Beng Chin Ooi
YOU?
Author Swipe
View article: Transformer-Based Deep Learning for Multiplanar Cervical Spine MRI Interpretation: Comparison with Spine Surgeons and Radiologists
Transformer-Based Deep Learning for Multiplanar Cervical Spine MRI Interpretation: Comparison with Spine Surgeons and Radiologists Open
Background: Degenerative cervical spondylosis (DCS) is a common and potentially debilitating condition, with surgery indicated in selected patients. Deep learning models (DLMs) can improve consistency in grading DCS neural stenosis on magn…
View article: NeurStore: Efficient In-database Deep Learning Model Management System
NeurStore: Efficient In-database Deep Learning Model Management System Open
With the prevalence of in-database AI-powered analytics, there is an increasing demand for database systems to efficiently manage the ever-expanding number and size of deep learning models. However, existing database systems typically stor…
View article: Exploring the Potential of a Deep Learning Model for Early CT Detection of High-Grade Metastatic Epidural Spinal Cord Compression and Its Impact on Treatment Delays
Exploring the Potential of a Deep Learning Model for Early CT Detection of High-Grade Metastatic Epidural Spinal Cord Compression and Its Impact on Treatment Delays Open
Background: Delay in diagnosing metastatic epidural spinal cord compression (MESCC) adversely impacts clinical outcomes. High-grade MESCC is frequently overlooked on routine staging CT scans. We aim to assess the potential of our deep lear…
View article: Heartcare Suite: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding
Heartcare Suite: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding Open
Although electrocardiograms (ECG) play a dominant role in cardiovascular diagnosis and treatment, their intrinsic data forms and representational patterns pose significant challenges for medical multimodal large language models (Med-MLLMs)…
View article: In-Context Adaptation to Concept Drift for Learned Database Operations
In-Context Adaptation to Concept Drift for Learned Database Operations Open
Machine learning has demonstrated transformative potential for database operations, such as query optimization and in-database data analytics. However, dynamic database environments, characterized by frequent updates and evolving data dist…
View article: <i>HAKES</i> : Scalable Vector Database for Embedding Search Service
<i>HAKES</i> : Scalable Vector Database for Embedding Search Service Open
Modern deep learning models capture the semantics of complex data by transforming them into high-dimensional embedding vectors. Emerging applications, such as retrieval-augmented generation, use approximate nearest neighbor (ANN) search in…
View article: The Cambridge Report on Database Research
The Cambridge Report on Database Research Open
On October 19 and 20, 2023, the authors of this report convened in Cambridge, MA, to discuss the state of the database research field, its recent accomplishments and ongoing challenges, and future directions for research and community enga…
View article: CCaaLF: Concurrency Control as a Learnable Function
CCaaLF: Concurrency Control as a Learnable Function Open
Concurrency control (CC) algorithms are important in modern transactional databases, as they enable high performance by executing transactions concurrently while ensuring correctness. However, state-of-the-art CC algorithms struggle to per…
View article: HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation Open
We present HealthGPT, a powerful Medical Large Vision-Language Model (Med-LVLM) that integrates medical visual comprehension and generation capabilities within a unified autoregressive paradigm. Our bootstrapping philosophy is to progressi…
View article: CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning
CtxPipe: Context-aware Data Preparation Pipeline Construction for Machine Learning Open
Machine learning models are only as good as their training data. Simple models trained on well-chosen features extracted from the raw data often outperform complex models trained directly on the raw data. Data preparation pipelines, which …
View article: SeSeMI: Secure Serverless Model Inference on Sensitive Data
SeSeMI: Secure Serverless Model Inference on Sensitive Data Open
Model inference systems are essential for implementing end-to-end data analytics pipelines that deliver the benefits of machine learning models to users. Existing cloud-based model inference systems are costly, not easy to scale, and must …
View article: VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection
VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection Open
Fraud detection presents a challenging task characterized by ever-evolving fraud patterns and scarce labeled data. Existing methods predominantly rely on graph-based or sequence-based approaches. While graph-based approaches connect users …
View article: NeurDB: On the Design and Implementation of an AI-powered Autonomous Database
NeurDB: On the Design and Implementation of an AI-powered Autonomous Database Open
Databases are increasingly embracing AI to provide autonomous system optimization and intelligent in-database analytics, aiming to relieve end-user burdens across various industry sectors. Nonetheless, most existing approaches fail to acco…
View article: VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection
VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection Open
Fraud detection presents a challenging task characterized by ever-evolving fraud patterns and scarce labeled data. Existing methods predominantly rely on graph-based or sequence-based approaches. While graph-based approaches connect users …
View article: GCON: Differentially Private Graph Convolutional Network via Objective Perturbation
GCON: Differentially Private Graph Convolutional Network via Objective Perturbation Open
Graph Convolutional Networks (GCNs) are a popular machine learning model with a wide range of applications in graph analytics, including healthcare, transportation, and finance. However, a GCN trained without privacy protection measures ma…
View article: CohortNet: Empowering Cohort Discovery for Interpretable Healthcare Analytics
CohortNet: Empowering Cohort Discovery for Interpretable Healthcare Analytics Open
Cohort studies are of significant importance in the field of healthcare analysis. However, existing methods typically involve manual, labor-intensive, and expert-driven pattern definitions or rely on simplistic clustering techniques that l…
View article: Characterizing the Performance and Cost of Blockchains on the Cloud and at the Edge
Characterizing the Performance and Cost of Blockchains on the Cloud and at the Edge Open
While state-of-the-art permissioned blockchains can achieve thousands of transactions per second on commodity hardware with x86/64 architecture, their performance when running on different architectures, such as ARM, is not clear. The goal…
View article: NeurDB: An AI-powered Autonomous Data System
NeurDB: An AI-powered Autonomous Data System Open
In the wake of rapid advancements in artificial intelligence (AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB (AIxDB) promises a new generation of data systems, which will relieve the b…
View article: Powering In-Database Dynamic Model Slicing for Structured Data Analytics
Powering In-Database Dynamic Model Slicing for Structured Data Analytics Open
Relational database management systems (RDBMS) are widely used for the storage of structured data. To derive insights beyond statistical aggregation, we typically have to extract specific subdatasets from the database using conventional da…
View article: Anytime Neural Architecture Search on Tabular Data
Anytime Neural Architecture Search on Tabular Data Open
The increasing demand for tabular data analysis calls for transitioning from manual architecture design to Neural Architecture Search (NAS). This transition demands an efficient and responsive anytime NAS approach that is capable of return…
View article: Managing Metaverse Data Tsunami: Actionable Insights
Managing Metaverse Data Tsunami: Actionable Insights Open
In the metaverse the physical space and the virtual space co-exist, and interact simultaneously. While the physical space is virtually enhanced with information, the virtual space is continuously refreshed with real-time, real-world inform…
View article: Development of a dental diet-tracking mobile app for improved caries-related dietary behaviours: Key features and pilot evaluation of quality
Development of a dental diet-tracking mobile app for improved caries-related dietary behaviours: Key features and pilot evaluation of quality Open
Objective Diet significantly contributes to dental decay (caries) yet monitoring and modifying patients’ diets is a challenge for many dental practitioners. While many oral health and diet-tracking mHealth apps are available, few focus on …
View article: Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective
Exploring Privacy and Fairness Risks in Sharing Diffusion Models: An Adversarial Perspective Open
Diffusion models have recently gained significant attention in both academia and industry due to their impressive generative performance in terms of both sampling quality and distribution coverage. Accordingly, proposals are made for shari…
View article: METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection
METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection Open
Real-time analytics and decision-making require online anomaly detection (OAD) to handle drifts in data streams efficiently and effectively. Unfortunately, existing approaches are often constrained by their limited detection capacity and s…
View article: Application of artificial intelligence in the assessment of thyroid eye disease (TED) - a scoping review
Application of artificial intelligence in the assessment of thyroid eye disease (TED) - a scoping review Open
Background There is emerging evidence which suggests the utility of artificial intelligence (AI) in the diagnostic assessment and pre-treatment evaluation of thyroid eye disease (TED). This scoping review aims to (1) identify the extent of…
View article: VeriTxn: Verifiable Transactions for Cloud-Native Databases with Storage Disaggregation
VeriTxn: Verifiable Transactions for Cloud-Native Databases with Storage Disaggregation Open
Cloud-native databases become increasingly popular while exposing to greater data security and correctness risks. Existing verifiable outsourced databases overlook either the correctness risk of transactions, or the disaggregation architec…
View article: Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs
Secure and Verifiable Data Collaboration with Low-Cost Zero-Knowledge Proofs Open
Organizations are increasingly recognizing the value of data collaboration for data analytics purposes. Yet, stringent data protection laws prohibit the direct exchange of raw data. To facilitate data collaboration, federated Learning (FL)…
View article: Passive Inference Attacks on Split Learning via Adversarial Regularization
Passive Inference Attacks on Split Learning via Adversarial Regularization Open
Split Learning (SL) has emerged as a practical and efficient alternative to traditional federated learning. While previous attempts to attack SL have often relied on overly strong assumptions or targeted easily exploitable models, we seek …