Searcharxiv⌕ Search

arXiv subjects

Su Fong Chien

Publications and source records attributed to Su Fong Chien.

2 recordsLinked to original sources

Hybrid quantum learning for imbalanced blood-cell classification: domain adaptation and classifier design

Limited annotated data, class imbalance, and morphological similarity make white blood cell classification challenging. We benchmark hybrid variational quantum classifier heads against an affine baseline on 821 microscopy images across seven morphological classes. Using ImageNet-initialised ResNet34 backbones and repeated stratified five-fold cross-validation, we first compare direct transfer with intermediate adaptation on MLL23, a larger peripheral blood cell microscopy dataset. To guide the head comparison, we explore different encoding strategies, variational depth, and the number of independent circuit blocks. We then compare the classifier performance using the affine head and two hybrid heads across multiple random seeds, under a shared training and evaluation protocol. For this comparison, all backbones share the same MLL23-adapted initialisation. Intermediate adaptation increases mean macro-F1 across all four affine-head fine-tuning configurations. The largest gain occurs with a frozen backbone, where macro-F1 rises from $0.685$ to $0.786$, a relative improvement of approximately $14.7\%$. The shallow two-block hybrid head achieves a mean pooled out-of-fold macro-F1 of $0.865 \pm 0.010$, compared with $0.879 \pm 0.008$ for the affine head. The corresponding balanced accuracies are $0.886 \pm 0.008$ and $0.889 \pm 0.010$, respectively. In the architectural exploration, the two-block hybrid head achieves the highest macro-F1 and balanced accuracy among the evaluated hybrid configurations, while the effect of encoding varies across the considered metrics. Our results help guide the design and evaluation of hybrid classifier heads for imbalanced microscopy by linking architectural choices to overall performance and class-specific precision-recall trade-offs.

eess.IV↗

Joint Security-vs-QoS Game Theoretical Optimization for Intrusion Response Mechanisms for Future Network Systems

Network connectivity exposes the network infrastructure and assets to vulnerabilities that attackers can exploit. Protecting network assets against attacks requires the application of security countermeasures. Nevertheless, employing countermeasures incurs costs, such as monetary costs, along with time and energy to prepare and deploy the countermeasures. Thus, an Intrusion Response System (IRS) shall consider security and QoS costs when dynamically selecting the countermeasures to address the detected attacks. This has motivated us to formulate a joint Security-vs-QoS optimization problem to select the best countermeasures in an IRS. The problem is then transformed into a matching game-theoretical model. Considering the monetary costs and attack coverage constraints, we first derive the theoretical upper bound for the problem and later propose stable matching-based solutions to address the trade-off. The performance of the proposed solution, considering different settings, is validated over a series of simulations.

cs.GT↗