Biometric Research Research Articles

FEATURES OF THE PAPILLARY PATTERN OF THE MIDDLE AND PROXIMAL PHALANGES OF THE FINGERS IN PATIENTS WITH ACUTE MYOCARDIAL INFARCTION

Cardiovascular diseases remain the most pressing healthcare problem in most countries of the world in the 21st century, despite the continuous improvement of diagnostic and treatment methods for cardiac patients. Today, the mortality rate for patients within a year after myocardial infarction remains quite high at 9.1%. Despite the large number of scientific papers, most of the available information sources reflect the possibility of using dermatoglyphs of the palms and distal phalanges as diagnostic markers for predicting the susceptibility to AMI and practically do not cover the possibility of using dermatoglyphs of the middle and proximal phalanges, although they also have a powerful prognostic potential. The material of our study were dermatoglyphs of the middle and proximal phalanges of the fingers obtained from 167 male subjects aged 35-69 years. The subjects were divided into 2 groups. Group 1 (83) included men with a history of AMI by questionnaire; Group 2 (84) included men who had never had AMI. The criteria for inclusion in the study groups were voluntary consent, absence of genetic pathology, endocrine and musculoskeletal system pathology, age over 35 and under 69 years. Exclusion criteria were refusal to participate in the study at any stage, presence of genetic pathology, endocrine and musculoskeletal system pathology, age under 35 and over 69 years. The scope and methods of the research do not contradict the basic principles of the Helsinki Declaration on Biometric Research (1974), adapted at the 41st International Assembly in Hong Kong (1989), in which a person is the subject of research. The research was conducted in compliance with the following basic principles: respect for the individual, information of the individual, and assessment of the risk of harm and benefit. Results and discussion. The dermatoglyphic parameters on the middle phalanges that determine the susceptibility to AMI in men with a high level of reliability are: Lu, Lr, Hdu, Hdr, Adu, Adsr, ApNu, ApNr, ApLr, DaN, Vu, Vr, Vm, Dhu, Fu, Fr, NdNu, Lsr, на PPh: Hdu, Adu, Adsu, Adsr, ApNr, ApNsu, Ladu, Ladr, ApLu, ApLr, DaN, DaLu, DaLr, Vu, Vr, Vm, Dhu, Dhr, Fu, Fr, Cl, NdNr, Npu, Dn, ApNpu, ApNpr, Vms, Lsu, Lsr; on the proximal phalanges are present: Ladr, Dhr, Ladu, ApNpr, Dn, Cl, ApLu, Vm, DaN, ApLr, Fr, ApNpu, Lsu, Adsr, Dhu, Hpu, ApNr, NdAdu. The result of the analysis was the construction of a model that allowed us to predict the susceptibility of men to AMI based on the use of dermatoglyphic parameters of the middle phalanges of the fingers with a probability of more than 68 % and dermatoglyphs located on the proximal phalanges with a probability of about 79 %. Conclusion. The incidence of AMI is a medical and social problem. The incidence of this disease among young working-age population is increasing every year and entails a number of negative consequences, including high mortality, disability and others. Therefore, the search for new diagnostic criteria for predicting the susceptibility to AMI, which can form the basis of screening tests, remains relevant. We have established prognostic markers (dermatoglyphs of the middle and proximal phalanges of the fingers): Vu, Vm, Hdr, Lr, Adsr, ApNu, Vr, NdNu, Hdu, Lsr, S, ApNr, Adu, Adr, Lsu, Npr, Lu, Dhu. The obtained results may play a significant role in the future as one of the factors of prevention of AMI development.

Explainable biometrics: a systematic literature review

AbstractBiometric systems are largely based on Machine Learning (ML) algorithms which are often considered as a black-box. There is a need to provide them with explanations to make their decision understandable. In this paper, we conduct a Systematic Literature Review aiming at investigating the present adoption of explainable Artificial Intelligence (XAI) techniques in biometric systems. By examining the biometric tasks performed by the selected papers (e.g., face detection or face spoofing), the datasets adopted by the different approaches, the considered ML models, the XAI techniques, and their evaluation methods. We started from 496 papers and, after an accurate analysis, selected 47 papers. Results revealed that XAI is mainly adopted in biometric systems related to the face biometric cues. The explanations provided were all based on model-centric metrics and did not consider how the end-users perceived the explanations, leaving wide space for the biometric researchers to apply the XAI models and enhance the explanation evaluation into an HCI perspective.

The robust SmartEnsembleNet: A game changer in finger knuckle biometrics

SmartEnsembleNet represents a major leap forward in the domain of biometric identification, focusing on the relatively underexplored area of finger knuckle biometrics. This research enhances the effectiveness and uniqueness of biometric systems by leveraging the distinct and secure features of finger knuckle patterns. As a complement to existing biometric techniques like fingerprints and facial recognition, it adds an additional layer of security and reliability. Addressing the challenges faced by finger knuckle identification, such as image acquisition, environmental effects, and aging, SmartEnsembleNet introduces a pioneering multi-layered ensemble learning strategy that combines eight diverse machine learning models. These models, trained via a 5-fold cross-validation on datasets from IIT Delhi and PolyU, demonstrate significant improvements in accuracy, precision, recall, and F1-score. A distinctive feature of SmartEnsembleNet is its innovative meta-model, streamlining the creation of a meta-dataset. This dataset is created by applying bilinear interpolation to the predicted probabilities from the top-performing model, and it is further refined by subtracting these interpolated probabilities from the validation data. This iterative process generates ‘smart data’, which serves as the basis for training the ultimate ‘smart model’. Logistic regression is chosen for its outstanding performance. This method, applied uniformly to both training and testing phases, considerably enhances classification accuracy in finger knuckle biometrics, establishing new benchmarks. SmartEnsembleNet’s performance undergoes a detailed evaluation using the Friedman test and Nemenyi post-hoc analysis, guaranteeing a selection process grounded in statistical rigor. With its resilience to noise and adaptability under various conditions, SmartEnsembleNet not only addresses existing gaps in finger knuckle biometric research but also pioneers future advancements, providing a versatile and secure solution impactful for both academia and high-security scenarios.

VARIABILITY OF QUANTITATIVE PLANT CHARACTERS OF EGGPLANT COLLECTION SAMPLES

Purpose. To determine the peculiarities of the variability of the quantitative characteristics of the plant in collection samples of eggplant of different origin during different years of cultivation Methods. During 2021-2023, an eggplant collection consisting of 21 varieties and 10 F1 hybrids of various geographical origins was studied at the experimental base of the Institute of Vegetable and Melon Growing of the National Academy of Sciences. Samples were evaluated by plant height, plant width, number of shoots per plant. Field, biometric, computational and analytical research methods were used. Results. It was found that the height and width of the plant had a tendency to decrease in 2023. The average height of the collection for this year by varieties was 97.4 cm, by hybrids – 98.7 cm. The width of the plant this year was 41.3 cm on average by varieties, by hybrids – 43.4 cm. The lowest plant height was noted variety Hangqi No.1 (81.0 cm on average over the years), the highest plant height is the variety Bambina. (120.7 cm). Among the hybrids, Piatachok F1 was the shortest, Gordita F1 was the tallest (121.7 cm). The smallest plant width among the varieties was the Xingyuun variety (35.3 cm on average over the years), among the hybrids – the Farama F1 hybrid (38.7 cm). The largest plant width is in the Thai Long Green variety (51.3 cm) and in the Gordita F1 and Briska F1 hybrids (49.3 cm). The smallest number of shoots was formed in plants of the Xingyuun variety (2.7 pcs. on average over the years) and the Galchonok F1 hybrid (3.3 pcs.). The variety Luisiana Long Green (6.9 pcs.) and the Purple Dragon F1 hybrid (8.1 pcs.) had the most shoots on the plant. Almost all studied varieties and hybrids were distinguished by weak and medium variability in three characteristics. Only the Zelenenky variety showed itself to be very variable in the number of shoots (CV = 21.16). Among the varieties, the variety Tai Long Green was distinguished by the least variability in height and width of plants, and Louisiana Long Green in the number of shoots on the plant. Among the hybrids, the lowest variability of plant height and width was observed in the Izumrudny F1 hybrid, and the number of shoots per plant in Bibo F1. Thai Long Green and Daejeon Purple varieties showed the least response to the change in growing conditions by plant height, Hangqi No. 1-2 variety by plant width, and Luisiana Long Green by the number of shoots per plant. The most stable among the hybrids were Izumrudny F1 in terms of plant height and width and Bibo F1 in terms of the number of shoots. Conclusions. Thus, breeding studies allowed to determine the levels of variability of quantitative traits of the eggplant plant and to identify valuable collection samples for use in breeding programs.

Reproductive qualities of French selection of the White Large breed of sows and their evaluation according to some mathematical models

Objective. To investigate the reproductive qualities of sows of the large white breed of French selection and to evaluate the indicated group of traits according to some mathematical models of selection indices. Methods. Zootechnical and statistical research methods were used to achieve the goal. The experimental part of the work was carried out in the breeding breeder for breeding pigs of the large white breed of the experimental farm of the Institute of Agriculture of the Northeast of the National Academy of Sciences. The assessment of sows of the large white breed of French breeding was carried out according to the indicators of reproductive qualities, taking into account the following quantitative characteristics: multifertility, goal, high fertility, kg; milk yield, kg; the number ofpiglets at the time of weaning, goal; nest weight at the time of weaning at the age of 28 days, kg; nest weight at the time of weaning at the age of 60 days, kg; preservation, %. A comprehensive evaluation of sows for reproductive qualities was carried out using the selection index of reproductive qualities of the sow (SIRQS) (Tsereniuk O. M. et al., 2010) and the index of Shatalina Yu. D. (Vashchenko P. A., 2019). Biometric research results were processed according to generally accepted methods (Kovalenko V. P. et al., 2010). Results. Studies have shown that sows of experimental group I prevailed over sows of the same age in groups II and III in terms of multifertility by 15.67 and 34.32 %, milk yield - 23.29 and 34.94 %, number of piglets at the time of weaning at the age of 28 days - 13.91 and 33.30 %, by the weight of the nest at the time of weaning at the age of 28 days - 17.39 and 27.60 %, by the weight of the nest at the time of weaning at the age of 60 days - 17.89 and 28.30 %. The difference between the animals of the I, II, and III experimental groups (intrabreed differentiation according to the index of Shatalina Yu. D.) in terms offertility, milk yield, the number ofpiglets at the time of weaning at the age of 28 days, the weight of the litter at the time of weaning at the age of 28 days and the weight of the litter at the time of weaning at the age of 60 days is highly reliable and is equal to 23.58 %. The maximum indicators of high fertility and survival ofpiglets at the time of weaning at the age of 28 days and the minimum values of the sow nest alignment (homogeneity) index based on the live weight of piglets at the time of their birth (IVH0) were established in sows of the III sub-experimental group of intrabreed differentiation according to SIRQS and the index of Shatalina Yu. D. Conclusions. Sows of the large white breed of French breeding are characterized by pretty high indicators of reproductive qualities, and in terms offertility and litter weight at the time of weaning at the age of 60 days, they belong to the 1st class and the elite class. The number of reliable pairwise correlation coefficients between the absolute indicators o f reproductive qualities of sows, SIRQS, the index of Shatalina Yu. D. and the index of evenness (homogeneity) of the sow's nest according to the live weight ofpiglets at the time of their birth (IVH0) is 100 %. This indicates a high level of efficiency of their use for evaluation and selection of highly productive animals in controlled populations. Keywords: sow, breed, reproductive qualities, index, variability, correlation.

Enhancing Resilience in Biometric Research: Generation of 3D Synthetic Face Data Using Advanced 3D Character Creation Techniques from High-Fidelity Video Games and Animation.

Biometric authentication plays a vital role in various everyday applications with increasing demands for reliability and security. However, the use of real biometric data for research raises privacy concerns and data scarcity issues. A promising approach using synthetic biometric data to address the resulting unbalanced representation and bias, as well as the limited availability of diverse datasets for the development and evaluation of biometric systems, has emerged. Methods for a parameterized generation of highly realistic synthetic data are emerging and the necessary quality metrics to prove that synthetic data can compare to real data are open research tasks. The generation of 3D synthetic face data using game engines' capabilities of generating varied realistic virtual characters is explored as a possible alternative for generating synthetic face data while maintaining reproducibility and ground truth, as opposed to other creation methods. While synthetic data offer several benefits, including improved resilience against data privacy concerns, the limitations and challenges associated with their usage are addressed. Our work shows concurrent behavior in comparing semi-synthetic data as a digital representation of a real identity with their real datasets. Despite slight asymmetrical performance in comparison with a larger database of real samples, a promising performance in face data authentication is shown, which lays the foundation for further investigations with digital avatars and the creation and analysis of fully synthetic data. Future directions for improving synthetic biometric data generation and their impact on advancing biometrics research are discussed.

Enhanced Local Binary Pattern Algorithm for Facial Recognition Using Chinese Remainder Theorem

Current biometrics research focuses on achieving a high authentication success rate for identity management and discussing the threat of various security attacks. Local Binary Pattern (LBP), one of the methods for feature extraction, and Chicken Swarm Optimization (CSO), one of the strategies for feature selection, were used for user identification and authentication. LBP requires high computational time to extract features from the facial images. The Chinese Remainder Theorem (CRT) was used to reduce its computational time by formulating an Enhanced Local Binary Pattern (ELBP). Michael Olugbenga Banji Abolarinwa (MOBA) database was created specifically for this study. 600 frontal facial images of 200 people were collected, each with three images. 360 images were used for training while 240 images were used for testing. MATLAB (R2016a) was used to run the simulation. The time it took to classify the facial images when LBP and CSO were combined and when ELBP and CSO were combined were enumerated. The LBP-CSO achieved a false-positive rate (FPR) of 11.67%, a sensitivity (SEN) of 92.78%, a specificity (SPEC) of 88.33%, a precision (PREC) of 95.98%, and an accuracy of 91.67% in 119.10 seconds at 0.80 thresholds for face recognition. ELBP-CSO obtained an FPR of 5.00%, SEN of 95.00%, SPEC of 95.00%, PREC of 98.28%, and accuracy of 95.00% in 79.16 seconds. The results showed that LBP-CSO took an average of 119.10 seconds and ELBP-CSO took an average of 79.16 seconds. In conclusion, the performance of CSO-ELBP justifies the usage of LBP enhancement with CRT.

Facial recognition based on enhanced neural network

Accurate automatic face recognition (FR) has only become a practical goal of biometrics research in recent years. Detection and recognition are the primary steps for identifying faces in this research, and The Viola-Jones algorithm implements to discover faces in images. This paper presents a neural network solution called modify bidirectional associative memory (MBAM). The basic idea is to recognize the image of a human's face, extract the face image, enter it into the MBAM, and identify it. The output ID for the face image from the network should be similar to the ID for the image entered previously in the training phase. The tests have conducted using the suggested model using 100 images. Results show that FR accuracy is 100% for all images used, and the accuracy after adding noise is the proportions that differ between the images used according to the noise ratio. Recognition results for the mobile camera images were more satisfactory than those for the Face94 dataset.

A survey on blockchain deployment for biometric systems

AbstractBlockchain technology has become an emerging area in recent years due to its capacity to improve the security, dependability, and resilience of distributed systems. Research based on this technique has impacted several firms, including banking, healthcare, data processing, remote sensing, and many others. The key characteristics of blockchain technology that make it appealing are data immutability, transparency, privacy, decentralization, and distributed ledgers. However, there is a chance of a privacy breach with sensitive biometric data. The purpose of this investigation is to examine blockchain‐based biometric applications research. It begins by determining the myriad ways that biometrics and blockchain may work together, including the storage and protection of biometric templates, identity management, and biometric authentication systems. Different biometric applications with respect to blockchain technology are also identified, along with the types of biometric data taken into account, features and capabilities of blockchain technology exploited, and blockchain technology frameworks employed. Finally, the authors seek to investigate blockchain concepts in the biometric domain by evaluating their pros and cons and summarizing the methods developed on blockchain for diverse biometric applications. Additionally, the applications of blockchain‐based biometric systems are highlighted before moving on to open research questions and potential future research areas.

Insights on 'Complex-Valued Iris Recognition Network'.

We comment on a recently published TPAMI paper presenting an iris recognition algorithm. While the approach is intriguing, we have identified several inconsistencies and errors in this paper. Additionally, their comparison with the state-of-the art methods lacks fairness. We take this opportunity to clarify and underline these errors, aiming to assist fellow researchers like us who are interested in advancing biometrics research.

Variations in Lens Thickness Affecting the Anterior Chamber Length and Their Potential Measurement Using a Biometer

Biometry is a critical aspect of ophthalmology, since it facilitates the measurement of several ocular parameters and aids in the diagnosis of conditions like glaucoma. The advent of the IOLMaster in 1999 marked a pivotal moment in biometry by introducing non-contact and highly precise measurements that revolutionized the field. Low-coherence optical reflectometry devices such as Lenstar LS900 and Aladdin have further advanced biometry, due to the exceptional accuracy they offer. Axial length, a fundamental measurement in biometry, directly correlates with conditions like myopia and glaucoma. The accurate measurement of axial length is crucial for diagnosis and treatment planning. Biometry also guides intraocular lens power calculation during cataract surgery, relying on factors like axial length, anterior chamber depth, lens thickness, and effective lens position (ELP). Ensuring precision in these measurements is essential for optimal surgical outcomes. While several studies have explored biometric parameters, dynamic changes in crystalline lens thickness during rest or accommodation have received little attention. These changes may have a significant effect on the measurement of the anterior chamber length, and consequently impact the overall biometric assessment. This study delves into dynamic biometry, particularly in the context of age-related presbyopia, and aims to assess the feasibility of incorporating into the biometric process a specialized device capable of accurately considering crystalline lens changes during different states like rest and accommodation. This exploration seeks to enhance the understanding of ocular dynamics and contribute to improving the precision of diagnostic and surgical techniques. It underscores the importance of staying at the forefront of biometric research, especially in the context of emerging technologies and their potential to transform ophthalmology.

Biometric Analysis on Smart Textile Garment in Real Life Scenario

The rapid proliferation of wearable applications and technologies capable of acquiring biomedical signals has prompted the incorporation of biomedical signals, such as the electrocardiogram (ECG), for biometric purposes in wearable platforms. Most ECG biometric research utilises medical-grade sensors in clinical settings, which is unrealistic for wearable ECG-based biometric applications in the real world. Therefore, this research aims to examine the ECG biometric on smart textile garments in real life, collected from commercially available wearable Hexoskin Proshirt and HeartIn Fit shirts. ECG data were obtained from 22 participants who took part in this study. The raw ECG signal is initially pre-processed using noise-removal Butterworth filters in the time domain, followed by an effective QRS segmented feature extraction technique. Finally, around 2076 datasets were created for training and validation, while the remaining 501 datasets were employed to test the suggested recognition approach with 29 Machine Learning Classifiers. Subsequently, Quadratic SVM has the highest accuracy at 96.8% for ECG biometrics, followed by Narrow Neural Network with 95.8% and Wide Neural Network with 95.4%. Further improvement to the QSVM parameter improved the accuracy to 97.4% with an error rate of 2.6%, followed by a sensitivity of 97.4% with a precision of 97.7% and a false rejection rate of 2.6%. Thus, the results of this study further validate the feasibility of applying ECG biometrics for recognition in real-life scenarios utilising a smart textile shirt with different configurations and brand is possible.

Biometric template attacks and recent protection mechanisms: A survey

It is an undeniable fact that biometric recognition systems are susceptible to different software-related or template attacks at different vulnerable points in the biometric authentication system. However, these attacks are frequently overlooked, implying one of two possibilities: either researchers and biometric stakeholders have forgotten or simply ignored the consequences of these attacks, or they are unaware of some of these threats. Meanwhile, if biometric systems do not have the required protection, these attacks can lead to biometric system compromise and consequently the loss of sensitive personal data, which is irreplaceable and irrevocable. Therefore, considering the significance of the implications posed by these threats, researchers and biometric stakeholders have, over the last two decades, proposed different methods to mitigate some of the attacks, while a large number of the existing attacks are left unattended to. Hence, we deemed it paramount to bring this to the attention of the research community. This article is an effort to emphasize the implications of these attacks, exploit the threat approach based on attackers’ knowledge, and consolidate them into a single, thorough, and comprehensive review together with recent state-of-the-art protection mechanisms that are put forward to mitigate these threats. Moreover, a comparative performance analysis of these protection mechanisms and other possible countermeasures to the attacks is given. It is expected that this survey will, on the one hand, be a wakeup call to the biometric template protection research community, thus drawing their attention to the task at hand. On the other hand, an awareness to the ordinary users and biometric stakeholders on the risks posed by these threats.

Synergy of on-surface and in-air trajectories: Exploratory analysis of forensic online signatures implementing lessons learned from biometrics

With the increased use of digital devices, forensic document examiners (FDEs) encounter increasing number of dynamic or online signatures during their physical examinations. This shift expands the possibility of examinations and creates new challenges for FDEs. As such, FDEs require new examination skills using data science-based analyses with artificial intelligence and machine-learning techniques. In recent years, automated signature verification has gained significant interest in biometric research and could be useful in forensic investigations. However, the use of complex black-box systems inconveniencing FDEs in explaining the rationale behind their final assessment, especially when dealing with limited signature samples and various types of forged signatures. Therefore, a new forensic method is needed to assist FDEs’ analysis. To tackle these challenges and incorporate lessons learned from biometrics into forensics, this study proposes a novel forensic online signature analysis method. The proposed method uses a single-template strategy based on recent scientific findings in biometrics while updating the strategy for forensic use. This strategy creates a mean-template set from known signature samples that serve as a writer’s signature master pattern. Consequently, FDEs can evaluate intra-writer and inter-item variations using the mean-template set and a questioned signature. Furthermore, to take advantage of recent digital devices, we focused on both on-surface and in-air trajectories of online signatures, which could improve the discriminative power because in-air trajectories are invisible for imposters. Finally, we demonstrate the effectiveness and applicability of the proposed method in a forensic scenario using a public forensic online signature dataset.

The level of adaptation and reproductive qualities of sows of the large white breed of different origins and lineages

The work aimed to study the reproductive qualities and signs of long-term adaptation of sows of the large white breed of various origins and genealogical lines. The research was conducted in the research farm and laboratory of animal husbandry and fodder production of the Institute of Agriculture of the Northeast of the National Academy of Sciences. The work was carried out following the scientific research program of the National Academy of Agrarian Sciences of Ukraine No. 30, “System of organizational and technological solutions for adaptation of animals to climate change for the production of livestock products” (“Climate-adaptive and organic livestock breeding”). “Generally accepted zootechnical, biometric, and economic research and analysis methods were used to achieve the goal”. It was established that sows of the large white breed of French and Belgian origin are characterized by high indicators of long-term adaptation (the “adaptation level” index is 8.99 ± 0.161 points). Regarding reproductive qualities, they meet the minimum requirements of the I and the “elite” classes. A significant difference between sows of French and Belgian origin was found in the length of life (2.6 months; P < 0.05), the number of farrowings obtained (0.5; P < 0.05), the number of live piglets obtained (9.9; Р < 0.01), multifertility (0.8 head.; Р < 0.001), the weight of the nest at the time of weaning at the age of 28 days (4.8 kg; Р < 0.01), index of reproductive qualities of the sow M. D. Berezovsky (1.76 points, P < 0.01). Sows of the genealogical line 5488 are characterized by the maximum indicators of life expectancy, duration of breeding use, number of farrowings obtained, multifertility, nest weight at the time of weaning at 28 days, and M. D. Berezovsky's index. According to these indicators, they prevailed over peers of other genealogical lines by an average of 15.97 %. It was established that the pairwise correlation coefficient between the signs of reproductive qualities of sows and the “level of adaptation” index ranges from -0.736 ± 0.0405 to +0.502 ± 0.0661. The maximum indicators of the value of additional products were obtained from sows of French origin (+ UAH 100.86, or + USD 2.55) and animals of the genealogical line 5488 (+ UAH 340.46, or USD + 8.61).

The effect of technological stress on the biochemical parameters of the blood of ewes

In the course of the research, the effect of technological stress on the biochemical parameters of the blood of Ukrainian Mountain Carpathian sheep was studied before shearing and after it on the first and fifth day. Zootechnical, clinical-biochemical, biometric research methods were used. The research results showed that after shearing, stress in sheep of the first and second groups was clinically manifested by general depression, accelerated heartbeat and breathing. Such differences in the frequency of heart contractions and the number of respiratory movements in ewes can be explained by increased excitability of the nervous system due to shearing. The number of erythrocytes and leukocytes in the blood of sheep of both experimental groups before and after shearing was normal and did not go beyond physiological fluctuations. A slight decrease in blood parameters was detected in ewes of the first and second groups one and five days after the hygienic procedure. No significant difference in the number of erythrocytes and leukocytes was found between the experimental groups. Under the influence of stress factors, the content of total protein in blood serum decreased in ewes, especially one day after shearing in the experimental groups. After exposure to stressors, a decrease in urea content was detected in all experimental animals after one day and on the fifth day, which is due to the fact that under the influence of stress in the body, the breakdown of proteins and, accordingly, the level of the end products of protein metabolism decreases. As a result of shearing after a day, the cholesterol content in the blood of experimental sheep of the first and second groups probably decreased, with a slight tendency to increase after the fifth day. After exposure to stressors, the total lipid content of ewes of the first and second groups probably decreased on the first day, and a significant increase was observed on the fifth day. When the body is under stress, energy is wasted. He receives part of it at the expense of fats, which is why the content of total lipids in the blood of experimental animals decreases a day after a haircut. After shearing, the blood glucose content of all ewes increased, especially with a high probability in experimental animals after the first day, which is a consequence of the breakdown of increased glycogen. This indicates that these sheep had a stronger state of stress. After the fifth day, in the experimental ewes of the first and second groups after shearing, all the investigated indicators probably did not differ from those obtained before their shearing.

Parkinson Disease Detection from Spiral and Wave Drawings using Machine Learning Algorithm

Abstract: Research in biometrics has experienced significant growth in recent years, leading to a wide range of applications. One prominent area where biometrics has proven invaluable is healthcare. In the field of healthcare, identifying relevant biomarkers specific to certain fitness issues and detecting them accurately is crucial for improving medical decision assistance systems. Parkinson's Disease (PD) is a condition where impairment in handwriting has been observed to correlate directly with disease severity. Additionally, individuals with Parkinson's disease tend to exhibit lower velocity and pressure while using a pen for sketching or writing. Detecting such biomarkers accurately and precisely at the early stages of the disease can greatly enhance medical diagnosis. Consequently, a system has been designed to analyse spiral and wave drawing patterns of individuals affected by Parkinson's disease. By leveraging various machine learning algorithms, it becomes possible to analyse these patterns and determine whether a person is suffering from Parkinson's disease or not.

Agrobiological principles of environmental protection and efficient use of drained organic soils under climate change

Goal. To determine the optimal parameters of the combination of reclamation, agricultural, and nature protection solutions to ensure the sustainable development of agricultural production in the humid zone on drained soils. To develop measures aimed at reduction of the degradation of organic soils and improvement of their fertility based on the sound environmental protection system of agriculture and energy-saving technologies for growing crops in conditions of global climate change. Methods. Field with a complex of the biometric, agrochemical, and laboratory research, mathematical and statistical. Results. On old arable well-mineralized carbonate drained organic soils, the creation of nature-preserving agro-landscapes with a yield of 9–10 t/ha of feed units of high-quality fodder from perennial grass mixtures; 8.4–8.7 t/ha of corn grain and more than 4 t/ha of winter rye and triticale grain will ensure the introduction of 8-field crop rotations with 5–6 fields of perennial grass mixtures and 2–3 annual crops with the application of mineral fertilizers at the rate of P40–45 K120–130 kg of acting substance under annual crops and with the addition of N45 under perennial grasses, which helps reduce the mineralization of organic matter and accumulation of mobile nitrogen compounds under crops of perennial grass mixtures. In addition, nutrients are more intensively leached into groundwater by growing annual crops compared to perennial grasses, which is an important conservation measure when creating crop rotations. Conclusions. Such crop rotations and fertilizers provide a reduction in the accumulation of nitrate compounds in the 0–30 cm soil layer by 2–3 times, which is evidenced by a significant decrease in peat mineralization and its leaching into soil and river waters.

Influence of winter storage methods of acorns on the development and growth processes of common oak

The economic value and biological stability of common oak stands (Quercus robur L.), grown from acorns is substantially higher in comparison with plantings of undergrowth origin. Therefore, the cultivation of acorn oak stands is relevant and promising, especially where there is no natural restoration of oak. The purpose of the study was the improvement of seed production technology and cultivation of high-quality planting material of common oak seeds with various methods of winter storage to expand the area of oak forests. In the course of the study, forest-cultural (determination of quality indicators of acorns, planting material, and forest cultures), biometric (determination of growth indicators and mass of planting material), and classical statistical research methods were used. The study was conducted on the territory of the forest fund of the Hertsaevsky state special Forestry and Kuzmynsky Forestry branches of “Chernivtsi Forestry” of the state specialised economic enterprise “Forests of Ukraine”. It is shown that each of the winter storing methods of acorns of common oak has its own advantages and disadvantages, which are more or less manifested in different methods of cultivation. As a result of comparing the influence of different cultivation methods on the development of common oak plants grown from seeds stored in a trench method, it was determined that the best growth parameters of the aboveground part of plants were observed when using the larding method. However, the least intensive development of the root system was observed when growing oak with a closed root system. It was found that the weighted average biometric indicators of the growth processes of common oak plants grown from seeds that were stored in tap water were the highest when growing acorns by larding. It is proved that the experimental plants of common oak grown from seeds that were stored in a cellar with sand lagged behind in the development of the aboveground part when grown by a landing method. It was established that the root system developed worse when growing plants with an open root system. The proposed acorn storage technology can be applied to improve the efficiency and quality of reproduction of oak stands by forestry enterprises in Ukraine

Performance Evaluation of Selected Classification Algorithms for Iris Recognition System

Quite a lot of techniques proven to be resourceful have been espoused to develop iris recognition system. Nearly hybridized, supervised and unsupervised artificial neural network techniques have been used individually in iris recognition system and other pattern recognitions but have not been compared based on some performance metrics. Counter Propagation Neural Network (CPNN) is a hybridized technique, Self-Organizing Feature Map (SOFM) is an unsupervised learning technique and Back Propagation Neural Network (BPNN) is a supervised learning technique. This research conducted a performance comparison of CPNN, SOFM and BPNN techniques to recognize iris dataset and establish the more efficient among the three techniques. A database of Three hundred (300) iris images was acquired from LAUIRIS dataset from LAUTECH Biometric Research Group database. The original images of 640*360 dimensions were resized to 200*200 without any alteration in the image using 80% for training and 20% for testing. Hough transform was applied to segment locate the iris region of eye image. Daugman’s Rubber Sheet Model was used to create a dimensionally consistent representation. Principle Component Analysis was applied for feature extraction and dimensionally reduction. Finally, classification and matching were done by using CPNN, SOFM and BPNN techniques. This was implemented using MATLAB (Matrix Laboratory) R2016b. The performance metrics used for classification were False Positive Rate (FPR), Sensitivity, Specificity, Re, cognition Accuracy and Recognition Time at 0.70 threshold value.The Recognition Accuracy (RA), Recognition Time (RT), False Acceptance Rate (FAR), Sensitivity and Specificity of the three selected techniques (CPNN, SOFM and BPNN) resulted in values of 95.17%, 177.48s, 6.33% and 93.67% for CPNN 92.50%, 179.69s, 9.00%, 94.00% and 90.99% for SOFM while BPNN had 91.17%, 187.88s, 10.33%, 92.67% and 89.67% respectively.This paper showed that CPNN classification technique performed best for iris recognition system in terms of RA and recognition time. This research output will serve as a basis to pre-inform and guide researchers in choosing an efficient kernel based feature extraction technique.