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 60 for “"input features"”.
-
Deep Learning for Human MicroRNA Precursor Prediction: A Systematic Literature Review
… in recent studies indicated that the use of few input features and a lack of domain understanding of selected input features could impact the accuracy of the results, causing significant bias and making the models appear to be a 'black box.' This study aims to gain more insight into the features …
-
Short-term wind power forecasting using artificial neural networks-based ensemble model
… can be obtained by selecting suitable input features, model parameters, and using forecasting techniques like spatial correlation and ensemble for ANNs. In this research, the effect of input features, model parameters, spatial correlation and ensemble techniques on short-term wind power …
-
Evaluating the Role of Balanced Causal and Non-Causal Features in Predictive Modeling
… challenging when the relationship between input features and target labels varies across domains. This study is motivated by recent work suggesting that causal features generalize better across domains as opposed to non-causal features. However, the evaluations comprised of varying sizes of …
-
An analysis of the performance and interpretability of machine learning classification algorithms to predict long-term share returns on the JSE
… summary plots to identify the most influential input features and to analyse the interpretability of these algorithms. The study found that ensemble-based classification algorithms, i.e. XGBoost, Random Forest and GradBoost, outperformed the other algorithms. Further analysis of the results …
-
Leveraging Subtle Verbalization and Speech Patterns to Help Evaluators Identify Usability Problem Encounters in Concurrent Think-aloud Sessions
… patterns in users’ verbalization and speech features that tend to occur when they encounter usability problems. Informed by the findings from the studies, I take the first step to designing computational methods that leverage these subtle patterns and the power of machine learning (ML) to …
-
Safe Exploration for Dynamic Computer Systems Optimization
… different applications and even different inputs of the same applications. Hence, models learned using data collected a priori are often suboptimal and violate safety constraints when used with new applications and/or inputs. To address this limitation, I introduce the concept of an …
-
GIS-based urban land use characterization and population modeling with subpixel information measured from remote sensing data
… and compare the performance of classifiers and input features. The proposed evaluation framework is applied to demonstrate the superiority of V-I-S fractions and LST for urban land use classification. It could also be applied to the assessment of input features and classifiers for other remote …
-
Decoding brains by paying attention: An attention-based fMRI task state decoding deep network architecture
… these models will include either handcrafted features or data driven approaches for downscaling the input features in successive layers. In this thesis, we explore and compare the effectiveness of linear, graph-based and attention-based methods for hierarchical classification. Furthermore, we …
-
Quantifying Dislocation Microstructures
… fields extracted via the D2C methods as input features for machine learning models for the classification of dislocation microstructures in nanoparticles. We found them to be well suited and that the combination of continuum fields is dependent on whether the microstructure is dominated …
-
Enhancing Cloud Database Performance: General-Purpose Compression and Workload-Driven Layout
… novel information-maximizing method for building input features. ColumnConstruct is competitive with existing ML compression methods for categorical data, but is not able to perform lossless compression on arbitrary tabular data. This limitation, as well as the additional compression and …
-
Empirical Analysis of Neural Architectures and Side Information in Financial Time Series Forecasting
… We explore the integration of options-derived features alongside traditional price data, compare recurrent architectures and transformer-based models, and evaluate multiple training strategies. Our key contributions include: (1) evidence that options-derived input features improve both error …
-
Comparing learned representations of deep neural networks
… network used for classification as converting inputs to a hidden representation in a high dimensional space and applying a linear classifier in this space. This work focuses on comparing these representations as well as the learned input features for different state-of-the-art convolutional …
-
Generic Architecture for Predictive Computational Modelling with Application to Financial Data Analysis: Integration of Semantic Approach and Machine Learning
… aimed at a more efficient selection of input features to the computational model. Since the model I propose is generic, it can be applied for data mining of all quantitative datasets (containing two-dimensional, size-mutable, heterogeneous tabular data); however, it is best suitable for …
-
Coastal water level prediction: a comparative study of statistical and machine learning techniques for time series forecasting
… Extreme gradient boosting with 24-hour of lagged input features was found to have the greatest overall test accuracy and stable predictions over the 96-hour forecast horizon. ARIMA models were the most accurate at predicting water levels in the positive stage (during high-tide). The exogenous …
-
Learning boiling properties of materials
… from experiments. Starting with high-level input features, we found that the sandblasting parameters used to manufacture the material are not predictive of boiling properties. This motivated us to investigate lower-level features: we developed and tested an algorithm to detect cavities in a …
-
Unsupervised discovery of activity primitives from multivariate sensor data
… which each pattern may span only a subset of the input features. An algorithm that can efficiently discover such "subdimensional" patterns was developed and evaluated. The discovery algorithms are evaluated by measuring the detection accuracy of discovered patterns relative to a set of expected …
-
Interpreting black-box models through sufficient input subsets
… process. In this thesis, we propose sufficient input subsets, minimal subsets of input features whose values form the basis for a model's decision. Our technique can rationalize decisions made by a black-box function on individual inputs and can also explain the basis for misclassifications. …
-
A Machine Learning-Based Heuristic to Explain Game-Theoretic Models
… on average, requires only 4.5 out of the 9 input features to explain its predictions effectively for a particular application. Therefore, our ensemble heuristic enhances the interpretability of game-theoretic optimization solutions, simplifying explanations and making them accessible to …
-
Modelling fitness and stability of G protein-coupled receptor variants
… of GPCR mutants in detergent. Combining these features with experimental measurements of GPCR expression further improved predictive performance beyond that reported for previous methods. Because of the simple structure of my model, the contributions of the input features could be checked …
Page 1 of 3