A tutorial on kernel density estimation and recent advances

A meshless stochastic method for Poisson-Nernst-Planck equations

A plethora of biological, physical, and chemical phenomena involve transport of charged particles (ions). Its continuum-scale description relies on the Poisson-Nernst-Planck (PNP) system, which encapsulates the conservation of mass and charge. The numerical solution of these coupled partial differential equations is challenging and suffers from both the curse of dimensionality and difficulty in efficiently parallelizing. We present a novel particle-based framework to solve the full PNP system by simulating a drift-diffusion process with time- and space-varying drift. We leverage Green's functions, kernel-independent fast multipole methods, and kernel density estimation to solve the PNP system in a meshless manner, capable of handling discontinuous initial states. The method is embarrassingly parallel, and the computational cost scales linearly with the number of particles and dimension. We use a series of numerical experiments to demonstrate both the method's convergence with respect to the number of particles and computational cost vis-à-vis a traditional partial differential equation solver.

The neural network RTNet exhibits the signatures of human perceptual decision-making

Convolutional neural networks show promise as models of biological vision. However, their decision behaviour, including the facts that they are deterministic and use equal numbers of computations for easy and difficult stimuli, differs markedly from human decision-making, thus limiting their applicability as models of human perceptual behaviour. Here we develop a new neural network, RTNet, that generates stochastic decisions and human-like response time (RT) distributions. We further performed comprehensive tests that showed RTNet reproduces all foundational features of human accuracy, RT and confidence and does so better than all current alternatives. To test RTNet's ability to predict human behaviour on novel images, we collected accuracy, RT and confidence data from 60 human participants performing a digit discrimination task. We found that the accuracy, RT and confidence produced by RTNet for individual novel images correlated with the same quantities produced by human participants. Critically, human participants who were more similar to the average human performance were also found to be closer to RTNet's predictions, suggesting that RTNet successfully captured average human behaviour. Overall, RTNet is a promising model of human RTs that exhibits the critical signatures of perceptual decision-making.

Predicting ADMET Properties from Molecule SMILE: A Bottom-Up Approach Using Attention-Based Graph Neural Networks

Understanding the pharmacokinetics, safety and efficacy of candidate drugs is crucial for their success. One key aspect is the characterization of absorption, distribution, metabolism, excretion and toxicity (ADMET) properties, which require early assessment in the drug discovery and development process. This study aims to present an innovative approach for predicting ADMET properties using attention-based graph neural networks (GNNs). The model utilizes a graph-based representation of molecules directly derived from Simplified Molecular Input Line Entry System (SMILE) notation. Information is processed sequentially, from substructures to the whole molecule, employing a bottom-up approach. The developed GNN is tested and compared with existing approaches using six benchmark datasets and by encompassing regression (lipophilicity and aqueous solubility) and classification (CYP2C9, CYP2C19, CYP2D6 and CYP3A4 inhibition) tasks. Results show the effectiveness of our model, which bypasses the computationally expensive retrieval and selection of molecular descriptors. This approach provides a valuable tool for high-throughput screening, facilitating early assessment of ADMET properties and enhancing the likelihood of drug success in the development pipeline.

Development of a machine vision-based weight prediction system of butterhead lettuce (Lactuca sativa L.) using deep learning models for industrial plant factory

Introduction

Indoor agriculture, especially plant factories, becomes essential because of the advantages of cultivating crops yearly to address global food shortages. Plant factories have been growing in scale as commercialized. Developing an on-site system that estimates the fresh weight of crops non-destructively for decision-making on harvest time is necessary to maximize yield and profits. However, a multi-layer growing environment with on-site workers is too confined and crowded to develop a high-performance system.This research developed a machine vision-based fresh weight estimation system to monitor crops from the transplant stage to harvest with less physical labor in an on-site industrial plant factory.

Methods

A linear motion guide with a camera rail moving in both the x-axis and y-axis directions was produced and mounted on a cultivating rack with a height under 35 cm to get consistent images of crops from the top view. Raspberry Pi4 controlled its operation to capture images automatically every hour. The fresh weight was manually measured eleven times for four months to use as the ground-truth weight of the models. The attained images were preprocessed and used to develop weight prediction models based on manual and automatic feature extraction.

Results and discussion

The performance of models was compared, and the best performance among them was the automatic feature extraction-based model using convolutional neural networks (CNN; ResNet18). The CNN-based model on automatic feature extraction from images performed much better than any other manual feature extraction-based models with 0.95 of the coefficients of determination (R2) and 8.06 g of root mean square error (RMSE). However, another multiplayer perceptron model (MLP_2) was more appropriate to be adopted on-site since it showed around nine times faster inference time than CNN with a little less R2 (0.93). Through this study, field workers in a confined indoor farming environment can measure the fresh weight of crops non-destructively and easily. In addition, it would help to decide when to harvest on the spot.

Unsupervised Machine Learning Reveals a Vulvodynia-Predominant Subtype in Bladder Pain Syndrome/Interstitial Cystitis

Background Bladder pain syndrome/interstitial cystitis (BPS/IC) is a chronic condition characterized by pelvic pain and urinary symptoms. Despite its significant impact on patients' quality of life, the heterogeneity of BPS/IC symptoms and the presence of comorbidities such as vulvodynia may not be adequately captured by validated questionnaires. Identifying vulvodynia in BPS/IC patients is crucial for providing appropriate treatment options. This study aimed to identify subtypes of BPS/IC patients using unsupervised machine learning and to investigate the prevalence of vulvodynia in each subtype. Methods We conducted a prospective cross-sectional study of 123 BPS/IC patients and 64 age-matched controls. Hierarchical clustering was performed using data from validated questionnaires, including the Numerical Rating Scale-11, Interstitial Cystitis Symptom Index (ICSI), Interstitial Cystitis Problem Index (ICPI), Pelvic Pain and Urgency/Frequency scores, Overactive Bladder Questionnaire Short Form (OABq SF), Overactive Bladder Symptom Score (OABSS), and Pelvic Floor Distress Inventory-20. The optimal number of clusters was determined using the elbow method, and the characteristics of each cluster were analyzed. All participants underwent a vulvodynia swab test to assess vulvodynia symptoms. Results Unsupervised machine learning revealed three distinct clusters of BPS/IC patients. Clusters 0 and 2 differed significantly, with Cluster 2 characterized by significantly higher vulvodynia scores compared to other clusters (P < 0.001). In contrast, Cluster 2 had lower bladder pain scores (ICSI and ICPI) and overactive bladder symptom scores (OABq SF and OABSS) compared to other clusters. Clusters 0 and 1 were characterized by a predominance of bladder pain and urinary frequency symptoms, with Cluster 0 exhibiting more severe symptoms. Conclusions Our study identified distinct subtypes of BPS/IC patients using unsupervised machine learning, with Cluster 2 representing a vulvodynia-predominant subtype. This finding, along with the potential of targeted therapies such as non-ablative erbium YAG laser for vulvodynia, underscores the importance of assessing extravesical symptoms, particularly vulvodynia, for the diagnosis and treatment of BPS/IC. A tailored approach, including laser therapy for vulvodynia-predominant patients, may be necessary for optimal management of BPS/IC. The vulvodynia swab test plays a crucial role in assessing vulvodynia symptoms, underlining the limitations of validated questionnaires in capturing the full spectrum of BPS/IC symptoms. A comprehensive evaluation of patients, including the vulvodynia swab test, is essential for accurate subtyping and management of BPS/IC. Further research with larger sample sizes and investigation of the relationship between identified subtypes and other clinical data is warranted to advance our understanding and management of BPS/IC.

GTE: a graph learning framework for prediction of T-cell receptors and epitopes binding specificity

The interaction between T-cell receptors (TCRs) and peptides (epitopes) presented by major histocompatibility complex molecules (MHC) is fundamental to the immune response. Accurate prediction of TCR-epitope interactions is crucial for advancing the understanding of various diseases and their prevention and treatment. Existing methods primarily rely on sequence-based approaches, overlooking the inherent topology structure of TCR-epitope interaction networks. In this study, we present $GTE$, a novel heterogeneous Graph neural network model based on inductive learning to capture the topological structure between TCRs and Epitopes. Furthermore, we address the challenge of constructing negative samples within the graph by proposing a dynamic edge update strategy, enhancing model learning with the nonbinding TCR-epitope pairs. Additionally, to overcome data imbalance, we adapt the Deep AUC Maximization strategy to the graph domain. Extensive experiments are conducted on four public datasets to demonstrate the superiority of exploring underlying topological structures in predicting TCR-epitope interactions, illustrating the benefits of delving into complex molecular networks. The implementation code and data are available at https://github.com/uta-smile/GTE.

Unbiasing Enhanced Sampling on a High-Dimensional Free Energy Surface with a Deep Generative Model

Biased enhanced sampling methods that utilize collective variables (CVs) are powerful tools for sampling conformational ensembles. Due to their large intrinsic dimensions, efficiently generating conformational ensembles for complex systems requires enhanced sampling on high-dimensional free energy surfaces. While temperature-accelerated molecular dynamics (TAMD) can trivially adopt many CVs in a simulation, unbiasing the simulation to generate unbiased conformational ensembles requires accurate modeling of a high-dimensional CV probability distribution, which is challenging for traditional density estimation techniques. Here we propose an unbiasing method based on the score-based diffusion model, a deep generative learning method that excels in density estimation across complex data landscapes. We demonstrate that this unbiasing approach, tested on multiple TAMD simulations, significantly outperforms traditional unbiasing methods and can generate accurate unbiased conformational ensembles. With the proposed approach, TAMD can adopt CVs that focus on improving sampling efficiency and the proposed unbiasing method enables accurate evaluation of ensemble averages of important chemical features.

Shelf-Life Management and Ripening Assessment of 'Hass' Avocado (Persea americana) Using Deep Learning Approaches

Avocado production is mostly confined to tropical and subtropical regions, leading to lengthy distribution channels that, coupled with their unpredictable post-harvest behavior, render avocados susceptible to significant loss and waste. To enhance the monitoring of 'Hass' avocado ripening, a data-driven tool was developed using a deep learning approach. This study involved monitoring 478 avocados stored in three distinct storage environments, using a 5-stage Ripening Index to classify each fruit's ripening phase based on their shared characteristics. These categories were paired with daily photographic records of the avocados, resulting in a database of labeled images. Two convolutional neural network models, AlexNet and ResNet-18, were trained using transfer learning techniques to identify distinct ripening indicators, enabling the prediction of ripening stages and shelf-life estimations for new unseen data. The approach achieved a final prediction accuracy of 88.8% for the ripening assessment, with 96.7% of predictions deviating by no more than half a stage from their actual classifications when considering the best side of the samples. The average shelf-life estimates based on the attributed classifications were within 0.92 days of the actual shelf-life, whereas the predictions made by the models had an average deviation of 0.96 days from the actual shelf-life.

Neuron-level explainable AI for Alzheimer's Disease assessment from fundus images

Alzheimer's Disease (AD) is a progressive neurodegenerative disease and the leading cause of dementia. Early diagnosis is critical for patients to benefit from potential intervention and treatment. The retina has emerged as a plausible diagnostic site for AD detection owing to its anatomical connection with the brain. However, existing AI models for this purpose have yet to provide a rational explanation behind their decisions and have not been able to infer the stage of the disease's progression. Along this direction, we propose a novel model-agnostic explainable-AI framework, called Granula ̲ r Neuron-le v ̲ el Expl a ̲ iner (LAVA), an interpretation prototype that probes into intermediate layers of the Convolutional Neural Network (CNN) models to directly assess the continuum of AD from the retinal imaging without the need for longitudinal or clinical evaluations. This innovative approach aims to validate retinal vasculature as a biomarker and diagnostic modality for evaluating Alzheimer's Disease. Leveraged UK Biobank cognitive tests and vascular morphological features demonstrate significant promise and effectiveness of LAVA in identifying AD stages across the progression continuum.

Spatiotemporal Patterns of Reptile and Amphibian Road Fatalities in a Natura 2000 Area: A 12-Year Monitoring of the Lake Karla Mediterranean Wetland

The pervasive expansion of human-engineered infrastructure, particularly roads, has fundamentally reshaped landscapes, profoundly affecting wildlife interactions. Wildlife-vehicle collisions, a common consequence of this intricate interplay, frequently result in fatalities, extending their detrimental impact within Protected Areas (PAs). Among the faunal groups most susceptible to road mortality, reptiles and amphibians stand at the forefront, highlighting the urgent need for global comprehensive mitigation strategies. In Greece, where road infrastructure expansion has encroached upon a significant portion of the nation's PAs, the plight of these road-vulnerable species demands immediate attention. To address this critical issue, we present a multifaceted and holistic approach to investigating and assessing the complex phenomenon of herpetofauna road mortality within the unique ecological context of the Lake Karla plain, a rehabilitated wetland complex within a PA. To unravel the intricacies of herpetofauna road mortality in the Lake Karla plain, we conducted a comprehensive 12-year investigation from 2008 to 2019. Employing a combination of statistical modeling and spatial analysis techniques, we aimed to identify the species most susceptible to these encounters, their temporal and seasonal variations, and the ecological determinants of their roadkill patterns. We documented a total of 340 roadkill incidents involving 14 herpetofauna species in the Lake Karla's plain, with reptiles, particularly snakes, being more susceptible, accounting for over 60% of roadkill occurrences. Moreover, we found that environmental and road-related factors play a crucial role in influencing roadkill incidents, while spatial analysis techniques, including Kernel Density Estimation, the Getis-Ord Gi*, and the Kernel Density Estimation plus methods revealed critical areas, particularly in the south-eastern region of Lake Karla's plain, offering guidance for targeted interventions to address both individual and collective risks associated with roadkill incidents.

High frequency oscillation network dynamics predict outcome in non-palliative epilepsy surgery

High frequency oscillations are a promising biomarker of outcome in intractable epilepsy. Prior high frequency oscillation work focused on counting high frequency oscillations on individual channels, and it is still unclear how to translate those results into clinical care. We show that high frequency oscillations arise as network discharges that have valuable properties as predictive biomarkers. Here, we develop a tool to predict patient outcome before surgical resection is performed, based on only prospective information. In addition to determining high frequency oscillation rate on every channel, we performed a correlational analysis to evaluate the functional connectivity of high frequency oscillations in 28 patients with intracranial electrodes. We found that high frequency oscillations were often not solitary events on a single channel, but part of a local network discharge. Eigenvector and outcloseness centrality were used to rank channel importance within the connectivity network, then used to compare patient outcome by comparison with the seizure onset zone or a proportion within the proposed resected channels (critical resection percentage). Combining the knowledge of each patient's seizure onset zone resection plan along with our computed high frequency oscillation network centralities and high frequency oscillation rate, we develop a Naïve Bayes model that predicts outcome (positive predictive value: 100%) better than predicting based upon fully resecting the seizure onset zone (positive predictive value: 71%). Surgical margins had a large effect on outcomes: non-palliative patients in whom most of the seizure onset zone was resected ('definitive surgery', ≥ 80% resected) had predictable outcomes, whereas palliative surgeries (<80% resected) were not predictable. These results suggest that the addition of network properties of high frequency oscillations is more accurate in predicting patient outcome than seizure onset zone alone in patients with most of the seizure onset zone removed and offer great promise for informing clinical decisions in surgery for refractory epilepsy.

Sustainable planning in Wuhan City during COVID-19: an analysis of influential factors, risk profiles, and clustered patterns

The outbreak of novel coronavirus pneumonia (COVID-19) is closely related to the intra-urban environment. It is important to understand the influence mechanism and risk characteristics of urban environment on infectious diseases from the perspective of urban environment composition. In this study, we used python to collect Sina Weibo help data as well as urban multivariate big data, and The random forest model was used to measure the contribution of each influential factor within to the COVID-19 outbreak. A comprehensive risk evaluation system from the perspective of urban environment was constructed, and the entropy weighting method was used to produce the weights of various types of risks, generate the specific values of the four types of risks, and obtain the four levels of comprehensive risk zones through the K-MEANS clustering of Wuhan's central urban area for zoning planning. Based on the results, we found: ①the five most significant indicators contributing to the risk of the Wuhan COVID-19 outbreak were Road Network Density, Shopping Mall Density, Public Transport Density, Educational Facility Density, Bank Density. Floor Area Ration, Poi Functional Mix ②After streamlining five indicators such as Proportion of Aged Population, Tertiary Hospital Density, Open Space Density, Night-time Light Intensity, Number of Beds Available in Designated Hospitals, the prediction accuracy of the random forest model was the highest. ③The spatial characteristics of the four categories of new crown epidemic risk, namely transmission risk, exposure risk, susceptibility risk and Risk of Scarcity of Medical Resources, were highly differentiated, and a four-level integrated risk zone was obtained by K-MEANS clustering. Its distribution pattern was in the form of "multicenter-periphery" gradient diffusion. For the risk composition of the four-level comprehensive zones combined with the internal characteristics of the urban environment in specific zones to develop differentiated control strategies. Targeted policies were then devised for each partition, offering a practical advantage over singular COVID-19 impact factor analyses. This methodology, beneficial for future public health crises, enables the swift identification of unique risk profiles in different partitions, streamlining the formulation of precise policies. The overarching goal is to maintain regular social development, harmonizing preventive measures and economic efforts.

Exposure hazards of particles and volatile organic compounds emitted from material extrusion 3D printing: Consolidation of chamber study data

Ultrafine particles and volatile organic compounds (VOCs) have been detected from material extrusion 3D printing, which is widely used in non-industrial environments. This study consolidates data of 447 particle emission and 58 VOC emission evaluations from a chamber study using a standardized testing method with various 3D printing scenarios. The interquartile ranges of the observed emission rates were 109-1011 #/h for particles and 0.2-1.0 mg/h for total VOC. Print material contributed largely to the variations of particle and total VOC emissions and determined the most abundantly emitted VOCs. Printing conditions and filament specifications, included printer brand, print temperature and speed, build plate heating setup, filament brand, color and composite, also affected emissions and resulted in large variations observed in emission profiles. Multiple regression showed that particle emissions were more impacted by various print conditions than VOC emissions. According to indoor exposure modeling, personal and residential exposure scenarios were more likely to result in high exposure levels, often exceeding recommended exposure limits. Hazardous VOCs commonly emitted from 3D printing included aromatics, aldehydes, alcohols, ketones, esters and siloxanes, among which were various carcinogens, irritants and developmental and reproductive toxins. Therefore, 3D printing emits a complex mixture of ultrafine particles and various hazardous chemicals, exposure to which may exceed recommended exposure limits and potentially induce acute, chronic, or developmental health effects for users depending on exposure scenarios.

Urban resilience in China's eight urban agglomerations: evolution trends and driving factors

Improving urban resilience (UR) and enhancing urban anti-risk ability are important foundations for promoting the high-quality development of new urbanization. This research employs the time-varying entropy method to evaluate the resilience level of 138 cities within China's eight urban agglomerations (UAs) between 2005 and 2019. Additionally, the Dagum Gini coefficient and the kernel density estimation method are utilized to examine the spatial disparities and distribution dynamics of UR across the eight UAs. The results of this investigation indicate that (1) the collective UR performance of the eight UAs has experienced an upward trend. However, a notable spatial disparity exits, which is primarily attributed to the differences among the UAs. (2) The overall UR development of the eight UAs has a certain gradient effect, and the UR within each UA has different degrees of polarization characteristics. (3) For the eight UAs as a whole, per capita savings deposits, capitalization of foreign capital, and per capita fiscal expenditure are the three most important driving factors. Within each UA, there was heterogeneity in the main influencing factors. The interplay between any two factors amplifies their individual driving effects on the spatial differentiation of UR.

MMPatho: Leveraging Multilevel Consensus and Evolutionary Information for Enhanced Missense Mutation Pathogenic Prediction

Understanding the pathogenicity of missense mutation (MM) is essential for shed light on genetic diseases, gene functions, and individual variations. In this study, we propose a novel computational approach, called MMPatho, for enhancing missense mutation pathogenic prediction. First, we established a large-scale nonredundant MM benchmark data set based on the entire Ensembl database, complemented by a focused blind test set specifically for pathogenic GOF/LOF MM. Based on this data set, for each mutation, we utilized Ensembl VEP v104 and dbNSFP v4.1a to extract variant-level, amino acid-level, individuals' outputs, and genome-level features. Additionally, protein sequences were generated using ENSP identifiers with the Ensembl API, and then encoded. The mutant sites' ESM-1b and ProtTrans-T5 embeddings were subsequently extracted. Then, our model group (MMPatho) was developed by leveraging upon these efforts, which comprised ConsMM and EvoIndMM. To be specific, ConsMM employs individuals' outputs and XGBoost with SHAP explanation analysis, while EvoIndMM investigates the potential enhancement of predictive capability by incorporating evolutionary information from ESM-1b and ProtT5-XL-U50, large protein language embeddings. Through rigorous comparative experiments, both ConsMM and EvoIndMM were capable of achieving remarkable AUROC (0.9836 and 0.9854) and AUPR (0.9852 and 0.9902) values on the blind test set devoid of overlapping variations and proteins from the training data, thus highlighting the superiority of our computational approach in the prediction of MM pathogenicity. Our Web server, available at http://csbio.njust.edu.cn/bioinf/mmpatho/, allows researchers to predict the pathogenicity (alongside the reliability index score) of MMs using the ConsMM and EvoIndMM models and provides extensive annotations for user input. Additionally, the newly constructed benchmark data set and blind test set can be accessed via the data page of our web server.

The Relationship Between Soil-Transmitted Helminth Infections and Environmental Factors in Puerto Iguazú, Argentina: Cross-Sectional Study

BACKGROUND

Soil-transmitted helminths (STHs) are widely distributed throughout the world. Various factors, including the environment, socioeconomic characteristics, and access to water and sanitation, play an important role in the spread and persistence of these parasites within communities. They, in turn, affect the growth and development of members of the community, especially children. Studies in the northern provinces of Argentina have shown variable prevalence of STHs, but the factors associated with their presence have not been completely elucidated.

OBJECTIVE

This cross-sectional study aimed to identify the socioeconomic and environmental factors related to STH infection in indigenous villages located in Puerto Iguazú (Misiones), Argentina.

METHODS

Between 2018 and 2019, stool samples were collected from individuals ≥1 year residing in 3 villages: Mini-Marangatú, Yriapú, and Fortín Mbororé. Standard parasitological methods were used to determine STH prevalence. Standardized questionnaires were used to assess participants' habits, customs, and household characteristics, and environmental data were obtained through satellite imagery. Multilinear regression with Akaike information criterion stepwise variables was used to explore relevant associations.

RESULTS

A total of 342 individuals from the 3 villages participated in this study. The prevalence of STHs varied across villages: 89.6% (43/48), in Mini-Marangatú, 80.8% (101/125) in Yriapú, and 68.5% (115/169) in Fortín Mbororé. Notably, there was a significant difference in hookworm infection among the villages (P=.02). The analysis highlighted the significant influence of specific environmental factors on STH presence and spatial distribution, particularly in relation to hookworm infection. Vegetation patterns represented by the Vegetation Heterogeneity Index, created ad hoc for this study, emerged as a critical factor, with 2 significant predictors related to it (P=.002 and P=.004) alongside impervious surface density with a significant predictor (P<.001). The multilinear regression model yielded a high F test score (F108=4.75, P<.001), indicating a strong fit (R2=0.5465). Furthermore, socioeconomic factors, including walking barefoot in houses with dirt floors and overcrowding, were significantly correlated with hookworm infection intensity (P<.001 and P=.001, respectively). We also used the multilinear regression model to calculate hookworm infection intensity (F110=21.15, P<.001; R2=0.4971).

CONCLUSIONS

Our study underscores the complexity of STH transmission, as villages with similar living conditions and environmental characteristics displayed varied STH prevalence and spatial distribution. Specific environmental factors, such as vegetation pattern and impervious surface density, played major roles in STH presence, demonstrating the crucial relationship between environmental factors and hookworm infection distribution. Moreover, our findings emphasize the significant influence of socioeconomic factors on hookworm infection intensity. By gaining insights into this complex interplay, our research contributes to a better understanding of STH transmission characteristics, thereby informing targeted public health interventions for effective control.

PRISMA: A novel approach for deriving probabilistic surrogate safety measures for risk evaluation

Surrogate Safety Measures (SSMs) are used to express road safety in terms of the safety risk in traffic conflicts. Typically, SSMs rely on assumptions regarding the future evolution of traffic participant trajectories to generate a measure of risk, restricting their applicability to scenarios where these assumptions are valid. In response to this limitation, we present the novel Probabilistic RISk Measure derivAtion (PRISMA) method. The objective of the PRISMA method is to derive SSMs that can be used to calculate in real time the probability of a specific event (e.g., a crash). The PRISMA method adopts a data-driven approach to predict the possible future traffic participant trajectories, thereby reducing the reliance on specific assumptions regarding these trajectories. Since the PRISMA is not bound to specific assumptions, the PRISMA method offers the ability to derive multiple SSMs for various scenarios. The occurrence probability of the specified event is based on simulations and combined with a regression model, this enables our derived SSMs to make real-time risk estimations. To illustrate the PRISMA method, an SSM is derived for risk evaluation during longitudinal traffic interactions. Since there is no known method to objectively estimate risk from first principles, i.e., there is no known risk ground truth, it is very difficult, if not impossible, to objectively compare the relative merits of two SSMs. Instead, we provide a method for benchmarking our derived SSM with respect to expected risk trends. The application of the benchmarking illustrates that the SSM matches the expected risk trends. Whereas the derived SSM shows the potential of the PRISMA method, future work involves applying the approach for other types of traffic conflicts, such as lateral traffic conflicts or interactions with vulnerable road users.

Roles of multi-level temperature-adaptive responses and microhabitat variation in establishing distributions of intertidal species

How intertidal species survive their harsh environment and how best to evaluate and forecast range shifts in species distribution are two important and closely related questions for intertidal ecologists and global change biologists. Adaptive variation in responses of organisms to environmental change across all levels of biological organization - from behavior to molecular systems - is of key importance in setting distribution patterns, yet studies often neglect the interactions of diverse types of biological variation (e.g. differences in thermal optima owing to genetic and acclimation-induced effects) with environmental variation, notably at the scale of microhabitats. Intertidal species have to cope with extreme and frequently changing thermal stress, and have shown high variation in thermal sensitivities and adaptive responses at different levels of biological organization. Here, I review the physiological and biochemical adaptations of intertidal species to environmental temperature on multiple spatial and temporal scales. With fine-scale datasets for the thermal limits of individuals and for environmental temperature variation at the microhabitat scale, we can map the thermal sensitivity for each individual in different microhabitats, and then scale up the thermal sensitivity analysis to the population level and, finally, to the species level by incorporating physiological traits into species distribution models. These more refined mechanistic models that include consideration of physiological variations have higher predictive power than models that neglect these variations, and they will be crucial to answering the questions posed above concerning adaptive mechanisms and the roles they play in governing distribution patterns in a rapidly changing world.

Evaluation of species thermal sensitivity with individual-based physiological performance

Ignoring intraspecific variations can prevent us from accurately assessing species' thermal sensitivity to global warming. Individual-based physiological performance provides a feasible solution to depict species' thermal sensitivity using a bottom-up approach. We measured the cardiac performance of intertidal bivalves (1159 individuals from multiple populations of six bivalves), determined the upper thermal limit of each individual, calculated the proportions of individuals suffering sublethal/lethal heat stress, and mapped sensitive regions to high temperatures. Results showed that high inter-individual variations of physiological performance existed in levels of populations and species, and species' thermal sensitivity was positively related to the intraspecific variations of heat tolerance. This bottom-up approach scaled up from individual, population to species emphasizes the importance of individual-based physiology performance in assessing thermal sensitivity across different hierarchical levels and enables better evaluating and forecasting of species responses to global warming.

Spatially-targeted tuberculosis screening has limited impact beyond household contact tracing in Lima, Peru: A model-based analysis

Mathematical models have suggested that spatially-targeted screening interventions for tuberculosis may efficiently accelerate disease control, but empirical data supporting these findings are limited. Previous models demonstrating substantial impacts of these interventions have typically simulated large-scale screening efforts and have not attempted to capture the spatial distribution of tuberculosis in households and communities at a high resolution. Here, we calibrate an individual-based model to the locations of case notifications in one district of Lima, Peru. We estimate the incremental efficiency and impact of a spatially-targeted interventions used in combination with household contact tracing (HHCT). Our analysis reveals that HHCT is relatively efficient with a median of 40 (Interquartile Range: 31.7 to 49.9) household contacts required to be screened to detect a single case of active tuberculosis. However, HHCT has limited population impact, producing a median incidence reduction of only 3.7% (Interquartile Range: 5.8% to 1.9%) over 5 years. In comparison, spatially targeted screening (which we modeled as active case finding within high tuberculosis prevalence areas 100 m2 grid cell) is far less efficient, requiring evaluation of ≈12 times the number of individuals as HHCT to find a single individual with active tuberculosis. Furthermore, the addition of the spatially targeted screening effort produced only modest additional reductions in tuberculosis incidence over the 5 year period (≈1.3%) in tuberculosis incidence. In summary, we found that HHCT is an efficient approach for tuberculosis case finding, but has limited population impact. Other screening approaches which target areas of high tuberculosis prevalence are less efficient, and may have limited impact unless very large numbers of individuals can be screened.

Systematic noise removal from analytical ultracentrifugation data with UltraScan

A method for removing time- and radially invariant noise from sedimentation velocity and sedimentation equilibrium experiments performed in an analytical ultracentrifuge is presented. The method averages repeat radial incident light measurements as a function of the photomultiplier response at different wavelengths to remove the majority of the time-invariant noise contributions from intensity data measurements. The results of this method are compared to traditional absorbance data generated with a buffer reference and the Beckman Optima AUC data acquisition program, and with the standard UltraScan refinement workflow. The method avoids the amplification of stochastic noise inherent in the absorbance scan subtraction traditionally employed in sedimentation velocity and equilibrium data. In addition, the collection of intensity data frees up the reference channel for additional samples, doubling the capacity of the instrument. In comparison to absorbance data, the residual mean square deviation of a fitted sedimentation velocity experiment without additional noise correction by UltraScan was improved by a factor of 4.5 when using the new method. This improvement benefits sedimentation equilibrium experiments as well as analytical buoyant density equilibrium experiments where routine time-invariant noise correction calculations cannot be performed.

Performance analysis of indicators of chaos for nonlinear dynamical systems

The efficient detection of chaotic behavior in orbits of a complex dynamical system is an active domain of research. Several indicators have been proposed, and new ones have recently been developed in view of improving the performance of chaos detection by means of numerical simulations. The challenge is to predict chaotic behavior based on the analysis of orbits of limited length. In this paper the performance analysis of past and recent indicators of chaos, in terms of predictive power, is carried out in detail using the dynamical system characterized by a symplectic Hénon-like cubic polynomial map.

Efficient Calibration of Groundwater Contaminant Transport Models Using Bayesian Optimization

Numerical modeling is a significant tool to understand the dynamic characteristics of contaminants transport in groundwater. The automatic calibration of highly parametrized and computationally intensive numerical models for the simulation of contaminant transport in the groundwater flow system is a challenging task. While existing methods use general optimization techniques to achieve automatic calibration, the large numbers of numerical model evaluations required in the calibration process lead to high computing overhead and limit the efficiency of model calibration. This paper presents a Bayesian optimization (BO) method for efficient calibration of numerical models of groundwater contaminant transport. A Bayes model is built to fully represent calibration criteria and derive the objective function for model calibration. The efficiency of model calibration is made possible by the probabilistic surrogate model and the expected improvement acquisition function in BO. The probabilistic surrogate model approximates the computationally expensive objective function with a closed-form expression that can be computed efficiently, while the expected improvement acquisition function proposes the most promising model parameters to improve the fitness to the calibration criteria and reduce the uncertainty of the surrogate model. These schemes allow us to find the optimized model parameters effectively by using a small number of numerical model evaluations. Two case studies for the calibration of the Cr(VI) transport model demonstrate that the BO method is effective and efficient in the inversion of hypothetical model parameters, the minimization of the objective function, and the adaptation of different model calibration criteria. Specifically, this promising performance is achieved within 200 numerical model evaluations, which substantially reduces the computing budget for model calibration.

Capturing the Complex Relationship Between Internal and External Training Load: A Data-Driven Approach

BACKGROUND

Training load is typically described in terms of internal and external load. Investigating the coupling of internal and external training load is relevant to many sports. Here, continuous kernel-density estimation (KDE) may be a valuable tool to capture and visualize this coupling.

AIM

Using training load data in speed skating, we evaluated how well bivariate KDE plots describe the coupling of internal and external load and differentiate between specific training sessions, compared to training impulse scores or intensity distribution into training zones.

METHODS

On-ice training sessions of 18 young (sub)elite speed skaters were monitored for velocity and heart rate during 2 consecutive seasons. Training session types were obtained from the coach's training scheme, including endurance, interval, tempo, and sprint sessions. Differences in training load between session types were assessed using Kruskal-Wallis or Kolmogorov-Smirnov tests for training impulse and KDE scores, respectively.

RESULTS

Training impulse scores were not different between training session types, except for extensive endurance sessions. However, all training session types differed when comparing KDEs for heart rate and velocity (both P < .001). In addition, 2D KDE plots of heart rate and velocity provide detailed insights into the (subtle differences in) coupling of internal and external training load that could not be obtained by 2D plots using training zones.

CONCLUSION

2D KDE plots provide a valuable tool to visualize and inform coaches on the (subtle differences in) coupling of internal and external training load for training sessions. This will help coaches design better training schemes aiming at desired training adaptations.

Fast and precise inference on diffusivity in interacting particle systems

Particle systems made up of interacting agents is a popular model used in a vast array of applications, not the least in biology where the agents can represent everything from single cells to animals in a herd. Usually, the particles are assumed to undergo some type of random movements, and a popular way to model this is by using Brownian motion. The magnitude of random motion is often quantified using mean squared displacement, which provides a simple estimate of the diffusion coefficient. However, this method often fails when data is sparse or interactions between agents frequent. In order to address this, we derive a conjugate relationship in the diffusion term for large interacting particle systems undergoing isotropic diffusion, giving us an efficient inference method. The method accurately accounts for emerging effects such as anomalous diffusion stemming from mechanical interactions. We apply our method to an agent-based model with a large number of interacting particles, and the results are contrasted with a naive mean square displacement-based approach. We find a significant improvement in performance when using the higher-order method over the naive approach. This method can be applied to any system where agents undergo Brownian motion and will lead to improved estimates of diffusion coefficients compared to existing methods.

Dynamic evaluation of low-carbon development in China's power industry and the impact of carbon market policies

At the 75th session of the United Nations General Assembly, China clearly put forward the goals of "carbon peak" in 2030 and "carbon neutrality" in 2060. Achievement of carbon targets. Therefore, the goal of this paper is to analyze the low-carbon development level of China's power industry and study the impact of carbon market policies on the low-carbon development level of the power industry. Based on this, this paper first constructs the low-carbon development evaluation index system of the power industry around the connotation of low-carbon development in the power industry and uses the global principal component analysis model to measure the low-carbon development level of China's power industry. Then, the dynamic change trend and spatial distribution characteristics of the low-carbon development level of China's power industry are analyzed using kernel density estimation and the K-means clustering method. Finally, propensity score matching and difference-in-difference methods are used to analyze the impact of carbon market policies on the low-carbon development level of China's power industry. The results show that, first, the low-carbon development level of China's power industry generally shows an upward trend and a polarized development trend. Second, the low-carbon development level of China's power industry has regional effects and gradient effects. The low-carbon development level of the power industry from high to low is the eastern region, central region and western region. Third, carbon market policies can help improve the low-carbon development level of China's power industry. The research results provide some reference and guidance for the evaluation of the low-carbon development level of China's power industry and the improvement of carbon market policies.

Environmental Adaptation in the Process of Human-Land Relationship in Southeast China's Ethnic Minority Areas and Its Significance on Sustainable Development

The relationship between regional human development and geographic environment is the basis for dynamic social change, and studying the evolution of human-land relations in typical regions can provide background knowledge for global change studies. This study is based on GIS and spatio-temporal statistical techniques, combined with the analysis of toponymic cultural landscapes, to study ethnic minority regions of southeastern China. The results show that: (1) The geographical environment of the region will affect the naming of villages, and the orientation and family name are the most common; the frequency of plants, pit (keng), animals, and flat (ping) is also very high. (2) Han settlements and She settlements have obvious spatial differentiation, and in general the Han distribution area is lower than that of the She. Han settlements are mainly distributed in plain areas along rivers with elevations less than 200 m; She settlements are mainly distributed in hilly areas (200~500 m) and low mountain areas (500~800 m). (3) The results of quadrat analysis and nearest neighbor index analysis show that both Han and She settlements are clustered in the spatial distribution pattern, and the distribution of She settlements is more clustered than that of Han, with more dense settlements at a certain spatial scale. The regional cultural landscape is the result of the development and evolution of human-land relationship, and the comprehensive analysis of cultural landscape can understand the process of human-land relationship in a small region. The settlements in the region are indicative of the geographic environment in terms of village naming, spatial pattern, elevation differentiation and relationship with rivers, which can reflect the environmental adaptation process of human activities.

A novel temporal generative adversarial network for electrocardiography anomaly detection

Cardiac abnormality detection from Electrocardiogram (ECG) signals is a common task for cardiologists. To facilitate efficient and objective detection, automated ECG classification by using deep learning based methods have been developed in recent years. Despite their impressive performance, these methods perform poorly when presented with cardiac abnormalities that are not well represented, or absent, in the training data. To this end, we propose a novel one-class classification based ECG anomaly detection generative adversarial network (GAN). Specifically, we embedded a Bi-directional Long-Short Term Memory (Bi-LSTM) layer into a GAN architecture and used a mini-batch discrimination training strategy in the discriminator to synthesis ECG signals. Our method generates samples to match the data distribution from normal signals of healthy group so that a generalised anomaly detector can be built reliably. The experimental results demonstrate our method outperforms several state-of-the-art semi-supervised learning based ECG anomaly detection algorithms and robustly detects the unknown anomaly class in the MIT-BIH arrhythmia database. Experiments show that our method achieves the accuracy of 95.5% and AUC of 95.9% which outperforms the most competitive baseline by 0.7% and 1.7% respectively. Our method may prove to be a helpful diagnostic method for helping cardiologists identify arrhythmias.

Learning pair potentials using differentiable simulations

Learning pair interactions from experimental or simulation data is of great interest for molecular simulations. We propose a general stochastic method for learning pair interactions from data using differentiable simulations (DiffSim). DiffSim defines a loss function based on structural observables, such as the radial distribution function, through molecular dynamics (MD) simulations. The interaction potentials are then learned directly by stochastic gradient descent, using backpropagation to calculate the gradient of the structural loss metric with respect to the interaction potential through the MD simulation. This gradient-based method is flexible and can be configured to simulate and optimize multiple systems simultaneously. For example, it is possible to simultaneously learn potentials for different temperatures or for different compositions. We demonstrate the approach by recovering simple pair potentials, such as Lennard-Jones systems, from radial distribution functions. We find that DiffSim can be used to probe a wider functional space of pair potentials compared with traditional methods like iterative Boltzmann inversion. We show that our methods can be used to simultaneously fit potentials for simulations at different compositions and temperatures to improve the transferability of the learned potentials.

Accounting for space, time, and behavior using GPS derived dynamic measures of environmental exposure

Time-weighted spatial averaging approaches (TWSA) are an increasingly utilized method for calculating exposure using global positioning system (GPS) mobility data for health-related research. They can provide a time-weighted measure of exposure, or dose, to various environments or health hazards. However, little work has been done to compare existing methodologies, nor to assess how sensitive these methods are to mobility data inputs (e.g., walking vs driving), the type of environmental data being assessed as the exposure (e.g., continuous surfaces vs points of interest), and underlying point-pattern clustering of participants (e.g., if a person is highly mobile vs predominantly stationary). Here we contrast three TWSA approaches that have been previously used or recently introduced in the literature: Kernel Density Estimation (KDE), Density Ranking (DR), and Point Overlay (PO). We feed GPS and accelerometer data from 602 participants through each method to derive time-weighted activity spaces, comparing four mobility behaviors: all movement, stationary time, walking time, and in-vehicle time. We then calculate exposure values derived from the various TWSA activity spaces with four environmental layer data types (point, line, area, surface). Similarities and differences across TWSA derived exposures for the sample and between individuals are explored, and we discuss interpretation of TWSA outputs providing recommendations for researchers seeking to apply these methods to health-related studies.

Replacing Histogram with Smooth Empirical Probability Density Function Estimated by K-Moments

Whilst several methods exist to provide sample estimates of the probability distribution function at several points, for the probability density of continuous stochastic variables, only a gross representation through the histogram is typically used. It is shown that the newly introduced concept of knowable moments (K-moments) can provide smooth empirical representations of the distribution function, which in turn can yield point and interval estimates of the density function at a large number of points or even at any arbitrary point within the range of the available observations. The proposed framework is simple to apply and is illustrated with several applications for a variety of distribution functions.

Robust Synchronization of Ambient Vibration Time Histories Based on Phase Angle Compensations and Kernel Density Function

The output-only modal analysis is ubiquitously used for structural health monitoring of civil engineering systems. The measurements for such applications require the use of multiple data acquisition systems (DAS) to avoid complicated meshes of cables in high-rise buildings, avoid traffic constriction on a bridge during measurements, or to avoid having limited channels in a single DAS. Nevertheless, such requirements introduce time synchronization problems which potentially lead to erroneous structural dynamic characterization and hence misleading or inconclusive structural health monitoring results. This research aims at proposing a system-identification-based time synchronization algorithm for output-only modal analysis using multiple DAS. A new procedure based on the compensation of the phase angle shifts is proposed to identify and address the time synchronization issue in ambient vibration data measured through multiple DAS. To increase the robustness of the proposed algorithm to the inherent inconsistencies in these datasets, the kernel density function is applied to rank multiple time-shift estimates that are sometimes detected by the algorithm when inaccuracies exist in the data arising from low signal-to-noise ratio and/or presence of colored noise in the ambient excitations. First, the synchronized ambient vibration dataset of a full-scale bridge is artificially de-synchronized and used to present a proof of concept for the proposed algorithm. Next, the algorithm is applied to ambient vibration data of a 30-story, reinforced concrete building, where the synchronization of the data could not be achieved using two DAS despite best efforts. The application of the proposed time synchronization algorithm is shown to both detect and correct the time synchronization discrepancies in the output-only modal analysis.

Smartphone Sensor-Based Human Motion Characterization with Neural Stochastic Differential Equations and Transformer Model

With many conveniences afforded by advances in smartphone technology, developing advanced data analysis methods for health-related information from smartphone users has become a fast-growing research topic in the healthcare field. Along these lines, this paper addresses smartphone sensor-based characterization of human motions with neural stochastic differential equations (NSDEs) and a Transformer model. NSDEs and modeling via Transformer networks are two of the most prominent deep learning-based modeling approaches, with significant performance yields in many applications. For the problem of modeling dynamical features, stochastic differential equations and deep neural networks are frequently used paradigms in science and engineering, respectively. Combining these two paradigms in one unified framework has drawn significant interest in the deep learning community, and NSDEs are among the leading technologies for combining these efforts. The use of attention has also become a widely adopted strategy in many deep learning applications, and a Transformer is a deep learning model that uses the mechanism of self-attention. This concept of a self-attention based Transformer was originally introduced for tasks of natural language processing (NLP), and due to its excellent performance and versatility, the scope of its applications is rapidly expanding. By utilizing the techniques of neural stochastic differential equations and a Transformer model along with data obtained from smartphone sensors, we present a deep learning method capable of efficiently characterizing human motions. For characterizing human motions, we encode the high-dimensional sequential data from smartphone sensors into latent variables in a low-dimensional latent space. The concept of the latent variable is particularly useful because it can not only carry condensed information concerning motion data, but also learn their low-dimensional representations. More precisely, we use neural stochastic differential equations for modeling transitions of human motion in a latent space, and rely on a Generative Pre-trained Transformer 2 (GPT2)-based Transformer model for approximating the intractable posterior of conditional latent variables. Our experiments show that the proposed method can yield promising results for the problem of characterizing human motion patterns and some related tasks including user identification.

Monte Carlo Simulation of Stochastic Differential Equation to Study Information Geometry

Information Geometry is a useful tool to study and compare the solutions of a Stochastic Differential Equations (SDEs) for non-equilibrium systems. As an alternative method to solving the Fokker-Planck equation, we propose a new method to calculate time-dependent probability density functions (PDFs) and to study Information Geometry using Monte Carlo (MC) simulation of SDEs. Specifically, we develop a new MC SDE method to overcome the challenges in calculating a time-dependent PDF and information geometric diagnostics and to speed up simulations by utilizing GPU computing. Using MC SDE simulations, we reproduce Information Geometric scaling relations found from the Fokker-Planck method for the case of a stochastic process with linear and cubic damping terms. We showcase the advantage of MC SDE simulation over FPE solvers by calculating unequal time joint PDFs. For the linear process with a linear damping force, joint PDF is found to be a Gaussian. In contrast, for the cubic process with a cubic damping force, joint PDF exhibits a bimodal structure, even in a stationary state. This suggests a finite memory time induced by a nonlinear force. Furthermore, several power-law scalings in the characteristics of bimodal PDFs are identified and investigated.

Spatiotemporal characteristics and influencing factors of carbon emissions from civil buildings: Evidence from urban China

Carbon emissions from civil buildings refer to the carbon emissions generated during the operation of civil buildings. With the continuous development of the urban economy and the improvement of people’s living standards, this part of carbon emission puts tremendous pressure on China to achieve the goal of carbon peaking and carbon neutral. In the context of rapid urbanization, studying the spatiotemporal characteristics and influencing factors of the carbon emissions from civil buildings have strong practical significance for China to achieve the "dual carbon" goal. Based on the emission data from 104 prefecture-level cities in China, we examine the spatiotemporal characteristics of the civil building carbon emissions from the perspectives of temporal evolution trend, spatial distribution and its dynamic evolution, spatial difference and its decomposition, and spatial autocorrelation characteristics. Finally, we reveal the influencing factors of the carbon emissions from civil buildings using static panel data models and spatial dynamic panel data models. The results of the study show that: (1) During the sample period, the carbon emissions from civil buildings have increased year by year. The civil building carbon emissions have become an important source of China’s overall carbon emissions. Realizing energy saving and emission reduction in the operational stage of civil buildings is crucial to realizing China’s "dual carbon" goal. (2) According to the estimated results, there is a significant inverted U-shaped non-linear relationship between urbanization and civil building carbon emissions. Most Chinese cities are located in the upward part of the inverted U-shaped curve at present. Thus, the traditional economic growth model characterized by high energy consumption and high emission during rapid urbanization should be abandoned to reduce the carbon emissions from civil buildings. (3) Technological progress and fixed asset investment can effectively reduce the carbon emissions from civil buildings. At the same time, the level of marketization and social consumption expenditure positively affect the carbon emissions from civil buildings. It is necessary to improve the relevant market mechanisms, policy subsidies, and other means to encourage the application of green energy-saving technologies in civil buildings. Also, it is needed to guide the urban residents’ consumption structure and lifestyle in a low-carbon direction, to reduce the energy consumption and carbon emissions during the operation of civil buildings.

Homicide rates are spatially associated with built environment and socio-economic factors: a study in the neighbourhoods of Toronto, Canada

Objectives

Homicide rate is associated with a large variety of factors and therefore unevenly distributed over time and space. This study aims to explore homicide patterns and their spatial associations with different socioeconomic and built-environment conditions in 140 neighbourhoods of the city of Toronto, Canada.

Methods

A homicide dataset covering the years 2012 to 2021 and neighbourhood-based indicators were analysed using spatial techniques such as Kernel Density Estimation, Global/Local Moran’s I and Kulldorff’s SatScan spatio-temporal methodology. Geographically weighted regression (GWR) and multi-scale GWR (MGWR) were used to analyse the spatially varying correlations between the homicide rate and independent variables. The latter was particularly suitable for manifested spatial variations between explanatory variables and the homicide rate and it also identified spatial non-stationarities in this connection.

Results

The adjusted R² of the MGWR was 0.53, representing a 4.35 and 3.74% increase from that in the linear regression and GWR models, respectively. Spatial and spatio-temporal high-risk areas were found to be significantly clustered in downtown and the north-western parts of the city. Some variables (e.g., the population density, material deprivation, the density of commercial establishments and the density of large buildings) were significantly associated with the homicide rate in different spatial ways.

Conclusion

The findings of this study showed that homicide rates were clustered over time and space in certain areas of the city. Socioeconomic and the built environment characteristics of some neighbourhoods were found to be associated with high homicide rates but these factors were different for each neighbourhood.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12889-022-13807-4.

Trends of overweight and obesity among preschool children from 2013 to 2018: a cross-sectional study in Rhine-Neckar County and the City of Heidelberg, Germany

BACKGROUND

Early childhood overweight and obesity is a growing public health concern worldwide. Few recent studies have addressed how time trends varied by sociodemographic characteristics at the regional level using large and high-quality data. This study determines how time trends vary in the prevalence of early childhood overweight and obesity by age, gender, and migration background at the regional level.

METHODS

We used a Kernel-density curve to describe the BMI distribution, and evaluated the trends of overweight and obesity by age, gender, and migration background using logistic regression.

RESULTS

Mean BMI and the overall prevalence of overweight and obesity increased among preschool children aged 4-6 years in the Rhine-Neckar County and the City of Heidelberg. After adjusting for age, sex, and migration background, trends of overweight significantly increased only among male children in the age 5 year group with migration background (P < 0.05), and an upward trend of obesity was observed only among male children in the age 5 year group and female children in the age 6 year group with migration background (P < 0.05).

CONCLUSIONS

BMI distribution as well as general prevalence of overweight and obesity are still increasing among preschool children. Children with migration backgrounds, particularly male children in the age 5 year groups and female children in the age 6 year group should be prioritized. Health promotion strategies for children with migration backgrounds will help address this challenge.

Error Reduction in Vision-Based Multirotor Landing System

New applications are continuously appearing with drones as protagonists, but all of them share an essential critical maneuver—landing. New application requirements have led the study of novel landing strategies, in which vision systems have played and continue to play a key role. Generally, the new applications use the control and navigation systems embedded in the aircraft. However, the internal dynamics of these systems, initially focused on other tasks such as the smoothing trajectories between different waypoints, can trigger undesired behaviors. In this paper, we propose a landing system based on monocular vision and navigation information to estimate the helipad global position. In addition, the global estimation system includes a position error correction module by cylinder space transformation and a filtering system with a sliding window. To conclude, the landing system is evaluated with three quality metrics, showing how the proposed correction system together with stationary filtering improves the raw landing system.

Assessing the Uncertainties of Simulation Approaches for Solar Thermal Systems Coupled to Industrial Processes

Industrial energy accounts for a large percentage of global consumption and, thus, it is a target for decarbonization by renewable and in particular solar energy adoption. Low uncertainty simulation tools can reduce the financial risk of solar projects, fostering the transition to a sustainable energy system. Several simulation tools are readily available to developers; differences exist in the format of input data and complexity of physical and numerical models. These tools can provide a variety of results from technical to financial and sensitivity analysis, often producing significant differences in yield assessment and uncertainty levels. IEA SHC Task 64/SolarPACES Task IV—Subtask C aims to address the lack of standard simulation tools for Solar Heating of Industrial Processes (SHIP) plants. This article describes the collaborative work developed by the researchers participating in the task. The identification and classification of several currently available simulation tools are performed on the basis of their capabilities and simulation approaches. A case study of solar heat supply to a copper mining operation is defined, allowing a comparison of the results produced by equivalent simulation tools. The proposed methodology identifies the main sources of differences among the simulation tools, the assessment of the deviation considering a series of statistical metrics for different time scales, and identifies their limitations and bias. The effects of physical characteristics of SHIP plants and different simulation approaches are discussed and quantified. The obtained results allow us to develop a basic guideline for a standardized yield assessment procedure with known uncertainties. Creating this common framework could partially reduce the risk perceived by the finance industry regarding SHIP systems.

Spatio-Temporal Evolution and Future Simulation of Agricultural Land Use in Xiangxi, Central China

Researches on agricultural land use would help the stakeholders to make better decisions about agricultural resources. However, studies on agricultural land have been lacking. In this context, Xiangxi was chosen as a typical region, and five indicators (Kernel Density, change importance, etc.) and two models (gray forecasting model and GeoSoS-FLUS) were used, to explore the spatio-temporal evolution trends and simulate the future scenarios of agricultural land use. The results were as follows: (1) Xiangxi was dominated by agricultural land, and nearly 50% of total extent was forestry land. Extent of agricultural land decreased by about 56.89 km2 or 3.74% from 2000 to 2018; (2) The density of each agricultural land in the study area had considerable spatial heterogeneity, and showed a main trend of shrinkage, especially in the south regions; (3) In 2030, the spatial pattern and composition of agricultural land in Xiangxi will maintain the existing status, while both of the area and proportion of agricultural land will decline, with a loss of 241.34 km2 or 2.85% decrease from 2000. Nevertheless, the study believed that the slight shrinkage of the agricultural land in Xiangxi is in line with the objective law. At the same time, the study suggested to strengthen the scientific management and rational utilization of agricultural land, with emphasis on arable land and fishery land in the south, especially the administrative center.

Comparison of UAV and fixed-wing aerial application for alfalfa insect pest control: evaluating efficacy, residues, and spray quality

BACKGROUND

Integrating unmanned aerial vehicles (UAV) as a new method of pesticide application into existing commercial crop protection systems requires extensive research and comparison to conventional, proven application technology. Pest control expressed as efficacy against target pests, and spray quality expressed as coverage and chemical residue are three key criteria. We investigated and compared these quantitative parameters between a multi-rotor UAV and conventional piloted airplanes in two commercial alfalfa production systems.

RESULTS

Effective and equivalent control of leaf-feeding insect pests was achieved by both methods of aerial application when delivering chlorantraniliprole at the same labeled use rate in different spray volumes (46.8 and 93.5 L ha^-1 ) on commercially grown alfalfa in California. Residue levels and spray coverage were also comparable and consistent between the UAV and airplane applications across three sampling techniques, specifically residue levels on alfalfa, insecticide recovery from filter paper, and spray coverage on water sensitive cards. Differences in droplet size and deposit characteristics were more variable for the UAV than airplanes based on analysis of deposition images.

CONCLUSION

The results of this study provide confidence supporting the use of small-scale multi-rotor UAVs for pesticide application on agricultural crops. According to the parameters tested, UAV application quality and crop protection performance were comparable to that of the conventional fixed wing airplane application. However, the droplet spectrum and the short-term fate of droplets from unmanned aerial spray system require further optimization for effective and efficient crop protection with minimal risk to the environment.

Unsupervised Learning Methods for Molecular Simulation Data

Unsupervised learning is becoming an essential tool to analyze the increasingly large amounts of data produced by atomistic and molecular simulations, in material science, solid state physics, biophysics, and biochemistry. In this Review, we provide a comprehensive overview of the methods of unsupervised learning that have been most commonly used to investigate simulation data and indicate likely directions for further developments in the field. In particular, we discuss feature representation of molecular systems and present state-of-the-art algorithms of dimensionality reduction, density estimation, and clustering, and kinetic models. We divide our discussion into self-contained sections, each discussing a specific method. In each section, we briefly touch upon the mathematical and algorithmic foundations of the method, highlight its strengths and limitations, and describe the specific ways in which it has been used-or can be used-to analyze molecular simulation data.

Density-based weighting for imbalanced regression

In many real world settings, imbalanced data impedes model performance of learning algorithms, like neural networks, mostly for rare cases. This is especially problematic for tasks focusing on these rare occurrences. For example, when estimating precipitation, extreme rainfall events are scarce but important considering their potential consequences. While there are numerous well studied solutions for classification settings, most of them cannot be applied to regression easily. Of the few solutions for regression tasks, barely any have explored cost-sensitive learning which is known to have advantages compared to sampling-based methods in classification tasks. In this work, we propose a sample weighting approach for imbalanced regression datasets called DenseWeight and a cost-sensitive learning approach for neural network regression with imbalanced data called DenseLoss based on our weighting scheme. DenseWeight weights data points according to their target value rarities through kernel density estimation (KDE). DenseLoss adjusts each data point’s influence on the loss according to DenseWeight, giving rare data points more influence on model training compared to common data points. We show on multiple differently distributed datasets that DenseLoss significantly improves model performance for rare data points through its density-based weighting scheme. Additionally, we compare DenseLoss to the state-of-the-art method SMOGN, finding that our method mostly yields better performance. Our approach provides more control over model training as it enables us to actively decide on the trade-off between focusing on common or rare cases through a single hyperparameter, allowing the training of better models for rare data points.

Quantitative Assessment of the Echogenicity of a Breast Tumor Predicts the Response to Neoadjuvant Chemotherapy

The aim of the study was to improve monitoring the treatment response in breast cancer patients undergoing neoadjuvant chemotherapy (NAC). The IRB approved this prospective study. Ultrasound examinations were performed prior to treatment and 7 days after four consecutive NAC cycles. Residual malignant cell (RMC) measurement at surgery was the standard of reference. Alteration in B-mode ultrasound (tumor echogenicity and volume) and the Kullback-Leibler divergence (kld), as a quantitative measure of amplitude difference, were used. Correlations of these parameters with RMC were assessed and Receiver Operating Characteristic curve (ROC) analysis was performed. Thirty-nine patients (mean age 57 y.) with 50 tumors were included. There was a significant correlation between RMC and changes in quantitative parameters (KLD) after the second, third and fourth course of NAC, and alteration in echogenicity after the third and fourth course. Multivariate analysis of the echogenicity and KLD after the third NAC course revealed a sensitivity of 91%, specificity of 92%, PPV = 77%, NPV = 97%, accuracy = 91%, and AUC of 0.92 for non-responding tumors (RMC ≥ 70%). In conclusion, monitoring the echogenicity and KLD parameters made it possible to accurately predict the treatment response from the second course of NAC.

Epidemiological characteristics and initial spatiotemporal visualisation of COVID-19 in a major city in the Middle East

BACKGROUND

The Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) emerged initially in China in December 2019 causing the COVID-19 disease, which quickly spread worldwide. Iran was one of the first countries outside China to be affected in a major way and is now under the spell of a fourth wave. This study aims to investigate the epidemiological characteristics of COVID-19 cases in north-eastern Iran through mapping the spatiotemporal trend of the disease.

METHODS

The study comprises data of 4000 patients diagnosed by laboratory assays or clinical investigation from the beginning of the disease on Feb 14, 2020, until May 11, 2020. Epidemiological features and spatiotemporal trends of the disease in the study area were explored by classical statistical approaches and Geographic Information Systems.

RESULTS

Most common symptoms were dyspnoea (69.4%), cough (59.4%), fever (54.4%) and weakness (19.5%). Approximately 82% of those who did not survive suffered from dyspnoea. The highest Case Fatality Rate (CFR) was related to those with cardiovascular disease (27.9%) and/or diabetes (18.1%). Old age (≥60 years) was associated with an almost five-fold increased CFR. Odds Ratio (OR) showed malignancy (3.8), nervous diseases (2.2), and respiratory diseases (2.2) to be significantly associated with increased CFR with developments, such as hospitalization at the ICU (2.9) and LOS (1.1) also having high correlations. Furthermore, spatial analyses revealed a geographical pattern in terms of both incidence and mortality rates, with COVID-19 first being observed in suburban areas from where the disease swiftly spread into downtown reaching a peak between 25 February to 06 March (4 incidences per km2). Mortality peaked 3 weeks later after which the infection gradually decreased. Out of patients investigated by the spatiotemporal approach (n = 727), 205 (28.2%) did not survive and 66.8% of them were men.

CONCLUSIONS

Older adults and people with severe co-morbidities were at higher risk for developing serious complications due to COVID-19. Applying spatiotemporal methods to identify the transmission trends and high-risk areas can rapidly be documented, thereby assisting policymakers in designing and implementing tailored interventions to control and prevent not only COVID-19 but also other rapidly spreading epidemics/pandemics.