Volume 25, Issue 1
Case Studies on Neural Networks for Recognition in Biometric Identity Problem5-12
Zhengwen Shen, Jun Wang, Zaiyu Pan, Kai Yang
doi: 10.7546/ijba.2021.25.1.000597
[ +/- how to cite ][ +/- abstract ][ full text ]
Zhengwen Shen, Jun Wang, Zaiyu Pan, Kai Yang (2021) Case Studies on Neural Networks for Recognition in Biometric Identity Problem, Int J Bioautomation, 25 (1), 5-12, doi: 10.7546/ijba.2021.25.1.000597
Abstract: Hand-dorsa vein recognition using a convolutional neural network is presented. Our network contains five convolutional layers and three full connected layers, which have high recognition and more robust. The experimental results on the self-established database with the proposed CNN achieves 98.02% in training part and 97.65% in testing part, which demonstrates the effectiveness of the proposed CNN.

Keywords: Hand-dorsa vein recognition, High recognition, Convolutional neural network
Motor Imagery EEG Classification Using Random Subspace Ensemble Network with Variable Length Features13-24
Zabir Al Nazi, A. B. M. Aowlad Hossain, Md. Monirul Islam
doi: 10.7546/ijba.2021.25.1.000611
[ +/- how to cite ][ +/- abstract ][ full text ]
Zabir Al Nazi, A. B. M. Aowlad Hossain, Md. Monirul Islam (2021) Motor Imagery EEG Classification Using Random Subspace Ensemble Network with Variable Length Features, Int J Bioautomation, 25 (1), 13-24, doi: 10.7546/ijba.2021.25.1.000611
Abstract: Classification of electroencephalography (EEG) signals for brain-computer interface has great impact on people having various kinds of physical disabilities. Motor imagery EEG signals of hand and leg movement classification can help people whose limbs are replaced by prosthetics. In this paper, random subspace ensemble network with variable length feature sampling has been proposed for improving the prediction accuracy of motor imagery EEG signal classification. The method has been tested on eight different subjects and a hybrid dataset of two subjects data combined. Discrete wavelet transform based de-noising scheme has been adopted to remove artifacts from the EEG signal. For sub-band selection, dual-tree complex wavelet Transform has been employed. Mutual information scoring has been used for univariate feature selection from the feature space. A comparative analysis has been carried out where random subspace ensemble network outperformed other classification models. The maximum accuracy obtained by the model was 90.00%. Furthermore, the model showed better performance on the hybrid dataset with an average accuracy of 86.00%. The findings of this study are expected to be useful in artificial limb movements through brain-computer interfacing for rehabilitation of people with such physical disabilities.

Keywords: Electroencephalography, Brain computer interface, Random subspace ensemble network, Discrete wavelet transform, Dual tree complex wavelet transform
Water Quality Assessment of Surface Waters and Wastewaters by Traditional and Ecotoxicological Indicators in Ogosta River, Bulgaria25-40
Galina Yotova, Svetlana Lazarova, Veronika Mihaylova, Tony Venelinov
doi: 10.7546/ijba.2021.25.1.000778
[ +/- how to cite ][ +/- abstract ][ full text ]
Galina Yotova, Svetlana Lazarova, Veronika Mihaylova, Tony Venelinov (2021) Water Quality Assessment of Surface Waters and Wastewaters by Traditional and Ecotoxicological Indicators in Ogosta River, Bulgaria, Int J Bioautomation, 25 (1), 25-40, doi: 10.7546/ijba.2021.25.1.000778
Abstract: Surface water samples in Ogosta River, Bulgaria and wastewater samples at the inlet and outlet of WWTP–Montana were tested for the traditional parameters and ecotoxicological effect. The river and Dam surface waters comply with category A1 of Directive 75/440/EEC for pH, EC, COD, TSS, NO3–, Cl–, SO42–, B, Ba, Co, Cr, Cu, Hg, Mn, Ni, Pb, Se, V and Zn; with category A2 for BOD5, NH4+–N and Fe; and with category A3 for TNb and As. The average annual concentrations of Al, Cr (III), Cr (VI) and U are lower than the set limits in the Water Framework Directive. Arsenic concentration in all the samples exceeds the maximum allowed concentration, a results from natural processes. All the levels of the studied parameters in the outlet wastewater samples are lower than the limits, set in Directive 91/271/EEC and in the complex permit of the WWTP. The results of the biotest Phytotoxkit FTM show low ecotoxicity of the water samples. Optimization of the sample pretreatment prior to this ecotoxicological test is analyzed and discussed.

Keywords: Surface Water, Wastewater, Ecotoxicity, Phytotoxkit FTM, Ogosta River
Do Mistletoe (Viscum album L.) Lectins Influence Isometric Contraction of Non-diseased Human Mesenteric Arteries ex vivo?41-52
Daniela Z. Dimitrova, Biliana Nikolova, Vanya Bogoeva, Bozhil Robev, Iana Tsoneva, Stanislav Dimitrov, Boris Kadinov
doi: 10.7546/ijba.2021.25.1.000788
[ +/- how to cite ][ +/- abstract ][ full text ]
Daniela Z. Dimitrova, Biliana Nikolova, Vanya Bogoeva, Bozhil Robev, Iana Tsoneva, Stanislav Dimitrov, Boris Kadinov (2021) Do Mistletoe (Viscum album L.) Lectins Influence Isometric Contraction of Non-diseased Human Mesenteric Arteries ex vivo?, Int J Bioautomation, 25 (1), 41-52, doi: 10.7546/ijba.2021.25.1.000788
Abstract: Mistletoe (Viscum album L., VA) lectins (MLs) are plant lectins with potent anticancer activity. Although wide use of VA extracts in curing cancer, the effects of purified MLs on human vasculature in term of possible side effect of the lectin has not yet been reported. The present study was aimed to investigate isometric contractions of isolated human mesenteric arteries during MLs application. The contractile response of arteries was studied using Mulvany-Halpern myograph and the isometric contractions under MLs’ treatment were examined in artery segments with either intact endothelium or after endothelium removal. Furthermore, the effect of the lectin was assessed in arterial preparations in basal tension, in arteries precontracted with 42 mM KCl as a depolarizing stimulus or endothelin-1 (ET-1) as a potent receptor-operated agonist of vascular smooth muscle contraction. The results showed that MLs (1 to 100 nM) failed to affect the high K+-induced contractions of both endothelium-intact and endothelium-denuded arteries. The contractions of tissue preparations without endothelium in basal tone or after ET-1 (1 nM) treatment were also not affected by the application of MLs. The observed mild effect of MLs on the contractility of human vasculature may potentially be beneficial with MLs-based anticancer therapy without vascular side effects.

Keywords: Mistletoe lectins, Human mesenteric artery, Contraction, ex vivo, Cancer treatment
Complex Analysis of New Unique Human Society Life in Eight Coordinate System53-72
Alexander Dimitrov Kroumov, Fabiano Bisinella Scheufele, Maya Margaritova Zaharieva, Aparecido Nivaldo Módenes, Daniela Estelita Goes Trigueros, Carlos Eduardo Borba, Fernando R. Espinoza-Quiñones, Hristo Miladinov Najdenski
doi: 10.7546/ijba.2021.25.1.000793
[ +/- how to cite ][ +/- abstract ][ full text ]
Alexander Dimitrov Kroumov, Fabiano Bisinella Scheufele, Maya Margaritova Zaharieva, Aparecido Nivaldo Módenes, Daniela Estelita Goes Trigueros, Carlos Eduardo Borba, Fernando R. Espinoza-Quiñones, Hristo Miladinov Najdenski (2021) Complex Analysis of New Unique Human Society Life in Eight Coordinate System, Int J Bioautomation, 25 (1), 53-72, doi: 10.7546/ijba.2021.25.1.000793
Abstract: The article presents deep and complex analysis based on the changes of life of human society during the COVID-19 pandemic. The World as never before has a global common enemy and everyone is in danger doesn’t matter where he lives and what is the occupation. The life new dimensions are considered as an 8-coordinate system where the new 4 coordinates – coronavirus, “virus” of poverty, “virus” of chronically ill people and scientists as new leading factor of the world. It means, a simple solution for prevention and regulation of pandemic doesn’t exist. Countries and outbreaks are represented by 4 everlasting coordinates – three for space and for time measurement. The life of human society is conditionally divided of 4 hierarchic levels. Interactions between them have to be studied by scientists from all areas in order to win this word challenge where all humans are on the same side of the barricade. The presented analysis could be extremely useful for explanation the errors made by leaders and to show them that the new reality requires relevant and effective decisions based on scientific complex analyzes and taking into account the four hierarchic levels of knowledge.

Keywords: COVID-19, System Analysis, Eight coordinate system, Human life, Coronavirus, Poverty, Chronically ill people
Review Article. Role of Electrophysiological Methods in Diagnosis of Hereditary Retinal Dystrophies73-86
Elena Mermeklieva
doi: 10.7546/ijba.2021.25.1.000805
[ +/- how to cite ][ +/- abstract ][ full text ]
Elena Mermeklieva (2021) Review Article. Role of Electrophysiological Methods in Diagnosis of Hereditary Retinal Dystrophies, Int J Bioautomation, 25 (1), 73-86, doi: 10.7546/ijba.2021.25.1.000805
Abstract: The aim of the study is to present the different electrophysiological methods (EF) for study the retinal function and to highlight their importance in the diagnosis of hereditary retinal dystrophies (HRDs). EF methods are objective methods including the different types of electroretinography (ERG) and electrooculography (EOG). They are “the golden standard” in the diagnosis of retinal dystrophies. EF are especially valuable in the initial stages of the diseases and in asymptomatic forms. They are also particularly important for monitoring the changes in dynamics, which is very important for the diseases prognosis. HRDs are a heterogeneous group of diseases with a relatively low frequency in the human population, characterized by involvement of different retinal layers, most often the complex retinal pigment epithelium-photoreceptors and causing severe visual impairment - loss of night vision, visual field, color vision and visual acuity in the initial stages and leading to progressive and severe loss of visual function by altering the retinal anatomy and function. By EF studies can evaluate the function of the retina in patients with these “rare eye diseases”. EF methods are most important in the diagnosis of HRDs. They are also important in the differential diagnosis between the different retinal dystrophies. A major challenge for the ophthalmologists is to identify the diseases in the early stages. There is an urgent need for more knowledge and practical use of these methods for accurate diagnosis which is a prerequisite for a proper therapy.

Keywords: Electroretinography, Electrooculography, Hereditary retinal dystrophies, Electrophysiology
Disease Diagnosis of Dairy Cow by Deep Learning Based on Knowledge Graph and Transfer Learning87-100
Meng Gao, Haodong Wang, Weizheng Shen, Zhongbin Su, Huihuan Liu, Yanling Yin, Yonggen Zhang, Yi Zhang
doi: 10.7546/ijba.2021.25.1.000812
[ +/- how to cite ][ +/- abstract ][ full text ]
Meng Gao, Haodong Wang, Weizheng Shen, Zhongbin Su, Huihuan Liu, Yanling Yin, Yonggen Zhang, Yi Zhang (2021) Disease Diagnosis of Dairy Cow by Deep Learning Based on Knowledge Graph and Transfer Learning, Int J Bioautomation, 25 (1), 87-100, doi: 10.7546/ijba.2021.25.1.000812
Abstract: In dairy herd management, it is significant and irreplaceable for veterinarians to make rapid and effective diagnosis of dairy cow diseases. Based on electronic medical records, deep learning (DL) has been widely used to support clinical decisions for humans. However, this method is rarely adopted in veterinary diagnosis. In addition, most DL models are driven by large datasets, failing to utilize the knowledge acquired by veterinarians in subjective experience, which is critical to disease diagnosis. To address these problems, this paper proposes a DL method for disease diagnosis of dairy cow: convolutional neural network (CNN) based on knowledge graph and transfer learning (KGTL_CNN). Firstly, the structural knowledge was extracted from a knowledge graph of dairy cow diseases, and treated as part of the inputs to the CNN based on knowledge graph (KG_CNN). Then, the model performance was enhanced through pre-training by transfer learning. To verify its performance, experiments were carried out on dairy cow clinical datasets. The results show that our model performed satisfactorily on disease diagnosis: the KG_CNN and KGTL_CNN achieved an F1-score of 85.87% and 86.77%, respectively, higher than that of typical CNN by 6.58% and 7.7%. The research results greatly promote the effective, fast, and automatic clinical diagnosis of dairy cow diseases.

Keywords: Knowledge graph, Deep learning, Transfer learning, Dairy cow, Disease diagnosis
Encapsulation of Opiorphin in Polymer-coated Alginate Beads for Controlled Delivery and Painkilling101-111
Svetozar Stoichev, Stefka Taneva, Avgustina Danailova, Jose Luis Toca-Herrera, Tonya Andreeva
doi: 10.7546/ijba.2021.25.1.000746
[ +/- how to cite ][ +/- abstract ][ full text ]
Svetozar Stoichev, Stefka Taneva, Avgustina Danailova, Jose Luis Toca-Herrera, Tonya Andreeva (2021) Encapsulation of Opiorphin in Polymer-coated Alginate Beads for Controlled Delivery and Painkilling, Int J Bioautomation, 25 (1), 101-111, doi: 10.7546/ijba.2021.25.1.000746
Abstract: Opiorphin (Oph) is a naturally produced endogenous peptide with a strong analgesic effect, superior to that of morphine, and without the severe side effects that morphine and morphine-like drugs exert. However, despite its strong therapeutic potential, the short duration of action, probably due to its low chemical stability and rapid degradation by the peptidases in the bloodstream, represents a serious obstacle to the Oph use into clinical practice. In this work a novel approach to construct Oph-loaded particles as a platform for its delivery has been developed. Gel beads loaded with Oph were synthesized from alginate, a naturally occurring biodegradable anionic polysaccharide, and coated with polyelectrolyte multilayers (from natural polyelectrolytes (chitosan and hyaluronic acid) and synthetic polyelectrolytes (poly(allylamine hydrochloride) and poly(styrene sulfonate)) or hybrid polyelectrolyte-graphene oxide multilayers. All coated Oph-loaded alginate beads show prolonged drug release compared to the non-coated ones, but the extent of the prolongation depends on the type of the coating. We expect that the successful encapsulation of opiorphin in biodegradable particles will provide an opportunity for the development of adequate drug delivery system with effective and prolonged analgesic activity and will offer a new alternative for pain management.

Keywords: Opiorphin, Alginate beads, Polyelectrolyte films, Graphene oxide

Sponsored by National Science Fund of Bulgaria, Grant No KP-06-NP/2/12, 2020

© 2021, BAS, Institute of Biophysics and Biomedical Engineering