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 1085 for “"ML models"”.
-
Towards Generalizable and Robust Multimodal ML Models for Video Emotion Recognition
… visual modality. Multimodal Machine Learning (MML) as a field aims to capture, process and infer from information across modalities. However, representation of cross-modal information is a challenging task, due to core characteristics of modalities such as heterogeneity. In addition to …
-
Interpretation and Robustness of Black-Box ML Models for Secure Cyber Space
The advent of sophisticated Machine Learning (ML) models has revolutionized the cybersecurity landscape, offering unprecedented capabilities to address complex challenges. Despite the ML model's capabilities, such models are still perceived as black boxes, the critical aspects of interpretability …
-
Impact of data quality on ML models: Improving data quality with Outlier Detection
In the dynamic landscape of Machine Learning (ML) applications, data quality comes out to be an important factor that impacts the performance of ML models. Through this thesis, we present a study that proposes innovative methods for enhancing data quality through an iterative data recapture …
-
Acoustic Sensing for Assistive Living: Investigating ML Models to Address Privacy and Data Collection Challenges
Assistive living technologies have advanced significantly, utilising wearable sensors and other smart devices. While wearables are effective in monitoring human activity, they may become impractical when the elderly are resistant to them. In contrast, audio sensing can passively monitor daily …
-
Mitigating Negative Impacts from Socio-Technical AI
… the past decade, data-driven Machine Learning (ML) models have become more popular because of the advances in their capabilities driven by increases in compute power and available data. ML models allow for speedier analysis of and learning from data than human analysts typically could provide. …
-
Robust Machine Learning Against Faults in Micro-Controllers and Stragglers in Distributed Training on the Cloud
… in the past decade. Optimally deploying ML models onto smaller devices and efficiently training more powerful ML models in parallel in different distributed system topologies have drawn interests. This thesis studies the robustness of ML models in the two scenarios when deployed on …
-
Examining the reliability of integrating machine learning with rock mass characterization and classification data
… increase in the use of machine learning (ML) in rock engineering. While ML has the potential to revolutionize rock engineering by increasing efficiency and lowering costs, the ML models first need to be reliable. Developing reliable ML models requires good quality (i.e., objective) data …
-
DEVELOPMENT AND APPLICATION OF ENSEMBLE MACHINE LEARNING ALGORITHMS TO ENABLE A PRIORI, HIGH-FIDELITY, AND PROMPT PREDICTIONS AND OPTIMIZATIONS OF COMPLEX MATERIALS AND SYSTEMS
… develop theoretical frameworks (i.e., empirical models) that could produce reliable predictions of properties of complex materials. In recent years, scientists have harnessed the power of machine learning (ML) and “Big” data to uncover the underlying mixture design-property correlations and …
-
Defining Safe Training Datasets for Machine Learning Models Using Ontologies
<p>Machine Learning (ML) models have been gaining popularity in recent years in a wide variety of domains, including safety-critical domains. While ML models have shown high accuracy in their predictions, they are still considered black boxes, meaning that developers and users do not know how the …
-
Machine learning for executable code in software testing and verification
… code. Recent advances in machine learning (ML) models, especially large language models (LLMs), can help reduce manual effort for testing and verification. Namely, developers can benefit from ML models’ predictions to write tests and proofs faster. However, existing models understand and …
-
Risk assessment in suspected acute coronary syndrome with decision support tools and artificial intelligence
… explores the potential of machine learning (ML) models as decision support tools to improvethe early identification of AMI and reduce unnecessary diagnostic procedures.The research consists of four studies. Study I evaluates whether combining glucose measurements withhs-cTnT improves the 0/1h …
-
Integrating Physics into Machine Learning for Monitoring Scientific Systems
Machine learning (ML) has transformed all aspects of our life including how we make decisions, entertain ourselves, and interact with each other. The power of ML models lies in their ability to automatically extract useful patterns from complex data. Given the well-known success of ML in commercial …
-
Balancing Privacy and Accuracy in IoT using Domain-Specific Features for Time Series Classification
… sensitive information and for machine learning (ML) tasks. However, there is a trade-off in balancing privacy and achieving ML accuracy since ε-DP reduces the model’s accuracy for classification tasks. Moreover, not many studies have applied DP to time series from sensors and Internet-of-Things …
-
PERFORMANCE OF EXTERNALLY VALIDATED MACHINE LEARNING MODELS BASED ON HISTOPATHOLOGY IMAGES FOR THE DIAGNOSIS, CLASSIFICATION, PROGNOSIS, OR TREATMENT OUTCOME PREDICTION IN FEMALE BREAST CANCER: A SYSTEMATIC REVIEW
Background: Numerous machine learning (ML) models have been developed for breast cancer using various types of data (e.g., images, text). Successful external validation (EV) of ML models is considered as important evidence of their generalizability. Objectives: Assess the performance of externally …
-
Data-Centric Bias Mitigation in Machine Learning Life Cycle
As Machine Learning (ML) becomes increasingly central to decision-making processes in our society, it is crucial to acknowledge the potential of these ML models to inadvertently perpetuate biases, disproportionately impacting certain demographic groups and individuals. For instance, some ML models …
-
SAMPLE-EFFICIENT AUTOMATED MACHINE LEARNING WITH BAYESIAN OPTIMIZATION
… hyperparameter optimization of machine learning (ML) models, referred to as AutoML, has been a challenging problem for practitioners, mainly due to the high computational cost of training modern ML models and the lack of gradient information with respect to the model hyperparameters. To this end, …
-
Metalearning by Exploiting Granular Machine Learning Pipeline Metadata
Automatic machine learning (AutoML) systems have been shown to perform better when they use metamodels trained offline. Existing offline metalearning approaches treat ML models as black boxes. However, modern ML models often compose multiple ML algorithms into ML pipelines. We expand previous …
-
Assessing The Impact of Differential Privacy on Data Security in Machine Learning Applications
… privacy, accuracy, and the practical utility of ML models. The research methods involve a thorough review of existing literature, development of a methodology to assess differential privacy's impact, and conducting comparative analyses on ML models with and without differential privacy. Findings …
-
detection and diagnosis of multiple dependent faults in HVAC systems using machine learning techniques
… in the HVAC systems. Machine learning (ML) models which are developed from BAS trend data without information about the physical system, proved in the past, good performance for analysis the linear and non-linear systems. Therefore, ML models due to their capacity for distinguishing the …
Page 1 of 55