arXiv subjects

Chun-Kai Huang

Publications and source records attributed to Chun-Kai Huang.

4 recordsLinked to original sources

arXiv2025

MedFuse: Multiplicative Embedding Fusion For Irregular Clinical Time Series

Clinical time series derived from electronic health records (EHRs) are inherently irregular, with asynchronous sampling, missing values, and heterogeneous feature dynamics. While numerical laboratory measurements are highly informative, existing embedding strategies usually combine feature identity and value embeddings through additive operations, which constrains their ability to capture value-dependent feature interactions. We propose MedFuse, a framework for irregular clinical time series centered on the MuFuse (Multiplicative Embedding Fusion) module. MuFuse fuses value and feature embeddings through multiplicative modulation, preserving feature-specific information while modeling higher-order dependencies across features. Experiments on three real-world datasets covering both intensive and chronic care show that MedFuse consistently outperforms state-of-the-art baselines on key predictive tasks. Analysis of the learned representations further demonstrates that multiplicative fusion enhances expressiveness and supports cross-dataset pretraining. These results establish MedFuse as a generalizable approach for modeling irregular clinical time series.

cs.AI↗

arXiv2024

Scalable Numerical Embeddings for Multivariate Time Series: Enhancing Healthcare Data Representation Learning

Multivariate time series (MTS) data, when sampled irregularly and asynchronously, often present extensive missing values. Conventional methodologies for MTS analysis tend to rely on temporal embeddings based on timestamps that necessitate subsequent imputations, yet these imputed values frequently deviate substantially from their actual counterparts, thereby compromising prediction accuracy. Furthermore, these methods typically fail to provide robust initial embeddings for values infrequently observed or even absent within the training set, posing significant challenges to model generalizability. In response to these challenges, we propose SCAlable Numerical Embedding (SCANE), a novel framework that treats each feature value as an independent token, effectively bypassing the need for imputation. SCANE regularizes the traits of distinct feature embeddings and enhances representational learning through a scalable embedding mechanism. Coupling SCANE with the Transformer Encoder architecture, we develop the Scalable nUMerical eMbeddIng Transformer (SUMMIT), which is engineered to deliver precise predictive outputs for MTS characterized by prevalent missing entries. Our experimental validation, conducted across three disparate electronic health record (EHR) datasets marked by elevated missing value frequencies, confirms the superior performance of SUMMIT over contemporary state-of-the-art approaches addressing similar challenges. These results substantiate the efficacy of SCANE and SUMMIT, underscoring their potential applicability across a broad spectrum of MTS data analytical tasks.

cs.LG↗

arXiv2020

A Longitudinal Analysis of University Rankings

Pressured by globalization and the increasing demand for public organisations to be accountable, efficient and transparent, university rankings have become an important tool for assessing the quality of higher education institutions. It is therefore important to carefully assess exactly what these rankings measure. In this paper, the three major global university rankings, The Academic Ranking of World Universities, The Times Higher Education and the Quacquarelli Symonds World University Rankings, are studied. After a description of the ranking methodologies, it is shown that university rankings are stable over time but that there is variation between the three rankings. Furthermore, using Principal Component Analysis and Exploratory Factor Analysis, we show that the variables used to construct the rankings primarily measure two underlying factors: a universities reputation and its research performance. By correlating these factors and plotting regional aggregates of universities on the two factors, differences between the rankings are made visible. Last, we elaborate how the results from these analysis can be viewed in light of often voiced critiques of the ranking process. This indicates that the variables used by the rankings might not capture the concepts they claim to measure. Doing so the study provides evidence of the ambiguous nature of university ranking's quantification of university performance.

cs.SI↗

arXiv2019

ZomeFab: Cost-effective Hybrid Fabrication with Zometools

In recent years, personalized fabrication has received considerable attention because of the widespread use of consumer-level three-dimensional (3D) printers. However, such 3D printers have drawbacks, such as long production time and limited output size, which hinder large-scale rapid-prototyping. In this paper, for the time- and cost-effective fabrication of large-scale objects, we propose a hybrid 3D fabrication method that combines 3D printing and the Zometool construction set, which is a compact, sturdy, and reusable structure for infill fabrication. The proposed method significantly reduces fabrication cost and time by printing only thin 3D outer shells. In addition, we design an optimization framework to generate both a Zometool structure and printed surface partitions by optimizing several criteria, including printability, material cost, and Zometool structure complexity. Moreover, we demonstrate the effectiveness of the proposed method by fabricating various large-scale 3D models.

cs.GR↗