PHD, Kent State University, 2022, College of Arts and Sciences / Department of Computer Science

Recently, location-based social networks, that involve both social and spatial information, have received much attention in many real-world applications such as location-based services (LBS), map utilities, business planning, and so on. User's location is one of the most important components of user context that implies extensive knowledge about an individual's interests and behavior, thereby providing researchers with opportunities to better understand users in a social structure according to not only online user behavior but also the user mobility and activities in the physical world. In this dissertation, we have an initial study of query processing over spatial-social networks and propose suitable solutions of query processing over spatial-social networks by proposing new novel queries that are Community Search (CS), Group Planning (GP), and Community Detection (CD) over the spatial-social network settings. For each proposed query over spatial-social networks, we have designed effective pruning strategies to reduce the search space by filtering false alarms, proposed effective indexing mechanisms to facilitate the query processing, and develop efficient query answering algorithms via index traversals. Extensive experiments have been conducted to evaluate the efficiency and effectiveness of our proposed queries processing approaches.

PhD, University of Cincinnati, 2008, Engineering : Computer Science and Engineering

Wireless Mesh Networks (WMNs) have revolutionized provisioning of economical and broadband wireless internet service to the whole community of users. The self-configurable and self-healing ability of WMNs has encouraged their rapid proliferation, as adding a mesh router (MR) is as simple as plugging and turning on. The plug-and-play architecture of WMN, however paves way to malicious intruders. An attacker can raise several security concerns, like rogue routers, selfishness, and denial-of-service attacks. Unfortunately, current thrust of research in WMNs, is primarily focused on developing multi-path routing protocols; and security is very much in its infancy. Owing to the hierarchical architecture of WMNs, security issues are multi-dimensional. As mesh routers form the backbone of the network, it is critical to secure them from various attacks. In this dissertation we develop integrated security architecture to protect the mesh backbone. It is important to provide an end-to-end security for mesh clients and hence we design a novel authentication protocol for mutually authenticating mesh clients and mesh routers. The aim of this dissertation is to explore various issues that affect the performance and security of WMNs. We first examine the threat of an active attack like Denial of service attack on MRs and design a cache based throttle mechanism to control it. Next, we develop a MAC identifier based trace table to determine the precise source of a DoS attacker. We then evaluate the vulnerability of WMNs to passive attacks, like selfishness and propose an adaptive mechanism to penalize selfish MRs that discretely drop other's packets. In order to handle route disruption attacks like malicious route discovery, we design an intelligent Intrusion Detection System. Through extensive simulations, we evaluate effectiveness of our proposed solutions in mitigating these attacks. Finally, we design a light weight authentication protocol for mesh clients using inexpensive hash (open full item for complete abstract)

Master of Science, University of Toledo, 2022, Engineering (Computer Science)

Data from various disciplines, such as complex social, biological, and physical systems are naturally represented by networks. The stochastic block model (SBM) is one of the most widely used generative models for network data. Many continuous-time dynamic network models are built upon the same assumption as the SBM: edges or events between all pairs of nodes are conditionally independent given the block or community memberships. In this thesis, we propose two models: First, we introduce the multivariate community Hawkes (MULCH) model, an extremely flexible community-based model for continuous-time networks. Contrary to the SBM assumption which prevents them from reproducing higher-order motifs such as triangles that are commonly observed in real networks, MULCH introduces dependence between node pairs using structured multivariate Hawkes processes. We fit the model using a spectral clustering and likelihood-based local refinement procedure. We find that our proposed MULCH model is far more accurate than existing models both for predictive and generative tasks. Next, we propose the marked block Hawkes model (marked BHM), designed to model dynamic networks characterized by both timestamps and marks. The marked BHM replaces the univariate Hawkes process in the original BHM model with a marked Hawkes process to model such networks. We show that modeling both timestamps and marks improves community detection and predictive accuracy.

Master of Science in Engineering, University of Toledo, 2021, Engineering (Computer Science)

The advancement in data collection has resulted in unprecedented quantity and variety of network data with diverse applications. This thesis analyzes two such network settings. The first is a computed transplant compatibility network which has a bipartite representation. We conduct local network analysis on this network and attempt link prediction on missing compatibilities. We conclude that while the techniques we develop result in modest prediction accuracy, we are able to provide an overview of the network and demonstrate the absence of some network properties we may otherwise expect. The second analysis performed is conducted on social network data, one of the most common targets for network analysis. Data compiled from these networks are perfect for analyzing social trends. One such trend that this thesis aims to address is political homophily. Evidence of political homophily is well researched and indicates that people have a strong tendency to interact with others with similar political ideologies. Additionally, as links naturally form in a social network either through recommendations or indirect interaction, new links are very likely to reinforce communities. This serves to make social media more insulated and ultimately more polarizing. We aim to address this problem by providing link recommendations that will reduce network homophily. We propose several variants of common neighbor-based link prediction algorithms that aim to recommend links to users who are similar but also would decrease homophily. We demonstrate that acceptance of these recommendations can indeed reduce the homophily of the network, whereas acceptance of link recommendations from a standard Common Neighbors algorithm does not.

Doctor of Philosophy, The Ohio State University, 2021, Physics

Reservoir computing (RC) is a machine learning method especially well suited to solving physical problems, by using an internal dynamic system known as a 'reservoir'. Many systems are suitable for use as an internal reservoir. A common choice is an echo state network (ESN), a network with recurrent connections that gives the RC a memory which it uses to efficiently solve many time-domain problems such as forecasting chaotic systems and hidden state inference. However, constructing an ESN involves a large number of poorly- understood meta-parameters, and the properties that an ESN must have to solve these tasks well are largely unknown. In this dissertation, I explore what parts of an RC are absolutely necessary. I build ESNs that perform well at system forecasting despite an extremely simple internal network structure, without any recurrent connections at all, breaking one of the most common rules of ESN design. These simple reservoirs indicate that the role of the reservoir in the RC is only to remember a finite number of time-delays of the RCs input, and while a complicated network can achieve this, in many cases a simple one achieves this as well. I then build upon a recent proof of the equivalence between a specific ESN construction and the nonlinear vector auto-regression (NVAR) method with my collaborators. The NVAR is an RC boiled down to its most essential components, taking the necessary time- delay taps directly rather than relying on an internal dynamic reservoir. I demonstrate these RCs-without-reservoirs on a variety of classical RC problems, showing that in many cases an NVAR will perform as well or better than an RC despite the simpler method. I then conclude with an example problem that highlights a remaining unsolved issue in the application of NVARs, and then look to a possible future where NVARs may supplant RCs.

Doctor of Philosophy (PhD), Wright State University, 2020, Computer Science and Engineering PhD

Deep Neural Networks (DNNs) are powerful tools blossomed in a variety of successful real-life applications. While the performance of DNNs is outstanding, their opaque nature raises a growing concern in the community, causing suspicions on the reliability and trustworthiness of decisions made by DNNs. In order to release such concerns and towards building reliable deep learning systems, research efforts are actively made in diverse aspects such as model interpretation, model fairness and bias, adversarial attacks and defenses, and so on. In this dissertation, we focus on the research topic of DNN interpretations for visual intelligence, aiming to unfold the black-box and provide explanations for visual intelligence tasks in a human-understandable way. We first conduct a categorized literature review, systematically introducing the realm of explainable deep learning. Following the review, two specific problems are tackled, explanations of Convolutions Neural Networks (CNNs), which relates the CNN decisions with input concepts, and interpretability of multi-model interactions, where an explainable model is built to solve a visual inference task. Visualization techniques are leveraged to depict the intermediate hidden states of CNNs and attention mechanisms are utilized to build an instinct explainable model. Towards increasing the trustworthiness of DNNs, a certainty measurement for decisions is also proposed as an extensive exploration of this study. To show how the introduced techniques holistically realize a contribution to interpretable and reliable deep neural networks for visual intelligence, further experiments and analyses are conducted for visual entailment task at the end of this dissertation.

PhD, University of Cincinnati, 2017, Engineering and Applied Science: Computer Science and Engineering

A ubiquitous pervasive network incorporates today's Internet of Things/Internet of Everything Paradigm: Everything becomes smart with at least one microprocessor and a network interface. All these are under an umbrella of IoT/IoE paradigm where everything is network capable and connected. In most of the cases, these devices have multiple microprocessors and network interfaces at their disposal. In such a scenario, bringing every application to specific network on the same platform is critical, specifically for Sensor Networks, Cloud, WPANs and VANETs. While, enforcing and satisfying the requirements of CIA triad with non-repudiation universally is critical as this can solve multiple existing problems of ISM band exhaustion, leading to excessive collisions and contentions. Cooperative Interoperability also enables universal availability of data across all platforms which can be reliable and fully synchronized. Plug and play universal usability can be delivered. Such a network necessitates robust security and privacy protocols, spanning uniformly across all platforms. Once, reliable data access is made available, it leads to an accurate situation aware decision modeling. Simultaneous multiple channel usage can be exploited to maximize bandwidth otherwise unused. Optimizing Content delivery in hybrid mode which will be the major chunk of network traffic as predicted for near future of IoE. Now, such a proposed hybrid network does sound very complicated and hard to establish and maintain. However, this is the future of networks with huge leaps of technological advancement and ever dropping prices of hardware coupled with immensely improved capabilities, such a hybrid ubiquitous network can be designed and deployed in a realistic scenario. In this work, we go through not only looking into the issues of the large scale hybrid WMN, but also minutely discovering every possible scenario of direct mesh clients or sub-nets (VANET, Cloud or BAN) associated to it. Further, we pr (open full item for complete abstract)

Doctor of Philosophy, University of Akron, 2016, Electrical Engineering

The current explosion of information and demand for high speed data communication call for novel solutions to utilize the radio resources more efficiently. The cognitive communication paradigm aims to mitigate this spectrum crunch by exploiting unused resources that are allocated to the primary communications systems. The aim of this research is to employ the concept of cognition in wireless devices and combine it with three recently introduced wireless communication techniques namely, K-user multi-input multi-output (MIMO) interference networks, spatial modulation scheme and molecular communications. Firstly, the feasibility of cognitive radio (CR) is studied in the presence of a K-user MIMO interference channel as the primary network. Assuming that the primary interference network has unused spatial degrees of freedom, the sufficient condition on the number of antennas is investigated at the secondary transmitter under which the secondary system can communicate and then the secondary precoding and decoding matrices are derived to have zero interference leakage into the primary network. A fast sensing method based on the eigenvalue analysis of the received signal covariance matrix is proposed to determine the availability of spatial holes. Also, a fine sensing method is provided based on the generalized likelihood ratio test to decide the absence of individual primary streams. The second part of this research is relevant to the application of spatial modulation (SM) in overlay CR networks, in which the primary and secondary networks work concurrently over the same spectrum band. The CR transmitter assists the primary network as a relay to amplify-and-forward (AF) the transmitted symbols of the primary. The secondary transmitter retransmits the primary symbols in amplitude-phase modulation domain, while its own information is transmitted by the index of transmitting antenna. The performance of the optimal detectors in terms of the average symbol error rate (ASER) an (open full item for complete abstract)

Master of Science in Engineering, University of Toledo, 2013, Engineering (Computer Science)

Radon-222 and its parent Radium-226 are naturally occurring radioactive decay products of Uranium-238. The US Environmental Protection Agency (USEPA) attributes about 10 percent of lung cancer cases that is `around 21,000 deaths per year' in the United States, caused due to indoor radon. The USEPA has categorized Ohio as a Zone 1 state (i.e. the average indoor radon screening level greater than 4 picocuries per liter). In order to implement preventive measures, it is necessary to know radon concentration levels in all the zip codes of a geographic area. However, it is not possible to survey all the zip codes, owing to reasons such as inapproachability. In such places where radon data are unavailable, several interpolation techniques are used to estimate the radon concentrations. This thesis presents a comparison between recently developed interpolation techniques to new techniques such as Support Vector Regression (SVR), and Random Forest Regression (RFR). Recently developed interpolation techniques include Artificial Neural Network (ANN), Knowledge Based Neural Networks (KBNN), Correction-Based Artificial Neural Networks (CBNN) and the conventional interpolation techniques such as Kriging, Local Polynomial Interpolation (LPI), Global Polynomial Interpolation (GPI) and Radial Basis Function (RBF) using the K-fold cross validation method.

MS, University of Cincinnati, 2006, Engineering : Computer Engineering

A majority of group communication applications in cellular-based heterogeneous wireless setups entail secure data exchange. The problem can be effectively tackled if the underlying cellular infrastructure is used to provide an authentication backbone to the security associations. We propose a novel distributed ID based key exchange mechanism using shared polynomials in which the shares are generated by the communicating groups. Our idea employs a mechanism where the Base Stations (BSs) carry out an initial key generation by a polynomial in a distributed manner and then pass on the key material to the Mobile Stations (MSs). The multi-interface MSs can now securely communicate over interfaces other than cellular. The scheme incorporates symmetric polynomials, which are chosen by the BS acting as polynomial distributors. Simulations done to measure performance have shown encouraging results.

PhD, University of Cincinnati, 2006, Engineering : Computer Science and Engineering

One of the main challenges in next generation wireless networks is to integrate heterogeneous wireless technologies to provide seamless connectivity, with guaranteed Quality of Service (QoS), to mobile users “anytime, anywhere and with any device”. In this dissertation, we investigate the problem of integrating cellular networks and Wireless Local Area Networks (WLANs) with the multi-hop communication paradigm used in Mobile Ad hoc Networks (MANETs) to exploit all the connectivity alternatives available to different types of Mobile Stations (MSs). We propose an integrated architecture based on three basic functionalities, namely, topology discovery, gateway discovery, and link quality estimation. We combine these three functionalities into an integrated routing mechanism that exploits all connectivity alternatives available in a generic heterogeneous scenario. Then, we provide a simulation-based analysis of our architecture and integrated routing mechanism in different heterogeneous networking scenarios. Our results show improvements in network's capacity and coverage achieved by our architecture as compared to isolated networks. The results also highlight the importance of the link quality estimation in providing QoS to users, as well as indicate that multi-hop links can be exploited in a controlled network configuration, but the QoS in multi-hop routes cannot be always guaranteed. Furthermore, we address the problem of selecting the best connectivity opportunity for a given service type based on the applications' QoS requirements, as well as on the network condition and user mobility profile. We propose the Connectivity opportunity Selection Algorithm (CSA) that allows MSs to select the connectivity opportunity most appropriate for a given type of service and mobility profile. Furthermore, we describe how our proposed selection algorithm can be introduced into the IEEE 802.21 standard for Media Independent Handover services.

MS, University of Cincinnati, 2003, Engineering : Electrical Engineering

Large-scale sensor networks (LSSN's) are formed when very large numbers of miniaturized sensor nodes with wireless communication capability are deployed randomly over an extended region, e.g., scattered from the air or embedded in material. Systems such as smart matter, smart paint and smart dust imply the existence of LSSN's, but they can also be used in applications involving large geographical regions such as environmental monitoring or disaster relief. Our contention is that, given their scale and random structure, LSSN's should be treated as complex systems rather than as standard wireless networks. Approaches from wireless networks typically have difficulty scaling up to large numbers of nodes, especially when the nodes have limited capabilities and are deployed over a region much larger than their communication range. We explore how a system comprising of very large number of randomly distributed sensor nodes can organize itself to communicate information. To keep the system realistic, we assume that nodes in our system are unreliable, have limited energy resources and have minimal on-board computational capabilities. Our focus is on the efficient routing of messages in such a system, specifically on the network algorithms aspect, rather than on issues such as hardware, signal processing and communication. The goal is to develop a system that scales effectively and is robust to node failures. The approach we propose is to limit the usage of bandwidth and energy while tapping the inherent parallelism of simple flooding to achieve robustness. Simulation results show significant improvement in performance compared to simple flooding algorithms.

Doctor of Philosophy in Engineering, University of Toledo, 2012, Civil Engineering

The objective of this research was to develop and evaluate an integrated approach to model the occupant exposure to in-bus contaminants using the advanced methods of data mining and artificial intelligence. The research objective was accomplished by executing the following steps. Firstly, an experimental field program was implemented to develop a comprehensive one-year database of the hourly averaged in-bus air contaminants (carbon dioxide (CO2), carbon monoxide (CO), nitric oxide (NO), nitrogen dioxide (NO2), sulfur dioxide (SO2), 0.3-0.4 micrometer (¿¿¿¿m) sized particle numbers, 0.4-0.5 ¿¿¿¿m sized particle numbers, particulate matter (PM) concentrations less than 1.0 ¿¿¿¿m (PM1.0), PM concentrations less than 2.5 ¿¿¿¿m (PM2.5), and PM concentrations less than 10.0 ¿¿¿¿m (PM10.0)) and the independent variables (meteorological variables, time-related variables, indoor sources, on-road variables, ventilation settings, and ambient concentrations) that can affect indoor air quality (IAQ). Secondly, a novel approach to characterize in-bus air quality was developed with data mining techniques that incorporated the use of regression trees and the analysis of variance. Thirdly, a new approach to modeling in-bus air quality was established with the development of hybrid genetic algorithm based neural networks (or evolutionary neural networks) with input variables optimized from using the data mining techniques, referred to as the GART approach. Next, the prediction results from the GART approach were evaluated using a comprehensive set of newly developed IAQ operational performance measures. Finally, the occupant exposure to in-bus contaminants was determined by computing the time weighted average (TWA) and comparing them with the recommended IAQ guidelines. In-bus PM concentrations and sub-micron particle numbers were predominantly influenced by the month/season of the year. In-bus SO2 concentrations were mainly affected by indoor relative humidity (RH) and the month of (open full item for complete abstract)

MS, Kent State University, 2024, College of Arts and Sciences / Department of Computer Science

Cryptography, derived from the Greek word meaning "to hide information," involves techniques for converting readable plaintext into unreadable ciphertext through a process called encryption. Cryptography algorithms are broadly categorized into two types: symmetric key cryptography and asymmetric key cryptography. Symmetric key cryptography is further divided into block ciphers and stream ciphers. Block ciphers, based on their structure, can be classified into two main categories: Substitution-Permutation Networks (SPN) and Feistel Networks (FN). This research focuses on SPN-based block ciphers. In 1949[1], Claude Shannon introduced two fundamental operations required for a robust cryptosystem: substitution and permutation. Substitution, the core component of SPN-based cryptography, is implemented through substitution boxes (S-Boxes), where each element in the plaintext is mapped to another element to achieve nonlinearity and provide the confusion property crucial for security. With the rise of constrained devices, such as the Internet of Things (IoT), there is an increasing demand for lightweight symmetric-key algorithms. However, in many cases, the S-Box contributes the most to the hardware complexity and computational load compared to other linear components. This research addresses this challenge by designing and optimizing a lightweight cryptosystem suitable for resource-limited environments. The thesis makes two key contributions to the field of lightweight cryptography. The first contribution is the development of chaos-based S-Boxes tailored for devices with restricted computational capabilities. By leveraging chaotic maps, the proposed S-Boxes achieve a high degree of nonlinearity and security while maintaining a minimal computational and hardware footprint, making them ideal for IoT and other constrained devices. These chaos-based S-Boxes introduce dynamic, unpredictable substitution patterns that enhance resistance to cryptanalysis techniques such as l (open full item for complete abstract)

Master of Science, The Ohio State University, 2006, Graduate School

Master of Science in Mechanical Engineering (MSME), Wright State University, 2024, Mechanical Engineering

An approach for the architecture optimization of emulator embedded neural networks is proposed. While the emulator embedded neural network has been shown to provide accurate predictions with suitable emulators, there is still a challenge regarding how to select the optimal hyperparameters of network architectures, such as, the number of neurons, layers, types of activation functions, etc. The selection of hyperparameters greatly affects the performance of the neural network model training both in terms of accuracy and efficiency. To address this challenge, this study proposes an algorithm that tests a range of hyperparameters and selects the best performing set. The algorithm compares network architectures using average cross-validation error and architecture size. Additionally, the algorithm implements Bayesian optimization to accelerate the hyperparameter selection process and leverages a database of benchmark analytical problems to better define the hyperparameter search space. The proposed method is demonstrated using analytical examples, an aerospace fracture mechanics design study, and a representative aerospace vehicle design study. It was found that the proposed algorithm was able to successfully select well-performing architectures from within the chosen search spaces. In comparison to the popular grid search algorithm, it found architectures of similar sizes and performance while testing less than half of the total number of architectures. The proposed algorithm was able to successfully avoid large architectures when the accuracy benefits were minimal compared to smaller architectures, saving both time and computational efficiency. The potential benefits of the algorithm when applied to aerospace design application are an increased confidence in the selected architecture, identification of best fit architectures with less dependence on experts' knowledge and experience, and reduction in time and computational efficiency when selecting an architecture.

Master of Science, The Ohio State University, 2024, Environment and Natural Resources

Persistent harmful algal blooms (HABs) in the western Lake Erie basin (WLEB), caused by excessive phosphorus in agricultural runoff, negatively affect both human and ecological well-being. To combat increased phosphorous levels from agricultural land, the goal of reducing total phosphorus loading by 40% from 2008 levels is believed critical to substantially reduce the frequency and severity of HABs. To effectively manage nutrient loss in agriculture and achieve phosphorus reduction targets, widespread implementation of agricultural Best Management Practices (BMPs) in the WLEB is crucial. The United States primarily relies on incentive and outreach programs to encourage farmers to voluntarily adopt BMPs. However, despite decades of effort to increase farmers' use of conservation practices, adoption rates remain low and relatively static. Several researchers have recommended farmer-led peer learning as an alternative to traditional, hierarchical outreach programs. In such approaches, farmers deliver outreach to engage other farmers in adopting various conservation practices. Previous studies have examined the role of peer learning networks in promoting conservation actions. Generally, these studies find that the benefits of farmer-led networks include the opportunity for direct interaction and learning from those who have actual experience with conservation practices, building relationships with other farmers, the ability to observe other farmers' outcomes with the practices, and building confidence in the practices they are already using. However, prior research on the effectiveness of farmer-led peer learning has focused largely on informal learning networks for women agricultural landowners, or formalized farmer networks (e.g., where the farmers doing the engagement have formal roles and the interactions are structured by traditional partners). These studies also tend to focus on the effect of peer learning after a singular event (e.g., one day meeting, one perso (open full item for complete abstract)

PhD, University of Cincinnati, 2024, Engineering and Applied Science: Mechanical Engineering

This dissertation advances the field of structural damage identification by introducing innovative methodologies based on continuous wavelet transform (CWT) and physics-informed neural networks (PINNs). These methods significantly contribute to the theoretical framework of baseline-free damage identification, laying the foundation for accurate, real-time detection and assessment of damage, thereby enhancing the safety and longevity of engineering structures. A baseline-free damage identification method based on two-dimensional CWT (2D-CWT) is proposed for isotropic and homogeneous plates. An adaptive vanishing moments algorithm is proposed to adaptively determine the number of vanishing moments in Gaussian wavelets. The Teager energy operator (TEO) is applied to the modulus of the 2D-CWT, deriving an accumulative damage index based on the Teager energy. This method enhances the ability to identify and localize damage by suppressing global trends and intensifying local anomalies within flexural wavefields. Extensive numerical and experimental investigations on aluminum plates under various damage scenarios validate the effectiveness and robustness of this method. Further, a CWT-based damage identification method using proper orthogonal modes (POMs) of flexural wavefields is explored. This exploration includes the deployment of an adaptive truncation technique to select significant POMs for damage identification. By focusing on these significant POMs rather than entire flexural wavefields, the method enhances the efficiency of the adaptive vanishing moments algorithm. Numerical and experimental investigations of the proposed method are conducted on beams. Their results verified that the proposed method is accurate and noise-robust for identifying the location and extent of damage. A novel baseline-free damage identification method utilizing PINNs is introduced. The method involves training a PINN with a measured flexural wavefield from damaged pla (open full item for complete abstract)

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)

PhD, University of Cincinnati, 2023, Engineering and Applied Science: Computer Science and Engineering

Traditional drug discovery is costly and time-consuming. With the availability of large-scale molecular interaction networks, novel predictive modeling strategies have become vital to study the effect of drugs. Graphs are a powerful and flexible data structure in this regard. Biomedical graphs encompass the complex relationships between drugs, diseases, genes, and other micro/macroscopic effects of drugs. Hence, analyzing and modeling graphs can be valuable in identifying novel insights for drug discovery and its effects. Recently, deep learning research has made significant advances in image, speech, and natural language domains. The research in these fields has fostered progress in applying neural networks to graphs, referred to as graph neural networks (GNNs), for learning and identifying valuable hidden insights in graphs. While these GNNs are effective in learning representations, early research has focused primarily on optimizing GNNs for simple graph structures. Real-world graphs, however, tend to have complex characteristics such as heterogeneity, multi-modality, and combinatoriality. These complexities are particularly apparent in biomedical graphs, particularly in the areas of drug repurposing, virtual screening, and drug-drug interaction studies. This hinders the ability of GNNs to learn accurate representations and fully understand a drug's behavior within the human body. Furthermore, for most current methods, the interpretation of the inferred predictions has not been investigated in detail, leading to skepticism in their adoption, especially in biomedical and healthcare domains. The work in this thesis aims to enhance the capabilities of GNNs for complex networks by studying and generating hypotheses for drug discovery and drug-drug interaction studies in biological networks. To achieve this, GNNs have been investigated and improved with three specific aims. Aim 1 is to develop GNNs that take heterogeneous networks as input and use multi (open full item for complete abstract)