Contents
Academic literature on the topic '004.934.2'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic '004.934.2.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Dissertations / Theses on the topic "004.934.2"
Діденко, Данііл Юрійович. "Алгоритми розпізнавання емоцій за мовними сигналами." Master's thesis, Київ, 2018. https://ela.kpi.ua/handle/123456789/25470.
Full textThe thesis contains the main part on 38 sheets, 24 illustrations. The purpose of the dissertation is to analyze and simulate the algorithms for recognizing emotions by speech signals. The object of research is the algorithms of emotion recognition. The subject of the study is the recognition of emotions by the speech signal. The result of the work is: Research of the principles of the algorithms of emotional recognition; Investigation of acoustic signs of a speech signal; Simulation and comparison of various algorithms for recognizing emotions by speech signal. Field of application: digital processing of acoustic signals.
Целью диссертации является анализ и моделирование алгоритмов распознавания эмоций по речевыми сигналам. Объектом исследования являются алгоритмы распознавания эмоций. Предметом исследования является распознавание эмоций по речевым сигналом. Результатом работы являются: Исследование принципов действия алгоритмов распознавания эмоций; Исследование акустических признаков речевого сигнала; Моделирование и сравнения различных алгоритмов распознавания эмоций по речевым сигналом. Область применения: цифровая обработка акустических сигналов.
Сокол, Ярослав Володимирович. "Метод розпізнавання двовимірних кодів на зображеннях." Master's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/45939.
Full textNowadays, two-dimensional bar codes have become widespread, which are used to encrypt and automatically read various types of information. In general, there are a number of types of the most commonly used two-dimensional barcodes. Therefore, universal decoders for decrypting the code must pass it through the decoding subsystems of each type of code. Since the decoding procedure is not simple, the time to try to process all code variants can be quite long. To overcome this problem in this work, a neural network for the primary recognition of the type of code, followed by the selection of the most likely for this type of decoder is proposed. Namely, the method of preliminary recognition of the most common types of two-dimensional codes based on the SqueezeNet neural network is proposed, which in contrast to the procedure of sequential verification by direct decryption using code decoding libraries allows to increase the speed of code type determination by 6 ms.
Ясенко, Лев Сергійович. "Апаратні засоби для підвищення продуктивності обробки зображень штучними нейронними мережами." Master's thesis, КПІ ім. Ігоря Сікорського, 2021. https://ela.kpi.ua/handle/123456789/45951.
Full textRelevance of the topic: significant demand in the market of image processing systems and services based on artificial intelligence algorithms determine the development of appropriate hardware. The relevance of the topic is confirmed by statistical research of scientific publications in this area. Therefore, the development of hardware for image processing systems using neural network algorithms is an urgent task. The object of the research is the hardware for image processing based on artificial neural networks. The subject of the research is to increase the productivity of image processing based on artificial neural networks with the help of hardware. Objective: to increase the productivity of digital image processing systems based on neural algorithms by improving the performance of relevant hardware. The scientific novelty of the work is the proposal to implement the operation of convolution at the hardware level to increase the productivity of image processing by hardware using artificial neural networks. Approbation of work. The study of the efficiency of digital image processing depending on the hardware is presented in the publications in "ПМК-2021" (Kyiv, November 17-19, 2021) and „Інформаційні технології та комп’ютерна інженерія” (Vinnytsia, in preparation for publication). The practical value of the work lies in obtaining results that can be used in the process of determining the directions of further research and using the proposed solution for the implementation of the convolution operation in image processing hardware using artificial neural networks. The structure and scope of the work include a table of contents, introduction, four chapters, conclusions, list of sources used and appendices. In the introduction the general characteristic is given, the general review of a condition of a problem is made and urgency of the decision of the set task is defined. The first section reviews the development of software and hardware for digital image processing, as well as an overview of the market for hardware for processing artificial neural networks, and outlines the direction of future research. The second section describes the theoretical model of the image processing system with artificial neural networks, identifies the features of the use of hardware in image processing problems and formulates the requirements for the proposed solution. The third section describes the modeling of the proposed solution. The fourth section describes how to evaluate the proposed solution. The conclusions present the results of the work carried out to solve the problem of improving the productivity of image processing hardware using artificial neural networks. The dissertation is presented on 104 pages, including appendices, and has 51 figures and 11 tables.
Душутін, Владислав Володимирович. "Паралельний адаптивний вирішувач для лінійних систем на основі нейронної мережі." Master's thesis, Київ, 2018. https://ela.kpi.ua/handle/123456789/23556.
Full textNow one of the main stages in the study of objects, phenomena and processes of different nature is mathematical modeling and related computer experiment. Numerous experiments give an opportunity to plan a full-scale experiment, as well as to get new knowledge about those processes and phenomena for which it is difficult, or in general, impossible to carry out a full-scale experiment. A large number of mathematical models can be described by systems of linear algebraic equations (SLRs) with soldered matrices after performing the corresponding transformations. The main feature of such systems is their large orders and a small number of non-zero elements. Large orders of SLAR arise due to the fact that researchers want to get the most reliable results, which is why more detailed models are being built. The small number of non-zero elements is due to the discretization of the model. In particular, systems of equations with sparse matrices arise in problems of analysis of the strength of structures in civil and industrial construction, filtration, heat and mass transfer, and others like that. Scope of the methods of solving SLR with sparse matrices is constantly expanding. Because of this, there is an interest in the problem of constructing effective methods for solving such systems, whose orders exceed hundreds of thousands. Classical results concerning the development of methods for solving SLRR with rarefied matrices are covered in a series of monographs of American and domestic authors: A. George, J. Liu, S. Pisanetski, J. Golub, R. Tjurson, I. A. Blatova, ME Ekseryrovskaya and others. Also, the requirements for the computer technology used to conduct a computer experiment are growing. It must provide sufficient speed and have the required amount of resources so that the result of the experiment can be obtained over a relatively short period of time. Now in the market there are many different architectures of computers with parallel computing organization. The most productive are the platforms of the so-called "hybrid" architecture. These systems combine MIMD (multiple instructions - multiple data) and SIMD architecture (single instruction - multiple data), in particular, in a multi-core processor system, computations are accelerated by means of a graphical accelerator. Hence, one of the effective approaches to solving SLR with sparse matrices is the construction of parallel algorithms that take into account the peculiarities of computer architecture. The main problems of developing effective parallel algorithms are: analysis of the structure of the matrix, or bringing it to the corresponding form, using appropriate conversion algorithms; choice of effective data decomposition; determining the effective number of processor cores and graphic accelerators used for calculations; definition of the interprocess communication topology, which reduces the number of communications and synchronizations. It is precisely for analyzing the structure of a sparse matrix that a neural network is used which allows the selection of groups of non-zero elements that can be processed independently. The results of the analysis will be based on the decomposition of data and the number of computing cores to be selected, which will provide the shortest settlement time for a particular matrix structure. The purpose and objectives of the study. The purpose of the work is to develop and research parallel methods and computer algorithms for research and solving SLR with sparse matrices of irregular structure on computers of MIMD architecture and MIMD and SIMD architecture combinations, testing of algorithms in mathematical modeling in applied problems. The research tasks include: • development and research of iterative parallel algorithms for SLR with sparse matrices of irregular structure with approximate data; • development of algorithms and programs for investigating the validity of solutions obtained by direct and iterative methods; • Approbation of algorithms for mathematical modeling in applied problems. The object of the study is the mathematical models described by SLAR with sparse matrices of the irregular structure. The subject of the study is parallel methods and computer algorithms for locating the SLR solution with sparse matrices of the irregular structure. Research methods. The paper uses methods of matrix theory, linear algebra, graph theory, functional analysis, error theory, and the theory of neural networks.
Бурмістр, Володимир Олександрович, and Volodymyr Burmistr. "Технологіı̈ оптичного розпізнавання реквізитів банківських карт." Master's thesis, Тернопільський національний технічний університет імені Івана Пулюя, 2020. http://elartu.tntu.edu.ua/handle/lib/33268.
Full textThe master's qualification work is devoted to the study of technologies of optical recognition of bank card details in order to improve the quality of optical recognition of their details. An algorithm for pre-processing the input image and a software module for pre- processing the bank card image have been created. To improve the image quality, it is proposed to use linear and nonlinear filters, convert the image to grayscale, binarize the image with a local maximum and minimum. The image pre-processing module, which implements the image enhancement algorithm, is written in c#, which allows in the future to embed this module in a large number of systems for optical character recognition of bank card details, including mobile applications. The paper presents specific results of recognition of bank card details using the image pre-processing algorithm, and compares these results with recognition without pre- processing.
1. Аналіз сучасних технологій оптичного розпізнавання та можливості їх використання для розпізнавання реквізитів банківської карти. 2.Дослідження можливості покращення результату розпізнавання реквізитів банківської карти. 3.Створення власного алгоритму попереднього опрацювання зображення з метою покращення точності розпізнавання реквізитів банківської карти. Розробка програмного модуля який буде працювати за розробленим алгоритмом попереднього опрацювання зображення.
Тимчак, Олександра Ігорівна, and Oleksandra Tymchak. "Алгоритм розпізнавання особи за зображенням обличчя для охоронних систем контролю та безпеки." Master's thesis, Тернопільський національний технічний університет імені Івана Пулюя, 2021. http://elartu.tntu.edu.ua/handle/lib/36674.
Full textThe qualification work considers modern security systems that use face recognition modules. The general shortcomings and factors influencing the efficiency of work are analyzed. A comparative analysis of existing algorithms and methods of selection and recognition of faces in images and an algorithm for pre-processing, which can increase the probability of correct selection and subsequent recognition of faces in the image.
Вступ ... 8 РОЗДІЛ 1. АНАЛІТИЧНА ЧАСТИНА ...10 1.1. Огляд існуючих систем та алгоритмів розпізнавання...10 1.1.1. Сучасні системи розпізнавання облич...11 1.1.2. Недоліки сучасних систем розпізнавання ...14 1.2. Огляд алгоритмів виділення обличчя на зображенні ...15 1.2.1. Алгоритм на основі емпіричних методів...15 1.2.2. Алгоритми на основі контурних моделей ...17 1.2.3. Алгоритми на основі порівняння із шаблоном ...27 1.2.4. Алгоритми з урахуванням навчання ...31 1.3. Огляд алгоритмів розпізнавання обличчя на зображеннях ...39 1.3.1. Алгоритм методом «власних осіб» ...39 1.3.2. Штучні нейронні мережі ...42 1.4. Висновки до розділу 1 ...46 РОЗДІЛ 2. ОСНОВНА ЧАСТИНА ...47 2.1. Аналіз та вибір алгоритму виділення осіб ...47 2.1.1. Результати роботи алгоритму сегментації ...47 2.1.2. Результати роботи алгоритму на основі порівняння із шаблоном ... 50 2.1.3. Результати роботи алгоритму Віоли – Джонса ...52 2.2. Розробка алгоритму виділення та розпізнавання обличчя на зображенні...53 2.3. Розробка алгоритму розпізнавання обличчя на зображенні...68 2.4. Висновки до розділу 2 ...69 РОЗДІЛ 3. НАУКОВО-ДОСЛІДНА ЧАСТИНА ...70 3.1. Дослідження алгоритму виділення осіб ...71 3.2. Дослідження алгоритму розпізнавання облич ...73 3.3. Висновки до розділу 3 ...75 РОЗДІЛ 4. ОХОРОНА ПРАЦІ ТА БЕЗПЕКА В НАДЗВИЧАЙНИХ СИТУАЦІЯХ ...77 4.1. Охорона праці ...77 4.2. Безпека в надзвичайних ситуаціях ...82 4.3. Висновок до розділу 4 ...86 ЗАГАЛЬНІ ВИСНОВКИ ...88 ПЕРЕЛІК ПОСИЛАНЬ...89 ДОДАТКИ...91
Левчук, Святослав Богданович. "Інтелектуальна система мерчандайзингу. Детекція та розпізнавання асортименту." Master's thesis, Київ, 2018. https://ela.kpi.ua/handle/123456789/23987.
Full textMaster thesis explanatory note: 126 p., 47 fig., 30 tab., 2 appendices, 31 sources. The object of research – intelligent merchandising system. The subject of research – classification methods of goods on shelves in stores. The purpose of the work is to develop an intelligent merchandising system that will reduce the use of human resources and maximize the process of merchandising through automatic monitoring of the availability of goods on shelves and to develop of goods classification system as a part of a merchandising system for the analysis of goods on the shelf in relation to the store planograms. In the work, modern merchandising systems and their shortcomings are considered and analyzed, as well as existing classification methods are considered. Goods classification method with specially developed convolutional neural network, which is constructed on the basis of methods using convolutional neural networks, with nonlinear classifiers and an adaptive optimization method is proposed. Intelligent merchandising system and assortment classification system are implemented using Python programming language with MySql DB. The results of this work are recommended for monitoring the compliance with the planogram and availiability of the goods on shelves in stores.
Бойко, Дмитрий Александрович. "Декомпозиционный метод и подсистема повышения качества визуализации анатомических и патологических структур на цифровых маммограммах." Thesis, НТУ "ХПИ", 2017. http://repository.kpi.kharkov.ua/handle/KhPI-Press/28544.
Full textThis dissertation was submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in technical sciences for specialty 05.11.17 – Biological and Medical Devices and Systems – at the National Technical University "Kharkov Polytechnic Institute", Kharkov, 2107. This work is dedicated to solving important scientific and technical tasks to improve the quality of visualization of anatomical and pathological structures on low-contrast gray-scale images of mammary glands (MG) using new method and a subsystem for visualizing mammographic images. A mathematical model of the MG image in a mammogram based on the original image decomposition into components was developed. The model further served as a foundation for the development of a decomposition method to improve the image quality of the MG. Next, the parameters of the method for improving the quality of IMRI-MAM mammogram visualization were optimized. As a result of this work, a new method of multi-criteria image quality assessment method, based on subjective and objective mammographic image characteristics, was developed. The results of processing digital mammograms with the IMRI-MAM method are presented. The structure of the decision making support system to be used in mammalogy is presented. A software to be used to visualize mammographic images was developed. The subsystems were verified on real medical data.
Бойко, Дмитро Олександрович. "Декомпозиційний метод та підсистема підвищення якості візуалізації анатомічних і патологічних структур на цифрових мамограмах." Thesis, НТУ "ХПІ", 2017. http://repository.kpi.kharkov.ua/handle/KhPI-Press/28541.
Full textThis dissertation was submitted in partial fulfillment of the requirements for the degree of Doctor of Philosophy in technical sciences for specialty 05.11.17 – Biological and Medical Devices and Systems – at the National Technical University "Kharkov Polytechnic Institute", Kharkov, 2107. This work is dedicated to solving important scientific and technical tasks to improve the quality of visualization of anatomical and pathological structures on low-contrast gray-scale images of mammary glands (MG) using new method and a subsystem for visualizing mammographic images. A mathematical model of the MG image in a mammogram based on the original image decomposition into components was developed. The model further served as a foundation for the development of a decomposition method to improve the image quality of the MG. Next, the parameters of the method for improving the quality of IMRI-MAM mammogram visualization were optimized. As a result of this work, a new method of multi-criteria image quality assessment method, based on subjective and objective mammographic image characteristics, was developed. The results of processing digital mammograms with the IMRI-MAM method are presented. The structure of the decision making support system to be used in mammalogy is presented. A software to be used to visualize mammographic images was developed. The subsystems were verified on real medical data.
Радюк, Павло Михайлович, and Pavlo Radiuk. "Інформаційна технологія раннього діагностування пневмонії за індивідуальним підбором параметрів моделі класифікації медичних зображень легень." Дисертація, Хмельницький національний університет, 2021. http://elar.khnu.km.ua/jspui/handle/123456789/11937.
Full textThe present thesis is devoted to solving the topical scientific and applied problem of automating the process of diagnosing viral pneumonia by medical images of the lungs through the development of information technology for early diagnosis of pneumonia by the individual selection of parameters of the classification model by medical images of the lungs. Applying the developed information technology for the early diagnosis of pneumonia in clinical practice by medical images of the human chest increases the accuracy and reliability of pneumonia identification in the early stages