Search

This study aims to evaluate the impact of export product concentration on the ecological footprint in the European Union between 1995 and 2018, using the environmental Kuznets curve framework. We utilized the pooled mean group/autoregressive distributed lag approach, which confirmed the environmental Kuznets curve hypothesis within the European Union. In addition, our findings reveal that export concentration has a negative impact on the ecological footprint, whereas energy consumption increases the ecological footprint. To further validate the obtained results, we conducted robustness checks using the fully modified ordinary least squares and dynamic ordinary least squares approaches, which validated the previous outcomes of the pooled mean group/autoregressive distributed lag approach. In the last step of our study, we employed the Dumitrescu–Hurlin causality analysis, which revealed a bidirectional causality involving the ecological footprint and energy consumption. These empirical findings directly result in valuable recommendations for policymakers. [ABSTRACT FROM AUTHOR]

This study evaluates the potential of applying echo state networks (ESN) and autoregression (AR) for dynamic time series prediction of free surface elevation for use in wave energy converters (WECs). The performance of these models is evaluated on time series data at different water depths and wave conditions, including both measured and simulated data with a focus on real-time prediction of ocean waves at a given location without resolving for the surrounding ocean surface, in other words, short-time single-point forecasting. The work presented includes training the models on historical wave data and testing their ability to predict phase-resolved future surface wave patterns for short-time forecasts. Additionally, this study discusses the feasibility of deploying these models for extended time intervals. It provides valuable insights into the trade-offs between accuracy and practicality in the real-time implementation of predictive models for wave elevation, which are needed in wave energy converters to optimise the control algorithm. [ABSTRACT FROM AUTHOR]

AbstractRecord-breaking temperature events are now very frequently in the news, viewed as evidence of climate change. With this as motivation, we undertake the first substantial spatial modeling investigation of temperature record-breaking across years for any given day within the year. We work with a dataset consisting of over sixty years (1960–2021) of daily maximum temperatures across peninsular Spain. Formal statistical analysis of record-breaking events is an area that has received attention primarily within the probability community, dominated by results for the stationary record-breaking setting with some additional work addressing trends. Such effort is inadequate for analyzing actual record-breaking data. Resulting from novel and detailed exploratory data analysis, we propose rich hierarchical conditional modeling of the indicator events which define record-breaking sequences. After suitable model selection, we discover explicit trend behavior, necessary autoregression, significance of distance to the coast, useful interactions, helpful spatial random effects, and very strong daily random effects. Illustratively, the model estimates that global warming trends have increased the number of records expected in the past decade almost two-fold, 1.93 (1.89,1.98) , but also estimates highly differentiated climate warming rates in space and by season. [ABSTRACT FROM AUTHOR]

• Long-term dynamics of algal bloom patterns and their causative factors are assessed. • Time-series satellite data are analyzed and modelled using non-parametric methods. • Increased occurrence and reduction in the areal extent of algal blooms are observed. • The relative influence of ocean, atmosphere, and land parameters changes by regions. • Temporal prediction of blooms is possible with a time lag of 2 months. Algal blooms are global phenomena in marine and fresh waters. An understanding of the impacts of climate change and anthropogenic activities on marine algal blooms is essential for protecting marine ecosystems. We have studied the long-term changes in the spatial patterns of algal blooms over the northern Indian Ocean and assessed the influence of the ocean, atmosphere, and land-based processes on them. We have analyzed multi-source satellite data (2003 – 2020) of various parameters such as algal concentration, temperature, salinity, sea level, particulate organic carbon, precipitation, wind speed, and river discharge on an open-source cloud computing platform. The seasonality of variables is assessed using a harmonic model, and their spatial trend is estimated using the non-parametric Mann-Kendall test. The spatial relationship between various geophysical parameters and algal bloom concentration is assessed by the cross-correlation test, and the prediction is done using a multivariate autoregression model. Results suggest that each variable exhibits distinguishable seasonal patterns. Algal bloom duration showed a significant increase over time. However, algal bloom coverage showed a significant decline in the coastal waters in all seasons except post-monsoon. The cross-correlation test unveils that lower temperatures, salinity, and sea level promote algal bloom occurrences in coastal waters rather than open waters. Furthermore, the statistical model with a time lag of 2 months shows better performance for prediction of bloom intensity (r2 = 0.86). [ABSTRACT FROM AUTHOR]

This study evaluates the potential of applying echo state networks (ESN) and autoregression (AR) for dynamic time series prediction of free surface elevation for use in wave energy converters (WECs). The performance of these models is evaluated on time series data at different water depths and wave conditions, including both measured and simulated data with a focus on real-time prediction of ocean waves at a given location without resolving for the surrounding ocean surface, in other words, short-time single-point forecasting. The work presented includes training the models on historical wave data and testing their ability to predict phase-resolved future surface wave patterns for short-time forecasts. Additionally, this study discusses the feasibility of deploying these models for extended time intervals. It provides valuable insights into the trade-offs between accuracy and practicality in the real-time implementation of predictive models for wave elevation, which are needed in wave energy converters to optimise the control algorithm.

The experience of a long-term study of the population dynamics of phyllophagous insects in Krasnoturansky pine forest (the southern part of Krasnoyarsk Krai) is discussed in the paper. Over the course of 40 years (1978–2016), regular counts of the abundance of five species of phyllophages were carried out in five landscape structures. Based on the data obtained, models of population dynamics of these species were proposed. The models were based on the idea of the existence of positive and negative feedbacks in populations. This approach made it possible to ignore the impact of parasites on insects. For calculations, an autoregressive (AR) model was proposed, according to which the current density linearly depends on the densities of previous years. The model coefficients were calculated using data from long-term surveys. It has been shown that most populations are characterized by the influence of the density of the past season on the current density in the form of a positive feedback and the influence on the current density of the density of the previous season in the form of a negative feedback. The characteristics of the stability of population dynamics of individual species in various habitats are considered. Stability margin indicators, widely used in control theory, were used as stability characteristics. It has been shown that the margin of resistance for sawflies (Tenthredinidae Latreille) is slightly greater than for other groups of species, which is consistent with the smaller dispersion of the population sizes of these species during long-term censuses. The use of AR models and characteristics of the stock of stability made it possible to classify landscape structures on the territory of the Krasnoturansky forest according to the risks of outbreaks of mass reproduction in these landscapes.

This study presents a short-term forecast of UT1-UTC and LOD using two methods, i.e. Dynamic Mode Decomposition (DMD) and combination of Least-Squares and Vector Autoregression (LS+VAR). The prediction experiments were performed separately for yearly time spans, 2018-2022. The prediction procedure started on January 1 and ended on December 31, with 7-day shifts between subsequent 30-day forecasts. Atmospheric Angular Momentum data (AAM) were used as an auxiliary time series to potentially improve the prediction accuracy of UT1-UTC and LOD in LS+VAR procedure. An experiment was also conducted with and without elimination of effect of zonal tides from UT1-UTC and LOD time series. Two approaches to using the best steering parameters for the methods were applied:. First, an adaptive approach, which observes the rule that before every single forecast, a preliminary one must be performed on the pre-selected sets of parameters, and the one with the smallest prediction error is then used for the final prediction; and second, an averaged approach, whereby several forecasts are made with different sets of parameters (the same parameters as in adaptive approach) and the final values are calculated as the averages of these predictions. Depending on the method and data combination mean absolute prediction errors (MAPE) for UT1-UTC vary from 0.63 ms to 1.43ms for the 10th day and from 3.07 ms to 8.05ms for the 30th day of the forecast. Corresponding values for LOD vary from 0.110 ms to 0.245 ms for the 10th day and from 0.148 ms to 0.325 ms for the 30th day.

Automatic classification of vessel types in the maritime domain is one of the challenging problems due to the complexity of moving patterns in the ocean that are collected by the Automatic Identification System (AIS). In this study, we explore the usability of different patterns extracted from univariate and multivariate autoregressive modeling for classifying ship types. In order to assess the differentiation power of these features we apply different supervised machine learning classification algorithms and assess the performance of trajectory classification of four different vessel types. In addition, we study the effect of region specification for distinguishing the vessels. The proposed approach produced an accuracy of 86% which confirms that the features obtained from autoregression modeling can identify vessel types effectively. In addition, we demonstrate that the performance of classification can be enhanced further by considering the location of movement. [ABSTRACT FROM AUTHOR]

The regression of mutually independent time series, whether stationary or non-stationary, will result in autocorrelation in the random error term. This leads to the over-rejection of the null hypothesis in the conventional t-test, causing spurious regression. We propose a new method to reduce spurious regression by applying the Cochrane-Orutt feasible generalized least squares method based on a bias-corrected method for a first-order autoregressive model in finite samples. This method eliminates the requirements for a kernel function and bandwidth selection, making it simpler to implement than the traditional heteroskedasticity and autocorrelation consistent method. A series of Monte Carlo simulations indicate that our method can decrease the probability of spurious regression among stationary, non-stationary, or trend-stationary series within a sample size of 10-50. We applied this proposed method to the actual data studied by Yule in 1926, and found that it can significantly minimize spurious regression. Thus, we deduce that there is no significant regressive relationship between the proportion of marriages in the Church of England and the mortality rate in England and Wales. [ABSTRACT FROM AUTHOR]

As part of the research in the recently ended project SANET II, we were trying to create a new machine-learning system without a teacher. This system was designed to recognize DDoS attacks in real time, based on adaptation to real-time arbitrary traffic and with the ability to be embedded into the hardware implementation of network probes. The reason for considering this goal was our hands-on experience with the high-speed SANET network, which interconnects Slovak universities and high schools and also provides a connection to the Internet. Similar to any other public-facing infrastructure, it is often the target of DDoS attacks. In this article, we are extending our previous research, mainly by dealing with the use of various statistical parameters for DDoS attack detection. We tested the coefficients of Variation, Kurtosis, Skewness, Autoregression, Correlation, Hurst exponent, and Kullback–Leibler Divergence estimates on traffic captures of different types of DDoS attacks. For early machine recognition of the attack, we have proposed several detection functions that use the response of the investigated statistical parameters to the start of a DDoS attack. The proposed detection methods are easily implementable for monitoring actual IP traffic. [ABSTRACT FROM AUTHOR]

Abstract Background Automated coaches (eCoach) can help people lead a healthy lifestyle (e.g., reduction of sedentary bouts) with continuous health status monitoring and personalized recommendation generation with artificial intelligence (AI). Semantic ontology can play a crucial role in knowledge representation, data integration, and information retrieval. Methods This study proposes a semantic ontology model to annotate the AI predictions, forecasting outcomes, and personal preferences to conceptualize a personalized recommendation generation model with a hybrid approach. This study considers a mixed activity projection method that takes individual activity insights from the univariate time-series prediction and ensemble multi-class classification approaches. We have introduced a way to improve the prediction result with a residual error minimization (REM) technique and make it meaningful in recommendation presentation with a Naïve-based interval prediction approach. We have integrated the activity prediction results in an ontology for semantic interpretation. A SPARQL query protocol and RDF Query Language (SPARQL) have generated personalized recommendations in an understandable format. Moreover, we have evaluated the performance of the time-series prediction and classification models against standard metrics on both imbalanced and balanced public PMData and private MOX2-5 activity datasets. We have used Adaptive Synthetic (ADASYN) to generate synthetic data from the minority classes to avoid bias. The activity datasets were collected from healthy adults (n = 16 for public datasets; n = 15 for private datasets). The standard ensemble algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) serve as input for the classification models. Subsequently, we re-verify the classifiers on the private MOX2-5 dataset. The performance of the ontology has been assessed with reasoning and SPARQL query execution time. Additionally, we have verified our ontology for effective recommendation generation. Results We have tested several standard AI algorithms and selected the best-performing model with optimized configuration for our use case by empirical testing. We have found that the autoregression model with the REM method outperforms the autoregression model without the REM method for both datasets. Gradient Boost (GB) classifier outperforms other classifiers with a mean accuracy score of 98.00%, and 99.00% for imbalanced PMData and MOX2-5 datasets, respectively, and 98.30%, and 99.80% for balanced PMData and MOX2-5 datasets, respectively. Hermit reasoner performs better than other ontology reasoners under defined settings. Our proposed algorithm shows a direction to combine the AI prediction forecasting results in an ontology to generate personalized activity recommendations in eCoaching. Conclusion The proposed method combining step-prediction, activity-level classification techniques, and personal preference information with semantic rules is an asset for generating personalized recommendations.

The task of detecting vocal abnormalities is characterized by a small amount of available data for training, as a consequence of which classification systems that use low-dimensional data are the most relevant. We propose to use LASSO (least absolute shrinkage and selection operator) and BSS (backward stepwise selection) methods together to select the most significant features for the detection of vocal pathologies, in particular amyotrophic lateral sclerosis. Features based on fine-frequency cepstral coefficients, traditionally used in speech signal processing, and features based on discrete estimation of the autoregressive spectrum envelope are used. Spectral features based on the autoregressive process envelope spectrum are extracted using the generative method, which involves calculating a discrete Fourier transform of the report sequence generated using the autoregressive model of the input voice signal. The sequence is generated by the autoregressive model so as to account for the periodic nature of the Fourier transform. This improves the accuracy of the spectrum estimation and reduces the spectral leakage effect. Using LASSO in conjunction with BSS allowed us to improve the classification efficiency using a smaller number of features as compared to using the LASSO method alone.

This study investigates the influential economic factors impacting auto insurance premiums and explores the potential for a long-term equilibrium relationship. Monthly data from 25 branches of the National Insurance Company in the regional agency of Ouargla, Algeria, is analyzed using descriptive and case study methods. Through a thorough trend analysis and statistical model formulation, including co-integration tests, stability tests, and regression analyses, we assess the relationship between variables and the impact of independent variables on the dependent variable. The results reveal a statistically acceptable yet weak short-term connection, lacking evidence of common integration. This research provides insights into the complex dynamics of insurance premiums and compensation relationships, suggesting nuanced connections and guiding recommendations for adaptable premium structures and responsive strategies.

Long-span single-pier rigid frame bridge may experience excessive bearing displacement under temperature variation, which can result in structural deformation or instability, causing significant engineering accidents and immeasurable losses on society. This paper proposes a spatial-temporal nonlinear modeling method for temperature and temperature-induced bearing displacement (TIBD) of long-span single-pier rigid frame bridge based on DCNN-LSTM network with elastic modulus fusion, relying on the monitoring data of the Second Yangtze River Bridge in Wuhan. This framework introduces a dynamic autoregressive method for model inference to improve the prediction accuracy of the model. This study addresses three major issues: Insufficient rational selection of temperature characteristic values; Inadequate research on correlation between structural temperature and TIBD for the bridges; Poor prediction accuracy of temperature-TIBD regression models. The method proposed in this study achieves prediction accuracy of up to 99.8 % for TIBD, and this model is not affected by seasonal variation.

Background: Automated coaches (eCoach) can help people lead a healthy lifestyle (e.g., reduction of sedentary bouts) with continuous health status monitoring and personalized recommendation generation with artificial intelligence (AI). Semantic ontology can play a crucial role in knowledge representation, data integration, and information retrieval. Methods: This study proposes a semantic ontology model to annotate the AI predictions, forecasting outcomes, and personal preferences to conceptualize a personalized recommendation generation model with a hybrid approach. This study considers a mixed activity projection method that takes individual activity insights from the univariate time-series prediction and ensemble multi-class classification approaches. We have introduced a way to improve the prediction result with a residual error minimization (REM) technique and make it meaningful in recommendation presentation with a Naïve-based interval prediction approach. We have integrated the activity prediction results in an ontology for semantic interpretation. A SPARQL query protocol and RDF Query Language (SPARQL) have generated personalized recommendations in an understandable format. Moreover, we have evaluated the performance of the time-series prediction and classification models against standard metrics on both imbalanced and balanced public PMData and private MOX2-5 activity datasets. We have used Adaptive Synthetic (ADASYN) to generate synthetic data from the minority classes to avoid bias. The activity datasets were collected from healthy adults (n = 16 for public datasets; n = 15 for private datasets). The standard ensemble algorithms have been used to investigate the possibility of classifying daily physical activity levels into the following activity classes: sedentary (0), low active (1), active (2), highly active (3), and rigorous active (4). The daily step count, low physical activity (LPA), medium physical activity (MPA), and vigorous physical activity (VPA) serve as input for the classification models. Subsequently, we re-verify the classifiers on the private MOX2-5 dataset. The performance of the ontology has been assessed with reasoning and SPARQL query execution time. Additionally, we have verified our ontology for effective recommendation generation. Results: We have tested several standard AI algorithms and selected the best-performing model with optimized configuration for our use case by empirical testing. We have found that the autoregression model with the REM method outperforms the autoregression model without the REM method for both datasets. Gradient Boost (GB) classifier outperforms other classifiers with a mean accuracy score of 98.00%, and 99.00% for imbalanced PMData and MOX2-5 datasets, respectively, and 98.30%, and 99.80% for balanced PMData and MOX2-5 datasets, respectively. Hermit reasoner performs better than other ontology reasoners under defined settings. Our proposed algorithm shows a direction to combine the AI prediction forecasting results in an ontology to generate personalized activity recommendations in eCoaching. Conclusion: The proposed method combining step-prediction, activity-level classification techniques, and personal preference information with semantic rules is an asset for generating personalized recommendations. [ABSTRACT FROM AUTHOR]

Three models of abundance dynamics for forest insects that depict the development of outbreak populations were analyzed. We studied populations of the Siberian silkmoth Dendrolimus sibiricus Tschetv. in Siberia and the Far East of Russia, as well as a population of the pine looper Bupalus piniarius L. in Thuringia, Germany. The first model (autoregression) characterizes the mechanism where current population density is dependent on population densities in previous k years. The second model considers an outbreak as analogous to a first-order phase transition in physical systems and characterizes the outbreak as a transition through a potential barrier from a low-density state to a high-density state. The third model treats an outbreak as an effect of stochastic resonance influenced by a cyclical factor such as solar activity and the "noise" of weather parameters. The discussion focuses on the prediction effectiveness of abundance dynamics and outbreak development for each model. [ABSTRACT FROM AUTHOR]

Artificial intelligence is overhauling the publication and textual production. Textual production with Large Language Models (LLMs) is more sophisticated and closer to human knowledge production thanks to its autoregressive nature. AI models by OpenAI such as the Generative Pre-trained Transformer 3 (GPT-3) and its iterations use deep learning to produce more human-like text. Such texts invite all kinds of problems that are not new to the human text-production system. Research shows that the output of such models tends to be biased towards a particular gender, race and ethnicity. This paper explores substantial texts produced by AI including articles, fiction, columns, opinion pieces etc. published in major journals and magazines to understand the nuances of such texts. Moreover, the paper will attempt to understand such features of AI-generated text by presenting the results of a particular set of instructions (prompt) to the LLM. These text outputs will be studied to demonstrate how AI-generated texts pave the way for a "postpost author" era, echoing Barthes' notion of the "Death of the Author". The scope, usability and limitations of the AI's textual production will also be investigated. [ABSTRACT FROM AUTHOR]

The article presents the results of the study of models for short-term forecasting of overall electricity imbalances in the IPS of Ukraine. The analysis of forecasting results obtained using different types of autoregressive models and two forecasting models based on artificial neural networks was performed. Conducted research based on actual data of the balancing market of electric energy of Ukraine showed the effectiveness of using artificial neural networks for the specified task. It is shown that the application of the LSTM (Long short-term memory) artificial neural network model achieves the highest forecasting accuracy for both positive and negative electricity imbalances, respectively, compared to forecasting using autoregressive models. Bibl. 11, fig. 3, table.

In this work, panel data that were characterized by features of no first order autocorrelation was modelled using three estimation models: Pool Regression, Fixed Effect, Random Effect models. Panel data like other aspects of econometrics, exploits regression analysis as one of the statistical tools to formulate and illustrate models. The regression analysis requires some assumptions which, if violated, results to one problem or the other. In such case, the Pooling method of estimation remains linear, unbiased and normally distributed but might not be efficient as the estimates of the parameters might become indeterminate, the confidence intervals may be too wide and the standard errors might become large. Simulation studies were carried out at different panel structures and autocorrelation level. The experiment was repeated for 10,000 times and Root Mean Square Error (RMSE) was used to judge the performance of the models. The results from this work showed that for small sample panel structure N = 25, T = 5 and n = 5, irrespective of autocorrelation levels, fixed effect model is preferable at all level. But when moderate for N = 50, T = 10, n = 5, irrespective of autocorrelation level, random effect model is preferred, while for large panel structure for N = 450, T = 30, n = 15, irrespective of autocorrelation level, random effect model is preferred. [ABSTRACT FROM AUTHOR]

Fire emissions of gases and aerosols alter atmospheric composition and have substantial impacts on climate, ecosystem function, and human health. Warming climate and human expansion in fire-prone landscapes exacerbate fire impacts and call for more effective management tools. Here we developed a global fire forecasting system that predicts monthly emissions using past fire data and climate variables for lead times of 1 to 6 months. Using monthly fire emissions from the Global Fire Emissions Database (GFED) as the prediction target, we fit a statistical time series model, the Autoregressive Integrated Moving Average model with eXogenous variables (ARIMAX), in over 1,300 different fire regions. Optimized parameters were then used to forecast future emissions. The forecast system took into account information about region-specific seasonality, long-term trends, recent fire observations, and climate drivers representing both large-scale climate variability and local fire weather. We cross-validated the forecast skill of the system with different combinations of predictors and forecast lead times. The reference model, which combined endogenous and exogenous predictors with a 1 month forecast lead time, explained 52% of the variability in the global fire emissions anomaly, considerably exceeding the performance of a reference model that assumed persistent emissions during the forecast period. The system also successfully resolved detailed spatial patterns of fire emissions anomalies in regions with significant fire activity. This study bridges the gap between the efforts of near-real-time fire forecasts and seasonal fire outlooks and represents a step toward establishing an operational global fire, smoke, and carbon cycle forecasting system.

Objectives. The problem of developing a method for calculating small-sized spectral features that increases the efficiency of existing machine learning systems for analyzing and classifying voice signals is being solved.Methods. Spectral features are extracted using a generative approach, which involves calculating a discrete Fourier spectrum for a sequence of samples generated using an autoregressive model of input voice signal. The generated sequence processed by the discrete Fourier transform considers the periodicity of the transform and thereby increase the accuracy of spectral estimation of analyzed signal.Results. A generative method for calculating spectral features intended for use in machine learning systems for the analysis and classification of voice signals is proposed and described. An experimental analysis of the accuracy and stability of the spectrum representation of a test signal with a known spectral composition has been carried out using the envelopes. The envelopes were calculated using proposed generative method and using discrete Fourier transform with different analysis windows (rectangular window and Hanna window). The analysis showed that spectral envelopes obtained using the proposed method more accurately represent the spectrum of test signal according to the criterion of minimum square error. A comparison of the effectiveness of voice signal classification with proposed features and the features based on the mel-frequency kepstral coefficients is carried out. A diagnostic system for amyotrophic lateral sclerosis was used as a basic test system to evaluate the effectiveness of proposed approach in practice. Conclusion. The obtained experimental results showed a significant increase of classification accuracy when using proposed approach for calculating features compared with the features based on the mel-frequency kepstral coefficients.

Bu çalışmada, enflasyon oranlarının giderek hız kazandığı Türkiye’de, sigorta şirketlerinin performanslarının ve prim üretimlerinin enflasyondan nasıl etkilendiği araştırılmıştır. Karlılık oranları için 2006:1-2022:3 ve prim üretimi için de 2008:4-2022:3 dönemlerini kapsayan iki örneklem kullanılarak enflasyonun etkileri incelenmiştir. Analizlerde alternatif zaman serisi teknikleriyle, enflasyon ile karlılık oranları arasındaki kısa ve uzun dönemli nedensellikler araştırılmıştır. Buna ek olarak, başlıca açıklayıcı değişkenin enflasyon oranı olduğu ardışık bağlanımlı regresyon modelleriyle enflasyonun sigorta şirketlerinin performansları ve prim üretimleri üzerindeki etkileri incelenmiştir. Bazı sigorta şirketleri için kimi performans ölçütleri ve prim üretimi açısından enflasyon ile kısa ve uzun dönemli nedensellik ilişkileri belirlenmiştir. Bu ilişkiler genelde enflasyondan prim üretimine doğru tek yönlüdür. Karlılık ölçütleri ve prim üretimi, enflasyondan ya hiç etkilenmemekte ya da pozitif etkilenmektedir. Sigorta şirketlerinin, bir şekilde enflasyonun etkilerinden korunmayı başardığı söylenebilir. Bu durum primlerin enflasyon oranındaki değişmelere göre güncellenmesinden ileri gelebilir. Bir diğer neden de sigorta şirketlerinin etkin bir fon yönetimi ile mali karlılıklarını yükseltmeleri olabilir.

One of the main problems in building energy-efficient and non-resource-intensive decentralized power supply systems in the Arctic zone and regions of the Far North is forecasting the consumption of electrical energy by small northern settlements. Among the existing methods that give an acceptable result in terms of accuracy, one can single out approaches based on the ARIMA econometric method. A method based on the Wold decomposition and correlation functions of the stochastic process is considered, an adaptive model of the difference equation is constructed, which makes it possible to predict energy consumption of the active power of autonomous systems of a small settlement in the interval of 0–4 hours, by reducing the stochastic process to a stationary Markov process with short memory. The purpose of the work is to build a methodology for short-term forecasting of electric energy consumption by autonomous energy systems of small northern settlements, taking into account the specifics of energy consumption in the conditions of the Arctic zone and the Far North, based on a stochastic series of data on electric energy consumed by the settlement over the previous period. Methods: approach to obtaining a short-term forecast of electricity consumption by autonomous energy systems of small northern settlements based on the ARIMA econometric method. In this case, a difference equation is constructed for the deterministic and random components of the available stochastic series of energy consumption; Wold decomposition and correlation functions of the energy consumption are used. To adapt the model, the studied stochastic process is reduced to a Markov process with a short memory. To do this, it is necessary to use a difference operator, which reduces the relative contribution of consumption deterministic component. Results. Based on Wold decomposition and correlation functions, it was possible to obtain a model that gives a short-term forecast of active power consumption for a lead time of 4 hours. Conclusions. Based on the Wold decomposition and the correlation functions of the stochastic process, the authors of the work managed to obtain an adaptive model of the difference equation, which makes it possible to predict active power consumption of autonomous systems of a small settlement with a lead time of 4 hours. The stationarity of the random process was carried out by introducing a difference operator of the first order, which makes it possible to reduce the relative contribution of the deterministic component of the stochastic series. The authors managed to reduce the process to a stationary Markov process with a short memory. The expansion coefficients of the difference equation were estimated by solving a nonlinear equation, which consists in finding the global maximum of the likelihood function. The constructed 90 % probabilistic boundaries allow us to talk about a satisfactory adjustment of the adaptive parameters of the difference equation for predicting the system. The result of forecast modeling with four-hour lead time shows good agreement with experiment.

Movement of soil and associated landslides frequently occur in hilly areas. Regular monitoring, accurate prediction, and timely alerting of people about soil movements on hills susceptible to landslides are essential due to the potential destruction to life and property. A more recent strategy for predicting soil movement is the use of machine learning (ML) models. Different univariate and multivariate ML models have been proposed in the literature. However, evaluating these univariate and multivariate approaches in predicting real-world landslides have received less attention. This paper’s primary goal is to develop and compare the ability of univariate and multivariate ML models (Autoregression (AR), Seasonal Autoregressive Integrated Moving Average (SARIMA), Sequential Minimal Optimization regression (SMOreg), Multilayer Perceptron (MLP), and Long-short Term Memory (LSTM)) to predict movements at a real-world landslide. The case study used for the analysis in this paper is the Tangni landslide in India. This study makes use of weekly averaged soil movement data collected from June 2012 to December 2013 (78 weeks) at the Tangni landslide site. The dataset comprises measurements from five sensors. To calibrate the parameters in each model, we divided the collected data into a training dataset (first 62 weeks) and a test dataset (last 16 weeks). Performance analysis of the models utilized Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and R-squared values. The training results revealed that the univariate AR model demonstrated the best performance, achieving an RMSE of 0.149 degrees and an R-squared value of 0.572. The univariate SMOreg model obtained the second-best performance with an RMSE of 0.336 degrees and an R-squared value of 0.582. However, on the test dataset, the multivariate SARIMAX model outperformed the other models, achieving an RMSE of 0.351 degrees and an R-squared value of 0.769. The univariate SARIMA model also performed well with an RMSE of 0.356 degrees and an R-squared value of 0.741. The findings of this study can have significant implications in the field of landslide prediction and prevention. The results indicate that the multivariate SARIMAX model, the most accurate in predicting soil movements, can aid in developing early warning systems against landslides in hilly areas.

Short-term load forecasting (STLF) is critical for the energy industry. Accurate predictions of future electricity demand are necessary to ensure power systems' reliable and efficient operation. Various STLF models have been proposed in recent years, each with strengths and weaknesses. This paper comprehensively reviews some STLF models, including time series, artificial neural networks (ANNs), regression-based, and hybrid models. It first introduces the fundamental concepts and challenges of STLF, then discusses each model class's main features and assumptions. The paper compares the models in terms of their accuracy, robustness, computational efficiency, scalability, and adaptability and identifies each approach's advantages and limitations. Although this study suggests that ANNs and hybrid models may be the most promising ways to achieve accurate and reliable STLF, additional research is required to handle multiple input features, manage massive data sets, and adjust to shifting energy conditions. [ABSTRACT FROM AUTHOR]

Relatively large deformations of the steel arch support in underground coal mines in the Republic of Serbia present one of the main problems for achieving the planned production of coal. Monitoring of the critical sections of the steel arch support in the underground roadways is necessary to gather quality data for the development of a forecasting model. With a new generation of 3D laser scanners that can be used in potentially explosive environments (ATEX), deformation monitoring is facilitated, while the process of collecting precise data is much shorter. In this paper, we used a combination of grey and stochastic system theory combined with an autoregressive process for processing collected data and the development of a forecasting model of the deformations of the steel arch support. Forecasted data accuracy based on the positions of the markers placed along the internal rim of support construction shows high accuracy with MAPE of 0.2143%. The proposed model can successfully be used by mining engineers in underground coal mines for steel arch support deformations prediction, consequentially optimizing the maintenance plan of the underground roadways and achieving planned production. [ABSTRACT FROM AUTHOR]

Computer technology has developed to a very advanced measure. Calculations using complex formulas are no longer an obstacle for industry and researchers. Along with advances in computing technology, the development of fuzzy system models is also experiencing rapid progress. This paper proposes a fuzzy model combined with Vector Autoregression. The fuzzy membership function is built by selecting the median of each set to be the center of the fuzzy set. The function chosen as the membership function is Gaussian. The fuzzy Vector Autoregression model obtained was applied to the Farmer's Exchange Rate in Central Java Province. The accuracy of the model is measured based on the Mean Absolute Percentage Error. The results of model trials on FER Central Java in 2014-2020, show a pretty good forecast, namely forecasting with MAPE around 5%, and not exceeding 10%.

As part of the research in the recently ended project SANET II, we were trying to create a new machine-learning system without a teacher. This system was designed to recognize DDoS attacks in real time, based on adaptation to real-time arbitrary traffic and with the ability to be embedded into the hardware implementation of network probes. The reason for considering this goal was our hands-on experience with the high-speed SANET network, which interconnects Slovak universities and high schools and also provides a connection to the Internet. Similar to any other public-facing infrastructure, it is often the target of DDoS attacks. In this article, we are extending our previous research, mainly by dealing with the use of various statistical parameters for DDoS attack detection. We tested the coefficients of Variation, Kurtosis, Skewness, Autoregression, Correlation, Hurst exponent, and Kullback–Leibler Divergence estimates on traffic captures of different types of DDoS attacks. For early machine recognition of the attack, we have proposed several detection functions that use the response of the investigated statistical parameters to the start of a DDoS attack. The proposed detection methods are easily implementable for monitoring actual IP traffic.

Three models of abundance dynamics for forest insects that depict the development of outbreak populations were analyzed. We studied populations of the Siberian silkmoth Dendrolimus sibiricus Tschetv. in Siberia and the Far East of Russia, as well as a population of the pine looper Bupalus piniarius L. in Thuringia, Germany. The first model (autoregression) characterizes the mechanism where current population density is dependent on population densities in previous k years. The second model considers an outbreak as analogous to a first-order phase transition in physical systems and characterizes the outbreak as a transition through a potential barrier from a low-density state to a high-density state. The third model treats an outbreak as an effect of stochastic resonance influenced by a cyclical factor such as solar activity and the “noise” of weather parameters. The discussion focuses on the prediction effectiveness of abundance dynamics and outbreak development for each model.

This paper describes a source tracking technique in a reverberant environment using a new combination of an adaptive species-based particle swarm optimization (ASPSO) algorithm and a multiple signal classification (MUSIC) algorithm. To mitigate the effects of reverberation, an insightful dereverberation method based on an online autoregressive (AR) array and a minimum variance distortionless response (MVDR) beamformer is developed to dereverberate the microphone signal prior to direction of arrival (DOA) estimation using MUSIC. On the basis of several evolutionary schemes, ASPSO enables rapid tracking by finding local maxima in the MUSIC pseudospectrum. In the ASPSO algorithm, particles are divided into different species, where each species is associated with a sound source. As the sound source moves, the DOA information is dynamically updated using ASPSO, in which the inertia weight decreases progressively to prevent premature convergence. Two update rules for adapting the filter coefficients are employed for drastically moving sources. Simulations and experiments are conducted using a circular microphone array to validate the proposed ASPSO with AR (ASPSO-AR) algorithm. The results demonstrate that ASPSO-AR requires one-third of the processing time of the grid search (GS) method. In addition, the root-mean-square error (RMSE) of the ASPSO-AR algorithm is 10° less than that of the GS method.

THE PURPOSE. Smart electrical grids involve extensive use of information infrastructure. Such an aggregate cyber-physical system can be subject to cyber attacks. One of the ways to counter cyberattacks is state estimation. State Estimation is used to identify the present power system operating state and eliminating metering errors and corrupted data. In particular, when a real measurement is replaced by a false one by a malefactor or a failure in the functioning of communication channels occurs, it is possible to detect false data and restore them. However, there is a class of cyberattacks, so-called False Data Injection Attack, aimed at distorting the results of the state estimation. The aim of the research was to develop a state estimation algorithm, which is able to work in the presence of cyber-attack with high accuracy.METHODS. The authors propose a Multi-Model Forecasting-Aided State Estimation method based on multi-model discrete tracking parameter estimation by the Kalman filter. The multimodal state estimator consisted of three single state estimators, which produced single estimates using different forecasting models. In this paper only linear forecasting models were considered, such as autoregression model, vector autoregression model and Holt’s exponen tial smoothing. When we obtained the multi-model estimate as the weighted sum of the single-model estimates. Cyberattack detection was implemented through innovative and residual analysis. The analysis of the proposed algorithm performance was carried out by simulation modeling using the example of a IEEE 30-bus system in Matlab.RESULTS. The paper describes an false data injection cyber attack and its specific impact on power system state estimation. A Multi - Model Forecasting-Aided State Estimation algorithm has been developed, which allows detecting cyber attacks and recovering corrupted data. Simulation of the algorithm has been carried out and its efficiency has been proved.CONCLUSION. The results showed the cyber attack detection rate of 100%. The Multi-Model Forecasting-Aided State Estimation is an protective measure against the impact of cyber attacks on power system.

This study empirically analyzes time series momentum (TSM) in the European equity market between 2000 & 2020. The study produces additional evidence on TSM where a significant and persistent market price anomaly enables investors to earn abnormal returns. To achieve this goal the present study implements a pooled autoregressive model to test the predictability power of European equity indices of future returns. The results indicate that strategies based on TSM are in line with the discussed literature and enable market agents to earn returns above the market (0.71% per month) by using a six-factor model.

We propose an extension of the N-mixture model that enables the estimation of abundances of multiple species as well as the correlations between them. Our novel multi-species N-mixture model (MNM) is the first to address the estimation of both positive and negative inter-species correlations, which allows us to assess the influence of the abundance of one species on another. We provide extensions that permit the analysis of data with excess of zero counts, and relax the assumption that populations are closed through the incorporation of an autoregressive term in the abundance. Our approach provides a method of quantifying the strength of association between species' population sizes and is of practical use to population and conservation ecologists. We evaluate the performance of the proposed models through simulation experiments in order to examine the accuracy of both model estimates and coverage rates. The results show that the MNM models produce accurate estimates of abundance, inter-species correlations and detection probabilities at a range of sample sizes. The MNM models are applied to avian point data collected as part of the North American Breeding Bird Survey between 2010 and 2019. The results reveal an increase in Bald Eagle abundance in south-eastern Alaska in the decade examined. [ABSTRACT FROM AUTHOR]

To reduce the probability of violent crimes, the deep learning (DL) technology and linear spatial autoregressive models (ARMs) are utilised to estimate the model parameters through different penalty functions. In addition, under a determinate space, the influences of environmental factors on violent crimes are discussed. By taking campus violence cases as examples, the major influencing factors of violent crimes are found through data analysis. The results show that campus violence cases are usually caused by the complex surrounding environments and persons. Also, campus security measures only cover a small range, and the security management is difficult. In the meantime, due to the younger ages and lack of self-protection awareness, students may easily become the targets of criminals. Therefore, the results have a positive significance for authorities to analyse the crime rates in a determinate area and take preventive measures against violent crimes.

Mobility is considered one of the main reasons for the COVID-19 spread. Predicting the effect of control measures on mobility is essential to apply effective decisions. This work proposes an AI-based model for mobility changes prediction. The proposed CNN-LSTM with Autoregression has achieved the best results compared to other investigated models. Results show that the proposed model can predict the effect of precaution control measures on future community mobility with minimum loss. The mean absolute error over all countries in the study is 5.3. For Egypt and Saudi Arabia, the model achieved an MAE loss of 4.6 and 3.7 consecutively.

Due to the fact that the autocorrelation of time series of passenger demand under normal conditions is, as a rule, practically undeveloped, traditional forecasting methods based on taking into account autocorrelation dependences are not effective enough. The article proposes a direct accounting of the main factor affecting the accuracy of forecasting, namely the factor of seasonal heterogeneity of demand. This accounting is made on the basis of polynomial regression for the time dependence of demand. A specific design example demonstrates the comparative advantages of this approach to assessing the forecast of demand for rail transport.The regression approach is applied to the weekly averaged demand metrics for the time domain, where these metrics are considered known from the sales history. If there is a weekly demand heterogeneity in the forecast zone, an algorithm is proposed to restore such heterogeneity from the initial data.The forecast accuracy based on the proposed method is compared with the results achieved on the basis of the ARIMA model, which reveals, according to preliminary estimates, fairly high accuracy parameters. It is shown on the calculated examples that for the series of demand, which can be considered typical for the sphere of passenger traffic, the regression approach gives the forecast accuracy higher than the ARIMA model. The reasons are considered, due to which, for typical series of passenger demand, the regression approach can be considered as more promising than methods that include taking into account autocorrelation.

Short-term load forecasting (STLF) is critical for the energy industry. Accurate predictions of future electricity demand are necessary to ensure power systems’ reliable and efficient operation. Various STLF models have been proposed in recent years, each with strengths and weaknesses. This paper comprehensively reviews some STLF models, including time series, artificial neural networks (ANNs), regression-based, and hybrid models. It first introduces the fundamental concepts and challenges of STLF, then discusses each model class’s main features and assumptions. The paper compares the models in terms of their accuracy, robustness, computational efficiency, scalability, and adaptability and identifies each approach’s advantages and limitations. Although this study suggests that ANNs and hybrid models may be the most promising ways to achieve accurate and reliable STLF, additional research is required to handle multiple input features, manage massive data sets, and adjust to shifting energy conditions.

Relatively large deformations of the steel arch support in underground coal mines in the Republic of Serbia present one of the main problems for achieving the planned production of coal. Monitoring of the critical sections of the steel arch support in the underground roadways is necessary to gather quality data for the development of a forecasting model. With a new generation of 3D laser scanners that can be used in potentially explosive environments (ATEX), deformation monitoring is facilitated, while the process of collecting precise data is much shorter. In this paper, we used a combination of grey and stochastic system theory combined with an autoregressive process for processing collected data and the development of a forecasting model of the deformations of the steel arch support. Forecasted data accuracy based on the positions of the markers placed along the internal rim of support construction shows high accuracy with MAPE of 0.2143%. The proposed model can successfully be used by mining engineers in underground coal mines for steel arch support deformations prediction, consequentially optimizing the maintenance plan of the underground roadways and achieving planned production.

The bootstrap procedure has emerged as a general framework to construct prediction intervals for future observations in autoregressive time series models. Such models with outlying data points are standard in real data applications, especially in the field of econometrics. These outlying data points tend to produce high forecast errors, which reduce the forecasting performances of the existing bootstrap prediction intervals calculated based on non-robust estimators. In the univariate and multivariate autoregressive time series, we propose a robust bootstrap algorithm for constructing prediction intervals and forecast regions. The proposed procedure is based on the weighted likelihood estimates and weighted residuals. Its finite sample properties are examined via a series of Monte Carlo studies and two empirical data examples. [ABSTRACT FROM AUTHOR]

This paper explores how human development responds to selected macroeconomic shocks in Nigeria. The study employed the Sen's capabilities approach as the analytical approach and posited that the level of education, health status, quality of investment, technology, and government fiscal and monetary policies are plausible determinants of human development. We used the Structural Vector Autoregression (SVAR) to estimate the responses of such selected shocks, which are inflation, interest rate, government capital expenditure, exchange rate, current account balance, and savings shocks. The Forecast Error Variance Decomposition (FEVD) and the Impulse Response (IR) showed that a fiscal policy shock is the major factor influencing human development outcomes. This finding underscored the important role government plays in enhancing the well-being of its citizens. Fiscal policy tools (such as investment in education, health, housing, and infrastructure) are essential for human development. In particular, the human development outcome is found to respond positively to shocks from real interest rates, which are felt significantly in the short run. We concluded that human development is negatively affected by a sudden decline in the federal government's capital budget expenditure. [ABSTRACT FROM AUTHOR]

We investigate the problem of short-term prediction of the free market price for electricity using various types of forecast models. A transition is made from considering traditional regression and autoregressive models to the proposed combined multivariate models, which also include the time trend and dummy variables. The combined forecast models have been constructed using dedicated statistical software packages. Comparison of the level of accuracy of the predicted values of the market electricity price obtained by different models has not revealed any advantages from the use of combined multivariate regression models. However, the use of the latter permits one to assess the influence of exogenous factors on the predicted variable and can be a fundamental advantage when choosing the forecast model type. [ABSTRACT FROM AUTHOR]

When introducing a new product or service to the market, a manufacturer or retailer is faced with the need to develop a promotion strategy. Taking into account the recent trends in e-commerce and social media marketing, it makes sense to evaluate the possibility of borrowing promotion strategies from producers of abstract, potentially monetized electronic content. The article considers the activity of advertising bots using the example of the social network Facebook. The paper carries out an autocorrelation analysis of the observation results and reveals the frequency of automated requests to the user by advertising bots. The authors construct an autoregressive model of the dynamics of the activity of advertising bots and verbalize Facebook’s strategy to increase traffic to the information space controlled by the social network.

In this article, we will cover various models for forecasting the stock price of global companies, namely the DCF model, with well-reasoned financial analysis and the ARIMA model, an integrated model of autoregression − moving average, as an econometric mechanism for point and interval forecasting. The main goal is to compare the obtained forecasting results and evaluate their real accuracy. The article is based on forecasting stock prices of two companies: Coca-Cola HBC AG (CCHGY) and Nestle S.A. (NSRGF). At the moment, it is not determined which approach is better for predicting the stock price − the analysis of financial indicators or the use of econometric data analysis methods.

The subject of research in the article are algorithms for fast calculation of autoregression coefficients in digital spectral analysis and estimation of the number of arithmetic operations required for their implementation. The aim of the article – comparative analysis of the speed of different algorithms for calculating the coefficients of autoregression as part of the algorithms of spectral analysis, including analysis of the complexity of their microcontroller implementation. Tasks to be solved: selection of spectral analysis methods suitable for diagnostics of technological equipment, analysis of methods for calculating autoregression coefficients and derivation of relations for estimating software complexity of algorithms and calculation of numerical estimates of addition and multiplication for some algorithms, adaptation of developed methods and estimates to microcontrollers. spectrum Applied methods: algorithm theory, Fourier transform, natural series, microcontroller programming. The results obtained: it is shown that spectral estimation methods based on Yul-Walker equations, which require the calculation of autoaggression coefficients, combine sufficient resolution and resistance to interference with acceptable implementation complexity. Estimates of the number of additions and multiplications for the Levinson, Durbin, and Trench algorithms are obtained, and their comparative analysis is performed. The calculation times for microcontroller arithmetic with fixed and floating points were count upon. Conclusions: When constructing spectrum analyzers for the diagnosis of technological equipment, it is advisable to use the Yul-Walker method. A comparison of Levinson, Durbin, and Trench algorithms for calculating autoregression coefficients showed that the Trench method requires a minimum number of additions, and the Durbin method requires a minimum number of multiplications. At microcontroller realization of spectrum analyzers, it is necessary to consider features of the arithmetic used by the controller. The Trench method is the fastest in the case of floating-point arithmetic and small-scale modeling. In other cases, Durbin's method is more effective.

Between subject variability in the spatial and spectral structure of oscillatory networks can be highly informative but poses a considerable analytic challenge. Here, we describe a data-driven modal decomposition of a multivariate autoregressive model that simultaneously identifies oscillations by their peak frequency, damping time and network structure. We use this decomposition to define a set of Spatio-Spectral Eigenmodes (SSEs) providing a parsimonious description of oscillatory networks. We show that the multivariate system transfer function can be rewritten in these modal coordinates, and that the full transfer function is a linear superposition of all modes in the decomposition. The modal transfer function is a linear summation and therefore allows for single oscillatory signals to be isolated and analysed in terms of their spectral content, spatial distribution and network structure. We validate the method on simulated data and explore the structure of whole brain oscillatory networks in eyes-open resting state MEG data from the Human Connectome Project. We are able to show a wide between participant variability in peak frequency and network structure of alpha oscillations and show a distinction between occipital ’high-frequency alpha’ and parietal ’low-frequency alpha’. The frequency difference between occipital and parietal alpha components is present within individual participants but is partially masked by larger between subject variability; a 10Hz oscillation may represent the high-frequency occipital component in one participant and the low-frequency parietal component in another. This rich characterisation of individual neural phenotypes has the potential to enhance analyses into the relationship between neural dynamics and a person’s behavioural, cognitive or clinical state.

Mobility is considered one of the main reasons for the COVID-19 spread. Predicting the effect of control measures on mobility is essential to apply effective decisions. This work proposes an AI-based model for mobility changes prediction. The proposed CNN-LSTM with Autoregression has achieved the best results compared to other investigated models. Results show that the proposed model can predict the effect of precaution control measures on future community mobility with minimum loss. The mean absolute error over all countries in the study is 5.3. For Egypt and Saudi Arabia, the model achieved an MAE loss of 4.6 and 3.7 consecutively. [ABSTRACT FROM AUTHOR]

Applicability of neural nets in time series forecasting has been considered and researched. For this, training of neural network on various time series with preliminary selection of optimal hyperparameters has been performed. Comparative analysis of received neural networking forecasting model with linear regression has been performed. Conditions, affecting on accuracy and stability of results of the neural network, have been revealed.

The aim of the article is to build a model for predicting behavior of an enterprise under conditions of its interaction with the external environment, involving the formation and support of the optimal trajectory of its behavior. Based on the analysis of research works, the category “enterprise behavior” is considered, and its relationship with the enterprise’s development is determined. There formed rules that constitute its methodological basis for constructing a prognostic model and allow taking into account various aspects of enterprise behavior in the system “enterprise – industry – national economy”. As a result of the research, a system of prediction models, containing the Cobb-Douglas production function, lag, autoregressive and vector autoregressive models is constructed. As part of this model, there investigated the following blocks: production; scientific and technological progress and innovation and marketing component; financial and labor components; type / style of the company in a competitive environment; external interaction. The proposed model for predicting the behavior of an enterprise in an unsteady environment, which has the form of a system of functional dependencies, allows carrying out comprehensive analysis of the enterprise’s internal and external capabilities. The prospect of further research in this area is the development of target guidelines for managing the behavior of an enterprise in a fluctuating market environment, with consideration for its real and potential resources and development opportunities of the industry and the national economy.

We introduce a hierarchical model to estimate haplotype effects based on phylogenetic relationships between haplotypes and their association with observed phenotypes. In a population there are many, but not all possible, distinct haplotypes and few observations per haplotype. Further, haplotype frequencies tend to vary substantially. Such data structure challenge estimation of haplotype effects. However, haplotypes often differ only due to few mutations, and leveraging similarities can improve the estimation of effects. We build on extensive literature and develop an autoregressive model of order one that models haplotype effects by leveraging phylogenetic relationships described with a directed acyclic graph. The phylogenetic relationships can be either in a form of a tree or a network, and we refer to the model as the haplotype network model. The model can be included as a component in a phenotype model to estimate associations between haplotypes and phenotypes. Our key contribution is that we obtain a sparse model, and by using hierarchical autoregression, the flow of information between similar haplotypes is estimated from the data. A simulation study shows that the hierarchical model can improve estimates of haplotype effects compared to an independent haplotype model, especially with few observations for a specific haplotype. We also compared it to a mutation model and observed comparable performance, though the haplotype model has the potential to capture background specific effects. We demonstrate the model with a study of mitochondrial haplotype effects on milk yield in cattle. We provide R code to fit the model with the INLA package.