Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 123 for “"Machine Learning Neural Network"”.
-
Numerical Linear Algebra for Scientific Machine Learning: Neural Network Compression and Continuous Trace Estimation
Scientific machine learning (SciML) combines models built from repeated linear algebraic operations (e.g. matrix multiplication, least squares) with scientific inductive biases, including differential equations, symmetries, and geometric structure. Thus, numerical linear algebra provides a natural …
-
CLASSICAL MOLECULAR DYNAMICS SIMULATIONS OF POLYMERIC IONIC LIQUIDS USING MACHINE LEARNING NEURAL NETWORK POTENTIAL
… the molecules. Recently, by taking advantage of machine learning (ML) methods, neural network (NN) based potential functions have been developed. In this study, we use MD simulations to investigate the bulk and ion-transport properties of two types of PILs: Poly(1-butyl-3-methylimidazolium) …
-
Design, development and investigation of innovative indoor approaches for healthcare solutions. Design and simulation of RFID and reconfigurable antenna for wireless indoor applications; modelling and Implementation of ambient and wearable sensing, activity recognition, using machine learning, neural network for unobtrusive health monitoring
… smart healthcare and smart homes are developed. Machine learning and deep learning methods using multivariate Gaussian and Long short-term memory recurrent neural network are used to experimentally validate the viability of the new approaches. This work follows the construction of the SmartWall …
-
Vehicle Engine Classification Using of Laser Vibrometry Feature Extraction
… a two-layer feed-forward 20 intermediate-nodes neural network to classify vehicles’ engine, the results are encouraging as they can consistently achieve accuracies over 96%. However, the TPI required a length of 1.25 seconds of vibration, which is a drawback of the TPI, as vehicles generally are …
-
Improving Cyber Security in Power Systems Using Neural Networks
… being combated. In addition, a potential machine learning neural network-based anomaly detection will be discussed.
-
Using Artificial Intelligence And Machine Learning To Develop Synthetic Well Logs
… logs using technologies such as the artificial neural networks which can be used when well logs are absent due to several factors such as difficulty in the logging operation and the tool timing. The aim of this research is to explore the form and the nature of artificial intelligence and machine …
-
Density-Wave Instability Characterization in Boiling Water Reactors under MELLLA+ Domain during ATWS
… profile on the stability boundary. Finally, two machine learning neural network-based models are developed and trained on various subsets of the experimental data. The results from each model showed certain benefits and drawbacks based on model complexity and physicality.
-
Inkjet 3D Printing Process Monitoring and Control for Quality Improvement
… developed for inkjet printing by integrating a machine learning neural network into the traditional proportional–integral–derivative (PID) control loop, which can link abstract features from the image to controllable jetting parameters without identifying the complex system transfer function. …
-
Exploring the Frontier of Amorphous Materials: Structure, Dynamics, Nucleation Behavior, and Glass Forming Ability
… of BaO·2SiO2 glass and the development of machine learning neural network potential. In total, six projects are presented in this dissertation. In the first project, the CuZrAl EAM potential was carefully examined against our experimental results such as the structure factor, radial pair …
-
Theoretical insight into the selective hydrogenation of acetylene on Pd-based catalysts
… transition metals. In Chapter 6, a Pd-C binary machine learning neural network potential is trained and used to search for the in-situ active site during the selective hydrogenation reaction. Chapter 7 concludes this thesis and proposed a paved path towards the rational design of …
-
Topics in Applied Algebraic Topology with a Measure-Theoretic Perspective
… topology in recent years to data analysis and machine learning. Persistent homology, one of the main such applications, constructs a filtered simplicial complex from a finite dataset, often using the Vietoris--Rips complex, and then computes algebraic invariants of the filtered simplicial …
-
Taxonomic Classification of Metagenomic Short Reads
… and Mycobacterium we implemented a feed-forward neural network. For Streptococcus species we obtained an accuracy of 95% while our models failed to reach higher than 31% accuracy for Mycobacterium species. One of the causes for these different results is that the pairwise BLAST identity within …
-
Αυτόματη ταξινόμηση κειμένων με χρήση αυτο-οργανούμενων χαρτών και μεθόδων μηχανικής μάθησης
… it and finally turning it into knowledge. Machine Learning techniques and more specifically techniques based on Unsupervised and Deep Neural Networks are considered as the most appropriate technology for the effective search and retrieval of information from texts. These techniques have the …
-
AUTOMATED DIAGNOSIS OF ACUTE APPENDICITIS BASED ON CLINICAL NOTES
… to doctors. We have developed a novel neural network model that is able to learn from free texts and additional real-valued features without any feature engineering. The performance of our model is close to that of emergency department (ED) doctors. Visualization shows that the model is …
-
Nanofluidic Platforms for Single-Molecule Protein Characterization and Peptide Fingerprinting of Proteins
… architecture is embedded within a nanofluidic network. This configuration improves analyte capture efficiency through geometric confinement, enables scalable manufacturing without serial drilling, and allows seamless integration with upstream processing modules. Using the same platform …
-
Optimizing the compliance of pedestrian facilities construction and alteration with accessibility requirements
… to assess the compliance of their pedestrian network with accessibility requirements. Transition plans must include a detailed schedule of all upgrade projects that are required to achieve full compliance with accessibility requirements. These self-evaluation and transition plan requirements …
-
DEVELOPMENT OF A 3D SIMULATION TOOL LEVERAGING GENETIC ALGORITHMS FOR NEURAL NETWORK OPTIMIZATION IN AUTOMATED DRIVING SYSTEMS: AN APPLICATION FOR SCENARIO ANALYSIS
… a simulation framework and software tool for machine learning consisting of a genetic algorithm (GA) with selection methods and artificial neural network (ANN) architectures all configurable via a user interface (UI), which guides the training and optimization of ANNs, allowing ADS policies to …
-
A machine-learning approach to reduce the risk of collision when changing lanes
… sensors is challenging. In this thesis, a machine learning approach is proposed for threat assessment for lane changing. The emphasis is on vehicle state prediction and maneuvers for autonomous emergency steering. The work includes feature selection, model selection, and model validation. …
-
Modelling COVID-19 Individual Risks in Sweden Using Spatial Information, Statistics and Machine Learning
… aims to model individual risks of Covid-19 using machine learning algorithms, and to extract information on feature importance from the fitted models. The models tested include logistic regression, random forest, support vector machines and neural network, and Shapley values were additionally …
-
Exploring Optimized CPU-Inference for Latency-Critical Machine Learning Tasks
In recent years, machine learning has grown to become increasingly prevalent for a wide range of applications spanning multiple industries. For some of these applica tions, low latency can be critical, which may limit the types of hardware that can be used. Graphical Processing Units (GPUs) have …
Page 1 of 7