The novelty of this dissertation is the optimization and acceleration of deep neural networks aimed at real-time predictions with minimal energy consumption. It consists of cross-layer optimization, output directed dynamic quantization, and opportunistic near-data computation for deep neural network acceleration. On two datasets (CIFAR-10 and CIFAR-100), the proposed deep neural network optimization and acceleration frameworks are tested using a variety of Convolutional neural networks (e.g., LeNet-5, VGG-16, GoogLeNet, DenseNet, ResNet). Experimental results are promising when compared to other state-of-the-art deep neural network acceleration efforts in the literature.

The original FlexiChain and its descendants are a revolutionary distributed ledger technology (DLT) for cyber-physical systems (CPS) and their embedded systems (ES). FlexiChain, a DLT implementation, uses cryptography, distributed ledgers, peer-to-peer communications, scalable networks, and consensus. FlexiChain facilitates data structure agreements. This thesis offers a Block Directed Acyclic Graph (BDAG) architecture to link blocks to their forerunners to speed up validation. These data blocks are securely linked. This dissertation introduces Proof of Rapid Authentication, a novel consensus algorithm. This innovative method uses a distributed file to safely store a unique identifier (UID) based on node attributes to verify two blocks faster. This study also addresses CPS hardware security. A system of interconnected, user-unique identifiers allows each block's history to be monitored. This maintains each transaction and the validators who checked the block to ensure trustworthiness and honesty. We constructed a digital version that stays in sync with the distributed ledger as all nodes are linked by a NodeChain. The ledger is distributed without compromising node autonomy. Moreover, FlexiChain Layer 0 distributed ledger is also introduced and can connect and validate Layer 1 blockchains. This project produced a DAG-based blockchain integration platform with hardware security. The results illustrate a practical technique …

This dissertation investigates computational models and methods to improve collaboration skills among students. The study targets pair programming, a popular collaborative learning practice in computer science education. This research led to the first machine learning models capable of detecting micromanagement, exclusive language, and other types of collaborative talk during pair programming. The investigation of computational models led to a novel method for adapting pretrained language models by first training them with a multi-task learning objective. I performed computational linguistic analysis of the types of interactions commonly seen in pair programming and obtained computationally tractable features to classify collaborative talk. In addition, I evaluated a novel metric utilized in evaluating the models in this dissertation. This metric is applicable in the areas of affective systems, formative feedback systems and the broader field of computer science. Lastly, I present a computational method, CollabAssist, for providing real-time feedback to improve collaboration. The empirical evaluation of CollabAssist demonstrated a statistically significant reduction in micromanagement during pair programming. Overall, this dissertation contributes to the development of better collaborative learning practices and facilitates greater student learning gains thereby improving students' computer science skills.

The goal of this thesis is to support the automated identification of accessibility in user reviews or bug reports, to help technology professionals prioritize their handling, and, thus, to create more inclusive apps. Particularly, we propose a model that takes as input accessibility user reviews or bug reports and learns their keyword-based features to make a classification decision, for a given review, on whether it is about accessibility or not. Our empirically driven study follows a mixture of qualitative and quantitative methods. We introduced models that can accurately identify accessibility reviews and bug reports and automate detecting them. Our models can automatically classify app reviews and bug reports as accessibility-related or not so developers can easily detect accessibility issues with their products and improve them to more accessible and inclusive apps utilizing the users' input. Our goal is to create a sustainable change by including a model in the developer's software maintenance pipeline and raising awareness of existing errors that hinder the accessibility of mobile apps, which is a pressing need. In light of our findings from the Blackboard case study, Blackboard and the course material are not easily accessible to deaf students and hard of hearing. Thus, deaf students …

Hateful content and offensive language are commonplace on social media platforms. Many surveys prove that high percentages of social media users experience online harassment. Previous efforts have been made to detect and remove online hate content automatically. However, removing users' content restricts free speech. A complementary strategy to address hateful content that does not interfere with free speech is to counter the hate with new content to divert the discourse away from the hate. In this dissertation, we complement the lack of previous work on counterhate arguments by analyzing and detecting them. Firstly, we study the relationships between hateful tweets and replies. Specifically, we analyze their fine-grained relationships by indicating whether the reply counters the hate, provides a justification, attacks the author of the tweet, or adds additional hate. The most obvious finding is that most replies generally agree with the hateful tweets; only 20% of them counter the hate. Secondly, we focus on the hate directed toward individuals and detect authentic counterhate arguments from online articles. We propose a methodology that assures the authenticity of the argument and its specificity to the individual of interest. We show that finding arguments in online articles is an efficient alternative compared to …

With increasing data and technology, multiple types of data from the same set of nodes have been generated. Since each data modality contains a unique aspect of the underlying mechanisms, multiple datatypes are integrated. In addition to multiple datatypes, networks are important to store information representing associations between entities such as genes of a protein-protein interaction network and authors of a citation network. Recently, some advanced approaches to graph-structured data leverage node associations and features simultaneously, called Graph Neural Network (GNN), but they have limitations for integrative approaches. The overall aim of this dissertation is to integrate multiple data modalities on graph-structured data to infer some context-specific gene regulation and predict outcomes of interest. To this end, first, we introduce a computational tool named CRINET to infer genome-wide competing endogenous RNA (ceRNA) networks. By integrating multiple data properly, we had a better understanding of gene regulatory circuitry addressing important drawbacks pertaining to ceRNA regulation. We tested CRINET on breast cancer data and found that ceRNA interactions and groups were significantly enriched in the cancer-related genes and processes. CRINET-inferred ceRNA groups supported the studies claiming the relation between immunotherapy and cancer. Second, we present SUPREME, a node classification framework, by comprehensively …

In this dissertation, I investigate the existing smart contract problems that limit cognitive abilities. I use Taylor's serious expansion, polynomial equation, and fraction-based computations to overcome the limitations of calculations in smart contracts. To prove the hypothesis, I use these mathematical models to compute complex operations of naive Bayes, linear regression, decision trees, and neural network algorithms on Ethereum public test networks. The smart contracts achieve 95\% prediction accuracy compared to traditional programming language models, proving the soundness of the numerical derivations. Many non-real-time applications can use our solution for trusted and secure prediction services.

In this dissertation, we address the problem of vagueness in traditional legal contracts by presenting novel methodologies that aid in the paradigm shift from traditional legal contracts to smart contracts. We discuss key enabling technologies that assist in converting the traditional natural language legal contract, which is full of vague words, phrases, and sentences to the blockchain-based precise smart contract, including metrics evaluation during our conversion experiment. To address the challenge of this contract-transformation process, we propose four novel proof-of-concept approaches that take vagueness and different possible interpretations into significant consideration, where we experiment with popular vendors' existing vague legal contracts. We show through experiments that our proposed methodologies are able to study the degree of vagueness in every interpretation and demonstrate which vendor's translated-smart contract can be more accurate, optimized, and have a lesser degree of vagueness. We also incorporated the method of fuzzy logic inside the blockchain-based smart contract, to successfully model the semantics of linguistic expressions. Our experiments and results show that the smart contract with the higher degrees of truth can be very complex technically but more accurate at the same time. By using fuzzy logic inside a smart contract, it becomes easier to solve the …

This dissertation introduces a hybrid strategy for automated testing of Android applications that combines reinforcement learning and test suite prioritization. These approaches aim to improve the effectiveness of the testing process by employing reinforcement learning algorithms, namely Q-learning and SARSA (State-Action-Reward-State-Action), for automated test case generation. The studies provide compelling evidence that reinforcement learning techniques hold great potential in generating test cases that consistently achieve high code coverage; however, the generated test cases may not always be in the optimal order. In this study, novel test case prioritization methods are developed, leveraging pairwise event interactions coverage, application state coverage, and application activity coverage, so as to optimize the rates of code coverage specifically for SARSA-generated test cases. Additionally, test suite prioritization techniques are introduced based on UI element coverage, test case cost, and test case complexity to further enhance the ordering of SARSA-generated test cases. Empirical investigations demonstrate that applying the proposed test suite prioritization techniques to the test suites generated by the reinforcement learning algorithm SARSA improved the rates of code coverage over original orderings and random orderings of test cases.

The purpose of this study is to propose a top-down policy engineering framework for attribute-based access control (ABAC) that aims to automatically extract ACPs from requirement specifications documents, and then, using the extracted policies, build or update an ABAC model. We specify a procedure that consists of three main components: 1) ACP sentence identification, 2) policy element extraction, and 3) ABAC model creation and update. ACP sentence identification processes unrestricted natural language documents and identify the sentences that carry ACP content. We propose and compare three different methodologies from different disciplines, namely deep recurrent neural networks (RNN-based), biological immune system (BIS-based), and a combination of multiple natural language processing techniques (PMI-based) in order to identify the proper methodology for extracting ACP sentences from irrelevant text. Our evaluation results improve the state-of-the-art by a margin of 5% F1-Measure. To aid future research, we also introduce a new dataset that includes 5000 sentences from real-world policy documents. ABAC policy extraction extracts ACP elements such as subject, object, and action from the identified ACPs. We use semantic roles and correctly identify ACP elements with an average F1 score of 75%, which bests the previous work by 15%. Furthermore, as SRL tools are often …

Machine learning algorithms based on neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy sensitive. To address this issue, we develop new techniques to provide solutions for running deep neural networks over encrypted data. In this paper, we develop new techniques to adopt deep neural networks within the practical limitation of current homomorphic encryption schemes. We focus on training and classification of the well-known neural networks and convolutional neural networks. First, we design methods for approximation of the activation functions commonly used in CNNs (i.e. ReLU, Sigmoid, and Tanh) with low degree polynomials which is essential for efficient homomorphic encryption schemes. Then, we train neural networks with the approximation polynomials instead of original activation functions and analyze the performance of the models. Finally, we implement neural networks and convolutional neural networks over encrypted data and measure performance of the models.

Intelligent transportation systems (ITS) are essential tools for traffic planning, analysis, and forecasting that can utilize the huge amount of traffic data available nowadays. In this work, we aggregated detailed traffic flow sensor data, Waze reports, OpenStreetMap (OSM) features, and weather data, from California Bay Area for 6 months. Using that data, we studied three novel ITS applications using convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The first experiment is an analysis of the relation between roadway shapes and accident occurrence, where results show that the speed limit and number of lanes are significant predictors for major accidents on highways. The second experiment presents a novel method for forecasting congestion severity using crowdsourced data only (Waze, OSM, and weather), without the need for traffic sensor data. The third experiment studies the improvement of traffic flow forecasting using accidents, number of lanes, weather, and time-related features, where results show significant performance improvements when the additional features where used.

Current works of bike demand prediction mainly focus on cluster level and perform poorly on predicting demands of a single station. In the first task, we introduce a contextual based bike demand prediction model, which predicts bike demands for per station by combining spatio-temporal network and environment contexts synergistically. Furthermore, since people's movement information is an important factor, which influences the bike demands of each station. To have a better understanding of people's movements, we need to analyze the relationship between different places. In the second task, we propose an origin-destination model to learn place representations by using large scale movement data. Then based on the people's movement information, we incorporate the place embedding into our bike demand prediction model, which is built by using multi-source large scale datasets: New York Citi bike data, New York taxi trip records, and New York POI data. Finally, as deep learning methods have been successfully applied to many fields such as image recognition and natural language processing, it inspires us to incorporate the complex deep learning method into the bike demand prediction problem. So in this task, we propose a deep spatial-temporal (DST) model, which contains three major components: spatial dependencies, temporal dependencies, …

In this disseration we propose semi-automated top-down policy engineering approaches for attribute-based access control (ABAC) development. Further, we propose a hybrid ABAC policy engineering approach to combine the benefits and address the shortcomings of both top-down and bottom-up approaches. In particular, we propose three frameworks: (i) ABAC attributes extraction, (ii) ABAC constraints extraction, and (iii) hybrid ABAC policy engineering. Attributes extraction framework comprises of five modules that operate together to extract attributes values from natural language access control policies (NLACPs); map the extracted values to attribute keys; and assign each key-value pair to an appropriate entity. For ABAC constraints extraction framework, we design a two-phase process to extract ABAC constraints from NLACPs. The process begins with the identification phase which focuses on identifying the right boundary of constraint expressions. Next is the normalization phase, that aims at extracting the actual elements that pose a constraint. On the other hand, our hybrid ABAC policy engineering framework consists of 5 modules. This framework combines top-down and bottom-up policy engineering techniques to overcome the shortcomings of both approaches and to generate policies that are more intuitive and relevant to actual organization policies. With this, we believe that our work takes essential steps towards …

Epileptic seizure presents a formidable threat to the life of its sufferers, leaving them unconscious within seconds of its onset. Having a mortality rate that is at least twice that of the general population, it is a true cause for concern which has gained ample attention from various research communities. About 800 million people in the world will have at least one seizure experience in their lifespan. Injuries sustained during a seizure crisis are one of the leading causes of death in epilepsy. These can be prevented by an early detection of seizure accompanied by a timely intervention mechanism. The research presented in this dissertation explores Kriging methods to exploit spatial correlations of electroencephalogram (EEG) Signals from the brain, for fast and accurate seizure detection in the Internet of Medical Things (IoMT) using edge computing paradigms, by modeling the brain as a three-dimensional spatial object, similar to a geographical panorama. This dissertation proposes basic, hierarchical and distributed Kriging models, with a deep neural network (DNN) wrapper in some instances. Experimental results from the models are highly promising for real-time seizure detection, with excellent performance in seizure detection latency and training time, as well as accuracy, sensitivity and specificity which compare …

There is an increased use of block-based programming environments in K-12 education and computing outreach activities to introduce novices to programming and computational thinking skills. However, despite their appealing design that allows students to focus on concepts rather than syntax, block-based programming by design is inaccessible to people with visual impairments and people who cannot use the mouse. In addition to this inaccessibility, little is known about the instructional experiences of students with visual impairments on current block-based programming environments. This dissertation addresses this gap by (1) investigating the challenges that students with visual impairments face on current block-based programming environments and (2) exploring ways in which we can use the keyboard and the screen reader to create block-based code. Through formal survey and interview studies with teachers of students with visual impairments and students with visual impairments, we identify several challenges faced by students with visual impairments on block-based programming environments. Using the knowledge of these challenges and building on prior work, we explore how to leverage the keyboard and the screen reader to improve the accessibility of block-based programming environments through a prototype of an accessible block-based programming library. In this dissertation, our empirical evaluations demonstrate that people …

CPU-memory bottleneck is a widely recognized problem. It is known that majority of high performance computing (HPC) database systems are configured with large memories and dedicated to process specific workloads like weather prediction, molecular dynamic simulations etc. My research on optimal address mapping improves the memory performance by increasing the channel and bank level parallelism. In an another research direction, I proposed and evaluated adaptive page migration techniques that obviates the need for offline analysis of an application to determine page migration strategies. Furthermore, I explored different migration strategies like reverse migration, sub page migration that I found to be beneficial depending on the application behavior. Ideally, page migration strategies redirect the demand memory traffic to faster memory to improve the memory performance. In my third contribution, I worked and evaluated a memory-side accelerator to assist the main computational core in locating the non-zero elements of a sparse matrix that are typically used in scientific, machine learning workloads on a low-power embedded system configuration. Thus my contributions narrow the speed-gap by improving the latency and/or bandwidth between CPU and memory.

This dissertation presents novel approaches to test context aware applications that suffer from a cost prohibitive number of context and GUI events and event combinations. The contributions of this work to test context aware applications under test include: (1) a real-world context events dataset from 82 Android users over a 30-day period, (2) applications of Markov models, Closed Sequential Pattern Mining (CloSPAN), Deep Neural Networks- Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU), and Conditional Random Fields (CRF) applied to predict context patterns, (3) data driven test case generation techniques that insert events at the beginning of each test case in a round-robin manner, iterate through multiple context events at the beginning of each test case in a round-robin manner, and interleave real-world context event sequences and GUI events, and (4) systematically interleaving context with a combinatorial-based approach. The results of our empirical studies indicate (1) CRF outperforms other models thereby predicting context events with F1 score of about 60% for our dataset, (2) the ISFreqOne that iterates over context events at the beginning of each test case in a round-robin manner as well as interleaves real-world context event sequences and GUI events at an interval one achieves …

The main research objective of this dissertation is to understand the sensing and communication challenges to achieving cooperative perception among autonomous vehicles, and then, using the insights gained, guide the design of the suitable format of data to be exchanged, reliable and efficient data fusion algorithms on vehicles. By understanding what and how data are exchanged among autonomous vehicles, from a machine learning perspective, it is possible to realize precise cooperative perception on autonomous vehicles, enabling massive amounts of sensor information to be shared amongst vehicles. I first discuss the trustworthy perception information sharing on connected and autonomous vehicles. Then how to achieve effective cooperative perception on autonomous vehicles via exchanging feature maps among vehicles is discussed in the following. In the last methodology part, I propose a set of mechanisms to improve the solution proposed before, i.e., reducing the amount of data transmitted in the network to achieve an efficient cooperative perception. The effectiveness and efficiency of our mechanism is analyzed and discussed.

Cyber physical systems (CPS) are an integration of computational and physical processes, where the cyber components monitor and control physical processes. Cyber-attacks largely target the cyber components with the intention of disrupting the functionality of the components in the physical domain. This dissertation explores the role of semantic inference in understanding such attacks and building resilient CPS systems. To that end, we present SIMON, an ontological design and verification framework that captures the intricate relationship(s) between cyber and physical components in CPS by leveraging several standard ontologies and extending the NIST CPS framework for the purpose of eliciting trustworthy requirements, assigning responsibilities and roles to CPS functionalities, and validating that the trustworthy requirements are met by the designed system. We demonstrate the capabilities of SIMON using two case studies – a vehicle to infrastructure (V2I) safety application and an additive manufacturing (AM) printer. In addition, we also present a taxonomy to capture threat feeds specific to the AM domain.

Autonomous vehicles have made milestone strides within the past decade. Advances up the autonomy ladder have come lock-step with the advances in machine learning, namely deep-learning algorithms and huge, open training sets. And while advances in CPUs have slowed, GPUs have edged into the previous decade's TOP 500 supercomputer territory. This new class of GPUs include novel deep-learning hardware that has essentially side-stepped Moore's law, outpacing the doubling observation by a factor of ten. While GPUs have make record progress, networks do not follow Moore's law and are restricted by several bottlenecks, from protocol-based latency lower bounds to the very laws of physics. In a way, the bottlenecks that plague modern networks gave rise to Edge computing, a key component of the Connected Autonomous Vehicle system, as the need for low-latency in some domains eclipsed the need for massive processing farms. The Connected Autonomous Vehicle ecosystem is one of the most complicated environments in all of computing. Not only is the hardware scaled all the way from 16 and 32-bit microcontrollers, to multi-CPU Edge nodes, and multi-GPU Cloud servers, but the networking also encompasses the gamut of modern communication transports. I propose a framework for negotiating, encapsulating and transferring data …

Prompt and efficient intervention is vital in reducing casualty figures during epidemic outbreaks, disasters, sudden civil strife or terrorism attacks. This can only be achieved if there is a fit-for-purpose and location-specific emergency response plan in place, incorporating geographical, time and vehicular capacity constraints. In this research, a comprehensive emergency response model for situations of uncertainties (in locations' demand and available resources), typically obtainable in low-resource countries, is designed. It involves the development of algorithms for optimizing pre-and post-disaster activities. The studies result in the development of four models: (1) an adaptation of a machine learning clustering algorithm, for pre-positioning depots and emergency operation centers, which optimizes the placement of these depots, such that the largest geographical location is covered, and the maximum number of individuals reached, with minimal facility cost; (2) an optimization algorithm for routing relief distribution, using heterogenous fleets of vehicle, with considerations for uncertainties in humanitarian supplies; (3) a genetic algorithm-based route improvement model; and (4) a model for integrating possible new locations into the routing network, in real-time, using emergency severity ranking, with a high priority on the most-vulnerable population. The clustering approach to solving dept location-allocation problem produces a better time complexity, and the …

In this dissertation, I start with an analysis of negation in eleven benchmark corpora covering six Natural Language Understanding (NLU) tasks. With a thorough investigation, I first show that (a) these benchmarks contain fewer negations compared to general-purpose English and (b) the few negations they contain are often unimportant. Further, my empirical studies demonstrate that state-of-the-art transformers trained using these corpora obtain substantially worse results with the instances that contain negation, especially if the negations are important. Second, I investigate whether translating negation is also an issue for modern machine translation (MT) systems. My studies find that indeed the presence of negation can significantly impact translation quality, in some cases resulting in reductions of over 60%. In light of these findings, I investigate strategies to better understand the semantics of negation. I start with identifying the focus of negation. I develop a neural model that takes into account the scope of negation, context from neighboring sentences, or both. My best proposed system obtains an accuracy improvement of 7.4% over prior work. Further, I analyze the main error categories of the systems through a detailed error analysis. Next, I explore more practical ways to understand the semantics of negation. I consider …

This dissertation focuses on a novel area of secure data management referred to as data cooperatives. A data cooperative solution promises its users better protection and control of their personal data as compared to the traditional way of their handling by the data collectors (such as governments, big data companies, and others). However, despite the many interesting benefits that the data cooperative approach tends to provide its users, it suffers from a few challenges hindering its development, adoption, and widespread use among data providers and consumers. To address these issues, we have divided this dissertation into two parts. In the first part, we identify the existing challenges and propose and implement a decentralized architecture built atop a blockchain system. Our solution leverages the inherent decentralized, tamper-resistant, and security properties of the blockchain. The implementation of our system was carried out on an existing blockchain test network, Ropsten, and our results show that blockchain is an efficient and scalable platform for the development of a decentralized data cooperative solution. In the second part of this work, we further addressed the existing challenges and the limitations of the implementation from the first part of our work. In particular, we addressed inclusivity---a core …