Machine learning generally requires large amounts of data, however data is often limited. On the whole the amount of data needed grows with the complexity of the problem to be solved. Utilising transfer learning, data augmentation and problem reduction, acceptable performance can be achieved with limited data for a multitude of tasks. The goal of this master project is to develop an artificial neural network-based model for food waste analysis, an area in which large quantities of data is not yet readily available. Given two images an algorithm is expected to identify what has changed in the image, ignore the uncharged areas even though they might contain objects which can be classified and finally classify the change. The approach chosen in this project was to attempt to reduce the problem the machine learning algorithm has to solve by subtracting the images before they are handled by the neural network. In theory this should resolve both object localisation and filtering of uninteresting objects, which only leaves classification to the neural network. Such a procedure significantly simplifies the task to be resolved by the neural network, which results in reduced need for training data as well as keeping the process of gathering data relatively simple and fast. Several models were assessed and theories of adaptation of the neural network to this particular task were evaluated. Test accuracy of at best 78.9% was achieved with a limited dataset of about 1000 images with 10 different classes. This performance was accomplished by a siamese neural network based on VGG19 utilising triplet loss and training data using subtraction as a basis for ground truth mask creation, which was multiplied with the image containing the changed object. / Maskininlärning kräver generellt mycket data, men stora mängder data står inte alltid till förfogande. Generellt ökar behovet av data med problemets komplexitet. Med hjälp av överföringsinlärning, dataaugumentation och problemreduktion kan dock acceptabel prestanda erhållas på begränsad datamängd för flera uppgifter.  Målet med denna masteruppsats är att ta fram en modell baserad på artificiella neurala nätverk för matavfallsanalys, ett område inom vilket stora mängder data ännu inte finns tillgängligt. Givet två bilder väntas en algoritm identifiera vad som ändrats i bilden, ignorera de oförändrade områdena även om dessa innehåller objekt som kan klassificeras och slutligen klassificera ändringen. Tillvägagångssättet som valdes var att försöka reducera problemet som maskininlärningsalgoritmen, i detta fall ett artificiellt neuralt nätverk, behöver hantera genom att subtrahera bilderna innan de hanterades av det neurala nätverket. I teorin bör detta ta hand om både objektslokaliseringen och filtreringen av ointressanta objekt, vilket endast lämnar klassificeringen till det neurala nätverket. Ett sådant tillvägagångssätt förenklar problemet som det neurala nätverket behöver lösa avsevärt och resulterar i minskat behov av träningsdata, samtidigt som datainsamling hålls relativt snabbt och simpelt.  Flera olika modeller utvärderades och teorier om specialanpassningar av neurala nätverk för denna uppgift evaluerades. En testnoggrannhet på som bäst 78.9% uppnåddes med begränsad datamängd om ca 1000 bilder med 10 klasser. Denna prestation erhölls med ett siamesiskt neuralt nätverk baserat på VGG19 med tripletförlust och träningsdata som använde subtraktion av bilder som grund för framställning av grundsanningsmasker (eng. Ground truth masks) multiplicerade med bilden innehållande förändringen.

This thesis proposes a method of performing fault detection and isolation in spacecraft attitude determination and control systems. The proposed method works by deploying a trained neural network to analyze a set of residuals that are dened such that they encompass the attitude control, guidance, and attitude determination subsystems. Eight neural networks were trained using either the resilient backpropagation, Levenberg-Marquardt, or Levenberg-Marquardt with Bayesian regularization training algorithms. The results of each of the neural networks were analyzed to determine the accuracy of the networks with respect to isolating the faulty component or faulty subsystem within the ADCS. The performance of the proposed neural network-based fault detection and isolation method was compared and contrasted with other ADCS FDI methods. The results obtained via simulation showed that the best neural networks employing this method successfully detected the presence of a fault 79% of the time. The faulty subsystem was successfully isolated 75% of the time and the faulty components within the faulty subsystem were isolated 37% of the time.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / 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.

Indiana University-Purdue University Indianapolis (IUPUI)

Indiana University-Purdue University Indianapolis (IUPUI) / 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.

Indiana University-Purdue University Indianapolis (IUPUI) / Heating, ventilation and air conditioning systems (HVAC) are the single largest consumer of energy in commercial and residential sectors. Minimizing its energy consumption without compromising indoor air quality (IAQ) and thermal comfort would result in environmental and financial benefits. Currently, most buildings still utilize constant air volume (CAV) systems with on/off control to meet the thermal loads. Such systems, without any consideration of occupancy, may ventilate a zone excessively and result in energy waste. Previous studies showed that CO2-based demand-controlled ventilation (DCV) methods are the most widely used strategies to determine the optimal level of supply air volume. However, conventional CO2 mass balanced models do not yield an optimal estimation accuracy. In this study, feed-forward neural network algorithm (FFNN) was proposed to estimate the zone occupancy using CO2 concentrations, observed occupancy data and the zone schedule. The occupancy prediction result was then utilized to optimize supply fan operation of the air handling unit (AHU) associated with the zone. IAQ and thermal comfort standards were also taken into consideration as the active constraints of this optimization. As for the validation, the experiment was carried out in an auditorium located on a university campus. The results revealed that utilizing neural network occupancy estimation model can reduce the daily ventilation energy by 74.2% when compared to the current on/off control.

Indiana University-Purdue University Indianapolis (IUPUI) / 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.

No description available.

Glycosphingolipids such as α- and β-glucosylceramides (GlcCers) and α- and β- galactosylceramides (GalCers) are stereoisomers differentially synthesized by gut bacteria and their mammalian hosts in response to environmental insult. Thus, lipidomic assessment of α- and β-GlcCers and α- and β-GalCers is crucial for inferring biological functions and biomarker discovery. However, simultaneous quantification of these stereoisomeric lipids is difficult due to their virtually identical structures. Differential mobility mass spectrometry (DMS), as an orthogonal separation to high performance liquid chromatography used in electrospray ionization, tandem mass spectrometry (LC-ESI-MS/MS), can be used to separate stereoisomeric lipids. Generating LC-ESI-DMS-MS/MS methods for lipidomic analyses is exceedingly difficult demanding intensive manual optimization of DMS parameters that depend on the availability of synthetic lipid standards. Where synthetic standards do not exist, method development is not possible. To address this challenge, I developed a supervised in silico machine learning approach to accelerate method development for ion mobility-based quantification of lipid stereoisomers. I hypothesized that supervised neural network models could be used to learn the relationships between lipid structural characteristics and optimal DMS machine parameter values thereby reducing the total number of empirical experiments required to develop a DMS method and enabling users to “predict” DMS parameters for analytes that lack synthetic standards. Specifically, this thesis describes a supervised learning approach that learns the relationship between two DMS machine parameter values (separation voltage and compensation voltage) and two lipid structural features (N-Acyl chain length and degree of unsaturation). I describe here, iDMS, an algorithm that was trained on 17 lipid species, and can further simulate results of DMS manual method development and suggest optimal parameter values for 47 lipid species. This approach promises to greatly accelerate the development of assays for the detection of lipid stereoisomers in biological samples.