Search

The objective identification of depression using physiological data has emerged as a significant research focus within the field of psychiatry. The advancement of wearable physiological measurement devices has opened new avenues for the identification of individuals with depression in everyday-life contexts. Compared to other objective measurement methods, wearables offer the potential for continuous, unobtrusive monitoring, which can capture subtle physiological changes indicative of depressive states. The present study leverages multimodal wristband devices to collect data from fifty-eight participants clinically diagnosed with depression during their normal daytime activities over six hours. Data collected include pulse wave, skin conductance, and triaxial acceleration. For comparison, we also utilized data from fifty-eight matched healthy controls from a publicly available dataset, collected using the same devices over equivalent durations. Our aim was to identify depressive individuals through the analysis of multimodal physiological measurements derived from wearable devices in daily life scenarios. We extracted static features such as the mean, variance, skewness, and kurtosis of physiological indicators like heart rate, skin conductance, and acceleration, as well as autoregressive coefficients of these signals reflecting the temporal dynamics. Utilizing a Random Forest algorithm, we distinguished depressive and non-depressive individuals with varying classification accuracies on data aggregated over 6 h, 2 h, 30 min, and 5 min segments, as 90.0%, 84.7%, 80.1%, and 76.0%, respectively. Our results demonstrate the feasibility of using daily wearable-derived physiological data for depression recognition. The achieved classification accuracies suggest that this approach could be integrated into clinical settings for the early detection and monitoring of depressive symptoms. Future work will explore the potential of these methods for personalized interventions and real-time monitoring, offering a promising avenue for enhancing mental health care through the integration of wearable technology. [ABSTRACT FROM AUTHOR]

Background and aims Design and setting Participants Measurements Findings Conclusions Within many alcohol prevention interventions, changes in alcohol‐related attitudes (ARA) are often proposed as precursors to changes in drinking behaviour. This study aimed to measure the longitudinal relationship between ARA and behaviour during the implementation of a large‐scale prevention trial.This study was a two‐arm school‐based clustered randomized controlled trial. A total of 105 schools in Northern Ireland and Scotland participated in the Steps Towards Alcohol Misuse Prevention Programme (STAMPP) Trial.A sample of 12 738 pupils (50% female; mean age = 12.5 years at baseline) self‐completed questionnaires on four occasions (T1–T4). The final data sweep (T4) was 33 months post baseline.Individual assessments of ARA and heavy episodic drinking (HED) were made at each time‐point. Additional covariates included location, school type, school socio‐economic status and intervention arm. Estimated models examined the within‐individual autoregressive and cross‐lagged effects between ARA and HED across the four time‐points (Bayes estimator).All autoregressive effects were statistically significant for both ARA and HED across all time‐points. Past ARA predicted future ARA [e.g. ARAT1 → ARAT2 = 0.071, credibility interval (CI) = 0.043–0.099, P < 0.001, one‐tailed]. Similarly, past HED predicated future HED (e.g. HEDT1 → HEDT2 = 0.303, CI = 0.222–0.382, P < 0.001, one‐tailed). Autoregressive effects for HED were larger than those for ARA at all time‐points. In the cross‐lagged effects, past HED statistically significantly predicted more positive ARA in the future (e.g. HEDT2 → ARAT3 = 0.125, CI = 0.078–0.173, P < 0.001, one tailed) except for the initial T1–T2 path. In contrast, past ARA did not predict future HED across any time‐points.Changes in alcohol‐related attitudes were not a precursor to changes in heavy episodic drinking within the Steps Towards Alcohol Misuse Prevention Programme (STAMPP) Trial in Scotland and Northern Ireland. Rather, alcohol‐related attitudes were more likely to reflect prior drinking status than predict future status. Heavy episodic drinking status appears to have a greater impact on future alcohol attitudes than attitudes do on future heavy episodic drinking. [ABSTRACT FROM AUTHOR]

This study examines the bias in weighted least absolute deviation ( W L 1 ) estimation within the context of stationary first-order bifurcating autoregressive (BAR(1)) models, which are frequently employed to analyze binary tree-like data, including applications in cell lineage studies. Initial findings indicate that W L 1 estimators can demonstrate substantial and problematic biases, especially when small to moderate sample sizes. The autoregressive parameter and the correlation between model errors influence the volume and direction of the bias. To address this issue, we propose two bootstrap-based bias-corrected estimators for the W L 1 estimator. We conduct extensive simulations to assess the performance of these bias-corrected estimators. Our empirical findings demonstrate that these estimators effectively reduce the bias inherent in W L 1 estimators, with their performance being particularly pronounced at the extremes of the autoregressive parameter range. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to discuss the problem of estimation and testing the equality of two autoregressive parameters of two first-order autoregressive processes AR (1) , where for each process, the observations are made at different time points. The primary interest is to propose the testing procedures for the homogeneity of autocorrelation parameters ρ 1 and ρ 2 . Furthermore, we are interested in estimating ρ 1 under uncertain and weak prior information about the possible equality of ρ 1 and ρ 2 , though we may not have full confidence in the tenacity of this information. A large sample test for the homogeneity of the parameters is developed. Pooled "P" (or restricted estimator) and preliminary test "PT" estimators are proposed, and their properties are investigated and compared with the unrestricted estimator "UE" of ρ 1 . [ABSTRACT FROM AUTHOR]

The purpose of this paper is to discuss the problem of estimation and testing the equality of two autoregressive parameters of two first-order autoregressive processes AR(1), where for each process, the observations are made at different time points. The primary interest is to propose the testing procedures for the homogeneity of autocorrelation parameters ρ1 and ρ2. Furthermore, we are interested in estimating ρ1 under uncertain and weak prior information about the possible equality of ρ1 and ρ2, though we may not have full confidence in the tenacity of this information. A large sample test for the homogeneity of the parameters is developed. Pooled “P” (or restricted estimator) and preliminary test “PT” estimators are proposed, and their properties are investigated and compared with the unrestricted estimator “UE” of ρ1.

This study examines the bias in weighted least absolute deviation (WL1) estimation within the context of stationary first-order bifurcating autoregressive (BAR(1)) models, which are frequently employed to analyze binary tree-like data, including applications in cell lineage studies. Initial findings indicate that WL1 estimators can demonstrate substantial and problematic biases, especially when small to moderate sample sizes. The autoregressive parameter and the correlation between model errors influence the volume and direction of the bias. To address this issue, we propose two bootstrap-based bias-corrected estimators for the WL1 estimator. We conduct extensive simulations to assess the performance of these bias-corrected estimators. Our empirical findings demonstrate that these estimators effectively reduce the bias inherent in WL1 estimators, with their performance being particularly pronounced at the extremes of the autoregressive parameter range.

The weight matrix is one of the most important things in Generalized SpaceTime Autoregressive (GSTAR) modeling. Commonly, the weight matrix is built based on the assumption or subjectivity of the researchers. This study proposes a new approach to composing the weight matrix using the minimum spanning tree (MST) approach. This approach reduces the level of subjectivity in constructing the weight matrix since it is based on the observations. The spatial dependency among locations is evaluated through the centrality measures of MST. It is obtained that this approach could give a similar weight matrix to the commonly used, even better in some ways, especially in modeling the data with higher variability. For the study case in traffic problems, the number of vehicles entering the Purbaleunyi toll was modeled by GSTAR with several weight matrix perspectives. According to Space-Time ACF-PACF plots, GSTAR(1;1), GSTAR(1,2), and GSTAR(2;1,1) models are the candidates for appropriate models. Based on the root mean square errors and mean absolute percentage errors, it is concluded that the GSTAR(2,1,1) with MST approach is the best model to forecast the number of vehicles entering the Purbaleunyi toll. This best model is followed by GSTAR(1,1) with an MST approach of spatial weight matrix. [ABSTRACT FROM AUTHOR]

The global pandemic due to SARS-Cov-2 ravaged the world and killed more than 6 million people globally within two years. Studies predicting future occurrences are essential to effectively combat the virus. This study modeled daily fatality rate in Nigeria from March 23, 2020 to March 19, 2022 and forecast future occurrences using Markov switching model (MSM). MSM estimates segmented fatality rates into three states of low-, medium- and highrisks. Further, estimates revealed that as at 19th March, 2022, Nigeria remained at the lowrisk regime in which 1 (95%CI: 0, 1) person, on the average, died of coronavirus daily; however, the most probable scenario in the nearest future was the medium-risk state in which an average of 4 (95%CI: 2, 5) persons would die daily with 48.7% probability. The study concluded that Nigerian COVID mortality risks followed a switching pattern which fluctuated within low-, medium- and high-risks; however, the medium-risk state was most likely in the future. Our results indicated that the quarantine measures adopted by the governments yielded positive results. It also underscored the need for governments and individuals to intensify efforts to ensure that the country remained at the low-risk zone till the virus would be eventually eradicated. [ABSTRACT FROM AUTHOR]

With the rapid growth of internet technologies, session-based recommendation systems have emerged as a key paradigm in delivering personalized recommendations by capturing users’ dynamic and short-term preferences. Traditional methods predominantly rely on modeling the sequential order of user interactions, deep learning approaches like recurrent neural networks and Transformer architectures. However, these sequence-based models often struggle in scenarios where the order of interactions is ambiguous or unreliable, limiting their real-world applicability. To address this challenge, we propose a novel session-based recommendation model, Deep Set Session-based Recommendation (DSETRec), which approaches the problem from a set-based perspective, eliminating dependence on the interaction sequence. By conceptualizing session data as unordered sets, our model captures the coupling relationships and co-occurrence patterns between items, enhancing prediction accuracy in settings where sequential information is either unavailable or noisy. The model is implemented using a deep autoregressive framework that iteratively masks known elements within a session, predicting and reconstructing additional items based on set data characteristics. Extensive experiments on benchmark datasets show that DSETRec achieves outperforms state-of-the-art baselines. DSETRec achieves a 13.2% and 11.85% improvement in P@20 and MRR@20, respectively, over its sequence-based variant on Yoochoose. Additionally, DSETRec generalizes effectively across both further short and long sessions. These results highlight the robustness of the set-based approach in capturing unordered interaction patterns and adapting to diverse session lengths. This finding provides a foundation for developing more flexible and generalized session-based recommendation systems.

A sequential procedure is developed to construct a fixed accuracy confidence interval (CI) of the common unknown variance of the random observations, where the observations arise from a first-order stationary autoregressive (AR(1)) process with a continuous and symmetric error distribution having mean zero and finite fourth-order moment. Using relevant estimators of the parameter of interest, related asymptotic properties of the derived fixed accuracy confidence interval are worked out. Furthermore, empirical evaluation of the proposed procedure together with application of it in the context of a real data is provided.

Understanding groundwater-dependent ecosystems (i.e., areas with a relatively shallow water table that plays a major role in supporting vegetation health) is key to sustaining water resources in the western United States. Groundwater-dependent ecosystems (GDEs) in Colorado have non-pristine temporal and spatial patterns, compared to agro-ecosystems, which make it difficult to quantify how these ecosystems are impacted by changes in water availability. The goal of this study is to examine how key hydrosocial parameters perturb GDE water use in time and in space. The temporal approach tests for the additive impacts of precipitation, surface water discharge, surface water mass balance as a surrogate for surface–groundwater exchange, and groundwater depth on the monthly Landsat normalized difference vegetation index (NDVI). The spatial approach tests for the additive impacts of river confluences, canal augmentation, development, perennial tributary confluences, and farmland modification on temporally integrated NDVI. Model results show a temporal trend (monthly, 1984–2019) is identifiable along segments of the Arkansas River at resolutions finer than 10 km. The temporal impacts of river discharge correlate with riparian water use sooner in time compared to precipitation, but this result is spatially variable and dependent on the covariates tested. Spatially, areal segments of the Arkansas River that have confluences with perennial streams have increased cumulative vegetation density. Quantifying temporal and spatial dependencies between the sources and effects of GDEs could aid in preventing the loss of a vulnerable ecosystem to increased water demand, changing climate, and evolving irrigation methodologies. [ABSTRACT FROM AUTHOR]

Air pollution, especially ground-level ozone, poses severe threats to human health and ecosystems. Accurate forecasting of ozone concentrations is essential for reducing its adverse effects. This study aims to use the functional time series approach to model ozone concentrations, a method less explored in the literature, and compare it with traditional time series and machine learning models. To this end, the ozone concentration hourly time series is first filtered for yearly seasonality using smoothing splines that lead us to the stochastic (residual) component. The stochastic component is modeled and forecast using a functional autoregressive model (FAR), where each daily ozone concentration profile is considered a single functional datum. For comparison purposes, different traditional and machine learning techniques, such as autoregressive integrated moving average (ARIMA), vector autoregressive (VAR), neural network autoregressive (NNAR), random forest (RF), and support vector machine (SVM), are also used to model and forecast the stochastic component. Once the forecast from the yearly seasonality component and stochastic component are obtained, both are added to obtain the final forecast. For empirical investigation, data consisting of hourly ozone measurements from Los Angeles from 2013 to 2017 are used, and one-day-ahead out-of-sample forecasts are obtained for a complete year. Based on the evaluation metrics, such as R 2 , root mean squared error (RMSE), and mean absolute error (MAE), the forecasting results indicate that the FAR outperforms the competitors in most scenarios, with the SVM model performing the least favorably across all cases. [ABSTRACT FROM AUTHOR]

The inherent volatility in electricity prices exerts a significant impact on the dynamic nature of the electricity market, shaping the decision-making processes of its stakeholders. Precise Electricity Price Forecasting (EPF) plays a pivotal role in enabling energy suppliers to optimize their bidding strategies, mitigate transactional risks, and capitalize on market opportunities, thereby ensuring alignment with the true economic value of energy transactions. Hence, this study proposes an advanced deep learning model for forecasting electricity prices one day in ahead. The model leverages the synergistic capabilities of Convolutional Neural Networks (CNN) and bidirectional Long Short-Term Memory networks (BiLSTM), operating concurrently with an autoregressive (AR) component, denoted as CNN-BiLSTM-AR. The integration of the AR model alongside CNN-BiLSTM enhances overall performance by exploiting AR’s proficiency in capturing transient linear dependencies. Simultaneously, CNN-BiLSTM excels in assimilating spatial and protracted temporal features. Moreover, the research delves into the implications of incorporating hyperparameter optimization (HPO) techniques, such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Random Search (RS). The effectiveness of the model is evaluated using two distinct European datasets sourced from the UK and German electricity markets. Performance metrics, including Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), serve as benchmarks for assessment. Finally, the findings underscore the notable performance enhancement achieved through the implementation of HPO methods in conjunction with the proposed model. Especially, the PSO-CNN-BiLSTM-AR model demonstrates substantial reductions in RMSE and MAE, amounting to 16.7% and 23.46%, respectively, for the German electricity market.

The Central Bank of Turkey’s policy to decrease the nominal interest rate has caused episodes of severe fluctuations in Turkish lira exchange rates during 2022. According to these conditions, the daily return of the USD/TRY have attracted the risk-taker investors’ attention. Therefore, the uncertainty about the rates has pushed algorithmic traders toward finding the best forecasting model. While there is a growing tendency to employ sophisticated models to forecast financial time series, in most cases, simple models can provide more precise forecasts. To examine that claim, present study has utilized several models to predict daily exchange rates for a short horizon. Interestingly, the simple exponential smoothing model outperformed all other alternatives. Besides, in contrast to the initial inferences, the time series neither had structural break nor exhibited signs of the ARCH and leverage effects. Despite that behavior, there was undeniable evidence of a long-memory trend. That means the series tends to keep a movement, at least for a short period. Finally, the study concluded the simple models provide better forecasts for exchange rates than the complicated approaches.

Life expectancy in the UK has increased since the 19th century. As of 2019, there are just under 12 million people in the UK aged 65 or over, with close to a quarter living by themselves. Thus, many families and carers are looking for new ways to improve the health and care of older people. Passive sensors such as infra-red motion and plug sensors have had success as a noninvasive way to help the older people. These provide a series of categorical sensor events throughout the day. Modeling this categorical dataset can help to understand and predict behavior. This article proposes a method to model the probability a sensor will trigger throughout the day for a household whilst accounting for the prior data and other sensors within the home. We present our results on a dataset from Howz, a company helping people to passively identify changes in their behavior over time.

Dinophysis spp. can produce diarrhetic shellfish toxins (DST) including okadaic acid and dinophysistoxins, and some strains can also produce non-diarrheic pectenotoxins. Although DSTs are of human health concern and have motivated environmental monitoring programs in many locations, these monitoring programs often have temporal data gaps (e.g., days without measurements). This paper presents a model for the historical time-series, on a daily basis, of DST-producing toxigenic Dinophysis in 8 monitored locations in western Andalucía over 2015-2020, incorporating measurements of algae counts and DST levels. We fitted a bivariate hidden Markov Model (HMM) incorporating an autoregressive correlation among the observed DST measurements to account for environmental persistence of DST. We then reconstruct the maximum-likelihood profile of algae presence in the water column at daily intervals using the Viterbi algorithm. Using historical monitoring data from Andalucía, the model estimated that potentially toxigenic Dinophysis algae is present at greater than or equal to 250 cells/L between < 1% and >10% of the year depending on the site and year. The historical time-series reconstruction enabled by this method may facilitate future investigations into temporal dynamics of toxigenic Dinophysis blooms.

Time series of proportions are often encountered in applications such as ecology, environmental science and public health. Strategies for such data include linear regression after logistic transformation. Though easy to fit, the transformation approach renders covariate effects uninterpretable on the scale on which they were observed owing to Jensen's inequality. An alternative to the transformation approach has been to directly model the response via the beta distribution. In this paper, we extend zero-inflated beta regression models for independent proportions to time series data that is bounded over the unit interval and that may take on zero values. Estimation is within the partial-likelihood framework and is computationally feasible to implement. We outline the asymptotic theory of our maximum partial likelihood estimators under mild regularity conditions and investigate their bias and variability using simulation studies. The utility of our method is illustrated using two real data examples. [ABSTRACT FROM AUTHOR]

Design randomizations and spatial corrections have increased understanding of genotypic, spatial, and residual effects in field experiments, but precisely measuring spatial heterogeneity in the field remains a challenge. To this end, our study evaluated approaches to improve spatial modeling using high-throughput phenotypes (HTP) via unoccupied aerial vehicle (UAV) imagery. The normalized difference vegetation index was measured by a multispectral MicaSense camera and processed using ImageBreed. Contrasting to baseline agronomic trait spatial correction and a baseline multitrait model, a two-stage approach was proposed. Using longitudinal normalized difference vegetation index data, plot level permanent environment effects estimated spatial patterns in the field throughout the growing season. Normalized difference vegetation index permanent environment were separated from additive genetic effects using 2D spline, separable autoregressive models, or random regression models. The Permanent environment were leveraged within agronomic trait genomic best linear unbiased prediction either modeling an empirical covariance for random effects, or by modeling fixed effects as an average of permanent environment across time or split among three growth phases. Modeling approaches were tested using simulation data and Genomes-to-Fields hybrid maize (Zea mays L.) field experiments in 2015, 2017, 2019, and 2020 for grain yield, grain moisture, and ear height. The two-stage approach improved heritability, model fit, and genotypic effect estimation compared to baseline models. Electrical conductance and elevation from a 2019 soil survey significantly improved model fit, while 2D spline permanent environment were most strongly correlated with the soil parameters. Simulation of field effects demonstrated improved specificity for random regression models. In summary, the use of longitudinal normalized difference vegetation index measurements increased experimental accuracy and understanding of field spatio-temporal heterogeneity. [ABSTRACT FROM AUTHOR]

Purpose: This research tackles the complexities of detecting bearing faults in wind turbines, which involves non-Gaussian, non-stationary signals submerged in diverse noise sources. The study aims to present an effective algorithm to address these challenges. Methods: The proposed algorithm integrates ICEEMDAN decomposition for signal analysis under varying conditions. AR filtering enhances fault feature extraction by eliminating noise. The method employs MEDA to refine detection accuracy by mitigating signal irregularities. Squared envelope analysis determines bearing fault characteristic frequencies. Results: The algorithm's performance is validated using experimental signals from Case Western Reserve University and real faulty wind turbine signals from Green Power Monitoring Systems (U.S). Conclusion: The proposed method emerges as a robust solution for detecting bearing faults amidst challenging signal environments. Its capacity to accurately diagnose bearing faults, coupled with its proficiency across diverse scenarios, positions it as a potent diagnostic tool for wind turbine systems. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The weight matrix is one of the most important things in Generalized Space–Time Autoregressive (GSTAR) modeling. Commonly, the weight matrix is built based on the assumption or subjectivity of the researchers. This study proposes a new approach to composing the weight matrix using the minimum spanning tree (MST) approach. This approach reduces the level of subjectivity in constructing the weight matrix since it is based on the observations. The spatial dependency among locations is evaluated through the centrality measures of MST. It is obtained that this approach could give a similar weight matrix to the commonly used, even better in some ways, especially in modeling the data with higher variability. For the study case in traffic problems, the number of vehicles entering the Purbaleunyi toll was modeled by GSTAR with several weight matrix perspectives. According to Space–Time ACF-PACF plots, GSTAR(1;1), GSTAR(1,2), and GSTAR(2;1,1) models are the candidates for appropriate models. Based on the root mean square errors and mean absolute percentage errors, it is concluded that the GSTAR(2,1,1) with MST approach is the best model to forecast the number of vehicles entering the Purbaleunyi toll. This best model is followed by GSTAR(1,1) with an MST approach of spatial weight matrix.

Copyright of REMAH Journal is the property of Research & Development of Human Recourses Center (REMAH) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Sample size formulas are provided to determine how many events and how many patient care units are needed to estimate the sensitivity of a monitoring system. The monitoring systems we consider generate time series binary data that are autocorrelated and clustered by patient care units. Our application of interest is an automated hand hygiene monitoring system that assesses whether healthcare workers perform hand hygiene when they should. We apply an autoregressive order 1 mixed effects logistic regression model to determine sample sizes that allow the sensitivity of the monitoring system to be estimated at a specified confidence level and margin of error. This model overcomes a major limitation of simpler approaches that fail to provide confidence intervals with the specified levels of confidence when the sensitivity of the monitoring system is above 90%. [ABSTRACT FROM AUTHOR]

The quality of the signal received at any location in communication channel depends on the degree of losses and attenuation experience along its path. The existing models are not suitable for 5G network propagation due to heavy channel interference and signal loss applicable at millimeter wave (mmWave) spectrum. The issues of Path Loss (PL) and signal interference in 5G New Radio (NR) network needs special attention. It is expected that 5G NR and 4G LTE-A networks will coexist for a very long time using the existing infrastructure. Hence, it is important to develop a good model to mitigate signal attenuation and co-channel interference that comes with the deployment of the 5G NR network. The existing models and measured data were compared to find out the closest model to the measured value. This paper proposed a modify Okumura-Hata (Ok-Hata) model for signal propagation in new 5G network. Also, an improved Autoregressive Particle Swarm Intelligent (APSI) algorithm was presented to enhance the proposed model for better performance. The modified Ok-Hata model outperformed all the existing models. The modified model has the potential to mitigate the effect of interference in 5G NR at 3.5 GHz frequency. The proposed new model has the capacity to solve some network issues such as; path loss, co-channel interference in 5G network. The result shows that there was no signal interference between the existing, and modified models. The result also shows that enhanced APSI is suitable for 5G NR network planning in Abuja, Nigeria. [ABSTRACT FROM AUTHOR]

Insufficient length of streamflow record poses challenges in capturing extreme events, frequencies, and sequences crucial for effective water resources systems design. Consequently, simulation and application of statistically similar streamflow values becomes imperative. In this study, two Markov-based models, namely the Thomas-Fiering (T-F) model and the Autoregressive (AR) model, were developed based on a log-normal probability distribution to synthesize monthly and annual flows using a decade of historical data (1980–1989) collected from the Umulokpa gauging station in the Adada River catchment of Enugu State, Nigeria. Except for the month of December (p = 0.03), no significant difference (p > 0.05) was observed between the monthly and annual model-predicted streamflows. However, both models demonstrated limitations in fully capturing the characteristics of the observed flows, particularly regarding Kurtosis. Further accuracy assessment from computed correlation coefficients (0.018 for T-F and 0.122 for AR), along with root mean square error (RMSE) values (12.84 for T-F and 11.95 for AR), indicate that while both models deviated from the observed flows, the AR model demonstrated superior performance compared to the T-F model. However, to apply these models reliably, for future flow prediction in the Adada catchment, streamflow data from rivers with comparable catchment characteristics is essential. [ABSTRACT FROM AUTHOR]

Abstract Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks. Graphical Abstract

Cardinality estimation, which aims at accurately estimating the result size of queries, is a fundamental task in database query processing and optimization. One of the most recent and effective solutions to this problem is the use of deep autoregressive models to obtain joint probability distributions through unsupervised learning. However, due to the data sparsity, it is difficult for the estimator to accurately capture the actual distribution, which affects the accuracy of the cardinality estimation. In addition, autoregressive estimators' progressive sampling characteristics are prone to error propagation, which is more evident in high-dimensional data. To reduce the autoregressive cardinality estimation error and to obtain a better trade-off between estimate accuracy and latency, we propose a random smoothing autoregressive cardinality estimation model (SAM-CE), which uses a random smoothing technique combined with a deep autoregressive model to simplify the learning of joint probability distributions. A smooth progressive sampling method that is suitable for range queries is designed to improve the estimator accuracy by improving the sample quality. We conduct extensive experiments to demonstrate the effectiveness and performance of the proposed SAM-CE. The results show that SAM-CE achieves the state of the art effectiveness of cardinality estimation. [ABSTRACT FROM AUTHOR]

Our research involves analyzing the latest models used for electricity price forecasting, which include both traditional inferential statistical methods and newer deep learning techniques. Through our analysis of historical data and the use of multiple weekday dummies, we have proposed an innovative solution for forecasting electricity spot prices. This solution involves breaking down the spot price series into two components: a seasonal trend component and a stochastic component. By utilizing this approach, we are able to provide highly accurate predictions for all considered time frames.

Hydrogen refueling stations are pivotal for renewable energy and carbon neutrality; however, they encounter challenges owing to equipment malfunctions. This study addresses the use of time-series forecasting techniques to predict and diagnose critical equipment failure at these stations. An analysis of the station equipment was conducted to create scenarios for potential malfunctions in compression equipment. Techniques such as the Recurrent Neural Network (RNN), Long Short-Term Memory network (LSTM), and Gated Recurrent Unit (GRU) have been employed to forecast the conditions of high-pressure compression equipment. Deep neural networks were constructed to enhance prediction accuracy, typically achieving an error margin of 0.01. Multi-step predictions using autoregression were utilized to bolster equipment resilience against aging and progressive failures. Autoregressive prediction models, particularly those using LSTMs and GRUs, outperform RNNs. However, predictions may be subject to errors due to algorithmic limitations and environmental factors. This study introduces a stochastic forecasting approach that, utilizes Gaussian distributions to predict probability distributions, not single-point estimates. This method yielded a 95% prediction interval with a standard deviation of 1.96. The reliability of multi-time step forecasts is significantly improved by adopting stochastic autoregressive forecasting and establishing prediction intervals. The proposed model enhances not only the accuracy of equipment failure predictions but also proactive maintenance, thus reducing downtime and boosting the efficiency of the hydrogen fuel infrastructure, which contributes to the wider utilization of hydrogen as a clean energy source.

Grassland ecosystems cover up to 40% of the global land area and provide many ecosystem services directly supporting the livelihoods of over 1 billion people. Monitoring long-term changes in grasslands is crucial for food security, biodiversity conservation, achieving Land Degradation Neutrality goals, and modeling the global carbon budget. Although long-term grassland monitoring using remote sensing is extensive, it is typically based on a single vegetation index and does not account for temporal and spatial autocorrelation, which means that some trends are falsely identified while others are missed. Our goal was to analyze trends in grasslands in Eurasia, the largest continuous grassland ecosystems on Earth. To do so, we calculated Cumulative Endmember Fractions (annual sums of monthly ground cover fractions) derived from MODIS 2002-2020 time series, and applied a new statistical approach PARTS that explicitly accounts for temporal and spatial autocorrelation in trends. We examined trends in green vegetation, non-photosynthetic vegetation, and soil ground cover fractions considering their independent change trajectories and relations among fractions over time. We derived temporally uncorrelated pixel-based trend maps and statistically tested whether observed trends could be explained by elevation, land cover, SPEI3, climate, country, and their combinations, all while accounting for spatial autocorrelation. We found no statistical evidence for a decrease in vegetation cover in grasslands in Eurasia. Instead, there was a significant map-level increase in non-photosynthetic vegetation across the region and local increases in green vegetation with a concomitant decrease in soil fraction. Independent environmental variables affected trends significantly, but effects varied by region. Overall, our analyses show in a statistically robust manner that Eurasian grasslands have changed considerably over the past two decades. Our approach enhances remote sensing-based monitoring of trends in grasslands so that underlying processes can be discerned. [ABSTRACT FROM AUTHOR]

Forecasting risk measures in order to minimize and prevent a worse risk is an important and challenging task in quantitative risk management. Methodology and assessment of forecast accuracy are still developed to give a better risk measure forecast. In this paper, we provide a simple procedure to forecast expected-based risk measures of Value-at-Risk (VaR) and Expected Shortfall (ES). These risk measures may be determined by not only quantile but also expectile. By extending the Historical Simulation (HS) method and adopting the Monte Carlo (MC) principle, we build alternative algorithms without disregarding the (estimated) probability and/or distribution function(s) of the loss distribution. Based on the illustration for return data from New South Wales (NSW) Australian and Iranian electricity markets, it is found that our proposed method gives the expected-based risk measure forecast with better accuracy, instead of using the conventional HS method. The accuracy is getting higher when we consider the model able to capture the features of heavy-tailedness and conditional heteroscedasticity in the data. [ABSTRACT FROM AUTHOR]

Non-autoregressive neural machine translation (NAMT) has received increasing attention recently in virtue of its promising acceleration paradigm for fast decoding. However, these splendid speedup gains are at the cost of accuracy, in comparison to its autoregressive counterpart. To close this performance gap, many studies have been conducted for achieving a better quality and speed trade-off. In this paper, we survey the NAMT domain from two new perspectives, i.e., target dependency management and training strategies arrangement. Proposed approaches are elaborated at length, involving five model categories. We then collect extensive experimental data to present abundant graphs for quantitative evaluation and qualitative comparison according to the reported translation performance. Based on that, a comprehensive performance analysis is provided. Further inspection is conducted for two salient problems: target sentence length prediction and sequence-level knowledge distillation. Accumulative reinvestigation of translation quality and speedup demonstrates that non-autoregressive decoding may not run fast as it seems and still lacks authentic surpassing for accuracy. We finally prospect potential work from inner and outer facets and call for more practical and warrantable studies for the future. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks. [ABSTRACT FROM AUTHOR]

We propose a model‐based approach that combines Bayesian variable selection tools, a novel spatial kernel convolution structure, and autoregressive processes for detecting a subject's brain activation at the voxel level in complex‐valued functional magnetic resonance imaging (CV‐fMRI) data. A computationally efficient Markov chain Monte Carlo algorithm for posterior inference is developed by taking advantage of the dimension reduction of the kernel‐based structure. The proposed spatiotemporal model leads to more accurate posterior probability activation maps and less false positives than alternative spatial approaches based on Gaussian process models, and other complex‐valued models that do not incorporate spatial and/or temporal structure. This is illustrated in the analysis of simulated data and human task‐related CV‐fMRI data. In addition, we show that complex‐valued approaches dominate magnitude‐only approaches and that the kernel structure in our proposed model considerably improves sensitivity rates when detecting activation at the voxel level. [ABSTRACT FROM AUTHOR]

Our research involves analyzing the latest models used for electricity price forecasting, which include both traditional inferential statistical methods and newer deep learning techniques. Through our analysis of historical data and the use of multiple weekday dummies, we have proposed an innovative solution for forecasting electricity spot prices. This solution involves breaking down the spot price series into two components: a seasonal trend component and a stochastic component. By utilizing this approach, we are able to provide highly accurate predictions for all considered time frames. [ABSTRACT FROM AUTHOR]