualitative methods with the analysing of large data masses. Without an understanding about the content of the materials, it is difficult to ask the right questions or interpret the computational analysis correctly.
 
‘The next areas of application in combining big data and ethnography could be commercial. For example, brand building or media events could combine both an ethnographic and a computational perspective, in which case we would not be trying to attract just clicks or reading the occasional message,’ Nelimarkka says in the end.
Digivaalit 2015 study was conducted by Aalto University Department of Computer Science as a representative of the HIIT research unit and Communication Research Centre CRC from the Department of Social Studies at the University of Helsinki. The study was funded by the Helsingin Sanomat Foundation and Kone Foundation.
 
Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Matti Nelimarkka (matti.nelimarkka@hiit.fi)

Finland wants to be world’s number one in artificial intelligence


Best student paper award at WSDM 2017

0
0

At this year's International Conference on Web Search and Data Mining (WSDM 2017), the best student paper award went to “Reducing Controversy by Connecting Opposing Views” by Venkata Rama Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, and Michael Mathioudakis, from Aalto University and Qatar Computing Research Institute.

For a high level description of the paper, please visit the blog of Aalto's Data Mining Group (link).

The full paper is publicly available on ACM's Digital Library (link).

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Michael Mathioudakis, michael.mathioudakis@aalto.fi

HIIT scientists make a breakthrough in genome-wide epistasis analysis

0
0

Epistatic interactions between polymorphisms in DNA are recognized as important drivers of evolution in numerous organisms. Study of epistasis in bacteria has been hampered by the lack of densely sampled population genomic data, suitable statistical models and inference algorithms sufficiently powered for extremely high-dimensional parameter spaces. In an article published in PloS Genetics, a HIIT team introduced the first model-based method for genome-wide epistasis analysis and use two of the largest available bacterial population genome data sets on Streptococcus pneumoniae (the pneumococcus) and Streptococcus pyogenes (group A Streptococcus) to demonstrate its potential for biological discovery. Our approach reveals interacting networks of resistance, virulence and core machinery genes in the pneumococcus, which highlights putative candidates for novel drug targets. We also discover a number of plausible targets of co-selection in S. pyogenes linked to RNA pseudouridine synthases. Our method significantly enhances the future potential of epistasis analysis for systems biology, and can complement genome-wide association studies as a means of formulating hypotheses for targeted experimental work.

Further details can be found at: http://journals.plos.org/plosgenetics/article?id=10.1371/journal.pgen.1006508

See also the media report by the Faculty of Science (in Finnish): https://www.helsinki.fi/fi/uutiset/tasmalaakkeita-bakteeri-infektioihin

Add to highlights: 
Banner image: 
Importance: 
Very important
Show in: 
HIIT news
Contact person: 
Jukka Corander

AncestryAI algorithm traces your family tree back more than 300 years

0
0

Aalto University doctoral student Eric Malmi has developed a family tree algorithm called AncestryAI. The algorithm looks for links between 5 million baptisms from the end of the 17th to the mid-19th century and partly to the beginning of the 20th century. To investigate your own family roots, you need to know about your own ancestors, because baptisms in the last hundred years are not public information.

‘The data is derived from parish registers. In the HisKi project, organized by the Genealogical Society of Finland, volunteer genealogists are entering information from registers into a database. Besides baptisms, the data includes marriages, burials and moves, although the algorithm is not yet taking advantage of this information. There are gaps in the material, for example because of churches burning down, but nevertheless, it is unusually comprehensive on an international level, including information for several centuries,’ said Malmi.

The family tree algorithm automatically searches for a child's most probable parents and creates family trees based on this. The algorithm gives several options based on the parents’ date and place of birth and similar names. The algorithm takes about half an hour to link all the records in the data.

‘The search path can also be used to find out whether two people are related to each other. Many people might be interested to know, for example, whether they are related to the great Finnish author Aleksis Kivi or other famous historical figures. Nevertheless, we need to consider the fact that if the path is long and all the links are uncertain, it is very unlikely that the whole path is correct,’ Malmi pointed out.

AncestryAI users can leave comments on the accuracy of the algorithm in inferring relationships. Using the comments, the algorithm can be trained to determine the relationships more accurately, and comments are displayed for other users.

‘It would be really interesting to have a family tree covering the whole of Finland, because it could also be used to study wars, epidemics, the influence of and changes in the class society. This is not possible yet, because, for example, the algorithm does not make use of communion books. So the algorithm is not intended to replace the work of genealogists, but to help them by speeding up their work, and somewhat improving the accuracy of their results,’ Malmi concluded.

Malmi is presenting AncestryAI at the Suku 2017 event in Otaniemi on 19 March 2017. At the beginning of April, Malmi is presenting the algorithm’s technical features at the World Wide Web Conference in Australia. AncestryAI can be accessed at http://ancestryai.cs.hut.fi/ and will run in a Chrome or Firefox browser. AncestryAI is part of Malmi’s doctoral thesis studies.

Further information:

Eric Malmi
Doctoral Candidate
Aalto University Department of Computer Science
eric.malmi@aalto.fi
www.genealogia.fi

hiski.genealogia.fi

 

Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
Contact person: 
Eric Malmi

Algorithms can exploit human perception in graph design

0
0

Algorithms can now exploit models and measures of human perception to generate scatterplot designs.

 

Scatterplots are widely used in various disciplines and areas beyond sciences to visually communicate relationships between two data variables. Yet, very few users realize the effect the visual design of scatterplots can have on the human perception and understanding. Moreover, default designs of scatterplots often represent the data poorly, and manually fine tuning the design is difficult.

HIIT researchers have recently found an algorithmic approach to automatically improve the design of scatterplots by exploiting models and measures of human perception.

See press release and project webpage.
 

Article: Micallef, L., Palmas, G., Oulasvirta, A. & Weinkauf, T. (2017), Towards Perceptual Optimization of the Visual Design of Scatterplots, IEEE Transactions on Visualization and Computer Graphics 23(6) : 1-12.

 

Add to highlights: 
Banner image: 
Importance: 
Very important
Show in: 
HIIT news
Contact person: 
Luana Micallef, Antti Oulasvirta

IEEE PacificVis 2017 Best Paper Honorable Mention Award

0
0

Perceptual Optimization of the Visual Design of Scatterplots


HIIT, Aalto and KTH researchers have recently found an algorithmic approach to automatically improve the design of scatterplots by exploiting models and measures of human perception.

Their work has received a best paper honorable mention award at IEEE PacificVis 2017.

See press release and project webpage.
 

Article: Micallef, L., Palmas, G., Oulasvirta, A. & Weinkauf, T. (2017), Towards Perceptual Optimization of the Visual Design of Scatterplots, IEEE Transactions on Visualization and Computer Graphics 23(6) : 1588-1599.
 
Add to highlights: 
Banner image: 
Importance: 
Normal
Show in: 
HIIT news
UIx news
Viewing all 73 articles
Browse latest View live




Latest Images