Science and Technology - Bachelor's theses. Kuni 2024

Permanent URI for this collectionhttps://hdl.handle.net/10062/63912

Browse

Browsing Science and Technology - Bachelor's theses. Kuni 2024 by Subject "AI"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Creating an Explainable AI Tool for First Impression Enhancement in Job Interviews
    (Tartu Ülikool, 2024) Gruzdeva, Dariia; Anbarjafari, Gholamreza, juhendaja; Aktas, Kadir, juhendaja; Tartu Ülikool. Loodus- ja täppisteaduste valdkond; Tartu Ülikool. Tehnoloogiainstituut
    In the world of job interviews, first impression plays a big role in candidate selection. However, current Human Resources (HR) technology tends to lack tools that can both provide candidates with meaningful feedback on their first impression and offer transparent, actionable advice for performance improvement. This thesis introduces an explainable artificial intelligence (AI) tool designed to provide advice to candidates for improving their first impressions during job interviews. The proposed tool uses the Big Five personality traits for evaluating and improving job candidates’ interview performances. The thesis focuses on demonstrating the potential of such a tool to provide automated, yet specialized feedback to candidates. The validation of this tool’s effectiveness is showcased through a series of experiments. It was observed that candidates exhibited enhanced performance after engaging with the tool. The findings suggest that this AI tool holds practical value, indicating a promising direction for future integration into HR software platforms. Such integration would not only augment the functionality of these platforms but also advance the goal of improving job interview outcomes through informed data-driven feedback. Further development and refinement are envisioned to fully realize the potential of this tool in professional settings, paving the way for an innovation in HR technology where first impressions are not just evaluated, but systematically improved.
  • Thumbnail Image
    Item
    Smart Traffic Control Using Optimised Convolutional Neural Network
    (Tartu Ülikool, 2019) Surrage Reis, Mateus; Anbarjafari, Gholamreza
    In English: The state-of-the-art in image object detection is in convolutional neural networks, which is a computationally expensive base to build on. To run accurate detection in an embedded device, additional optimization is required if there is a need to run it real-time on each frame of a video. This thesis details work done in the development of a smart pedestrian crosswalk: an Internet of Things enabled embedded platform for traffic control. By fine-tuning an individual neural network for each SPC post, it was possible to significantly boost accuracy in a fast, low-accuracy CNN. This was accomplished by taking advantage of the low variation in possible input images, being drawn from only 3 cameras per post. The improvement was from 33.1% mAP in general context images and 80 classes to 60.7% mAP on solely traffic images and seven traffic-relevant classes. Eesti keeles: Uusimad objekti tuvastus meetodid kasutavad oma töös konvuleerivaid närvivõrke, mis arvutuslikust küljest on ressursiahned. Täpsete tuvastusmudelite jooksutamine manussüsteemides vajab palju optimeerimist, eriti kui seade peab toimima reaalajas. Käesolev töö kirjeldab targa ülekäiguraja teemärgi loomist: nutiseade, mis on mõeldud liikluse juhtimiseks. Seadistades iga SPC posti eraldi närvivõrku, oli võimalik märkimisväärselt tõsta kiire ja ebatäpse närvivõrgu selgust. See saavutati kasutades ära kolmest kaamerast tulevate sisendpiltide minimaalset varieeruvust. Algoritmi täpsust parandati 80 klassilise üldnärvivõrgu 33.1% mAP pealt 60.7% mAP peale, rakendades ainult liiklusega seotud pilte koos seitsme erineva teemakohase klassiga.