A5055076829- Neuroscience and Music Perception
- Neural and Behavioral Psychology Studies
- Neural dynamics and brain function
- Multisensory perception and integration
- Time Series Analysis and Forecasting
- Decision-Making and Behavioral Economics
- Neural Networks and Applications
- Network Security and Intrusion Detection
- Diabetes Management and Research
- Anomaly Detection Techniques and Applications
- Machine Learning in Healthcare
- Hearing Loss and Rehabilitation
- Pancreatic function and diabetes
- EEG and Brain-Computer Interfaces
- Spectroscopy Techniques in Biomedical and Chemical Research
- Microbial bioremediation and biosurfactants
- ECG Monitoring and Analysis
- Artificial Intelligence in Healthcare
- Musculoskeletal pain and rehabilitation
- Advanced Malware Detection Techniques
- Legume Nitrogen Fixing Symbiosis
- Machine Learning and Data Classification
- Diabetes and associated disorders
- Financial Distress and Bankruptcy Prediction
- Single-cell and spatial transcriptomics
Women's Hospital, School of Medicine, Zhejiang University
2024-2025
Zhejiang University
2024
Jilin Medical University
2021-2024
Jilin University
2021-2024
Nanjing Agricultural University
2020
The neural mechanisms underlying novelty detection are not well understood, especially in relation to behavior. Here, we present single-unit responses from the primary auditory cortex (A1) two monkeys trained detect deviant tones amid repetitive ones. Results show that can sounds, and there is a strong correlation between late neuronal (250–350 ms after onset) monkeys' perceptual decisions. magnitude timing of both behavioral increased by larger frequency differences standard increasing...
The Inferior Colliculus (IC) has traditionally been regarded as an important relay in the auditory pathway, primarily involved relaying information from brainstem to thalamus. However, this study uncovers multifaceted role of IC bridging processing, sensory prediction, and reward prediction. Through extracellular recordings monkeys engaged a sound duration-based deviation detection task, we observed “climbing effect” neuronal firing rates, indicative enhanced response over sequences linked...
Abstract Temporal integration stands as a cornerstone of auditory perception, yet its underlying neural mechanisms have remained relatively elusive. The intricate process by which discrete stimuli integrate into cohesive perception is defined “temporal merging” in this study. We use paradigm, the transitional click train, to probe intricacies temporal merging within cortex. protocol underscores robust change response an adapted cortex upon introducing perceptual switch between distinct...
Medical time series has been playing a vital role in real-world healthcare systems as valuable information monitoring health conditions of patients. Accurate classification for medical series, e.g., Electrocardiography (ECG) signals, can help early detection and diagnosis. Traditional methods towards rely on handcrafted feature extraction statistical methods; with the recent advancement artificial intelligence, machine learning deep have become more popular. However, existing often fail to...
Diffusion-based generative models have recently excelled in generating molecular conformations but struggled with the generalization issue -- trained on one dataset may produce meaningless out-of-distribution molecules. On other hand, distance geometry serves as a generalizable tool for traditional computational chemistry methods of conformation, which is predicated assumption that it possible to adequately define set all potential any non-rigid system using purely geometric constraints. In...
Carbaryl is a widely used carbamate pesticide in agriculture. The strain Rhizobium sp. X9 possesses the typical carbaryl degradation pathway which mineralized via 1-naphthol, salicylate, and gentisate. In this study, we cloned hydrolase gene cehA novel two-component 1-naphthol hydroxylase cehC1C2. CehA mediates hydrolysis to CehC1, an FMNH2 or FADH2-dependent monooxygenase belonging HpaB superfamily, hydroxylates presence of reduced nicotinamide-adenine dinucleotide (FMN)/flavin adenine...
While most time series are non-stationary, it is inevitable for models to face the distribution shift issue in forecasting. Existing solutions manipulate statistical measures (usually mean and std.) adjust distribution. However, these operations can be theoretically seen as transformation towards zero frequency component of spectrum which cannot reveal full information would further lead utilization bottleneck normalization, thus hindering forecasting performance. To address this problem, we...
imbalanced-ensemble, abbreviated as imbens, is an open-source Python toolbox for leveraging the power of ensemble learning to address class imbalance problem. It provides standard implementations popular imbalanced (EIL) methods with extended features and utility functions. These include resampling-based, e.g., under/over-sampling, reweighting-based, cost-sensitive learning. Beyond implementation, we empower EIL algorithms new functionalities like customizable resampling scheduler verbose...
Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparsely/densely clustered) detect anomalies. However, are complex and vary significantly across different domains. No single assumption can describe such complexity be valid in all scenarios. This also confirmed by recent research that shows no method...
Continuous glucose monitoring prediction is a crucial yet challenging task in precision medicine. This paper presents novel neural ODE based approach for predicting continuous (CGM) levels purely on sporadic self-monitoring signals. We integrate the expert knowledge from physiological model into our to improve accuracy. Experiments real-world data demonstrate that method outperforms other state-of-the-art methods NRMSE metrics.
While most time series are non-stationary, it is inevitable for models to face the distribution shift issue in forecasting. Existing solutions manipulate statistical measures (usually mean and std.) adjust distribution. However, these operations can be theoretically seen as transformation towards zero frequency component of spectrum which cannot reveal full information would further lead utilization bottleneck normalization, thus hindering forecasting performance. To address this problem, we...
Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. With the recent success of deep learning, many tabular machine learning (ML) methods based on networks (e.g., Transformer, ResNet) achieved competitive performance benchmarks. However, existing ML suffer from representation entanglement and localization, which largely hinders their prediction leads to inconsistency tasks. To overcome these problems, we explore...
Abstract The Inferior Colliculus (IC) has traditionally been regarded as an important relay in the auditory pathway, primarily involved relaying information from brainstem to thalamus. However, this study uncovers multifaceted role of IC bridging processing, sensory prediction, and reward prediction. Through extracellular recordings monkeys engaged a sound duration-based deviation detection task, we observed “climbing effect” neuronal firing rates, indicative enhanced response over sequences...
The Inferior Colliculus (IC) has traditionally been regarded as an important relay in the auditory pathway, primarily involved relaying information from brainstem to thalamus. However, this study uncovers multifaceted role of IC bridging processing, sensory prediction, and reward prediction. Through extracellular recordings monkeys engaged a sound duration-based novelty detection task, we observed "climbing effect" neuronal firing rates, indicative enhanced response over sequences linked...
The inferior colliculus (IC) has traditionally been regarded as an important relay in the auditory pathway, primarily involved relaying information from brainstem to thalamus. However, this study uncovers multifaceted role of IC bridging processing, sensory prediction, and reward prediction. Through extracellular recordings monkeys engaged a sound duration-based deviation detection task, we observed 'climbing effect' neuronal firing rates, indicative enhanced response over sequences linked...
Offset responses are traditionally viewed as indicators of sound cessation. Here, we investigate offset to auditory click trains, examining how they modulated by inter-click intervals (ICIs) and train duration. Using extracellular recordings electrocorticography (ECoG) in non-human primates, alongside electroencephalography (EEG) humans, show that significantly influenced both ICI length, thereby establishing them markers temporal integration. We introduce the concept 'Neuronal Integrative...
Temporal integration, the process by which auditory system combines sound information over a curtain period to form coherent object, is essential for perception, yet its neural mechanisms remain underexplored. We use "transitional click train" paradigm, concatenates two trains with slightly differing inter-click intervals (ICIs), investigate temporal integration in human cortex. Using 64-channel electroencephalogram (EEG), we recorded responses from 42 healthy participants exposed regular...
Temporal integration is crucial for auditory perception, yet the mechanisms underlying its role are not fully elucidated. This study examines perceptual discrimination of click trains with varied temporal configurations to determine if they can be perceived as distinct objects, potentially introducing a novel dimension sound perception. In humans, psychological experiments using delayed match-to-sample task revealed that participants could distinctly discriminate between different...
Unsupervised Anomaly Detection (UAD) is a key data mining problem owing to its wide real-world applications. Due the complete absence of supervision signals, UAD methods rely on implicit assumptions about anomalous patterns (e.g., scattered/sparsely/densely clustered) detect anomalies. However, are complex and vary significantly across different domains. No single assumption can describe such complexity be valid in all scenarios. This also confirmed by recent research that shows no method...
Abstract Background: With the increasing use and growing popularity of insulin pumps continuous glucose monitoring(CGM) devices, more reliable sources data could be obtained to lead better control, treatment decision diabetes management. The critical challenge management is develop accurate algorithms that can predict future blood trends manage amount insulin. However, in reality, unavailable difficult acquire some scenarios: for example, most type-2 diabetic patients only measure their...