Volgenau School of Engineering Graduate Research
Permanent URI for this collection
Browse
Browsing Volgenau School of Engineering Graduate Research by Title
Now showing 1 - 20 of 72
Results Per Page
Sort Options
Item A CNN/MLP Neural Processing Engine, Powered by Novel Temporal-Carry-deferring MACs(2021) Mirzaeian, AliThe applications of machine learning algorithms are innumerable and cover nearly every domain of modern technology. During this rapid growth of this area, more and more companies have expressed a desire to utilize machine learning techniques in smaller devices, such as cell phones or smart Internet of Things (IoT) instruments. However, as machine learning has so far required a power source with more capacity and higher efficiency than a conventional battery. Therefore, introducing neural network accelerators with low energy demands and low latency for executing machine learning techniques has drawn lots of attention in both the academia and industry.Item A Side Channel Delay Analysis for Hardware Trojan Detection(2020-10) Vakil, AshkanThis research proposal introduces a learning assisted modeling technique for the purpose of Hardware Trojan detection. Our proposed model, unlike the prior art, does not require a Golden fabricated chip as a fingerprint to compare the side channel signals. Instead, by modeling the voltage drop and voltage noise pre-fabrication, and with training a Neural Network post-fabrication, our proposed technique can improve the timing model collected during timing closure and produces a Neural assisted Golden Timing Model (NGTM) for side channel delay-signal analysis. The Neural Network acts as a process tracking watchdog for correlating the static timing data (produced at design time) to the delay information obtained from clock frequency sweeping test. Proposed modeling technique enables Hardware Trojan detection close to 90% in the simulated scenarios.Item A Study of Epileptic Seizure Detection using Machine Learning Algorithms(2022-05) Kamaraju, Rajeev; Peixoto, NathaliaThis paper focuses on studying epileptic seizure detection using machine learning algorithms. Algorithms like Naïve Bayes, Logistic Regression, Stochastic Gradient Descent, KNearest Neighbour, Decision trees and random forests have been studied. For each of the classifier, many performance metrics have been computed and Area Under Curve (AUC) has been chosen as our performance metric. The paper also introduces the possibility of detecting epileptic seizures using Neural networks.Item A Survey On Techniques Used for Designing Fault Tolerant and Process Variation Aware Memories and Caches(2020) Beheshti-Shirazi, Sayed AreshAggressive voltage and frequency scaling schemes applied to memory and cache structures, specially for memory systems fabricated in advanced and scaled geometry nodes that are severely affected by process variation,significantly increases the likelihood of read, write and access failures to/from memory cell array, and reduces the extent of frequency and voltage scaling. To remedy this problem, in the past decade, many researchers have investigated alternative and fault tolerant cache and memory organizations to mitigate the impact of process variation, and to reduce the failure rate of memory array in the results of voltage and frequency scaling. This paper discusses and compare many of such cache and memory design techniques.Item A Technical Report On Accelerator Design For Deep Neural Networks(2019) Mirzaeian, AliItem A Technical Report on Key Management and Vulnerability Assessment of Logic Obfuscation(2019) Zamiri Azar, KimiaItem A Technical Report on Logic Obfuscation using Reconfigurable Logic and Routing Blocks(2019) Mardani Kamali, HadiThe increasing cost of building, operating, managing, and maintaining state-of-the-art silicon manufacturing facilities has pushed several stages of the semiconductor device’s manufacturing supply chain offshore. However, many of these offshore facilities are identified as untrusted entities. Processing and fabrication of ICs in an untrusted supply chain poses a number of challenging security threats such as IC overproduction, Trojan insertion, Reverse Engineering, Intellectual Property (IP) theft, and counterfeiting. To counter these threats, various hardware design-for-trust techniques have been pro- posed. Logic locking, as a proactive technique among these techniques, has been introduced as a technique that obfuscates and conceals the functionality of IC/IP using additional key inputs that are driven by an on-chip tamper-proof memory. Shortly after introducing the primitive logic locking solutions, a very strong Boolean attack, the Satisfiability (SAT) attack. It was shown that the SAT attack could break all previously proposed primitive locking mechanisms in almost polynomial time. To thwart the strength of SAT attack, researchers have investigated many directions, such as formulating locking solutions that significantly increase the number of required SAT iterations, or formulating the locking solutions such that it is not translatable to a SAT problem. However, further investigations demonstrated that some of these locking techniques are vulnerable to other types of attacks such as Signal Probability Skew (SPS) attack, removal attack, approximate-based attack(s), bypass attack, and Satisfiability Module Theories (SMT) attack. In addition, these techniques suffer from very low output corruption. Hence, an unactivated IC behaves almost identical to an unlocked IC with exception of one or few inputs.Item A Technical Report on Security Evaluation of Logic Locking: Attacks and Defenses(2020) Zamiri Azar, KimiaItem Analysis of Social Media Comments(2021-04-28) Mohamed, MazenFighting the COVID-19 is widespread acceptance of the covid-19 vaccines. Achieving the widespread uptake might be challenging and may be obstructed by the misinformation prevalent in social media. The social media platforms have become a common source of information and disinformation on vaccines. Vaccine’s hesitancy is more prevalent in social media, especially Twitter. Machine learning models can explain the social media comments about this topic.Item Bert Model for Social Media Bot Detection(2022-03) Heidari, Maryam; Jones, James H Jr.Millions of online posts about different topics and products are shared on popular social media platforms. One use of this content is to provide crowd-sourced information about a specific topic, event, or product. However, this use raises an important question: what percentage of the information available through these services is trustworthy? In particular, might some of this information be generated by a machine, i.e., a ``bot" instead of a human? Bots can be, and often are, purposely designed to generate enough volume to skew an apparent trend or position on a topic, yet the consumer of such content cannot easily distinguish a bot post from a human post. This paper introduces a new model that uses Bidirectional Encoder Representations from Transformers (Google Bert) for sentiment classification of tweets to identify topic-independent features for the social media bot detection model. Using a Natural Language Processing approach to derive topic-independent features for the new bot detection model distinguishes this work from previous bot detection models. We achieve 94\% accuracy classifying the contents of data set Cresci \cite{cresci-etal-2017-paradigm}as generated by a bot or a human, where the most accurate prior work achieved an accuracy of 92\%.Item Beyond Bibliometrics: Understanding Library Services in Multidisciplinary Research(Mason Graduate Interdisciplinary Conference, 2019-04-06) Mahapasuthanon, Pattiya; Hoffman, KimberlyBibliometric methods, using citations as data, are an alternate way to learn from the literature of science and technology. These statistical methods are used, with visualization tools, to determine the relationship between authors and papers, scientific subjects reflected in publishing, and word or frequency occurrence. Bibliometrics are used by libraries to get a broad view of the growth, structure, connections and productivity of a discipline reflected in literature. This research studies trends and multidisciplinary connections across university researchers and campuses. With a strategic initiative from George Mason University (GMU) to become excellent in multidisciplinary research, Mason Libraries support multidisciplinary research activities. This study completes an analysis on bibliometric and funding across five centers at the GMU Science and Technology campus (SciTech) to understand research activities and interactions. Bibliometric network graphs were created from Web of Science (WoS) citation datasets and VOSViewer, a visualization tool. Federal RePORTER [documentation and analysis of inputs, outputs, and outcomes resulting from federal investments in science available: https://www.starmetrics.nih.gov/Star/About] and WoS were used to generate funding charts. For research activities not captured by scientific literature, and involving ongoing library resources, the creation of a pilot version of an interactive visualization for experience mapping was tested to successfully identify and seek new service opportunities. The results obtained from the bibliometric analysis indicate that libraries must plan to reach researchers in those relatively young multidisciplinary research institutes. The research trends at SciTech have shifted towards applied health and biological medicine according to the keyword analysis. From the funding analysis, the SciTech campus accounted for 30 percent of the total funded projects to GMU from National Institutes of Health (NIH). With these preliminary results, understanding resources and services the SciTech researchers and multidisciplinary researchers need will increase research connections and productivity. Future research will seek to incorporate more sophisticated tools to further understand impactful resources and plan for future library collaborations.Item Bias prevention in Loan Applications by Using Machine Learning Models(2021-04-28) Zaid, Altukhi; Kordu, Sushma Sree; Muraleedharakumar, Dipukumar; Wilson, CarltonCreditworthiness is based on how the borrower handled debt and credit. Creditworthiness is how a lender decides if the person or company who requests for money can repay the loan that will be borrowed. The first step to get a loan is to complete and fill an application.The main aim of this research is to use attributes such as loan type, credit history, credit amount, employment history status, education background, marital status, the duration of the loan, and the current status of checking or savings account etc. to come up with an alternate mechanism for determining creditworthiness.Item Bimodal Data Mining: Integration of Key Data and Semantic Analysis for Text/Audio Datasets(2021-04-28) Corja, Victor; Crow, Austin; Liu, NannanThis research was aimed at combining these individual methodologies into a consolidated model that takes in data in both audio and text format. For each desired function, models were selected and ranked by adherence to criteria which determined their applicability to the desired product. Upon selection of the models, they were implemented through libraries into a consolidated program, which took as an input a combinatorial text and audio dataset, and provided a report of the analysis resulting from data mining. The program was tested using data from TED talks, performed text mining and semantic analysis, and provided a structured output of the generated statistics.Item Classification vs Regression Models for Creating prediction models for vaccination rates of incoming kindergarten students(2021-04-28) Lee, Chen Yuan; Orellana, Erick; Zhu, KeningVaccinations have been proven over the years to help treat some of the deadliest diseases as well as to prevent the further spread of those diseases. A major factor that can dictate the success or failure of a vaccine at treating the broader population is to reach heard immunity. To reach heard immunity, it is important to have a certain percentage of the population vaccinated so that they themselves will not be impacted by the disease and so that they will not spread throughout the community. Public health officials in conjunction with education officials understand the importance of immunizations and therefore set standards on vaccination rates and collect data to drive efforts to improve vaccination rates. The state of California is one of those states that has set standards for the vaccinations that kindergarten students should have before entering the school system and collect this information and make it public each year. There is an interest in using this information to make models that can be used to make prediction about vaccination levels at the county level. The most prominent approach taken is a geospatial approach of using a physical map to show vaccination rates. This is a useful visual, but it does not too much in the way of explaining why those vaccination rates are what they are based on certain factors. These geospatial models also do not provide a way to predict how changes in certain factors will impact the vaccination rates. In this study, variables that may impact vaccination rates are explored to generate a regression model and two classification models to understand if those models can be accurately used with the given predictor variables to gage potential changes to vaccination rates based on those given variables.Item Cloud Computing: Literature Review(2019) Hassan, RakibulCloud computing has recently emerged as a new paradigm for hosting and delivering services over the Internet. Cloud computing is attractive to business owners as it eliminates the requirement for users to plan ahead for provisioning, and allows enterprises to start from the small and increase resources only when there is a rise in service demand. However, despite the fact that cloud computing offers huge opportunities to the IT industry, the development of cloud computing technology is currently at its infancy, with many issues still to be addressed. In this paper, we present a survey of cloud computing, highlighting its key concepts, architectural principles, state-of-the-art implementation as well as research challenges. The aim of this paper is to provide a better understanding of the design challenges of cloud computing and identify important research directions in this increasingly important area.Item Combinatorial Trends of Tissue Engineering for Peripheral Nerve Regeneration(2022-05) Dando, EmmaPeripheral nerve damage is frequently seen due to injury or illnesses, like diabetes. Despite its prevalence and the fact that many patients with less serious injuries have good clinical outcomes, many patients do not fully recover sensation and in many cases, use of the affected area. For this reason, there has been extensive research into improving or replacing the current treatment options. Many tissue engineering solutions focus on peripheral nerve injury or damage caused specifically by external trauma. The aim of this paper is to list and summarize the primary areas of research for tissue engineering approaches to peripheral nerve regeneration. Moreover, the focus is on the increasing awareness that no single tissue engineering technique is currently capable of providing optimal healing and regeneration for peripheral nerve damage and may never be fully capable of providing complete regeneration. Instead, clinical outcomes may be improved by combining these techniques in multifaceted approaches some of which include combining growth factors and nerve guidance conduits.Item Comparative Analysis of Medication Based on Machine Learning Models(2021-04-28) Kouser, Nashid; Barekzai, SaraOur society is seeing a sharp rise in the number of people suffering from complicated chronic diseases. Presently, 6 in 10 adults in the United States have a chronic disease. This is the leading cause of death and the leading driver of the Nation's $3.8 Trillion in Annual Health Care Costs. With that figure predicted to grow, clearly, something is lacking from the one-size. the fits-all paradigm of traditional medicine. Caring for this new population requires an entirely different mindset; this is where functional medicine steps in. Functional medication can help prevent disease thus potentially proving to be more cost-effective for the insured and insurer overall in the long term. However, there are approximately 1400 functional medicine practitioners across the U.S., and a little under 350 that accept insurance. We analyze health data from a new point in this research.Item Conditional Classification: A Solution for Computational Energy Reduction(2021) Mirzaeian, Ali; Manoj P D, Sai; Vakil, Ashkan; Homayoun, Houman; Sasan, AvestaDeep convolutional neural networks have shown high efficiency in computer visions and other applications. However, with the increase in the depth of the networks, the computational complexity is growing exponentially. In this paper, we propose a novel solution to reduce the computational complexity of convolutional neural network models used for many class image classification. Our proposed technique breaks the classification task into two steps: 1) coarse-grain classification, in which the input samples are classified among a set of hyper-classes, 2) fine-grain classification, in which the final labels are predicted among those hyper-classes detected at the first step. We illustrate that our proposed classifier can reach the level of accuracy reported by the best in class classification models with less computational complexity (Flop Count) by only activating parts of the model that are needed for the image classification.Item COVID-19 Vaccine Data Review and Reactions on Social Media(2021-04-28) Bhandari, Shova; Mohamed, Mazen; Maupin, JakeThe USA is one of the hardest hit areas by COVID-19. As of March 13th, 2021, 29.5M people were infected and 534K have lost their lives [1]. The USA government has authorized Pfizer and Moderna mRNA COVID-19 vaccines for the prevention of Coronavirus. However, these vaccines are allocated to certain groups and are not available to the public yet. Vaccine’s demand is skyrocketing as the United States of America is unable to contain the virus, and a new more contagious and deadlier Covid-19 variant is emerging. Given the impact of the COVID-19 pandemic, it is imperative to efficiently distribute vaccines to contain and eventually eradicate the virus. It is important to identify the hardest hit region/state that is still struggling to fight and protect their residence from viruses. The main question we are attempting to answer is how we can use COVID-19 data to identify focal points for COVID-19 breakout and formulate an efficient and speedy response. In this research we analyze COVID-19 vaccine trend.Item Creating a Digital Twin of an Insider Threat Detection Enterprise using Model Based Systems Engineering(AI4SE and SE4AI Workshop, 2021-10-20) Lee, James; Alghamdi, Ahmad; Zaidi, Abbas