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 433 for “"SHAP"”.
-
Privacy-Preserving Federated SHAP Explanations of Clinical Prediction Models
… τι καθορίζει τις προβλέψεις τους. Οι τιμές SHAP είναι μια ευρέ- ως γνωστή μέθοδος για την επεξήγηση αυτών των προβλέψεων, καθώς δείχνουν πόσο συνεισφέρει κάθε χαρακτηριστικό σε αυτές. Οι επεξηγήσεις αυτές όμως υπολογίζονται α- πό τα δεδομένα, και προηγούμενες μελέτες έχουν δείξει ότι μπορούν …
-
Enhancing Neural Network Performance through SHAP-based Latent Class Integration
… with Dynamic Integration Network)—that integrate SHAP (SHapley Additive exPlanations)-based feature importance into the model training process to uncover and leverage latent substructures in data. Rather than clustering in the raw feature space, both architectures rely on absolute SHAP values to …
-
Igneous and metamorphic processes in the Shap Granite and its aureole
The Shap Granite outcrops in eastern Cumbria, N.W. England and is a post—orogenic granite intruded during the Lower Devonian (ie 394 Ma) into rocks of Ordovician to Siturian age. It is of adamellite composition and is notable in having megacrysts of orthoclase which crystallised late (relative to …
-
IoT network Malicious Behaviour Profiling Based on Explainable AI Using LSTM and SHAP
… using the Bayesian Optimization algorithm. SHAP analysis provides insightful individual and collective bot characteristic profiles. The model’s performance was evaluated using the augmented BCCC-Aposemat-Bot-IoT-24 dataset, built upon the Aposemat-Bot-IoT-23 dataset, and compared against …
-
Outage Prediction And Detecting Influential Factors Under Extreme Weather Events Using SHAP Analysis
As electricity demands continue to grow and extreme weather events become more frequent, the need for resilient energy infrastructure is increasingly urgent. This thesis addresses three critical areas of power system resilience and monitoring. The first section of the thesis reviews the Texas power …
-
3D-printed sHAP-PCL scaffolds as bone graft substitutes for spinal fusion surgery
… and strontium-substituted hydroxyapatite (sHAP) into polycaprolactone (PCL) composites, intended to replace autografts when contraindicated. To ensure the reproducibility of in vitro testing, a standard operating procedure (SOP) was developed to address cell sensitivity to environmental …
-
Controls on the Development and Distribution of K-Feldspar Megacrysts: Evidence From the Shap Granitoid
… phenocrysts grown in magmatic conditions. The Shap granitoid, Cumbria, N.E. England, is an example of a (393Ma) late-Caledonian intrusion. Geochemical, isotopic and REE evidence suggests that the intrusion was emplaced with relatively little fractionation from a subduction generated melt. …
-
Identification of cardiovascular risk factors of COVID-19 patients using SHAP values for tree-based machine learning models
… patients. Using an algorithm known as Tree SHAP, the final trained tree model is interpreted together with distributions of mortality to identify the most important predictors (risk factors).The method used in this thesis produces intuitive graphs for analyzing risk factors by using …
-
Personalized AI Driver Coaching in Heavy-Duty Trucks for Fuel-Efficient Driving - From Vehicle Telemetry to Eco-Driving Feedback through SHAP and Retrieval-Augmented LLMs
… from driving behaviour variables, while SHAP values were used to identify the behaviours that most strongly influenced each prediction in each segment-specific model. These explanations were then translated into conversational coaching feedback using a large language model. To support …
-
Relationships Between Habitat Variables and Biotic Integrity of the Embarras River Basin
… using the Stream Habitat Assessment Procedure (SHAP), while stream fish quality was determined by species richness and the Index of Biotic Integrity (IBI). A positive linear correlation was observed between SHAP and IBI (r2 = 0.409, n = 13, p < 0.05) for the 13 sites sampled. However no …
-
Detecting Eye Diseases and Intraocular Lesions from Fundus Images Using Deep Learning Approaches
… of blindness globally, by using a combination of SHapley Additive exPlanations (SHAP) analysis and transfer learning ResNet50 model. Achieving impressive accuracy rates of 97% for binary and 81% for multi-class DR classification, the study demonstrates the potential of SHAP analysis to enhance …
-
Increasing the Performance and Predictability of the Code Execution on an Embedded Java Platform
… vehicle of this thesis is the Java-programmed SHAP platform. It consists of its platform tool chain and the highly-customizable SHAP bytecode processor. SHAP offers a fully operational embedded CLDC environment, in which the proposed techniques have been implemented, verified, and evaluated. …
-
Towards Explainable Time Series: An Exploration Of Post-hoc Local Explanations From A Multi-disciplinary Perspective
… methods of explanation. We focus on LIME and SHAP, two of the most popular post-hoc local explanation methods. Our methods address the limitations of both LIME and SHAP in the following ways:<br/><br/>Both LIME and SHAP do not consider the complex temporal dependency of time series as they …
-
Predictive Modeling for B2B Cybersecurity Sales Optimization
… Model interpretation combines global SHAP importance, SHAP dependence plots on a complementary Random Forest, Partial Dependence Plots, and individual SHAP waterfall explanations. First, predictive power in this domain is concentrated in three binary process-and-stakeholder signals — …
-
Development of osteoinductive coatings for spinal implants (fusion cages)
… TiO2 and Mg and Sr-substituted hydroxyapatite (sHAP). To reduce variability during the project, the in vitro culture of mesenchymal stem cells (MSCs) in serum-free media (SFM) was studied. One commercially available SFM outperformed standard culture conditions and specialised media containing …
-
Using Explainability to Improve Predictive Modeling Performance
… This dissertation introduces three novel methods—SHAP-Enhanced Predictive Modeling (SEPM), Latent Structure-Based Sample Weighting (LSSW), and their hybrid SEPM-LSSW—to address these challenges by combining selective data refinement and adaptive weighting. In SEPM, high-impact observations are …
-
Dirbtinių neuroninių tinklų modelių paaiškinamumo ir intepretuojamumo tyrimai /
… and provides a new source of learning. LIME, SHAP, and Grad-CAM are explainable artificial intelligence methods that can help bring transparency to very complex and unclear models, uncover the reasoning behind the model’s decisions, and detect adversarial attacks in which an image is corrupted …
-
Interpretação de zonas carstificadas usando redes neurais convolucionais e interpretabilidade através de Explainable AI
… Artificial Intelligence (XAI) techniques using SHapley additive exPlanation (SHAP) values are applied to improve the interpretability and explainability of the generated models. These techniques were employed in order to assess the rules found by the models, the modeling quality and the presence …
-
Explainable Deep Learning for Medical Imaging Classification
… were developed for classification of data, and Shapley Additive exPlanations (SHAP) were used to explain predictions. A novel pipeline was developed to apply SHAP to volumetric medical imaging data.The application of explainable deep learning to various types of data and task demonstrates the …
Page 1 of 22