arXiv subjects

Ning Ma

Publications and source records attributed to Ning Ma.

At least 37 records · Page 2Linked to original sources

arXiv2026

Estimating Respiratory Effort from Nocturnal Breathing Sounds for Obstructive Sleep Apnoea Screening

Obstructive sleep apnoea (OSA) is a prevalent condition with significant health consequences, yet many patients remain undiagnosed due to the complexity and cost of over-night polysomnography. Acoustic-based screening provides a scalable alternative, yet performance is limited by environmental noise and the lack of physiological context. Respiratory effort is a key signal used in clinical scoring of OSA events, but current approaches require additional contact sensors that reduce scalability and patient comfort. This paper presents the first study to estimate respiratory effort directly from nocturnal audio, enabling physiological context to be recovered from sound alone. We propose a latent-space fusion framework that integrates the estimated effort embeddings with acoustic features for OSA detection. Using a dataset of 157 nights from 103 participants recorded in home environments, our respiratory effort estimator achieves a concordance correlation coefficient of 0.48, capturing meaningful respiratory dynamics. Fusing effort and audio improves sensitivity and AUC over audio-only baselines, especially at low apnoea-hypopnoea index thresholds. The proposed approach requires only smartphone audio at test time, which enables sensor-free, scalable, and longitudinal OSA monitoring.

cs.SD↗

arXiv2026

Transfer Learning for Paediatric Sleep Apnoea Detection Using Physiology-Guided Acoustic Models

Paediatric obstructive sleep apnoea (OSA) is clinically significant yet difficult to diagnose, as children poorly tolerate sensor-based polysomnography. Acoustic monitoring provides a non-invasive alternative for home-based OSA screening, but limited paediatric data hinders the development of robust deep learning approaches. This paper proposes a transfer learning framework that adapts acoustic models pretrained on adult sleep data to paediatric OSA detection, incorporating SpO2-based desaturation patterns to enhance model training. Using a large adult sleep dataset (157 nights) and a smaller paediatric dataset (15 nights), we systematically evaluate (i) single- versus multi-task learning, (ii) encoder freezing versus full fine-tuning, and (iii) the impact of delaying SpO2 labels to better align them with the acoustics and capture physiologically meaningful features. Results show that fine-tuning with SpO2 integration consistently improves paediatric OSA detection compared with baseline models without adaptation. These findings demonstrate the feasibility of transfer learning for home-based OSA screening in children and offer its potential clinical value for early diagnosis.

eess.AS↗

arXiv2025

Understanding and Estimating the Execution Time of Quantum Circuits

Due to the scarcity of quantum computing resources, researchers and developers have very limited access to real quantum computers. Therefore, judicious planning and utilization of quantum computer runtime are essential to ensure smooth execution and completion of projects. Accurate estimation of a quantum circuit's execution time is thus necessary to prevent unexpectedly exceeding the anticipated runtime or the maximum capacity of the quantum computers; it also allows quantum computing platforms to make precisely informed provisioning and prioritization of quantum computing jobs. In this paper, we first study the characteristics of quantum circuits' runtime on simulators and real quantum computers. Then, we introduce an innovative method that employs a graph transformer-based model, utilizing the graph information and global information of quantum circuits to estimate their execution time. We selected a benchmark dataset comprising over 1,510 quantum circuits, initially predicting their execution times on simulators, which yielded promising results with an R-squared value greater than 95%. Subsequently, we applied active learning to select 340 circuit samples with a confidence level of 95% to build and evaluate our approach for the estimation of circuit execution times on quantum computers, achieving an average R-squared value exceeding 90%. Our approach can be integrated into quantum computing platforms to provide an accurate estimation of quantum execution time and be used as a reference for prioritizing quantum execution jobs. In addition, our findings provide insights for quantum program developers to optimize their circuits for reduced execution time.

cs.SE↗

arXiv2025

Deep Learning for Tuberculosis Screening in a High-burden Setting using Cough Analysis and Speech Foundation Models

Artificial intelligence (AI) systems can detect disease-related acoustic patterns in cough sounds, offering a scalable and cost-effective approach to tuberculosis (TB) screening in high-burden, resource-limited settings. Previous studies have been limited by small datasets, under-representation of symptomatic non-TB patients, and recordings collected in controlled environments. In this study, we enrolled 512 participants at two hospitals in Zambia, categorised into three groups: bacteriologically confirmed TB (TB+), symptomatic patients with other respiratory diseases (OR), and healthy controls (HC). Usable cough recordings with demographic and clinical data were obtained from 500 participants. Deep learning classifiers based on pre-trained speech foundation models were fine-tuned on cough recordings to predict diagnostic categories. The best-performing model, trained on 3-second audio clips, achieved an AUROC of 85.2% for distinguishing TB coughs from all other participants (TB+/Rest) and 80.1% for TB+ versus symptomatic OR participants (TB+/OR). Incorporating demographic and clinical features improved performance to 92.1% for TB+/Rest and 84.2% for TB+/OR. At a probability threshold of 0.38, the multimodal model reached 90.3% sensitivity and 73.1% specificity for TB+/Rest, meeting WHO target product profile benchmarks for TB screening. Adversarial testing and stratified analyses shows that the model was robust to confounding factors including background noise, recording time, and device variability. These results demonstrate the feasibility of cough-based AI for TB screening in real-world, low-resource settings.

cs.SD↗

arXiv2025

Experimental demonstration of the clock asynchrony model in space-borne gravitational wave detection

Space-borne gravitational wave detection will open the observation window in the 0.1 mHz$-$1 Hz bandwidth, playing a crucial role in the development of cosmology and physics. Precise clock synchronization among satellites is essential for the accurate detection of gravitational wave signals. However, the independent clock counting mechanisms of each satellite pose a significant challenge. This work reports the mathematical model of clock asynchrony, which is mainly dominated by the constant term factor and the linear term factor. Moreover, it experimentally verifies the clock asynchronization technique based on a dual-phasemeter system. Through experimentation, the impacts of these two aspects of clock asynchrony were confirmed, and post-processing techniques were employed to reduce these impacts to as low as $\rm 2π\times 10^{-6} rad/Hz^{1/2}@ 3mHz$. Specifically, the constant term factor is measured by Time-delay Interferometry Ranging (TDIR), while the linear term factor can be gauged by clock transmission link. This study provides a reference for understanding the clock asynchrony mechanism and processing clock synchronization issues. Additionally, a low additional noise clock synchronization test system is introduced to support such measurements.

gr-qc↗

arXiv2025

How Private are Language Models in Abstractive Summarization?

In sensitive domains such as medical and legal, protecting sensitive information is critical, with protective laws strictly prohibiting the disclosure of personal data. This poses challenges for sharing valuable data such as medical reports and legal cases summaries. While language models (LMs) have shown strong performance in text summarization, it is still an open question to what extent they can provide privacy-preserving summaries from non-private source documents. In this paper, we perform a comprehensive study of privacy risks in LM-based summarization across two closed- and four open-weight models of different sizes and families. We experiment with both prompting and fine-tuning strategies for privacy-preservation across a range of summarization datasets including medical and legal domains. Our quantitative and qualitative analysis, including human evaluation, shows that LMs frequently leak personally identifiable information in their summaries, in contrast to human-generated privacy-preserving summaries, which demonstrate significantly higher privacy protection levels. These findings highlight a substantial gap between current LM capabilities and expert human expert performance in privacy-sensitive summarization tasks.

cs.CL↗

arXiv2024

DEL-Ranking: Ranking-Correction Denoising Framework for Elucidating Molecular Affinities in DNA-Encoded Libraries

DNA-encoded library (DEL) screening has revolutionized the detection of protein-ligand interactions through read counts, enabling rapid exploration of vast chemical spaces. However, noise in read counts, stemming from nonspecific interactions, can mislead this exploration process. We present DEL-Ranking, a novel distribution-correction denoising framework that addresses these challenges. Our approach introduces two key innovations: (1) a novel ranking loss that rectifies relative magnitude relationships between read counts, enabling the learning of causal features determining activity levels, and (2) an iterative algorithm employing self-training and consistency loss to establish model coherence between activity label and read count predictions. Furthermore, we contribute three new DEL screening datasets, the first to comprehensively include multi-dimensional molecular representations, protein-ligand enrichment values, and their activity labels. These datasets mitigate data scarcity issues in AI-driven DEL screening research. Rigorous evaluation on diverse DEL datasets demonstrates DEL-Ranking's superior performance across multiple correlation metrics, with significant improvements in binding affinity prediction accuracy. Our model exhibits zero-shot generalization ability across different protein targets and successfully identifies potential motifs determining compound binding affinity. This work advances DEL screening analysis and provides valuable resources for future research in this area.

cs.LG↗

arXiv2024

SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition

Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed by video fine-tuning" for high-dimensional video data inevitably poses significant performance bottlenecks. Furthermore, in the medical domain, many surgical video tasks encounter additional challenges posed by the limited availability of video data and the necessity for comprehensive spatial-temporal modeling. Recently, Parameter-Efficient Image-to-Video Transfer Learning has emerged as an efficient and effective paradigm for video action recognition tasks, which employs image-level pre-trained models with promising feature transferability and involves cross-modality temporal modeling with minimal fine-tuning. Nevertheless, the effectiveness and generalizability of this paradigm within intricate surgical domain remain unexplored. In this paper, we delve into a novel problem of efficiently adapting image-level pre-trained models to specialize in fine-grained surgical phase recognition, termed as Parameter-Efficient Image-to-Surgical-Video Transfer Learning. Firstly, we develop a parameter-efficient transfer learning benchmark SurgPETL for surgical phase recognition, and conduct extensive experiments with three advanced methods based on ViTs of two distinct scales pre-trained on five large-scale natural and medical datasets. Then, we introduce the Spatial-Temporal Adaptation module, integrating a standard spatial adapter with a novel temporal adapter to capture detailed spatial features and establish connections across temporal sequences for robust spatial-temporal modeling. Extensive experiments on three challenging datasets spanning various surgical procedures demonstrate the effectiveness of SurgPETL with STA.

cs.CV↗

arXiv2024

CODIS: Benchmarking Context-Dependent Visual Comprehension for Multimodal Large Language Models

Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of their capabilities has grown increasingly important. However, most existing benchmarks fail to consider that, in certain situations, images need to be interpreted within a broader context. In this work, we introduce a new benchmark, named as CODIS, designed to assess the ability of models to use context provided in free-form text to enhance visual comprehension. Our findings indicate that MLLMs consistently fall short of human performance on this benchmark. Further analysis confirms that these models struggle to effectively extract and utilize contextual information to improve their understanding of images. This underscores the pressing need to enhance the ability of MLLMs to comprehend visuals in a context-dependent manner. View our project website at https://thunlp-mt.github.io/CODIS.

cs.CV↗

arXiv2023

Homophily-enhanced Structure Learning for Graph Clustering

Graph clustering is a fundamental task in graph analysis, and recent advances in utilizing graph neural networks (GNNs) have shown impressive results. Despite the success of existing GNN-based graph clustering methods, they often overlook the quality of graph structure, which is inherent in real-world graphs due to their sparse and multifarious nature, leading to subpar performance. Graph structure learning allows refining the input graph by adding missing links and removing spurious connections. However, previous endeavors in graph structure learning have predominantly centered around supervised settings, and cannot be directly applied to our specific clustering tasks due to the absence of ground-truth labels. To bridge the gap, we propose a novel method called \textbf{ho}mophily-enhanced structure \textbf{le}arning for graph clustering (HoLe). Our motivation stems from the observation that subtly enhancing the degree of homophily within the graph structure can significantly improve GNNs and clustering outcomes. To realize this objective, we develop two clustering-oriented structure learning modules, i.e., hierarchical correlation estimation and cluster-aware sparsification. The former module enables a more accurate estimation of pairwise node relationships by leveraging guidance from latent and clustering spaces, while the latter one generates a sparsified structure based on the similarity matrix and clustering assignments. Additionally, we devise a joint optimization approach alternating between training the homophily-enhanced structure learning and GNN-based clustering, thereby enforcing their reciprocal effects. Extensive experiments on seven benchmark datasets of various types and scales, across a range of clustering metrics, demonstrate the superiority of HoLe against state-of-the-art baselines.

cs.LG↗

arXiv2023

Partition Speeds Up Learning Implicit Neural Representations Based on Exponential-Increase Hypothesis

$\textit{Implicit neural representations}$ (INRs) aim to learn a $\textit{continuous function}$ (i.e., a neural network) to represent an image, where the input and output of the function are pixel coordinates and RGB/Gray values, respectively. However, images tend to consist of many objects whose colors are not perfectly consistent, resulting in the challenge that image is actually a $\textit{discontinuous piecewise function}$ and cannot be well estimated by a continuous function. In this paper, we empirically investigate that if a neural network is enforced to fit a discontinuous piecewise function to reach a fixed small error, the time costs will increase exponentially with respect to the boundaries in the spatial domain of the target signal. We name this phenomenon the $\textit{exponential-increase}$ hypothesis. Under the $\textit{exponential-increase}$ hypothesis, learning INRs for images with many objects will converge very slowly. To address this issue, we first prove that partitioning a complex signal into several sub-regions and utilizing piecewise INRs to fit that signal can significantly speed up the convergence. Based on this fact, we introduce a simple partition mechanism to boost the performance of two INR methods for image reconstruction: one for learning INRs, and the other for learning-to-learn INRs. In both cases, we partition an image into different sub-regions and dedicate smaller networks for each part. In addition, we further propose two partition rules based on regular grids and semantic segmentation maps, respectively. Extensive experiments validate the effectiveness of the proposed partitioning methods in terms of learning INR for a single image (ordinary learning framework) and the learning-to-learn framework.

cs.CV↗

arXiv2023

Intelligibility prediction with a pretrained noise-robust automatic speech recognition model

This paper describes two intelligibility prediction systems derived from a pretrained noise-robust automatic speech recognition (ASR) model for the second Clarity Prediction Challenge (CPC2). One system is intrusive and leverages the hidden representations of the ASR model. The other system is non-intrusive and makes predictions with derived ASR uncertainty. The ASR model is only pretrained with a simulated noisy speech corpus and does not take advantage of the CPC2 data. For that reason, the intelligibility prediction systems are robust to unseen scenarios given the accurate prediction performance on the CPC2 evaluation.

eess.AS↗

arXiv2023

Perpendicular in-plane negative magnetoresistance in ZrTe5

The unique band structure in topological materials frequently results in unusual magneto-transport phenomena, one of which is in-plane longitudinal negative magnetoresistance (NMR) with the magnetic field aligned parallel to the electrical current direction. This NMR is widely considered as a hallmark of chiral anomaly in topological materials. Here we report the observation of in-plane NMR in the topological material ZrTe5 when the in-plane magnetic field is both parallel and perpendicular to the current direction, revealing an unusual case of quantum transport beyond the chiral anomaly. We find that a general theoretical model, which considers the combined effect of Berry curvature and orbital moment, can quantitatively explain this in-plane NMR. Our results provide new insights into the understanding of in-plane NMR in topological materials.

cond-mat.mes-hall↗

arXiv2023

Multi-source adversarial transfer learning for ultrasound image segmentation with limited similarity

Lesion segmentation of ultrasound medical images based on deep learning techniques is a widely used method for diagnosing diseases. Although there is a large amount of ultrasound image data in medical centers and other places, labeled ultrasound datasets are a scarce resource, and it is likely that no datasets are available for new tissues/organs. Transfer learning provides the possibility to solve this problem, but there are too many features in natural images that are not related to the target domain. As a source domain, redundant features that are not conducive to the task will be extracted. Migration between ultrasound images can avoid this problem, but there are few types of public datasets, and it is difficult to find sufficiently similar source domains. Compared with natural images, ultrasound images have less information, and there are fewer transferable features between different ultrasound images, which may cause negative transfer. To this end, a multi-source adversarial transfer learning network for ultrasound image segmentation is proposed. Specifically, to address the lack of annotations, the idea of adversarial transfer learning is used to adaptively extract common features between a certain pair of source and target domains, which provides the possibility to utilize unlabeled ultrasound data. To alleviate the lack of knowledge in a single source domain, multi-source transfer learning is adopted to fuse knowledge from multiple source domains. In order to ensure the effectiveness of the fusion and maximize the use of precious data, a multi-source domain independent strategy is also proposed to improve the estimation of the target domain data distribution, which further increases the learning ability of the multi-source adversarial migration learning network in multiple domains.

eess.IV↗

arXiv2023

Temporally distributed parent body accretion in the C reservoir of the solar system

Accretion processes in protoplanetary disks produce a diversity of small bodies that played a crucial role in multiple reshuffling events throughout the solar system and in both early and late accretion of planets. Application of thermo-chronometers to meteorites provides precise dating of the formation age of mineralogical components. Nucleosynthetic anomalies indicating a dichotomy between NC and C meteorites and precise parent body (PB) chronology can be combined with thermal evolution models to constrain the timescale of accretion and dynamical processes in the early solar system. Achondrite PBs are considered to have accreted early and mostly in the NC region, while late accretion in the C region produced mostly undifferentiated PBs, such as the CR chondrite PB that formed as late as 4 Ma after CAIs. However, presence of more evolved CR-related meteorites suggests also an earlier accretion timing. We present modeling evidence for a temporally distributed accretion of parent bodies of CR-related meteorite groups that originate from a C reservoir and range from aqueously altered chondrites to partially differentiated primitive achondrites. The PB formation times derived range from <1 Ma to ~4 Ma after solar system formation, with ~3.7 Ma, ~1.5-2.75 Ma, <~0.6 Ma, and <~0.7 Ma for CR, Flensburg, NWA 6704, and NWA 011. This implies that accretion processes in the C reservoir started as early as in the NC reservoir and produced differentiated PBs with carbonaceous compositions in addition to undifferentiated C chondritic PBs. The accretion times correlate inversely with the degree of the meteorites' alteration, metamorphism, or differentiation. Accretion times for CI/CM, Ryugu, and Tafassites PBs of ~3.75 Ma, ~1-3 Ma, and 1.1 Ma, respectively, fit well into this correlation in agreement with the thermal and alteration conditions suggested by the meteorites.

astro-ph.EP↗

arXiv2022

Transport evidence of superlattice Dirac cones in graphene monolayer on twisted boron nitride substrate

Strong band engineering in two-dimensional (2D) materials can be achieved by introducing moiré superlattices, leading to the emergence of various novel quantum phases with promising potential for future applications. Presented works to create moiré patterns have been focused on a twist embedded inside channel materials or between channel and substrate. However, the effects of a twist inside the substrate materials on the unaligned channel materials are much less explored. In this work, we report the realization of superlattice multi-Dirac cones with the coexistence of the main Dirac cone in a monolayer graphene (MLG) on a ~0.14° twisted double-layer boron nitride (tBN) substrate. Transport measurements reveal the emergence of three pairs of superlattice Dirac points around the pristine Dirac cone, featuring multiple metallic or insulating states surrounding the charge neutrality point (CNP). Displacement field tunable and electron-hole asymmetric Fermi velocities are indicated from temperature dependent measurements, along with the gapless dispersion of superlattice Dirac cones. The experimental observation of multiple Dirac cones in MLG/tBN heterostructure is supported by band structure calculations employing periodic moiré potential. Our results unveil the potential of using twisted substrate as a universal band engineering technique for 2D materials regardless of lattice matching and crystal orientations, which might pave the way for a new branch of twistronics.

cond-mat.mes-hall↗

arXiv2022

Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired Listeners

An accurate objective speech intelligibility prediction algorithms is of great interest for many applications such as speech enhancement for hearing aids. Most algorithms measures the signal-to-noise ratios or correlations between the acoustic features of clean reference signals and degraded signals. However, these hand-picked acoustic features are usually not explicitly correlated with recognition. Meanwhile, deep neural network (DNN) based automatic speech recogniser (ASR) is approaching human performance in some speech recognition tasks. This work leverages the hidden representations from DNN-based ASR as features for speech intelligibility prediction in hearing-impaired listeners. The experiments based on a hearing aid intelligibility database show that the proposed method could make better prediction than a widely used short-time objective intelligibility (STOI) based binaural measure.

eess.AS↗

arXiv2022

Unsupervised Uncertainty Measures of Automatic Speech Recognition for Non-intrusive Speech Intelligibility Prediction

Non-intrusive intelligibility prediction is important for its application in realistic scenarios, where a clean reference signal is difficult to access. The construction of many non-intrusive predictors require either ground truth intelligibility labels or clean reference signals for supervised learning. In this work, we leverage an unsupervised uncertainty estimation method for predicting speech intelligibility, which does not require intelligibility labels or reference signals to train the predictor. Our experiments demonstrate that the uncertainty from state-of-the-art end-to-end automatic speech recognition (ASR) models is highly correlated with speech intelligibility. The proposed method is evaluated on two databases and the results show that the unsupervised uncertainty measures of ASR models are more correlated with speech intelligibility from listening results than the predictions made by widely used intrusive methods.

eess.AS↗