Search Results (43)

Residential air conditioning systems are a major contributor to household electricity consumption in tropical regions, where environmental factors such as climate variability and particulate pollution (PM10) can further increase cooling demand and accelerate equipment degradation. This study proposes an Enhanced Deep Q-Network (Enhanced DQN) for energy-efficient and maintenance-aware control of residential split-type air conditioners under dynamic environmental conditions. The proposed method integrates several stability-oriented reinforcement learning mechanisms, including Double Q-learning, a dueling architecture, prioritized experience replay, multi-step returns, Bayesian-style regularization via Monte Carlo dropout, and entropy-aware exploration. The framework is evaluated through a two-stage process consisting of a diagnostic benchmark on LunarLander-v3 to assess learning stability, followed by a realistic 365-day simulation driven by Thai weather and PM10 data. Compared with a fixed 25 °C baseline, the proposed controller reduced annual electricity consumption from 5116.22 kWh to as low as 4440.03 kWh, corresponding to a saving of 13.22%. The learned policy also exhibited environmentally adaptive behavior under high PM10 conditions, indicating maintenance-aware characteristics. These findings demonstrate that reinforcement learning can provide robust, adaptive, and sustainable control strategies for residential cooling systems in tropical environments. Full article

This study evaluates the performance of six feature selection methods (BORUTA, LASSO, RFE, XGBoost, FSM, and SEV) and five predictive modelling techniques (ANN, MARS, RST, SRT, and SVM) for the spatial estimation of municipal waste accumulation rates across 79 districts in the Slovak Republic. Using a 2022 cross-sectional dataset comprising 45 socio-economic and demographic variables, the study focuses on spatial prediction for unseen districts rather than temporal forecasting. Feature selection results indicate that BORUTA, RFE, and XGBoost consistently identify key predictors, notably the share of three-person households, the density of transport and warehousing companies, and average monthly wages. Model robustness was ensured through repeated random sub-sampling (30 iterations, 70/30 split) and validated using the Friedman test with Nemenyi post hoc comparisons (α = 0.05). The highest accuracy was achieved by MARS and ANN models coupled with SEV selection (MAE ≈ 28–30 kg/(person·year), MAPE ≈ 6%, R² > 0.88), and by SVM with XGBoost (MAE ≈ 30 kg/(person·year), R² ≈ 0.90). Reducing the predictor set from ten to five resulted in only minor performance degradation (MAPE increase < 1 pp), confirming the effectiveness of dimensionality reduction. The proposed approach enables accurate, computationally efficient waste generation estimation, thereby supporting regional planning and evidence-based policy development. In a broader context, the findings contribute to the implementation of the European Green Deal and circular economy objectives by providing tools for spatially targeted waste management strategies, directly aligned with United Nations Sustainable Development Goal 11 (Sustainable Cities and Communities) and Goal 12 (Responsible Consumption and Production). Full article

Telework has expanded rapidly, yet its determinants and temporal dynamics remain insufficiently documented in developing countries. This study examines the evolution of telework in Brazil from 2022 to 2025 using machine learning models applied to nationally representative microdata from the Continuous National Household Sample Survey, based on approximately 210,000 households per reference period. A standardized pipeline was implemented across four time windows, including preprocessing, missing-data handling, class balancing via random under-sampling, feature encoding and normalization, and stratified data splitting with 5-fold cross-validation. Nine classification algorithms were evaluated and hyperparameter-tuned using ANOVA racing, with model performance assessed primarily through the ROC AUC metric. The results indicate consistently high discriminative performance across all analyzed periods (ROC AUC > 0.80). The temporal evaluation further reveals overlapping confidence intervals among the predictive models, indicating statistically comparable performance over time and no evidence of a universally dominant algorithm. Variable-importance analyses show that the set of the eight most relevant predictors remained stable, although their relative rankings changed, with gender increasing in importance in the most recent periods. Overall, telework in Brazil is jointly shaped by sociodemographic and occupational factors, highlighting its selective nature and the relevance of temporal monitoring to inform research and policy. Full article

Background/Objectives: People with mobility limitations face disproportionately high rates of chronic health conditions and demonstrate lower adherence to wellness interventions. Digital programs such as MENTOR offer accessible alternatives but often face high rates of attrition. This study applied machine learning (ML) methods to predict adherence to the eight-week MENTOR telewellness program and identify key predictors of participant attendance. Methods: Data were drawn from 1218 adults enrolled in MENTOR (2023–2024). Adherence was defined as the percentage of 40 sessions attended. Baseline demographic, socioeconomic, psychosocial, mindfulness, resilience, health status, and physical activity variables were included as predictors. Following preprocessing and imputation, 13 ML regression models were trained using an 80/20 train–test split. The best-performing model was identified using mean absolute error (MAE), followed by feature selection and SHAP interpretability analyses. Pairwise synergy analysis quantified interactions between top predictors. Results: Model performance was modest overall. Bayesian ridge regression achieved the best performance (MAE 20.98; RMSE 25.26; R² = 0.12). SHAP analyses revealed that education, race, emotional support, Area Deprivation Index, household size, mindfulness, life satisfaction, and disability onset were the strongest predictors of adherence. Higher emotional support, mindfulness, and life satisfaction were associated with greater adherence, while socioeconomic disadvantage predicted lower adherence. Synergy analyses showed the strongest predictive interactions between low education and psychosocial resources (emotional support and life satisfaction). Conclusions: Baseline characteristics alone modestly predicted adherence to a digital wellness program. However, psychosocial and socioeconomic factors emerged as meaningful predictors, underscoring the need for personalized support strategies to reduce dropout among participants with mobility limitations. Full article

With the escalating energy consumption of air conditioning systems worldwide, reducing such energy use has become a critical research priority. Evaporative cooling technology plays a significant role in reducing the energy consumption of existing air conditioning systems, especially by enhancing the heat exchange efficiency of condensers. This paper presents the design of an evaporative cooling household split-type air conditioner (SAC) that employs a submerged water method. By utilizing motor-driven rotation, the water distributor ensures full and even water distribution across a double-layer wet pad. Additionally, condensate water is recycled, and direct evaporative cooling (DEC) technology is applied to lower the condenser temperature, thereby achieving energy savings. Experiments were conducted under various meteorological conditions, comparing the performance of the split air conditioning system with the water distributor to that of the system without it. The comparative experiments revealed that the average air temperature differences at the inlet and outlet of the water distributor were 8.7 °C and 4.8 °C, respectively, with maximum air temperature differences reaching 12.3 °C and 8.2 °C, respectively. Compared to the system without the water distributor, the average condensing temperature at the condenser outlet of the system with the water distributor was reduced by 2.6 °C and 2.1 °C. Moreover, within an 11 h operation period, the average system coefficient of performance (COP) increased by 22.6% and 18.2%, respectively, and the energy savings reached 17.9% and 12.7%, respectively. Full article

Background: Household contacts of smear-positive tuberculosis (TB) patients face an elevated risk of infection and disease progression, particularly young children and individuals living in overcrowded households. Despite WHO recommendations for systematic contact screening and provision of TB preventive therapy (TPT), implementation remains suboptimal in high-burden rural areas. This study aimed to develop a practical framework for identifying and prioritizing high-risk families by examining demographic predictors, household clustering, and machine learning-based risk models. Methods: A total of 437 household contacts linked to smear-positive index cases were assessed and classified as high or low risk. Statistical analyses included descriptive measures, χ² tests, Z-tests for age-group differences, and multivariable logistic regression. Household-level vulnerability patterns were explored using network visualizations, clustered heatmaps, and risk-ranking charts. Three machine learning models, logistic regression, random forest, and gradient boosting, were trained using demographic and household variables with 5-fold cross-validation and an 80/20 hold-out test split. Model performance was evaluated using the AUROC, AUPRC, accuracy, F1-score, calibration curves, and decision curve analysis. Results: Of the 437 contacts, 290 (66.4%) were classified as high risk. A younger age was strongly associated with high-risk status (χ² = 16.61, p = 0.005), with children aged 0–4 years being significantly more likely to be in a high-risk category (Z = 2.706). Gender showed no significant association (p = 0.523). Logistic regression identified younger age (aOR = 2.41, 95% CI: 1.48–3.94) and larger household size (aOR = 1.12 per additional member, 95% CI: 1.01–1.25) as independent predictors of the outcome. Visual analytics revealed apparent clustering of high-risk individuals within “hotspot families,” enabling prioritization through composite risk scores. Gradient boosting achieved the strongest performance (AUROC = 0.65; AUPRC = 0.76), with acceptable calibration (Brier score = 0.21) and a positive net clinical benefit in the decision curve analysis. Conclusions: TB risk is highly clustered at the household level, with large families and young children carrying disproportionate vulnerability. Combining demographic risk assessment, household-level visualization, and predictive modeling provides a practical, data-driven approach to prioritizing households during contact investigation. These findings support the WHO’s family-centered strategy and underscore the need to strengthen clinical governance and community-engaged education to optimize TB prevention in resource-limited rural settings. Full article

Conventional commuting mode split models are characterized by inherent limitations in dynamic adaptability, primarily due to persistent dependence on periodic survey data with significant temporal gaps. A dominant transportation distance-based modeling framework for commuting mode choice is proposed, formalizing a generalized cost function. Through the application of random utility theory, probability density curves are generated to quantify mode-specific dominant distance ranges across three demographic groups: car-owning households, non-car households, and collective households. Empirical validation was conducted using Dongguan as a case study, with model parameters calibrated against 2015 resident travel survey data. Parameter updates are dynamically executed through the integration of big data sources (e.g., mobile signaling and LBS). Successful implementation has been achieved in maintaining Dongguan’s transportation models during the 2021 and 2023 iterations. Full article

Accurate electrical phase identification (PI) is essential for efficient grid management, yet existing research predominantly focuses on high-frequency smart meter data, not adequately addressing phase identification with low sampling rates using energy consumption data. This study addresses this gap by proposing a novel method that employs a fully connected neural network (FCNN) to predict household phases from energy consumption data. The research utilizes the IEEE European Low Voltage Testing Feeder dataset, which includes one-minute energy consumption readings for 55 households over a full day. The methodology involves data cleaning, preprocessing, and feature extraction through recursive feature elimination (RFE), along with splitting the data into training and testing sets. To enhance performance, training data are augmented using a generative adversarial network (GAN), achieving an accuracy of 91.81% via 10-fold cross-validation. Additional experiments assess the model’s performance across extended sampling intervals of 5, 10, 15, and 30 min. The proposed model demonstrates superior performance compared to existing classification, clustering, and AI methods, highlighting its robustness and adaptability to varying sampling durations and providing valuable insights for improving grid management strategies. Full article

The best practice for killing decapod crustaceans lacking a centralized ganglion has been debated for a century. Currently, there is a movement away from live boiling towards electrocution and mechanical splitting or spiking, which are efficient in the large commercial setting but may be unavailable and impractical for small decapods such as shrimp and prawn in the small-scale setting of, e.g., the household. Here, using carcasses of varying sizes of prawn, crayfish, lobster and green and brown crab, we used micro-CT imaging to measure surface area and sphericity in relation to body mass. Then, we measured heating profiles at the anterior ganglion and in the core of carcasses of the same species when exposed to standardized boiling regimes. We found a relationship with positive allometry between surface area and body mass for all species and a decrease in sphericity with mass. Heating times until proposed stunning (26 °C) and killing (44 °C) varied with body size and starting temperature and exceeded minutes for larger species. For a small species like prawn, times to stunning and killing by boiling are comparable to electrocution times and within the acceptable range compared to recreational killing of other sentient beings such as game mammals. Full article

Climate change, primarily driven by human activities such as burning fossil fuels, is causing significant long-term changes in temperature and weather patterns. To mitigate these impacts, there is an increased focus on renewable energy sources. However, optimizing power consumption through effective usage control and waste recycling also offers substantial potential for reducing energy demands. This study explores non-intrusive load monitoring (NILM) to estimate disaggregated energy consumption from a single household meter, leveraging advancements in deep learning such as convolutional neural networks. The study uses the UK-DALE dataset to extract and plot power consumption data from the main meter and identify five household appliances. Convolutional neural networks (CNNs) are trained with transfer learning using VGG16 and MobileNet. The models are validated, tested on split datasets, and combined using ensemble methods for improved performance. A new voting scheme for ensembles is proposed, named weighted average confidence voting (WeCV), and it is used to create combinations of the best 3 and 5 models and applied to NILM. The base models achieve up to 97% accuracy. The ensemble methods applying WeCV show an increased accuracy of 98%, surpassing previous state-of-the-art results. This study shows that CNNs with transfer learning effectively disaggregate household energy use, achieving high accuracy. Ensemble methods further improve performance, offering a promising approach for optimizing energy use and mitigating climate change. Full article

China’s agriculture is increasingly becoming more specialized. However, specialized production has disrupted traditional farming culture and may threaten sustainable mental health. This study takes Chinese farmers’ subjective happiness and agricultural production outsourcing as the research object, in an attempt to reveal the possible unhappy impacts of Chinese-style agricultural specialization represented by agricultural production outsourcing. First, we construct a theoretical framework of the relationship between agricultural production outsourcing and farmers’ subjective well-being. Secondly, based on more than 3800 household survey data collected by the Chinese Academy of Social Sciences in 2020, we use the classical econometrics and psychological analysis methods such as the Ordered Probit model and the instrumental variable estimation to conduct a rigorous impact assessment. The results show that for every doubling of agricultural outsourcing expenditure, the probability that farmers think they are very happy decreases by about 21%, and the probability that they think they are relatively happy decreases by about 9%. The groups affected by the negative psychological impact mainly include farmers growing rice and corn, farmers in hills and mountains, and farmers with small-scale operations. Further analysis shows that outsourcing risks, the weakening of farmers’ professional autonomy, and family split caused by agricultural outsourcing bring unhappiness, and the increase in income cannot offset the negative psychological effect of outsourcing. The findings of this study may bring inspiration to other countries with agricultural outsourcing markets and programs to improve the national subjective well-being. Full article

Addressing transport in cities requires a change in people’s behavior and a better distribution of different transport modes’ performances—a change in the modal split. This article focuses on detailed research on the transport behaviors of residents and their attitudes towards possible changes. We developed a questionnaire and distributed it online and physically. The data came from an anonymous survey, and basic statistical methods and a correlation analysis were applied to them. One of the research tasks was to find the correlations between individual characteristics. The analysis showed that the respondents’ education influenced their opinions about transport behavior. The results showed that the most common means of shared mobility was bicycles. The paper contains detailed results regarding the use of private cars and transport behavior in general. In addition, the study presents other significant findings regarding the average number of vehicles in households, the types of vehicles, and their usage patterns. The results of our study are useful for practical applications, because they describe traffic behavior patterns and can improve future decision making and transport planning. Full article

This paper aims to develop a machine-learning model based on a gradient-boosting algorithm to predict the energy-saving awareness of households using a questionnaire survey and 11-month energy data collected from more than 200 smart houses in Kitakyushu, Japan. We utilize the LightGBM (light gradient boosting machine) classifier to perform feature selection for the prediction. By using this approach, we demonstrate that the key features are the standard deviations of electricity purchased between 8 a.m. and 9 a.m. and electricity consumed between 7 p.m. and 9 p.m. Next, by using k-means clustering we split the households based on the obtained features into three groups. Finally, by using statistical hypothesis testing, we prove that these three groups have statistically distinct levels of energy-saving awareness. This model enables us to detect eco-friendly households from their energy data, which may support energy policymaking. Full article

The energy demand generated by fossil fuels is increasing day by day, and it has drastically increased after the COVID-19 pandemic as industries and household utilities rejuvenate. Renewable sources are thus becoming more essential as easily available, alternative methods of low-cost energy generation. Among these renewables, solar energy, i.e., solar power, is a promising energy source and can be used for solar-based H₂ evolution because H₂ technology is a leading source of eco-friendly electricity generation, and most of the worldwide efforts to develop this method involve heterogeneous catalysis for H₂ evolution via water splitting and its storage, i.e., using a fuel cell. In the current scenario, there is a need to develop a stable, recyclable, and reusable heterogeneous catalyst system, which is a great challenge. In the current study, we have focused on novel ferrite magnetic nanomaterials for recyclable and reusable robust photocatalysis. Moreover, discussions of the factors contributing to the photocatalytic hydrogen evolution, low-cost synthesis techniques, and prospects for making them ideal photocatalysts are uncommon in the literature. The study will impart possible approaches for the design and development of novel ferrite nanomaterials and their nanocomposites for H₂ generation in the forthcoming years. Full article

Despite the frequent changes in household composition in Sub-Saharan Africa, the literature on the household division process is sparse, with no evidence of its effect on food security. This paper addresses the topic in Malawi, where the fission process is evident and malnutrition is a severe problem. Using the Integrated Household Panel Dataset, this study applies the difference-in-difference model with the propensity score matching technique to compare matched groups of households that did and did not split between 2010 and 2013. The results suggest that coping strategies adopted by poor households and life course events determine household fission in Malawi, a process that benefits household food security in the short term. On average, the food consumption score is 3.74 units higher among households that split between 2010 and 2013 compared to the matched households that did not. However, the household division might have long-run adverse effects on food insecurity, especially for poor households due to the adoption of coping strategies that might compromise their human capital and income-generating activities. Therefore, this process warrants attention for the more accurate understanding, design, and evaluation of food security interventions. Full article