Match!
Krisztian Buza
University of Bonn
54Publications
14H-index
464Citations
Publications 54
Newest
#2Regina Meszlényi (MTA: Hungarian Academy of Sciences)H-Index: 5
Last.Mihai Alexandru SuciuH-Index: 6
view all 6 authors...
Recent advances in brain imaging technology, coupled with large-scale brain research projects, such as the BRAIN initiative in the U.S. and the European Human Brain Project, allow us to capture brain activity in unprecedented details. In principle, the observed data is expected to substantially shape our knowledge about brain activity, which includes the development of new biomarkers of brain disorders. However, due to the high dimensionality, the analysis of the data is challenging, and selecti...
6 CitationsSource
#1Ladislav Peska (MTA: Hungarian Academy of Sciences)H-Index: 1
#2Krisztian BuzaH-Index: 14
Last.Jlia Koller (Semmelweis University)H-Index: 1
view all 3 authors...
Proposing BRDTI method for per-drug ranking of DTIs.Performed comparative evaluation of BRDTI w.r.t. AUC and per-drug nDCG.BRDTI achieved best average results on predicting new targets for existing drugs. Background and objectiveIn silico prediction of drug-target interactions (DTI) could provide valuable information and speed-up the process of drug repositioning finding novel usage for existing drugs. In our work, we focus on machine learning algorithms supporting drug-centric repositioning app...
16 CitationsSource
#1Regina Meszlényi (MTA: Hungarian Academy of Sciences)H-Index: 5
#2Krisztian Buza (MTA: Hungarian Academy of Sciences)H-Index: 14
Last.Zoltán Vidnyánszky (MTA: Hungarian Academy of Sciences)H-Index: 5
view all 3 authors...
Machine learning techniques have become increasingly popular in the field of resting state fMRI (functional magnetic resonance imaging) network based classification. However, the application of convolutional networks has been proposed only very recently and has remained largely unexplored. In this paper we describe a convolutional neural network architecture for functional connectome classification called connectome-convolutional neural network (CCNN). Our results on simulated datasets and a pub...
19 CitationsSource
#1Krisztian Buza (MTA: Hungarian Academy of Sciences)H-Index: 14
#2Ladislav Peska (Charles University in Prague)H-Index: 8
Abstract Computational prediction of drug–target interactions is an essential task with various applications in the pharmaceutical industry, such as adverse effect prediction or drug repositioning. Recently, expert systems based on machine learning have been applied to drug–target interaction prediction. Although hubness-aware machine learning techniques are among the most promising approaches, their potential to enhance drug–target interaction prediction methods has not been exploited yet. In t...
8 CitationsSource
#1Krisztian Buza (University of Bonn)H-Index: 14
#2Ladislav Peska (Charles University in Prague)H-Index: 8
Due to its pharmaceutical applications, one of the most prominent machine learning challenges in bioinformatics is the prediction of drug–target interactions. State-of-the-art approaches are based on various techniques, such as matrix factorization, restricted Boltzmann machines, network-based inference and bipartite local models (BLM). In this paper, we extend BLM by the incorporation of a hubness-aware regression technique coupled with an enhanced representation of drugs and targets in a multi...
2 CitationsSource
#1Regina Meszlényi (MTA: Hungarian Academy of Sciences)
#2Ladislav Peska (Charles University in Prague)H-Index: 8
Last.Vidnyanszky Zoltan (MTA: Hungarian Academy of Sciences)H-Index: 23
view all 6 authors...
Objectives Traditionally resting-state networks are analysed with methods implying zero-lag linear dependence between brain regions, i.e. functional connectivity strength between voxel pairs is characterized by the correlation-coefficient of the two measured signal. It is known that the shape and timing of hemodynamic response function differs between brain regions and this introduces artefacts in linear measures. Methods We proposed Dynamic Time Warping (DTW) distance to be used as an alternati...
Source
May 22, 2017 in CORES (Computer Recognition Systems)
#1Krisztian Buza (University of Bonn)H-Index: 14
#2Piroska B. KisH-Index: 4
As shown by various studies, the dynamics of typing on a keyboard is characteristic to persons. On the one hand, this may allow for person identification based on keystroke dynamics in various applications. On the other hand, in certain situations, such as chat-based anonymous helplines, web search for sensitive topics, etc., users may not want to reveal their identity. In general, there are various methods to increase the protection of personal data. In this paper, we propose the concept of pri...
1 CitationsSource
May 22, 2017 in CORES (Computer Recognition Systems)
#1Dora Neubrandt (BME: Budapest University of Technology and Economics)H-Index: 2
#2Krisztian Buza (University of Bonn)H-Index: 14
The increasing interest in person identification based on keystroke dynamics can be attributed to several factors. First of all, it is a cheap and widely applicable technique, whereas online services such as internet banking or online tax declaration require reliable person identification methods. Furthermore, there are various attack techniques against the existing identification methods, thus combining the existing methods with new person identification methods could improve the reliability of...
2 CitationsSource
Echo state networks are simple recurrent neural networks that are easy to implement and train. Despite their simplicity, they show a form of memory and can predict or regenerate sequences of data. We make use of this property to realize a novel neural cryptography scheme. The key idea is to assume that Alice and Bob share a copy of an echo state network. If Alice trains her copy to memorize a message, she can communicate the trained part of the network to Bob who plugs it into his copy to regene...
4 Citations
#1Krisztian Buza (MTA: Hungarian Academy of Sciences)H-Index: 14
#2Dora Neubrandt (BME: Budapest University of Technology and Economics)H-Index: 2
The availability of cheap and widely applicable person identification techniques is essential due to wide-spread usage of online services. The dynamics of typing is characteristic to particular users, and users are hardly able to mimic the dynamics of typing of others. State-of-the-art solutions for person identification from the dynamics of typing are based on machine learning. The presence of hubs, i.e., few instances that appear as nearest neighbors of surprisingly many other instances, have ...
Source
123456