Search

A visual analytics (VA) interface for formulating evaluation metrics of multi-dimensional time-series data is proposed. Evaluation metrics such as key performance indicators (KPI) are expected to play an important role in quantitatively evaluating current situations and the quality of target objects. However, it is difficult for even domain experts to formulate metrics, especially for data with complexity related to dimensionality and temporal characteristics. The proposed interface is designed by extending the concept of semantic interaction to consider the temporal characteristics of target data. It represents metrics as a linear combination of data attributes and provides a means for adjusting it through interactive VA. On an animated scatter plot, an analyst can directly manipulate several visualized objects, i.e., a node, a trajectory, and a convex hull, as the group of nodes and trajectories. The result of manipulating the objects is reflected in the linear combination of attributes, which corresponds to an axis of the scatter plot. Using the axes as the output of the analysis, analysts can formulate a metric. The effectiveness of the proposed interface is demonstrated through an example and evaluated by two user experiments on the basis of hypotheses obtained from the example.

To prevent severe air pollution, it is important to analyze time-series air quality data, but this is often challenging as the time-series data is usually partially missing, especially when it is collected from multiple locations simultaneously. To solve this problem, various deep-learning-based missing value imputation models have been proposed. However, often they are barely interpretable, which makes it difficult to analyze the imputed data. Thus, we propose a novel deep learning-based imputation model that achieves high interpretability as well as shows great performance in missing value imputation for spatio-temporal data. We verify the effectiveness of our method through quantitative and qualitative results on a publicly available air-quality dataset.

Food texture is one of the characteristics of food and is an important factor in food development. In this paper, a method of food texture quantification based on expressions for texture instead of physical properties is proposed. The method obtains two sets of time-series data of force and vibration during food compression using a magnetic food texture sensor. Dynamic time warping (DTW) matches the time-series data and standard data and calculates the degree of texture similarity. The standard data are determined by DTW barycenter averaging (DBA). The experimental results for tempura showed that the degree of texture similarity based on the vibration data had a strong correlation with the sensory evaluation data.

Anomaly detection is widely in demand in the field where automated detection of anomalous conditions in many observation tasks. While conventional data science approaches have shown interesting results, deep learning approaches to anomaly detection problems reveal new perspectives of possibilities especially where massive amount of data need to be handled. We develop anomaly detection applications on city train vibration data using deep learning approaches. We carried out preliminary research on anomaly detection in general and applied our real world data to existing solutions. In this paper, we provide a survey on anomaly detection and analyse our results of experiments using deep learning approaches.

The creation of the Internet of Things (IoT), along with the latest developments in wearable technology, has provided new opportunities in human activity recognition (HAR). The modern smartwatch offers the potential for data from sensors to be relayed to novel IoT platforms, which allow the constant tracking and monitoring of human movement and behavior. Recently, traditional activity recognition techniques have done research in advance by choosing machine learning methods such as artificial neural network, decision tree, support vector machine, and naive Bayes. Nonetheless, these conventional machine learning techniques depend inevitably on heuristically handcrafted feature extraction, in which human domain knowledge is normally limited. This work proposes a hybrid deep learning model called CNN-LSTM that employed Long Short-Term Memory (LSTM) networks for activity recognition with the Convolution Neural Network (CNN). The study makes use of HAR involving smartwatches to categorize hand movements. Using the study based on the Wireless Sensor Data Mining (WISDM) public benchmark dataset, the recognition abilities of the deep learning model can be accessed. The accuracy, precision, recall, and F-measure statistics are employed using the evaluation metrics to assess the recognition abilities of LSTM models proposed. The findings indicate that this hybrid deep learning model offers better performance than its rivals, where the achievement of 96.2% accuracy, while the f-measure is 96.3%, is obtained. The results show that the proposed CNN-LSTM can support an improvement of the performance of activity recognition.

Classification of foot&ndash, ground contact phases, as well as the swing phase is essential in biomechanics domains where lower-limb motion analysis is required, this analysis is used for lower-limb rehabilitation, walking gait analysis and improvement, and exoskeleton motion capture. In this study, sliding-window label overlapping of time-series wearable motion data in training dataset acquisition is proposed to accurately detect foot&ndash, ground contact phases, which are composed of 3 sub-phases as well as the swing phase, at a frequency of 100 Hz with a convolutional neural network (CNN) architecture. We not only succeeded in developing a real-time CNN model for learning and obtaining a test accuracy of 99.8% or higher, but also confirmed that its validation accuracy was close to 85%.

Social media is a popular platform for timely information sharing. One of the important challenges for social media platforms like Twitter is whether to trust news shared on them when there is no systematic news verification process. On the other hand, timely detection of rumors is a non-trivial task, given the fast-paced social media environment. In this work, we proposed an ensemble model, which performs majority-voting on a collection of predictions by deep neural networks using time-series vector representation of Twitter data for timely detection of rumors. By combining the proposed data pre-processing method with the ensemble model, better performance of rumor detection has been demonstrated in the experiments using PHEME dataset. Experimental results show that the classification performance has been improved by 7.9% in terms of micro F1 score compared to the baselines., Comment: 12 pages, 3 figures

In this paper, forecasting sales model for truck components using machine learning algorithms is proposed. The forecasting model helps companions (i.e. Volvo Trucks) in the activity of trade and business. It also plays a major role for firms in decision-making operations in the areas corresponding to sales, production, purchasing, finance, and accounting. In order to achieve good forecasting sales mode, firstly, a normalization approach is performed on the time-series data to reduce and eliminate the data redundancy. After that, feature extraction and selection techniques are employed on the normalized data. Finally, different machine learning methods such as Support Vector Machine Regression, Ridge Regression, Gradient Boosting Regression and Random Forest Regression have been applied to the features of the normalized time-series data. Results depict that ridge regression method gives the most promising forecasting sale results of truck components compared to the other machine learning methods. © 2020 IEEE. open access

Wireless Sensor Networks (WSN) refers to a group of spatially deployed and dedicated sensors for sending, recording, and monitoring the physical conditions of the environment and transmitting the collected data to a central location. The major challenge is to extract high level knowledge from such data. Detecting abnormality in such data can help finding the faulty sensor and also the sensor collecting the most interesting reading from the dataset. This paper proposes a machine learning based hybrid model for knowledge discovery that works best with multivariate time-series data. The Intel Berkeley Research lab (IBRL) dataset is one of the most trending dataset collected by a WSN is considered for the study. The spatial-temporal correlation was also taken as reference to find anomalies in the dataset using three models - 1) Histogram Based Outlier Score (HBOS), 2) Minimum Covariant Determinant (MCD) and 3) Isolation Forests (IF). Further, the electrical configuration about components of WSN has been used to find faults among the outliers found in the dataset. The results show that the proposed hybrid model with Isolation Forest outperformed with a precision of 94.86%. The experiment was also able to spot the least trustful or faulty sensors among the deployed sensors in IBRL dataset.

【Background】 Atrial fibrillation (AF) is an arrhythmia commonly encountered in clinical practice. There is a high risk of thromboembolism in patients with AF. Nonlinear analyses such as electroencephalogram (EEG), electrocardiogram (ECG), and respiratory movement have been used to quantify biological signals, and sample entropy (SampEn) has been employed as a statistical measure to evaluate complex systems. In this study, we examined the values of SampEn in ECG signals for patients with and without AF to measure the regularity and complexity. 【Methods】 ECG signals of lead II were recorded from 34 subjects without arrhythmia and 15 patients with chronic AF in a supine position. The ECG signals were converted into time-series data and SampEn was calculated. 【Results】 The SampEn values for the group without arrhythmia were 0.252 ± 0.114 [time lag (τ) = 1] and 0.533 ± 0.163 (τ = 5), and those for the chronic AF group were 0.392 ± 0.158 (τ = 1) and 0.759 ± 0.246 (τ = 5). The values of SampEn were significantly higher in the group with chronic AF than in the group without arrhythmia (P < 0.01 for τ = 1, P < 0.004 for τ = 5). The constructed three-dimensional vectors were plotted in time-delayed three-dimensional space. We used time lags of τ = 5 and τ = 1. The shape of the loops of the three-dimensional space was better for τ = 5. 【Conclusion】 The values of SampEn from ECG for chronic AF patients were higher than for subjects without arrhythmia, suggesting greater complexity for the time-series from chronic AF patients. SampEn is considered a new index for evaluating complex systems in ECG.

Food-web indicators for marine management are required to describe the functioning and structure of marine food-webs. In Europe, the Marine Strategy Framework Directive (MSFD), intended to lead to a 'good environmental status' of the marine waters, requires indicators of the status of the marine environment that also respond to manageable anthropogenic pressures. Identifying such relationships to pressures is particularly challenging for food-web indicators, as they need to be disentangled from linkages between indicators of different functional groups caused by species interactions. Still, such linkages have not been handled in the indicator development. Here we used multivariate autoregressive time series models to identify how fish indicators in an exploited food-web relate to fishing, climate and eutrophication, while accounting for the linkages between indicators caused by species interactions. We assembled 31-year long time series of indicators of key functional groups of fish in the Central Baltic Sea pelagic food-web, which is characterized by strong trophic links between cod (Gadus morhua) and its main fish prey sprat (Sprattus sprattus) and herring (Clupea harengus). These food-web indicators were either abundance-based indicators of key piscivores (cod) and zooplanktivores (sprat and herring) or size-based indicators of the corresponding trophic groups (biomass of large predatory fish (cod >= 38 cm) and biomass of small prey fish (sprat and herring

In this paper we describe an interactive web-based visual analysis tool for Formula one races. It first provides an overview about all races on a yearly basis in a calendar-like representation. From this starting point, races can be selected and visually inspected in detail. We support a dynamic race position diagram as well as a more detailed lap times line plot for showing the drivers' lap times in comparison. Many interaction techniques are supported like selections, filtering, highlighting, color coding, or details-on-demand. We illustrate the usefulness of our visualization tool by applying it to a Formula one dataset while we describe the different dynamic visual racing patterns for a number of selected races and drivers.

Distributed generation (DG) has seen tremendous growth to meet the needs of ever-increasing energy demand. Most of these distributed sources are renewable in nature and connected at the consumer end. The increasing penetration of DG sources has made their control and operation complex. One of the issues that are responsible for this increased complexity is islanding. This study presents a new islanding detection method (IDM) that is based on deep learning approach, using a convolution neural network (CNN). The proposed method first converts time-series data to images and then uses them to train and test the designed CNN. A CNN is specifically designed to perform islanding detection. The results using the designed CNN are compared with IDMs based on artificial NN and support vector machine. These comparisons show that islanding detection performed using deep learning technique has better detection accuracy. Also, the proposed method performs well even for noisy data.

Human Activity Recognition (HAR) employing inertial motion data has gained considerable momentum in recent years, both in research and industrial applications. From the abstract perspective, this has been driven by an acceleration in the building of intelligent and smart environments and systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc. Such environments and systems necessitate and subsume activity recognition, aimed at recognizing the actions, characteristics, and goals of one or more individuals from a temporal series of observations streamed from one or more sensors. Due to the reliance of conventional Machine Learning (ML) techniques on handcrafted features in the extraction process, current research suggests that deep-learning approaches are more applicable to automated feature extraction from raw sensor data. In this work, the generic HAR framework for smartphone sensor data is proposed, based on Long Short-Term Memory (LSTM) networks for time-series domains. Four baseline LSTM networks are comparatively studied to analyze the impact of using different kinds of smartphone sensor data. In addition, a hybrid LSTM network called 4-layer CNN-LSTM is proposed to improve recognition performance. The HAR method is evaluated on a public smartphone-based dataset of UCI-HAR through various combinations of sample generation processes (OW and NOW) and validation protocols (10-fold and LOSO cross validation). Moreover, Bayesian optimization techniques are used in this study since they are advantageous for tuning the hyperparameters of each LSTM network. The experimental results indicate that the proposed 4-layer CNN-LSTM network performs well in activity recognition, enhancing the average accuracy by up to 2.24% compared to prior state-of-the-art approaches.

This study proposed a feature-based decision method for the mapping of rice cultivation by using the time-series C-band synthetic aperture radar (SAR) data provided by Sentinel-1A. In this study, a model related to crop growth was first established. The model was developed based on a cubic polynomial function which was fitted by the complete time-series SAR backscatters during the rice growing season. From the developed model, five rice growth-related features were introduced, including backscatter difference (BD), time interval (TI) between vegetative growth and maturity stages, backscatter variation rate (BVR), average normalized backscatter (ANB) and maximum backscatter (MB). Then, a decision method based on the combination of the five extracted features was proposed to improve the rice detection accuracy. In order to verify the detection performance of the proposed method, the test data set of this study consisted of 50,000 rice and non-rice fields which were randomly sampled from a research area in Taiwan for simulation verification. From the experimental results, the proposed method can improve overall accuracy in rice detection by 6% compared with the method using feature BD. Furthermore, the rice detection efficiency of the proposed method was compared with other four classifiers, including decision tree (DT), support vector machine (SVM), K-nearest neighbor (KNN) and quadratic discriminant analysis (QDA). The experimental results show that the proposed method has better rice detection accuracy than the other four classifiers, with an overall accuracy of 91.9%. This accuracy is 3% higher than fine SVM, which performs best among the other four classifiers. In addition, the consistency and effectiveness of the proposed method in rice detection have been verified for different years and studied regions.

This paper proposes an Individual Compositional Cluster Analysis with the aids of conventional individual difference scaling (INDSCAL) model. Our target data is 3-way data which consists of objects, variables, and subjects and we treat the case when the number of objects is relatively large. The purpose of this method is to show the difference of individual subjects visually in a lower dimensional space including the feature of objects with respect to variables as clusters. Numerical examples using sensor data obtained from several subjects show a better performance.

Background As societies become more complex, larger populations suffer from insomnia. In 2014, the US Centers for Disease Control and Prevention declared that sleep disorders should be dealt with as a public health epidemic. However, it is hard to provide adequate treatment for each insomnia sufferer, since various behavioral characteristics influence symptoms of insomnia collectively. Objective We aim to develop a neural-net based unsupervised user clustering method towards insomnia sufferers in order to clarify the unique traits for each derived groups. Unlike the current diagnosis of insomnia that requires qualitative analysis from interview results, the classification of individuals with insomnia by using various information modalities from smart bands and neural-nets can provide better insight into insomnia treatments. Methods This study, as part of the precision psychiatry initiative, is based on a smart band experiment conducted over 6 weeks on individuals with insomnia. During the experiment period, a total of 42 participants (19 male; average age 22.00 [SD 2.79]) from a large university wore smart bands 24/7, and 3 modalities were collected and examined: sleep patterns, daily activities, and personal demographics. We considered the consecutive daily information as a form of images, learned the latent variables of the images via a convolutional autoencoder (CAE), and clustered and labeled the input images based on the derived features. We then converted consecutive daily information into a sequence of the labels for each subject and finally clustered the people with insomnia based on their predominant labels. Results Our method identified 5 new insomnia-activity clusters of participants that conventional methods have not recognized, and significant differences in sleep and behavioral characteristics were shown among groups (analysis of variance on rank: F4,37=2.36, P=.07 for the sleep_min feature; F4,37=9.05, P Conclusions Our research suggests that unsupervised learning allows health practitioners to devise precise and tailored interventions at the level of data-guided user clusters (ie, precision psychiatry), which could be a novel solution to treating insomnia and other mental disorders.

We have developed a procedure for hierarchical agglomerative clustering of time series data. To measure the dissimilarity between these data, we use classically the Euclidean distance or we apply the costs of the series nonlinear alignment (time warping). In the latter approach, we use the classical costs or the modified ones. The modification consists in matching short signal segments instead of single signal samples. The procedure is applied to a few datasets from the internet archive of time series. In this archive, the series of the same classes possess visual similarity but their time evolution is often different (the characteristic waves have different location within the individual signals). Therefore the use of the Euclidean distance as the dissimilarity measure gives poor results. After time warping, the nonlinearly aligned signals match each other better, and therefore the total cost of the alignment appears to be a much more effective measure. It results in higher values of the Purity index used to evaluate the results of clustering. In most cases, the proposed modification of the alignment costs definition leads to still higher values of the index. © 2018, Springer International Publishing AG. Ministry of Higher Education: BK-220/RAu-3/2016, BKM-508/RAu-3/2016, POIG.02.03.01-24-099/ Acknowledgements. This work was partially supported by the Ministry of Science and Higher Education funding for statutory activities (BK-220/RAu-3/2016) and the Ministry of Science and Higher Education funding for statutory activities of young researchers (BKM-508/RAu-3/2016). The work was performed using the infrastructure supported by POIG.02.03.01-24-099/13 grant: GeCONiI—Upper Silesian Center for Computational Science and Engineering.

The quantification of spiking variability is prevalent to many questions in neuroscience. In this review, several measures of variability are presented, as well as algorithms for implementing analyses including: spike rates and Fano factor, inter-spike intervals, coefficient of variation and local variation, autocorrelation, period histograms, a synchrony index (vector strength), and finally post-stimulus time histograms. Some of the techniques show significant overlap; however, each measure is qualitatively unique and can be tuned to the researchers needs.

In the Air Pollution and Health: A European Approach (APHEA2) project, the effects of ambient ozone concentrations on mortality were investigated. Data were collected on daily ozone concentrations, the daily number of deaths, confounders, and potential effect modifiers from 23 cities/areas for at least 3 years since 1990. Effect estimates were obtained for each city with city-specific models and were combined using second-stage regression models. No significant effects were observed during the cold half of the year. For the warm season, an increase in the 1-hour ozone concentration by 10 mug/ml was associated with a 0.33% (95% confidence interval [CI], 0.17-0.52) increase in the total daily number of deaths, 0.45% (95% CI, 0.22-0.69) in the number of cardiovascular deaths, and 1.13% (95% CI, 0.62-1.48) in the number of respiratory deaths. The corresponding figures for the 8-hour ozone were similar. The associations with total mortality were independent of SO2 and particulate matter with aerodynamic diameter less than 10 mum (PM10) but were somewhat confounded by NO2 and CO. Individual city estimates were heterogeneous for total (a higher standardized mortality rate was associated with larger effects) and cardiovascular mortality (larger effects were observed in southern cities). The dose-response curve of ozone effects on total mortality during the summer did not deviate significantly from linearity.

Exercise support systems for the elderly have been developed and some were equipped with a motion sensor to evaluate their exercise motion. Normally, it provides three-dimensional time-series data of over 20 joints. In this study, we propose to apply Convolutional Neural Network (CNN) methodology to the motion evaluation. The method converts the motion data of one exercise interval into one gray scale image. From simulation results, the CNN was possible to classify the images into specified motions.

The APHEA 2 project investigated short-term health effects of particles in eight European cities. In each city associations between particles with an aerodynamic diameter of less than 10 microm (PM(10)) and black smoke and daily counts of emergency hospital admissions for asthma (0-14 and 15-64 yr), chronic obstructive pulmonary disease (COPD), and all-respiratory disease (65+ yr) controlling for environmental factors and temporal patterns were investigated. Summary PM(10) effect estimates (percentage change in mean number of daily admissions per 10 microg/m(3) increase) were asthma (0-14 yr) 1.2% (95% CI: 0.2, 2.3), asthma (15-64 yr) 1.1% (0.3, 1.8), and COPD plus asthma and all-respiratory (65+ yr) 1.0% (0.4, 1.5) and 0.9% (0.6, 1.3). The combined estimates for Black Smoke tended to be smaller and less precisely estimated than for PM(10). Variability in the sizes of the PM(10) effect estimates between cities was also investigated. In the 65+ groups PM(10) estimates were positively associated with annual mean concentrations of ozone in the cities. For asthma admissions (0-14 yr) a number of city-specific factors, including smoking prevalence, explained some of their variability. This study confirms that particle concentrations in European cities are positively associated with increased numbers of admissions for respiratory diseases and that some of the variation in PM(10) effect estimates between cities can be explained by city characteristics.

In this paper, we consider the problem of continuous dissemination of time series data, such as sensor measurements, to a large number of subscribers. These subscribers fall into multiple subscription levels, where each subscription level is specified by the bandwidth constraint of a subscriber, which is an abstract indicator for both the physical limits and the amount of data that the subscriber would like to handle. To handle this problem, we propose a system framework for multi-scale time series data dissemination that employs a typical tree-based dissemination network and existing time-series compression models. Due to the bandwidth limits regarding to potentially sheer speed of data, it is inevitable to compress and re-compress data along the dissemination paths according to the subscription level of each node. Compression would caused the accuracy loss of data, thus we devise several algorithms to optimize the average accuracies of the data received by all subscribers within the dissemination network. Finally, we have conducted extensive experiments to study the performance of the algorithms.

In this paper a kernel for time-series data is presented. The main idea of the kernel is that it is designed to recognize as similar time series that may be slightly shifted with one another. Namely, it tries to focus on the shape of the time-series and ignores the fact that the series may not be perfectly aligned. The proposed kernel has been validated on several datasets based on the UCR time-series repository [1]. A comparison with the well-known Dynamic Time Warping (DTW) distance and Euclidean distance shows that the proposed kernel outperforms the Euclidean distance and is competitive with respect to the DTW distance while having a much lower computational cost.

International audience; Visual representations of time-series are useful for tasks such as identifying trends, patterns and anomalies in the data. Many techniques have been devised to make these visual representations more scalable, enabling the simultaneous display of multiple variables, as well as the multi-scale display of time-series of very high resolution or that span long time periods. There has been comparatively little research on how to support the more elaborate tasks associated with the exploratory visual analysis of time- series, e.g., visualizing derived values, identifying correlations, or discovering anomalies beyond obvious outliers. Such tasks typically require deriving new time-series from the original data, trying different functions and parameters in an iterative manner. We introduce a novel visualization technique called ChronoLenses, aimed at supporting users in such exploratory tasks. ChronoLenses perform on-the-fly transformation of the data points in their focus area, tightly integrating visual analysis with user actions, and enabling the progressive construction of advanced visual analysis pipelines.

Cointegration has established itself as a powerful means of projecting out long-term trends from time-series data in the context of econometrics. Recent work by the current authors has further established that cointegration can be applied profitably in the context of structural health monitoring (SHM), where it is desirable to project out the effects of environmental and operational variations from data in order that they do not generate false positives in diagnostic tests. The concept of cointegration is partly built on a clear understanding of the ideas of stationarity and nonstationarity for time-series. Nonstationarity in this context is 'traditionally' established through the use of statistical tests, e.g. the hypothesis test based on the augmented Dickey-Fuller statistic. However, it is important to understand the distinction in this case between 'trend' stationarity and stationarity of the AR models typically fitted as part of the analysis process. The current paper will discuss this distinction in the context of SHM data and will extend the discussion by the introduction of multi-resolution (discrete wavelet) analysis as a means of characterising the time-scales on which nonstationarity manifests itself. The discussion will be based on synthetic data and also on experimental data for the guided-wave SHM of a composite plate. © 2011 Published under licence by IOP Publishing Ltd. 305

Integer-valued time series data appear in several diverse applications. However, modeling and inference for these types of dependent data pose several questions and interesting problems. The method of generalized linear models turns out to provide a sound framework for modeling and estimation whereby all computations are carried out by well-established software. I review this area of research and propose some other models. © 2009 John Wiley & Sons, Inc. 1 3 361 364

A new methodology for automated extraction of repeated patterns in time-series data is presented, aimed in particular at the analysis of musical sequences. The basic principles consists in a search for closed patterns in a multi-dimensional parametric space. It is shown that this basic mechanism needs to be articulated with a periodic pattern discovery system, implying therefore a strict chronological scanning of the time-series data. Thanks to this modelling global pattern filtering may be avoided and rich and highly pertinent results can be obtained. The modelling has been integrated in a collaborative pro ject between ethnomusicology, cognitive sciences and computer science, aimed at the study of Tunisian Modal Music., Une méthodologie d'extraction automatique de motifs répétés dans des séquences temporelles est présentée, dédiée en particulier à l'analyse de séquences musicales. L'approche initiale consiste en une recherche de motifs fermés dans un espace paramétrique multidimensionnel. Il est montré que ce premier mécanisme doit être articulé avec un système de découverte de motifs périodiques, ce qui implique un parcours strictement chronologique de la séquence. Cette modélisation permet d'éviter un filtrage global des patterns, et donc d'obtenir des résultats présentant une richesse et une pertinence élevée. La modélisation a été intégrée au sein d'un projet collaboratif entre ethnomusicologie, sciences cognitives et informatique, dédié à l'étude de la musique modale tunisienne.

Author(s): Shwiff, Stephanie A.; Sterner, Ray T. | Abstract: Benefit-cost analysis (BCA) involves comparing all of the gains and losses from a given wildlife damage management action or management technique over time in similar units, thereby providing a total picture of potential gains and losses to society. This technique is at the core of justifications for wildlife damage management efforts. BCA has been noticeably absent from the study of vertebrate pest management problems, and in the few studies where a BCA has been included, the analysis is incomplete. This paper provides an overview of the steps in a BCA, using specific wildlife damage examples to highlight and expand the technique for researchers interested in documenting these effects.

To avoid the usual problems of multi-population correlation studies of air pollution and mortality, and for reasons of convenience, daily time-series mortality studies within single populations have recently become popular in air pollution epidemiology. Such studies describe how the short-term distribution of deaths relates to short-term fluctuations in air pollution levels. The regression-based risk coefficients from these acute-effects studies have been widely used to estimate the excess annual mortality within a population with a specified average level of air pollution. Such calculations are inappropriate. Since daily time-series data provide no simple direct information about the degree of life-shortening associated with the excess daily deaths (many of which are thought to be due to exacerbation of well-advanced disease, especially cardiovascular disease), such data cannot contribute to the estimation of the effects of air pollution upon chronic disease incidence and long-term death rates. Yet it is that category of effect that is of most public health importance.Such effects are best estimated from long-term cohort studies that incorporate good knowledge of local (or personal) exposure to air pollutants and of potential confounders. Time-series studies, properly evaluated, can identify the existence of acute toxic effects of transient peak levels of air pollution; they are thus useful for monitoring acute toxicity and for identifying the most noxious pollutants. However, to quantify the long-term health impacts of air pollution we cannot use acute-effects data.

Significance Migratory activity is a critical factor in shaping processes of biological and cultural change through time. We introduce a method to estimate changes in underlying migratory activity that can be applied to genetic, morphological, or cultural data and is well-suited to samples that are sparsely distributed in space and through time. By applying this method to ancient genome data, we infer a number of changes in human mobility in Western Eurasia, including higher mobility in pre- than post-Last Glacial Maximum hunter–gatherers, and oscillations in Holocene mobility with peaks centering on the Neolithic transition and the beginnings of the Bronze Age and the Late Iron Age., Mobility is one of the most important processes shaping spatiotemporal patterns of variation in genetic, morphological, and cultural traits. However, current approaches for inferring past migration episodes in the fields of archaeology and population genetics lack either temporal resolution or formal quantification of the underlying mobility, are poorly suited to spatially and temporally sparsely sampled data, and permit only limited systematic comparison between different time periods or geographic regions. Here we present an estimator of past mobility that addresses these issues by explicitly linking trait differentiation in space and time. We demonstrate the efficacy of this estimator using spatiotemporally explicit simulations and apply it to a large set of ancient genomic data from Western Eurasia. We identify a sequence of changes in human mobility from the Late Pleistocene to the Iron Age. We find that mobility among European Holocene farmers was significantly higher than among European hunter–gatherers both pre- and postdating the Last Glacial Maximum. We also infer that this Holocene rise in mobility occurred in at least three distinct stages: the first centering on the well-known population expansion at the beginning of the Neolithic, and the second and third centering on the beginning of the Bronze Age and the late Iron Age, respectively. These findings suggest a strong link between technological change and human mobility in Holocene Western Eurasia and demonstrate the utility of this framework for exploring changes in mobility through space and time.

The management of renewable energy resources plays an important role in the availability, stability and energy quality in the modern power systems. A key role of the energy management policies is played by the primary resource availability adjustment to the required consumption. As the renewable energy resources are variable in time their forecast represents an important issue. In this paper is explored how the use of consecrated artificial intelligence techniques such as feed-forward and Elman neural networks are suitable for such energy production forecasting. The main reason is that artificial intelligence techniques offers a viable solution to correct the behavior of these systems while operating by learning the changes that occur as a result of power systems external and internal factors evolution. In this case the back-propagation learning algorithm was tested in different configurations of the neural networks to find an adequate solution for the specific datasets of solar photovoltaic renewable energy resource availability.