K. Lim

MS-RBC: A Range Bias Correction Method for Saturated Returns in Multiwavelength Underwater LiDAR

Multiwavelength underwater LiDAR can simultaneously provide 3-D geometric and spectral information for precise seafloor topography mapping and benthic habitat characterization. However, achieving both high-ranging accuracy and cross-wavelength ranging consistency remains challenging. Systems employing a supercontinuum...

A Survey on Vision Transformers: Design Pressures, Architectural Taxonomy, and Future Outlook

Vision Transformers (ViTs) have developed from a patch-based alternative to convolutional backbones into a diverse architectural family spanning tokenization, attention reformulation, hierarchy construction, hybrid design, token economy, and training-oriented regularization. As this literature has matured, the main que...

Diffusion-inspired prototypical network for few-shot fine-grained classification

Churn Prediction and Risk Profiling Using Machine Learning and Customer Segmentation

Customer churn occurs when they stop doing business with a company, leading to the loss of customers. Customer churn prediction has become a significant technique for identifying customers who are about to churn. The proposed method begins with data preprocessing, involving the standardization of data types and the imp...

AM-DANet: Additive margin with dynamic augmentation network for speaker identification

The proposed framework improves data utilization through an improved preprocessing pipeline and incorporates an additive margin-based learning strategy to promote strong inter-class separability while preserving compact intra-class representations, enabling the model to learn more discriminative speaker embeddings.