Doctor of Philosophy (PhD), Wright State University, 2013, Computer Science and Engineering PhD

A sensor network serves as a vital source for collecting raw sensory data. Sensor data are later processed, analyzed, visualized, and reasoned over with the help of several decision making tools. A decision making process can be disastrously misled by a small portion of anomalous sensor readings. Therefore, there has been a vast demand for mechanisms that identify and then eliminate such anomalies in order to ensure the quality, integrity, and/or trustworthiness of the raw sensory data before they can even be interpreted. Prior to identifying anomalies, it is essential to understand the various anomalous behaviors prevalent in a sensor network deployment. Therefore, we begin this work by providing a comprehensive study of anomalies that exist in a sensor network deployment, or are likely to exist in future deployments. After this thorough systematic analysis, we identify those anomalies that, in fact, hinder the quality and/or trustworthiness of the collected sensor data. One approach towards the reduction of the negative impact of misleading sensor readings is to perform off-line analysis after storing a large amount of sensor data into a centralized database. To this end, in this work, we propose an off-line abnormal node detection mechanism rooted in machine learning and data mining. Our proposed mechanism achieves high detection accuracy with low false positives. The major disadvantage of a centralized architecture is the tremendous amount of energy wasted while communicating the sensor readings. Therefore, we further propose an on-line distributed anomaly detection framework that is capable of accurately and rapidly identifying data-centric anomalies in-network, while at the same time maintaining a low energy profile. Unlike previous approaches, our proposed framework utilizes a very small amount of data memory through on-line extraction of few statistical features over the sensor data stream. In addition, previous detection mechanisms leverage sensor (open full item for complete abstract)

Committee: Bin Wang Ph.D. (Advisor); Yong Pei Ph.D. (Committee Member); Keke Chen Ph.D. (Committee Member); Shu Schiller Ph.D. (Committee Member) Subjects: Computer Engineering; Computer Science

Doctor of Philosophy, Case Western Reserve University, 2024, Physics

In this thesis, we examine a few facets of the interplay between symmetry and topology in condensed matter and high energy physics. A particular focus is on anomalies, which are violations of classical symmetries at the quantum level. While an anomaly associated with a background field can lead to novel physical phenomena, a gauge anomaly present in a gauge theory would render the theory inconsistent. We will see the implications of both cases in the context of topological semimetals and dark matter models. We begin with the study of a nonlinear Hall effect in Weyl semimetals, which is a consequence of the chiral anomaly in the presence of external electromagnetic fields. This chiral anomaly induced nonlinear Hall (CNH) effect also relies on the nontrivial band topology of Weyl semimetals. Based on the semiclassical Boltzmann approach and a low-energy Weyl Hamiltonian, we show that a nonvanishing CNH effect requires an asymmetric Fermi surface about the Γ point. One way to achieve this is to introduce tilting to the Weyl cones and we analyze the cases of type-I and type-II Weyl semimetals in detail. If a pair of Weyl cones are tilted in opposite directions, additional symmetries such as time-reversal may be broken to create a relative energy shift between the two Weyl points, such that an asymmetric Fermi surface is generated. Then we discuss the spin-charge conversion process in class-I topological Dirac semimetals, which possess a pair of Dirac points on a rotation axis. When an external magnetic field is absent, a pure spin current will be generated in response to an applied electric field due to the intrinsic spin Hall effect. We argue that the anisotropic electric tunability is intimately tied to the topological nature of the Dirac semimetal. Upon the application of a magnetic field, the Dirac semimetal can be driven into a Weyl semimetal phase and thus, charge Hall current will be induced by the anomalous Hall effect. Additionally, unconventional spin Ha (open full item for complete abstract)

Committee: Shulei Zhang (Advisor); Matthew Willard (Committee Member); Xuan Gao (Committee Member); Walter Lambrecht (Committee Member) Subjects: Condensed Matter Physics; Particle Physics; Physics; Theoretical Physics

Doctor of Philosophy, The Ohio State University, 2014, Computer Science and Engineering

Abduction, or inference to the best explanation, is, plausibly, part of commonsense reasoning, and a means by which a cognitive system may arrive at estimates of its world from observational and other evidence. We take this "world estimate" to be the cognitive system's beliefs. Since such reasoning is fallible, and world estimates will sometimes contain errors, an abductive reasoning system might improve its performance if it has a way to engage in belief revision when new evidence, or further reasoning, indicates the existence of a problem. In this study, we develop, implement, and experimentally validate a metareasoning system that monitors and attempts to correct beliefs established by the base-level abductive reasoning system. We first identify that the presence of an anomaly, which we define as an observation or other evidence that cannot plausibly and consistently be explained, as a signal that the cognitive system's world estimate might be incorrect or, alternatively, that the unexplainable datum is noise. The metareasoning system responds to the presence of anomalies by asking exactly that question: which anomalies are due to mistakes in the world estimate, and warrant specific belief revisions, and which anomalies are due to noise, and should not instigate belief revisions? Various considerations regarding the nature of the anomalies and the system's reasoning history are brought to bear to answer this question. Fundamentally, we see the metareasoning question ("what explains these anomalies: mistaken beliefs, or noise?") as structurally similar to the cognitive system's original question, "what explains these observations?" Thus, the metareasoning system is an abductive reasoning system, just like the base-level system. The anomalies constitute meta-evidence which may be explained by meta-hypotheses. These meta-hypotheses describe the various kinds of causes of anomalies and specify particular belief revisions in order to resolve the anomalies. The (open full item for complete abstract)

Committee: John Josephson Dr. (Advisor); Balakrishnan Chandrasekaran Prof. (Committee Member); Neil Tennant Prof. (Committee Member) Subjects: Artificial Intelligence; Computer Science

Master of Science, The Ohio State University, 2008, Graduate School

Committee: Not Provided (Other) Subjects:

Doctor of Philosophy (Ph.D.), University of Dayton, 2024, Engineering

Anomaly detection is a common application of machine learning. Out-of-distribution (OOD) detection in particular is a semi-supervised anomaly detection technique where the detection method is trained only on the inlier (in-distribution) samples---unlike the fully supervised variant, the distribution of the outlier samples are never explicitly modeled in OOD detection tasks. In this work, we design a novel GAN-based OOD detection network specifically designed to protect a cyber-physical signal systems from novel Trojan malware called non-control data (NCD) attack that evades conventional malware detection techniques. Inspired in part by the classical locally most powerful (LMP) test in statistical inferences, the proposed LMP-GAN trains the OOD detector (discriminator) by generating OOD samples that are aimed at making maximal alteration to the inlier samples while evading detection. We experimentally compare the results to the state-of-the-art anomaly detection methods to demonstrate the benefits and the appropriateness of the LMP-GAN OOD detector.

Committee: Keigo Hirakawa (Committee Chair); Raul Ordóñez (Committee Member); Temesgen Kebede (Committee Member); David Kapp (Committee Member) Subjects: Computer Engineering; Electrical Engineering; Engineering

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

Anomaly Detection in Irregular Time Series is an under-explored topic, especially in the healthcare domain. An example of this is weight entry errors. Erroneous weight records pose significant challenges to healthcare data quality, impacting clinical decision-making and patient safety. Existing studies primarily utilize rule-based methods, achieving an Area Under the Receiver Operating Characteristic Curve (AUROC) ranging from 0.546 to 0.620. This thesis introduces a two-module method, employing bi-directional Long Short-Term Memory (bi-LSTM) with Attention Mechanism, for the prospective detection of anomalous weight entries in electronic health records. The proposed method consists of a predictor and a classifier module, both leveraging bi-LSTM and Attention Mechanism. The predictor module learns the normal pattern of weight changes, and the classifier module identifies anomalous weight entries. The performance of both modules was evaluated, exhibiting a clear superiority over other methods in distinguishing normal from anomalous data points. Notably, the proposed approach achieved an AUROC of 0.986 and a precision of 9.28%, significantly outperforming other methods when calibrated for a similar sensitivity. This study contributes to the field of entry error detection in healthcare data, offering a promising solution for real-time anomaly detection in electronic health records.

Committee: Raj Bhatnagar Ph.D. (Committee Chair); Danny T. Y. Wu PhD (Committee Member); Vikram Ravindra Ph.D. (Committee Member) Subjects: Computer Science

MS, University of Cincinnati, 2024, Medicine: Genetic Counseling

Objectives Significant gaps exist in the understanding of the presentation of genetic conditions across the lifespan, particularly during the prenatal period. This study aimed to describe the limitations of prenatal phenotyping by detailing the differences between prenatal and postnatal evaluations of neonates with genetic conditions. Methods We conducted a retrospective chart review of neonates with genetic diagnoses who previously received a detailed prenatal phenotype evaluation by fetal ultrasound, MRI, and echocardiogram at the Cincinnati Children's Fetal Care Center (CCFCC) between July 2018 and October 2022. Details of the prenatal and postnatal phenotypes were collected using Human Phenotype Ontology (HPO) terms to compare findings between the time points. Results Between July 2018 and October 2022, there were 85 neonates with genetic diagnoses who were prenatally evaluated in the CCFCC; these patients either received diagnoses prenatally (n=38), postnatally (n=45), or differing diagnoses before and after birth (n=2). The number of HPO terms significantly increased after postnatal evaluation (mean: 8.45) compared to what was identified prenatally at time of referral (mean: 3.45) (p<0.001) and during CCFCC evaluation (mean: 4.41) (p<0.001). There was a significant increase in the number of anomalies noted postnatally in most body systems compared to what was observed prenatally, including the musculoskeletal, nervous, genitourinary, head and neck, and respiratory systems. Conclusions There is a significant increase in phenotypic information in most body systems that becomes available as a fetus grows and after a child is born. Thus, fetuses with anomalies should be evaluated at multiple time points during prenatal life and after birth to ensure comprehensive phenotype information is available, particularly when a genetic etiology is suspected since most genetic testing and interpretation is phenotype driven. Awareness of bod (open full item for complete abstract)

Committee: Melanie Myers Ph.D. (Committee Chair); Leandra Tolusso M.S. (Committee Member); Daniel Swarr (Committee Member); Hua He M.S. (Committee Member); Kimberly Widmeyer (formerly Lewis) MS (Committee Member) Subjects: Genetics

Doctor of Philosophy, The Ohio State University, 2024, Mathematics

Bershadsky-Cecotti-Ooguri-Vafa higher genus B-model for the mirror symmetry conjectures a set of partial differential equations for Calabi-Yau threefolds, called holomorphic anomaly equations. Yamaguchi-Yau approach to holomorphic anomaly equations predicts that the Gromov-Witten potential lies in a certain polynomial ring with finite generators. This polynomiality prediction is referred to as finite generation property. Moreover, the Yamaguchi-Yau approach foresees that holomorphic anomaly equations can be reinterpreted as partial derivatives with respect to the generators of this ring. In recent years, mathematicians proved the finite generation property and holomorphic anomaly equations for certain three-dimensional Calabi-Yau geometries. In this thesis, we prove a finite generation result and holomorphic anomaly equations for the quotient stack [C^n/Z_n] for n greater than equal to 3. In other words, we show that phenomena predicted only for dimension three can also occur in any higher dimensions n greater than equal to 3. These results are beyond the consideration of physicists. To achieve the main theorems, we detail the cohomological field theory (CohFT) structure of the Gromov-Witten theory of [C^n/Z_n]. The main tools used in the proofs are the Givental-Teleman classification of the semisimple CohFTs and an extensive study of the genus-zero Gromov-Witten theory of [C^n/Z_n]. We provide a recipe for the Gromov-Witten potential of [C^n/Z_n] as a sum over graphs and perform a detailed analysis of this combinatorial data to obtain the main theorems. This thesis is based on the first part of a two-part joint work with Hsian-Hua Tseng.

Committee: David E. Anderson (Committee Member); Hsian-Hua Tseng (Advisor); James W. Cogdell (Committee Member) Subjects: Mathematics

Master of Arts (MA), Ohio University, 2024, History (Arts and Sciences)

This paper examines the antislavery stance of Catholic Archbishop of Cincinnati John Baptist Purcell and his brother, Father Edward Purcell, during the American Civil War. Purcell is an anomaly in that he advocated for the immediate end of slavery when most prominent Catholics did not. This study situates Purcell in state, national, Catholic, political, and social contexts, and shows how Purcell's thoughts on slavery developed in the antebellum and Civil War years. Purcell developed a distinctly Catholic antislavery position that drew from Catholic theology and experience. He received much criticism from other prominent Catholic persons and publications for his stance. This study examines the debates between Purcell and his critics and discusses their impact on the ecclesial unity of the Catholic Church in the United States.

Committee: Brian Schoen (Advisor); T. David Curp (Committee Member); Mariana Dantas (Committee Member) Subjects: American History; Clergy; Religious History

Master of Science, University of Toledo, 2023, Engineering (Computer Science)

Anomaly detection in power grids has become a significant challenge in recent years. The heterogeneous nature and integration of different smart grid appliances make it difficult to detect system faults or energy thefts leading to substantial cumulative losses over long periods. However, implementing the anomaly detection mechanism at every node in the grid network can be costly. Therefore, it is crucial to optimize the anomaly detection technique to not only detect local anomalies but also those further down the network. By doing so, we can ensure minimal resource usage and maximum reliability. In this study, we investigate anomaly detection capabilities at various levels in the distribution power system. We utilize Recurrent Neural Networks (RNNs) for anomaly detection and evaluate their performance compared to other machine learning techniques. The power grid analyzed in this research is a Digital Twin - a digital replica of a real-world power grid modeled using Gridlab-D and Helics. To ensure accurate simulation behavior and simulate with real consumption data and voltage properties. This paper presents two aspects of the study: building the Digital Twin and conducting anomaly detection in the Digital Twin Simulation at various grid levels.

Committee: Ahmad Y Javaid (Committee Chair); Weiqing Sun (Committee Co-Chair); Raghav Khanna (Committee Member) Subjects: Computer Engineering; Electrical Engineering

Master of Science (MS), Wright State University, 2023, Computer Science

The Industrial Internet of Things (IIoT) refers to a set of smart devices, i.e., actuators, detectors, smart sensors, and autonomous systems connected throughout the Internet to help achieve the purpose of various industrial applications. Unfortunately, IIoT applications are increasingly integrated into insecure physical environments leading to greater exposure to new cyber and physical system attacks. In the current IIoT security realm, effective anomaly detection is crucial for ensuring the integrity and reliability of critical infrastructure. Traditional security solutions may not apply to IIoT due to new dimensions, including extreme energy constraints in IIoT devices. Deep learning (DL) techniques like Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Long Short-Term Memory (LSTM) have been the focus of recent research to increase the precision and effectiveness of anomaly identification. This Thesis initially investigates a unique hybrid DL-enabled approach that provide the needed security analysis before successful attacks are launched against IIoT infrastructure. For that, different hybrid models are developed, trained, tested, and validated using Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), Short-Term Memory (LSTM), Autoencoder, and XGBoost algorithms. Experimental results show that the proposed XGBoost ML model exhibits the highest performance, as compared to other models, and excels across multiple metrics, including recall, precision, F1-score, and false alarm rate (FAR). The results also show that hybrid CNN+GRU model is closely behind, which exhibited strong performance in accurately detecting anomalies in encrypted IoT traffic. Specifically, Our experimental results show that the developed hybrid CNN+GRU model outperforms the others, achieving an accuracy of 94.94%, a recall of 92.29%, a precision of 98.49%, an F1 score of 95.24%, and a low false alarm rate of 0.001. However, it is (open full item for complete abstract)

Committee: Fathi Amsaad Ph.D. (Advisor); Lingwei Chen Ph.D. (Committee Member); Michael L. Raymer Ph.D. (Committee Member); Anton Netchaev Ph.D. (Committee Member) Subjects: Computer Science

PHD, Kent State University, 2023, College of Arts and Sciences / Department of Physics

Heavy Fermion materials are a class of correlated electron materials that are best known for their partially filled 4-f and 5-f electron orbitals. These partially filled electron orbitals cause the formation of local magnetic moments within many of these materials which can lead to a vast array of interesting interaction with the conduction electrons. These interactions often manifest themselves as interesting physical phenomena, such as superconductivity, Fermi liquid/non-Fermi liquid behavior, magnetic ordering, and quantum criticality. In this work, we report on heat capacity measurements for a group of "1-2-20 cage compounds", and magnetoresistivity measurements for a samarium doped cerium based superconductor. Motivated to ascertain a better understanding of the electronic structure of these cage compounds, we first investigated multiple praseodymium and cerium based 1-2-20 cage compounds through heat capacity measurements down to 0.4 K and in magnetic fields up to 14 T. This analysis illuminated the ground state of the PrNi2Cd20 and PrPd2Cd20 materials to be non-Kramers doublet states, while for CeNi2Cd20 and CePd2Cd20, the ground state was a Kramers doublet. Further investigation into the cerium based compounds indicated that the lack of magnetic order normally seen in cerium based heavy fermions could potentially be attributed to this ground state driving a minimal Ruderman-Kasuya-Kittel-Yosida (RKKY) interaction strength in the material. We also analyzed samarium doped CeCoIn5, motivated to further explore the quantum critical behavior of this material and how it interacts with magnetism. Resistivity measurements in Ce1-xSmxCoIn5 display a clear onset of the Kondo effect within the material, evidenced by a local resistivity minimum. A closer inspection of the resistivity in this material shows that it can be expressed as a superposition of two portions, one positive and one negative. By separating the resistivity in this way, we can more closely exam (open full item for complete abstract)

Committee: Carmen Almasan (Advisor); Almut Schroeder (Committee Member); Songping Huang (Committee Member); Gokarna Sharma (Committee Member); John Portman (Committee Member) Subjects: Physics

Master of Science (MS), Wright State University, 2023, Computer Science

Most of today's time series data contain anomalies and multiple seasonalities, and accurate anomaly detection in these data is critical to almost any type of business. However, most mainstream forecasting models used for anomaly detection can only incorporate one or no seasonal component into their forecasts and cannot capture every known seasonal pattern in time series data. In this thesis, we propose a new multi-seasonal forecasting model for anomaly detection in time series data that extends the popular Seasonal Autoregressive Integrated Moving Average (SARIMA) model. Our model, named multi-SARIMA, utilizes a time series dataset's multiple pre-determined seasonal trends to increase anomaly detection accuracy even more than the original SARIMA model. Our experimental results demonstrate the higher accuracy of multi-SARIMA when multiple seasonalities are present than most models with one or no seasonal component, although with more processing time.

Committee: Soon M. Chung Ph.D. (Advisor); Vincent A. Schmidt Ph.D. (Committee Member); Nikolaos Bourbakis Ph.D. (Committee Member) Subjects: Computer Science; Information Science

Master of Science (MS), Bowling Green State University, 2023, Geology

This study evaluates the potential for mineral prospectivity mapping (MPM) within the Kerkesha area, southwestern Eritrea using remote sensing and geochemical data analysis. The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote sensing data was used for mapping zones of hydrothermal alteration, while assessment of geologic structures is based on automated extraction of lineaments from a digital elevation model. Integration of these alteration and structural dataset with surface geochemical data were used in identifying pathfinder elements associated with Au-Cu-Zn mineralization as well as evaluating and delineating anomalous mineralization regions in this relatively underexplored region of Arabia Nubia Shield (ANS). Specifically, the modeling approach for the extraction and the interpretation of mineralization-related spectral footprints uses selective principal component analysis (SPCA), while the lineament features, which were extracted from different digital terrain models, were integrated with the soil geochemical data and modeled by principal component analysis (PCA). The results reveal a northeast-southwest trend of lineaments, delineate zones of hydrothermal alteration which indicate presence of multi-deposit type mineralization, and identify pathfinder elements. In addition, Au-Cu-Zn anomalous zones are extracted by one class support vector machine (OCSVM) and performances of such classification is validated by Kruskal-Wallis and Pearson's Chi-square tests. The results show significance in differences between the anomalous and non-anomalous zones and existence of a relationship between known mineral deposits and predicted anomalies. The proposed MPM shows promising results for robust automated delineation and understanding of mineralization processes.

Committee: Peter Gorsevski Ph. D. (Committee Chair); Kurt Panter Ph. D. (Committee Member); John Farver Ph. D. (Committee Member) Subjects: Geochemistry; Geographic Information Science; Geology

Master of Computer Science (M.C.S.), University of Dayton, 2022, Computer Science

Variational autoencoders (VAE) have recently become one of the most interesting developments in deep learning, as they take input data (e.g., images or text), learn its latent space, and then generate new similar and smooth data. The ability of discovering the latent space and creating new data makes VAEs powerful generative models, having applications in dimensionality reduction, data reconstruction, text automatic generation, art design, unsupervised clustering, semi-supervised classification, anomaly/outlier detection, and so on. Classic VAEs consider a Gaussian latent space, which does not allow for more complex representations. Gumbel-Softmax VAEs are an interesting extension, which provides practical solutions to implement the reparameterization trick for sampling a one-hot vector from a categorical distribution. During training, Gumbel-Softmax VAE needs to rely on softmax temperature tau, which guides the annealing process for categorical latent variables. Prior work simply decreases the temperature by a fixed factor and ignores the impact of the starting value and the active range of the temperature. We find that the temperature directly determines the performance of training. We present a novel parallel structure for VAEs, which combines two symmetric VAEs with different updating mechanics for the temperature and adjusts it at each training epoch based on the loss from these two VAEs. We show that our model offers a better performance than the original Gumbel-Softmax VAEs and can be used for data reconstruction, anomaly detection, and renovation of the imperfect with relatively lower distortion and noises.

Committee: Zhongmei Yao (Committee Chair); Luan V Nguyen (Committee Member); Xin Chen (Committee Member) Subjects: Computer Science

Master of Science (MS), Wright State University, 2021, Computer Science

The additive manufacturing (AM) field is striving to identify anomalies in laser powder bed fusion (LPBF) using multi-sensor in-process monitoring paired with machine learning (ML). In-process monitoring can reveal the presence of anomalies but creating a ML classifier requires labeled data. The present work approaches this problem by printing hundreds of Inconel-718 coupons with different processing parameters to capture a wide range of process monitoring imagery with multiple sensor types. Afterwards, the process monitoring images are encoded into feature vectors and clustered to isolate groups in each sensor modality. Four texture representations were learned by training two convolutional neural network texture classifiers on two general texture datasets for clustering comparison. The results demonstrate unsupervised texture-driven clustering can isolate roughness categories and process anomalies in each sensor modality. These groups can be labeled by a field expert and potentially be used for defect characterization in process monitoring.

Committee: Tanvi Banerjee Ph.D. (Advisor); Thomas Wischgoll Ph.D. (Committee Member); John Middendorf Ph.D. (Committee Member) Subjects: Computer Science; Materials Science

MA, Kent State University, 2021, College of Arts and Sciences / Department of Geography

The Sundarbans mangrove forest, one of the world's largest of its kind situated at the southwest of Bangladesh (approximately 60%), plays a vital role in safeguarding the country from the wrath of tropical cyclones and other disaster events. It is known to act as a vegetative shield to protect cyclonic wind's initial threat during any tropical cyclone towards Bangladesh. During Sidr (November 15, 2007), the second-largest cyclone in Bangladesh since 1877, it is estimated that the Sundarbans lost 30% of its plant habitat while upwards of 15% of the forest sustained severe damage. To manage the natural resources of the Sundarbans after disturbance, proper study regarding the impact and post-disturbance recovery of the forests is an immediate requirement. Most of the literature has focused on change in land cover types, which can help investigate the overall impact. However, the question of how long it takes these forests to recover is still relatively unexplored. This study used a pixel-based approach using MODIS (MOD09Q1.006 Terra Surface Reflectance 8-Day Global 250m product) to explore the impact of Sidr and further recovery of the Sundarbans. State QA Bitmask was used to mask out the clouds, cloud shadows, and water from the images using Google Earth Engine (GEE) to ensure the quality of pixels. A specific threshold level was determined to collect the clear sky observations only. Plant productivity anomalies were used to understand the change in vegetation condition related to cyclone Sidr. Season based impact analysis was performed using a known reference period to determine the deviation from normal growth condition. I found that the east side of the Sundarbans's was severely impacted, with a total of 2,261 sq. km. (approx.) being negatively impacted during the dry season immediately after Sidr. This area of the Sundarbans took approximately 3 years (2007 to 2010) to recover from the damage. This study is reproducible and rapid assessment for cyclone impact on (open full item for complete abstract)

Committee: Timothy Assal (Advisor); Emariana Widner (Committee Member); He Yin (Committee Member) Subjects: Geography; Remote Sensing

Master of Science (M.S.), University of Dayton, 2021, Computer Science

Automobile companies are focused on moving to connected, smart vehicles which it relates not only to privacy and usual security concerns, but to the safety of drivers and passengers. This matter shines the light on the need of building systems that can detect anomalies and zero-day attack for smart vehicles. The objective of this thesis is to develop an online learning in-vehicle anomaly detection system on neuromorphic Intel's chip and build a cost-cutting and high-speed tester to measure real memristor device properties. The entire thesis work is divided into three tasks. Task 1 shows an offline learning converted Autoencoder-based model to spiking neural network for in-vehicle cyber-attack detection running on Loihi Chip, this work has been published [44]. Task 2 introduces an online learning anomaly detection system that can detect anomalies for car hacking identification using Intel's Loihi low power device which can also be applied to many other tasks, such as fault detection, and financial data processing. Task 3 examines a built an FPGA-based tester for memristor device characterization, the typical approach is to use an analog tester which can be extremely expensive.

Committee: Tarek Taha Ph.D. (Committee Chair); Chris Yakopcic Ph.D. (Committee Member) Subjects: Computer Engineering; Electrical Engineering

MS, University of Cincinnati, 2021, Engineering and Applied Science: Computer Science

Detecting anomalies in a given data set has been a vital task always with various applications in the areas of healthcare, banking, security and law enforcement. While there have been numerous methods and algorithms being developed in the past for anomaly detection, the technique of biclustering numerical data with the help of Triadic Concept Analysis (TCA) as an extension of FCA (Formal Concept Analysis) for ternary relations have started surfacing only recently. We have used this idea along with a very efficient algorithm called as 'TRIMAX Biclustering Algorithm' to find out anomalous biclusters in our data set for a given 'Theta' parameter. This Theta parameter is the condition under which a given node-attribute pair is identied as being similar. The technique of biclustering helps in overcoming the limitation of standard clustering techniques where distance function producing partitions of objects takes into consideration all attributes as this method may be ineffective or difficult to interpret. A Bicluster shows a strong association between a subset of objects and a subset of attributes in a numerical object/attribute data set up which when combined with the statistical concept of Z-Score helps in finding anomalous biclusters in a given data set. This method is flexible and can be scaled to an n-dimensional numerical data set. We go a step further to verify whether the identied biclusters are persistent or not with the change in the 'Theta' parameter. Finally, we present three real-world applications of graph-based anomaly detection of a varying domain, size, shape and density.

Committee: Raj Bhatnagar Ph.D. (Committee Chair); Yizong Cheng Ph.D. (Committee Member); Nan Niu Ph.D. (Committee Member) Subjects: Computer Science

Master of Science, Miami University, 2021, Computational Science and Engineering

This project seeks to investigate and apply anomaly detection algorithms for a wideband receiver, that will flag anomalous radar behaviors sent by some transmitter external to the receiver's system. Flagging these anomalies will indicate to the receiver system that the radar's behavior has been reprogrammed, knowledge which is important for determining optimal countermeasures. The programs developed have investigated several approaches to accomplish this. Firstly, clustering methods like DBSCAN can group the observed pulses into distinct classes, reducing the problem to finding disruptions in patterns of numerical labels. Semi-supervised techniques like Hidden Markov Models and Long Short-Term Memories can be applied to learn these patterns for normal behavior and flag anomalies where the patterns are broken. Lastly, an unsupervised technique based on cross-correlations takes an alternative approach of flagging all the different behaviors in a sequence, without any initial training. Simulation results on test data demonstrate the functionality of these techniques, which are offered as potential suggestions for implementation in a real system.

Committee: Chi-Hao Cheng Ph.D. (Advisor); Dmitriy Garmatyuk Ph.D. (Committee Member); Mark Scott Ph.D. (Committee Member) Subjects: Computer Engineering; Computer Science; Electrical Engineering; Remote Sensing