IRTUM – Institutional Repository of the Technical University of Moldova

Browsing Colecția instituțională by Subject "machine learning"

Browsing Colecția instituțională by Subject "machine learning"

Sort by: Order: Results:

  • Applications of artificial intelligence for cryptographic and security purposes 
    CRETU, Cristian; SCHIPSCHI, Daniil; NEGAI, Marin (Universitatea Tehnică a Moldovei, 2023)
    The use of artificial intelligence (AI) in cryptography and security is a rapidly growing field. In security, AI is used to detect potential threats and weaknesses within a system by identifying "safe" versus "malicious" ...
  • Artificial Intelligence in healthcare 
    JOLONDCOVSCHI, Valentin (Universitatea Tehnică a Moldovei, 2023)
    The following article discusses the development, history, and importance of Artificial Intelligence in healthcare, in addition to an extra examination of some of the problems rising simultaneously. The history of Artificial ...
  • Automatic Detection of Arabicized Berber and Arabic Varieties 
    ADOUANE, Wafia; SEMMAR, Nasredine; JOHANSSON, Richard; BOBICEV, Victoria (The COLING 2016 Organizing Committee, 2016)
    Automatic Language Identification (ALI) is the detection of the natural language of an input text by a machine. It is the first necessary step to do any language-dependent natural language processing task. Various methods ...
  • Automatic microexpression detection. History and developments 
    SMOCVIN, Denis (Universitatea Tehnică a Moldovei, 2022)
    Emotions govern our life. Through facial expressions we can understand what other people feel. Microexpressions are a special kind of facial expressions that are hard to spot. Interest arises over the development of ...
  • Classification of Emotion Words in Russian and Romanian Languages 
    SOKOLOVA, Marina; BOBICEV, Victoria (Association for Computational Linguistics, 2009)
    This paper presents a machine learning study of affective words in Russian and Romanian languages. We tag the word affective meaning by one of the WordNet Affect six labels anger, disgust, fear, joy, sadness, surprise and ...
  • Designul unei aplicații de Data Mining pentru achiziționarea noilor clienți 
    POPA, Alina (Universitatea Tehnică a Moldovei, 2021)
    Clienții reprezintă cel mai important activ al unei organizații. Astfel, o companie trebuie să-și planifice și să utilizeze o strategie clară pentru gestionarea acestora. Pentru identificarea de noi clienți și extinderea ...
  • Effect of training data changing step and input vector excessive dimension of a neural network on approximation accuracy. Load calculation of a unstable communication line 
    PENIN, Alexandr; SIDORENKO, Anatolie (Technical University of Moldova, 2024)
    The machine and especially deep learning do not have a powerful mathematical platform and are based almost exclusively on engineering solutions. It is a practical discipline in which ideas are often proven empirically ...
  • An Effective and Robust Method for Short Text Classification 
    BOBICEV, Victoria; SOKOLOVA, Marina (The AAAI Press, Menlo Park, California, 2008)
    Classification of texts potentially containing a complex and specific terminology requires the use of learning methods that do not rely on extensive feature engineering. In this work we use prediction by partial matching ...
  • Exploring the debate on Artificial Intelligence: boon or bane 
    DAVID, Cătălina (Universitatea Tehnică a Moldovei, 2023)
    Today, we are living and breathing artificial intelligence. As we all clearly see, AI is interfering with all aspects of our lives; some may call it the backbone of our industry, education, and healthcare sectors. As AI ...
  • Hardware implementation of Hopfield-like neural networks: Quantitative analysis of FPGA approach 
    ZAPOROJAN, Sergiu; CARBUNE, Viorel; SLAVESCU, Radu Razvan (IEEE, 2021)
    This paper provides a rigorous analysis of FPGA implementation of Hopfield-like neural networks. The relationship between the hardware resources used to synthesize the data path and those used to provide network connections ...
  • Key concepts and approaches of Big Data analytics 
    IORDAN, Marius (Universitatea Tehnică a Moldovei, 2023)
    The growing volume and complexity of data generated by individuals and businesses have led to the emergence of big data analytics as a vital tool for gaining insights and making better decisions to keep today's data-ruled ...
  • Language-independent features for authorship attribution on Ukrainian texts 
    HLAVCHEVA, Yuliia; GLAVCHEV, Maksym; BOBICEV, Victoria; KANISHCHEVA, Olga (Taras Shevchenko National University of Kyiv, 2021)
    Authorship attribution is the natural language processing task of the author identification of an input text. The main goal of this task is to define the salient characteristics of documents that capture the author's writing ...
  • Maximizing a neural network's accuracy and boosting the learning process for detecting the absolute colour similarity based on the centroids of normal distributions 
    SCROB, Sergiu; LISNIC, Inga; LEAHU, Alexei (Universitatea de Stat din Moldova, 2021)
    Our aim is to demonstrate that the ANN is prone to converge faster and with a higher level of accuracy using training data where tuples of triplets also represents the centroids of those 12 colour classes, considering each ...
  • Net impact of large language models trained on code 
    GHERCIU, Pavel (Universitatea Tehnică a Moldovei, 2022)
    Natural language processing has seen many improvements in recent years, particularly driven by machine learning models such as OpenAI’s GPT-3. This paper aims to present the various language models, as well as OpenAI Codex, ...
  • Online recognition of mobile objects 
    CIORBA, Dina; LEȘCO, Andrei; DODI, Cristian-Dumitru; PLEȘCA, Anișoara-Ionela (Universitatea Tehnică a Moldovei, 2021)
    The system designed for the recognition of geometrical figures that are moving on a conveyor belt was developed by using the Canny edge detection algorithm, where the objects are identified with the maximum accuracy. The ...
  • Optical reservoir computing: prospects of using SUB-10 picosecond lasers 
    ALEXANDRU, Burlacu (Tehnica UTM, 2020)
    Training neural networks is hard. The industry is approaching the limits of siliconbased computing, both in terms of transistor size and chip dimensions. There are already examples of technologies that allow computations ...
  • Some aspects of deep representation learning on transformed EEG data 
    IAPĂSCURTĂ, Victor (Universitatea Tehnică a Moldovei, 2023)
    Visualizing high-dimensional datasets can be challenging. While it is possible to plot data in two or three dimensions to reveal the data's innate structure, analogous high-dimensional representations are significantly ...
  • What Goes Around Comes Around: Learning Sentiments in Online Medical Forums 
    BOBICEV, Victoria; SOKOLOVA, Marina; OAKES, Michael (Springer Nature Switzerland, 2015)
    It has been shown that online health-related discussions significantly influence the attitudes and behavioral intentions of the discussion participants. Although empirical evidence strongly supports the importance of ...

Search DSpace


Browse

My Account