Browsing by Subject "Neural Network"

Now showing 1 - 6 of 6
  • Thumbnail Image
    Item
    Analyzing and evaluating security features in software requirements
    (2016-10-28) Hayrapetian, Allenoush; Raje, Rajeev
    Software requirements, for complex projects, often contain specifications of non-functional attributes (e.g., security-related features). The process of analyzing such requirements for standards compliance is laborious and error prone. Due to the inherent free-flowing nature of software requirements, it is tempting to apply Natural Language Processing (NLP) and Machine Learning (ML) based techniques for analyzing these documents. In this thesis, we propose a novel semi-automatic methodology that assesses the security requirements of the software system with respect to completeness and ambiguity, creating a bridge between the requirements documents and being in compliance. Security standards, e.g., those introduced by the ISO and OWASP, are compared against annotated software project documents for textual entailment relationships (NLP), and the results are used to train a neural network model (ML) for classifying security-based requirements. Hence, this approach aims to identify the appropriate structures that underlie software requirements documents. Once such structures are formalized and empirically validated, they will provide guidelines to software organizations for generating comprehensive and unambiguous requirements specification documents as related to security-oriented features. The proposed solution will assist organizations during the early phases of developing secure software and reduce overall development effort and costs.
  • Thumbnail Image
    Item
    Enhancing Our Genetic Knowledge of Human Iris Pigmentation and Facial Morphology
    (2019-12) Eller, Ryan; Walsh, Susan; Berbari, Nicolas; Lapish, Christopher; Picard, Christine; Roper, Randall
    The biological underpinnings that control iris pigmentation and facial morphology are two areas of research that over the last decade are becoming more thoroughly investigated due to the increased affordability of genotyping and advances in technology allowing for more advanced analysis techniques. Despite the ease of access to the data and the tools required to perform iris pigmentation and facial morphological studies, there are still numerous challenges researchers must overcome when exploring the genetics of these complex phenotypes. Some of these challenges include difficulty in working with the bioinformatic programs designed to analyze genetic associations, the inability to define a phenotype that captures the true nature of these traits, and analysis techniques that fail to model complex gene-gene interactions and their effect on a phenotype or phenotypes of interest. In this body of work, I attempted to address these challenges by designing a bioinformatic pipeline, Odyssey, that bridges the communication gaps between various data preparation programs and the programs that analyze genomic data. With this program, genome-wide association studies (GWAS) could be conducted in a quicker, more efficient, and easier manner. I also redefined iris color as a quantitative measurement of pre-defined color classes. In this way it is possible to define and quantify the unique and intricate mixtures of color, which allows for the identification of known and novel variants that affect individual iris color. I also improved upon current prediction models by developing a neural network model capable of predicting a quantitative output to four pre-defined classes; blue/grey, light brown (hazel), perceived green, and dark brown. I examined the effects of defining a simple facial morphology phenotype that more accurately captures the lower face and jaw shape. I then analyzed this phenotype via a GWAS and found several novel variants that may be associated with a square and diamond shaped face. Lastly, I demonstrated that structural equation modeling can be used in combination with traditional GWAS to examine interactions amongst associated variants, which unearths potential biological relationships that impact the multifaceted phenotype of facial morphology.
  • Thumbnail Image
    Item
    Extracting Symptoms from Narrative Text using Artificial Intelligence
    (2020-12) Gandhi, Priyanka; Zou, Xukai; Luo, Xiao; Xia, Yuni
    Electronic health records collect an enormous amount of data about patients. However, the information about the patient’s illness is stored in progress notes that are in an un- structured format. It is difficult for humans to annotate symptoms listed in the free text. Recently, researchers have explored the advancements of deep learning can be applied to pro- cess biomedical data. The information in the text can be extracted with the help of natural language processing. The research presented in this thesis aims at automating the process of symptom extraction. The proposed methods use pre-trained word embeddings such as BioWord2Vec, BERT, and BioBERT to generate vectors of the words based on semantics and syntactic structure of sentences. BioWord2Vec embeddings are fed into a BiLSTM neural network with a CRF layer to capture the dependencies between the co-related terms in the sentence. The pre-trained BERT and BioBERT embeddings are fed into the BERT model with a CRF layer to analyze the output tags of neighboring tokens. The research shows that with the help of the CRF layer in neural network models, longer phrases of symptoms can be extracted from the text. The proposed models are compared with the UMLS Metamap tool that uses various sources to categorize the terms in the text to different semantic types and Stanford CoreNLP, a dependency parser, that analyses syntactic relations in the sentence to extract information. The performance of the models is analyzed by using strict, relaxed, and n-gram evaluation schemes. The results show BioBERT with a CRF layer can extract the majority of the human-labeled symptoms. Furthermore, the model is used to extract symptoms from COVID-19 tweets. The model was able to extract symptoms listed by CDC as well as new symptoms.
  • Thumbnail Image
    Item
    OPTIMAL ENERGY MANAGEMENT SYSTEM OF PLUG-IN HYBRID ELECTRIC VEHICLE
    (ProQuest, 2009) Banvait, Harpreetsingh; Anwar, Sohel; Chen, Yaobin; Eberhart, Russell C.
    Plug-in Hybrid Electric Vehicles (PHEV) are new generation Hybrid Electric Vehicles (HEV) with larger battery capacity compared to Hybrid Electric Vehicles. They can store electrical energy from a domestic power supply and can drive the vehicle alone in Electric Vehicle (EV) mode. According to the U.S. Department of Transportation 80 % of the American driving public on average drives under 50 miles per day. A PHEV vehicle that can drive up to 50 miles by making maximum use of cheaper electrical energy from a domestic supply can significantly reduce the conventional fuel consumption. This may also help in improving the environment as PHEVs emit less harmful gases. However, the Energy Management System (EMS) of PHEVs would have to be very different from existing EMSs of HEVs. In this thesis, three different Energy Management Systems have been designed specifically for PHEVs using simulated study. For most of the EMS development mathematical vehicle models for powersplit drivetrain configuration are built and later on the results are tested on advanced vehicle modeling tools like ADVISOR or PSAT. The main objective of the study is to design EMSs to reduce fuel consumption by the vehicle. These EMSs are compared with existing EMSs which show overall improvement. x In this thesis the final EMS is designed in three intermediate steps. First, a simple rule based EMS was designed to improve the fuel economy for parametric study. Second, an optimized EMS was designed with the main objective to improve fuel economy of the vehicle. Here Particle Swarm Optimization (PSO) technique is used to obtain the optimum parameter values. This EMS has provided optimum parameters which result in optimum blended mode operation of the vehicle. Finally, to obtain optimum charge depletion and charge sustaining mode operation of the vehicle an advanced PSO EMS is designed which provides optimal results for the vehicle to operate in charge depletion and charge sustaining modes. Furthermore, to implement the developed advanced PSO EMS in real-time a possible real time implementation technique is designed using neural networks. This neural network implementation provides sub-optimal results as compared to advanced PSO EMS results but it can be implemented in real time in a vehicle. These EMSs can be used to obtain optimal results for the vehicle driving conditions such that fuel economy is improved. Moreover, the optimal designed EMS can also be implemented in real-time using the neural network procedure described.
  • Thumbnail Image
    Item
    Residual Capsule Network
    (2019-08) Bhamidi, Sree Bala Shruthi; El-Sharkawy, Mohamed; King, Brian; Rizkalla, Maher
    The Convolutional Neural Network (CNN) have shown a substantial improvement in the field of Machine Learning. But they do come with their own set of drawbacks. Capsule Networks have addressed the limitations of CNNs and have shown a great improvement by calculating the pose and transformation of the image. Deeper networks are more powerful than shallow networks but at the same time, more difficult to train. Residual Networks ease the training and have shown evidence that they can give good accuracy with considerable depth. Putting the best of Capsule Network and Residual Network together, we present Residual Capsule Network and 3-Level Residual Capsule Network, a framework that uses the best of Residual Networks and Capsule Networks. The conventional Convolutional layer in Capsule Network is replaced by skip connections like the Residual Networks to decrease the complexity of the Baseline Capsule Network and seven ensemble Capsule Network. We trained our models on MNIST and CIFAR-10 datasets and have seen a significant decrease in the number of parameters when compared to the Baseline models.
  • Thumbnail Image
    Item
    User Modeling and Optimization for Environmental Planning System Design
    (2014) Singh, Vidya Bhushan; Mukhopadhyay, Snehasis; Tuceryan, Mihran; Xia, Yuni
    Environmental planning is very cumbersome work for environmentalists, government agencies like USDA and NRCS, and farmers. There are a number of conflicts and issues involved in such a decision making process. This research is based on the work to provide a common platform for environmental planning called WRESTORE (Watershed Restoration using Spatio-Temporal Optimization of Resources). We have designed a system that can be used to provide the best management practices for environmental planning. A distributed system was designed to combine high performance computing power of clusters/supercomputers in running various environmental model simulations. The system is designed to be a multi-user system just like a multi-user operating system. A number of stakeholders can log-on and run environmental model simulations simultaneously, seamlessly collaborate, and make collective judgments by visualizing their landscapes. In the research, we identified challenges in running such a system and proposed various solutions. One challenge was the lack of fast optimization algorithm. In our research, several algorithms are utilized such as Genetic Algorithm (GA) and Learning Automaton (LA). However, the criticism is that LA has a slow rate of convergence and that both LA and GA have the problem of getting stuck in local optima. We tried to solve the multi-objective problems using LA in batch mode to make the learning faster and accurate. The problems where the evaluation of the fitness functions for optimization is a bottleneck, like running environmental model simulation, evaluation of a number of such models in parallel can give considerable speed-up. In the multi-objective LA, different weight pair solutions were evaluated independently. We created their parallel versions to make them practically faster in computation. Additionally, we extended the parallelism concept with the batch mode learning. Another challenge we faced was in User Modeling. There are a number of User Modeling techniques available. Selection of the best user modeling technique is a hard problem. In this research, we modeled user's preferences and search criteria using an ANN (Artificial Neural Network). Training an ANN with limited data is not always feasible. There are many situations where a simple modeling technique works better if the learning data set is small. We formulated ways to fine tune the ANN in case of limited data and also introduced the concept of Deep Learning in User Modeling for environmental planning system.