Regressive Model Research Articles

Drivers of the dynamics of the spread of cholera in the Democratic Republic of the Congo, 2000-2018: An eco-epidemiological study.

The dynamics of the spread of cholera epidemics in the Democratic Republic of the Congo (DRC), from east to west and within western DRC, have been extensively studied. However, the drivers of these spread processes remain unclear. We therefore sought to better understand the factors associated with these spread dynamics and their potential underlying mechanisms. In this eco-epidemiological study, we focused on the spread processes of cholera epidemics originating from the shores of Lake Kivu, involving the areas bordering Lake Kivu, the areas surrounding the lake areas, and the areas out of endemic eastern DRC (eastern and western non-endemic provinces). Over the period 2000-2018, we collected data on suspected cholera cases, and a set of several variables including types of conflicts, the number of internally displaced persons (IDPs), population density, transportation network density, and accessibility indicators. Using multivariate ordinal logistic regression models, we identified factors associated with the spread of cholera outside the endemic eastern DRC. We performed multivariate Vector Auto Regressive models to analyze potential underlying mechanisms involving the factors associated with these spread dynamics. Finally, we classified the affected health zones using hierarchical ascendant classification based on principal component analysis (PCA). The increase in the number of suspected cholera cases, the exacerbation of conflict events, and the number of IDPs in eastern endemic areas were associated with an increased risk of cholera spreading outside the endemic eastern provinces. We found that the increase in suspected cholera cases was influenced by the increase in battles at lag of 4 weeks, which were influenced by the violence against civilians with a 1-week lag. The violent conflict events influenced the increase in the number of IDPs 4 to 6 weeks later. Other influences and uni- or bidirectional causal links were observed between violent and non-violent conflicts, and between conflicts and IDPs. Hierarchical clustering on PCA identified three categories of affected health zones: densely populated urban areas with few but large and longer epidemics; moderately and accessible areas with more but small epidemics; less populated and less accessible areas with more and larger epidemics. Our findings argue for monitoring conflict dynamics to predict the risk of geographic expansion of cholera in the DRC. They also suggest areas where interventions should be appropriately focused to build their resilience to the disease.

Design and Testing of a Clamping Manipulator for Removing Abnormal Plants in Rape Breeding

Aiming at the time-consuming, laborious, and inefficient process of removing abnormal rape plants during breeding, combined with the agronomic requirements for planting rapeseed, a clamping manipulator was designed. This manipulator is mainly composed of hollow splints, grip-force sensors, connecting rods, cylinders and other components. Additionally, a removing test platform was built. Single-factor and Box-Behnken experiments were conducted. Taking the output air pressure, pulling angle and pulling speed as the test factors, the rape uprooted removal rate, rape removal breakage rate and pulling force were the test indicators. Mathematical models for multiple regression were established separately for each evaluation index, and analysis of variance was conducted. Objective optimization was performed using the Numerical component to obtain the optimal combination of operating parameters: output air pressure of 0.47 MPa, pulling angle of 68.8° and extraction speed of 8 cm/s. The field validation test showed that the uprooted removal rate was 83.33%, the removal breakage rate was 6.67% and the pulling force was 84.9 N at the output air pressure of 0.5 MPa, pulling angle of 70° and pulling speed of 8 cm/s. The validation test values are in good agreement with the parameter optimization values, indicating that the parameter optimization model is reasonable.

Does geopolitics trigger energy inflation in the European economic area? Evidence from a panel time-varying regression

PurposeThis paper aims to examine the reaction of energy inflation to geopolitical risks in the European Economic Area between 1990 and 2015.Design/methodology/approachThis study applies the nonparametric time-varying coefficient panel data model with fixed effects. In addition, to further reveal potential tail effects that may not have been captured by conditional mean-based regressions, the method of moments quantile regression was also used.FindingsThe findings of this study are as follows: first, as European countries get exposed to geopolitical tensions, it is expected that energy prices will surge. Second, the ability of geopolitical risk to trigger energy inflation in recent times is not as powerful as it used to be. Third, countries with a lower inflation rate, when exposed to geopolitical risks, experience smaller increases in energy inflation compared to countries with a higher inflation rate.Research limitations/implicationsThe findings of this study lead us to the conclusion that transitioning from nonrenewable to renewable energy use is one channel through which the sampled countries can battle the energy inflation, which geopolitical risks trigger. A sound macroeconomic policy for inflation control is a complementary channel through which the same goal can be achieved.Originality/valueGiven the increasing level of energy inflation and geopolitical risks in the world today, this study is an attempt to reveal the time-varying characteristics of the relationship between these variables in European countries using a nonparametric time-varying coefficient panel data model and method of moments quantile regression with fixed effects.

Conditionally Simulated Nonstationary Multi-point Earthquake Accelerograms Using Regressive Model

A new method is presented that simulates nonstationary multipoint earthquake accelerograms at local field points, when the observed ground motions are specified at several locations. This process effectively avoids the stochastic decomposition of the spectral matrix. In addition, it does not use the target spectrum and spatial coherence function to define the information of each point. First, the observed ground motions are reconstructed using an autoregressive model. Second, a new cross-regressive model is proposed based on the formulation of the auto-regressive model. The cross-regressive model can reconstruct different observed ground motions by using recordings from any nearby area. To consider the nonstationary characteristics and spatial coherence, the ground motions of unobserved points between two observed points can be generated using an interpolation algorithm. This new method simulates the ground motions of target points in the Chiba array using partially observed earthquake accelerograms. The simulated earthquake accelerograms satisfy the nonstationary characteristics and spatial coherence of the Chiba array. This study is promising for engineering applications and hazard analyses.

Analysis of COVID-19 cases and comorbidities using machine learning algorithms: A case study of the Limpopo Province, South Africa

This study examined the biological, social, and clinical risk factors for mortality in coronavirus of the year 2019 (COVID-19) hospitalised patients. The population of the study is prone to COVID-19, thus understanding the most common traits and comorbidities of people who were affected is crucial in reducing its consequences. In this study, four supervised machine learning algorithms were implemented and compared to predict the mortality rate based on the explanatory variables across the five districts of Limpopo Province in South Africa. The data was obtained from Limpopo Department of Health. Prediction about the chances of dying from COVID-19 disease was made using logistic regression, random forest, support vector machine, and decision tree algorithms on the dataset of 20,592 records with twenty-one attributes. Due to the imbalanced nature of the data, Random Over-Sampling Examples (ROSE) were employed to balance our data for more accurate classification effectively. The ROSE package provides functions to deal with binary classification problems in the presence of imbalanced classes. We used 70% of the data for training, while 30% was selected for testing the predictive algorithms. A technique called Step Akaike's Information Criterion (StepAIC) was deployed to reduce the insignificant variables from the full model of the logistic regression. According to the findings of the study, among the four algorithms tested, random forest had the highest recall rate for predicting mortality at roughly 79 percent compared to the other three algorithms. Accordingly, we conclude that random forest algorithm is appropriate for predicting the chances of patients dying from COVID-19 based on the attributes of the five districts of Limpopo Province. In terms of the features and their importance, a function called Variable Importance (VarImp) was used to check which of the attributes have predictive power on the outcome variable (discharged status). The findings revealed that age, ever ventilated, ever oxygenated, intensive ward upon admission, Waterberg district, and private facility type were among the risk factors that could be selected for the logistic regression model to predict mortality in hospitalised patients. This implies that special attention should be given to these identified variables. The random forest model is adequate to establish these factors since the findings reveal that a fairly considerable percentage of explained variation would correctly classify 79% of the cases. The novelty of conducting research on the analysis of COVID-19 cases and comorbidities using machine learning algorithms lies in the potential to uncover new insights and patterns that might not be immediately apparent through traditional statistical methods. Machine learning algorithms can quickly and accurately analyze large datasets and identify complex relationships between variables, which could provide valuable information for public health officials and policymakers.

REGRESSIVE ANALYSIS AND FORECAST OF STATE DEBT

Sophio Beridze 
 E-mail: sopho1982@hotmail.com 
 PhD Student, Batumi Shota Rustaveli State University 
 Batumi, Georgia
 https://orcid.org/0009-0002-7264-2873
 
 Lela Oniani 
 E-mail: lela.oniani@bsu.edu.ge 
 Associate Professor, Batumi Shota Rustaveli State University 
 Batumi, Georgia
 https://orcid.org/0000-0002-5960-4015
 Abstract: Actuality of the topic is caused by the role of the debt as financial instrument, as in the sphere of prosperity of the country, as well in its maintenance. State debt plays an important role in the macro-economic system of any Government. Formation of debt, .service and its covering, have a great influence on financial situation of the state, on the movement of money streams, investing climate, establishing international cooperation and its future development between the states. Actuality of the problem of external state debt was increased due to the fact that it is directly connected to the economic safety of the state.
 The goal of the article -originating/growth of state debt, despite of its burden is inevitable. If the level of income and employment more or less increase proportionally among with state debt, burden can be bearable and will not need concern. Percentage indicator of debt can not determine the burden of debt. Main determiner of the debt burden is: Annual capacity of debt service, reflection of state debt in economy, face of tax system. The aim of the article is to forecast the scales of factors, which influence on external state debt and implementation of main principles for effective management. In order to achieve goals which are set, there is a model to foresee scales of factors,which influence on state external debt.
 Methodology/approach: in order to learn and foresee existing condition of state debt, first of all,there were selected valid factors, which mostly effect on state external debt rather than other factors. Research took place by the building up regressive model, checking its quality and using forecasting models.
 Practical value/Implications: the practical significance of the paper is that its statements and conclusions are oriented on solving problems within the optimization of state external debt dynamic. Learning and researching about the influence of state debt on the stability of the state economy, will help conductors of economic policy to plan the right measures to avoid debt crisis. For this purpose:
 - We revealed valid factors on the stability of debt according to regressive analysis, among which the most important are the quality of debt service, deficiency of budget and level of employment.
 -We have made forecasts about the stability of state external debt and about the factors which influence them till the 2030.

Daily residential heat load prediction based on a hybrid model of signal processing, econometric model, and support vector regression

Daily residential heat load prediction based on a hybrid model of signal processing, econometric model, and support vector regression

The Relationship Between Fear Avoidance Belief and Threat Learning in Postoperative Patients After Lung Surgery: An Observational Study.

The role of fear-avoidance beliefs (FAB) in patients with chronic pain has been widely confirmed. However, few conclusions have been drawn about its role in postoperative patients. To explore the characteristics of FAB in postoperative patients after lung surgery as well as the effect of threat learning on FAB. Between May and September 2022, this study recruited 150 participants who had undergone thoracoscopic surgery. Variables such as age, gender, education, chronic pain, fear of pain, surgery method, pain intensity, FAB, cough, ambulation and threat learning were collected and subjected to correlation analysis and stepwise regression. The correlation analysis revealed that FAB was associated with age (r = -0.183, p < 0.05), gender (r = -0.256, p < 0.01), and preoperative FOP-9 (r = 0.400, p < 0.01). Postoperative variables such as pain intensity (r = 0.574, p < 0.01), initiation day of ambulation (r = 0.648, p < 0.01), total numbers of ambulation (r = -0.665, p < 0.01), and cough performance (r = -0.688, p < 0.01) were correlated with FAB. Furthermore, FAB was highly correlated with indicators of threat learning: direct (r = 0.556, p < 0.01), observation (r = 0.655, p < 0.01), and instruction (r = 0.671, p < 0.01). The highest variance explanation model of stepwise regression which explained 52.8% of the variance including instruction (B=1.751; p<0.01), direct (B=1.245; p<0.01), observation (B=0.768; p<0.01), age (B=-0.085; p<0.01), and surgery method (B=1.321; p<0.05). Patients commonly experience FAB after lung surgery, which can directly affect their recovery behaviors such as ambulation and active coughing. The formation of FAB is influenced by threat learning, which suggests that controlling threat learning is important in preventing postoperative FAB.

Financing Economic Growth and Development in Sub-Saharan Africa (1981–2021)

The aim of this paper is to explore the relationship between financing growth and development using panel data, Auto regressive distributed lag model (ARDL) analysis in 31 selected high income sub-Saharan African countries for the period of 40 years from 1981 to 2021. The sampled countries were based on their average GDP growth rate over the years under study. The study used ex post-facto and analytical research design. The Gross Domestic Per Capita Growth (GDPPCG) served as the dependent variable while Domestic Credit to Private Sector by Banks (DCPSB), Bank Liquidity Reserve to Bank Assets Ratio (BLR) and Gross Domestic Savings (GDS) were used as the independent variables. The inflation rate served as the control variable. Using the bound test proposed by Pesaran, Shin, and Smith in 2001 (and long &amp; short run causality approaches), the long-run association was estimated. The ARDL model's findings show that financial development has a favorable and considerable influence on economic growth in sub-Saharan African high-income nations. The study suggests implementing a financial inclusion approach to increase financial institution accessibility to households, particularly the unbanked in rural areas.

Design and Parameter Optimization of Variable Speed Reel for Oilseed Rape Combine Harvester

A variable speed anti-tangling reel mechanism was designed to address the problems of tangling, hanging and rewinding of the tassel wheel and the high paddling loss in the current Chinese rape combine harvester cutting table. The kinematic equations of the reel mechanism were developed, and the analysis showed that the speed in the entry stage is low and the speed in the exit stage is high, and the attitude of the reel teeth change with the rape plant movement during the whole paddling process. A single-factor test and a multi-factor regression orthogonal combination test were carried out using the cutting table loss rate of rape harvesting as the evaluation index. The main and secondary factors affecting the cutting table loss of the variable speed reel were obtained as the reel input speed, the machine travel speed and the ground angle of the frame. The optimal range of the input speed of the reel is from 25 r·min−1 to 31 r·min−1, the optimal range of the forward speed of the implement is 0.8 m·s−1~1 m·s−1, and the optimal range of the rack level angle is from −10°to 10°. A mathematical model of regression of cutter loss and the main influencing factors was established, with the coefficient of determination R2 = 0.9918, the relative error between the test value and the optimised value of the regression equation was 5.36%. The optimal combination of parameters for the variable speed reel was obtained with the lowest cutting table loss rate in rape harvesting as the optimization target: reel input speed 25 r·min−1, frame parallel to the ground and implement travel speed 0.7 m·s−1. Field validation tests and comparative tests of cutting table loss of the two reels were carried out. The test results show that the regression mathematical model of the cutting table loss is more accurate, and the cutting table loss is reduced by 13.9% with the variable speed reel compared to the cam-action reel, and there are no problems with the paddle teeth hanging and tangling during the paddling process.

Self-Stigma's Effect on Psychosocial Functioning Among People With Mental Illness.

Consequences of self-stigma exhibit a four-step regressive model from being aware of public stigma, to agreeing with it, to applying it to oneself, to resulting harm on the self. We hypothesize the relationship between self-stigma and psychosocial functioning is mediated by three constructs: the why try effect, stigma stress coping resources, and personal recovery. Two hundred eight people with depressive and bipolar disorders participated the study. Data partially supported the regressive model of self-stigma. Awareness was not found to be associated with other regressive stages. The model representing the path between self-stigma-harm and psychosocial functioning was significant and robust. The path was mediated by the why try effect and personal recovery. Findings echo the growing body of research attempting to describe outcomes of self-stigma, in this case, psychosocial functioning. Programs meant to erase self-stigma, and its effect on functioning should incorporate the why try effect and personal recovery as strategic ingredients.

The Impact of Financing Structure on Enterprise’ Overseas Direct Investment: A Case of A-share Listed Companies in China

This research analyzed the impact of financing structure on enterprises' overseas direct investment and its underlying mechanisms. It reviewed relevant literature and theories, used panel data of 1,725 Chinese A-share listed companies from 2000 to 2020, and employed the debt-to-equity ratio as a measure of financing structure. The study applied the Probit model for benchmark regression and conducted robustness tests using the Logit and negative binomial panel models. Additionally, it explored the influence mechanism through factors like innovation, research and development, productivity, and performed heterogeneity analysis and endogeneity tests. (1) The financing structure had an impact on enterprises' overseas direct investment. A higher proportion of equity financing in the structure positively contributed to the initiation of overseas investment projects and led to an expansion in scale. (2) The financing structure influenced enterprises' overseas direct investment by impacting factors such as innovation, research and development, and productivity. (3) The results of analyzing industry heterogeneity indicated that the financing structure of manufacturing enterprises had a limited impact on their overseas direct investment.

Trade Off and Pecking Order Capital Structure Theories in Tourism Sector in the Portuguese Central Region

The present study aims to identify the predominant theory in financing decisions, and which are the determinants of the capital structure of small and medium enterprises (SMEs) of the tourism sector in the Central Region of Portugal. The statistical method applied was the econometric model of linear regression, using a sample of 606 SMEs in the tourism sector in the Central Region, for a period of analysis between 2011 and 2018. The focus on the tourism sector is due to its importance in the Portuguese economy and to the existence of few studies, particularly in the Central Region. In the analysis of the determinants of capital structure decisions we used as explanatory variables profitability, asset tangibility, size, total liquidity, other non-debt tax shields, risk and age of SMEs. The results obtained suggest that the capital structure decisions follow more closely the assumptions of the Pecking Order theory but may also follow the assumptions of the Trade-Off theory. Therefore, this paper enhances that Trade-Off and Pecking Order Theories are not mutually exclusive in explaining the capital structure decisions of SMEs. We may conclude that SMEs firstly finance themselves with retained earnings, then use external financing and finally resort to capital increases. Keywords: determinants of capital structure, SMEs, tourism sector, pecking order theory, trade-off theory

Mathematical model for assessing the prognostic significance of 25(OH)D deficiency in the progression of diabetic retinopathy in type 2 diabetes patients

Background. In modern medicine, modeling of pathological processes is actively implementing in clinical endocrinology and ophthalmology. This process provides an opportunity to predict the risk of occurrence, course, prognosis and development of complications of type 2 diabetes mellitus (T2DM), in particular diabetic retinopathy (DR). Nowadays, special attention is paid to the course of DR against the background of vitamin D deficiency. But in the scientific literature, there are no mathematical models for assessing the risk of DM progression in patients with type 2 diabetes against the background of vitamin D deficiency. Aim of the study is to develop an adequate mathematical model for assessing the prognostic significance of 25(OH)D deficiency in the progression of diabetic retinopathy in patients with type 2 diabetes. Materials and methods. An open observational single-center one-stage selective study was conducted. It was approved by the Local Ethics Committee. Seventy-one patients (138 eyes) with T2DM and DR (men and women; mean age 61.9 ± 2.4 years; mean HbA1c 8.12 ± 0.91 %) were divided into 3 groups, based on the stage of DR (according to fundus instrumental examination). The inclusion of patients in groups with DR was carried out in accordance with the ETDRS protocol (2019). Statistical processing included ANOVA, MANOVA and regression analysis with the construction of logistic regression models. Results. A statistically significant (p &lt; 0.001) decrease in the risk of a high degree of DR was found with an increasing concentration of 25(OH)D in the blood plasma for each 1 ng/ml (odds ratio = 0.46 (0.32–0.67)). The pseudocorrelation index (Nagelkerke) R2 is 0.54, area under a receiver operating characteristic curve is 0.92 (95% confidence interval (CI) 0.85–0.97), which indicates the presence of a strong relationship between the risk of a high degree of DR and the concentration of 25(OH)D in the blood, gender and HbA1c level. The obtained multifactorial model was represented by the appropriate mathematical formula. The sensitivity (according to the Youden index) of the obtained logistic regression model is 84.4 % (95% CI 73.1–92.2), specificity is 92.3% (95% CI 74.9–99.1). Conclusions. An adequate mathematical model of logistic regression was developed to assess the prognostic significance of total vitamin D deficiency in the progression of DR in patients with T2DM. Its prognostic significance is 96.4 % (95% CI 87.7–99.0).

Predicting Parkinson's Disease Severity using Telemonitoring Data and Machine Learning Models: A Principal Component Analysis-based Approach for Remote Healthcare Services during COVID-19 Pandemic

Parkinson's disease (PD) is a progressive and chronic neurological condition that affects about 1% of the world's over-60 population. The COVID-19 pandemic has emphasized the significance of remote healthcare services, such as telemedicine, in managing chronic diseases such as PD. This research intends to construct machine learning (ML) models to predict PD severity utilizing vocal data derived from the UCI database for motor and total Unified Parkinson's disease rating scale (UPDRS) ratings. ML was used to study the association between voice vibration and PD, and PCA and ML models were utilized to minimize model complexity and compare the predictive performance of various statistical models for PD regression. The dataset included 5,875 medical voice records from 42 patients with early-stage PD who participated in a six-month clinical trial. The proposed PCA model simplified the model and achieved a root-mean-square error of 1.78 with an R-squared value of 0.95 for predicting the motor UPDRS and 1.78 with an R-squared value of 0.97 for predicting the total UPDRS. This work can give a framework for developing remote healthcare services for Parkinson's disease and other chronic conditions, which can be helpful during pandemics and other situations where access to in-person care is limited.

Knowledge, Practice and Self-Reported Confidence Level of Croatian Dentists in the Use of Local Anesthesia: A Cross-Sectional Study.

Objectives: To provide safe and effective local anesthesia, dentists must have knowledge of neuroanatomy, anesthesia agents, techniques, equipment, and proper use of local anesthetics. This study aims to explore the knowledge, practices, and confidence regarding local anesthetics and anesthetic techniques in dentistry. Material and Methods: The online cross-sectional questionnaire was conducted via social media, and yielded 441 responses from across the country (69.8% women and 30.2% men; 70.7% general dentists; and 29.3 specialists). The data collected included sociodemographic characteristics, knowledge, and practices pertaining to the usage of local anesthesia. The questionnaire also documents their self-assessed confidence level in applying different local anesthetic techniques and experiences with adverse reactions. The obtained data were processed by description and using a generalized linear model for regression. Results: The respondents had a median knowledge score of 6 out of a possible 14 points regarding local anesthetics in dental medicine, and their median self-confidence level in the successful application of various techniques of local anesthesia was 54 out of a maximum of 85 points. The results showed that a higher knowledge level was associated with the female gender (OR 1.83, CI 1.13-2.98, p = 0.014) and specialization in oral surgery (OR 7.04, CI 1.71-29.07, p = 0.007). In contrast, a lack of confidence in using various local anesthetic techniques was also associated with the female gender (OR 0.63, CI 0.41-0.99, p = 0.047) and specialization in orthodontics (OR 0.16, CI 0.03-0.88, p = 0.035). Of the respondents, 81.4% (n = 371) experienced a local complication, and 42.2% (n = 186) experienced a systemic complication during local anesthesia. The complications experienced cannot be associated with a lack of knowledge or self-confidence (p > 0.05). The majority of respondents (364 of the 441 total-82.5%) expressed interest in receiving further education on the topic of local anesthesia. Conclusions: The research results show that the dentists involved in the study have poor knowledge of local anesthetics and moderate self-reported confidence levels in using various local anesthetic techniques. Moreover, dentists' self-confidence in applying different techniques of local anesthesia is not related to their knowledge. Therefore, it would be necessary for dentists to undergo a continuing dental education program that enables them to enhance their skills and knowledge in local anesthesia.

Modelling Regional Sustainable Development in Ukrainian Crisis and War

The article investigates the impact of force majeure crisis factors that appeared in the Ukrainian economy as a result of the global recession, the events of 2014-2021: annexation of Crimea, temporary occupation of part of the industrial territories of Donetsk and Luhansk regions, military operations in Donbas, during the fight against pandemic (COVID-19) and war in 2022 on the stable development of regions. Based on the analysis of official indicators of the State Statistics Service of Ukraine, it was proved that the said factors create additional multiplier and acceleration effects that adversely affect the dynamics of the gross regional product in the crisis conditions. It has been determined that the result of these effects is the transformation of crisis signals from a proactive to an active phase. The construction of a heat map of GRP correlation indicators made it possible to determine the existence of a disbalance between the economic and social development of the regions. Building a model of linear regression, allowed us to draw conclusions about the existing disbalance of GRP regions during the crisis and war.

Drivers of WACR-Repo Rate Spread: An Empirical Analysis of India

The spread between the policy rate and operating target rate of the Reserve Bank of India (RBI) has consequences on the transmission of monetary policy signals. Using weekly data from 2011 to 2020 (504 observations), the study employs variants of General Auto Regressive Conditional Heteroskedastic model to comprehensively analyse the factors that drive this spread. Besides the factors retrieved from the literature, this study also gauges the impact of COVID-19 on the spread and its volatility. The results indicate that the spread is significantly impacted by its lag, volume of transactions in the counterpart markets, distribution pattern of the liquidity by the central bank, foreign market intervention, liquidity adjustment facility (LAF), currency in circulation and reserve requirement while market expectations and government cash balances are found to be non-significant. Besides, announcement effect of COVID and changes in key rates are found to be significant. The results of Exponential GARCH do not find significant asymmetry in response to positive and negative shocks on the spread. Volatility in the spread is comparatively more responsive to its lags than to the market shocks.

Road Traffic Noise Predictions by means of L10 Modelling with a Multilinear Regression Calibrated on Simulated Data

Estimation of road traffic noise is fundamental for the health of people living in urban areas, and it is usually assessed based on field-measured data. Real data may not always be available, anyway, and for this reason, predictive models play an important role in the evaluation and controlling of the noise impact. In this contribution, the authors present a multilinear regressive model calibrated on simulated noise levels instead that on real measured ones, correlating percentile noise levels to independent traffic variables. The model efficiency is then evaluated on two field measurement datasets by analyzing data statistics and error metrics. Results show that the model provides good results in terms of mean error (less than 1 dBA on average) even if slight underestimations and overestimations are present. The presented model, then, can be used to assess the impact of road traffic noise anytime field measurements are not available, or even predict it when designing new road infrastructures.

A method of mental disorder recognition based on visibility graph

The causes of mental disorders are complex, and early recognition and early intervention are recognized as effective way to avoid irreversible brain damage over time. The existing computer-aided recognition methods mostly focus on multimodal data fusion, ignoring the asynchronous acquisition problem of multimodal data. For this reason, this paper proposes a framework of mental disorder recognition based on visibility graph (VG) to solve the problem of asynchronous data acquisition. First, time series electroencephalograms (EEG) data are mapped to spatial visibility graph. Then, an improved auto regressive model is used to accurately calculate the temporal EEG data features, and reasonably select the spatial metric features by analyzing the spatiotemporal mapping relationship. Finally, on the basis of spatiotemporal information complementarity, different contribution coefficients are assigned to each spatiotemporal feature and to explore the maximum potential of feature so as to make decisions. The results of controlled experiments show that the method in this paper can effectively improve the recognition accuracy of mental disorders. Taking Alzheimer's disease and depression as examples, the highest recognition rates are 93.73% and 90.35%, respectively. In summary, the results of this paper provide an effective computer-aided tool for rapid clinical diagnosis of mental disorders.