Filtering by
- Member of: Theses and Dissertations
To facilitate rapid, correct, efficient, and intuitive development of graph based solutions we propose a new programming language construct - the search statement. Given a supra-root node, a procedure which determines the children of a given parent node, and optional definitions of the fail-fast acceptance or rejection of a solution, the search statement can conduct a search over any graph or network. Structurally, this statement is modelled after the common switch statement and is put into a largely imperative/procedural context to allow for immediate and intuitive development by most programmers. The Go programming language has been used as a foundation and proof-of-concept of the search statement. A Go compiler is provided which implements this construct.
The tool was developed following the incremental development process in order to quickly create a functional and testable tool. The incremental process also allowed for feedback from radio astronomers to help guide the project's development.
UVLabel provides both a functional product, and a modifiable and scalable code base for radio astronomer developers. This enables astronomers studying various astronomical interferometric data labelling capabilities. The tool can then be used to improve their filtering methods, pursue machine learning solutions, and discover new trends. Finally, UVLabel will be open source to put customization, scalability, and adaptability in the hands of these researchers.
considered a difficult problem to be solved by computers. Image captioning involves not just detecting objects from images but understanding the interactions between the objects to be translated into relevant captions. So, expertise in the fields of computer vision paired with natural language processing are supposed to be crucial for this purpose. The sequence to sequence modelling strategy of deep neural networks is the traditional approach to generate a sequential list of words which are combined to represent the image. But these models suffer from the problem of high variance by not being able to generalize well on the training data.
The main focus of this thesis is to reduce the variance factor which will help in generating better captions. To achieve this, Ensemble Learning techniques have been explored, which have the reputation of solving the high variance problem that occurs in machine learning algorithms. Three different ensemble techniques namely, k-fold ensemble, bootstrap aggregation ensemble and boosting ensemble have been evaluated in this thesis. For each of these techniques, three output combination approaches have been analyzed. Extensive experiments have been conducted on the Flickr8k dataset which has a collection of 8000 images and 5 different captions for every image. The bleu score performance metric, which is considered to be the standard for evaluating natural language processing (NLP) problems, is used to evaluate the predictions. Based on this metric, the analysis shows that ensemble learning performs significantly better and generates more meaningful captions compared to any of the individual models used.
Current IoT integration utilities attempt to help simplify this task, but most fail to satisfy one of the requirements many users want in such a system ‒ simplified integration with third party devices. This project seeks to solve this issue through the creation of an easily extendable, modular integrating utility. It is open-source and does not require the use of a cloud-based server, with users hosting the server themselves. With a server and data controller implemented in pure Python and a library for embedded ESP8266 microcontroller-powered devices, the solution seeks to satisfy both casual users as well as those interested in developing their own integrations.
The aim of this project is to understand the basic algorithmic components of the transformer deep learning architecture. At a high level, a transformer is a machine learning model based off of a recurrent neural network that adopts a self-attention mechanism, which can weigh significant parts of sequential input data which is very useful for solving problems in natural language processing and computer vision. There are other approaches to solving these problems which have been implemented in the past (i.e., convolutional neural networks and recurrent neural networks), but these architectures introduce the issue of the vanishing gradient problem when an input becomes too long (which essentially means the network loses its memory and halts learning) and have a slow training time in general. The transformer architecture’s features enable a much better “memory” and a faster training time, which makes it a more optimal architecture in solving problems. Most of this project will be spent producing a survey that captures the current state of research on the transformer, and any background material to understand it. First, I will do a keyword search of the most well cited and up-to-date peer reviewed publications on transformers to understand them conceptually. Next, I will investigate any necessary programming frameworks that will be required to implement the architecture. I will use this to implement a simplified version of the architecture or follow an easy to use guide or tutorial in implementing the architecture. Once the programming aspect of the architecture is understood, I will then Implement a transformer based on the academic paper “Attention is All You Need”. I will then slightly tweak this model using my understanding of the architecture to improve performance. Once finished, the details (i.e., successes, failures, process and inner workings) of the implementation will be evaluated and reported, as well as the fundamental concepts surveyed. The motivation behind this project is to explore the rapidly growing area of AI algorithms, and the transformer algorithm in particular was chosen because it is a major milestone for engineering with AI and software. Since their introduction, transformers have provided a very effective way of solving natural language processing, which has allowed any related applications to succeed with high speed while maintaining accuracy. Since then, this type of model can be applied to more cutting edge natural language processing applications, such as extracting semantic information from a text description and generating an image to satisfy it.
The seamless integration of autonomous vehicles (AVs) into highly interactive and dynamic driving environments requires AVs to safely and effectively communicate with human drivers. Furthermore, the design of motion planning strategies that satisfy safety constraints inherit the challenges involved in implementing a safety-critical and dynamics-aware motion planning algorithm that produces feasible motion trajectories. Driven by the complexities of arriving at such a motion planner, this thesis leverages a motion planning toolkit that utilizes spline parameterization to compute the optimal motion trajectory within a dynamic environment. Our approach is comprised of techniques originating from optimal control, vehicle dynamics, and spline interpolation. To ensure dynamic feasibility of the computed trajectories, we formulate the optimal control problem in relation to the intrinsic state constraints derived from the bicycle state space model. In addition, we apply input constraints to bound the rate of change of the steering angle and acceleration provided to the system. To produce collision-averse trajectories, we enforce extrinsic state constraints extracted from the static and dynamic obstacles in the circumambient environment. We proceed to exploit the mathematical properties of B-splines, such as the Convex Hull Property, and the piecewise composition of polynomial functions. Second, we focus on constructing a highly interactive environment in which the con- figured optimal control problem is deployed. Vehicle interactions are categorized into two distinct cases: Case 1 is representative of a single-agent interaction, whereas Case 2 is representative of a multi-agent interaction. The computed motion trajectories per each case are displayed in simulation.
In this thesis, several different methods for detecting and removing satellite streaks from astronomic images were evaluated and compared with a new machine learning based approach. Simulated data was generated with a variety of conditions, and the performance of each method was evaluated both quantitatively, using Mean Absolute Error (MAE) against a ground truth detection mask and processing throughput of the method, as well as qualitatively, examining the situations in which each model performs well and poorly. Detection methods from existing systems Pyradon and ASTRiDE were implemented and tested. A machine learning (ML) image segmentation model was trained on simulated data and used to detect streaks in test data. The ML model performed favorably relative to the traditional methods tested, and demonstrated superior robustness in general. However, the model also exhibited some unpredictable behavior in certain scenarios which should be considered. This demonstrated that machine learning is a viable tool for the detection of satellite streaks in astronomic images, however special care must be taken to prevent and to minimize the effects of unpredictable behavior in such models.
Kitsune attempts to remedy these issues by tying itself to Antlr, a pre-existing language recognition tool with over 200 currently supported languages. In addition, it provides an interface through which generic manipulations can be applied to the parse tree generated by Antlr. As Kitsune relies on language-agnostic structure modifications, it can be adapted with minimal effort to provide plagiarism detection for new languages. Kitsune has been evaluated for 10 of the languages in the Antlr grammar repository with success and could easily be extended to support all of the grammars currently developed by Antlr or future grammars which are developed as new languages are written.