Correlation Model Research Articles

Loneliness, Psychological Well-being, Depression, and Social Participation in the Older Persons: Rural and Urban Differences.

The purpose of this study is to compare the loneliness, psychological well- being, depression, and social participation of elderly people living in Turkish society between rural and urban areas. The sample group of the study, in which a correlational survey model was used, consisted of 610 elderly adults. The study population consists of two groups: the first group consists of individuals over 65 years of age living in the city (Istanbul) (n= 291), and the second group consists of individuals over 65 years of age living in rural areas (rural areas of Ordu) (n= 319). Socio-demographic Information Form, Loneliness in the Elderly Scale, Geriatric Depression Scale, Psychological Well-Being in the Elderly Scale, and Social Inclusion Scale were applied online. Statistical analyses of the study were conducted using SPSS 27.00, and the Independent Samples t-test and ANOVA test were used. According to the findings of this study, statistically significant results were found in psychological well-being, social inclusion, social relations, loneliness and depression, and place of residence. It was observed that the social isolation and social acceptance levels of those living in urban areas were higher than those living in rural areas. Social, loneliness, and depression scores of those living in the village/town were found to be higher than those living in the city centre. Furthermore, the social relationship scores of those living in the village/town were found to be higher than those living in the city centre. The increasing elderly population worldwide has become an issue that requires global measures. Place of residence is one of the factors thought to affect older people's health and well- being. It is thought that the study data will contribute to new policies that will ensure the protection and promotion of elderly health and those working in this field. In addition, the study, which provides information about Turkish culture, will also enable intercultural comparisons.

Dietary creatine and carcinogenic biomarkers in adult population.

Background: Several reports suggest potential cytotoxic effects of creatine, possibly due to its role in facilitating the formation of food-borne chemical carcinogenic compounds. Aim: This cross-sectional study aims to investigate the relationship between creatine consumption and various carcinogenic biomarkers in blood and urine among individuals aged 18 years and older, utilizing data from the 2013-2014 National Health and Nutrition Examination Survey (NHANES). Methods: Daily creatine intake was assessed using the Dietary Data databases, which were compiled from individual in-person 24-h food recall interviews. The concentrations of carcinogenic compounds (heterocyclic amines, acrylamide, and formaldehyde) were extracted from NHANES 2013-2014 Laboratory Data database. Results: The final analysis included 1763 adult respondents, of whom 907 (51.4%) were female. The mean daily creatine intake was 0.83 ± 0.77 grams (95% CI, from 0.80 to 0.87). Regression analysis revealed no significant relationship between daily creatine intake and most carcinogenic biomarkers, except for a significant correlation (Model 1) between creatine intake and acrylamide levels (B = -3.999, ß = -0.088, p = 0.05). Model 2 (demographics) confirmed a significant relationship between daily creatine intake and circulating acrylamide (B = -3.490, ß = -0.077, p = 0.02), as well as for blood levels of glycidamide (B = -2.992, ß = -0.068, p = 0.05) and urinary 2-Amino-1-methyl-6-phenylimidazo[4,5-b]pyridine (B = 0.190, ß = 0.088, p = 0.03). However, no correlation between creatine consumption and any carcinogenic biomarkers remained significant after adjusting for nutritional factors (Model 3) (p > 0.05). Conclusion: In conclusion, the consumption of dietary creatine may be considered safe and not associated with increased levels of above carcinogens in the general population.

Application of machine learning for predictions of consecutive dependent data of type {[(a, b)->c]->d}

Objective: Machine learning techniques have emerged in response to the desire for automatic pattern detection withindatasets in fields such as statistics, mathematics, and data analytics. They allow for the extraction of relevant informationfrom datasets of significantly large volumes, providing the possibility of making predictions. This paper presents an application focused on decision trees, linear regression, and random forest regression algorithms to predict final data fromconsecutive dependent data of type {[(a, b) → c] → D}. Methodology: The study adopts a quantitative research design, which takes as input datasets based on interval data. It utilizes a correlational research model by implementing Python and its Scikit-Learn library, which includes various algorithms for prediction. Specifically, we compare the application of decision trees, linear regression, and random forest regression on the same set of datasets, but with a characteristic of dependency between them. Results: Upon application of the proposed model, it yields an estimated prediction score, which indicates the accuracy of the model concerning the data provided. Conclusions: The application of a complex algorithm does not inherently guarantee a higher rate of accuracy. Conversely, configuring the model correctly, training multiple trees, or adjusting parameter values can significantly enhance the obtained results

Investment Allowance and Financial Performance of Dt-Saccos in Nairobi County, Kenya

Purpose: The main objective of the study was to determine the effect of investment allowance on financial performance of DT-SACCOS in Nairobi County, Kenya. Methodology: This study utilized explanatory research design to investigate the influence of tax policies, including investment allowances, accelerated depreciation, and capital gains tax exemption, on the financial health of Deposit Taking SACCOs in Nairobi County, Kenya. The study used advanced estimation techniques, such as correlation and panel data regression models to estimate the relationship. Results: The study established that investment allowance has a significant negative impact on the financial performance of deposit-taking savings and credit cooperative societies (DT-SACCOs) in Nairobi County. Conclusion: Investment allowances, despite their negative association with financial performance, offer a valuable opportunity for DT-SACCOS to reduce taxable income and optimize investment in growth-enhancing assets. However, this should be balanced with careful planning to avoid potential adverse effects on financial performance.

Examining the relationship between social well-being levels of health personnel and their perception of gender roles: a university hospital example

ABSTRACT The purpose of this research is to examine the relationship between the social well-being of healthcare professionals and their perception of gender roles. The correlational screening model was used in the research. The study group consisted of 247 healthcare professionals working in a university hospital. As a data collection tool in the research, the Social Well-Being Scale-Healthcare Professionals Version, Gender Roles Attitude Scale, and Demographic Data Form were used. Unrelated Samples t-test, One-Way Analysis of Variance, Pearson Product Moment Correlation Coefficient, and Multiple Linear Regression Analysis techniques were used to analyze the data. It was determined that the social well-being average of healthcare workers was 121.43 ± 24.46 and the gender role average was 99.48 ± 9.70. It was observed that the average social well-being of healthcare professionals differed at a statistically significant level according to family structure, length of service in the current institution, alcohol use, gender roles, gender, and profession (p < .05). As a result of the research, it was determined that there is a positive relationship between social well-being and gender roles. It was determined that gender roles, gender, length of service in the current institution and alcohol use status significantly predict social well-being.

Correlation models for next-generation amplitude and cumulative intensity measures using artificial neural networks

Various next-generation intensity measures (IMs) have emerged in recent years. For instance, filtered incremental velocity, FIV3, was shown to be efficient in predicting the collapse of structures, or average spectral acceleration, Saavg, shown to be well-correlated with a wide range of response, from initiation of structural damage yielding to structural collapse. Different ground motion models (GMMs) are available to predict the probabilistic distribution of these IMs, given a set of seismological parameters. Nonetheless, a few key correlation models are still missing in the literature, which are elemental for a more holistic approach to ground motion record selection. These models are vital when performing seismic hazard analysis and ground motion record selection using state-of-the-art approaches like the conditional spectrum or generalized conditional intensity measure (GCIM) methods. This study uses a single machine-learning-based generalized ground motion model (GGMM) to estimate all the IMs. The model is based on the Next-Generation Attenuation (NGA)-West2 database and was utilized to quantify the correlations between the residuals. Correlations were calculated for intra- and inter-event residuals, but only those for total residuals are presented here, given their utility. Since the calculation of residuals comes from the same GMM and the same database of ground motions, this produces more consistent correlation coefficients between all IMs. To facilitate the usage of these correlation coefficients, predictive models of the empirical data were developed using machine-learning-based techniques, namely artificial neural networks (ANNs). It was found that FIV3 is strongly correlated with Sa(~1 s) and itself across all periods and has a weak negative correlation with duration at short periods and near-zero correlation for longer periods. Also, a stronger negative correlation between Sa and significant duration was found, compared with other prominent existing models. Direct correlation models between Sa and Saavg are also proposed.

Vortex-Induced Vibration Performance Analysis of Long-Span Sea-Crossing Bridges Using Unsupervised Clustering

Vortex-induced vibration is a type of wind-induced vibration occurring frequently in large-span sea-crossing bridges under relatively low wind speeds, posing a threat to the structural fatigue performance and driving comfort. Identifying the instantaneous occurrence moments of vortex-induced vibration is a prerequisite for establishing a data-driven prediction model for vortex-induced vibration, and it is of great significance for the monitoring and early warning of vortex-induced vibration performance in bridges. To automatically detect the occurrence moments of vortex-induced vibration and establish a correlation model between vortex-induced vibration amplitude and environmental factors, this study proposes a fuzzy C-means clustering-based classification method. In order to detect the occurrence moments of vortex-induced vibration more finely, only short-term or even instantaneous structural vibration indicators were selected and transformed for distribution as clustering features. The entire detection process could be carried out unsupervised, reducing the manual cost of obtaining vortex-induced vibration information from massive monitoring data. Finally, actual vortex-induced vibration test data from a certain overseas bridge was utilized to verify the feasibility of this method. Based on the classification results, the correlation between vortex-induced vibration amplitude and environmental variables was determined, providing valuable guidance for predicting vortex-induced vibration amplitudes.

The role of bullying perpetration and victimization in adolescents' perceptions of school climate and social media usage

AbstractPrevious research has reported a relationship between adolescents' perceptions of school climate and social media use. However, the underlying mechanisms associated with the relationship have yet to be fully explored. This study aimed to examine the role of peer bullying in the relationship under consideration. This cross‐sectional study applied a correlational research model to examine the perceptions of 718 adolescents aged 11–14. Data gathering entailed the School Climate Survey, Peer Bullying Self‐Report Form, and the Social Media Disorder Scale. Significant relationships between school climate, social media addiction, and peer bullying emerged from the gathered data. The study also found that peer bullying partially mediated the relationship between school climate and social media usage, both in terms of perpetrating bullying behavior and experiencing victimization. Specifically, 22.43% of the total effect of school climate on social media addiction was mediated through exposure to bullying perpetration, while 25.10% was mediated through experiencing victimization. A notable finding of this study is the role played by a perceived negative school climate in terms of increasing social media addiction; additionally, this increase may be partially mediated by exposure to peer bullying. A discussion of the results in light of the relevant literature is included, along with suggestions for future study.

Time–Frequency Co-Movement of South African Asset Markets: Evidence from an MGARCH-ADCC Wavelet Analysis

The growing prominence of generating a well-diversified portfolio by holding securities from multi-asset markets has, over the years, drawn criticism. Various financial market events have caused asset markets to co-move, especially in emerging markets, which reduces portfolio diversification and enhances return losses. Consequently, this study examines the time–frequency co-movement of multi-asset classes in South Africa by using the Multivariate Generalized Autoregressive Conditional Heteroscedastic–Asymmetrical Dynamic Conditional Correlation (MGARCH-DCC) model, Maximal Overlap Discrete Wavelet Transformation (MODWT), and the Continuous Wavelet Transform (WTC) for the period 2007 to 2024. The findings demonstrate that the equity–bond, equity–property, equity–gold, bond–property, bond–gold, and property–gold markets depict asymmetrical time-varying correlations. Moreover, correlation in these asset pairs varies at investment periods (short-term, medium-term, and long-term), with historical events such as the 2007/2008 Global Financial Crisis (GFC) and the COVID-19 pandemic causing these asset pairs to co-move at different investment periods, which reduces diversification properties. The findings suggest that South African multi-asset markets co-move, affecting the diversification properties of holding multi-asset classes in a portfolio at different investment periods. Consequently, investors should consider the holding periods of each asset market pair in a portfolio as they dictate the level of portfolio diversification. Investors should also remember that there are lead–lag relationships and risk transmission between asset market pairs, enhancing portfolio volatility. This study assists investors in making more informed investment decisions and identifying optimal entry or exit points within South African multi-asset markets.

The cost of obesity and related NCDs in Brazil: An analysis of hospital admissions, disability retirement benefits, and statutory sick pay

ObjectivesThis study analyses the prevalence of overweight/obesity in Brazil, and its costs regarding hospital admissions (HA), disability retirement benefits (DRB), and statutory sick pay (SSP) associated with obesity-related non-communicable diseases (NCDs). Study designTime-series study. MethodsThis study analyses data from the VIGITEL system (2010–2019) to calculate the body-mass index (BMI) of adult residents in Brazil's state capitals. Data on HA, DRB, and SSP were obtained from Brazil's SIH/SUS and AEPS Infologo systems. Pearson's correlation and linear regression models were applied. The study selected 23 diseases of the International Classification of Disease (ICDs) belonging to chapters C; E; I; and K. Cost values in BRL were deflated using IPCA. ResultsThe results showed a significant increase in overweight and obesity rates in Brazil, with BMI rising by 0.09 kg/m2 annually. Regression analysis revealed that each 1-point increase in the average BMI of the population is associated with an increase of 81,772 (BRL 237.51 million/year) new HA per year, 5541 (BRL 18.8 million/year) new DRB granted per year, and 42,360 (BRL 131 million/year) new SSP per year. Also, every 1 % increase in the share of the Brazilian population with obesity is associated with an increase of 16,973 (BRL 48.8 million/year) new HA per year, 1202 (BRL 3.97 million/year) new DRB granted per year, and 8686 (BRL 26.8 million/year) new SSP per year. Regressions for deflated values showed lower significance, suggesting a strong impact of inflation on health costs in Brazil. ConclusionsObesity prevalence in Brazil implies high direct and indirect costs for the Brazilian government, especially considering circulatory system diseases.

Comprehensive experimental assessment of biomass steam gasification with different types: correlation and multiple linear regression analysis with feedstock characteristics

In order to reveal the correlation between gasification behavior and products with feedstock characteristics, the steam gasification of 13 biomasses was investigated using a thermogravimetric analyzer and a fixed-bed reactor. Meanwhile, a multiple linear regression was used to construct correlation models. The results showed that cellulose content and crystallinity had the greatest influence on pyrolysis reactivity, which was reflected that the cellulose content was strongly positively correlated with the pyrolysis reactivity (Pmax = 0.77), while the lignin content and cellulose crystallinity were opposite. H/C, O/C ratios and SiO2 content had the greatest influence on gasification stage. O/C were strongly negatively correlated with gasification reactivity (Pmax = −0.81). But correlations of K and Ca contents were much less than that of Si. Husk has the best gasification performance than straw and woody with highest H2 and total gas yield of 28.26 and 68.93 mmol·g−1. H2 concentration and yield were significantly affected by the cellulose crystallinity and the fixed carbon content with positively correlation (P = 0.69–0.85). CH4 and CnHm were also influenced by them, but the trend was opposite to that of H2. Cellulose content, followed by SiO2 content mainly affected CO and CO2 and negatively correlated with CO while positively with CO2.

Исследование факторов, определяющих динамику и качество прогнозирования потребительских цен на рыбную продукцию

Using information of the Territorial body of the Federal State Statistics Service for the Primorsky Territory (Primorskstat), the dynamics of consumer price indices for fishery products in the country as a whole, the Far Eastern Federal District and the Primorsky Territory for 2002-2023, and the dynamics of prices by type of fish products in the Primorsky Territory for 2013-2023 were studied. It is concluded that the cost of fishery products has been steadily increasing throughout the analyzed period, and ahead of the inflation rate. The most intensive increase in the cost of processed fish, cut, more valuable in terms of nutritional characteristics. To determine the reasons for the constant growth, a correlation and regression analysis of the consumer price index for fishery products with other related indicators was carried out. Multicollinear factors were identified and excluded (consumer price index for food, per capita cash income of the population, fish consumption in the Primorsky Territory, industrial production index for the type of activity “Fishing and fish farming”). According to the criteria used in functional analysis, the multiple regression equation compiled using the remaining factors (inflation level and producer price index for fish products) was found to be untenable. As a result of excluding the factor “inflation level”, which had a less close connection with the performance indicator, a pair correlation model was obtained that describes the dependence of the consumer price index on the producer price index of fish products. The synthesized model is recognized as practically significant, and therefore can be used to obtain quantitative estimates of the consumer price index for fish products when forecasting.

Forecasting Carbon Dioxide Emission Regional Difference in China by Damping Fractional Grey Model

The emission of carbon dioxide is the main reason for many global warming problems. Although China has made tremendous efforts to reduce carbon emission, the space–time dynamics of the carbon emission trend is still imbalanced. To forecast CDED in China, the Dagum Gini coefficient was applied to measure regional CDED. Then, a grey correlation model was used to select potential influence factors and a wrapping method for selecting the optimal subset. DGMC is proposed to forecast CDED. The research results showed that the DGMC generalization performance is significantly superior to other models. The MAPE of DGMC in six cases are 1.18%, 1.11%, 0.66%, 1.13%, 1.27% and 0.51%, respectively. The RMSPEPR of DGMC in six cases are 1.08%, 1.21%, 0.97%, 1.36%, 1.41% and 0.57%, respectively. The RMSPEPO of DGMC in six cases are 1.29%, 0.69%, 0.02%, 0.58%, 0.78% and 0.32%, respectively. In future trends, the eastern carbon dioxide emission intraregional differences will decrease. Additionally, the intraregional differences in western and middle-region carbon dioxide emissions will expand. Interregional carbon emission difference will display a narrowing trend. Compared with the traditional grey model and ANN model, integrating the influence factor information significantly improved forecasting accuracy. The proposed model will present better balanced historical information and accurately forecast future trends. Finally, policy recommendations are proposed based on the research results.

Integrated spectral based monitoring, optimization and control of the combined ozonation and powdered activated carbon adsorption process to remove organic micropollutants from secondary effluent

In this study, an innovative approach for the integrated monitoring, optimization and control of the combined ozonation (O3) and powdered activated carbon (PAC) adsorption process is introduced making use of spectral surrogates (UVA254 and EEM-PARAFAC components). The combined O3-PAC process is designed to remove organic micropollutants (µP) from secondary effluent. Therefore, the removal of 6 µP with varying ozone reactivity was systematically studied in both O3 and PAC as stand-alone systems and in the combined O3-PAC system. For the latter, adsorption experiments were performed with µP spiked into ozonated secondary effluent (sequential system) and with µP spiked into the initial secondary effluent before ozonation (integrated system). In accordance with Swiss standards, the goal was to achieve 80% atrazine removal (as a model O3 recalcitrant compound) at optimized O3 and PAC doses. An ozone dose ranging from 0.45 to 0.65 mg O3/mg DOC was more cost-effective in promoting subsequent PAC adsorption (less than 40%), particularly at low PAC doses (1-2 mg PAC/mg (initial (DOC))). The classical ideal adsorbed solution theory (IAST) model could not be used to predict the subsequent PAC dose after ozonation in the integrated system. Therefore, correlation models were established between (i) the reduction of spectral surrogates during both O3 and PAC dosing and µP removal, (ii) the reduction of spectral surrogates during ozonation and the related PAC dose of the subsequent adsorption process and (iii) between the reduction of spectral surrogates during ozonation and the integrated process. Based on these correlation models, an online spectral control strategy was developed and implemented. Finally, the optimal dosing strategy for 80% atrazine removal was determined as 0.5 mg O3/mg DOC and 1.4 mg PAC/mg (initial) DOC.

AirNet: predictive machine learning model for air quality forecasting using web interface

Air is one of the most significant elements of the environment. The increasing global air pollution crisis poses an unavoidable threat to human health, environmental sustainability, ecosystems, and the earth's climate. Air pollution has been referred to as a silent killer due to its insidious nature. Its indirect impact on human health further underscores its dangerous effects. Early detection of air quality can potentially save millions of lives globally. A unique and transformative approach can harness the power of machine learning to combat air pollution. This research presents a manual and web-based automatic prediction system that provides real-time alerts on air quality status and can help prevent premature deaths, chronic diseases, and other health problems. Air pollutants, including carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2), and particulate matter (PM 2.5), are used in this study for feature analysis and extraction. The system utilizes publicly available data from 23,463 different cities worldwide. Data preprocessing was performed before feeding the data into the machine learning models for feature correlation and evaluation. The proposed research uses various machine learning models to predict air quality, including Random Forest (100%), Logistic Regression (79%), Decision Tree (100%), Support Vector Machine (93%), Linear SVC (98%), K-Nearest Neighbor (99%), and Multinomial Naïve Bayes (52%). A user-friendly Django-based web interface offers an accessible platform for users to monitor air quality in real-time, based on the two best-performing models: Random Forest and Decision Tree techniques.

Perceived Infant Discomfort Linked to Lower Maternal Oral Health Quality of Life: Results from a Cross-Sectional Study

Aim: We aimed to explore whether there is an association between maternal perceived infant discomfort due to suggestive gastrointestinal alterations and oral-health-related quality of life (OHRQoL) through a survey. Materials and Methods: The present study included two main phases involving Portuguese-speaking parents with full-term infants aged 2–12 weeks old who were not previously hospitalized in a neonatal nursery. First, the original French Infant Colic Questionnaire (ColiQ) was translated, cross-culturally adapted and validated to Portuguese (ColiQ-PT). Then, a survey was distributed, and included sociodemographics, the ColiQ-PT, an oral health value scale, OHRQoL, self-perceived periodontal status, and smoking and oral health habits. Data were analyzed through inferential, correlation and multivariate logistic models in this cross-sectional study. Results: The ColiQ-PT revealed reliability and validity. From a total of 421 responses, higher infant discomfort was correlated with less maternal professional dental care prioritization (ρ = −0.096, p &lt; 0.05). Self-perceived periodontitis correlated with all items of OHRQoL (p &lt; 0.001), all seven OHIP-14 domains, and with the physical (p &lt; 0.001), psychological (p = 0.006), and social (p = 0.011) super-domains. While the infant-related score was associated with baby age (p = 0.023) and physical pain (p = 0.040) related to OHRQoL, the parent score was associated with education (p = 0.005), unemployment (p = 0.035), and physical pain (p = 0.017). The total ColiQ-PT score was significantly associated with more deteriorated social disability related to maternal OHRQoL (ρ = −0.130, p &lt; 0.05). Conclusions: Perceived infant discomfort seems to be linked to maternal deteriorated OHRQoL. This finding highlights the importance of prioritizing oral health in postpartum care. Further research is needed to explore the mechanisms underlying this association and to develop targeted interventions.

Development of an expert system for technological support of required roughness when machining hardened steel parts on numerically controlled machines

This work addresses the problem of improving the surface quality of parts of rotation bodies, which are made of hardened steels, in the course of their machining on lathes with numerical program control. The research object was the surface roughness of parts. The methodology involved system analysis and synthesis, artificial neural networks, fuzzy logic, experiment, and processing of experimental results. A decomposition scheme for the expert system structure was developed, which can be used as the basis for formulating requirements to a future expert system for monitoring and prediction of roughness parameters. It was established that the models currently applied to describe the relationship between surface quality and the technological regimes used to ensure the technological level of roughness give a high error of over 20%. The possibility of using models that apply artificial intelligence and contain neural network blocks and decision-making devices based on fuzzy logic is substantiated. It is shown that such a combination makes it possible to customize the system for processing parts of a certain production range, as well as a more correct assessment of the onset of catastrophic wear of cutting tools. The neuro-fuzzy model was confirmed to have an error of less than 10%, which is significantly lower than when using spectral or correlation models. According to the testing results, the proposed expert system for monitoring and prediction of roughness parameters enables a 2.5-fold reduction in the scatter of roughness parameters under an increase in tool wear, compared to without its application. Thus, the proposed system makes it possible to assess the level of cutting tool wear more correctly and determine the onset of its limit state.

Development of a feed-forward audio-visual notification system for reducing motion sickness in autonomous vehicles

To mitigate motion sickness occurring in seat positions where driving conditions cannot be predicted due to the changed interior structure of autonomous vehicles, a feed-forward audio-visual notification system was developed. The design, implemented in the driving environment, provides information through ambient light and notifying sound by predicting signal processing information, including steering angle and turn signals, to address the audio-visual impact of changes in the vehicle's direction, speed, and acceleration with feed-forward alerts. The correlation model between psychological and physiological responses was developed through measurements such as MSQ, MISC, EEG, fNIRS, and HRV during driving, quantifying the degree of motion sickness and improvement situations. The effect of visual variation by ambient light and the customized effect of notifying sound were combined to compare and analyze the degree of motion sickness reduction following the installation of the notification system.

Air quality historical correlation model based on time series

Air quality is closely linked to human health and social development, making accurate air quality prediction highly significant. The Air Quality Index (AQI) is inherently a time series. However, most previous studies have overlooked its temporal features and have not thoroughly explored the relationship between pollutant emissions and air quality. To address this issue, this study establishes a historical correlation model for air quality based on a time series model—the Gaussian Hidden Markov Model (GHMM)—using industrial exhaust emissions and historical air quality data. Firstly, a traversal method is used to select the optimal number of hidden states for the GHMM. To optimize the traditional GHMM and reduce error accumulation in the prediction process, the Multi-day Weighted Matching method and the Fixed Training Set Length method are utilized. Both direct and indirect prediction modes are then used to predict the AQI in the Zhangdian District. Experimental results indicate that the improved GHMM with the indirect mode provides higher accuracy and more stable state estimation results (MAE = 13.59, RMSE = 17.59, mean forecasted value = 117.94). Finally, the air quality historical correlation model is integrated with the air quality meteorological correlation model from a previous study, further improving prediction accuracy (MAE = 11.59, RMSE = 14.87, mean forecasted value = 120.88). This study demonstrates that the GHMM’s strong ability to analyze temporal features significantly enhances the accuracy and stability of air quality predictions. The integration of the air quality historical correlation model with the air quality meteorological correlation model from a previous study leverages the strengths of each sub-model in handling different feature groups, leading to even more accurate predictions.

ADCMDES: Design of an augmented cross-domain collaborative recommendation model using novel distance metric and ensemble stratification

Collaborative recommendation involves leveraging information from one entity to suggest attributes of other entities through pattern analysis. These models are invaluable for understanding data behaviour’s impact on related entities. Researchers propose various pattern recognition and correlation models, employing distance metrics like Jaccard, Cosine, etc., to estimate correlations between user queries and recommendation datasets. However, these models become less efficient as dataset size increases due to exponential correlation estimation delays. To enhance scalability while retaining recommendation quality, a new approach is introduced: ADCMDES. This novel augmented cross-domain collaborative model employs a hybrid distance metric and ensemble stratification for dataset pruning. It operates semi-supervisedly, requiring information about the entities being collaborated upon. This data is used to cluster similar collaborative entities, producing a condensed cluster with greater relevancy to user queries. Utilizing word2vec, records are transformed into features for an ensemble classification engine. The resultant model categorizes user input, directing it to the most relevant cluster. Entries within this cluster are ranked using a hybrid metric amalgamating 18 distance measures, enhancing correlation between input queries and recommendations. In testing, ADCMDES exhibited 15% better accuracy, 8% better precision, 9% better recall, and 3% lower RMSE compared to standard models across datasets. While some delay is introduced due to ensemble classification and augmented feature pooling, this doesn't considerably affect long-term recommendation performance and can be mitigated through parallel processing and redundancy reduction techniques.