Adam Gonczarek

Decision rules extraction from data stream in the presence of changing context for diabetes treatment

The knowledge extraction is an important element of the e-Health system. In this paper, we introduce a new method for decision rules extraction called Graph-based Rules Inducer to support the medical interview in the diabetes treatment. The emphasis is put on the capability of hidden context change tracking. The context is understood as a set of all factors affecting patient condition. In order to follow context changes, a forgetting mechanism with a forgetting factor is implemented in the proposed algorithm. Moreover, to aggregate data, a graph representation is used and a limitation of the search space is proposed to protect from overfitting. We demonstrate the advantages of our approach in comparison with other methods through an empirical study on the Electricity benchmark data set in the classification task. Subsequently, our method is applied in the diabetes treatment as a tool supporting medical interviews.

Learning Invariant Features Using Subspace Restricted Boltzmann Machine

The subspace restricted Boltzmann machine (subspaceRBM) is a third-order Boltzmann machine where multiplicative interactions are between one visible and two hidden units. There are two kinds of hidden units, namely, gate units and subspace units. The subspace units reflect variations of a pattern in data and the gate unit is responsible for activating the subspace units. Additionally, the gate unit can be seen as a pooling feature. We evaluate the behavior of subspaceRBM through experiments with MNIST digit recognition task and Caltech 101 Silhouettes image corpora, measuring cross-entropy reconstruction error and classification error.

Articulated tracking with manifold regularized particle filter

In this paper, we investigate articulated human motion tracking from video sequences using Bayesian approach. We derive a generic particle-based filtering procedure with a low-dimensional manifold. The manifold can be treated as a regularizer that enforces a distribution over poses during tracking process to be concentrated around the low-dimensional embedding. We refer to our method as manifold regularized particle filter. We present a particular implementation of our method based on back-constrained gaussian process latent variable model and gaussian diffusion. The proposed approach is evaluated using the real-life benchmark dataset HumanEva. We show empirically that the presented sampling scheme outperforms sampling-importance resampling and annealed particle filter procedures.

A Probabilistic Approach to Structural Change Prediction in Evolving Social Networks

We propose a predictive model of structural changes in elementary sub graphs of social network based on Mixture of Markov Chains. The model is trained and verified on a dataset from a large corporate social network analyzed in short, one day-long time windows, and reveals distinctive patterns of evolution of connections on the level of local network topology. We argue that the network investigated in such short timescales is highly dynamic and therefore immune to classic methods of link prediction and structural analysis, and show that in the case of complex networks, the dynamic sub graph mining may lead to better prediction accuracy. The experiments were carried out on the logs from the Wroclaw University of Technology mail server.

Interaction prediction in structure-based virtual screening using deep learning

We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each compound separately. These fingerprints are further transformed non-linearly, their inner-product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E and PDBBind databases.We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each molecule separately. These fingerprints are further non-linearly transformed, their inner product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E, MUV and PDBBind databases.

Sparse hidden units activation in Restricted Boltzmann Machine

Sparsity has become a concept of interest in machine learning for many years. In deep learning sparse solutions play crucial role in obtaining robust and discriminative features. In this paper, we study a new regularization term for sparse hidden units activation in the context of Restricted Boltzmann Machine (RBM). Our proposition is based on the symmetric Kullback-Leibler divergence applied to compare the actual and the desired distribution over the active hidden units. We compare our method against two other enforcing sparsity regularization terms by evaluating the empirical classification error using two datasets: (i) for image classification (MNIST), (ii) for document classification (20-newsgroups).

Accelerated learning for Restricted Boltzmann Machine with momentum term

Restricted Boltzmann Machines are generative models which can be used as standalone feature extractors, or as a parameter initialization for deeper models. Typically, these models are trained using Contrastive Divergence algorithm, an approximation of the stochastic gradient descent method. In this paper, we aim at speeding up the convergence of the learning procedure by applying the momentum method and the Nesterov’s accelerated gradient technique. We evaluate these two techniques empirically using the image dataset MNIST.

New classes of integrals inherent in the mathematical structure of extended equations describing superconducting systems

In this paper, we discuss the mathematical structure of the s-wave superconducting gap and other quantitative characteristics of superconducting systems. In particular, we evaluate and discuss integrals inherent in fundamental equations describing superconducting systems. The results presented here extend the approach formulated by Abrikosov and Maki, which was restricted to the first-order expansion. A few infinite families of integrals are derived and allow us to express the fundamental equations by means of analytic formulas. They can be then exploited in order to find some quantitative characteristics of superconducting systems by the method of successive approximations. We show that the results can be applied to some modern formalisms in order to study high-Tc superconductors and other superconducting materials of the new generation.

Migration-aware Optimization of Virtualized Computational Resources Allocation in Complex Systems

In this paper a task of resources allocation in the complex system is considered. Novelty of the formulated task consists of assumption that the applications assigned with resources of one machine can be migrated to another machine during system lifetime. The formulated task has been solved using proposed heuristic optimization method. Due to non-convex set of valid solutions the optimization procedure has been decomposed into two stages and forms approach similar to the relax-and-round approach. Proposed decomposition approach facilitates fast algorithm convergence and guaranties that achieved solution satisfies assumed constraints.

NMRNet: a deep learning approach to automated peak picking of protein NMR spectra

Motivation: Automated selection of signals in protein NMR spectra, known as peak picking, has been studied for over 20 years, nevertheless existing peak picking methods are still largely deficient. Accurate and precise automated peak picking would accelerate the structure calculation, and analysis of dynamics and interactions of macromolecules. Recent advancement in handling big data, together with an outburst of machine learning techniques, offer an opportunity to tackle the peak picking problem substantially faster than manual picking and on par with human accuracy. In particular, deep learning has proven to systematically achieve human‐level performance in various recognition tasks, and thus emerges as an ideal tool to address automated identification of NMR signals. Results: We have applied a convolutional neural network for visual analysis of multidimensional NMR spectra. A comprehensive test on 31 manually annotated spectra has demonstrated top‐tier average precision (AP) of 0.9596, 0.9058 and 0.8271 for backbone, side‐chain and NOESY spectra, respectively. Furthermore, a combination of extracted peak lists with automated assignment routine, FLYA, outperformed other methods, including the manual one, and led to correct resonance assignment at the levels of 90.40%, 89.90% and 90.20% for three benchmark proteins. Availability and implementation: The proposed model is a part of a Dumpling software (platform for protein NMR data analysis), and is available at https://dumpling.bio/. Supplementary information: Supplementary data are available at Bioinformatics online.