Wyniki wyszukiwania - BazTech

1

Analiza zbioru danych dotyczących oceny akceptowalności samochodów za pomocą teorii zbiorów przybliżonych i programu RSES

Gorączka Mateusz

Studia i Materiały Informatyki Stosowanej

|

2024

|

T. 16, nr 1

24--32

PL

Artykuł skupia się na analizie danych z wykorzystaniem teorii zbiorów przybliżonych oraz różnych metod, takich jak algorytm genetyczny, klasyfikacja za pomocą zestawu reguł i metoda walidacji krzyżowej. Przedstawiono także kompletny proces analizy danych przy użyciu programu RSES. Wykorzystany zbiór danych oraz wyniki analizy zostałyomówione w kontekście teorii zbiorów przybliżonych. Artykuł kończy się podsumowaniem i wnioskamiskupiającymi się na aspekcie skuteczności wspomnianych metod w analizie zbioru danych oraz efektywności programu w kwestii przeprowadzania w nim analiz.

EN

The article focuses on data analysis using rough set theory and various methods such as the genetic algorithm, rule set classification and the cross-validation method. The complete data analysis process using RSES is also presented. The data set used and the results of the analysis are discussed in the context of rough set theory. The article concludes with a summary and conclusions focusing on the aspect of the effectiveness of aforementioned methods in analysing the dataset and the efficiency of the programin terms of performing analysis in it.

2

Liquid Detection and Instance Segmentation based on Mask R-CNN in Industrial Environment

Gawdzik Grzegorz, Arkadiusz Orłowski

Machine Graphics and Vision

|

2023

|

Vol. 32, No. 3/4

193--203

EN

The goal of the paper is to present an efficient approach to detect and instantiate liquid spilled in the industrial and industrial-like environments. Motivation behind it is to enable mobile robots to automatically detect and collect samples of spilled liquids. Due to the lack of useful training data of spilled substances, a new dataset with RGB images and masks was gathered. A new application of the Mask-RCNN-based algorithm is proposed which has the functionalities of detecting the spilled liquid and segmenting the image.

3

Design of Artificial Neural Network for Prediction of Hydrogen Sulfide and Carbon Dioxide Concentrations in a Natural Gas Sweetening Plant

Alardhi Saja Mohsen, Al-Jadir Thaer, Hasan Ahmed Mudheher, Jaber Alaa Abdulhady, Al Saedi Laith Majeed

Ecological Engineering & Environmental Technology

|

2023

|

Vol. 24, iss. 2

55--66

EN

Gas sweetening is a fundamental step in gas treatment processes for environmental and safety concerns. One of the most extensively used and largely recognized solvents for gas sweetening is methyl diethanolamine (MDEA). One of the most crucial metrics for measuring the effectiveness of gas treatment units is the amount of acid gas that has been treated with MDEA solution. As a result, it should be regularly monitored to avoid operational issues in downstream processes and excessive energy consumption. In this study, the artificial neural network (ANN) approach was followed to predict the H2S and CO2 sour gases concentrations of sweetening process. The model was built using dataset gathered from a real operation plant in Iraq, collected from February 2019 to February 2020, and used as input to the neural network. The data include H2S and CO2 concentrations of the feed gas, temperature, pressure, and flow rate of the unit. The designed ANN model showed good accuracy in modeling the process under investigation, even for a wide range of parameter variability. The testing outcomes demonstrated a high coefficient of determination (R2) of greater than 0.99, while the overall training performance showed a low mean squared error (MSE) of less than 0.0003.

4

Elaboration of financial fraud ontology

Hussaini Adamu, Guessoum Zahia, Mercier-Laurent Eunika

Annals of Computer Science and Information Systems

|

2022

|

Vol. 32

277--285

EN

Financial Frauds have dynamically changed, the fraudsters are becoming more sophisticated.There has been an estimated global loss of 5.127 trillion each year due to various forms of financial frauds. Industries like banking, insurance, e-commerce and telecommunication are the main victims of financial frauds. Several techniques have been proposed and applied to understand and detect financial frauds. In this paper we propose an ontology to describe financial frauds and related knowledge. The aim of this ontology is to provide a semantic framework for the detection of financial frauds. Theoretical ontology has been elaborated exploring various sources of information. After describing the research objectives, related works and research methodology, this paper presents details of theoretical ontology. It is followed by its validation using real data sets. Discussion of the obtained results gives some perspectives for the future work.