Search

The subject of study is the creation process of an artificial intelligence system for automatic license plate detection. The goal is to achieve high license plate recognition accuracy on large camera angles with character extraction. The tasks are to study existing license plate recognition technics and to create an artificial intelligence system that works on big shooting camera angles with the help of modern machine learning solution – deep learning. As part of the research, both hardware and software-based solutions were studied and developed. For testing purposes, different datasets and competing systems were used. Main research methods are experiment, literature analysis and case study for hardware systems. As a result of analysis of modern methods, Mask R-CNN algorithm was chosen due to high accuracy. Conclusions. Problem statement was declared; solution methods were listed and characterized; main algorithm was chosen and mathematical background was presented. As part of the development procedure, accurate automatic license plate system was presented and implemented in different hardware environments. Comparison of the network with existing competitive systems was made. Different object detection characteristics, such as Recall, Precision and F1-Score, were calculated. The acquired results show that developed system on Mask R-CNN algorithm process images with high accuracy on large camera shooting angles. Предметом дослідження є процес створення системи штучного інтелекту для автоматичного визначення номерних знаків. Мета полягає в тому, щоб досягти високої точності розпізнавання номерних знаків під великими кутами камери з виділенням символів. Завдання полягають у дослідженні існуючих технологій розпізнавання номерних знаків і створенні системи штучного інтелекту, яка працює на великих ракурсах зйомки за допомогою сучасного рішення машинного навчання – глибокого навчання. У рамках дослідження були вивчені та розроблені як апаратні, так і програмні рішення. Для цілей тестування використовувалися різні набори даних і конкуруючі системи. Основними методами дослідження є експеримент, аналіз літератури та тематичні дослідження апаратних систем. В результаті аналізу сучасних методів було обрано алгоритм Mask R-CNN завдяки високій точності. В роботі проведено постановку проблеми; перераховано та охарактеризовано методи її вирішення; було обрано основний алгоритм і представлено математичне підґрунтя. У рамках процедури розробки була представлена точна автоматична система визначення номерних знаків, яка реалізована в різних апаратних середовищах. Проведено порівняння запропонованої мережі з існуючими конкурентними системами. Були розраховані різні характеристики виявлення об’єктів, такі як Recall, Precision і F1-Score. Отримані результати показують, що розроблена система на алгоритмі Mask R-CNN з високою точністю обробляє зображення під великими кутами зйомки камерою.

This study presents a methodology for synthesizing optimal control algorithms for the flow parameters of a conveyor-type transport system with a variable transport delay. A multi-section transport conveyor is a complex dynamic system with a variable transport delay. The transport conveyor is an important element of the production system, used to synchronize technological operations and move material. The Analytical PiKh-model of the conveyor section was used as a model for designing a control system for flow parameters. The characteristic dimensionless parameters of the conveyor section are introduced and the similarity criteria for the conveyor sections are determined. The model of a conveyor section in a dimensionless form is used to develop a methodology for synthesizing algorithms for optimal control of the flow parameters of a transport conveyor section. The dependencies between the value of the input and output material flow of the section are determined, taking into account the initial distribution of the material along the conveyor section, variable transport delay, restrictions on the specific density of the material, and restrictions on the speed of the belt. The dependencies between the value of the input and output material flow for the case of a constant transport delay are analyzed. A technique for synthesizing algorithms for optimal belt speed control based on the PiKh-model of a conveyor section is presented. As a simplification, a two-stage belt speed control is considered. Particular attention is paid to the methodology for synthesizing optimal control algorithms based on the energy management methodology (TOU-Tariffs). The criteria of control quality are introduced and problems of optimal control of flow parameters of the transport system are formulated. Taking into account differential connections and restrictions on phase variables and admissible controls, which are typical for the conveyor section, the Pontryagin function and the adjoint system of equations are written. As examples demonstrating the design of optimal control, algorithms for optimal control of the flow parameters of the transport system are synthesized and analysis of optimal controls is performed. Дане дослідження презентує методику синтезу алгоритмів оптимального керування потоковими параметрами транспортної системи конвеєрного типу із змінною транспортною затримкою. Багатосекційний транспортний конвеєр – це складна динамічна система із змінною транспортною затримкою. Транспортний конвеєр є важливим елементом виробничої системи, що використовується для синхронізації технологічних операцій та переміщення матеріалу. Як модель для проектування системи управління потоковими параметрами використана аналітична PiKh-модель секції конвеєра. Введено характерні безрозмірні параметри секції конвеєра та визначено критерії подібності до секцій конвеєра. Модель секції конвеєра у безрозмірному вигляді використана для розробки методики синтезу алгоритмів оптимального керування потоковими параметрами секції транспортного конвеєра. Визначено залежності між значенням вхідного та вихідного потоку матеріалу секції з урахуванням початкового розподілу матеріалу вздовж секції конвеєра, змінної транспортної затримки, обмежень на питому щільність матеріалу та обмежень на швидкість стрічки. Проаналізовано залежність між значенням вхідного та вихідного потоку матеріалу для випадку постійної транспортної затримки. Представлено методику синтезу алгоритмів оптимального управління швидкістю стрічки, засновану на PiKh-моделі секції конвеєра. Як спрощення розглянуто двоступінчасте регулювання швидкості стрічки. Особливу увагу приділено методиці синтезу алгоритмів оптимального управління, що ґрунтується на методології енергоменеджменту (TOU-Tariffs). Введено критерії якості керування та сформульовано завдання оптимального керування потоковими параметрами транспортної системи. З урахуванням диференціальних зв'язків та обмежень на фазові змінні та допустимі керування, характерні для конвеєрної ділянки, записана функція Понтрягіна та приєднана система рівнянь. Як приклади, що демонструють проектування оптимального керування, синтезовано алгоритми оптимального керування потоковими параметрами транспортної системи та проведено аналіз оптимальних керування.

In this paper, the statistical characteristics of the flow of material entering the input of a conveyor-type transport system are studied. For a set of data obtained as a result of experimental measurements of the input flow of material, the law of distribution of a random variable and the correlation function is investigated. Theoretical assumptions about the law of change of the correlation function for the input flow of material are confirmed.

This paper describes the developed method for binary contour images vectorization of handwritten characters for recognition by detector neural networks. A description of the software that implements the developed method is given. Описывается разработанный метод векторизации двоичных контурных изображений рукописных символов для распознавания нейронными сетями детекторного типа. Приводится описание программного обеспечения, реализующего разработанный метод.

Rare members of environmental microbial communities are often overlooked and unexplored, primarily due to the lack of techniques capable of acquiring their genomes. Chloroflexi belong to one of the most understudied phyla, even though many of its members are ubiquitous in the environment and some play important roles in biochemical cycles or biotechnological applications. We here used a targeted cell-sorting approach, which enables the selection of specific taxa by fluorescent labeling and is compatible with subsequent single-cell genomics, to enrich for rare Chloroflexi species from a wastewater-treatment plant and obtain their genomes. The combined workflow was able to retrieve a substantially higher number of novel Chloroflexi draft genomes with much greater phylogenetical diversity when compared to a metagenomics approach from the same sample. The method offers an opportunity to access genetic information from rare biosphere members which would have otherwise stayed hidden as microbial dark matter and can therefore serve as an essential complement to cultivation-based, metagenomics, and microbial community-focused research approaches.

Single-cell genomics and transcriptomics can provide reliable context for assembled genome fragments and gene expression activity on the level of individual prokaryotic genomes. These methods are rapidly emerging as an essential complement to cultivation-based, metagenomics, metatranscriptomics, and microbial community-focused research approaches by allowing direct access to information from individual microorganisms, even from deep-branching phylogenetic groups that currently lack cultured representatives. Their integration and binning with environmental ‘omics data already provides unprecedented insights into microbial diversity and metabolic potential, enabling us to provide information on individual organisms and the structure and dynamics of natural microbial populations in complex environments. This review highlights the pitfalls and recent advances in the field of single-cell omics and its importance in microbiological and biotechnological studies.

As discussed in Part I, a large accumulation of mammalian faeces at the mire site in the upper Guil Valley near Mt. Viso, dated to 2168cal 14C yr., provides the first evidence of the passage of substantial but indeterminate numbers of mammals within the time frame of the Punic invasion of Italia. Specialized organic biomarkers bound up in a highly convoluted and bioturbated bed constitute an unusual anomaly in a histosol comprised of fibric and hemist horizons that are usually expected to display horizontal bedding. The presence of deoxycholic acid and ethylcoprostanol derived from faecal matter, coupled with high relative numbers of Clostridia 16S rRNA genes, suggests a substantial accumulation of mammalian faeces at the site over 2000years ago. The results reported here constitute the first chemical and biological evidence of the passage of large numbers of mammals, possibly indicating the route of the Hannibalic army at this time. Combined with the geological analysis reported in Part I, these data provide a background supporting the need for further historical archaeological exploration in this area.

Controversy over the alpine route that Hannibal of Carthage followed from the Rhône Basin into Italia has raged amongst classicists and ancient historians for over two millennia. The motivation for identifying the route taken by the Punic Army through the Alps lies in its potential for identifying sites of historical archaeological significance and for the resolution of one of history's most enduring quandaries. Here, we present stratigraphic, geochemical and microbiological evidence recovered from an alluvial floodplain mire located below the Col de la Traversette (~3000 m asl-above sea level) on the French/Italian border that potentially identifies the invasion route as the one originally proposed by Sir Gavin de Beer (de Beer 1974). The dated layer is termed the MAD bed (mass animal deposition) based on disrupted bedding, greatly increased organic carbon and key/specialized biological components/compounds, the latter reported in Part II of this paper. We propose that the highly abnormal churned up (bioturbated) bed was contaminated by the passage of Hannibal's animals, possibly thousands, feeding and watering at the site, during the early stage of Hannibal's invasion of Italia (218 BC).

Background Mutations in the BRCA1, BRCA2 and PALB2 genes are well-established risk factors for the development of breast and/or ovarian cancer. The frequency and spectrum of mutations in these genes has not yet been examined in the population of Southern Poland. Methods We examined the entire coding sequences of the BRCA1 and BRCA2 genes and genotyped a recurrent mutation of the PALB2 gene (c.509_510delGA) in 121 women with familial and/or early-onset breast or ovarian cancer from Southern Poland. Results A BRCA1 mutation was identified in 11 of 121 patients (9.1 %) and a BRCA2 mutation was identified in 10 of 121 patients (8.3 %). Two founder mutations of BRCA1 accounted for 91 % of all BRCA1 mutation carriers (c.5266dupC was identified in six patients and c.181 T > G was identified in four patients). Three of the seven different BRCA2 mutations were detected in two patients each (c.9371A > T, c.9403delC and c.1310_1313delAAGA). Three mutations have not been previously reported in the Polish population (BRCA1 c.3531delT, BRCA2 c.1310_1313delAAGA and BRCA2 c.9027delT). The recurrent PALB2 mutation c.509_510delGA was identified in two patients (1.7 %). Conclusions The standard panel of BRCA1 founder mutations is sufficiently sensitive for the identification of BRCA1 mutation carriers in Southern Poland. The BRCA2 mutations c.9371A > T and c.9403delC as well as the PALB2 mutation c.509_510delGA should be included in the testing panel for this population.

Irisin induces the browning of adipose tissue. The goal of this study was to investigate the influence of acute exercise in untrained and trained rats and endurance training on FNDC5 mRNA and irisin levels in white and red skeletal muscle and serum. Rats (n=60) were randomly divided into two groups: untrained and trained (subjected to 6-week endurance training with increasing load). Subgroups of rats from each group were sacrificed before (controls), immediately after, or 3 hours following acute exercise with the same work load. Muscle samples (red and white) and serum were collected. FNDC5 mRNA was evaluated using RT-PCR. Irisin levels were measured using an immunoenzymatic method. Muscle FNDC5 mRNA decreased immediately after acute exercise compared with baseline levels, but not in red muscle in trained rats. Atrend toward a return to baseline appeared 3 hours after the exercise, but only in white muscle in untrained group. Irisin protein levels increased after acute exercise in red muscle 3 hours post-exercise compared with samples taken immediately after exercise, and decreased 3 hours post-exercise compared to pre-exercise level in white muscles. FNDC5 mRNA did not change following training, whereas irisin protein levels increased in red muscle and decreased in white muscle. Serum irisin levels remained unchanged following acute exercise and training. We concluded that changes in irisin mRNA and protein levels in rat muscle after acute exercise are limited and depend on training status and the muscle type. Irisin serum levels remained stable after acute exercise or endurance training.