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 149 for “"Explainable AI (XAI)"”.
-
EXPLAINABLE AI (XAI) FOR A MACHINE LEARNING HEART DISEASE PREDICTION MODEL
Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, …
-
Efficient on-device saliency prediction via knowledge distillation and explainable AI (XAI)
… and interpretability. Thus, by leveraging Explainable AI, insight is provided into how knowledge is transferred from the teacher to the student network under the knowledge distillation method.
-
INVESTIGATING COLLABORATIVE EXPLAINABLE AI (CXAI)/SOCIAL FORUM AS AN EXPLAINABLE AI (XAI) METHOD IN AUTONOMOUS DRIVING (AD)
Explainable AI (XAI) systems primarily focus on algorithms, integrating additional information into AI decisions and classifications to enhance user or developer comprehension of the system's behavior. These systems often incorporate untested concepts of explainability, lacking grounding in the …
-
Attention to Context is What xAI Needs: A Framework for Generating Context-Dependent Requirements for Human-Centric Explainable AI (xAI)
… deployment of Artificial Intelligence (AI) systems across vital societal domains have yielded promising results, their opacity - the "black box" problem - poses significant barriers to trust in, accountability of, broad acceptance, and adoption of this transformative technology. While …
-
Mitigating noise and instability in Industrial Explainable AI using Density-Aware and Complexity-Adjusted Explanations
… of instability and noise sensitivity in Explainable AI (XAI) within high-stakes manufacturing environments. We review the state of the art, identifying a gap in robust local explanations. We introduce two novel contributions: CESHAP, a complexity-aware feature importance method, and …
-
Toward XAI for Intelligent Tutoring Systems : a case study
… a step toward understanding when explanations of AI-driven hints and feedback are useful in Intelligent Tutoring Systems (ITS). We added an explanation functionality for the adaptive hints provided by the Adaptive CSP (ACSP) applet, an intelligent interactive simulation that helps students learn …
-
Útoky na algoritmy AI a obrany proti nim
Bezpečnost AI a útoky na umělou inteligenci představují komplexní a dosud nedostatečně prozkoumanou problematiku. Cílem této práce je nabídnout ucelený přehled klíčových metod a možných vysvětlení útoků na AI a obran proti nim, aby se toto téma stalo přístupnějším a srozumitelnějším pro širší …
-
AI-Driven Cardiorespiratory Signal Processing: Separation, Clustering, and Anomaly Detection
This thesis applies artificial intelligence (AI) to separate, cluster, and analyze cardiorespiratory sounds. We recorded a new dataset and developed several AI models, including generative AI methods based on large language models (LLMs) for guided separation, explainable AI (XAI) techniques to …
-
Probing Human Visual Strategies Using Interpretability Methods for Artificial Neural Networks
… visual strategies during object recognition remains a challenge in vision science. Existing psychophysical methods used to investigate these strategies are limited in accurately interpreting human decisions. Recently, artificial neural network (ANN) models, which show remarkable similarities to …
-
Article Search Tool and Topic Classifier
This thesis focuses on 3 main tasks related to Document Recommendations. The first approach deals with applying existing techniques on Document Recommendations using Doc2Vec. A robust representation of the same is presented to understand how noise induced in the embedding space affects predictions …
-
Explainability of multi-modal machine learning and deep learning applications in health
Artificial Intelligence (AI) continues to be developed and has the potential to be incorporated into health, allowing for more efficient and effective diagnosis. However, many AI models operate as ”black-boxes” in how conclusions are drawn or made, leading to a lack of trust. Explainable AI (XAI) …
-
Personalized Explanations of Robot Behavior for Human Users
AI and robotic agents are becoming increasingly prevalent in sectors such as transportation, manufacturing, and disaster response. As these robots are integrated into existing workflows, it is important for their users to understand and anticipate their actions to ensure efficient human-robot …
-
UNDERSTANDING MODEL EXPLAINABILITY AND PRIVACY FOR FACIAL RECOGNITION APPLICATIONS
The use of facial data in AI applications raises privacy concerns and requires trustbuilding through providing explanations. 1) We argue that Explainable AI (XAI) can pose privacy risks. While current model inversion attacks reconstruct input data from model predictions, we exploit model …
-
"Ethics, Governance, and Bias Mitigation in AI-Enabled loT Applications: A Focus on Transparency and Fairness
… of Things (IoT) and Artificial Intelligence (AI) technologies promises to address urban challenges yet raises significant security and ethical concerns. This study emphasizes the need for robust governance frameworks to ensure the ethical deployment of these technologies, focusing on the roles …
-
Explainable Autoencoder Deciphering Key Pathways Underlying Cancer Expression Patterns
… interpretations, we developed a tool, XAE4Exp (eXplainable AutoEn-coder for Expression data), which integrates AE and SHapley Additive exPlanations (SHAP), a flagship technique in the field of eXplainable AI (XAI). It quantitatively evaluates the contributions of each gene to the hidden …
-
Post-hoc explainable semantic image segmentation: applications for interpretability and adversarial attacks /
Explainable AI (XAI) has become increasingly important in computer vision applications. While substantial progress has been made in explainable image classification, XAI in semantic segmentation remains underexplored despite its critical role in healthcare, autonomous systems, and other high-stakes …
-
Human-in-the-loop and Storytelling-based Explainable Frameworks for the Next Generation of Explainable Ensemble Methods and Artificial Intelligence Techniques
Artificial intelligence (AI) is being adopted in diverse fields, including medical diagnosis and scientific research, to assist with decision-making thanks to its ability to learn underlying patterns from large amounts of data. However, these advances present a challenge. Modern AI systems, …
-
Interactive AI Tutors for Training the Workforce of the Future
The need to train new workers effectively and upskill the existing workforce is a challenge faced by almost every industry across the globe. The healthcare industry, in particular, is confronting a crisis. The World Health Organization (WHO) projects a shortage of 10 million healthcare workers by …
-
Explainable data fusion
The recent resurgence of Artificial Intelligence (AI), specifically in the context of applications like healthcare, security and defense, IoT, and other areas that have a big impact on human life, has led to a demand for eXplainable AI (XAI). The production of explanations is argued to be a key …
-
Adversarial Explanations for Text-Based Local Surrogate Models
… as one of the most commonly referenced tools in explainable AI (XAI) frameworks that is integrated into critical machine learning applications–e.g., healthcare and finance. However, its stability remains little explored, especially in the context of text data, due to the unique challenges when it …
Page 1 of 8