Galina MomchevaBulgarian Academy of Sciences | BAS · Institute of Mathematics and Informatics
Galina Momcheva
ANN architectures; biomedical image analyses; algorithms; digital competence
About
47
Publications
7,422
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
32
Citations
Introduction
Galina Momcheva has research interests in:
A. Design and Evaluation of Novel Models and Architectures for Artificial Neural Networks Inspired by Contemporary Brain Research
A1. Dendritic Computing
A2. Fuzzy-Based NN
A3. Biomimetic NN
B. Research for Business
B1. Research-Based Ecosystems Sustainability
B2. Immune Support Businesses
C. Computer Science and Education
C1. Talents in Research Networks (mentorship/supervision) of PhD/UnivStu/HighSchoolStu)
C2. PD for Teachers
C3. AI in Education
Publications
Publications (47)
The author shared her experience in: new artificial neural networks architectures; design approaches; biomedical image analysis; multimodal image registration; computational topology; development of fundamental research in the domain specific area; cloud services for research; commercialization of research; research communities building represented...
The presentation describes the author's practices and ideas for building research-based ecosystems that are based on values for the region. Numerous events, initiatives and research are presented.
Тhe presentation describes the author's experience in attracting young people to scientific teams and in building an ecosystem (Biomed-Varna), which successfully develops research, entrepreneurial and educational initiatives in an interdisciplinary environment of life sciences, computer sciences and arts.
https://space.innowavesummit.com
In the presentation, the author shares the experience and expectations on the topic of commercialization of scientific research, including the possibility of financing innovative researched-based businesses and practices.
The author shares trends in STEAM and AI and its benefits for students (8. grade) and teachers in computer science in Bulgaria.
Тhe presentation describes the author's experience of participating in research interdisciplinary scientific groups and activities in building a researcher-based ecosystem developed through research practices.
Тhe author shares trends in software development and training on the subject for teachers in Bulgaria
Тhe author shares trends in educational practices in programming training for teachers in Bulgaria
Методическо пособие за изследване на функции
Първата ми книга в съавторство с Валентина Момчилова, 1997
Книгата не може да се купи (и никога не е можело от издателството), затова я слагам тук.
Имам интерес да се преиздаде с допълнения за адекватно използване на математичски софтуер.
![Fig. 1. Scheme of the chosen autoencoder created with Graphviz [ 14 ]](profile/Stoyan-Pavlov-2/publication/375971909/figure/fig1/AS:11431281207329710@1701179164564/Scheme-of-the-chosen-autoencoder-created-with-Graphviz-14_Q320.jpg)
Currently, analysis of microscopic In Situ Hybridization (ISH) images is done manually by experts. Precise evaluation and classification of such microscopic images can ease experts' work and reveal further insights about the data. In this work, we propose a deep-learning workflow to detect and classify areas of microscopic images with similar level...
Throughout the years neural networks have been based on the perceptron model of the artificial neuron. Attempts to stray from it are few to none. The perceptron simply works and that has discouraged research around other neuron models. New discoveries highlight the importance of dendrites in the neuron, but the perceptron model does not include the...
The main purpose of this research is to facilitate the readers’ understanding about the need and the importance of exploring key topics concerning the neural networks architecture design, from both scientific and practical points of view. Another key aim of the monograph is to attract members of diverse research groups to do extensive interdiscipli...
The aim of this article is to analyse existing STEM practices at High School of Mathematics-Varn and international practices in the area and current technological and social trends and to try to synthesize a roadmap for sustainable development of STEAM practices. The roadmap given examines milestones, indicators of success and assessment of progres...
The aim of the article is to give feedback on learning practices for English for Computer Science courses and to suggest meaningful updates, increasing the effectiveness and usefulness of these courses. The recommendations given are based on the experience of the author as a lecturer in Computer Science (programming, algorithms, data mining, design...
Currently, analysis of microscopic In Situ Hybridization images is done manually by experts. Precise evaluation and classification of such microscopic images can ease experts' work and reveal further insights about the data. In this work, we propose a deep-learning framework to detect and classify areas of microscopic images with similar levels of...
This textbook aims to satisfy the need of practical approach to Cybersecurity and to present some engaging real-case scenarios (case studies) of solving problems in the area of Cybersecurity with the help of Machine Learning.
The target group of this textbook are lecturers in computer science for bachelors' and masters' degree programs, students C...
The aim of the paper is to study sustainability of the research-based entrepreneurial ecosystem BioMed-Varna. The BioMed-Varna is focused on interdisciplinary research in Biomedical Image Analysis, Computational Life Sciences, and Neuroscience. Its main activities include multidisciplinary scientific research, educational projects, development of S...
Artefacts are a common occurrence in microscopic images and scans used in life science research. The artefacts may be regular and irregular and arise from different sources: distortions of the illumination field, optical aberrations, foreign particles in the illumination and optical path, errors, irregularities during the processing and staining ph...
One of the problems in biomedical image analysis is the problem of nuclei segmentation. The annotation of nuclei by hand has proven itself very time consuming with varying results depending on many factors. More recently convolutional neural networks have made the problem of automatic image segmentation easier, faster and more reliable. In this art...
High-throughput chromogenic in-situ hybridization (CISH) is a bright-field microscopic technique that reveals the spatial distribution of gene expression in animal cells and tissues by an easily detectable coloured precipitate. The “golden standard” for the grading of CISH-stained tissues involves qualitative scoring by a domain expert. This method...
Cybersecurity education in schools is related to both career opportunities for students and the safe use of Internet technologies. Therefore, the topic of cybersecurity training is covered in school curricula in a number of countries. The article analyzes the good experience of leading countries in training in this field. The different forms of suc...
Varna Free University has a tradition in teaching cyber security through bachelor’s, master’s and doctoral degrees and LLL (Lifelong Learning) courses for school teachers and students. The latest Cyberwizards project stems from the need to teach teachers and students how to protect themselves online, how to manage their digital identity, what types...
This paper presents a proof of concept for the usefulness of second-order texture features for the qualitative analysis and classification of chromogenic in-situ hybridization whole slide images in high-throughput imaging experiments. The challenge is that currently, the gold standard for gene expression grading in such images is expert assessment....
The presentation shows the sucessful interdisciplinary interuniversity collboration (Medical University - Varna, Varna Free University) for estabslishing master degree programs "AI in BioMedicine" and "AI in Healthcare", Varna 2021.
The presentation shows the experience of Computer Science Department at Varna Free University and partners in providing STEAM practices from universities to schools in the region of Varna, Bulgaria.
The article aims to explore the relationship between readability of texts from instructions (assignments texts, technical documentation, law/regulation texts) and the corresponding source code (task solution) from a particular education resource for programming on the topic with neural/positive sentiment ‘identity documents’. The article examines t...
Regression is a powerful technique for predicting a single scalar value with a high degree of certainty. A regression model requires a dataset that consists of only numeric features. However, datasets frequently contain both numeric and categorical features. This paper sets out to study several different text encoding techniques, which can solve th...
In this article, the optimization of the modified U-Net neural network model extended with fuzzy layers has been studied with the usage of Grid search and Keras tuner. The article is a continuation of previous work where the model is suggested and explored. From one point of view, the research is focused on the optimization of Fuzzy Layers embedded...
In this article, the optimization of the modified U-Net neural network model extended with fuzzy layers has been studied with the usage of Grid search and Keras tuner. The article is a continuation of previous work where the model is suggested and explored. From one point of view, the research is focused on the optimization of Fuzzy Layers embedded...
![Fig. 1. FedMD Architecture by [7]](profile/Galina-Momcheva/publication/347172951/figure/fig1/AS:968923495280640@1608020771054/FedMD-Architecture-by-7_Q320.jpg)
![Fig. 5. LEAF's SENTIMENT140 results by [2]](profile/Galina-Momcheva/publication/347172951/figure/fig5/AS:968923495268359@1608020771227/LEAFs-SENTIMENT140-results-by-2_Q320.jpg)
Federated learning is a distributed machine learning technique in which client devices train models locally without sharing any data, except for parameter changes, which get aggregated to a central model. This privacy-preserving approach has a huge potential for reconciling the need for large Deep Learning datasets with the increasing sensitivity o...
This paper presents a proof of concept for the usefulness of second-order texture features for the qualitative analysis and classification of chromogenic in-situ hybridization whole slide images in high-throughput imaging experiments. The challenge is that currently, the gold standard for gene expression grading in such images is expert assessment....
A survey of Information Technology (IT) undergraduate degree programs in Canada is presented. IT Bachelor degrees have not been very popular in Canada although they have existed for a number of years in other parts of the world, including the United States (US) and the European Union (EU). This survey is looking into the current status of IT underg...
The educational effect of games can be found in the formation of a certain system of qualities, views and beliefs, in the constructing of the relation between person and reality; the teaching effect is found in the acquisition of a system of knowledge, skills and habits. The article aims to demonstrate the benefits of using a set of educational gam...
https://www.book.store.bg/p203833/informatika-za-8-klas-galina-momcheva-todorka-glushkova-rosica-marinova.html
Approved by the Bulgarian Ministry of Education and Science РД 09 3313 /14.08.2017 г.
Учебникът ИНФОРМАТИКА за 8. клас е разработка на авторски колектив в състав: Галина Момчева, Тодорка Глушкова и Росица Маринова.
Чрез него екипът предла...
Книгата за учителя по ИНФОРМАТИКА за 8. клас е разработка на авторски колектив в състав: Галина Момчева, Тодорка Глушкова и Росица Маринова.
В нея са представени концепцията за самото обучение, методически бележки по реализацията на процеса на обучение с този учебник, отговорите на някои задачи или насоки за решаването им. Създадени са помощни файл...
In this publication, the author shares her experience with practices with collages of digits, conducted during trainings of teachers, pupils and students, for the purpose of relaxation, introductory games for acquaintance (ice-breaking), etc. The observations are that people with skills in a particular field intuitively create collages in this fiel...
КОЛАЖИ ОТ ЦИФРИ
В настоящата публикация се споделя от автора опит от практики с колажи от цифри, проведени по време на обучения на учители, ученици и студенти, с цел релакт, въвеждащи игри за запознаване и др. Наблюденията са, че хората с умения в оперелена област интуитивно създават колажи в тази област, което е основание за продължаващо методиче...
Книгата разглежда темата "Разделяй и владей" както като техника на програмиране, така и като техника на дизайн на алгоритми.
Глава 1,2 - автор Мария Брусева
Глава 3,4 - автор Галина Момчева
Глава 1. Алгоритъм. Класификация на алгоритми. Алгоритмична техника "Разделяй и владей"
Глава 2. Анализ на алгоритми
Глава 3. "Разделяй и владей". Използване н...
The paper presents some important problems in bioinformatics and genomics such as the gene prediction problem. The task of finding the local and global alignment of two sequences is also presented as well as the well-known algorithms that solve it. A new method solving the gene prediction problem using a dictionary coder is presented. The paper con...
Questions
Questions (3)
Computational topology of solitons
The well-established research area of algebraic topology currently goes interdisciplinary with computer science in many directions. The Topological Data Analysis gives new opportunities in visualization for modeling and special mapping. A study on metrics used or simplicial complexes are reliable for future results in the area of mathematics.
Today, the machine learning from one side is a tool for the analysis in topology optimization, topological persistence and optimal homology problems, from other side the topological features in machine learning are new area of research, topological layers in neural networks, topological autoencoders, and topological analysis for the evaluation of generative adversarial networks are in general aspects of topology machine learning.
On practical point of view, the results in this area are important for solitary-like waves research, biomedical Image analysis, neuroscience, physics and many others.
That gives us opportunity to establish and scale up an interdisciplinary team of researchers to apply for funding for fundamental science research in interdisciplinary field.
More Info: https://euraxess.ec.europa.eu/jobs/249043
Dear colleagues from academia and industry,
dear friends or sansfriends :)
I presented this summer on the "languages" conference the idea of the need for change in the area of English for Computer Science (Computer Engineering etc).
I see a lot of people that are ready to be involved in this actions in Bulgaria and abroad.
So I'm writing this description not to discuss here but to use the community to find out appropriate team (people with values, skills and experience). And I think we can manage this problem with some efforts. In this team I think different type of people are more then welcome (e.g. academics/teachers English/Computer Science/Engineering, students, professionals from IT Industry).
Please reply here in this post (to support me and the initiative) and also register here https://docs.google.com/forms/d/e/1FAIpQLSd2h527OHr6gkdxL5ZAOsJyzQEKaXt-YhW7nNxOAM6aQcvGsg/viewform
My suggestion for the first meeting is December 18, 19 h BG time
To all of registered people I will send a link (Google meet).
Galina Momcheva
According to me Lifecycle Practices/Paradigm is a little behind in comparrison with software practices. I'm thinking also on the influence of Automated Machine Learning on ML Lifecyce and in the modeling of new lifecycle.
