Search

The fire plume behavior of over-ventilated compartment fire is believed to be related with the façade fire. When the fire plume is reattached to the façade wall, the combustible materials over building wall are potential to be ignited soon. To investigate the window spill fire plume trajectory of over-ventilated intermediate-scale compartment fires, a modeling of fire plume trajectory is set up by using the energy conservation equation and spread theory. The temperature history of over-ventilated compartment fire is conducted by using a 1.35 m (L) × 1.35 m (H) × 1.35 m (W) compartment with window opening aspect varied from 1.12 to 4.44 and HRR differed from 200 kW to 1000 kW. The temperature of fire plume is recorded by the thermocouple mesh and the IR camera. It shows that the modelling theory could be used to predict the shape of fire plume. It agrees well with experimental result. The heat release rate of compartment fire is found to impact little influence on the shape of fire plume regarding a fixed opening dimension. It could provide a reasonable method for fire plume trajectory prediction of the intermediate-scale enclosure fire under an over-ventilated condition.

Abstract Background Clustering approaches using single omics platforms are increasingly used to characterise molecular phenotypes of eosinophilic and neutrophilic asthma. Effective integration of multi‐omics platforms should lead towards greater refinement of asthma endotypes across molecular dimensions and indicate key targets for intervention or biomarker development. Objectives To determine whether multi‐omics integration of sputum leads to improved granularity of the molecular classification of severe asthma. Methods We analyzed six ‐omics data blocks–microarray transcriptomics, gene set variation analysis of microarray transcriptomics, SomaSCAN proteomics assay, shotgun proteomics, 16S microbiome sequencing, and shotgun metagenomic sequencing–from induced sputum samples of 57 severe asthma patients, 15 mild‐moderate asthma patients, and 13 healthy volunteers in the U‐BIOPRED European cohort. We used Monti consensus clustering algorithm for aggregation of clustering results and Similarity Network Fusion to integrate the 6 multi‐omics datasets of the 72 asthmatics. Results Five stable omics‐associated clusters were identified (OACs). OAC1 had the best lung function with the least number of severe asthmatics with sputum paucigranulocytic inflammation. OAC5 also had fewer severe asthma patients but the highest incidence of atopy and allergic rhinitis, with paucigranulocytic inflammation. OAC3 comprised only severe asthmatics with the highest sputum eosinophilia. OAC2 had the highest sputum neutrophilia followed by OAC4 with both clusters consisting of mostly severe asthma but with more ex/current smokers in OAC4. Compared to OAC4, there was higher incidence of nasal polyps, allergic rhinitis, and eczema in OAC2. OAC2 had microbial dysbiosis with abundant Moraxella catarrhalis and Haemophilus influenzae. OAC4 was associated with pathways linked to IL‐22 cytokine activation, with the prediction of therapeutic response to anti‐IL22 antibody therapy. Conclusion Multi‐omics analysis of sputum in asthma has defined with greater granularity the asthma endotypes linked to neutrophilic and eosinophilic inflammation. Modelling diverse types of high‐dimensional interactions will contribute to a more comprehensive understanding of complex endotypes. Key Points Unsupervised clustering on sputum multi‐omics of asthma subjects identified 3 out of 5 clusters with predominantly severe asthma. One severe asthma cluster was linked to type 2 inflammation and sputum eosinophilia while the other 2 clusters to sputum neutrophilia. One severe neutrophilic asthma cluster was linked to Moraxella catarrhalis and to a lesser extent Haemophilus influenzae while the second cluster to activation of IL‐22.

Dialogue systems are an important research direction in artificial intelligence, with broad application prospects and market value. In order to improve system efficiency and user satisfaction, an open domain generative dialogue system integrating knowledge graphs has been developed, which facilitates the utilization of rich background knowledge during dialogue generation, thereby generating more coherent and meaningful dialogue content. At the same time, based on the sequence to sequence model, a bidirectional gated loop unit is introduced to better capture contextual information and improve the model’s understanding and generation ability. These results confirmed that the average values of the improved model in the training and validation sets were 98.66% and 87.34%, respectively, with loss values of 0.01 and 0.10. Compared to the baseline model, this improved model improved Hits@1 and Hits@3 by 0.09% and 0.25%, respectively. This improved model had the minimum perplexity of 17.62. The security and diversity of this improved system were 0.80 and 0.82, respectively, taking into account the balance of these two types of performance. Its correlation and fluency were 1.44 and 1.56, respectively. This indicates that this improved model is beneficial for improving the efficiency of generating dialogue and has certain effectiveness, better meeting users’ needs and improve user satisfaction. This system can provide users with a better conversation experience and provide technological and innovative features for artificial intelligence dialogue assistants.

Operating overvoltage occurs when the pantograph or main breaker of an electric locomotive is operated, which is prone to causing insulation failure of high-voltage equipment. The HXD1 electric locomotive is taken as the research object in this paper to explore the characteristics and influencing factors of operating overvoltage. Under pantograph lifting, main breaker closing, main breaker opening, and pantograph dropping, operating overvoltage waveform in the high-voltage system is recorded by a high-speed oscilloscope and resistance–capacitance voltage divider to analyze the overvoltage characteristics and distribution law. Tested data show that the amplitude of operating overvoltage is in the range of 80 to 330 kV with ultra-high steepness, which is similar to the Very Fast Transient Overvoltage (VFTO) in power systems. The maximum overvoltage during the entire test occurred during the main breaker closing and its amplitude is 328.60 kV with a steepness of 4.21 × 104 kV/μs. The max overvoltage of the other operations (pantograph lifting, main breaker opening, and pantograph dropping) are 280.60 kV, 194.73 kV, and 305.56 kV with ultra-high steepness. High-amplitude overvoltage is predominantly located at the pantograph, while the low-amplitude sort is mainly observed around other high-voltage equipment. The result indicates that operating overvoltage belongs to ultra-fast transient overvoltage and its amplitude and steepness are higher than existing research.

When the electric locomotive pantograph is dropping, the interruption of pantograph catenary contact causes electromagnetic oscillation and arcing. The frequent arc burning that occurs due to charge accumulation results in the amplitude of overvoltage increasing gradually, posing a threat to locomotive high-voltage equipment. However, the physical mechanisms and characteristics of overvoltage are still unclear. This paper proposes a simulation model of operating overvoltage due to a dropping pantograph based on the pantograph–catenary arc and variable capacitance. Distributed RLC electromagnetic oscillation is considered, which allows the real-time calculation of arc resistance and capacitance. Under the same working conditions, the error between the simulation and test results is less than 4.0%, which proves the credibility of the model. The variation law of overvoltage under different dropping speeds or catenary phases was investigated, which shows the max amplitude is 298.20 kV and steepness is 2096.80 kV/μs at 0.30 m/s speed. The waveform shows the characteristics of high amplitude and high steepness, similar to very fast transient overvoltage (VFTO). There is a sinusoidal relationship between the catenary phase and overvoltage amplitude. The closer the catenary phase to 90°, the higher the overvoltage amplitude. The research has important guiding significance for the overvoltage formation mechanism of a traction power supply system and the insulation coordination design of high-voltage equipment.

Abstract Machine learning is widely used to infer ground-level concentrations of air pollutants from satellite observations. However, a single pollutant is commonly targeted in previous explorations, which would lead to duplication of efforts and ignoration of interactions considering the interactive nature of air pollutants and their common influencing factors. We aim to build a unified model to offer a synchronized estimation of ground-level air pollution levels. We constructed a multi-output random forest (MORF) model and achieved simultaneous estimation of hourly concentrations of PM2.5, PM10, O3, NO2, CO, and SO2 in China, benefiting from the world’s first geostationary air-quality monitoring instrument Geostationary Environment Monitoring Spectrometer. MORF yielded a high accuracy with cross-validated R2 reaching 0.94. Meanwhile, model efficiency was significantly improved compared to single-output models. Based on retrieved results, the spatial distributions, seasonality, and diurnal variations of six air pollutants were analyzed and two typical pollution events were tracked.

Abstract Methane (CH4) is the second most potent greenhouse gas (GHG), and China emerges as the largest anthropogenic CH4 emitter by country. Current limited CH4 monitoring systems in China are unfortunately inadequate to support carbon management. Here we use the Weather Research and Forecasting model (WRF) coupled with a GHG module and satellite constrained emissions to simulate the spatiotemporal distribution of CH4 over East Asia in 2017. Model evaluations using both satellite retrievals and ground-based observations indicate reliable performance. We further inter-compare four proper orthogonal decomposition (POD)-based sensor placement algorithms and find they are able to capture main spatial features of surface CH4 under an oversampled condition. The QR pivot algorithm exhibits superiority in capturing high CH4, and it offers the best reconstruction with both high efficiency and accuracy. Areas with high CH4 concentrations and intense anthropogenic activities remain underrepresented by current CH4 sampling studies, leading to notable reconstruction error over central and eastern China. Optimal planning of 160 sensors guided by the QR pivot algorithm can yield reasonable reconstruction performance and costs of site construction. Our results can provide valuable references for future planning of CH4 monitoring sites.

Knowledge Graphs (KGs), a structural way to model human knowledge, have been a critical component of many artificial intelligence applications. Many KG-based tasks are built using knowledge representation learning, which embeds KG entities and relations into a low-dimensional semantic space. However, the quality of representation learning is often limited by the heterogeneity and sparsity of real-world KGs. Multi-KG representation learning, which utilizes KGs from different sources collaboratively, presents one promising solution. In this paper, we propose a simple, but effective iterative method that post-processes pre-trained knowledge graph embedding (IPPT4KRL) on individual KGs to maximize the knowledge transfer from another KG when a small portion of alignment information is introduced. Specifically, additional triples are iteratively included in the post-processing based on their adjacencies to the cross-KG alignments to refine the pre-trained embedding space of individual KGs. We also provide the benchmarking results of existing multi-KG representation learning methods on several generated and well-known datasets. The empirical results of the link prediction task on these datasets show that the proposed IPPT4KRL method achieved comparable and even superior results when compared against more complex methods in multi-KG representation learning.

Limitations in the current capability of monitoring PM2.5 adversely impact air quality management and health risk assessment of PM2.5 exposure. Commonly, ground-based monitoring networks are established to measure the PM2.5 concentrations in highly populated regions and protected areas such as national parks, yet large gaps exist in spatial coverage. Satellite-derived aerosol optical properties serve to complement the missing spatial information of ground-based monitoring networks. However, satellite remote sensing AODs are hampered under cloudy/hazy conditions or during nighttime. Here we strive to overcome the long-standing restriction that surface PM2.5 cannot be obtained with satellite remote sensing under cloudy/hazy conditions or during nighttime. In this work, we introduce a deep spatiotemporal neural network (ST-NN) and demonstrate that it can artfully fill these observational gaps. We quantified the quantitative impact of input variables on the results using sensitivity and visual analysis of the model. This technique provides ground-level PM2.5 concentrations with a high spatial resolution (0.01°) and 24-h temporal coverage, hour-by-hour, complete coverage. In central and eastern China, the 10-fold cross-validation results show that R2 is between 0.8 and 0.9, and RMSE is between 6 and 26 (µg m−3). The relative error varies in different concentration ranges and is generally less than 20%. Better constrained spatiotemporal distributions of PM2.5 concentrations will contribute to improving health effects studies, atmospheric emission estimates, and air quality predictions.

Abstract Consciousness is one of the unique features of creatures, and is also the root of biological intelligence. Up to now, all machines and robots haven’t had consciousness. Then, will the artificial intelligence (AI) be conscious? Will robots have real intelligence without consciousness? The most primitive consciousness is the perception and expression of self‐existence. In order to perceive the existence of the concept of ‘I’, a creature must first have a perceivable boundary such as skin to separate ‘I’ from ‘non‐I’. For robots, to have the self‐awareness, they also need to be wrapped by a similar sensory membrane. Nowadays, as intelligent tools, AI systems should also be regarded as the external extension of human intelligence. These tools are unconscious. The development of AI shows that intelligence can exist without consciousness. When human beings enter into the era of life intelligence from AI, it is not the AI became conscious, but that conscious lives will have strong AI. Therefore, it becomes more necessary to be careful on applying AI to living creatures, even to those lower‐level animals with only consciousness. The subversive revolution of such application may produce more careful thinking.

Abstract Background The global spread of the COVID-19 pandemic has become the most fundamental threat to human health. In the absence of vaccines and effective therapeutical solutions, non-pharmaceutic intervention has become a major way for controlling the epidemic. Gentle mitigation interventions are able to slow down the epidemic but not to halt it well. While strict suppression interventions are efficient for controlling the epidemic, long-term measures are likely to have negative impacts on economics and people’s daily live. Hence, dynamically balancing suppression and mitigation interventions plays a fundamental role in manipulating the epidemic curve. Methods We collected data of the number of infections for several countries during the COVID-19 pandemics and found a clear phenomenon of periodic waves of infection. Based on the observation, by connecting the infection level with the medical resources and a tolerance parameter, we propose a mathematical model to understand impacts of combining intervention measures on the epidemic dynamics. Results Depending on the parameters of the medical resources, tolerance level, and the starting time of interventions, the combined intervention measure dynamically changes with the infection level, resulting in a periodic wave of infections controlled below an accepted level. The study reveals that, (a) with an immediate, strict suppression, the numbers of infections and deaths are well controlled with a significant reduction in a very short time period; (b) an appropriate, dynamical combination of suppression and mitigation may find a feasible way in reducing the impacts of epidemic on people’s live and economics. Conclusions While the assumption of interventions deployed with a cycle of period in the model is limited and unrealistic, the phenomenon of periodic waves of infections in reality is captured by our model. These results provide helpful insights for policy-makers to dynamically deploy an appropriate intervention strategy to effectively battle against the COVID-19.

The early identification of metabolic disorders could improve or prevent overt disease. Here the authors show that the circulating concentration of hyocholic acid (HCA) species is decreased in the context of obesity and diabetes and increased after gastric bypass surgery in humans, and further that serum HCA species are predictive of metabolic outcomes in healthy individuals.

Abstract Background Patients with severe asthma may have a greater risk of dying from COVID-19 disease. Angiotensin converting enzyme-2 (ACE2) and the enzyme proteases, transmembrane protease serine 2 (TMPRSS2) and FURIN, are needed for viral attachment and invasion into host cells. Methods We examined microarray mRNA expression of ACE2, TMPRSS2 and FURIN in sputum, bronchial brushing and bronchial biopsies of the European U-BIOPRED cohort. Clinical parameters and molecular phenotypes, including asthma severity, sputum inflammatory cells, lung functions, oral corticosteroid (OCS) use, and transcriptomic-associated clusters, were examined in relation to gene expression levels. Results ACE2 levels were significantly increased in sputum of severe asthma compared to mild-moderate asthma. In multivariate analyses, sputum ACE2 levels were positively associated with OCS use and male gender. Sputum FURIN levels were significantly related to neutrophils (%) and the presence of severe asthma. In bronchial brushing samples, TMPRSS2 levels were positively associated with male gender and body mass index, whereas FURIN levels with male gender and blood neutrophils. In bronchial biopsies, TMPRSS2 levels were positively related to blood neutrophils. The neutrophilic molecular phenotype characterised by high inflammasome activation expressed significantly higher FURIN levels in sputum than the eosinophilic Type 2-high or the pauci-granulocytic oxidative phosphorylation phenotypes. Conclusion Levels of ACE2 and FURIN may differ by clinical or molecular phenotypes of asthma. Sputum FURIN expression levels were strongly associated with neutrophilic inflammation and with inflammasome activation. This might indicate the potential for a greater morbidity and mortality outcome from SARS-CoV-2 infection in neutrophilic severe asthma.

Abstract Background Exacerbation‐prone asthma is a feature of severe disease. However, the basis for its persistency remains unclear. Objectives To determine the clinical and transcriptomic features of frequent exacerbators (FEs) and persistent FEs (PFEs) in the U‐BIOPRED cohort. Methods We compared features of FE (≥2 exacerbations in past year) to infrequent exacerbators (IE,

Objective Clinical notes contain information that has not been documented elsewhere, including responses to treatment and clinical findings, which are crucial for predicting key outcomes in patients in acute care. In this study, we propose the automatic annotation of phenotypes from clinical notes as a method to capture essential information to predict outcomes in the intensive care unit (ICU). This information is complementary to typically used vital signs and laboratory test results.Methods In this study, we developed a novel phenotype annotation model to extract the phenotypical features of patients, which were then used as input features of predictive models to predict ICU patient outcomes. We demonstrated and validated this approach by conducting experiments on three ICU prediction tasks, including in-hospital mortality, physiological decompensation and length of stay (LOS) for over 24 000 patients using the Medical Information Mart for Intensive Care (MIMIC-III) dataset.Results The predictive models incorporating phenotypical information achieved 0.845 (area under the curve–receiver operating characteristic (AUC-ROC)) for in-hospital mortality, 0.839 (AUC-ROC) for physiological decompensation and 0.430 (kappa) for LOS, all of which consistently outperformed the baseline models using only vital signs and laboratory test results. Moreover, we conducted a thorough interpretability study showing that phenotypes provide valuable insights at both the patient and cohort levels.Conclusion The proposed approach demonstrates that phenotypical information complements traditionally used vital signs and laboratory test results and significantly improves the accuracy of outcome prediction in the ICU.

Estimating the changes of epidemiological parameters, such as instantaneous reproduction number, Rt, is important for understanding the transmission dynamics of infectious diseases. Current estimates of time-varying epidemiological parameters often face problems such as lagging observations, averaging inference, and improper quantification of uncertainties. To address these problems, we propose a Bayesian data assimilation framework for time-varying parameter estimation. Specifically, this framework is applied to estimate the instantaneous reproduction number Rt during emerging epidemics, resulting in the state-of-the-art 'DARt' system. With DARt, time misalignment caused by lagging observations is tackled by incorporating observation delays into the joint inference of infections and Rt; the drawback of averaging is overcome by instantaneously updating upon new observations and developing a model selection mechanism that captures abrupt changes; the uncertainty is quantified and reduced by employing Bayesian smoothing. We validate the performance of DARt and demonstrate its power in describing the transmission dynamics of COVID-19. The proposed approach provides a promising solution for making accurate and timely estimation for transmission dynamics based on reported data.

Perinatal exposure to heat and air pollution has been shown to affect the risk of preterm birth (PTB). However, limited evidence exists regarding their joint effects, particularly in heavily polluted regions like China. This study utilized data from the ongoing China Birth Cohort Study, including 103 040 birth records up to December 2020, and hourly measurements of air pollution (PM _2.5 , NO _2 , and O _3 ) and temperature. We assessed the nonlinear associations between air pollution and temperature extereme exposures and PTB by employing generalized additive models with restricted cubic slines. Air pollution and temperature thresholds (corresponding to minimum PTB risks) were determined by the lowest Akaike Information Criterion. We found that maternal exposures to PM _2.5 , NO _2 , O _3 , and both low and high temperature during the third trimester of pregnancy were independently associated with increased risk of PTB. The adjusted risk ratios for PTB of PM _2.5 , O _3 , NO _2 , and temperature at the 95th percentile against thresholds were 1.32 (95% CI: 1.23, 1.42), 1.33 (95% CI: 1.18, 1.50), 1.44 (95% CI: 1.33, 1.56) and 1.70 (95% CI: 1.56, 1.85), respectively. Positive additive interactions [relative excess risk due to interaction (RERI) > 0] of PM _2.5 –high temperature (HT), O _3 –HT, O _3 –low temperature (LT) are identified, but the interactive effects of PM _2.5 and LT were negative (RERI < 0). These observed independent effects of air pollution and temperature, along with their potential joint effects, have important implications for future studies and the development of public health policies aimed at improving perinatal health outcomes.

Asthma affects more than 300 million people globally and is both under diagnosed and under treated. The most recent and largest genome-wide association study investigating moderate to severe asthma to date was carried out in 2019 and identified 25 independent signals. However, as new and in-depth downstream databases become available, the translational analysis of these signals into target genes and pathways is timely. In this study, unique (U-BIOPRED) and publicly available datasets (HaploReg, Open Target Genetics and GTEx) were investigated for the 25 GWAS signals to identify 37 candidate causal genes. Additional traits associated with these signals were identified through PheWAS using the UK Biobank resource, with asthma and eosinophilic traits amongst the strongest associated. Gene expression omnibus dataset examination identified 13 candidate genes with altered expression profiles in the airways and blood of asthmatic subjects, including MUC5AC and STAT6. Gene expression analysis through publicly available datasets highlighted lung tissue cell specific expression, with both MUC5AC and SLC22A4 genes showing enriched expression in ciliated cells. Gene enrichment pathway and interaction analysis highlighted the dominance of the HLA-DQA1/A2/B1/B2 gene cluster across many immunological diseases including asthma, type I diabetes, and rheumatoid arthritis. Interaction and prediction analyses found IL33 and IL18R1 to be key co-localization partners for other genes, predicted that CD274 forms co-expression relationships with 13 other genes, including the HLA-DQA1/A2/B1/B2 gene cluster and that MUC5AC and IL37 are co-expressed. Drug interaction analysis revealed that 11 of the candidate genes have an interaction with available therapeutics. This study provides significant insight into these GWAS signals in the context of cell expression, function, and disease relationship with the view of informing future research and drug development efforts for moderate-severe asthma.

An amendment to this paper has been published and can be accessed via the original article.

Geospatial Information Verification Mid-End Platform for Natural Resource Administration is designed in response to issues such as repeated development, low scalability, and inconsistent verification rules in existing approval and supervision application systems. We first discussed the architecture of the middle platform and micro-services and also examined the business requirements. Secondly, we presented the architecture of the spatial information verification platform. Finally, the application method in the construction land approval business is introduced. Practical applications proved that the spatial information verification platform is highly scalable and maintainable, with reusable business components and data services for a variety of government affairs application systems.

Reconstructing the full shape of neurons is a major informatics challenge as it requires handling huge whole-brain imaging datasets. Here the authors present an open-source virtual reality annotation system for precise and efficient data production of neuronal shapes reconstructed from whole brains.

Abstract Background For large international research consortia, such as those funded by the European Union’s Horizon 2020 programme or the Innovative Medicines Initiative, good data coordination practices and tools are essential for the successful collection, organization and analysis of the resulting data. Research consortia are attempting ever more ambitious science to better understand disease, by leveraging technologies such as whole genome sequencing, proteomics, patient-derived biological models and computer-based systems biology simulations. Results The IMI eTRIKS consortium is charged with the task of developing an integrated knowledge management platform capable of supporting the complexity of the data generated by such research programmes. In this paper, using the example of the OncoTrack consortium, we describe a typical use case in translational medicine. The tranSMART knowledge management platform was implemented to support data from observational clinical cohorts, drug response data from cell culture models and drug response data from mouse xenograft tumour models. The high dimensional (omics) data from the molecular analyses of the corresponding biological materials were linked to these collections, so that users could browse and analyse these to derive candidate biomarkers. Conclusions In all these steps, data mapping, linking and preparation are handled automatically by the tranSMART integration platform. Therefore, researchers without specialist data handling skills can focus directly on the scientific questions, without spending undue effort on processing the data and data integration, which are otherwise a burden and the most time-consuming part of translational research data analysis.

Due to the complexity of scientific experiments, existing methods for capturing the provenance information from the scientific workflows (SWFs) face high programming overhead and code errors. In addition, the coarse-grained nature of the SWF provenance implies the loss of internal details of the workflow processes, which can lead to incomplete or inaccurate data dependencies and dependency differentiation problems. The diversity in scientific fields also reveals the limited versatility of the SWF provenance models. In this context, we propose a content-rich and fine-grained SWF provenance model (CF-PROV). This model provides normative transformations and documentation declarations for the multi-field SWFs, reducing the programming overhead and increasing the versatility. Our method of dividing the workflow provenance into data provenance and process provenance and our formal description of data deduction at the field level enrich the provenance information and transform the coarse-grained workflow provenance into a fine-grained provenance. Finally, the experiments on the model compression ratio and model generation time in multiple scientific fields demonstrate the versatility and rationality of the CF-PROV.

Abstract COVID‐19 is spreading rapidly worldwide, posing great threats to public health and economy. This study aims to examine how the transmission of COVID‐19 is modulated by climate conditions, which is of great importance for better understanding of the seasonal feature of COVID‐19. Constrained by the accurate observations we can make, the basic reproduction numbers (R0) for each country were inferred and linked to temperature and relative humidity (RH) with statistical analysis. Using R0 as the measure of COVID‐19 transmission potential, we find stronger transmission of COVID‐19 under mildly warm (0°C < T 60%) climate conditions, while extremely low (T 20°C) temperature or a dry climate (RH

Large-scale automatic speech recognition model has achieved impressive performance. However, huge computational resources and massive amount of data are required to train an ASR model. Knowledge distillation is a prevalent model compression method which transfers the knowledge from large model to small model. To improve the efficiency of knowledge distillation for end-to-end speech recognition especially in the low-resource setting, a Mixup-based Knowledge Distillation (MKD) method is proposed which combines Mixup, a data-agnostic data augmentation method, with softmax-level knowledge distillation. A loss-level mixture is presented to address the problem caused by the non-linearity of label in the KL-divergence when adopting Mixup to the teacher–student framework. It is mathematically shown that optimizing the mixture of loss function is equivalent to optimize an upper bound of the original knowledge distillation loss. The proposed MKD takes the advantage of Mixup and brings robustness to the model even with a small amount of training data. The experiments on Aishell-1 show that MKD obtains a 15.6% and 3.3% relative improvement on two student models with different parameter scales compared with the existing methods. Experiments on data efficiency demonstrate MKD achieves similar results with only half of the original dataset.

High-order, beyond-pairwise interdependencies are at the core of biological, economic, and social complex systems, and their adequate analysis is paramount to understand, engineer, and control such systems. This paper presents a framework to measure high-order interdependence that disentangles their effect on each individual pattern exhibited by a multivariate system. The approach is centered on the local O-information, a new measure that assesses the balance between synergistic and redundant interdependencies at each pattern. To illustrate the potential of this framework, we present a detailed analysis of music scores from J. S. Bach, which reveals how high-order interdependence is deeply connected with highly nontrivial aspects of the musical discourse. Our results place the local O-information as a promising tool of wide applicability, which opens other perspectives for analyzing high-order relationships in the patterns exhibited by complex systems.

Generating designs via machine learning has been an on-going challenge in computer-aided design. Recently, deep learning methods have been applied to randomly generate images in fashion, furniture and product design. However, such deep generative methods usually require a large number of training images and human aspects are not taken into account in the design process. In this work, we seek a way to involve human cognitive factors through brain activity indicated by electroencephalographic measurements (EEG) in the generative process. We propose a neuroscience-inspired design with a machine learning method where EEG is used to capture preferred design features. Such signals are used as a condition in generative adversarial networks (GAN). First, we employ a recurrent neural network Long Short-Term Memory as an encoder to extract EEG features from raw EEG signals; this data are recorded from subjects viewing several categories of images from ImageNet. Second, we train a GAN model conditioned on the encoded EEG features to generate design images. Third, we use the model to generate design images from a subject’s EEG measured brain activity. To verify our proposed generative design method, we present a case study, in which the subjects imagine the products they prefer, and the corresponding EEG signals are recorded and reconstructed by our model for evaluation. The results indicate that a generated product image with preference EEG signals gains more preference than those generated without EEG signals. Overall, we propose a neuroscience-inspired artificial intelligence design method for generating a design taking into account human preference. The method could help improve communication between designers and clients where clients might not be able to express design requests clearly.

Crohn's disease and ulcerative colitis are driven by both common and distinct underlying mechanisms of pathobiology. Both diseases, exhibit heterogeneity underscored by the variable clinical responses to therapeutic interventions. We aimed to identify disease-driving pathways and classify individuals into subpopulations that differ in their pathobiology and response to treatment. We applied hierarchical clustering of enrichment scores derived from gene set variation analysis of signatures representative of various immunological processes and activated cell types, to a colonic biopsy dataset that included healthy volunteers, Crohn's disease and ulcerative colitis patients. Patient stratification at baseline or after anti-TNF treatment in clinical responders and non-responders was queried. Signatures with significantly different enrichment scores were identified using a general linear model. Comparisons to healthy controls were made at baseline in all participants and then separately in responders and non-responders. Fifty-nine percent of the signatures were commonly enriched in both conditions at baseline, supporting the notion of a disease continuum within ulcerative colitis and Crohn's disease. Signatures included T cells, macrophages, neutrophil activation and poly:IC signatures, representing acute inflammation and a complex mix of potential disease-driving biology. Collectively, identification of significantly enriched signatures allowed establishment of an inflammatory bowel disease molecular activity score which uses biopsy transcriptomics as a surrogate marker to accurately track disease severity. This score separated diseased from healthy samples, enabled discrimination of clinical responders and non-responders at baseline with 100% specificity and 78.8% sensitivity, and was validated in an independent data set that showed comparable classification. Comparing responders and non-responders separately at baseline to controls, 43% and 70% of signatures were enriched, respectively, suggesting greater molecular dysregulation in TNF non-responders at baseline. This methodological approach could facilitate better targeted design of clinical studies to test therapeutics, concentrating on patient subsets sharing similar underlying pathobiology, therefore increasing the likelihood of clinical response.

The authors propose a novel reinforcement learning (RL) framework, where agent behaviour is governed by traditional control theory. This integrated approach, called time-in-action RL, enables RL to be applicable to many real-world systems, where underlying dynamics are known in their control theoretical formalism. The key insight to facilitate this integration is to model the explicit time function, mapping the state-action pair to the time accomplishing the action by its underlying controller. In their framework, they describe an action by its value (action value), and the time that it takes to perform (action time). An action-value results from the policy of RL regarding a state. Action time is estimated by an explicit time model learnt from the measured activities of the underlying controller. RL value network is then trained with embedded time model to predict action time. This approach is tested using a variant of Atari Pong and proved to be convergent.

Background: The timed 25-foot walk (T25FW) is widely used as a clinic performance measure, but has yet to be directly validated against gait speed in the home environment.Objectives: To develop an accurate method for remote assessment of walking speed and to test how predictive the clinic T25FW is for real-life walking.Methods: An AX3-Axivity tri-axial accelerometer was positioned on 32 MS patients (Expanded Disability Status Scale [EDSS] 0–6) in the clinic, who subsequently wore it at home for up to 7 days. Gait speed was calculated from these data using both a model developed with healthy volunteers and individually personalized models generated from a machine learning algorithm.Results: The healthy volunteer model predicted gait speed poorly for more disabled people with MS. However, the accuracy of individually personalized models was high regardless of disability (R-value = 0.98, p-value = 1.85 × 10−22). With the latter, we confirmed that the clinic T25FW is strongly predictive of the maximum sustained gait speed in the home environment (R-value = 0.89, p-value = 4.34 × 10−8).Conclusion: Remote gait monitoring with individually personalized models is accurate for patients with MS. Using these models, we have directly validated the clinical meaningfulness (i.e., predictiveness) of the clinic T25FW for the first time.

The advertising industry depends on an effective assessment of the impact of advertising as a key performance metric for their products. However, current assessment methods have relied on either indirect inference from observing changes in consumer behavior after the launch of an advertising campaign, which has long cycle times and requires an ad campaign to have already have been launched (often meaning costs having been sunk). Or through surveys or focus groups, which have a potential for experimental biases, peer pressure, and other psychological and sociological phenomena that can reduce the effectiveness of the study. In this paper, we investigate a new approach to assess the impact of advertisement by utilizing low-cost EEG headbands to record and assess the measurable impact of advertising on the brain. Our evaluation shows the desired performance of our method based on user experiment with 30 recruited subjects after watching 220 different advertisements. We believe the proposed SVM method can be further developed to a general and scalable methodology that can enable advertising agencies to assess impact rapidly, quantitatively, and without bias.

Robust and fast traffic sign recognition is very important but difficult for safe driving assistance systems. This study addresses fast and robust traffic sign recognition to enhance driving safety. The proposed method includes three stages. First, a typical Hough transformation is adopted to implement coarse-grained location of the candidate regions of traffic signs. Second, a RIBP (Rotation Invariant Binary Pattern) based feature in the affine and Gaussian space is proposed to reduce the time of traffic sign detection and achieve robust traffic sign detection in terms of scale, rotation, and illumination. Third, the techniques of ANN (Artificial Neutral Network) based feature dimension reduction and classification are designed to reduce the traffic sign recognition time. Compared with the current work, the experimental results in the public datasets show that this work achieves robustness in traffic sign recognition with comparable recognition accuracy and faster processing speed, including training speed and recognition speed.

Classification models built on biological expression data are increasingly used to predict distinct disease subtypes. Selected features that separate sample groups can be the candidates of biomarkers, helping us to discover biological functions/pathways. However, three challenges are associated with building a robust classification and feature selection model: 1) the number of significant biomarkers is much smaller than that of measured features for which the search will be exhaustive; 2) current biological expression data are big in both sample size and feature size which will worsen the scalability of any search algorithms; and 3) expression profiles of certain features are typically highly correlated which may prevent to distinguish the predominant features. Unfortunately, most of the existing algorithms are partially addressing part of these challenges but not as a whole. In this paper, we propose a unified framework to address the above challenges. The classification and feature selection problem is first formulated as a nonconvex optimisation problem. Then the problem is relaxed and solved iteratively by a sequence of convex optimisation procedures which can be distributed computed and therefore allows the efficient implementation on advanced infrastructures. To illustrate the competence of our method over others, we first analyse a randomly generated simulation dataset under various conditions. We then analyse a real gene expression dataset on embryonal tumour. Further downstream analysis, such as functional annotation and pathway analysis, are performed on the selected features which elucidate several biological findings.

This paper presents a new methodology for collaborative sensor data management known as WikiSensing. It is a novel approach that incorporates online collaboration with sensor data management. We introduce the work on this research by describing the motivation and challenges of designing and developing an online collaborative sensor data management system. This is followed by a brief survey on popular sensor data management and online collaborative systems. We then present the architecture for WikiSensing highlighting its main components and features. Several example scenarios are described to present the functionality of the system. We evaluate the approach by investigating the performance of aggregate queries and the scalability of the system.

In this paper, we present a distributed infrastructure based on wireless sensors network and Grid computing technology for air pollution monitoring and mining, which aims to develop low-cost and ubiquitous sensor networks to collect real-time, large scale and comprehensive environmental data from road traffic emissions for air pollution monitoring in urban environment. The main informatics challenges in respect to constructing the high-throughput sensor Grid are discussed in this paper. We present a twolayer network framework, a P2P e-Science Grid architecture, and the distributed data mining algorithm as the solutions to address the challenges. We simulated the system in TinyOS to examine the operation of each sensor as well as the networking performance. We also present the distributed data mining result to examine the effectiveness of the algorithm.

BACKGROUNDS: Recent explosion of biological data brings a great challenge for the traditional clustering algorithms. With increasing scale of data sets, much larger memory and longer runtime are required for the cluster identification problems. The affinity propagation algorithm outperforms many other classical clustering algorithms and is widely applied into the biological researches. However, the time and space complexity become a great bottleneck when handling the large-scale data sets. Moreover, the similarity matrix, whose constructing procedure takes long runtime, is required before running the affinity propagation algorithm, since the algorithm clusters data sets based on the similarities between data pairs. METHODS: Two types of parallel architectures are proposed in this paper to accelerate the similarity matrix constructing procedure and the affinity propagation algorithm. The memory-shared architecture is used to construct the similarity matrix, and the distributed system is taken for the affinity propagation algorithm, because of its large memory size and great computing capacity. An appropriate way of data partition and reduction is designed in our method, in order to minimize the global communication cost among processes. RESULT: A speedup of 100 is gained with 128 cores. The runtime is reduced from serval hours to a few seconds, which indicates that parallel algorithm is capable of handling large-scale data sets effectively. The parallel affinity propagation also achieves a good performance when clustering large-scale gene data (microarray) and detecting families in large protein superfamilies.

Signalling network inference is a central problem in system biology. Previous studies investigate this problem by independently inferring local signalling networks and then linking them together via crosstalk. Since a cellular signalling system is in fact indivisible, this reductionistic approach may have an impact on the accuracy of the inference results. Preferably, a cell-scale signalling network should be inferred as a whole. However, the holistic approach suffers from three practical issues: scalability, measurement and overfitting. Here we make this approach feasible based on two key observations: 1) variations of concentrations are sparse due to separations of timescales; 2) several species can be measured together using cross-reactivity. We propose a method, CCELL, for cell-scale signalling network inference from time series generated by immunoprecipitation using Bayesian compressive sensing. A set of benchmark networks with varying numbers of time-variant species is used to demonstrate the effectiveness of our method. Instead of exhaustively measuring all individual species, high accuracy is achieved from relatively few measurements.

With the deployment of multi-modality and large-scale sensor networks for monitoring air quality, we are now able to collect large and multi-dimensional spatio-temporal datasets. For these sensed data, we present a comprehensive visual analysis approach for air quality analysis. This approach integrates several visual methods, such as map-based views, calendar views, and trends views, to assist the analysis. Among those visual methods, map-based visual methods are used to display the locations of interest, and the calendar and the trends views are used to discover the linear and periodical patterns. The system also provides various interaction tools to combine the map-based visualization, trends view, calendar view and multi-dimensional view. In addition, we propose a self-adaptive calendar-based controller that can flexibly adapt the changes of data size and granularity in trends view. Such a visual analytics system would facilitate big-data analysis in real applications, especially for decision making support.

In large-scale machine-to-machine sensor networks, the applications such as urban air pollution monitoring require information management over widely distributed sensors under restricted power, processing, storage, and communication resources. The continual increases in size, data generating rates, and connectivity of sensor networks present significant scale and complexity challenges. Traditional schemes of information management are no longer applicable in such a scenario. Hence, an elastic resource allocation strategy is introduced which is a novel management technique based on elastic computing. With the discussion of the challenges of implementing real-time and high-performance information management in an elastic manner, an air pollution monitoring system, called EIMAP, was designed with a four-layer hierarchical structure. The core technique of EIMAP is the elastic resource provision scheduler, which models the constraint satisfaction problem by minimizing the use of resources for collecting information for a defined quality threshold. Simulation results show that the EIMAP system has high performance in resource provision and scalability. The experiment of pollution cloud dispersion tracking presents a case study of the system implementation.

In many situations, placing a physical sensor in the ideal position in or on the human body to acquire sensing data is incredibly difficult. Virtual sensors, in contrast to physical sensors, can provide indirect measurements by making use of other available sensor data. In this paper, we demonstrate a virtual sensing application developed as a service on top of a cloud-based health sensor data management platform called Wiki-Health. The proposed application “implants” virtual sensors in the human body by integrating environmental, geographic and personal sensor data with physiological models to compute temperature estimations of various parts of the body. The feasibility of the proposed virtual sensing service is supported by a case study. The ability to share computational models relevant to do calculations on measured data on the go is also discussed.