A5018266083- Topic Modeling
- Asthma and respiratory diseases
- Machine Learning in Healthcare
- Biomedical Text Mining and Ontologies
- Advanced Graph Neural Networks
- Genomics and Phylogenetic Studies
- Artificial Intelligence in Healthcare
- Chronic Obstructive Pulmonary Disease (COPD) Research
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- COVID-19 epidemiological studies
- Recommender Systems and Techniques
- Face and Expression Recognition
- Long-Term Effects of COVID-19
- Sparse and Compressive Sensing Techniques
- Functional Brain Connectivity Studies
- Digital Marketing and Social Media
- Evaluation Methods in Various Fields
- Graph Theory and Algorithms
- IL-33, ST2, and ILC Pathways
- Natural Language Processing Techniques
- COVID-19 Pandemic Impacts
- Metabolomics and Mass Spectrometry Studies
- Software System Performance and Reliability
- Respiratory and Cough-Related Research
University of Manchester
2022-2025
Zunyi Medical University
2025
Imperial College London
2014-2024
State Forestry and Grassland Administration
2022-2024
Hunan City University
2024
China Southern Power Grid (China)
2024
Hohai University
2024
Dongbei University of Finance and Economics
2021-2023
Affiliated Hospital of Qingdao University
2022-2023
Southwest Jiaotong University
2023
With the rapid growth of cloud service systems and their increasing complexity, failures become unavoidable. Outages, which are critical failures, could dramatically degrade system availability impact user experience. To minimize downtime ensure high availability, we develop an intelligent outage management approach, called AirAlert, can forecast occurrence outages before they actually happen diagnose root cause after indeed occur. AirAlert works as a global watcher for entire system,...
Electronic health records (EHRs) are a valuable source of information that can aid in understanding patient's condition and making informed healthcare decisions. However, modelling longitudinal EHRs with heterogeneous is challenging task. Although recurrent neural networks (RNNs), which current artificial intelligence (AI) models, have the capability to capture information, their explanatory power limited. Predictive clustering recent development this field, provides cluster-level...
Quercus variabilis (Fagaceae) is an ecologically and economically important deciduous broadleaved tree species native to widespread in East Asia. It a valuable woody indicator of local forest health, occupies dominant position ecosystems However, genomic resources from Q. are still lacking. Here, we present high-quality genome generated by PacBio HiFi Hi-C sequencing. The assembled size 787 Mb, with contig N50 26.04 Mb scaffold 64.86 comprising 12 pseudo-chromosomes. repetitive sequences...
Electronic health records (EHRs) contain diverse patient information, including medical notes, clinical events, and laboratory test results. Integrating this multimodal data can improve disease diagnoses using deep learning models. However, effectively combining different modalities for diagnosis remains challenging. Previous approaches, such as attention mechanisms contrastive learning, have attempted to address but do not fully integrate the into a unified feature space. This paper...
In the fields of industrial production or safety monitoring, wireless sensor networks are often content with unreliable and time-varying channels that susceptible to interference. Consequently, ensuring both transmission reliability data accuracy has garnered substantial attention in recent years. Although multipath routing-based schemes can provide for networks, achieving high simultaneously remains challenging. To address this issue, an Energy-efficient Multipath Routing algorithm...
In multi-end-to-end path request planning, the control plane may not be able to meet all requirements under limited bandwidth resources. Moreover, suboptimal planning can lead localized network congestion, which in turn causes an overall imbalance load. Therefore, multi-domain needs consider more resource states during selection, such as link weights, load saturation, and occupancy rates, order select optimal paths maximize satisfaction of data while maintaining balance. To address issues,...
Abstract The global pandemic of the 2019-nCov requires evaluation policy interventions to mitigate future social and economic costs quarantine measures worldwide. We propose an epidemiological model for forecasting which incorporates new data in real-time through variational assimilation. analyze discuss infection rates UK, US Italy. furthermore develop a custom compartmental SIR fit variables related available pandemic, named SITR model, allows more granular inference on numbers. compare...
Multilevel data integration is becoming a major area of research in systems biology. Within this area, multi-'omics datasets on complex diseases are more readily available and there need to set standards good practices for integrated analysis biological, clinical environmental data. We present framework plan generate single signatures disease states. The divided into four steps: dataset subsetting, feature filtering, 'omics-based clustering biomarker identification. illustrate the usefulness...
In large-scale online service systems, incidents occur frequently due to a variety of causes, from updates software and hardware changes in operation environment. These could significantly degrade system's availability customers' satisfaction. Some are linked because they duplicate or inter-related. The can greatly help on-call engineers find mitigation solutions identify the root causes. this work, we investigate their links representative real-world incident management (IcM) system. Based...
Restrictions on human activities remarkably reduced emissions of air pollutants in China during the COVID-19 lockdown periods. However, distinct responses O3 concentrations were observed across China. In Beijing–Tianjin–Hebei (BTH) and Yangtze River Delta (YRD) regions, enhanced by 90.21 71.79% from pre-lockdown to periods 2020, significantly greater than equivalent for same over 2015–2019 (69.99 43.62%, p < 0.001). contrast, a decline was detected (−1.1%) Pearl (PRD) region. To better...
Electronic health records (EHRs) contain vast medical information like diagnosis, medication, and procedures, enabling personalized drug recommendations treatment adjustments. However, current recommendation methods only model patients' conditions from EHR data, neglecting the rich relationships within data. This paper seeks to utilize a heterogeneous network (HIN) represent develop graph representation learning method for medication recommendation. three critical issues need be...
Abstract Decision support systems are being developed to assist clinicians in complex decision-making processes by leveraging information from clinical knowledge and electronic health records (EHRs). One typical application is disease risk prediction, which can be challenging due the complexity of modelling longitudinal EHR data, including unstructured medical notes. To address this challenge, we propose a deep state-space model (DSSM) that simulates patient’s state transition process...