My research optimizes three lightweight cryptographic algorithms—AES-256, ChaCha20, and Speck—for enhanced performance and security in IoT medical devices. By analyzing these algorithms throughput, latency, and memory usage on an Arduino board and applying specific optimization techniques, I have improved these algorithms and extrapolated the results to diagnostic, monitoring, and wearable devices. The core focus is finding the optimal tradeoff between security and performance for each optimized algorithm. The less memory usage the algorithm takes up in the device, the greater the performance. However, this also leads to lesser security. Finding the optimal balance will reduce computational overhead, improve processing speed, and lower energy consumption, leading to faster data processing. I strongly believe that these improvements to the algorithms will significantly enhance the functionality, security, and reliability of IoT medical devices, improving patient outcomes and advancing healthcare technology as a whole.

Predictive maintenance (PdM) is an emerging approach in aviation aimed at enhancing safety and reducing operational costs by forecasting engine failures before they occur. This research explores the development of a predictive maintenance model for aircraft engines using Long Short-Term Memory (LSTM) networks for time-series analysis and anomaly detection algorithms, including Isolation Forest and Autoencoders. The model was trained and tested on real-world sensor data to predict engine performance and identify early signs of degradation. Results demonstrated high accuracy, with significant reductions in unscheduled maintenance events and operational disruptions. The integration of machine learning into maintenance operations offers a proactive, data-driven approach, improving reliability and safety while reducing costs. Despite challenges such as data quality and implementation complexity, the study underscores the potential of advanced predictive models to transform aviation maintenance practices. Future research should focus on integrating new sensor technologies, enhancing model precision, and expanding this approach to other critical aircraft systems.

This research investigates the fine-tuning of large language models, specifically GPT-3, to enhance predictive text and other functionalities in Augmentative and Alternative Communication (AAC) systems for users with speech and language impairments. Through domain-adaptive pretraining and multi-task learning, the GPT-3 model was tailored to the linguistic needs of AAC users, resulting in significant improvements in perplexity, keystroke savings, and communication rate. User feedback highlighted the model's enhanced accuracy, ease of use, and overall satisfaction, underscoring its potential to reduce the cognitive and physical effort associated with AAC communication. Despite challenges related to data scarcity, computational demands, and bias mitigation, the study demonstrates the promise of advanced language models in creating more personalized, efficient, and user-friendly AAC tools. The findings provide a foundation for future research aimed at further refining and expanding the capabilities of AAC technologies.

Optimizing neural network architectures presents significant challenges due to the vast search spaces and computational costs involved. This study explores the integration of evolutionary algorithms (EAs) and mathematical modeling techniques to enhance neural network optimization. We propose a novel framework combining EAs with dimensionality reduction, surrogate modeling, and hybrid optimization strategies to reduce computational complexity and improve performance. Our results demonstrate that the adapted EAs significantly increase accuracy and F1-scores while reducing the number of generations required for convergence. The hybrid approach, combining EAs with local search techniques, achieves superior performance and robustness across various datasets. These findings provide a foundational basis for future research in advanced optimization methods for neural networks.

Early detection of sepsis is crucial for timely intervention and improved patient outcomes. Traditional diagnostic methods often fail to identify sepsis in its initial stages, leading to delays in treatment. This study investigates the potential of machine learning techniques, particularly multilayer perceptron (MLP) models, for early sepsis prediction using physiological data from intensive care unit (ICU) patients. A large dataset comprising approximately 40,000 ICU patient records from two hospital systems was analyzed. Various machine learning algorithms were implemented and compared, with a focus on optimizing an MLP model for early sepsis detection. The MLP model was trained on physiological data collected up to six hours before the clinical manifestation of sepsis symptoms. The findings demonstrated that the MLP model outperformed traditional methods, accurately predicting sepsis onset up to six hours before clinical symptoms became apparent. The MLP model exhibited significant improvements in accuracy compared to conventional models used for sepsis diagnosis. The ability to predict sepsis development at an early stage holds immense clinical value. Early detection facilitated by the MLP model can potentially lead to prompt administration of appropriate treatments, thereby improving patient outcomes and reducing mortality rates associated with sepsis. Moreover, early identification of sepsis cases can optimize resource allocation and improve operational efficiency in critical care environments. This study highlights the efficacy of MLP models in leveraging physiological data for early sepsis prediction. The proposed approach offers a promising solution for enhancing sepsis management protocols, ultimately contributing to improved patient care and resource utilization in intensive care settings.

The rapid advancement of neural networks in various applications, from healthcare diagnostics to financial modeling, has significantly improved the accuracy and efficiency of decision-making processes. However, these models often operate as black boxes, providing little to no insight into how they arrive at specific predictions. This lack of interpretability presents a major barrier to their adoption in critical domains where trust, accountability, and transparency are paramount. This study aims to address this issue by developing a novel framework that integrates multiple Explainable AI (XAI) techniques to enhance the interpretability of neural networks. The proposed framework combines feature importance analysis, layer-wise relevance propagation (LRP), and visual explanation methods such as Gradient-weighted Class Activation Mapping (Grad-CAM). These techniques collectively offer a comprehensive view of the decision-making processes of neural networks, making them more transparent and understandable to stakeholders. Our experimental results demonstrate that the integrated XAI framework not only improves interpretability but also maintains high levels of accuracy, thereby bridging the gap between performance and transparency. This research provides a foundational basis for the deployment of interpretable neural networks in critical applications, ensuring that AI-driven decisions are both reliable and comprehensible.