Publications
Filters
total: 843
Catalog Publications
Year 2024
-
An intelligent cellular automaton scheme for modelling forest fires
PublicationForest fires have devastating consequences for the environment, the economy and human lives. Understanding their dynamics is therefore crucial for planning the resources allocated to combat them effectively. In a world where the incidence of such phenomena is increasing every year, the demand for efficient and accurate computational models is becoming increasingly necessary. In this study, we perform a revision of an initial proposal...
-
Data on LEGO sets release dates and worldwide retail prices combined with aftermarket transaction prices in Poland between June 2018 and June 2023
PublicationThe dataset contains LEGO bricks sets item count and pricing history for AI-based set pricing prediction. The data spans the timeframe from June 2018 to June 2023. The data was obtained from three sources: Brickset.com (LEGO sets retail prices, release dates, and IDs), Lego.com official web page (ID number of each set that was released by Lego, its retail prices, the current status of the set) and promoklocki.pl web page (the retail...
-
Dataset Characteristics and Their Impact on Offline Policy Learning of Contextual Multi-Armed Bandits
PublicationThe Contextual Multi-Armed Bandits (CMAB) framework is pivotal for learning to make decisions. However, due to challenges in deploying online algorithms, there is a shift towards offline policy learning, which relies on pre-existing datasets. This study examines the relationship between the quality of these datasets and the performance of offline policy learning algorithms, specifically, Neural Greedy and NeuraLCB. Our results...
-
LSA Is not Dead: Improving Results of Domain-Specific Information Retrieval System Using Stack Overflow Questions Tags
PublicationThe paper presents the approach to using tags from Stack Overflow questions as a data source in the process of building domain-specific unsupervised term embeddings. Using a huge dataset of Stack Overflow posts, our solution employs the LSA algorithm to learn latent representations of information technology terms. The paper also presents the Teamy.ai system, currently developed by Scalac company, which serves as a platform that...
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublicationIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
Sampling-based novel heterogeneous multi-layer stacking ensemble method for telecom customer churn prediction
PublicationIn recent times, customer churn has become one of the most significant issues in business-oriented sectors with telecommunication being no exception. Maintaining current customers is particularly valuable due to the high degree of rivalry among telecommunication companies and the costs of acquiring new ones. The early prediction of churned customers may help telecommunication companies to identify the causes of churn and design...
Year 2023
-
A Formal Approach to Model the Expansion of Natural Events: The Case of Infectious Diseases
PublicationA formal approach to modeling the expansion of natural events is presented in this paper. Since the mathematical, statistical or computational methods used are not relevant for development, a modular framework is carried out that guides from the external observation down to the innermost level of the variables that have to appear in the future mathematical-computational formalization. As an example we analyze the expansion of Covid-19....
-
A multithreaded CUDA and OpenMP based power‐aware programming framework for multi‐node GPU systems
PublicationIn the paper, we have proposed a framework that allows programming a parallel application for a multi-node system, with one or more GPUs per node, using an OpenMP+extended CUDA API. OpenMP is used for launching threads responsible for management of particular GPUs and extended CUDA calls allow to manage CUDA objects, data and launch kernels. The framework hides inter-node MPI communication from the programmer who can benefit from...
-
AngioScore: An artificial intelligence tool to assess coronary artery lesions
PublicationThe functionality scope of the AngioScore tool in semi-automatic assessment of stenoses according to the SYNTAX scale was presented. An evaluation of the preliminary accuracy of AngioScore in lesion assessment was performed.
-
Antipsychotic drug prescription sequence analysis in relation to death occurrence and cardiometabolic drug usage: A retrospective longitudinal study
PublicationThe potential role of antipsychotics in increasing cardiovascular risk of mortality is still debated. The aim of this study was to assess the death risk associated with sequences of first-generation antipsychotic (FGA) and second-generation antipsychotic (SGA) prescriptions, including clozapine and lithium, and drugs for cardiometabolic diseases. We conducted a retrospective longitudinal analysis involving 84,881 patients who received...
-
Application of a stochastic compartmental model to approach the spread of environmental events with climatic bias
PublicationWildfires have significant impacts on both environment and economy, so understanding their behaviour is crucial for the planning and allocation of firefighting resources. Since forest fire management is of great concern, there has been an increasing demand for computationally efficient and accurate prediction models. In order to address this challenge, this work proposes applying a parameterised stochastic model to study the propagation...
-
Characterizing the Scalability of Graph Convolutional Networks on Intel® PIUMA
PublicationLarge-scale Graph Convolutional Network (GCN) inference on traditional CPU/GPU systems is challenging due to a large memory footprint, sparse computational patterns, and irregular memory accesses with poor locality. Intel’s Programmable Integrated Unffied Memory Architecture (PIUMA) is designed to address these challenges for graph analytics. In this paper, a detailed characterization of GCNs is presented using the Open-Graph Benchmark...
-
Comparison of Selected Neural Network Models Used for Automatic Liver Tumor Segmentation
PublicationAutomatic and accurate segmentation of liver tumors is crucial for the diagnosis and treatment of hepatocellular carcinoma or metastases. However, the task remains challenging due to imprecise boundaries and significant variations in the shape, size, and location of tumors. The present study focuses on tumor segmentation as a more critical aspect from a medical perspective, compared to liver parenchyma segmentation, which is the...
-
Dataset Related Experimental Investigation of Chess Position Evaluation Using a Deep Neural Network
PublicationThe idea of training Articial Neural Networks to evaluate chess positions has been widely explored in the last ten years. In this paper we investigated dataset impact on chess position evaluation. We created two datasets with over 1.6 million unique chess positions each. In one of those we also included randomly generated positions resulting from consideration of potentially unpredictable chess moves. Each position was evaluated...
-
Dynamic GPU power capping with online performance tracing for energy efficient GPU computing using DEPO tool
PublicationGPU accelerators have become essential to the recent advance in computational power of high- performance computing (HPC) systems. Current HPC systems’ reaching an approximately 20–30 mega-watt power demand has resulted in increasing CO2 emissions, energy costs and necessitate increasingly complex cooling systems. This is a very real challenge. To address this, new mechanisms of software power control could be employed. In this...
-
Efficient parallel implementation of crowd simulation using a hybrid CPU+GPU high performance computing system
PublicationIn the paper we present a modern efficient parallel OpenMP+CUDA implementation of crowd simulation for hybrid CPU+GPU systems and demonstrate its higher performance over CPU-only and GPU-only implementations for several problem sizes including 10 000, 50 000, 100 000, 500 000 and 1 000 000 agents. We show how performance varies for various tile sizes and what CPU–GPU load balancing settings shall be preferred for various domain...
-
Empirical analysis of tree-based classification models for customer churn prediction
PublicationCustomer churn is a vital and reoccurring problem facing most business industries, particularly the telecommunications industry. Considering the fierce competition among telecommunications firms and the high expenses of attracting and gaining new subscribers, keeping existing loyal subscribers becomes crucial. Early prediction of disgruntled subscribers can assist telecommunications firms in identifying the reasons for churn and...
-
Energy-Aware Scheduling for High-Performance Computing Systems: A Survey
PublicationHigh-performance computing (HPC), according to its name, is traditionally oriented toward performance, especially the execution time and scalability of the computations. However, due to the high cost and environmental issues, energy consumption has already become a very important factor that needs to be considered. The paper presents a survey of energy-aware scheduling methods used in a modern HPC environment, starting with the...
-
From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies
PublicationIn this paper, we propose a novel approach for obtaining predictions from per-class scores to improve the accuracy of multi-label classification systems. In a multi-label classification task, the expected output is a set of predicted labels per each testing sample. Typically, these predictions are calculated by implicit or explicit thresholding of per-class real-valued scores: classes with scores exceeding a given threshold value...
-
General Provisioning Strategy for Local Specialized Cloud Computing Environments
PublicationThe well-known management strategies in cloud computing based on SLA requirements are considered. A deterministic parallel provisioning algorithm has been prepared and used to show its behavior for three different requirements: load balancing, consolidation, and fault tolerance. The impact of these strategies on the total execution time of different sets of services is analyzed for randomly chosen sets of data. This makes it possible...