Subjective Estimates Research Articles

Predicting virtual reality discomfort

Purpose: Virtual Reality (VR) headsets are becoming more and more popular and are now standard attractions in many places such as museums and fairs. Although the issues of VR induced cybersickness or eye strain are well known, as well as the associated risks factors, most studies have focused on reducing it or assessing this discomfort rather than predicting it. Since the negative experience of few users can have a strong impact on the product or an event's publicity the aim of the study was to develop a simple questionnaire that could help a user to rapidly and accurately self-assess personal risks of experiencing discomfort before using VR. Methods: 224 subjects (age 30.44±2.62 y.o.) participated to the study. The VR experience was 30 minutes long. During each session, 4 users participated simultaneously. The experience was conducted with HTC Vive. It consisted in being at the bottom of the ocean and observing surroundings. Users could see the other participants' avatars, move in a 12 m2 area and interact with the environment. The experience was designed to produce as little discomfort as possible. Participants filled out a questionnaire which included 11 questions about their personal information (age, gender, experience with VR, etc.), good binocular vision, need for glasses and use of their glasses during the VR session, tendencies to suffer from other conditions (such as motion sickness, migraines) and the level of fatigue before the experiment, designed to assess their susceptibility to cybersickness. The questionnaire also contained three questions through which subjects self-assessed the impact of the session on their level of visual fatigue, headache and nausea, the sum of which produced the subjective estimate of “VR discomfort” (VRD). 5-point Likert scale was used for the questions when possible. The data of 29 participants were excluded from the analysis due to incomplete data. Results: The correlation analysis showed that five questions' responses correlated with the VRD: sex (r = -.19, p = .02 (FDR corrected)), susceptibility to head aches and migraines (r = -.25, p = .002), susceptibility to motion sickness (r = -.18, p = .02), fatigue or a sickness before the session (r = -.26, p < .002), and the stereoscopic vision issues (r = .23, p = .004). A linear regression model of the discomfort with these five questions as predictors (F(5, 194) = 9.19, p < 0.001, R2 = 0.19) showed that only the level of fatigue (beta = .53, p < .001) reached statistical significance. Conclusion: Even though answers to five questions were found to correlate with VR induced discomfort, linear regression showed that only one of them (the level of fatigue) proved to be useful in prediction of the level of the discomfort. The results suggest that a tool whose purpose is to predict VR-induced discomfort can benefit from a combination of subjectve and objective measures. Conclusion: Even though answers to five questions were found to correlate with VR induced discomfort, linear regression showed that only one of them (the level of fatigue) proved to be useful in prediction of the level of the discomfort. The results suggest that a tool whose purpose is to predict VR-induced discomfort can benefit from a combination of subjectve and objective measures.

Impact of risk aversion, reactance proneness and risk appraisal on travel destination risk perception

The aim of the study is to investigate the motivational effects of tourist traits and risk appraisal on tourist destination risk perception. Risk appraisal involves subjective estimates of vulnerability to a threat and the threat’s consequential severity. Fear levels influence both of these elements of risk appraisal. Individual differences in reactance proneness and risk aversion are introduced into the study model to more fully account for differences in travel destination risk perceptions. The study design involves US adults, who have used their passports for international travel in the past 5 years. Travel risk assessments were studied for four destination sites: London, Tokyo, Kuala Lumpur and Istanbul. A general structural model is developed to test hypotheses about antecedents and consequents of risk appraisal and destination risk perception.

The burden of hypertension in Ecuador: a systematic review and meta-analysis.

Hypertension is a major risk factor of cardiovascular diseases, which occurrence has increased consistently worldwide. With this in mind, this review was designed to evaluate the prevalence of hypertension in Ecuador. We systematically searched publications in Medline, Cumulative Index of Nursing and Allied Health Literature, Cochrane Database, and Ibero-America electronic databases for articles published through September 2019 and reporting the prevalence of hypertension in Ecuador. Selected data were subjected to meta-analysis, and pooled prevalence and their 95% (95% CI) were calculated. Seventeen articles have been selected according to the inclusion/exclusion criteria of the study. The overall estimate of the pooled prevalence of hypertension was 35.8% (CI: 31.3-38.4). Most importantly, the prevalence of hypertension increased markedly with age and obesity. Pooled estimates for the four age subdivisions (<30 years), (≥30 and ≤50 years), (>50 and ≤60 years) and (>60 years) were 9.4% (CI: 7.3-11.5), 22.0% (CI: 19.0-25.0), 26.1% (22.2-30.0) and 48.7% (CI: 45.4-52.0), respectively. Moreover, the pooled estimate of subjects with BMI ≥ 30 kg/m2 (57.7%, CIs: 45.6-69.8) was markedly higher than those with BMI < 30 kg/m2 (30.4%, CI: 23.3-38.4). Although limited, available data reported higher rates of hypertension in Afro-Ecuadorians than other ethnicities. This study underlines a high prevalence of hypertension in adults nationwide, but mostly in elderly and obese individuals. The magnitude of this burden emphasizes the need for robust and targeted interventions to control hypertension, and ultimately reverse the trend of cardiovascular diseases.

Evaluation of Fatigue and Workload among Workers Conducting Complex Manual Assembly in Manufacturing

OCCUPATIONAL APPLICATIONS We conducted a study to evaluate fatigue and workload among workers performing complex assembly tasks. We investigate several predictors of fatigue, including subjective workload estimates, sleep duration, the shift being worked, and production levels. High levels of fatigue were reported in one-third of the shifts evaluated. The main predictors of high fatigue were workload estimates, working evening shifts, and baseline fatigue. Among the six dimensions of workload, only mental demand and frustration were predictors of high fatigue. Mental demand was also rated highest. Participants reported less than seven hours of sleep in 60% of the nights evaluated. These results suggest that managers and supervisors should consider cognitive workload as a key contributing factor to fatigue in complex manual assembly. Similarly, work schedule planning should consider shift duration, start times, and end times, because of the negative influence on fatigue and the potential disruptions on sleep among workers.

FEATURES OF ASSESSMENT OF THE INFLUENCE OF PROCESSES OF FORCED MIGRATION ON SOCIO-ECONOMIC DEVELOPMENT OF REGIONS

Forced migration processes, which started in Ukraine with the collapse of the Soviet Union, have taken new forms and reached their peak with the aggression of the Russian Federation in 2014. Since then, the problem of determining the impact of these processes on the development and security of the country's regions has been particularly relevant. In this regard, the article considers existing methods and international experience of a quantitative assessment of the impact of migration phenomena on the socio-economic development of regions. In addition, the author pays special attention to the identification and justification of the features inherent in internal migration processes, which directly impose restrictions on the quantitative assessment of the impact of these phenomena on the socio-economic development of regions and the obstacles researchers face in this field. Several critical features are determining the requirements for the choice of quantitative methods for assessing the impact of migration processes on regional socio-economic development, i.e., the complexity of establishing a direct relationship resulting from displacement is completely separated from the general societal changes; the impact of displacement will vary depending on several key factors; a high level of subjective judgements and estimations; the research results are sensitive to the level of initial data aggregation, their homogeneity and comparability; the lack of statistical information must be taken into account. A retrospective analysis of existing domestic and foreign approaches to overcome these problems has been carried out. Moreover, their advantages and disadvantages are pointed out. Based on the obtained results, it has been proved that the linear paradigm, which is superior to the classical economic and mathematical methods, is not always applicable. At the same time, the possibility of using modern non-linear approaches such as the theory of open systems, the theory of chaos has been proposed and justified. Furthermore, relevant conclusions have been made, and prospects for further research have been outlined.

Comparing Growth Rates Used in Discounted Cash Flow Valuations

Estimating growth in net cash flows is one of the key components in applying the discounted cash flow (DCF) method in valuing any company, reporting unit, or other business unit. This paper explains the underlying assumptions of the DCF method and demonstrates how to compare the most commonly used basis for estimating net cash flows (sometimes referred to as free cash flows), expected organic growth, to historic estimates of growth of the subject company and estimates of earning growth commonly prepared by security analysts.

Decomposing the Effects of Crowd-Wisdom Aggregators: The Bias-Information-Noise (BIN) Model

Aggregating predictions from multiple judges often yields more accurate predictions than relying on a single judge: the wisdom-of-the-crowd effect. But there is a wide range of aggregation methods, from one-size- fits-all techniques, such as simple averaging, prediction markets, and Bayesian aggregators to customized (supervised) techniques, such as weighted averaging, that require past performance data. This article applies a wide range of aggregation methods to subjective probability estimates from geopolitical forecasting tournaments. It uses the Bias-Information-Noise (BIN) model to disentangle three mechanisms by which aggregators improve accuracy: the tamping down of bias and noise and the extraction of valid information across forecasters. Simple averaging works almost entirely by reducing noise, whereas more complex techniques, like prediction markets and Bayesian aggregators, work via all three pathways: better signal extraction as well as noise and bias reduction. We close by exploring the utility of a BIN approach to the modular construction of aggregators.

Reproductive health and environment at the Russian Far East: objective conditions and subjective assessments

The quality of the living environment of the population as an external, objective factor, determines the level of comfort, affects its quality, health, reproduction and decision-making on migration. The quality of the environment is of a potential nature, serving as a basis for the socio-economic development of the region; it has a comparative nature in its original content and assumes a comparison of the specific indicators in spatial terms. Given the significant contrasts in environment at the Russian Far East (RFE), even small changes in natural and climatic conditions are crucial for determining quality of life of the population. Differences of environmental: natural, demographic, economic and social quality – were studied for regions at the southern part of the RFE. Sociological survey of women of reproductive age (17-45 years old) within both urban in rural areas in the Nanai District of Khabarovsk Krai, and Smidovichsky District of the Jewish Autonomous Region, gives a whole picture of their self-assessment of ecological, social and economic environment. Disproportions in the development, the main issues specific to individual areas, and spatial behavior of the residents are analyzed. Social and economic divergences are reflected in subjective estimates of native and non-indigenous women of reproductive age.

Correction of halitosis in chronic inflammatory diseases of the oropharynx in adults

To evaluate the effectiveness and safety of the probiotic strain Streptococcus salivarius K12 in the Bactoblis product in exacerbation of chronic inflammatory diseases of the oropharynx. 45 patients diagnosed with a diagnosis of exacerbation of chronic pharyngitis were studied, gastroesophageal reflux disease was found in 33 patients. After a microbiological testing, all patients were prescribed probiotic strain Streptococcus salivarius K12 in the amount of 1×109 colony-forming units (CFU) in the form of tablets for resorption as monotherapy for 14 days. The assessment of the therapy was based on physical examination data and on the subjective estimation of the clinical symptoms using a 10-point visual analog scale (VAS) before the start of the treatment and on the 5th and on the 7th day of the therapy. According to the microbiological analysis was revealed the growth of Staphylococcus aureus, Candida albicans, Pseudomonas aeruginosa, Streptococcus agalactiae, Streptococcus viridans which was seen within 103-105 CFU. A significant clinical progress was achieved for all three analyzed signs of diseases (the severity of pain when swallowing, a feeling of perspiration (foreign body) in the pharynx, halitosis), within the statistical significance between the 1st and the 7th day and the 7th and the 14th day of the surveillance. The pain severity was decreased from 5.69±0.39 points to 2.69±0.34 points on the 7th day and to 0.08±0.05 point on the 14th day from the start of the therapy, itchy throat (foreign body sensation) was relived from 6.88±0.23 points to 3.54±0.29 points on the 7th day and to 0.69±0.12 point on the 14th day of the therapy. In addition, there was a decline in the severity of halitosis from 6.16±0.31 points to 2.47±0.44 points on the 7th day and to 0.68±0.29 point on the 14th day of the therapy. Topical application of a drug containing a probiotic Streptococcus salivarius K12, in case of chronic inflammatory diseases of the oropharynx of various etiologies, showed satisfactory effectiveness in the regression of the main symptoms of the exacerbation of the inflammatory process, expressed through pain in the throat when swallowing, halitosis and the foreign body sensation in the oropharynx.

Gulaim Formation of Nouns with Diminutive Meaning in Modern Karakalpak Language

The article deals with ways and forms of expressing subjective estimation of diminutive terms of nouns in modern Karakalpak. In spite ofn some works on this theme, it remains insufficiently explored in modern Karakalpak language. One of the forms of expressing subjective estimation of diminutive terms of nouns is affixation. This study presentsn the formation of diminutive affixes of nouns– sha/ - she, shaq/ -shek, -shyq/-shik , - ek// -k inn modern Karakalpak language.n The paper first presents the characteristics of subjective evaluation and expressiveness ofn nouns. Next, the paper reviews the studies on subjective forms of the noun in Turkic linguistics. Then analysis of the diminutive suffixes of nouns inn modern Karakalpak language is given, concluding that, diminutive forms in the Karakalpak language are expressed by means of diminutive affixes. These include the affixes -sha/ - she, - shak/ - shek, - shyk/ - shik, -ek /-k and give a diminutive meaning to a person, object, animal names, etc. and create a new form.

Can Housing Property Necessarily Lead to Job Satisfaction? Based on the Observation of Urban Housing and Job Satisfaction

In the context of the current social stratification of housing wealth, a large number of researches have confirmed the positive impact of housing property rights on happiness. However, as a special commodity with both consumption and investment attributes, the impact of housing on modern urban families may not be limited to life feelings. Most of the current researches focus on the observation of overall well-being or life satisfaction, and pay little attention to workers’ working attitude.For urban families who rely on their occupational income to obtain class status and use housing investment to resist social risks, housing and employment issues are the core content of the middle class anxiety. This paper uses CLDS data to explore the impact of housing stratification on workers’ job satisfaction from many dimensions. This study shows the realistic mentality of families in various housing classes in terms of job satisfaction: For families with more than one housing property right, their “housing freedom” increases their freedom in working choices, so they maintain a high degree of satisfaction with their jobs; for families with single housing property right, the pressure of repaying the mortgage and the relative sense of deprivation that the rise of housing prices cannot be realized makes the real estate class show obvious anxiety and dissatisfaction in employment, especially in work income. The conclusion of this paper reveals a worrying fact: Although most urban workers have already achieved “Live in Peace”, high housing prices and high mortgages have restricted their ability to “Work in Contentment”, and housing differentiation has restrained and replaced the spirit of “work hard and work happy” of urban workers to a certain extent.Different from the existing research, this paper reveals the negative effect of housing property rights on the job satisfaction of people with single housing property right. There are two possible marginal contributions: First, most of the current researches focus on the overall subjective satisfaction or life satisfaction, while the research on the subjective employment attitude such as housing to workers’ job satisfaction is rarely involved. This study, from the perspectives of housing stratification and job satisfaction, depicts the anxiety problems of urban families, especially those with housing property rights, and reveals the employment anxiety that the single housing property right brings to the property families. This finding enriches the academic research on the impact of housing on subjective satisfaction and the job market from a micro perspective. Second, this paper not only conducts empirical exploration on the three psychological mechanisms of housing property rights affecting job satisfaction, but also uses subjective and objective index estimation results to compare work income, working hours and working environment to reveal the reasons for the employment anxiety of families with single housing property right. The reason is largely due to the dissatisfaction with work income. This idea is expected to enrich the related research based on purely subjective variables. The findings also help to broaden the academic community’s understanding of the anxiety of middle class, and have enlightening significance for the government to formulate housing and employment policies.

To a question оf formation of an integrated estimation of an economic subject’s competitiveness

To a question оf formation of an integrated estimation of an economic subject’s competitiveness

The Adjustment of Covariates in Cox’s Model under Case-Cohort Design

Case-cohort design is a biased sampling method. Due to its cost-effective and theoretical significance, this design has extensive application value in many large cohort studies. The case-cohort data includes a subcohort sampled randomly from the entire cohort and all the failed subjects outside the subcohort. In this paper, the adjustment for the distorted covariates is considered to case-cohort data in Cox’s model. According to the existing adjustable methods of distorted covariates for linear and nonlinear models, we propose estimating the distorting functions by nonparametrically regressing the distorted covariates on the distorting factors; then, the estimators for the parameters are obtained using the estimated covariates. The proof of consistency and being asymptotically normal is completed. For calculating the maximum likelihood estimates of the regression coefficients subject in Cox’s model, a minorization-maximization (MM) algorithm is developed. Simulation studies are performed to compare the estimations with the covariates undistorted, distorted, and adjusted to illustrate the proposed methods.

A Semi-Automated Method to Extract Green and Non-Photosynthetic Vegetation Cover from RGB Images in Mixed Grasslands.

Green (GV) and non-photosynthetic vegetation (NPV) cover are both important biophysical parameters for grassland research. The current methodology for cover estimation, including subjective visual estimation and digital image analysis, requires human intervention, lacks automation, batch processing capabilities and extraction accuracy. Therefore, this study proposed to develop a method to quantify both GV and standing dead matter (SDM) fraction cover from field-taken digital RGB images with semi-automated batch processing capabilities (i.e., written as a python script) for mixed grasslands with more complex background information including litter, moss, lichen, rocks and soil. The results show that the GV cover extracted by the method developed in this study is superior to that by subjective visual estimation based on the linear relation with normalized vegetation index (NDVI) calculated from field measured hyper-spectra (R2 = 0.846, p < 0.001 for GV cover estimated from RGB images; R2 = 0.711, p < 0.001 for subjective visual estimated GV cover). The results also show that the developed method has great potential to estimate SDM cover with limited effects of light colored understory components including litter, soil crust and bare soil. In addition, the results of this study indicate that subjective visual estimation tends to estimate higher cover for both GV and SDM compared to that estimated from RGB images.

Validity of Bioimpedance Spectroscopy in the Assessment of Total Body Water and Body Composition in Wrestlers and Untrained Subjects.

Bioimpedance spectroscopy (BIS) is an easy tool to assess hydration status and body composition. However, its validity in athletes remains controversial. We investigated the validity of BIS on total body water (TBW) and body composition estimation in Japanese wrestlers and untrained subjects. TBW of 49 young Japanese male subjects (31 untrained, 18 wrestlers) were assessed using the deuterium dilution method (DDM) and BIS. De Lorenzo’s and Moissl’s equations were employed in BIS for TBW estimation. To evaluate body composition, Siri’s 3-compartment model and published TBW/fat-free mass (FFM) ratio were applied in DDM and BIS, respectively. In untrained subjects, DDM and BIS with de Lorenzo’s equation showed consistent TBW estimates, whereas BIS with Moissl’s equation overestimated TBW (p < 0.001 vs. DDM). DDM and BIS with de Lorenzo’s equation estimated FFM and percent of fat mass consistently, whereas BIS with Moissl’s equation over-estimated and under-estimated them (p < 0.001 vs. DDM). In wrestlers, BIS with de Lorenzo’s and Moissl’s equations assessed TBW similarly with DDM. However, the Bland–Altman analysis revealed a proportional bias for TBW in BIS with de Lorenzo’s equation (r = 0.735, p < 0.001). Body composition assessed with BIS using both equations and DDM were not different. In conclusion, BIS with de Lorenzo’s equation accurately estimates the TBW and body composition in untrained subjects, whereas BIS with Moissl’s equation is more valid in wrestlers. Our results demonstrated the usefulness of BIS for assessing TBW and body composition in Japanese male wrestlers.

Prevalence of behavioral risk factors that cause contagion with COVID-19 among population in belarus: results obtained via cross-sectional study

Our research objects were behavioral risk factors that could cause contagion with coronavirus infection (hereinafter called COVID-19). Our research goal was to assess prevalence of behavioral risk factors that could cause contagion with COVID-19 among population in Belarus. The present work contains results obtained via online questioning that included 7,590 respondents and employed a specifically designed questionnaire covering most common behavioral risk factors of contagion with COVID-19. The factors were related to adherence to recommendations on physical and social distancing, use of personal protective equipment, and sticking to personal hygiene rules; the questionnaire also asked respondents to give a subjective estimate of their health and whether they had specific symptoms typical for COVID-19. Data analysis involved assessing prevalence of behavioral risk factors, and occurrence of a relation between specific factors and values of prevalence ratio. We determined prevalence of the most common behavioral risk factors and assessed to what extent risk factors influenced prevalence of subjective complaints by patients that they had symptoms typical for COVID-19. It was shown that certain behavioral risk factors authentically influenced prevalence of subjective symptoms of the disease. Subjective symptoms were more widely spread among respondents who regularly went to work as well as those whose family members regularly went to work or an educational establishment; among respondents who used public transport, went to shopping centers and catering facilities every day; among respondents who didn’t keep social distance, didn’t pay proper attention to personal hygiene, didn’t use antiseptics, and had a habit to touch their face with their hands; among smoking respondents; among respondents who attended mass events, family and corporate parties; and also respondents whose relatives, close friends, or colleagues had returned from abroad. Our research results can be used for carrying out information campaigns aimed at COVID-19 prevention; they can also give grounds for performing more profound studies on assessing contributions made by various behavioral factors into risks of contagion with COVID-19

Распространенность поведенческих факторов риска инфицирования COVID-19 среди населения республики Беларусь: результаты кросс-секционного исследования

Our research objects were behavioral risk factors that could cause contagion with coronavirus infection (hereinafter called COVID-19). Our research goal was to assess prevalence of behavioral risk factors that could cause contagion with COVID-19 among population in Belarus. The present work contains results obtained via online questioning that included 7,590 respondents and employed a specifically designed questionnaire covering most common behavioral risk factors of contagion with COVID-19. The factors were related to adherence to recommendations on physical and social distancing, use of personal protective equipment, and sticking to personal hygiene rules; the questionnaire also asked respondents to give a subjective estimate of their health and whether they had specific symptoms typical for COVID-19. Data analysis involved assessing prevalence of behavioral risk factors, and occurrence of a relation between specific factors and values of prevalence ratio. We determined prevalence of the most common behavioral risk factors and assessed to what extent risk factors influenced prevalence of subjective complaints by patients that they had symptoms typical for COVID-19. It was shown that certain behavioral risk factors authentically influenced prevalence of subjective symptoms of the disease. Subjective symptoms were more widely spread among respondents who regularly went to work as well as those whose family members regularly went to work or an educational establishment; among respondents who used public transport, went to shopping centers and catering facilities every day; among respondents who didn’t keep social distance, didn’t pay proper attention to personal hygiene, didn’t use antiseptics, and had a habit to touch their face with their hands; among smoking respondents; among respondents who attended mass events, family and corporate parties; and also respondents whose relatives, close friends, or colleagues had returned from abroad. Our research results can be used for carrying out information campaigns aimed at COVID-19 prevention; they can also give grounds for performing more profound studies on assessing contributions made by various behavioral factors into risks of contagion with COVID-19

Quantifying smartphone “use”: Choice of measurement impacts relationships between “usage” and health.

Problematic smartphone scales and duration estimates of use dominate research that considers the impact of smartphones on people and society. However, issues with conceptualization and subsequent measurement can obscure genuine associations between technology use and health. Here, we consider whether different ways of measuring “smartphone use,” notably through problematic smartphone use (PSU) scales, subjective estimates, or objective logs, lead to contrasting associations between mental and physical health. Across two samples including iPhone (n = 199) and Android (n = 46) users, we observed that measuring smartphone interactions with PSU scales produced larger associations between mental health when compared with subjective estimates or objective logs. Notably, the size of the relationship was fourfold in Study 1, and almost three times as large in Study 2, when relying on a PSU scale that measured smartphone “addiction” instead of objective use. Further, in regression models, only smartphone “addiction” scores predicted mental health outcomes, whereas objective logs or estimates were not significant predictors. We conclude that addressing people’s appraisals including worries about their technology usage is likely to have greater mental health benefits than reducing their overall smartphone use. Reducing general smartphone use should therefore not be a priority for public health interventions at this time.

Supplemental Material for Quantifying smartphone “use”: Choice of measurement impacts relationships between “usage” and health.

Problematic smartphone scales and duration estimates of use dominate research that considers the impact of smartphones on people and society. However, issues with conceptualization and subsequent measurement can obscure genuine associations between technology use and health. Here, we consider whether different ways of measuring “smartphone use,” notably through problematic smartphone use (PSU) scales, subjective estimates, or objective logs, lead to contrasting associations between mental and physical health. Across two samples including iPhone (n = 199) and Android (n = 46) users, we observed that measuring smartphone interactions with PSU scales produced larger associations between mental health when compared with subjective estimates or objective logs. Notably, the size of the relationship was fourfold in Study 1, and almost three times as large in Study 2, when relying on a PSU scale that measured smartphone “addiction” instead of objective use. Further, in regression models, only smartphone “addiction” scores predicted mental health outcomes, whereas objective logs or estimates were not significant predictors. We conclude that addressing people’s appraisals including worries about their technology usage is likely to have greater mental health benefits than reducing their overall smartphone use. Reducing general smartphone use should therefore not be a priority for public health interventions at this time.

КОМБІНОВАНА МЕТРИКА ВІЗУАЛЬНОЇ ЯКОСТІ ЗОБРАЖЕНЬ ДИСТАНЦІЙНОГО ЗОНДУВАННЯ НА ОСНОВІ НЕЙРОННОЇ МЕРЕЖІ

The wide distribution of images of remote sensing (RS) of the Earth in various application areas makes it important to ensure the high quality of such images, which is important to identify necessary information. The complexity of the systems and the impact of various physical processes cause a significant number of distortions that lead to image corruption and possible loss of information. The use of processing methods that should reduce the impact of such factors requires control of their work, which uses quantitative indicators of visual quality. The article considers the task of creating a combined visual quality metric based on an artificial neural network (ANN), which provides high accuracy of visual quality assessment and stability of work on the noise characteristic of the RS. The problem of analysis of RS distortions is considered and the approach of using the database of test images TID2013 for verification on typical RS distortions is offered. The analysis of well-known visual quality metrics and their suitability for the estimation of such images is carried out. According to its results, it was determined that the best metrics provide the accuracy of image quality assessment for RS tasks at the level of 0.93 according to Spearman's rank-order correlation coefficient with subjective estimates of the TID2013 image database. The joint application of existing quality metrics allows eliminating the shortcomings of each of them and increasing the overall efficiency, so the article considers the problems and defines the requirements for creating a combined metric involving a neural network. A method of limiting the number of involved quality metrics with the involvement of Lasso regularization is proposed, which allows determining the most informative features (quality metrics) and simplifying the procedure of selection and reduction of their number. A study was conducted on the influence of the metric selection criterion and quantity on the accuracy of the combined metric. The influence of the structure of the neural network, the number of hidden layers, and the number of neurons in them are also analyzed. Based on the obtained results, the best implementation of ANN was selected, which with the involvement of 16 visual quality metrics allows achieving the accuracy of visual quality assessment at 0.97 according to Spearman's correlation with subjective estimates of the TID2013 database.