Doctor of Philosophy (Ph.D.), Bowling Green State University, 2024, Statistics

Deep learning, neural network, has been penetrating into almost every corner of data analyses. With advantages on computing power and speed, adding more layers in a neural network analysis becomes a common practice to improve the prediction accuracy. However, over depleting information in the training dataset may consequently carry data noises into the learning process of neural network and result in over-fitting errors. Neural Network has been used to predict the future time series data. It had been claimed by several authors that the Neural Network (Recurrent Neural Network) can predict the time series data, although time series models have also been used to predict the future time series data. This dissertation is thus motivated to investigate the prediction performances of neural networks versus the conventional inference method of time series analysis. After introducing basic concepts and theoretical background of neural network and time series prediction in Chapter 1, Chapter 2 analyzes fundamental structure of time series, along with estimation, hypothesis testing, and prediction methods. Chapter 3 discusses details of computing algorithms and procedures in neural network with theoretical adjustment for time series prediction. In conjunction with terminologies and methodologies in the previous chapters, Chapter 4 directly compares the prediction results of neural networks and conventional time series for the squared error function. In terms of methodology assessment, the evaluation criterion plays a critical role. The performance of the existing neural network models for time series predictions has been observed. It has been experimentally observed that the time series predictions by time series models are better compared to the neural network models both computationally and theoretically. The conditions for the better performances of the Time Series Models over the Neural Network Models have been discovered. Theorems have also been pro (open full item for complete abstract)

Committee: John Chen Ph.D. (Committee Chair); Hanfeng Chen Ph.D. (Committee Member); Umar Islambekov Ph.D. (Committee Member); Brigid Burke Ph.D. (Other) Subjects: Applied Mathematics; Artificial Intelligence; Behavioral Sciences; Computer Science; Education Finance; Finance; Information Systems; Operations Research; Statistics

Master of Sciences (Engineering), Case Western Reserve University, 2024, EECS - Computer and Information Sciences

The clustering of single-cell RNA-sequencing data has been established as an important first step in single-cell gene expression data analysis for scientists to identify cell type based on RNA level expression. This is important because once a cell type has been identified, the phenotype association, as well as the spatiotemporal dynamics of specific cell types, can be characterized, which could lead to identifying cells associated with cancers and other diseases. However, the high-dimensionality of the data poses computational challenges, while drop-outs (genes that are not identified despite being expressed) hamper the reliability of inference. Since established knowledge on transcriptional regulatory networks provide information on the regulatory relationships between genes, we hypothesize that regulatory networks can help remedy missing data, while also reducing dimensionality. To test this hypothesis, we use a previously existing regulatory network, modern clustering methods, and network propagation together to help enhance clustering performance, which enhances accurate identification of cell types.

Committee: Mehmet Koyutürk (Advisor); Mehmet Koyutürk (Committee Chair); Jing Li (Committee Member); Yinghui Wu (Committee Member) Subjects: Bioinformatics; Computer Science; Information Science; Statistics

Doctor of Philosophy, Case Western Reserve University, 2023, EECS - Computer and Information Sciences

This dissertation presents a comprehensive approach to advancing proteomics and under-studied proteins in network biology, emphasizing the development of reliable algorithms, fair evaluation practices, and accessible computational tools. A key contribution of this work is the introduction of RoKAI, a novel algorithm that integrates multiple sources of functional information to infer kinase activity. By capturing coordinated changes in signaling pathways, RoKAI significantly improves kinase activity inference, facilitating the identification of dysregulated kinases in diseases. This enables deeper insights into cellular signaling networks, supporting targeted therapy development and expanding our understanding of disease mechanisms. To ensure fairness in algorithm evaluation, this research carefully examines potential biases arising from the under-representation of under-studied proteins and proposes strategies to mitigate these biases, promoting a more comprehensive evaluation and encouraging the discovery of novel findings. Additionally, this dissertation focuses on enhancing accessibility by developing user-friendly computational tools. The RoKAI web application provides a convenient and intuitive interface to perform RoKAI analysis. Moreover, RokaiXplorer web tool simplifies proteomic and phospho-proteomic data analysis for researchers without specialized expertise. It enables tasks such as normalization, statistical testing, pathway enrichment, provides interactive visualizations, while also offering researchers the ability to deploy their own data browsers, promoting the sharing of findings and fostering collaborations. Overall, this interdisciplinary research contributes to proteomics and network biology by providing robust algorithms, fair evaluation practices, and accessible tools. It lays the foundation for further advancements in the field, bringing us closer to uncovering new biomarkers and potential therapeutic targets in diseases like cancer, Alzheimer' (open full item for complete abstract)

Committee: Mehmet Koyutürk (Committee Chair); Mark Chance (Committee Member); Vincenzo Liberatore (Committee Member); Kevin Xu (Committee Member); Michael Lewicki (Committee Member) Subjects: Bioinformatics; Biomedical Research; Computer Science

Master of Science in Cyber Security (M.S.C.S.), Wright State University, 2023, Computer Science

Malware detection is a critical task in ensuring the security of computer systems. Due to a surge in malware and the malware program sophistication, machine learning methods have been developed to perform such a task with great success. To further learn structural semantics, Graph Neural Networks abbreviated as GNNs have emerged as a recent practice for malware detection by modeling the relationships between various components of a program as a graph, which deliver promising detection performance improvement. However, this line of research attends to individual programs while overlooking program interactions; also, these GNNs tend to perform feature aggregation from neighbors without considering any label information and significantly suffer from over-smoothing on node presentations. To address these issues, this thesis constructs a graph over program collection to capture the program relations and designs two enhanced graph convolutional network (GCN)architectures for malware detection. More specifically, the first proposed GCN model in-corporates label propagation into GCN to take advantage of label information for facilitating neighborhood aggregation, which is used to propagate labels from the labeled nodes to the unlabeled nodes; the second proposed GCN model introduces residual connections between the original node features and the node representations produced by GCN layer to enhance the flow of information through the network and address over-smoothing is-sue. The experimental results after substantial experiments show that the proposed models outperform the baseline GCN and classic machine learning methods for malware detection, which confirm their effectiveness in program representation learning using either label propagation or residual connections and malware detection using program graph. Furthermore, these models can be used for other graph-based tasks other than malware detection, demonstrating their versatility and promise.

Committee: Lingwei Chen Ph.D. (Advisor); Meilin Liu Ph.D. (Committee Member); Junjie Zhang Ph.D. (Committee Member) Subjects: Computer Science; Information Science

MS, University of Cincinnati, 2020, Engineering and Applied Science: Mechanical Engineering

Unmanned Aerial Vehicles (UAV) are gaining attention in the civilian domain with their numerous potential applications. This has been demonstrated recently in light of developments around the pandemic, where UAVs were used by law enforcement departments of various countries of the world. Multinational Corporations such as Mercedes Benz partnered with Matternet for drone-based deliveries in Switzerland. Ford recently filed a patent for a drone system that can be integrated with a car that could provide emergency services. UAVs rely very much on positional signals for navigation. Positional signals such as a global positioning system (GPS) are susceptible to an outage for periods ranging from one second to a minute. This work provides a novel approach by introducing an Artificial Neural Network (ANN) in the cases where there are long gaps in positional signal received by a UAV. During our prior research, similar problems were manifesting during bridge inspection during flights flown by the drones. Even in our experiments with indoor localization systems using `Decawave', we faced similar problems. Decawave comprises Ultra-Wide-band modules that use Positioning and Networking Stack (PANS), a software library, that implements the Two-Way-Ranging method for localization. In the proposed work, an ANN is trained on drone dynamics for a pre-traveled path. Then this pre-trained network, during flight, uses back-propagation to update its weights/parameters in an online fashion, where-by it learns to “fill in” the GPS signal gaps by predicting the dynamics. In the event of a GPS Signal loss, this ANN, receiving the current state of the body as input, performs a forward propagation to predict the rigid body dynamics for the next state. The online learning capability ensures that this ANN's weights are updated to reflect changing dynamics arising from changes such as different payloads. The results highlight a comparative study between a drone that implements only Extended Kalm (open full item for complete abstract)

Committee: Manish Kumar Ph.D. (Committee Chair); Janet Jiaxiang Dong Ph.D. (Committee Member); David Thompson Ph.D. (Committee Member) Subjects: Mechanical Engineering

Master of Science in Electrical Engineering, University of Toledo, 2010, Electrical Engineering

The increasing need to design multiband tactical radio communication modems that will incorporate several waveforms has made the investigation of the performance of different tactical waveforms absolutely necessary. These different waveforms must also meet various demands in quality and nature of data. Range maximization, high data throughput, and power conservation requirements are usually not fulfilled by a single waveform. To effectively deliver tactical multimedia data including coded audio, text, video, map, and navigation information using radio, multiple choice of frequency bands exist. These include: HF, VHF and UHF. However, along with the effective delivery of quality data, the maximization of transmission range under hostile propagation environments – especially under terrain blockage in ground-to-ground (GTG) communication scenario - is of utmost importance. This thesis discusses the results of Link Budget Analysis (LBA) performed for the estimation of maximum delivery range of tactical radio waveforms using variety of data rates for three typically different waveforms – High Frequency Waveform (HFW), Very High Frequency Waveform (VHFW) and OFDM based Wideband Network Waveform (WNW). Center frequencies of 27 MHz, 60 MHz, and 500 MHz respectively were used for the simulations. Results show that HFW produces the longest range, followed by VHFW and the WNW – which delivered the highest data rate. Also, the amount of variation in propagation range that was noticed while parameters like center frequency, antenna height, antenna gain, transmitter power were varied were also computed.

Committee: Junghwan Kim PhD (Committee Chair); Lawrence Miller PhD (Committee Member); Ezzatollah Salari PhD (Committee Member) Subjects: Electrical Engineering