Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 19 of 19 for “"Long short-term memory (LSTM) networks"”.
-
A comparative analysis of machine learning models for forecasting JSE Stock Returns
… using monthly data from 2005 to 2021: neural networks, random forest, long short- term memory (LSTM) networks, and conventional linear regression. The explanatory variables comprise nine firm-specific financial metrics, motivated by prior research. The sample is divided into a training period …
-
USE OF LANGUAGE TECHNOLOGY TO IMPROVE MATCHING AND RETRIEVAL IN TRANSLATION MEMORY
Current Translation Memory (TM) tools lack semantic knowledge while matching. Most TM tools compute similarity at the string level, which does not take into account semantic aspects in matching. Therefore, semantically similar segments, which differ on the surface form, are often not retrieved. In …
-
Evaluating transformers as memory systems in reinforcement learning
Memory is an important component of effective learning systems and is crucial in non-Markovian as well as partially observable environments. In recent years, Long Short-Term Memory (LSTM) networks have been the dominant mechanism for providing memory in reinforcement learning, however, the success …
-
Analog On-chip Training and Inference with Non-volatile Memory Devices
As the demand for computation in neural networks continues to rise, conventional computing resources are increasingly constrained by their limited energy efficiency. One promising solution to this challenge is analog in-memory computing (AIMC), which enables efficient matrix-vector multiplications …
-
Analysis of bankruptcy prediction of shipping industry - Machine Learning Approach
… Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks. A comprehensive literature review and interviews with industry practitioners were conducted to refine the variables used in the models. These models predict bankruptcy across 1, 3, and 5-year horizons, with …
-
Predicting Passenger Demand and Optimizing Fleet Allocation: A Machine Learning Approach for Icelandic Tour Operators
… Neural Network, Support Vector Regression, and Long Short-Term Memory (LSTM) networks. An intelligent bus assignment system using a Best Fit greedy algorithm was developed to utilize these forecasts. The best performance was demonstrated by the LSTM model, with a Mean Absolute Error of 9.08 …
-
Improving Text Classification Using Graph-based Methods
… is challenging. Several studies employ Long Short- Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), but Graph Convolutional Networks (GCNs) have not yet been investigated for the task. Sequence- based models can successfully capture semantics in local consecutive …
-
eMARLIN: Addressing Coordination and Partial Observability in Distributed Reinforcement Learning for Traffic Signal Control
… like incorporating historical data sequences and Long Short-Term Memory (LSTM) networks are employed to mitigate these issues. Additionally, the integration of Transformer-based models into eMARLIN demonstrates further advancements in handling temporal information and enhancing coordination among …
-
Cloud and digital-twin enhanced thermal safety framework for e-mobility battery management systems
… However, frequent EV fires expose critical shortcomings in current battery management systems (BMS) and thermal controls. LIBs exhibit nonlinear characteristics sensitive to operating and environmental conditions, but existing BMS technologies rely solely on surface temperature measurements, …
-
Formation control of multiple robots under packet loss
… this problem, the thesis proposes the use of Long Short-Term Memory (LSTM) networks, which excel at retaining long-term dependencies, for predicting missing data during packet loss. A comparative analysis involving LSTM, Gated Recurrent Units (GRUs), Linear Interpolation Predictor (LIP), and …
-
BERT-Based Intrusion Detection System for RF Jamming Attacks in Vehicular Network
As vehicular networks continue to evolve toward increased connectivity and autonomy, they become more vulnerable to cybersecurity threats, particularly Radio Frequency (RF) jamming attacks that can severely disrupt communication systems. This thesis presents a comprehensive study on the application …
-
Time series analysis and machine learning studies of biophotovoltaic systems
… into mathematical mechanistic models. Here, Long Short-Term Memory (LSTM) networks were explored for their ability to replicate complex time-evolving phenomena without a priori knowledge. Results. Seasonal and trend decomposition using locally estimated scatterplot smoothing (STL) was first …
-
Onshore wind farm battery energy storage systems optimisation
… hybrid forecasting models that combine Long Short-Term Memory (LSTM) networks, Complementary Ensemble Empirical Mode Decomposition (CEEMD), and hybrid optimisation (ACO-GA-PSO) to attain accurate long-term predictions of wind energy variability. Lastly, the study reviews and applies a …
-
Applications of Data-Driven Learning Models in Fluid Mechanics: Solid-Fluid Multiphase Systems and Bat Flight
… learning models—including convolutional neural networks (CNNs) and graph neural networks (GNNs)—that incorporate both local particle neighborhood information and global suspension parameters. We demonstrate the effectiveness of these models in predicting particle-scale drag forces more …
-
Post-secondary Students' Travel Behavior through the Lens of Urban and Rural Contexts
… architectures Gated Recurrent Units (GRU), Long Short-Term Memory (LSTM) networks, and Transformers to capture sequential decision-making and nonlinear dependencies in activity type and departure time choices. The rural-focused mode choice analysis estimates both RP–SP multinomial logit …
-
Electric load forecasting with increased embedded renewable generation
… a number of load forecasting methodologies for short-term day-ahead load forecasting under these new conditions using data from the Northern Ireland (NI) and New York (NY) state power systems as case studies. <br/><br/>Motivation for the selection of key model structures, in particular the same …
-
Evolving and Proactive Risk Modelling in Underground Working Environments
… spaces. This thesis aims to address these shortcomings by presenting an environmental Digital Twin (DT) framework for evolving and proactive underground risk modelling that integrates real-time Internet of Things (IoT) sensor networks, advanced probabilistic modelling, and adaptive deep …
-
Secure Machine Learning Based RF Signal Classification for Wireless Systems
… Recent research shows that deep neural networks (DNNs) can identify the underlying waveform of an RF signal based on the in-phase/quadrature (I/Q) samples without decoding them. Our research starts with DNN designs in the context of spectrum sharing, focusing on Wi-Fi, LTE-LAA, and 5G …
-
SCIENTIFIC MACHINE LEARNING METHODS FOR REACTIVE-TRANSPORT AND THERMAL-TRANSPORT PROBLEMS
… for reactive-transport problems overcomes this shortcoming to improve prediction accuracy using available time-history data. The framework uses convolutional neural networks for capturing spatial patterns and long short-term memory networks for forecasting temporal variations in mixing. The …