arXiv subjects

Anne H. H. Ngu

Publications and source records attributed to Anne H. H. Ngu.

16 recordsLinked to original sources

arXiv2026

Class-Conditioned Gaussian Mixture Modeling for Imbalanced Time Series Quantification

Quantification, estimating class prevalences in bags of unlabeled instances is vital in domains where aggregate statistics are more important than individual instance labels, such as biosignal monitoring, fall detection, and activity recognition. We investigate this issue in the challenging setting of imbalanced time series data and develop CC-GMNet-TS, a class-conditioned Gaussian mixture quantifier that combines a Transformer-based feature extractor with per-class latent mixtures. Unlike previous mixture-based quantifiers, which use a single Gaussian mixture shared by all classes, CC-GMNet-TS assigns each class its own compact mixture in a bounded latent space and scores segment embeddings against these class-specific components to create bag-level representations that emphasize rare but informative patterns. Bags are constructed from labeled pools using the Artificial Prevalence Protocol (APP) and prior shift bag sampling (PShift) to cover a wide range of class prevalence scenarios, and the model is trained end-to-end with a quantification-oriented loss. Experiments on three benchmarks: EMG Data for Gestures, SmartFallMM, and UCI-HAR show that CC-GMNet-TS achieves lower error across the three benchmarks compared to traditional aggregators and recent deep quantifiers, while ablations confirm the contributions of both the Transformer backbone and class-conditioned mixtures during PShift.

cs.LG↗

arXiv2026

MA-RAG: Multi-Agent Retrieval-Augmented Generation for Query-Driven Summarization of Longitudinal Parkinson's Disease Assessments

Accurate interpretation of single-visit and longitudinal clinical assessments for Parkinson's disease is time-consuming and often depends on specialist expertise. Although large language models (LLMs) can generate natural language summaries, they frequently lack domain-specific clinical grounding and struggle to produce factually correct and temporally consistent responses for structured longitudinal assessment data. To address these limitations, we propose MA-RAG, a query-driven multi-agent retrieval-augmented generation framework that decomposes clinical reasoning into domain-specialized agents, combines structured fact extraction, and synthesizes clinically grounded summaries through a final verification stage. The framework supports four clinical analysis tasks: single-session, trajectory, comparison, and cohort summarization. We evaluate MA-RAG using objective metrics, namely Fact Precision, Hallucination Rate, Temporal Fidelity, and Semantic Similarity, together with subjective evaluations conducted by clinical experts. Compared to Traditional, RAG-only, and Single-agent RAG baselines, MA-RAG substantially improves factual correctness, achieving up to a 122% relative increase in Fact Precision (from 0.436 to 0.990) and reducing the Hallucination Rate by up to 98% (from 0.564 to 0.010), while consistently receiving top ratings from clinical experts for organization and clinical usefulness. These results demonstrate that domain-specialized multi-agent reasoning enables reliable query-driven summarization of structured longitudinal clinical assessment data.

cs.CL↗

arXiv2026

You Don't Need Attention: Gated Convolutional Modeling for Watch-Based Fall Detection

Existing deep learning approaches for wearable fall detection systems rely on self-attention mechanisms that impose quadratic computational overhead, distributing weights across all time steps. This global weight distribution impairs the precise localization of the brief impact signatures that characterize falls within short, fixed-length windows. To overcome this challenge, we propose Gated-CNN, a lightweight dual-stream architecture that processes accelerometer and gyroscope streams through independent one-dimensional convolutional feature extractors, followed by (i) a sigmoid gating module that selectively suppresses uninformative background activations while amplifying fall-discriminative features, (ii) a global average pooling layer that compresses each stream into a compact fixed-length descriptor, and (iii) a shared classification head that fuses both descriptors for binary fall prediction. For offline evaluation, we evaluate the model across five wrist-mounted inertial measurement unit (IMU) datasets, achieving average F1-scores of 93%, 93%, 90%, 91%, and 90% on SmartFallMM, WEDA-Fall, FallAllD, UMAFall, and UP-Fall, outperforming Transformer baselines. For real-time evaluation, we deployed the model on a Google Pixel Watch 3 and tested across 12 participants. The model achieves an average F1-score of 97% and an accuracy of 98% with zero missed falls, showing that sigmoid gating offers a more structurally aligned and computationally efficient alternative to attention for commodity smartwatch-based fall detection.

cs.CV↗

arXiv2026

Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning

Personalized fall detection models can significantly improve accuracy by adapting to individual motion patterns, yet their effectiveness is often limited by the scarcity of real-world fall data and the dominance of non-fall feedback samples. This imbalance biases the model toward routine activities and weakens its sensitivity to true fall events. To address this challenge, we propose a personalization framework that combines semi-supervised clustering with contrastive learning to identify and balance the most informative user feedback samples. The framework is evaluated under three retraining strategies, including Training from Scratch (TFS), Transfer Learning (TL), and Few-Shot Learning (FSL), to assess adaptability across learning paradigms. Real-time experiments with ten participants show that the TFS approach achieves the highest performance, with up to a 25% improvement over the baseline, while FSL achieves the second-highest performance with a 7% improvement, demonstrating the effectiveness of selective personalization for real-world deployment.

cs.LG↗

arXiv2026

TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare

The lack of real-world data in clinical fields poses a major obstacle in training effective AI models for diagnostic and preventive tools in medicine. Generative AI has shown promise in increasing data volume and enhancing model training, particularly in computer vision and natural language processing (NLP) domains. However, generating physiological time-series data, a common type in medical AI applications, presents unique challenges due to its inherent complexity and variability. This paper introduces TransConv-DDPM, an enhanced generative AI method for biomechanical and physiological time-series data generation. The model employs a denoising diffusion probabilistic model (DDPM) with U-Net, multi-scale convolution modules, and a transformer layer to capture both global and local temporal dependencies. We evaluated TransConv-DDPM on three diverse datasets, generating both long and short-sequence time-series data. Quantitative comparisons against state-of-the-art methods, TimeGAN and Diffusion-TS, using four performance metrics, demonstrated promising results, particularly on the SmartFallMM and EEG datasets, where it effectively captured the more gradual temporal change patterns between data points. Additionally, a utility test on the SmartFallMM dataset revealed that adding synthetic fall data generated by TransConv-DDPM improved predictive model performance, showing a 13.64% improvement in F1-score and a 14.93% increase in overall accuracy compared to the baseline model trained solely on fall data from the SmartFallMM dataset. These findings highlight the potential of TransConv-DDPM to generate high-quality synthetic data for real-world applications.

cs.LG↗

arXiv2025

AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detection

Training fall detection systems is challenging due to the scarcity of real-world fall data, particularly from elderly individuals. To address this, we explore the potential of Large Language Models (LLMs) for generating synthetic fall data. This study evaluates text-to-motion (T2M, SATO, ParCo) and text-to-text models (GPT4o, GPT4, Gemini) in simulating realistic fall scenarios. We generate synthetic datasets and integrate them with four real-world baseline datasets to assess their impact on fall detection performance using a Long Short-Term Memory (LSTM) model. Additionally, we compare LLM-generated synthetic data with a diffusion-based method to evaluate their alignment with real accelerometer distributions. Results indicate that dataset characteristics significantly influence the effectiveness of synthetic data, with LLM-generated data performing best in low-frequency settings (e.g., 20Hz) while showing instability in high-frequency datasets (e.g., 200Hz). While text-to-motion models produce more realistic biomechanical data than text-to-text models, their impact on fall detection varies. Diffusion-based synthetic data demonstrates the closest alignment to real data but does not consistently enhance model performance. An ablation study further confirms that the effectiveness of synthetic data depends on sensor placement and fall representation. These findings provide insights into optimizing synthetic data generation for fall detection models.

cs.CL↗

arXiv2024

Automated Update of Android Deprecated API Usages with Large Language Models

Android apps rely on application programming interfaces (APIs) to access various functionalities of Android devices. These APIs however are regularly updated to incorporate new features while the old APIs get deprecated. Even though the importance of updating deprecated API usages with the recommended replacement APIs has been widely recognized, it is non-trivial to update the deprecated API usages. Therefore, the usages of deprecated APIs linger in Android apps and cause compatibility issues in practice. This paper introduces GUPPY, an automated approach that utilizes large language models (LLMs) to update Android deprecated API usages. By employing carefully crafted prompts, GUPPY leverages GPT-4, one of the most powerful LLMs, to update deprecated-API usages, ensuring compatibility in both the old and new API levels. Additionally, GUPPY uses GPT-4 to generate tests, identify incorrect updates, and refine the API usage through an iterative process until the tests pass or a specified limit is reached. Our evaluation, conducted on 360 benchmark API usages from 20 deprecated APIs and an additional 156 deprecated API usages from the latest API levels 33 and 34, demonstrates GUPPY's advantages over the state-of-the-art techniques.

cs.SE↗

arXiv2024

Physical-aware Cross-modal Adversarial Network for Wearable Sensor-based Human Action Recognition

Wearable sensor-based Human Action Recognition (HAR) has made significant strides in recent times. However, the accuracy performance of wearable sensor-based HAR is currently still lagging behind that of visual modalities-based systems, such as RGB video and depth data. Although diverse input modalities can provide complementary cues and improve the accuracy performance of HAR, wearable devices can only capture limited kinds of non-visual time series input, such as accelerometers and gyroscopes. This limitation hinders the deployment of multimodal simultaneously using visual and non-visual modality data in parallel on current wearable devices. To address this issue, we propose a novel Physical-aware Cross-modal Adversarial (PCA) framework that utilizes only time-series accelerometer data from four inertial sensors for the wearable sensor-based HAR problem. Specifically, we propose an effective IMU2SKELETON network to produce corresponding synthetic skeleton joints from accelerometer data. Subsequently, we imposed additional constraints on the synthetic skeleton data from a physical perspective, as accelerometer data can be regarded as the second derivative of the skeleton sequence coordinates. After that, the original accelerometer as well as the constrained skeleton sequence were fused together to make the final classification. In this way, when individuals wear wearable devices, the devices can not only capture accelerometer data, but can also generate synthetic skeleton sequences for real-time wearable sensor-based HAR applications that need to be conducted anytime and anywhere. To demonstrate the effectiveness of our proposed PCA framework, we conduct extensive experiments on Berkeley-MHAD, UTD-MHAD, and MMAct datasets. The results confirm that the proposed PCA approach has competitive performance compared to the previous methods on the mono sensor-based HAR classification problem.

cs.MM↗

arXiv2024

A Survey on Multimodal Wearable Sensor-based Human Action Recognition

The combination of increased life expectancy and falling birth rates is resulting in an aging population. Wearable Sensor-based Human Activity Recognition (WSHAR) emerges as a promising assistive technology to support the daily lives of older individuals, unlocking vast potential for human-centric applications. However, recent surveys in WSHAR have been limited, focusing either solely on deep learning approaches or on a single sensor modality. In real life, our human interact with the world in a multi-sensory way, where diverse information sources are intricately processed and interpreted to accomplish a complex and unified sensing system. To give machines similar intelligence, multimodal machine learning, which merges data from various sources, has become a popular research area with recent advancements. In this study, we present a comprehensive survey from a novel perspective on how to leverage multimodal learning to WSHAR domain for newcomers and researchers. We begin by presenting the recent sensor modalities as well as deep learning approaches in HAR. Subsequently, we explore the techniques used in present multimodal systems for WSHAR. This includes inter-multimodal systems which utilize sensor modalities from both visual and non-visual systems and intra-multimodal systems that simply take modalities from non-visual systems. After that, we focus on current multimodal learning approaches that have applied to solve some of the challenges existing in WSHAR. Specifically, we make extra efforts by connecting the existing multimodal literature from other domains, such as computer vision and natural language processing, with current WSHAR area. Finally, we identify the corresponding challenges and potential research direction in current WSHAR area for further improvement.

eess.SP↗

arXiv2022

Progressive Cross-modal Knowledge Distillation for Human Action Recognition

Wearable sensor-based Human Action Recognition (HAR) has achieved remarkable success recently. However, the accuracy performance of wearable sensor-based HAR is still far behind the ones from the visual modalities-based system (i.e., RGB video, skeleton, and depth). Diverse input modalities can provide complementary cues and thus improve the accuracy performance of HAR, but how to take advantage of multi-modal data on wearable sensor-based HAR has rarely been explored. Currently, wearable devices, i.e., smartwatches, can only capture limited kinds of non-visual modality data. This hinders the multi-modal HAR association as it is unable to simultaneously use both visual and non-visual modality data. Another major challenge lies in how to efficiently utilize multimodal data on wearable devices with their limited computation resources. In this work, we propose a novel Progressive Skeleton-to-sensor Knowledge Distillation (PSKD) model which utilizes only time-series data, i.e., accelerometer data, from a smartwatch for solving the wearable sensor-based HAR problem. Specifically, we construct multiple teacher models using data from both teacher (human skeleton sequence) and student (time-series accelerometer data) modalities. In addition, we propose an effective progressive learning scheme to eliminate the performance gap between teacher and student models. We also designed a novel loss function called Adaptive-Confidence Semantic (ACS), to allow the student model to adaptively select either one of the teacher models or the ground-truth label it needs to mimic. To demonstrate the effectiveness of our proposed PSKD method, we conduct extensive experiments on Berkeley-MHAD, UTD-MHAD, and MMAct datasets. The results confirm that the proposed PSKD method has competitive performance compared to the previous mono sensor-based HAR methods.

cs.CV↗

arXiv2021

Cross-modal Knowledge Distillation for Vision-to-Sensor Action Recognition

Human activity recognition (HAR) based on multi-modal approach has been recently shown to improve the accuracy performance of HAR. However, restricted computational resources associated with wearable devices, i.e., smartwatch, failed to directly support such advanced methods. To tackle this issue, this study introduces an end-to-end Vision-to-Sensor Knowledge Distillation (VSKD) framework. In this VSKD framework, only time-series data, i.e., accelerometer data, is needed from wearable devices during the testing phase. Therefore, this framework will not only reduce the computational demands on edge devices, but also produce a learning model that closely matches the performance of the computational expensive multi-modal approach. In order to retain the local temporal relationship and facilitate visual deep learning models, we first convert time-series data to two-dimensional images by applying the Gramian Angular Field ( GAF) based encoding method. We adopted ResNet18 and multi-scale TRN with BN-Inception as teacher and student network in this study, respectively. A novel loss function, named Distance and Angle-wised Semantic Knowledge loss (DASK), is proposed to mitigate the modality variations between the vision and the sensor domain. Extensive experimental results on UTD-MHAD, MMAct, and Berkeley-MHAD datasets demonstrate the effectiveness and competitiveness of the proposed VSKD model which can deployed on wearable sensors.

cs.MM↗

arXiv2018

ContextServ: Towards Model-Driven Development of Context-AwareWeb Services

In the era of Web of Things and Services, Context-aware Web Services (CASs) are emerging as an important technology for building innovative context-aware applications. CASs enable the information integration from both the physical and virtual world, which affects human living. However, it is challenging to build CASs, due to the lack of context provisioning management approach and limited generic approach for formalizing the development process. We therefore propose ContextServ, a platform that uses a model-driven approach to support the full life cycle of CASs development, hence offering significant design and management flexibility. ContextServ implements a proposed UML-based modelling language ContextUML to support multiple modelling languages. It also supports dynamic adaptation of WS-BPEL based context-aware composite services by weaving context-aware rules into the process. Extensive experimental evaluations on ContextServ and its components showcase that ContextServ can support effective development and efficient execution of context-aware Web services.

cs.SE↗

arXiv2017

SmartMTD: A Graph-Based Approach for Effective Multi-Truth Discovery

The Big Data era features a huge amount of data that are contributed by numerous sources and used by many critical data-driven applications. Due to the varying reliability of sources, it is common to see conflicts among the multi-source data, making it difficult to determine which data sources to trust. Recently, truth discovery has emerged as a means of addressing this challenging issue by determining data veracity jointly with estimating the reliability of data sources. A fundamental issue with current truth discovery methods is that they generally assume only one true value for each object, while in reality, objects may have multiple true values. In this paper, we propose a graph-based approach, called SmartMTD, to unravel the truth discovery problem beyond the single-truth assumption, or the multi-truth discovery problem. SmartMTD models and quantifies two types of source relations to estimate source reliability precisely and to detect malicious agreement among sources for effective multi-truth discovery. In particular, two graphs are constructed based on the modeled source relations. They are further used to derive the two aspects of source reliability (i.e., positive precision and negative precision) via random walk computation. Empirical studies on two large real-world datasets demonstrate the effectiveness of our approach.

cs.DB↗

arXiv2017

From Appearance to Essence: Comparing Truth Discovery Methods without Using Ground Truth

Truth discovery has been widely studied in recent years as a fundamental means for resolving the conflicts in multi-source data. Although many truth discovery methods have been proposed based on different considerations and intuitions, investigations show that no single method consistently outperforms the others. To select the right truth discovery method for a specific application scenario, it becomes essential to evaluate and compare the performance of different methods. A drawback of current research efforts is that they commonly assume the availability of certain ground truth for the evaluation of methods. However, the ground truth may be very limited or even out-of-reach in practice, rendering the evaluation biased by the small ground truth or even unfeasible. In this paper, we present CompTruthHyp, a general approach for comparing the performance of truth discovery methods without using ground truth. In particular, our approach calculates the probability of observations in a dataset based on the output of different methods. The probability is then ranked to reflect the performance of these methods. We review and compare twelve existing truth discovery methods and consider both single-valued and multi-valued objects. Empirical studies on both real-world and synthetic datasets demonstrate the effectiveness of our approach for comparing truth discovery methods.

cs.DB↗

arXiv2017

Up in the Air: When Homes Meet the Web of Things

The emerging Internet of Things (IoT) will comprise billions of Web-enabled objects (or "things") where such objects can sense, communicate, compute and potentially actuate. WoT is essentially the embodiment of the evolution from systems linking digital documents to systems relating digital information to real-world physical items. It is widely understood that significant technical challenges exist in developing applications in the WoT environment. In this paper, we report our practical experience in the design and development of a smart home system in a WoT environment. Our system provides a layered framework for managing and sharing the information produced by physical things as well as the residents. We particularly focus on a research prototype named WITS, that helps the elderly live independently and safely in their own homes, with minimal support from the decreasing number of individuals in the working-age population. WITS enables an unobtrusive monitoring of elderly people in a real-world, inhabituated home environment, by leveraging WoT technologies in building context-aware, personalized services.

cs.CY↗

arXiv2017

Unveiling Contextual Similarity of Things via Mining Human-Thing Interactions in the Internet of Things

With recent advances in radio-frequency identification (RFID), wireless sensor networks, and Web services, physical things are becoming an integral part of the emerging ubiquitous Web. Finding correlations of ubiquitous things is a crucial prerequisite for many important applications such as things search, discovery, classification, recommendation, and composition. This article presents DisCor-T, a novel graph-based method for discovering underlying connections of things via mining the rich content embodied in human-thing interactions in terms of user, temporal and spatial information. We model these various information using two graphs, namely spatio-temporal graph and social graph. Then, random walk with restart (RWR) is applied to find proximities among things, and a relational graph of things (RGT) indicating implicit correlations of things is learned. The correlation analysis lays a solid foundation contributing to improved effectiveness in things management. To demonstrate the utility, we develop a flexible feature-based classification framework on top of RGT and perform a systematic case study. Our evaluation exhibits the strength and feasibility of the proposed approach.

cs.CY↗