Informatics Engineering

Topic title	Possible scientific supervisors	Source of funding
Deep learning for monitoring and risk analysis of brain hemorrhage	prof. dr. Robertas ALZBUTAS	state-funded
UML, BPMN and SBVR integration for business processes and rules modelling for transforming them to IS design models	prof. dr. Rimantas BUTLERIS	state non-funded
Application of deep learning methods for the energy consumption prediction of the building	prof. dr. Vidas RAUDONIS	state non-funded
Application of deep learning techniques for dynamic images anomaly detection	doc. dr. Arūnas LIPNICKAS	state non-funded	Research Topic Summary. In production-oriented industry of the furniture, textile, food and packaging, processes are extremely fast. The natural cause of the rising is the – mass consumption. As the amount of production speeds up the number of defects speeds up as well. Therefore, the company shall take the necessary measures for the control of the development and implement the systems to ensure a high level quality of product. The production of the bulk of the problem lies in how to remove defective products without losing production speed and ensuring that all of the low-quality products will be removed. This problem can be solved in several ways: Visual inspection, defects detection of the production can be integrated into entire manufacturing process. The registration of visual images is usually done by speed cameras; various cameras operating at different light could be engaged. The images are processed by artificial intelligence techniques to take decisions about the action of the objects with defects. Recently emerged new artificial intelligence method called deep learning neural networks that has shown the ability to carry contextual analysis of video information. Such methods works perfectly with monolithicall surfaces, but not jet applied in the food, textile and furniture industry with a patterned and mottled surfaces. Supervised approaches, however, can be challenging, since it is often difficult to obtain large amounts of labelled training data for abnormal class. The aim of this work is to build one-class unsupervised learning on fault-free samples by training a deep convolutional neural network to find dynamic images anomality.
Cryptographic Algorithms Specification Methods for Power Consumption Forecasting and Management in Mobile Devices	prof. dr. Jevgenijus TOLDINAS	state non-funded	Research Topic Summary. The number of mobile phone users in the world is expected to pass the five billion mark by 2019. Today mobile phone in our pocket is a high performance computer with gigabytes of RAM, processor that has two, four or more cores, Wi-Fi, Bluetooth, display, and etc. All of mentioned devices consume battery energy. Unfortunately, while technical parameters of mobile phones growths quickly, battery lifetime remains very short and users must charge their phones more and more frequently. BYOD (bring your own device) is the increasing trend when employee brings their owned smartphones, tablets or laptops to their workplace. That is why prediction of energy consumption for devices with battery is an important issue. Main purpose of the dissertation: 1) To propose novel models, methods and software tools for energy consumption forecasting at application level; 2) To specify how much cryptographic algorithms consume the power of a mobile device. New results are expected: 1) Common models, specialized methods that assess the variability of the criteria and enable prediction, management of energy consumption at the application level; 2) Realization of specialized methods - software components that enable users to evaluate the energy consumption of cryptographic algorithms in relation to other criteria; (3) Adaptation of specialized methods for the flexible use of mobile devices for energy forecasting.
Artificial intelligence based image processing method for detection of illegal driving maneuvers	prof. dr. Rytis MASKELIŪNAS	state non-funded
Efficient Learning method for Computer Vision from Small Datasets	prof. dr. Rytis MASKELIŪNAS	state non-funded
Microbial process modelling and optimal control	prof. dr. Renaldas URNIEŽIUS	state non-funded	Research Topic Summary. This study will involve development of non-invasive software sensors for biotechnology applications, which cover monitoring recombinant E.coli and other biotechnological processes and controlling specific growth rate. The PhD student will be responsible for research and experimental development activities, taking care of bioprocess publications and participating in scientific conferences. Depending on the results achieved and the initiative, it is possible to take part in additional project activities related to the PhD topic.
Identification and tracing methods creation and analysis of dishonest blockchain technology users	prof. dr. Eligijus SAKALAUSKAS	state non-funded	Research Topic Summary. According to modern trends, the technology of Blockchain is and will be relevant in the process of development of the information society. Many Blockchain technologies declare partial or cryptographically secure anonymity. However, there is a lot of dishonest users who abuse the anonymity to obtain an illegal benefit. There are currently restricted methods of resolution that prevent double spending in cryptocurrencies systems. Cryptocurrency transactions are conducted in a chaotic manner on the network, partial resolution methods are insufficient. The purpose of the dissertational work: to create and analyze identification and tracing methods of dishonest Blockchain technology users. The tasks of dissertation: 1. Analyze the types of existing forgeries in Blockchain technologies. 2. Establish a security model to mitigate the effects of attacks. 3. Investigate the effectiveness of the model.
Method for seating posture detection based on near field depth information	prof. dr. Rytis MASKELIŪNAS	state non-funded
Self training deep learning based method for „solving“ CAPTCHA systems	prof. dr. Rytis MASKELIŪNAS	state non-funded

Download the list

Apply

Minimum requirements

Persons with a Bachelor’s and Master’s Degrees in technologies or physical sciences may participate in an open competition for admission to doctoral studies.

Applicants to the doctoral program in the field of science are accepted by competition according to the competition score. Minimum Competition Score 7,5

Application procedure

Application and the following documents are submitted online at apply.ktu.edu

Official legalised Bachelor’s and Master’s diplomas or a higher education degree equivalents and academic transcripts (translated into English or Lithuanian and notary verified)
Curriculum Vitae
Recommendations by two researchers of the relevant science field (one of the recommendations must be written by the supervisor of the research topic the candidate is applying for)
A research proposal on the selected topic
A list of the research works (this list is submitted with full bibliographic description) along with copies of the research works (or a research paper on the topic (-s) consistent with the dissertation topic (-s) indicated in the candidate’s application, if a candidate does not have any research works)
A copy of the passport personal data page, or a copy of the ID card
A copy of the receipt of the application fee payment (40 EUR for EU citizens, and 100 EUR for non-EU citizens)
A certificate issued by IELTS, TOEFL, CERF or any other competent institution within the last 2 years certifying the level of the English language if the candidate is not a graduate of the first or second cycle studies conducted in the English language

Participation in motivational interview (Kaunas University of Technology, K. Donelaičio g. 73, Kaunas, Lithuania or online)

Signing a study agreement (if invited to study)

Selection criteria and their weighted coefficients

Research experience Research experience in ten-point grading system (The evaluation of the research experience includes the candidate’s scientific publications or the research paper, other research experience, scientific qualifications, the compliance of the scientific publications and research experience with the topic of doctoral studies)	0,4
Weighted grade point average of the diploma supplement	0,3
Motivational interview, including evaluation of the knowledge of a foreign language	0,2
Research proposal	0,1

Doctoral School contacts

Apply

Code	T007
Cycle	Third cycle
Language	Lithuanian, English
Duration	4 y.
Degree awarded	Doctor of Science

Partners

Research Topic Summary.

Research Topic Summary.

Research Topic Summary.

Research Topic Summary.

Minimum requirements

Application procedure

Selection criteria and their weighted coefficients