Sparsity-inducing multiple kernel Fisher discriminant analysis (MK-FDA) has been studied in the literature. Building on recent advances in non-sparse multiple kernel learning (MKL), we propose a non-sparse version of MK-FDA, which imposes a general ℓ p norm regularisation on the kernel weights. We formulate the associated optimisation problem as a semi-infinite program (SIP), and adapt an iterative wrapper algorithm to solve it. We then discuss, in light of latest advances in MKL optimisation techniques, several reformulations and optimisation strategies that can potentially lead to significant improvements in the efficiency and scalability of MK-FDA. We carry out extensive experiments on six datasets from various application areas, and compare closely the performance of ℓ p MK-FDA, fixed norm MK-FDA, and several variants of SVM-based MKL (MK-SVM). Our results demonstrate that ℓ p MK-FDA improves upon sparse MK-FDA in many practical situations. The results also show that on image categorisation problems, ℓ p MK-FDA tends to outperform its SVM counterpart. Finally, we also discuss the connection between (MK-)FDA and (MK-)SVM, under the unified framework of regularised kernel machines.

Electronic medical records (EMR) have largely replaced hand-written patient files in healthcare.The growing pool of EMR data presents a significant resource in medical research, but the U.S. Health Insurance Portability and Accountability Act (HIPAA) mandates redacting medical records before performing any analysis on the same. This process complicates obtaining medical data and can remove much useful information from the record. As part of a larger project involving ontologydriven medical processing, we employ a method of recognizing protected health information (PHI) that maps to ontological terms. We then use the relationships defined in the ontology to redact medical texts so that roles and semantics of terms are retained without compromising anonymity. The method is evaluated by clinical experts on several hundred medical documents, achieving up to a 98.8% f-score, and has already shown promise for retaining semantic information in later processing.