Parallel Time Series Research Articles

Diverging phenology of American lobster (Homarus americanus) larvae and their zooplankton prey in a warming ocean

Abstract We build on previous research describing correlative links between changes in the abundance of the copepod Calanus finmarchicus, a foundational zooplankton species of the pelagic food web, and diminishing recruitment of young-of-year American lobster (Homarus americanus) to benthic nurseries in the Gulf of Maine. Using parallel 31-year time series of lobster larvae and zooplankton collected on the New Hampshire coast between 1988 and 2018, we investigated how changes in phenology of stage I larval lobster and their putative copepod prey, C. finmarchicus, affect their temporal overlap and potential to interact during the larval season. We found that over the time series both the lobster egg hatch and first appearance of larvae began earlier in the season, a trend significantly correlated with ocean warming. The last appearance of larvae in late summer has been delayed, however, thereby extending the larval season. Even with the longer larval lobster season, the C. finmarchicus season has increasingly been ending before the peak abundance of stage I lobster larvae. The net effect is a widening mismatch in phenology of the two species, an outcome consistent with the hypothesis that changes in abundance and phenology of C. finmarchicus have contributed to recent declines in lobster recruitment.

Forecasting Pitch Response of Floating Offshore Wind Turbines with a Deep Learning Model

The design and optimization of floating offshore wind turbines (FOWTs) pose significant challenges, stemming from the complex interplay among aerodynamics, hydrodynamics, structural dynamics, and control systems. In this context, this study introduces an innovative method for forecasting the dynamic behavior of FOWTs under various conditions by merging Convolutional Neural Network (CNN) with a Gated Recurrent Unit (GRU) network. This model outperforms traditional numerical models by delivering precise and efficient predictions of dynamic FOWT responses. It adeptly handles computational complexities and reduces processing duration, while maintaining flexibility and effectively managing nonlinear dynamics. The model’s prowess is showcased through an analysis of a spar-type FOWT in a multivariate parallel time series dataset using the CNN–GRU structure. The outcomes are notably promising, underscoring the model’s proficiency in accurately forecasting the performance of FOWTs.

Learning From the Dark Side: A Parallel Time Series Modelling Framework for Forecasting and Fault Detection on Intelligent Vehicles

Learning From the Dark Side: A Parallel Time Series Modelling Framework for Forecasting and Fault Detection on Intelligent Vehicles

Multi-scale one-dimensional convolution tool wear monitoring based on multi-model fusion learning skills

Effective tool wear monitoring (TWM) is crucial for accurately assessing the degree of tool wear, guiding tool replacement during actual cutting processes, ensuring stable machine operation, and improving workpiece processing quality. With the arrival of the era of Big data, more and more data-driven monitoring methods are used for TWM problems, but it also exposes the problems of over reliance on artificial feature extraction and selection, low robustness of the actual industrial environment and poor generalization of different machining processes. To solve these problems, this paper proposes a multi-scale one-dimensional convolution (MODC-MMFL) end-to-end TWM integrated network model based on multi-model fusion learning (MMFL) skills. Firstly, multi-scale local features of multi-sensor signals are adaptively extracted by multi-scale one-dimensional convolution (MODC) network, to realize multi-feature fusion. Then, using MMFL skills, the MMFL network is composed of deep attention temporal convolutional network (DATCN) and stacked bidirectional gate recurrent unit network (SBIGRU)， parallel learning time series features related to tool wear characteristics，and use a fusion layer to fuse these learned features, in which residual channel attention mechanism (RCAM) is used to improve network performance in DATCN network. Finally, the predicted tool wear value is output by fully connected regression network (FCR). In addition, this paper uses the PHM tool wear dataset to conduct experimental study on the proposed model, first verifying the effectiveness of the proposed model. Then, ablation experiments were conducted to investigate the impact of hyper-parameters on the predictive performance of the model. The model was enhanced through hyper-parameter tuning, and a generalized enhanced model was established. The experimental results showed that the enhanced model had better predictive performance compared to ordinary models. Finally, Gaussian noise is added to the original signal of the PHM tool wear dataset to simulate the high noise signal of the actual industrial environment. The noise signal is used to carry out experimental study on the enhanced model. The experimental results show that the enhanced model still has good prediction performance in the high noise environment and has high robustness to the actual industrial environment. After the above research, this paper uses the NASA tool wear dataset to conduct experimental study on the proposed model. The experimental results show that the proposed model has good predictive performance for different machining processes, verifying the generalizability of the proposed model for different machining processes. In summary, the model proposed in this paper can accurately predict tool wear values based on processing monitoring information, and has good predictive performance, anti-interference ability, and environmental adaptability, making it very suitable for practical industrial applications.

Parallel Optimization for Large Scale Interferometric Synthetic Aperture Radar Data Processing

Interferometric synthetic aperture radar (InSAR) has developed rapidly over the past years and is considered as an important method for surface deformation monitoring, benefiting from growing data quantities and improving data quality. However, the handing of SAR big data poses significant challenges for related algorithms and pipeline, particularly in large-scale SAR data processing. In addition, InSAR algorithms are highly complex, and their task dependencies are intricate. There is a lack of efficient optimization models and task scheduling for InSAR pipeline. In this paper, we design parallel time-series InSAR processing models based on multi-thread technology for high efficiency in processing InSAR big data. These models concentrate on parallelizing critical algorithms that have high complexity, with a focus on deconstructing two computationally intensive algorithms through loop unrolling. Our parallel models have shown a significant improvement of 10–20 times in performance. We have also developed a parallel optimization tool, Simultaneous Task Automatic Runtime (STAR), which utilizes a data flow optimization strategy with thread pool technology to address the problem of low CPU utilization resulting from multiple modules and task dependencies in the InSAR processing pipeline. STAR provides a data-driven pipeline and enables concurrent execution of multiple tasks, with greater flexibility to keep the CPU busy and further improve CPU utilization through predetermined task flow. Additionally, a supercomputing-based system has been constructed for processing massive InSAR scientific big data and providing technical support for nationwide surface deformation measurement, in accordance with the framework of time series InSAR data processing. Using this system, we processed InSAR data with the volumes of 500 TB and 700 TB in 5 and 7 days, respectively. Finally we generated two maps of land surface deformation all over China.

A Novel Deep Parallel Time-Series Relation Network for Fault Diagnosis

Currently, deep learning based methods are widely used in the fault diagnosis of time series data for their high precision. However, the application of traditional deep learning fault diagnosis models is limited by their calculational efficiency and poor interpretation ability. To address the problems, a fault diagnosis model named the deep parallel time-series relation network (DPTRN) is proposed in this paper. There are three main advantages of the DPTRN. (1) Our proposed time relationship unit can perform feature extraction on each time node of a time series sample simultaneously, therefore, the DPTRN performs fault diagnosis in a parallel way and improves the computing efficiency significantly. (2) By improving the absolute position embedding, our novel decoupling position embedding unit can be directly applied for fault diagnosis and can learn contextual information. (3) Our proposed DPTRN has an obvious advantage in feature interpretability compared with traditional deep learning based models. Applying the DPTRN model on four datasets, we achieved higher diagnosis performance with much lower cost, which indicates the effectiveness, efficiency and interpretability of the proposed DPTRN model.

Modification effects of ambient temperature on ozone-mortality relationships in Chengdu, China.

A multitude of epidemiological studies have demonstrated that both ambient temperatures and air pollution are closely related to health outcomes. However, whether temperature has modification effects on the association between ozone and health outcomes is still debated. In this study, three parallel time-series Poisson generalized additive models (GAMs) were used to examine the effects of modifying ambient temperatures on the association between ozone and mortality (including non-accidental, respiratory, and cardiovascular mortality) in Chengdu, China, from 2014 to 2016. The results confirmed that the ambient high temperatures strongly amplified the adverse effects of ozone on human mortality; specifically, the ozone effects were most pronounced at > 28°C. Without temperature stratification conditions, a 10-μg/m3 increase in the maximum 8-h average ozone (O3-8hmax) level at lag01 was associated with increases of 0.40% (95% confidence interval [CI] 0.15%, 0.65%), 0.61% (95% CI 0.27%, 0.95%), and 0.69% (95% CI 0.34%, 1.04%) in non-accidental, respiratory, and cardiovascular mortality, respectively. On days during which the temperature exceeded 28°C, a 10-μg/m3 increase in O3-8hmax led to increases of 2.22% (95% CI 1.21%, 3.23%), 2.67% (95% CI 0.57%, 4.76%), and 4.13% (95% CI 2.34%, 5.92%) in non-accidental, respiratory, and cardiovascular mortality, respectively. Our findings validated that high temperature could further aggravate the health risks of O3-8hmax; thus, mitigating ozone exposure will be brought into the limelight especially under the context of changing climate.

Veterinary syndromic surveillance using swine production data for farm health management and early disease detection

The use of syndromic surveillance (SyS) has grown in animal health since the 2010s, but the use of production data has been underexplored due to methodological and practical challenges. This paper aimed to tackle some of those challenges by developing a SyS system using production data routinely collected in pig breeding farms. Health-related indicators were created from the recorded data, and two different time-series types emerged: the weekly counts of events traditionally used in SyS; and continuous time-series, where every new event is a new observation, and grouping by time-unit is not applied. Exponentially Weighted Moving Average (EWMA) and Shewhart control charts were used for temporal aberration detection, using three detection limits to create a “severity” score. The system performance was evaluated using simulated outbreaks of porcine respiratory and reproduction syndrome (PRRS) as a disease introduction scenario. The system proved capable of providing early detection of unexpected trends, serving as a useful health and management decision support tool for farmers. Further research is needed to combine results of monitoring multiple parallel time-series into an overall assessment of the risk of reproduction failure.

A parallel time series algorithm for searching similar sub-sequences

<p><span>Dynamic time warping (DTW) is an important metric for measuring similarity for most time series applications. The computations of DTW cost too much especially with the gigantic of sequence databases and lead to an urgent need for accelerating these computations. However, the multi-core cluster systems, which are available now, with their scalability and performance/cost ratio, meet the need for more powerful and efficient performance. This paper proposes a highly efficient parallel vectorized algorithm with high performance for computing DTW, addressed to multi-core clusters using the Intel quad-core Xeon co-processors. It deduces an efficient architecture. Implementations employ the potential of both message passing interface (MPI) and OpenMP libraries. The implementation is based on the OpenMP parallel programming technology and offloads execution mode, where part of the code sub-sequences on the processor side, which are uploaded to the co-processor for the DTW computations. The results of experiments confirm the effectiveness of the algorithm.</span></p>

Impact of emerging virus pandemics on cause-specific maternal mortality time series: a population-based natural experiment using national vital statistics, Argentina 1980-2017

BackgroundEmerging pandemic viruses may have multiple deleterious effects on maternal health. This study examines the effects of a pandemic influenza virus on cause-specific maternal mortality time series, using Argentinian vital statistics. MethodsWe conducted a population-based natural experiment from national vital records of maternal deaths between 1980 and 2017. Joinpoint regression models were used to model time series of the maternal mortality ratio (MMR). The sensitivity of the registry to detect the effects of the pandemic H1N1 2009 influenza virus on cause-specific MMR was analysed using a panel of parallel interrupted time series (ITS). FindingsOver this 38-year study, the MMR decreased by 58·6% (69·5 to 28·8 deaths/100,000 live births), transitioning from direct obstetric causes (67·0 to 21·1/100,000 live births; 68·4% decrease) to indirect causes (2·6 to 7·7/100,000 live births; 196·2% increase). The regression analysis showed an average reduction of -2·2%/year (95% CI: -2·9 to -1·4) with 2 join points in the total trend (1998 and 2009). Parallel ITS analyses revealed the pandemic H1N1 virus had an increasing effect on mortality from the respiratory system- and sepsis-related complications (level change 4·7 and 1·6/100,000 live births respectively), reversing after the outbreak. No effect was found on MMR from hypertensive disorders, haemorrhage, abortive outcomes, other direct obstetric causes, and indirect non-respiratory comorbidities. InterpretationThe Argentinian maternal death registry appears sensitive to detect different effects of emerging infectious epidemics on maternal health. In a population-based natural experiment, pandemic H1N1 virus impacted maternal mortality almost exclusively from the respiratory system- and sepsis-related complications. FundingSupported by FISAR www.fisarchile.org

Impact of Emerging Virus Pandemics on Cause-Specific Maternal Mortality Time Series: A Population-Based Natural Experiment Using National Vital Statistics, Argentina 1980-2017

Background: Emerging pandemic viruses may have multiple deleterious effects on maternal health. This study examines effects of a pandemic influenza virus on cause-specific maternal mortality time series, using Argentinian vital statistics. Methods: We conducted a population-based natural experiment from national vital records of maternal deaths between 1980 and 2017. Joinpoint regression models were used to model time series of the maternal mortality ratio (MMR). The sensitivity of the registry to detect effects of the pandemic H1N1 2009 influenza virus on cause-specific MMR was analysed using a panel of parallel interrupted time series (ITS). Findings: Over this 38-year study, the MMR decreased by 58·6% (69·5 to 28·8 deaths/100,000 live births), transitioning from direct obstetric causes (67·0 to 21·1/100,000 live births; 68·4% decrease) to indirect causes (2·6 to 7·7/100,000 live births; 196·2% increase). The regression analysis showed an average reduction of -2·2%/year (95% CI: -2·9 to -1·4) with 2 joinpoints in the total trend (1998 and 2009). Parallel ITS analyses revealed the pandemic H1N1 virus had an increasing effect on mortality from respiratory system- and sepsis-related complications (level change 4·7 and 1·6/100,000 live births respectively), reversing after the outbreak. No effect was found on MMR from hypertensive disorders, haemorrhage, abortive outcomes, other direct obstetric causes, and indirect non-respiratory comorbidities. Interpretation: The Argentinian maternal death registry appears sensitive to detect different effects of emerging infectious epidemics on maternal health. In a population-based natural experiment, pandemic H1N1 virus impacted maternal mortality almost exclusively from respiratory system- and sepsis-related complications. Funding: FISAR, EPI-092018-01 and ONE-052021-01. Declaration of Interest: None to declare. Ethical Approval: This study was approved by an institutional review board from Pontificia Universidad Catolica Argentina.

Digital storytelling within the Australian mining industry: worker engagement and health literacy indicator effects.

The mining industry is a demanding context for workplace health education due to a range of factors including productivity targets, workforce diversity and work roster schedules. This project investigated the impact of digital story health communication on worker engagement and its effect on interactive and critical health literacy indicators. The study comprised a quasi-experimental parallel time series research design, with control and intervention groups at each of the mine sites (n = 2). Workers in the intervention group (n = 85) received a 'toolbox talk' presentation incorporating a digital story featuring a mining industry worker and a leading cardiovascular health expert. The control group (n = 90) received equivalent health information communicated in a non-narrative manner, reflective of typical practices within the mining industry. A significantly greater effect was evident for worker engagement within the intervention group, with substantial maintenance over the follow-up period, compared with no significant effect at follow-up within the control group. Significant effects on interactive health literacy indicators (n = 3) were evident for the intervention group with corresponding lower level or nil effects within the control group. The findings highlight the benefits of evidence-based digital stories as an efficient and efficacious worker-centred health communication strategy for complex industrial workplace environments.

Toward Safe Human–Robot Interaction: A Fast- Response Admittance Control Method for Series Elastic Actuator

Series elastic actuator (SEA) is a promising compliance device due to its lower output mechanical impedance, and it is widely applied to ensure safe human-robot interaction. Although some efforts have been made to achieve accurate stiffness tracking, the time-delay issue in SEA control has still not been well investigated. However, the time delay can cause an inaccurate response and increase the risk of injury. To overcome this problem, this article proposes a fast-response admittance control method for SEAs. First, an admittance control scheme considering the external force estimation is developed for a hydraulic SEA. Then, a parallel adaptive time-series (ATS) (P-ATS) compensator is proposed and further adopted in the admittance control scheme to compensate for the time delay and tracking error. The P-ATS compensator is a modification of the ATS compensator, which is enhanced with a unique parallel mechanism. Such a mechanism can save more computational resources on locating better parameters the for P-ATS compensator, thus improving its performance. Moreover, the parameter setting is converted to an optimization task, which is solved by the whale swarm algorithm (WSA) to achieve higher accuracy. The newly located parameters are compared to the current parameters based on a proposed evaluation criterion, thus guaranteeing the quality of the updated parameters. All the above strategies are employed to improve the SEA admittance control performance. The results obtained from both simulation and real-world experiments validate that, compared to conventional methods, the proposed method achieves a better performance in SEA stiffness tracking with lower time delay and tracking error.

Evaluating the robustness of snow climate indicators using a unique set of parallel snow measurement series

AbstractSnow on the ground is an important climate variable which is normally measured either as snow depth or height of new snow. Like any other meteorological variable, manually measured snow is prone to local influences, changes in the environment or procedure of the measurements. In order to investigate the robustness of snow measurement series towards such non‐climatic changes, a unique set of parallel manual snow measurements over 25 years from 23 station pairs between 490 and 1800 m a.s.l. was compiled. A sensitivity analysis based on typical snow climate indicators (e.g., mean snow depth, sum of new snow) from these parallel time series was carried out to find the most robust snow climate indicators for climatological analyses. Results show that there are only small differences in the sensitivity of the various snow climate indicators with regards to local changes. However, the indicators number of days with snow on the ground as well as the maximum snow depth are least affected by local influences and changes at station level. Median values of all station pairs reveal relative differences of about 7% for the number of days with snow cover and 11–16% for all other indicators. However, in extreme cases, the deviations within a single station pair can reach 25–40%.

A Stacked Human Activity Recognition Model Based on Parallel Recurrent Network and Time Series Evidence Theory.

As the foundation of Posture Analysis, recognizing human activity accurately in real time assists in using machines to intellectualize living condition and monitor health status. In this paper, we focus on recognition based on raw time series data, which are continuously sampled by wearable sensors, and a fine-grained evidence reasoning approach has been proposed to produce a timely and reliable result. First, the basic time unit of input data is selected by finding a tradeoff between accuracy and time cost. Then, the approach uses Long Short Term Memory to extract features and project raw multidimensional data into probability assignments, followed by trainable evidence combination and inference network that reduce uncertainly to improve the classification accuracy. Experiments validate the effectiveness of fine granularity and evidence reasoning while the final results indicate that the recognition accuracy of this approach can reach 96.4% with no additional complexity in training.

Impact of Near-Time Information for Prediction on Microeconomic Balanced Time Series Data using Different Machine Learning Methods

Instead of relying solely on data of a single time series it is possible to use information of parallel, similar time series to improve prediction quality. Our data set consists of microeconomic data of daily store deposits from a large number of different stores. We analyze how prediction performance regarding a given store can be increased by using data from other stores. First we compare several machine learning methods, including Elastic Nets, Partial Least Squares, Generalized Additive Models, Random Forests, Gradient Boosting and Neural Networks using only data of a single time series. Afterwards we show that Random Forests are able to better utilize parallel time series data compared to Partial Least Squares. Using near-time data of parallel time series is highly beneficial for prediction performance. To allow a fair comparison between different machine learning methods, we present a novel hyper-parameter optimization technique using a regression tree. It enables a fast and flexible determination of optimal parameters for a given method.

Parallel time series join using spark

SummaryA time series is a sequence of data points in successive temporal order. Time series data is produced in many applications scenarios, and the techniques for its analysis have generated substantial interest. Time series join is a primitive operation that retrieves all pairs of correlated subsequences from two given time series. As the Pearson correlation coefficient, a measure of the correlation between two variables, has multiple beneficial mathematical properties, for example, the fact that it is invariant with respect to scale and offset, it is used to measure the correlation between two time series. Considering the need to analyze big time series data, we focus on the study of scalable and distributed techniques to process massive data sets. Specifically, we propose a parallel approach to perform time series joins using Spark, a popular analytics engine for large‐scale data processing. Our solution builds on (1) a fast method to compute the fast Fourier transform on the times series to calculate the correlation between two time series, (2) a lossless partition method to divide the time series into multiple subsequences and enable a parallel and correct computation of the join result, and (3) optimization techniques to avoid redundant computations. We performed extensive tests and showed that the proposed approach is efficient and scalable across different data sets and test configurations.

Effectiveness of dental health education on oral hygiene among hearing impaired adolescents in India: A randomized control trial

To assess the effectiveness of two different methods of dental health education (DHE) for improving oral hygiene among hearing impaired adolescents in school aged 11-20 years. A randomized double blind controlled parallel time series trial was done among 178 hearing impaired adolescents. Considering existing literature, the required sample size was found to be 82 per group, at 95% confidence interval, design effect=1, type I error=5%, power of study=80%, and 20% attrition rate. Two out of five schools were randomly selected. Different methods of DHE were used, schools were coded as School A (DHE using sign language by the investigator) and School B (DHE by conventional visual method, using only posters). The mean reduction in Simplified Oral Hygiene Index (OHI-S), Plaque Index (PI), and Gingival Index (GI) scores was 1.13 ± 0.81, 0.66 ± 0.31, and 0.58 ± 0.32, respectively, in school A. The mean reductions seen in school B was 0.52 ± 0.89 in OHI-S, 0.44 ± 0.44 in PI, and 0.34 ± 0.32 in GI index (P-value<0.05). Basic training of dental professionals in sign language is both effective and feasible, and brings about greater improvement in oral hygiene status and gingival health as compared to the conventional methods of health education.

Labour’s declining share of national income in Ireland and Denmark: the national specificities of structural change

The share of national income going to workers has decreased steadily across Europe since the 1980s. This apparently uniform decrease in labour’s share conceals differences amongst states however—in ‘liberal’ Ireland, this fall has been drastic, while that of ‘social democratic’ Denmark has been moderate. This article presents a parallel time series analysis of institutional and structural factors shaping labour’s share in Ireland and Denmark. Our results show that factors common to the study of variation in labour’s share operate in different ways in different countries, both in magnitude and causal mechanism. We find that stressors such as global trade, foreign investment and high-tech growth produce different effects in each location. Equally, protections such as unionization, leftist cabinets and welfare spending display contradictory effects in both locations. We conclude that ‘power resource’ models of labour share should be supplemented with comparative approaches that emphasize how institutionalized socio-political logics mediate returns to labour.

Labour’s declining share of national income in Ireland and Denmark: the national specificities of structural change

AbstractThe share of national income going to workers has decreased steadily across Europe since the 1980s. This apparently uniform decrease in labour’s share conceals differences amongst states however—in ‘liberal’ Ireland, this fall has been drastic, while that of ‘social democratic’ Denmark has been moderate. This article presents a parallel time series analysis of institutional and structural factors shaping labour’s share in Ireland and Denmark. Our results show that factors common to the study of variation in labour’s share operate in different ways in different countries, both in magnitude and causal mechanism. We find that stressors such as global trade, foreign investment and high-tech growth produce different effects in each location. Equally, protections such as unionization, leftist cabinets and welfare spending display contradictory effects in both locations. We conclude that ‘power resource’ models of labour share should be supplemented with comparative approaches that emphasize how institutionalized socio-political logics mediate returns to labour.