Empirical Characteristics Research Articles

The roles and unexplored potential of policy experimentation in climate adaptation governance: A systematic literature review

AbstractPolicy experimentation has emerged globally as a novel governance approach to address complex socio‐environmental problems. In the climate adaptation literature, policy experiments that test technical and governance innovations on a small scale in real‐world conditions are increasingly utilized to explore new pathways for climate adaptation. However, there is a lack of empirical evidence on how policy experiments lead to transformative change in climate adaptation governance, particularly regarding their role as a change strategy. This systematic literature review aims to thoroughly investigate the topic by mapping the empirical characteristics of policy experiments, their role and their outcomes. An existing analytical framework was adapted to fulfill this objective by qualitatively and quantitatively analyzing 27 empirical papers. The findings reveal that policy experiments in climate adaptation often address multiple climate hazards, sectors and actors, yet they are spatially and temporally limited, being predominantly located in Europe. Moreover, the study highlights the transformative potential of policy experiments in climate adaptation governance, emphasizing their effectiveness in testing technical and governing innovations, as well as implementing adaptation policies. Policy experiments predominantly contribute to social learning rather than direct policy changes, requiring specific strategies to upscale the knowledge generated. We conclude the paper with a research agenda that stresses the need for more cumulative and comparative (post)assessments of climate adaptation experiments. This is important given the potential of policy experiments as governing approaches in the advancement of climate adaptation.

FROM CALENDAR TIME TO BUSINESS TIME: THE CASE OF COMMODITY MARKETS

We address the problem of modeling commodity forward curves, while preserving empirical features observed in commodity markets. By letting a commodity market to “ live” in the tempo of a business rather than calendar clock, we create a model with a rich but realistic set of features, such as stochastic volatility, stochastic rate of mean reversion and various shapes of forward curves such as backwardation and contango. The model, when applied to extensive historical datasets of crude oil and natural gas forward curves, shows a remarkably good fit to the observed futures prices, also in periods of high volatility and negative prices. The model is developed in such a way that it can be used for a wide variety of applications, ranging from exotic derivatives pricing to risk management of commodity portfolios.

SiRNADiscovery: a graph neural network for siRNA efficacy prediction via deep RNA sequence analysis.

The clinical adoption of small interfering RNAs (siRNAs) has prompted the development of various computational strategies for siRNA design, from traditional data analysis to advanced machine learning techniques. However, previous studies have inadequately considered the full complexity of the siRNA silencing mechanism, neglecting critical elements such as siRNA positioning on mRNA, RNA base-pairing probabilities, and RNA-AGO2 interactions, thereby limiting the insight and accuracy of existing models. Here, we introduce siRNADiscovery, a Graph Neural Network (GNN) framework that leverages both non-empirical and empirical rule-based features of siRNA and mRNA to effectively capture the complex dynamics of gene silencing. On multiple internal datasets, siRNADiscovery achieves state-of-the-art performance. Significantly, siRNADiscovery also outperforms existing methodologies in in vitro studies and on an externally validated dataset. Additionally, we develop a new data-splitting methodology that addresses the data leakage issue, a frequently overlooked problem in previous studies, ensuring the robustness and stability of our model under various experimental settings. Through rigorous testing, siRNADiscovery has demonstrated remarkable predictive accuracy and robustness, making significant contributions to the field of gene silencing. Furthermore, our approach to redefining data-splitting standards aims to set new benchmarks for future research in the domain of predictive biological modeling for siRNA.

Extracting actigraphy-based walking features with structured functional principal components

Objective. We extract walking features from raw accelerometry data while accounting for varying cadence and commonality of features among subjects. Walking is the most performed type of physical activity. Thus, we explore if an individual’s physical health is related to these walking features. Approach. We use data collected using ActiGraph GT3X+ devices (sampling rate = 80 Hz) as part of the developmental epidemiologic cohort study, I = 48, age = 78.7±5.7 years, 45.8% women. We apply structured functional principal component analysis (SFPCA) to extract features from walking signals on both, the subject-specific and the subject-spectrum-specific level of a fast-paced 400 m walk, an indicator of aerobic fitness in older adults. We also use the subject-specific level feature scores to study their associations with age and physical performance measures. Specifically, we transform the raw data into the frequency domain by applying local Fast Fourier Transform to obtain the walking spectra. SFPCA decomposes these spectra into easily interpretable walking features expressed as cadence and acceleration, which can be related to physical performance. Main results. We found that five subject-specific and 19 subject-spectrum-specific level features explained more than 85% of their respective level variation, thus significantly reducing the complexity of the data. Our results show that 54% of the total data variation arises at the subject-specific and 46% at the subject-spectrum-specific level. Moreover, we found that higher acceleration magnitude at the cadence was associated with younger age, lower BMI, faster average cadence and higher short physical performance battery scores. Lower acceleration magnitude at the cadence and higher acceleration magnitude at cadence multiples 2.5 and 3.5 are related to older age and higher blood pressure. Significance. SFPCA extracted subject-specific level empirical walking features which were meaningfully associated with several health indicators and younger age. Thus, an individual’s walking pattern could shed light on subclinical stages of somatic diseases.

A new empirical mass flow correlation and mass flow rate characteristics of R600a through novel rotary-baffle curved-channel electronic expansion valve

The novel rotary-baffle curved-channel electronic expansion valve (RBCC-EEV) has appeared in industry to replace a capillary tube as the variable expansion device in household refrigerators. However, due to the structure differences between the RBCC-EEV and the traditional orifice-type EEV, the previous empirical mass flow correlation inapplicable. In this paper, a new empirical correlation is proposed based on the structure and regulation principle of the novel RBCC-EEV, and the effects of different operating conditions on the mass flow rate of R600a flowing through two different RBCC-EEVs are experimentally investigated. The new empirical correlation introduces a centrifugal force coefficient and a variable length coefficient to represent the effect of asymmetric cavitation phenomenon and super-linear mass flow rate characteristics. The experimental results show a rise in the mass flow rate with increasing inlet pressure, inlet subcooling and opening ratio. Under the test range, the flow pattern of R600a flowing through the RBCC-EEV is chocked flow. Moreover, the proposed new empirical mass flow correlation agrees well with the experimental data. For 95.7 % of the prediction value, the relative deviation is below 15 %, while 89.0 % exhibit a relative deviation less than 10 %. The average deviation and standard deviation stand at 6.52 % and 4.56 %, respectively.

Profiling residential energy vulnerability: Bayesian-based spatial mapping of occupancy and building characteristics

With global trends in electrification, communities highly dependent on electricity are facing increasing challenges, particularly due to more frequent weather events, which lead to significant surges in electricity demand or result in blackouts. However, the impact is disproportionate across space and time, which raises an urgent need to comprehensively assess residential energy vulnerabilities to ensure energy security for households. Existing methodologies, whether large-scale regional assessments or community-based surveys, predominantly rely on static data. This reliance significantly limits their ability to capture the spatial and temporal dynamics of energy vulnerability, which is particularly important in the face of climate change. This study analyses residential energy vulnerability in the dimensions of social vulnerability, building resilience, and energy burden by innovatively linking occupancy patterns with the built environment through a Bayesian-based spatial mapping methodology. We applied this method through a case study in a Philadelphia census tract area identified for its high vulnerability based on FEMA's National Risk Index. By mapping occupancy with residential buildings, we simulated the energy consumption patterns of approximately 900 residential buildings. The simulations utilized DOE single-family energy prototypes, tailored to account for empirical occupancy and building features, to predict hourly energy consumption and assess indoor thermal comfort during power outages on days with extreme temperatures. The findings reveal disparities across different dimensions of energy vulnerability and illustrate the dynamic nature of energy vulnerability that fluctuates with daily activities. The study also highlights areas with low thermal resilience, suggesting a need for retrofitting older buildings to improve energy efficiency. The implications of this research extend beyond the built environment to the socioeconomic aspects of energy use, advocating for adaptive community planning and the development of resilient energy infrastructures. The results serve as a foundation for stakeholders to implement targeted interventions, prioritize retrofitting efforts, and support equitable access to energy resources, thereby enhancing urban sustainability and resilience.

Tail Risk Dynamics under Price-Limited Constraint: A Censored Autoregressive Conditional Fréchet Model.

This paper proposes a novel censored autoregressive conditional Fréchet (CAcF) model with a flexible evolution scheme for the time-varying parameters, which allows deciphering tail risk dynamics constrained by price limits from the viewpoints of different risk preferences. The proposed model can well accommodate many important empirical characteristics of financial data, such as heavy-tailedness, volatility clustering, extreme event clustering, and price limits. We then investigate tail risk dynamics via the CAcF model in the price-limited stock markets, taking entropic value at risk (EVaR) as a risk measurement. Our findings suggest that tail risk will be seriously underestimated in price-limited stock markets when the censored property of limit prices is ignored. Additionally, the evidence from the Chinese Taiwan stock market shows that widening price limits would lead to a decrease in the incidence of extreme events (hitting limit-down) but a significant increase in tail risk. Moreover, we find that investors with different risk preferences may make opposing decisions about an extreme event. In summary, the empirical results reveal the effectiveness of our model in interpreting and predicting time-varying tail behaviors in price-limited stock markets, providing a new tool for financial risk management.

Toward a third-generation rational choice theory: the multiple player approach to collective action problems

This paper aims to contribute to the development of a “third-generation” rational choice theory by introducing a Multiple Player Approach for analysing collective action problems. Drawing on the foundational first and second generation works of Olson (The logic of collective action, Cambridge University Press, Cambridge, 1965) and Ostrom (Scand Polit Stud 23(1):3–16), we introduce five player types that we believe capture essential empirical features of many real world collective action problems: Blind Riders, Tough Riders, Hard Riders, Easy Riders, and Low Riders. We consider the complex interaction and dynamics that unfold among them. The main novelty of the analysis is to draw attention to the need for active societal support to effectively empower and reward hard riders for resolving collective action problems, particularly when facing external shocks such as the Covid-19 pandemic, Brexit, and financial crises.

A generalized vector-field framework for mobility

Given the identification with travel demand and its relevance for transportation and urban planning, the estimation of trip flows between areas is a fundamental metric for human mobility. Previous models focus on flow intensity, disregarding the information provided by the local mobility orientation. A field-theoretic approach can overcome this issue and handle both intensity and direction at once. Here we propose a general vector-field representation starting from individuals’ trajectories valid for any type of mobility. We also show with simplified models how individuals’ choices determine the mesoscopic properties of the mobility field. Distance optimization in long displacements and random-like local exploration are necessary to reproduce empirical field features observed in Chinese logistic data and in New York City Foursquare check-ins. Our framework is able to capture hidden symmetries in mesoscopic urban mobility and opens the doors to the use of field theory in a wide spectrum of applications.

Mid-to-long Term Wind Power Forecasting Based on ARIMA-BP Combined Model

Background: Increasing the accuracy of the output power forecasting for wind power is helpful to the improvement of the reliability of power dispatching. Objective: This study aimed to improve the forecasting accuracy of mid-to-long term wind power. Methods: A mid-to-long term wind power forecasting based on ARIMA-BP combined model was proposed. The Empirical Mode Decomposition (EMD) was used to decompose the historical wind power series and obtain the Intrinsic Mode Function (IMF) and residual components, thereby obtaining more regular components. Then, the optimum feature set was obtained based on the minimum Redundancy Maximum Relevance (mRAR) to improve the prediction accuracy for feature extraction. After that, the high-frequency components were predicted using the Back Propagation (BP) neural network model, while the low-frequency components were predicted using the Autoregressive Integrated Moving Average model (ARIMA). Finally, the predicted components obtained were superimposed to deduce the final mid- and long-term wind power prediction results. Results: An analysis was conducted according to the actual data from a typical wind farm. After comparison, it was found that, after empirical mode decomposition and feature extraction analysis, the error of the intelligent combination algorithm based on the ARIMA-BP combined model was smaller than that using only the BP neural network or only the ARIMA. Conclusion: By means of actual data analysis, the effectiveness of the method proposed by the study for mid- and long-term wind power prediction was verified.

Superhomicide offenders: Nosology, empirical features, and linkages to sexual and multiple murder typologies.

The nosology for criminals who murder multiple victims is at once well-established and controversial, perhaps because theorists have largely segregated such offenders from the broader criminal population. The current study introduces the superhomicide offender, an individual convicted of at least five murders, to locate multiple homicide offenders within the criminological and epidemiological science pertaining to the most pathological offenders, and statistically place them with other conceptualizations of severe offenders at the 95th percentile of the offending distribution. Relative to other capital murderers, superhomicide offenders have lengthier criminal history, greater conviction history, and coextensive psychopathology characterized by psychopathy, sexual sadism, homicidal ideation, cluster A and B personality disorders, and major depressive disorder. Superhomicide offenders are profoundly psychopathic with 20 of the 39 offenders reaching the clinical threshold of 30 or more on the PCL-R, and 19 of the 39 are sexually sadistic. Regarding extant typologies of sexual and multiple homicide offenders, 15 are serial murderers, 17 are sexual homicide offenders, 17 are mass murderers, and 17 are spree murderers. Twenty-four of the 39 superhomicide offenders (61.5%) met criteria for multiple typologies, suggesting the new prototype can help unify the study of those who perpetrate multicide and embed them within criminological and epidemiological models that specify pathological antisocial outcomes.

Estimation and Prediction of Commodity Returns Using Long Memory Volatility Models

Modelling the volatility of commodity prices and creating more reliable models for estimating and forecasting commodity price returns are crucial. The body of research on statistical models that can fully reflect the empirical characteristics of commodity price returns is lacking. The main aim of this research was to develop a modelling framework that could be used to accurately estimate and forecast commodity price returns by combining long memory models with heavy-tailed distributions. This study employed dual hybrid long-memory generalised autoregressive conditionally heteroscedasticity (GARCH) models with heavy-tailed innovations, namely, the Student-t distribution (StD), skewed-Student-t distribution (SStD), and the generalised error distribution (GED). Based on the smallest forecasting metrics values for mean absolute error (MAE) and mean squared error (MSE) values, the best performing LM-GARCH-type model for lithium is the ARFIMA (1, o, 1)-FIAPARCH (1, ξ, 1) with normal innovations. For tobacco, the best model is ARFIMA (1, o, 1)-FIGARCH (1, ξ, 1) with SStD innovations. The robust performing model for gold is the ARFIMA (1, o, 1)-FIGARCH (1, ξ, 1)-GED model. The best performing forecasting model for crude oil and cotton returns are the FIAPARCH 1,ξ, 1−SStD model and HYGARCH 1,ξ, 1−StD model, respectively. The results obtained from this study would be beneficial to those concerned with financial market modelling techniques, such as derivative pricing, risk management, asset allocation, and valuation.

Concept analysis of self-neglect in the elderly: a hybrid model.

Clarifying the concept of elder self-neglect. Researchers investigated the concept of elder self-neglect using a hybrid approach, including theoretical, fieldwork, and final analysis phases. After an extensive review of related literature to define the concept of self-neglect and describe its characteristics, the fieldwork phase was carried out to illustrate its empirical features. Accordingly, it led to the extraction of the elder self-neglect attributes from the first two phases. Elder self-neglect includes "subjective and objective high-risk behaviors pertinent to physical and spiritual health as well as restricted social interactions, disregarding the living environment, and a lack of compliance to personal hygiene routines that the elderly demonstrate deliberately or unintentionally. Various factors can contribute to such behaviors, including individual features, poor physical performance, elderly-oriented psychological disorders, financial challenges, detrimental stressors, unsuccessful social interactions, inaccessible supportive resources, inadequate educational resources, and inappropriate cultural norms. Consequently, such behaviors result in impaired physical and psychological health status, higher risk of misbehavior, poor quality of life, extra caregiving-treatment burden, and affected mental security in society." Given that elder self-neglect is considered a relatively unknown concept in Iran, the study findings can pave the way for future extensive research in the Iranian context by clarifying the concept. It can play a significant role in developing related tools to design more efficient interventions and improve the quality of nursing care services. The elder self-neglect concept can lead to numerous health-related disorders among the elderly in society. Nurses cannot deal with an unknown phenomenon without exploring and identifying its exact meaning. It is, therefore, imperative to illustrate the different dimensions of this concept to help create a deep understanding among the nurses and perform timely diagnosis and interventional procedures.

Discharge estimation in compound channels with converging and diverging floodplains using an optimised Gradient Boosting Algorithm

ABSTRACT River discharge estimation is vital for effective flood management and infrastructure planning. River systems consist of a main channel and floodplains, collectively forming a compound channel, posing challenges in discharge calculation, particularly when floodplains converge or diverge. In the present study, ML algorithms such as XGBoost, CatBoost, and LightGBM were developed to predict discharge in a compound channel. PSO algorithm is applied for optimization of hyperparameters of gradient boosting models, denoted as PSO-XGBoost, PSO-LightGBM, and PSO-CatBoost. ML model discharge predictions were validated with existing empirical models and feature importance was explored using SHAP and sensitivity analysis. Results show that all three gradient-boosting algorithms effectively predict discharge in compound channels and are further enhanced by application of PSO algorithm. The R2 values for XGBoost, PSO-XGBoost, CatBoost, and PSO-CatBoost exceed 0.95, whereas they are above 0.85 for LightBoost and PSO-LightBoost. PSO-CatBoost performance is better than other models based on findings of statistical performance parameters, uncertainty analysis, reliability index, and resilience index for prediction of discharge in a compound channel with converging and diverging flood plains. The findings of this study validate the suitability of the proposed models especially optimized with PSO is recommended for predicting discharge in a compound channel.

Fluctuation Analysis of Uterine Contractions in Term Pregnancies Using Electrohysterography Signals and Empirical Mode Decomposition-Based Multifractal Features

Investigating the fluctuations of uterine contractions is an indispensable diagnostic practice to evaluate the onset of labor. This work aims to differentiate the fluctuations associated with Term (gestation ≥ 37 weeks) pregnancies during varied gestational ages using electrohysterography (EHG) signals. The signals in the second and third trimesters are subjected to Multifractal-Empirical Mode Decomposition-based Detrended Fluctuation Analysis (MF-EMDDFA). Multifractal spectrum is estimated and features namely, Holder exponents ([Formula: see text], [Formula: see text]), broadness (BD), root slopes (LS, RS) and tangential slopes (TL, TR) are extracted. Machine learning methods, such as Naïve Bayes, adaptive boosting and random forest (RF) classifiers, are utilized to discriminate the contractions during different weeks of gestation. Results show that five multifractal features, namely [Formula: see text], [Formula: see text], BD, LS and TL, show significant differences between the considered gestational ages. An increase in regularity of the uterine contractions is observed as the gestational age increases. These features along with the RF classifier provide an accuracy, sensitivity, precision, recall and F1-score of greater than 98.30%. As the differentiation of uterine contractions during different weeks of gestation is vital to understanding the pregnancy progress, the proposed multifractal features could be used as potential biomarkers in clinical practices.

Switching Triple-Weight-SMOTE in Empirical Feature Space for Imbalanced and Incomplete Data

Most existing techniques to handle imbalanced data might be invalid in the presence of data missing since they are based on the assumption that the data is complete. To shorten such a gap, a novel synthetic minority oversampling technique (SMOTE), i.e., Non-negative latent factor analysis-incorporated and Switching triple-weight-SMOTE (NSS), is proposed. The main idea of NSS is 4-fold: 1) a Lagrange non-negative matrix factorization (LNMF) method is put forward to impute the missing values with a guaranteed non-negativity according to the original distribution owing to the consideration of the global feature information; 2) by mapping the complete data after imputation into an empirical feature space (EFS), a more separable dataset is achieved, which rigidly maintains the same geometrical structure as the original data while efficiently reducing the redundant features to enhance model generalization and operational efficiency; 3) after fulfilling the fuzzy <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$c$</tex-math> </inline-formula> -means (FCM) clustering, the inter-cluster distance, the capacity of each minority cluster and its sparsity are comprehensively taken into account to develop a triple-weight assignment strategy, which contributes to allocate the number of synthetic samples to each cluster appropriately; 4) a switching oversampling strategy is provided in response to the clusters with different distributions (i.e., either Gaussian or uniform distribution). Moreover, a posterior is used to check the correctness of the synthetic samples. Finally, experiments on a real dataset and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$12$</tex-math> </inline-formula> public datasets show that the proposed NSS outperforms other <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$11$</tex-math> </inline-formula> state-of-art methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Data classification is an important computer task, which has been successfully used in many domains, including but not limited to, the medical domain, finance domain, and manufacturing domain. However, there are two big challenges when a classifier is to handle real-world data in the presence of imbalanced data and missing values. More specifically, the model performance is very likely to be degraded due to the missing information and the inclination of classifiers to the majority class. To surmount this problem, a natural idea is to use the LNMF model to obtain the desired recovery. Then, for the complete data after imputation, the empirical-feature-space-based switching triple-weight-SMOTE is applied to synthesize safe and correct data (i.e., lie solidly on the region of minority class) to achieve the balance. Such a working principle generates a novel NSS strategy. The proposed NSS strategy has the following obvious merits: 1) the imputation guarantees the similarity to the original dataset; and 2) new synthetic data are safely generated by taking adequate consideration of the information and distribution of datasets. Thus, the proposed NSS can greatly help improve the classification accuracy of real-world datasets.

Resource allocation modeling for autonomous prediction of plant cell phenotypes

Predicting the plant cell response in complex environmental conditions is a challenge in plant biology. Here we developed a resource allocation model of cellular and molecular scale for the leaf photosynthetic cell of Arabidopsis thaliana, based on the Resource Balance Analysis (RBA) constraint-based modeling framework. The RBA model contains the metabolic network and the major macromolecular processes involved in the plant cell growth and survival and localized in cellular compartments. We simulated the model for varying environmental conditions of temperature, irradiance, partial pressure of CO2 and O2, and compared RBA predictions to known resource distributions and quantitative phenotypic traits such as the relative growth rate, the C:N ratio, and finally to the empirical characteristics of CO2 fixation given by the well-established Farquhar model. In comparison to other standard constraint-based modeling methods like Flux Balance Analysis, the RBA model makes accurate quantitative predictions without the need for empirical constraints. Altogether, we show that RBA significantly improves the autonomous prediction of plant cell phenotypes in complex environmental conditions, and provides mechanistic links between the genotype and the phenotype of the plant cell.

Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes

Double-descent curves in neural networks describe the phenomenon that the generalisation error initially descends with increasing parameters, then grows after reaching an optimal number of parameters which is less than the number of data points, but then descends again in the overparameterized regime. In this paper, we use techniques from random matrix theory to characterize the spectral distribution of the empirical feature covariance matrix as a width-dependent perturbation of the spectrum of the neural network Gaussian process (NNGP) kernel, thus establishing a novel connection between the NNGP literature and the random matrix theory literature in the context of neural networks. Our analytical expressions allow us to explore the generalisation behavior of the corresponding kernel and GP regression. Furthermore, they offer a new interpretation of double-descent in terms of the discrepancy between the width-dependent empirical kernel and the width-independent NNGP kernel.

Effect of Financial Frictions on Monetary Policy Conduct: A Comparative Analysis of DSGE Models with and without Financial Frictions

In this study, we explored the impact of bank leverage and financial frictions on the transmission of real and financial shocks. Two new Keynesian dynamic stochastic general equilibrium (DSGE) models, with and without financial frictions, were employed in the context of the Tunisian economy. In the analysis, we considered three types of shocks—productivity, monetary, and adverse bank capital shocks. The findings reveal that, in the model with financial frictions, the response of macroeconomic and financial variables to demand and supply shocks was more pronounced than in the baseline model, where frictions primarily exist at the borrower level. In this study, we underscored the significance of financial shocks, particularly negative bank capital shocks, in triggering substantial macroeconomic and financial fluctuations, especially when banks operate with higher leverage ratios. Additionally, the inclusion of financial frictions in the DSGE model enhanced its ability to capture the empirical features of real and financial shocks, providing valuable insights for effective monetary policymaking. The results provide foundational insights for Tunisian policymakers to assess the impact of financial frictions in the context of the Tunisian economy. This is significant for the Central Bank of Tunisia, which has not yet adopted a specific DSGE model. Therefore, through our analysis, we determined the amplificatory role of financial frictions in the dynamics of macroeconomic and financial variables in Tunisia and examined the main transmission channels of shock propagation.

Detection of Coronary Artery Disease Based on Clinical Phonocardiogram and Multiscale Attention Convolutional Compression Network.

Heart sound is an important physiological signal that contains rich pathological information related with coronary stenosis. Thus, some machine learning methods are developed to detect coronary artery disease (CAD) based on phonocardiogram (PCG). However, current methods lack sufficient clinical dataset and fail to achieve efficient feature utilization. Besides, the methods require complex processing steps including empirical feature extraction and classifier design. To achieve efficient CAD detection, we propose the multiscale attention convolutional compression network (MACCN) based on clinical PCG dataset. Firstly, PCG dataset including 102 CAD subjects and 82 non-CAD subjects was established. Then, a multiscale convolution structure was developed to catch comprehensive heart sound features and a channel attention module was developed to enhance key features in multiscale attention convolutional block (MACB). Finally, a separate downsampling block was proposed to reduce feature losses. MACCN combining the blocks can automatically extract features without empirical and manual feature selection. It obtains good classification results with accuracy 93.43%, sensitivity 93.44%, precision 93.48%, and F1 score 93.42%. The study implies that MACCN performs effective PCG feature mining aiming for CAD detection. Further, it integrates feature extraction and classification and provides a simplified PCG processing case.