Heart Rate Modeling and Prediction Using Autoregressive Models and Deep Learning

Physiological time series are affected by many factors, making them highly nonlinear and nonstationary. As a consequence, heart rate time series are often considered difficult to predict and handle. However, heart rate behavior can indicate underlying cardiovascular and respiratory diseases as well as mood disorders. Given the importance of accurate modeling and reliable predictions of heart rate fluctuations for the prevention and control of certain diseases, it is paramount to identify models with the best performance in such tasks. The objectives of this study were to compare the results of three different forecasting models (Autoregressive Model, Long Short-Term Memory Network, and Convolutional Long Short-Term Memory Network) trained and tested on heart rate beats per minute data obtained from twelve heterogeneous participants and to identify the architecture with the best performance in terms of modeling and forecasting heart rate behavior. Heart rate beats per minute data were collected using a wearable device over a period of 10 days from twelve different participants who were heterogeneous in age, sex, medical history, and lifestyle behaviors. The goodness of the results produced by the models was measured using both the mean absolute error and the root mean square error as error metrics. Despite the three models showing similar performance, the Autoregressive Model gave the best results in all settings examined. For example, considering one of the participants, the Autoregressive Model gave a mean absolute error of 2.069 (compared to 2.173 of the Long Short-Term Memory Network and 2.138 of the Convolutional Long Short-Term Memory Network), achieving an improvement of 5.027% and 3.335%, respectively. Similar results can be observed for the other participants. The findings of the study suggest that regardless of an individual’s age, sex, and lifestyle behaviors, their heart rate largely depends on the pattern observed in the previous few minutes, suggesting that heart rate can be reasonably regarded as an autoregressive process. The findings also suggest that minute-by-minute heart rate prediction can be accurately performed using a linear model, at least in individuals without pathologies that cause heartbeat irregularities. The findings also suggest many possible applications for the Autoregressive Model, in principle in any context where minute-by-minute heart rate prediction is required (arrhythmia detection and analysis of the response to training, among others).

Effects of infill pattern and density on wear performance of FDM-printed acrylonitrile-butadiene-styrene parts

Acrylonitrile-butadiene-styrene test specimens were additively manufactured by fused deposition method to investigate the effects of infill pattern and density on wear rate, coefficient of friction, wear mechanisms, and microscopic wear characterization. The surface morphology of specimens was characterized using a scanning electron microscope. Under constant parameters of applied load, sliding speed, and sliding time, wear tests were carried out at room temperature. The study revealed that a grid pattern of high infill density and a honeycomb pattern of low infill density showed the lowest wear rate and lowest coefficient of friction compared to the rectilinear pattern. Infill pattern and density affected the wear rate behavior of specimens directly. Moreover, adhesion between additively manufactured layers along with surface texture affects the wear behavior and wear rate. Increasing infill density allowed poor cooling of previously built layers. Longer process time results in rough surfaces.

Well Performance Evaluation of Carbonate Reservoirs After a Novel Hybrid Volume Stimulation Treatment

A large proportion of gas and oil resources are trapped in carbonate reservoirs. Efficient development of these formations is crucial for world energy supply. Recently, a novel hybrid volume stimulation (HVS) technique has been proposed and enhanced carbonate reservoir production in the Bohai Bay Basin and the Ordos Basin of China (Cai et al., 2015; Chu, 2017). This technique involves three stages, including pad-fluid fracturing (primary fracture and fracture branch initiation), massive acid fracturing (acid etching and connection of natural and induced fractures), and proppant injection (conductivity maintenance). Compared with conventional acid fracturing, HVS generates a more complex fracture system by taking the advantage of both hydraulic fracturing and acid fracturing, mitigating high-temperature effects, and increasing the acid penetration distance. Currently, no existing models can predict the pressure and rate behavior of wells after HVS treatments due to the complex fracture geometry and the complicated flow pattern. This study presents a multi-region linear flow model to facilitate evaluating well performance of carbonate reservoirs after HVS and obtaining a better understanding of key factors that control well responses. The model incorporates the fundamental characteristics of the complex fracture system generated by HVS. The primary hydraulic fracture is characterized by two flow regions. One is for the propped primary fracture segment (region 1), while the other represents the unpropped but acid-etched primary fracture tip (region 2). The region adjacent to the primary fracture (region 3) denotes acid-etched fracture branches. Because the acid usually cannot fully penetrate the hydraulic-fracturing-induced branches, the fractal theory is employed to depict the properties of the small fracture branches beyond the acid-etched sections. Finally, the unstimulated reservoir is described by a dual-porosity region (region 4) with vug and matrix systems. Specifically, triple-porosity region 3 contains two possible flow scenarios: one is from vugs to matrices, to fracture branches, and to the primary fracture, while the other is from vugs to matrices, and to the primary fracture. Two weighting factors are utilized to describe the proportion of reservoir volume that is involved in the two fluid flow scenarios. These flow regions are coupled through flux and pressure continuity conditions. The degenerated form of this model is verified against a published analytical model. A good agreement has been achieved between the results of the two models. Analysis results show that four flow regimes can be identified in the log-log type curve. Compared with classical type curves of fractured wells, there is a distinctive fracture-branch-affected transient regime in the pressure derivative curve with a slope between one-half and unity. The HVS generated complex fracture system enhances well productivity from the inter-porosity flow regime to the late fracture-branch-affected transient regime. The impacts of various fracture and reservoir properties on pressure and rate behavior are also documented.

Exchange Rate Behavior of Plantation Subsector Farmers in North Kolaka Regency

The implementation of the research on the behavior of farmers exchange rate subsector plantations in North Kolaka District, conducted in the sub-district area that qualifies as a sample area in the researcher's perspective aims to see the exchange rate behavior of plantation subsector farmers in north Kolaka district, conducted in January-March 2021. The calculation of Farmer Exchange Rate is obtained from the comparison of the price index received by farmers against the price index paid by farmers using the survey method with the number of 340 respondents spread in North Kolaka Regency. The results showed that the behavior of the price received by farmers 110.23%, The Behavior of Prices Paid by Farmers 95.22%, and the exchange rate of farmers in the subsector of plantation crops in North Kolaka District in 2019-2020 115.81%.

Exchange Rate Behavior of Plantation Subsector Farmers in North Kolaka Regency

The implementation of the research on the behavior of farmers exchange rate subsector plantations in North Kolaka District, conducted in the sub-district area that qualifies as a sample area in the researcher's perspective aims to see the exchange rate behavior of plantation subsector farmers in north Kolaka district, conducted in January-March 2021. The calculation of Farmer Exchange Rate is obtained from the comparison of the price index received by farmers against the price index paid by farmers using the survey method with the number of 340 respondents spread in North Kolaka Regency. The results showed that the behavior of the price received by farmers 110.23%, The Behavior of Prices Paid by Farmers 95.22%, and the exchange rate of farmers in the subsector of plantation crops in North Kolaka District in 2019-2020 115.81%.

UNEMPLOYMENT HYSTERESIS IN MIDDLE-INCOME COUNTRIES

Business cycles pave the way for asymmetry in the unemployment rate behavior with rapid increases during recessions and slight decreases in expansions. It, in turn, may raise the non-accelerating inflation rate of unemployment and the cost in terms of inflation of any demand stimulus policy. The recent jump in unemployment worldwide due to the COVID-19 pandemic and the government’s stimulus package following it raises questions about the cost of such a decision. We use the smooth transition model (STR) to analyze unemployment dynamics on quarterly data over the last two decades for fifteen middle-income countries. Our results suggest the absence of hysteresis except for Bulgaria, Mexico, and Ukraine. Our policy recommendation for these countries is the necessity of labor market reforms, as hysteresis will considerably reduce any economic stimulus on unemployment.Keywords: Unemployment, hysteresis, STRJEL Classification: C10, J60