Národní úložiště šedé literatury Nalezeno 18 záznamů.  1 - 10další  přejít na záznam: Hledání trvalo 0.00 vteřin. 
Development of Automated Emotion Recognition System through Voice using Python
Magerková, Tereza ; Malik, Aamir Saeed (oponent) ; Hussain, Yasir (vedoucí práce)
This work presents an in-depth investigation into the design and implementation of deep learning models for speech emotion recognition. It proposes a model based on a comprehensive review of existing techniques from the field. The model is trained and tested on large-scale emotion-labeled speech datasets. Experimental evaluations are conducted to assess the performance of the model in terms of accuracy, robustness, and generalization.
Analyzing a person’s handwriting for recognizing his/her emotional state
Chudárek, Aleš ; Matoušek, Jiří (oponent) ; Malik, Aamir Saeed (vedoucí práce)
Emotion recognition from handwriting is a challenging and interdisciplinary task that can provide insights into the psychological and emotional aspects of the writer. In this study, we developed and evaluated a machine learning model that can predict the emotional state of a writer from their handwriting samples. We utilized the EMOTHAW dataset, which consists of handwriting and drawing samples from subjects whose emotional states are measured by the DASS test, which gives a score for depression, anxiety, and stress and the CIU Handwritten database for verification and experimentation. We extracted a large number of features that are inspired by the standard graphology work, as well as features that are specific to online data. We used ANOVA to select statistically significant features and normalized the data using Z-Score, MinMax, IQR or Log. We reduced the dimensionality of the features using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA). We employed a meta approach Ensemble learning that seeks to reduce the errors of a single model by exploiting the diversity and complementarity of multiple models. The structure of our classifier is dependent on multiple arguments resulting in over 300,000 different configurations. We optimized arguments using argument freezing. We found the best classifiers for binary and trinary classification for each emotion, resulting in six optimal models. We evaluated our models using different metrics, such as accuracy, precision, recall, and F1-score. Our models reached adequate results in all metrics. In addition to finding the classifiers, this thesis explored the importance of each extracted feature, providing a sorted list of the most significant features used for emotion recognition from handwriting. We also enhanced the EMOTHAW database by identifying tasks that are more indicative of specific emotions, thereby reducing the need for a full task battery for emotional analysis.
Diagnosing anxiety and depression from brain electroencephalogram (EEG) signals
Osvald, Martin ; Jaroš, Marta (oponent) ; Malik, Aamir Saeed (vedoucí práce)
Mental disorders represent inevitable emotions in our society. These psychological states affect the cognitive, emotional and behavioural functioning of individuals. Common men- tal disorders fall into two main diagnostic categories: depressive disorders and anxiety disorders. The aim of this work is to find a new method for detecting whether a given patient suffers from anxiety or depression using EEG classification. In this work, we use a combination of genetic algorithms and models from deep learning.
Creating a Python-based Automated System for Recognizing Emotions from Facial Expressions.
Zima, Samuel ; Malik, Aamir Saeed (oponent) ; Hussain, Yasir (vedoucí práce)
This thesis examines facial expression recognition (FER) using deep learning by focusing on its application in devices with limited memory and computational resources. It begins by researching emotions and facial expressions from psychological, biological, and sociological perspectives. The core of this thesis involves the design and implementation of an automated FER system using the FER-2013 dataset. This system uses a customized SqueezeNet architecture enhanced with a simple bypass, dropout layers and batch normalization layers. This system achieves an accuracy of 66.37 % on the FER-2013 dataset. For comparative analysis, this model was compared with a customized VGG16 architecture which achieved an accuracy of 65.09 %. This thesis provides valuable insights into the development of smaller, more efficient machine learning models for FER which are usable in a wide range of devices, including low-performance CPUs and embedded devices.
Game Development for Assessment of Human Memory, Attention and Reflexes
Petrovskyi, Denys ; Hussain, Yasir (oponent) ; Malik, Aamir Saeed (vedoucí práce)
This thesis details the development of an Android application designed to simultaneously assess memory, attention and reflexes. The main goal was to create an interactive platform that not only engages users in cognitive tasks, but also allows them to track their performance over time through statistical analysis and progress graphs. Using the Flutter framework, the application offers a user-friendly and clear design, integrated with Firebase for efficient user data management and authentication. The project involved the development of a series of cognitive modules integrated into a single game that dynamically adjusts to the user's results, ensuring accurate assessments and user engagement. The user interface was designed to be intuitive, ensuring ease of use and accessibility. User test results show that the application successfully measures cognitive abilities and provides users with valuable feedback, thereby supporting continuous cognitive improvement. This work demonstrates the potential of gamified cognitive assessments in mobile applications, contributing to the fields of educational technology and cognitive psychology.
Electroencephalogram (EEG) and machine learning based classification of depression: unveiling hidden patterns for early detection
Jurkechová, Adriana ; Malik, Aamir Saeed (oponent) ; Zaheer, Muhammad Asad (vedoucí práce)
This work deals with the pre-processing EEG signals, extraction of the features and classifying depressed patients and healthy control group. For classification, 5 different machine learning models were considered and evaluated. Findings confirm results from prior research and show the importance of a large, diverse dataset. This work utilises a public dataset.
Cognitive Game Battery: Assessing and Identifying Deficits in Memory, Attention, Problem-Solving, and Decision-Making Skills
Češka, Ondřej ; Malik, Aamir Saeed (oponent) ; Hussain, Yasir (vedoucí práce)
The goal of this work is the non-invasive assessment of selected cognitive domains (attention, memory, decision-making) using a new mobile application developed for this purpose. Assessment of cognitive deficits is important for the prevention of neurocognitive disorders. Existing assessment tasks were analyzed and based on them a cognitive game battery consisting of 3 mobile games was successfully designed and implemented. The application is made for the Android platform and was developed in the Unity engine. A system for collecting and storing game data and their subsequent evaluation with the help of cloud availability was created and evaluated using data collection and findings of existing studies. The presented application brings a different perspective to the assessment of cognitive deficits, compares the user's achieved score with other players, and provides them with detailed feedback.
Detection of Anxiety from Brain Electroencephalogram (EEG) Signals
Marko, Július ; Shakil, Sadia (oponent) ; Malik, Aamir Saeed (vedoucí práce)
Anxiety affects human abilities, behavior, productivity, and quality of life. Anxiety keeps us safe as part of a system that helps to control and avert danger. However, this safety system can go wrong. When such impairment emerges, it can lead to depression and even suicide. This work aims to develop a novel method of anxiety detection from brain signals, in particular electroencephalography (EEG), a non-invasive and cost-effective screening method. The proposed method incorporates microstates, which were not previously utilized for anxiety detection. Additional features in the time and frequency domain are extracted. Finally, a machine learning classifier is trained and evaluated on these features, outperforming other existing methods.
Electroencephalogram (EEG) and machine learning-based classification of various stages of mental stress
Lapčíková, Tereza ; Malik, Aamir Saeed (oponent) ; Zaheer, Muhammad Asad (vedoucí práce)
This thesis deals with the recognition of various stress stages experienced by patients from electroencephalogram (EEG). Various Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) models classifying EEG into three classes – not stressed, moderate stressed, and very stressed were created. The process of implementing such a classifier consisted of data preparation, extraction, and finally, classification. This solution also implements augmentation of data. The highest accuracy achieved in this thesis was of 90 % using the SVM model. The best LSTM model was a three-layer LSTM and achieved classification accuracy of 70 %.
Emotion Recognition from Analysis of a Person’s Speech using Deep Learning
Galba, Šimon ; Kekely, Lukáš (oponent) ; Malik, Aamir Saeed (vedoucí práce)
This thesis deals with the analysis and implementation of a neural network for the purpose of recognizing emotions from human speech using deep learning. The thesis also focuses on tuning this network to achieve greater sensitivity to a specific emotion and explores the time and indirectly the financial requirements of this tuning. The inspiration for creating this work is the increasing integration of artificial intelligence in the fields of biology, healthcare, as well as psychology, and one of the goals is also to study the complexity of creating specific models of neural networks for purposes in these sciences, which should contribute to better accessibility of artificial intelligence models. The work is based on the implementation of the "AST: Audio Spectrogram Transformer" model, which is publicly available under the BSD 3-Clause License and utilizes methods that have been used so far for classification and recognition of images by converting an audio track into a spectrogram. The resulting values of weighted accuracy are as follows: 93.5% for the EMODB dataset, 92.8% for EMOVO, and 92.9% for the RAVDESS dataset.

Národní úložiště šedé literatury : Nalezeno 18 záznamů.   1 - 10další  přejít na záznam:
Chcete být upozorněni, pokud se objeví nové záznamy odpovídající tomuto dotazu?
Přihlásit se k odběru RSS.