Saugos problemos virtualizuotose aplinkose tampa vis aktualesnės, todėl darbe nagrinėjama piktavališkos programinės įrangos virtualių mašinų aplinkoje aptikimo problematika. Darbe pateikiama: 1)piktavališkos programinės įrangos veikiančios virtualizuotose aplinkose analizė 2)metodikos, piktavališkos programinės įrangos virtualių mašinų aplinkoje aptikimui, sudarymas 3)piktavališkos programinės įrangos virtualioje mašinoje aptikimo, panaudojant sudaryta metodiką, eksperimento rezultatai ir jų priklausomybė nuo virtualios mašinos darbinės atminties dydžio. / In the context of virtual environment, The Security problems are highly important. The work presents analysis of malware types and it‘s presence in virtualized environments. Work also presents some results of experiments that have been carried out within the real virtual machine environment through modeling aiming to identify dependencies between the malware type, called Rootkits, detection time and the virtual machine memory size. Rootkits exploit kernel vulnerabilities and gain privileges (popularity) within any system, virtual or not. The basic result of the work is as follows: 1) the malware detection methodology for the virtual environment when the memory size of a virtual machine is changing; 2) dependences between the virtual machine memory size and Rootkit detection time.

Mechanical properties of polymers are reviewed and the phenomenon of the abrasive wear is analyzed in the literary part. The researches of other authors on the abrasive wear and their results are surveyed. Laboratory equipment for carrying out the abrasive wear researches is introduced. Optimal mount of laboratory simulation for modeling polymeric material wear in the abrasive environment is chosen. The testing materials‘ properties are characterized. The results of researches on polymeric materials, used in enginery, on the wear in the abrasive environment are presented. The carried out research showed that wear results of the same materials under different testing conditions (“polymer-abrasive”, “polymer-steel disc” ASTM G176-03) the dependence of wear on hardness end on the coefficient of friction differs. That is influenced by the choice of polymeric materials. The scope of the work is 62 pages: 57 pictures, 1 table, 7 appendixes are included, 25 sources of literature were referred to in this work.

Web services provide means to computerize e-business processes. To be able to satisfy business requirements web services must be developed rapidly and in high quality. Code generation techniques are frequently employed. In such context, verification of web service models emerges as a relevant issue: model verification makes it easier to detect and remove errors of system specification at the early stages of software development cycle. Available model verification tools require transformation of the objective model into complex formal notations, supported by the tool. It would be convenient to implement model verification directly in a CASE tool. This thesis describes a method for checking web service models based on verification of UML state machines. Conceptual algorithms for checking state machine’s safety criteria: reachability, completeness and consistency are provided. These algorithms, implemented in CASE tools could help to ensure the correctness and consistency of behavioral models. Also, a state machine template for composite web services is presented. Template complements state machine with transitions representing unsuccessful scenarios. Designer is freed from necessity to repeat reoccurring unsuccessful transitions for every event. This template is useful for automatic code generation.

At the moment social exclusion is a topical problem in a whole Europe. That’s why innovative decisions are prompted for social exclusive group of people in order to facilitate their integration process into the labour market. The stepping-stone of this work is e-advisor for choosing possibilities within social isolation environment. This e-advisor is created in accordance with artificial neural network and considering to individual person’s features give suggestions for the most suitable professions. Also in this work is presented disease diagnostic model, which is defined by artificial neural network.

Baigiamajame magistro darbe nagrinėjamos decentralizuoto (paskirstytojo) generavimo ir atsinaujinančių energijos išteklių panaudojimo sprendimai, aprūpinant pastatą įvairia energija – šiluma, vėsa, karštu vandeniu, elektra. Energija aprūpinama panaudojant tokius įrenginius – kogeneratorių, kompresorinę ir absorbcinę šaldymo mašinas, saulės kolektorius, dujinį katilą. Apibūdinami pasirinkti įrenginiai, jų veikimo principai, savybės, atskleidžiami jų privalumai ir trūkumai. Parengiamos trys alternatyvių variantų principinės energijos sistemų schemos, suformuotos iš minėtų įrenginių derinių. Pristatomi šių alternatyvių įvairios eneregijos gaminimo variantų galios ir energijos kiekių rodikliai. Parenkamas optimalus naujų technologijų derinys. Alternatyvių variantų ekonominis pagrįstumas įvertinamas, parenkant optimalų energijos generatorių derinį atsižvelgiant į jų bendrą atsiperkamumą. Apibendrinus teorines žinias ir gautus skaičiavimo rezultatus, pateikiamos baigiamojo darbo išvados ir pasiūlymai. Darbą sudaro 6 dalys: įvadas, teorin�� dalis, analizinė dalis, ekonominė dalis, išvados ir pasiūlymai, literatūros sąrašas. Darbo apimtis – 61 psl. teksto be priedų, 34 iliustr., 11 lent., 46 literatūros šaltiniai. Atskirai pridedami darbo priedai. / Solutions of decentralized (distributed) production and application of renewable energy sources in the case of different energy - like heating, cooling, hot water, electricity - supply for a building were analyzed in the final master thesis work. Energy supply sources are cogenerator, compressor and absorption cooling machines, solar collectors, gas boiler. Selected devices, their principles of work, characteristics, their advantages and disadvantages were described. Three schemes of principal energy system alternative were described, using combinations of devices mentioned above. Power and energy amount indexes of different energy generating alternatives were specified. The optimal combinations of new technologies were selected. After the optimal combination of energy generating system was done, economical validity of alternatives were estimated taking into account their total payback time. After theory and received results were summarized, the conclusions and suggestions were presented in the end of the final master work. Work consists of 6 parts: introduction, theory, analysis part, economical part, conclusions and suggestions, literature source. Size of Work: 61 pages of text excluding the appendixes, 34 pictures, 11 tables, 46 literature sources. Appendixes of the work are attached separately.

Neuroninė kompiuterio sąsaja – tai alternatyvus būdas valdyti kompiuterį nenaudojant rankų. Ji gali būti apibrėžta, kaip komunikavimo sistema, kuri leidžia valdyti kompiuterį ar kitą skaitmeninį įrenginį, naudojant nervinės kilmės fiziologinius signalus. Pagrindinė neuroninės kompiuterio sąsajos taikymo sritis yra neįgaliesiems skirti įrenginiai. Tai ne tik specifiniai įrenginiai, tokie, kaip galūnių protezai, tačiau ir kompiuteriai su papildoma aparatine ir programine įranga, kuri leidžia žmonėms, nevaldantiems rankų, valdyti kompiuterį. Taip pat išmanieji invalido vežimėliai, kuriuos galima vairuoti nenaudojant rankų judesių. Šiame darbe analizuojama neuroninė kompiuterio sąsaja, skirta vežimėlio tipo roboto valdymui. Pateikiama mūsų sukurta neuroninės kompiuterio sąsajos sistema, gebanti nuskaityti žmogaus EEG ir galvos raumenų EMG signalus, juos apdoroti, klasifikuoti ir jų pagalba valdyti vežimėlio tipo robotą. Taip pat pateikiamas trijų komandų vežimėlio tipo roboto valdymo per galvos paviršinio EMG signalo lygį metodas. Pateikiami roboto valdymo taikant šį metodą tikslumo eksperimentai ir jų rezultatai. / Neural computer interface is alternative way to control computer without hands. It is defined as a communication system which allows user control computer or any other digital device using neural breed physiological signal. The main application of neural computer interface is various devices for people with disabilities. For example, electronic prosthetic limbs, PC‘s with additional hardware and software which allows people with motor disabilities to control PC or intelligent wheelchairs. In this work we are analyzing neural computer interface applied for robot control. The author presents neural computer interface system which allows to read EEG and head surface EMG signals, pre-process the signals, classify the signals and control Arduino 4WD robot. We also propose approach to control robot with head surface EMG signal amplitude using 3 control commands. Robot control research using proposed approach is presented.

Šis magistrinis darbas aprašo plačiausiai naudojamus dirbtinio intelekto metodus ir galimybes juos taikyti kredito rizikos, kuri yra viena svarbiausių sričių bankininkystėje ir finansuose, vertinime. Pagrindinė problema yra rizikos, atsirandančios kreditoriui išduodant kreditą tam tikram individui ar bendrovei, vertinimas, naudojant įvairius matematinius, statistinius ar kitus metodus. Ši rizika atsiranda tada, kai skolininkas negali laiku grąžinti skolos kreditoriui, kas reiškia papildomus nuostolius. Ji gali pasireikšti, priklausomai nuo skolininko tipo (individas, bendrovė ar užsienio vyriausybė) bei finansinio instrumento tipo ar su juo atliekamo veiksmo (skolos teikimas, finansinių derivatyvų tranzakcijos ir kt.), todėl finansinės institucijos jos įvertinimui bei valdymui naudoja įvairius metodus nuo vertinimo balais bei skirtingų faktorių, tokių kaip valdymo bei veiklos strategijos bei politika, įvertinimo iki klasifikavimo pagal įvairius kriterijus, naudojant modernius ir sudėtingus metodus, tiek matematinius, tiek dirbtinio intelekto. Ši sritis plačiai tiriama ir daug naujų metodų bei sprendimų pastoviai randama. Šio darbo tyrimas sukoncentruotas į atraminių vektorių mašinų (angl.Support Vector Machines, sutr. SVM) metodų, kuris yra viena populiariausių dirbtinio intelekto bei mašininio mokymo metodų ir kurio efektyvumas daugeliu atveju įrodytas. Šiuo tyrimo tikslas yra ištirti galimybes pritaikyti SVM metodą čia aprašomai problemai bei realizuoti sistemą, naudojančią... [toliau žr. visą tekstą] / This master work describes the most widely used artificial intelligence methods and the possibilities to apply them in credit risk evaluation which is one of the most important fields in banking and in finance. The main problem here is to evaluate the risk arising when a creditor gives a credit to a particular individual or an enterprise, using various mathematical, statistical or other methods and techniques. This risk arises when the debtor isn’t able to pay for the loan to the creditor in time which means additional loss. It can appear in many forms depending on the type of debtor (individ-ual, enterprise, government of an abroad country) and type of financial instrument or action that is done with it (giving of a loan, transactions of financial derivatives, etc.), this is the reason why fi-nancial institutions and for it’s evaluation and management use various different methodologies which comprise a lot of methods and techniques from credit scoring (evaluating by a particular formula, usually linear) and evaluating different factors, like management and business strategies or policies, to classification by various criterions by using modern and sophisticated methods, either algebraic, either artificial intelligence and machine learning. This field is widely researched and many new techniques are being found. The research here is concentrated mainly on Support Vector Machines (abbr. SVM) which is one of the most popular artificial intelligence and machine learning... [to full text]