| Volume 26, Issue 1 | |
| FireGrid – Software for 2-D Fire Simulation Using the Game Method for Modelling | 5-18 |
| Deyan G. Mavrov, Veselina Bureva | |
| doi: 10.7546/ijba.2022.26.1.000880 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Deyan G. Mavrov, Veselina Bureva (2022) FireGrid – Software for 2-D Fire Simulation Using the Game Method for Modelling, Int J Bioautomation, 26 (1), 5-18, doi: 10.7546/ijba.2022.26.1.000880 | |
| Abstract: The paper presents FireGrid, an application software program for performing two-dimensional fire spread simulation using Atanassov's Game Method for Modelling (GMM). The software implements a model of fire spread with one or more starting points of ignition onto a planar grid of square cells that represent an idealized terrain of flammable areas of vegetation, and inflammable areas of rocks and water basins. The applications allows also locating a fire's starting point(s) by subtracting the initial configuration from the final one and decrementing all affected and adjacent cells by one. In addition to the preliminary defining the pattern of fire spread, manual control of the spread is allowed during simulation by selecting the cells that are to burn on the next iteration.
Keywords: Game Method for Modelling, GUI, Programming | |
| A Gene-disease Association Prediction Algorithm Based on Multi-source Data Fusion | 19-36 |
| Fei Wang | |
| doi: 10.7546/ijba.2022.26.1.000870 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Fei Wang (2022) A Gene-disease Association Prediction Algorithm Based on Multi-source Data Fusion, Int J Bioautomation, 26 (1), 19-36, doi: 10.7546/ijba.2022.26.1.000870 | |
| Abstract: Accurate gene-disease association prediction results are the basis for effective diagnosis and treatment of complex genetic diseases. However, existing studies related to this topic generally face problems in two aspects: large volume of original data and diverse data type, and data fusion difficulty. Therefore, this paper studied a gene-disease association prediction algorithm based on multi-source data fusion. At first, it processed the multi-dimensional gene phenotype data, analyzed the gene-disease associations of different phenotypes, and completed the selection of disease gene loci under multi-dimensional phenotypes. Then, this paper fused the multi-source data containing the gene expression data, gene sequence data, gene interaction data, and transcriptome sequencing data, and established the corresponding gene-disease association prediction model. At last, the effectiveness of the constructed prediction model was verified by experimental results. The research results obtained in this paper can improve the low utilization of gene datasets, restored the main features of the datasets to the greatest extent, reasonably processed the data noise, effectively enhanced the robustness of the model, and further improved the classification accuracy of the prediction of disease-causing genes.
Keywords: Gene-disease association prediction, Multi-dimensional phenotype, Multi-source data fusion | |
| On a Possible Approach to Risk Prediction of Recurrence of Atrial Fibrillation аfter Catheter Ablation According to Data from the Pre-procedure Period | 37-66 |
| Iskren Garvanski, Mikhail Matveev, Vessela Krasteva, Todor Stoyanov, Iana Simova | |
| doi: 10.7546/ijba.2022.26.1.000869 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Iskren Garvanski, Mikhail Matveev, Vessela Krasteva, Todor Stoyanov, Iana Simova (2022) On a Possible Approach to Risk Prediction of Recurrence of Atrial Fibrillation аfter Catheter Ablation According to Data from the Pre-procedure Period, Int J Bioautomation, 26 (1), 37-66, doi: 10.7546/ijba.2022.26.1.000869 | |
| Abstract: The aim of the study is to identify and evaluate predictors of recurrent paroxysms of atrial fibrillation (AF) paroxysms based on data from the preprocedural period among personal indices, history, comorbidities, ultrasound examination, and morphological components of f-waves, such as spectral amplitude and frequency. 39 patients with antral pulmonary vein isolation using radiofrequency or cryoenergy were included. Spectral analysis of f-waves was performed by fast Fourier transform of the ECG signal after suppression of the T-wave and QRS-complex. The performed U-test for the difference between the amplitude and frequency indicators in the groups without and with recurrence of AF shows a significant difference between the amplitude values in the two studied groups of patients. Through a stepwise discriminant analysis of a total of 14 indicators, 5 reliably separated groups without and with recurrence were determined: Echo LV-EF, spectral amplitude of f-waves, heart failure, Stroke/TIA, diabetes. The discriminator synthesized on these indicеs classified among the 39 patient – 25 without relapse (group 1) and 14 with relapse (group 2), 3 patients wrong from group 1 to group 2 (false positive), or 12%, and 1 patient was wrong from group 2 to group 1 (false negative), or 7.1%. These results give grounds to accept the hypothesis that it is possible to develop a decision rule for determining the degree of risk of post-procedural recurrence of AF from pre-procedural period data.
Keywords: Atrial fibrillation, Catheter Ablation, Post-procedural recurrence of atrial, Fibrillation | |
| Knowledge Mapping of Medicinal Plants Based on Artificial Neural Network | 67-82 |
| Lei Miao | |
| doi: 10.7546/ijba.2022.26.1.000871 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Lei Miao (2022) Knowledge Mapping of Medicinal Plants Based on Artificial Neural Network, Int J Bioautomation, 26 (1), 67-82, doi: 10.7546/ijba.2022.26.1.000871 | |
| Abstract: Knowledge mapping of medicinal plants enable ordinary people to differentiate between medicinal plants and learn their pharmacological effects, provide assistances and instructions to medical workers during the use of medicinal plants, and support intelligent queries of the properties of traditional medicinal plants. This paper innovatively introduces artificial neural network to the knowledge mapping of medicinal plants, and provides a practical and valuable reference for scientific development and reasonable use of medicinal plants. Firstly, the entity relationships were designed for medical knowledge map, and the definitions, scales, and examples were given for each type of data in the proposed knowledge map of medicinal plants. Next, the authors detailed the ideas of multi-source knowledge fusion, and the acquisition and storage strategies for entity information of medicinal plants. Then, the attention-based bidirectional gated recurrent network was combined with convolutional neural network to detect the genetic relationships between medicinal plants from the angles of semantics and texts. Finally, this paper explains the semantic retrieval algorithm for medicinal plants, and visualizes the knowledge map. The proposed model and semantic retrieval algorithm were proved effective and superior through experiments. It is concluded that: The smaller the batch size, the higher the recognition accuracy of plant entities, and the better the recognition effect. The research findings provide a reference for knowledge mapping in other fields.
Keywords: Neural network, Medicinal plants, Knowledge map, Genetic relationship detection, Multisource knowledge fusion | |
| An Approach to Successful Power-line Interference Suppression in ECG Signals | 83-92 |
| Ivan Dotsinsky | |
| doi: 10.7546/ijba.2022.26.1.000848 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Ivan Dotsinsky (2022) An Approach to Successful Power-line Interference Suppression in ECG Signals, Int J Bioautomation, 26 (1), 83-92, doi: 10.7546/ijba.2022.26.1.000848 | |
| Abstract: The ECG signals acquisition is usually corrupted by presence of Power-line Interference (PLI) induced by the electromagnetic field around us. Many methods for PLI suppression/elimination have been developed over the years. The easy to apply traditional notch filters suppress unacceptably the ECG spectrum around the rated PL frequencies of 50 or 60 Hz and their deviations, which are restricted by the standards within the range of ± 0.5 Hz. The changes are very slow but the current PL frequency has to be continuously checked to allow start and performance of adequate PLI suppression during any ECG recordings including the 24 hours Holter monitoring. According to the proposed approach, the corrupted ECG recording is bi-directional band-pass (BP) filtered. The resulting sinusoidal BP waves differ in amplitude from the PLI but their zero crossing points remain identical. The two out-sample distances located at both ends of each current sinusoidal curve are calculated and aided to the inter-sample distances. The obtained fractal wave period is converted into current PL frequency and used for bi-directional notch filtration with narrow stop-band. The results obtained demonstrate a very successful PLI suppression in ECG signals. The errors committed are within a few μV, except for the edges of the recordings due to the transition processes.
Keywords: ECG signals, Power line interference suppression, Subtraction procedure, Narrow notch filtration | |
| The Highlighting of a Biological Process for the Treatment of Leachate from a Public Discharge | 93-108 |
| Naoual Tchich, Abdel-ilah Aziane, Souad Hammoutou, Mohamed Ouhssine, Mohamed El Yachioui, Abdelaziz Chaouch | |
| doi: 10.7546/ijba.2022.26.1.000727 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Naoual Tchich, Abdel-ilah Aziane, Souad Hammoutou, Mohamed Ouhssine, Mohamed El Yachioui, Abdelaziz Chaouch (2022) The Highlighting of a Biological Process for the Treatment of Leachate from a Public Discharge, Int J Bioautomation, 26 (1), 93-108, doi: 10.7546/ijba.2022.26.1.000727 | |
| Abstract: Due to the composition and their impact on the environment, landfill leachate is a serious environmental and public health problem. Our physicochemical and microbiological study has shown that leachate is highly loaded with minerals including iron, Mg, Cd, etc.) and pathogenic microorganisms hence the need for effective and sustainable treatment. Our present study enters this preoccupation we have highlighted a biological process allowing the transformation of leachate by way of fermentation, being based on leaven having fermenting, acidifying and antimicrobial power. Microbiological analysis showed that almost all the pathogenic flora was removed showing the biological treatment efficacy. In addition, the stable product obtained after 15 days of fermentation was used as a base in a formula of a bio-fertilizer. Application trials in different crops (wheat, peas, corn, etc.) have shown satisfactory results.
Keywords: Leachate, Biological treatment, Fermentation starter | |
| Classification of Parkinson's Disease Using EMG Signals from Different Upper Limb Movements Based on Multiclass Support Vector Machine | 109-125 |
| Hamdia Murad Adem, Abel Worku Tessema, Gizeaddis Lamesgin Simegn | |
| doi: 10.7546/ijba.2022.26.1.000849 | |
| [ +/- how to cite ][ +/- abstract ][ full text ] | |
| Hamdia Murad Adem, Abel Worku Tessema, Gizeaddis Lamesgin Simegn (2022) Classification of Parkinson's Disease Using EMG Signals from Different Upper Limb Movements Based on Multiclass Support Vector Machine, Int J Bioautomation, 26 (1), 109-125, doi: 10.7546/ijba.2022.26.1.000849 | |
| Abstract: Parkinson's disease (PD) is the second most common neurodegenerative disease that affects a wide range of productive individuals worldwide. The common approach to diagnose PD is through clinical assessment of the patient, which is highly subjective and time consuming. Electromyography (EMG) can be taken as a cheap way of PD diagnosis. However, highly experienced experts are required to interpret the signals. The manual procedures are complex, time-consuming, and prone to error resulting in misdiagnosis. In this research, an automatic system for detection and classification of PD stages using EMG signals acquired from different upper limb movements is proposed. In addition, effective upper limb movement for the identification of PD has been investigated. The data required for training and testing the system was collected from flexor carpi radialis and biceps brachii muscles of 15 PD patients and 10 healthy control subjects at Jimma University Medical Center. The raw EMG signal was preprocessed and frequency and time-domain features were extracted. A multiclass support vector machine model was then trained for four-class classification (normal, early, moderate, and advanced PD levels). The performance of the system was evaluated using different performance evaluators and a promising result has been obtained. 90%, 91.7%, 95%, and 96.6% overall classification accuracies were obtained for elbow flexion by 90-degrees without load, elbow flexion by 90-degrees with load, touching the shoulder, and wrist pronation, respectively. A user-friendly interface has been also developed for ease of use of the automatic PD classification system.
Keywords: Classification, Detection, Electromyogram, Parkinson's disease, Support-vector machine |
Sponsored by National Science Fund of Bulgaria, Grant No KP-06-NP3-37, 2022
© 2022, BAS, Institute of Biophysics and Biomedical Engineering