Том 8

Permanent URI for this collection

https://ekmair.ukma.edu.ua/handle/123456789/38090

Browse

Now showing 1 - 7 of 7

Development of an iOS Application for Task Planning with Consideration of the User’s Emotional State
(2025) Piz, Mariana; Nahirna, Alla
The article focuses on the development of a digital tool designed to address the problem of decreased productivity caused by emotional exhaustion. The main objective of the study is to create an iOS application for task planning that takes into account the user’s emotional state, offers mindful breaks for emotional awareness and recovery, and provides analytics on emotional trends. The research includes a comparative analysis of existing software solutions in the areas of time management and mental well-being. During the development process, modern frameworks, tools, and architectural patterns for iOS development were analyzed. An adaptive planning algorithm was implemented, that takes into accountboth the user’s emotional feedback and the attributes of tasks. As a result of the research, a mobile application named Moodpace was developed using Swift, with SwiftUI for building the user interface, SwiftData for data persistence, and the MVVM architectural pattern to ensure maintainable code structure. During the development process, SwiftLint was used for static code analysis, and SwiftFormat was integrated for automatic code formatting. The app was localized into Ukrainian using String Catalog. The developed application is designed to help users manage their tasks while maintaining balance with their mental well-being. It is suitable for everyday use and especially beneficial for individuals with flexible schedules.
Energy Conservation for Autonomous Agents Using Reinforcement Learning
(2025) Beimuk, Volodymyr; Kuzmenko, Dmytro
Reinforcement learning (RL) has shown strong potential in autonomous racing for its adaptability to complex and dynamic driving environments. However, most research prioritizes performance metrics such as speed and lap time. Limited consideration is given to improving energy efficiency, despite its increasing importance in sustainable autonomous systems. This work investigates the capacity of RL agents to develop multi-objective driving strategies that balance lap time and fuel consumption by incorporating a fuel usage penalty into the reward function. To simulate realistic uncertainty, fuel usage is excluded from the observation space, forcing the agent to infer fuel consumption indirectly. Experiments are conducted using the Soft Actor-Critic algorithm in a high-fidelity racing simulator, Assetto Corsa, across multiple configurations of vehicles and tracks. We compare various penalty strengths against the non-penalized agent and evaluate fuel consumption, lap time, acceleration and braking profiles, gear usage, engine RPM, and steering behavior. Results show that mild to moderate penalties lead to significant fuel savings with minimal or no loss in lap time. Our findings highlight the viability of reward shaping for multi-objective optimization in autonomous racing and contribute to broader efforts in energy-aware RL for control tasks. Results and supplementary material are available on our project website.
Hybrid AI Model for Financial Market Prediction
(2025) Voitishyn, Mykyta; Kuzmenko, Dmytro
Financial time series modeling is increasingly complex due to volatility, unexpected breakouts, and the impact of external factors, such as macroeconomic indicators, investor sentiment, company fundamentals, and extreme shocks, like geopolitical events or market manipulations. This paper introduces a hybrid artificial intelligence framework that integrates traditional statistical methods, machine learning models, and Bayesian neural networks (BNNs) to improve predictive performance and uncertainty quantification in financial forecasting. The model leverages a variety of engineered features, including rolling statistics, technical indicators, anomaly scores, interpolated macroeconomic data, and transformer-based sentiment scores. A complete ablation study compares various architectures, including ARIMA, SARIMA, MLR, SNN, and BNN, across multiple prediction windows (1, 3, 5 days) and feature combinations. Results show that while linear models yield the lowest MSE for short-term predictions, they fail to capture non-linear dependencies and uncertainty. In contrast, BNNs offer more reliable mid-term predictions by estimating predictive distributions. The best BNN configuration (Normal distribution, constant variation, TanH activation, 1 hidden layer) achieved an MSE of 0.00022, confirming the advantage of uncertainty-adjusted modeling. Sentiment analysis and anomaly detection were especially impactful when combined with macroeconomic indicators, improving signal reliability and behavioral insight. Our findings highlight the importance of integrating diverse data sources and accounting for predictive uncertainty in financial applications. Additionally, the experiments revealed that compact network architectures often outperform deeper ones when paired with engineered features. All experiments were systematically tracked to ensure reproducibility and facilitate future model benchmarking.
Modern Approaches to Controllable Emotional Speech Synthesis
(2025) Ivashchenko, Dmytro; Marchenko, Oleksandr
The generation of emotionally expressive and controllable speech is one of the most dynamic and technically demanding areas in the intersection of artificial intelligence, natural language processing, and speech synthesis. Recent progress in emotional text-to-speech (TTS) systems has enabled increasingly natural and emotionally nuanced voice generation, shifting from early concatenative methods to advanced neural models. This review provides a structured overview of the state of the art in controllable emotional TTS, highlighting key architectural paradigms. A special focus is placed on emotional control mechanisms, including discrete emotional tagging with categorical or dimensional labels, reference-based control which conditions synthesis on prosodic or stylistic exemplars, and prompt-based techniques that leverage the capabilities of large language models for flexible and intuitive emotional specification. Despite substantial improvements in synthesis quality and emotional expressiveness, several critical challenges remain unresolved. These include the disentanglement of emotional, speaker, and prosodic features, the lack of standardized evaluation metrics for emotional clarity and naturalness, and the significant computational demands associated with training high-fidelity models. Furthermore, the scarcity of diverse and emotion-labeled speech data, especially for low-resource and morphologically rich languages, continues to limit the generalizability of current approaches. This review not only summarizes existing methods and their trade-offs but also outlines promising research directions, aiming to support the development of more robust, efficient, and emotionally expressive speech generation systems.
MorphoNAS-Bench: a Benchmark Suite for Morphogenetic Neural Network Generation
(2025) Medvid, Serhii
We present MorphoNAS-Bench, a benchmark and toolkit for neural architecture search (NAS) using a generative, developmentally inspired design space. Unlike current NAS benchmark datasets (NAS-Bench-101, NATS-Bench) that use static graph encodings of networks, in MorphoNAS-Bench networks are simple, compact genomes that drive morphogenetic development, allowing for a variety of richly defined, spatially embedded recurrent architectures that emerge through different forms of deterministic growth. The following local developmental rules are used in MorphoNAS to grow genomes: morphogen diffusion, cell division, differentiation, and axon guidance as key mechanisms. The seed benchmark dataset presented in this work consists of 1,000 genome-architecture pairs, taken from a pool of over 50,000 generation attempts using the following quality thresholds: a minimum 5 neurons, 3 edges, and 70% out-degree coverage. The dataset was constructed using Latin Hypercube Sampling (LHS) with orthogonal array design to ensure comprehensive parameter space coverage. The attempts were conducted using both fully stratified parameter sampling and a biologically inspired Genome.random() sampling method, ensuring a reasonable level of coverage of the search space while being plausible. Each sample includes detailed annotations of graph entropy, hierarchy scores, core-periphery structure, transitivity, reciprocity, and structural balance metrics. We share an analysis of the emergent properties like size, modularity, grouping, and efficiency, demonstrating that both generation strategies can produce structured networks that are rich in their nontriviality. The provided Python toolkit provides the means of investigation to test how genomes develop into neural networks, with associated structural analysis, framing MorphoNAS-Bench as a reproducible and biologically inspired testbed for any research studies exploring architecture diversity, evolution, and emergent structure in NAS.
Robustness of Neural Decision Trees to Noise in Input Data for Image Classification Tasks
(2025) Mokryi, Mykhailo; Shvai, Nadiia
Neural networks, particularly convolutional neural networks (CNNs), have demonstrated high effectiveness in image classification tasks. However, they are known to be vulnerable to input data perturbations and have weak interpretability due to their black-box nature. In contrast, traditional decision trees (DTs) provide transparent decision-making processes, but are limited to low-dimensional or tabular data, restricting their field of application in computer vision tasks such as image classification. To address this gap, a hybrid architecture known as Neural Decision Trees (NDTs) has emerged, combining strong generalization and learning capabilities of neural networks, with transparent hierarchical inference and interpretability of DTs. The article investigates the robustness of NDTs to noise in input data for image classification tasks. Despite the extensive studies covering the robustness of both CNNs and traditional DTs against various forms of input perturbations, the robustness of NDT models remains a largely underexplored area. This study provides two robust training methods to improve robustness: constant noise learning and incremental noise learning, originally developed for CNNs, but which can be effectively applied to NDT-based architectures and significantly improve the robustness to noisy images for models. These methods involve adding perturbed samples via a Gaussian blur during the training stage. The noisy test set consists of images perturbed by a Gaussian blur and is used to evaluate the robustness performance. A series of experiments were conducted on the CIFAR-10 dataset using the original training baseline and robust training methods. The results demonstrate that constant and incremental noise learning significantly improve the robustness of all tested NDT models to noisy images compared to their original training performance. While the ResNet18 baseline model demonstrates higher overall performance, the NDT models show comparable robustness improvements using the proposed robust training strategies. Constant noise learning offered an adjustable trade-off between performance on clean and noisy images, while incremental noise learning provided a more stable training process. The first method is considered preferable due to the simplicity of implementation. This study empirically confirms that NDT models can effectively use methods adapted from CNNs to improve their robustness against perturbations in input data. An NDT framework was developed to conduct training and validation using a standardized shared pipeline. It is available via the link: github.com/ MikhailoMokryy/NDTFramework.
Validating Architectural Hypotheses in Neural Decision Trees with Neural Architecture Search
(2025) Mykytyshyn, Artem; Shvai, Nadiia
This article introduces an automated and unbiased framework for validating architectural hypotheses for neural network models, with a particular focus on Neural Decision Trees (NDTs). The proposed methodology employs Neural Architecture Search (NAS) as an unbiased tool to explore architectural variations and empirically assess theoretical claims. To demonstrate this framework, we investigate a hypothesis found in the literature: that the complexity of decision nodes in NDTs decreases monotonically with tree depth. This assumption, initially motivated by the task of monocular depth estimation, suggests that deeper nodes in the tree require fewer parameters due to simpler split functions. To rigorously test this hypothesis, we conduct a series of NAS campaigns over the CIFAR-10 image and fully connected layers, while all other architectural components are held constant to isolate the effect of node depth. By applying Tree-structured Parzen Estimator (TPE)-based NAS and evaluating over 300 architectures, we quantify complexity metrics across tree levels and analyze their correlations using Spearman’s rank coefficient. The results provide no statistical or visual evidence supporting the hypothesized trend: node complexity does not decrease with depth. Instead, complexity remains nearly constant across levels, regardless of tree depth or search space size. These results suggest that assumptions derived from specific applications may not generalize to other domains, underscoring the importance of empirical validation and careful searchspace design. The presented framework may serve as a foundation for verifying other structural assumptions across various neural network families and applications.

Browse

Browsing Том 8 by Subject "article"

Results Per Page

Sort Options