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 33 for “"classifier accuracy"”.
-
Semi-Supervised Self-Learning on Imbalanced Data Sets
… algorithms have been shown to improve classifier accuracy under a variety of conditions. In this thesis, semi-supervised self-learning using ensembles of random forests and fuzzy c-means clustering similarity was applied to three data sets to show where improvement is possible over …
-
Energy-Aware TinyML for Ambient-Powered, Hardware-Constrained IoT Nodes
… mean squared error (NMSE) and downstream classifier accuracy. The baseline models were further optimized using post-training quantization (PTQ), quantization-aware training (QAT), and a two-stage magnitude-based pruning method. Different optimization orders were compared with respect to …
-
Enhancing Gene Expression Signatures in Cancer Prediction Models: Understanding and Managing Classification Complexity
… and algorithms for reducing this complexity. Classifier algorithms that generate predictive signatures of cancer models must generalize to independent datasets for successful translation to clinical practice. The predictive performance of classifier models is shown to be dependent on the …
-
Improvements to Ambient Audio Collection Systems for Smart City Applications
… to have a system that meets the power and accuracy requirements. In this thesis, an ambient audio acquisition system was designed and improved using a custom threshold circuit and filtering. The results show a power reduction of up to 70% when compared to a standard implementation. The …
-
Pronunciation Ambiguities in Japanese Kanji
… an experiment using logistic regression (LR) classifier. A baseline is computed to compare with the LR classifier accuracy. The LR classifier improves the modeling performance by 16%. This experiment provides the first experimental research in Japanese single kanji homograph disambiguation. …
-
Embedded weights multi-objective feature selection : a novel hybrid method for sparse high-dimensional data
… benefits that go far beyond just improvements in classifier accuracy. Multi-objective approaches are typically chosen to minimize both the number of features and classifier error. These often combine heuristic search methods with machine learning algorithms to create wrapper methods. Wrappers, in …
-
Hybrid system optimization for industrial deployment under limited data conditions /
… showed that the main cause was not a weak classifier, but rather several preprocessing errors in the hybrid pipeline. Trays were not cropped correctly, an obsolete 180degree rotation remained in the normalization function, camera undistortion relied on incorrect frame resolution …
-
Feature selection and hierarchical classifier design with applications to human motion recognition
The performance of a classifier is affected by a number of factors including classifier type, the input features and the desired output. This thesis examines the impact of feature selection and classification problem division on classification accuracy and complexity. Proper feature selection can …
-
Landmine classification using possibilistic K-nearest neighbors with wideband electromagnetic induction data
… this thesis, a possibilistic K-nearest neighbor classifier is presented to distinguish between and classify mine and non-mine targets on data obtained from wideband electromagnetic induction sensors. The goal of this work is to develop methods for classifying wide-band electromagnetic induction …
-
Combination of PCA and DWT features from hyperspectral images for skin tumor detection
… of information. A support vector machine (SVM) classifier is used to determine if a pixel falls in a normal skin or tumorous skin categories. To provide additional classifier accuracy, an algorithm based on the average intensity of the pixel signal, is used to combine the two classifiers. The …
-
Exploring the Use of Enhanced SWAD Towards Building Learned Models that Generalize Better to Unseen Sources
… typically, take significant time to train. Classifier ensembles are areliable way to increase classifier accuracy and perhaps generalizability to unseen sources of data. These classifiers can be combined with a simple voting scheme. The problem is that having multiple models can very heavily …
-
Applying the Wrapper Approach for Auto Discovery of Under-Sampling and Over-Sampling Percentages on Skewed Datasets
… classes are very unequally represented. A naïve classifier learned from these skewed datasets is always biased towards the majority classes which constitute a major percentage of the samples in the dataset. As a result the accuracy on the minority classes is hampered. In many real world …
-
Developing Time Series Analysis Methods for M/EEG
… thesis extends MVPA by incorporating time series classifiers that explicitly model temporal dependencies to improve decoding accuracy, i.e., predicting experimental conditions from neural data. We employ three time series classification methods, each capturing temporal information over varying …
-
NLP-driven, data-curated, reliable modeling of health-related risk factors
… of flagged cases yields measurable gains in classifier accuracy and offers a general strategy for improving training data quality in other specialized domains. The second direction focuses on structured LLM reasoning pipelines. To complement extraction models, I design a multi-stage …
-
Remote multimodal sensor monitoring and analytics for aging and neurodegenerative clinical assessment support
… fused sensor and clinical text features improve classifier accuracy, outperforming single-modality approaches. Semi-supervised regression models for estimating between-clinic visit ALSFRS-R functional assessment trajectories were evaluated in individuals living with amyotrophic lateral sclerosis. …
-
Using a Multimodal Sensing Approach to Characterize Human Responses to Affective and Deceptive States
… were able to predict automatically, with higher accuracy than the baseline, affective and deceptive states of a person. In the affective state recognition, the classifier software differentiated affective state versus neutral state with 92.85% accuracy. Then it differentiated Positive State, …
-
MAXIMIZING LEARNING EFFICIENCY WITH LIMITED LABELED DATA: APPLICATIONS TO HEALTHCARE AND EDUCATION
… we address the problem of training accurate classifiers in low-resource settings with limited labeled data. In our first approach, MERIT (Minimal Supervision Through Label Augmentation for Biomedical Relation Extraction), we propose using shortest dependency path (SDP) representation and …
-
Deep SELECTOR-JPEG: ADAPTIVE JPEG IMAGE COMPRESSION FOR COMPUTER VISION IN IMAGE CLASSIFICATION AND HUMAN VISION
… attention to CV, resulting in classification accuracy drop of DNNs, especially at high Compression Ratios (CRs). This work presents Deep Selector-JPEG, an adaptive JPEG compression method that simultaneously targets both image classification and HV. For each image, Deep Selector-JPEG selects a …
-
Automatic face recognition using stereo images
… depth reconstruction, which in turn led to poor classifier accuracy for both 3D surface matching and 211) 2 depth maps. Recognition experiments axe performed on the Sheffield Dataset, consisting 692 images of 22 individuals with varying pose, illumination and expressions.
-
Applications of Hyper-parameter Optimisations for Static Malware Detection
… a variety of ML algorithms for building malware classifiers and also how best to tune the parameters of those algorithms – a process generally known as hyper-parameter optimisation (HPO). Firstly, we examine the effects of some simple (model-free) ways of parameter tuning together with a …
Page 1 of 2