Lower RMSE Research Articles

Development of novel computational models based on artificial intelligence technique to predict the viscosity of ionic liquids-water mixtures

This paper delves into the practical application of K-Nearest Neighbors (KNN), Kernel Ridge Regression (KRR), and Lasso Regression for the prediction of viscosity of ionic liquids in a dataset characterized by categorical variables (Cation, Anion) and numeric variables (T(K), xIL(mol%)). Indeed, mole percentage of ionic liquids and temperature were considered as inputs for the models. The models' effectiveness is rigorously assessed, with K-Nearest Neighbors notably exhibiting exceptional predictive performance. To enhance model accuracy, Tabu Search is employed as an optimization tool for hyperparameter tuning. Numeric results showcase KNN's superiority, supported by a remarkable R2 test score of 0.91628 and the lowest RMSE among the models. Tabu Search optimization further refines model performance, emphasizing the critical role of hyperparameter tuning in achieving robust regression models in predicting the viscosity of ionic liquid-water mixtures. This study contributes valuable insights into the optimization process, demonstrating tangible improvements in predictive accuracy for viscosity predictions in similar contexts.

Mapping of nearshore bathymetry using Gaofen-6 images for the Yellow River Delta-Laizhou Bay, China

Bathymetric mapping is integral to maintaining marine ecosystems, managing coastal zones, and safeguarding the environment. However, achieving accurate large-scale bathymetric maps remains a challenge in China, particularly in nearshore turbid waters. To address this gap, we leveraged seasonal Gaofen-6 (GF-6) data to conduct bathymetry mapping in the Yellow River Delta-Laizhou Bay area. In our study, we found that longer wavelengths, such as those in the red-edge2 and near-infrared (NIR) bands, exhibited superior performance in determining bathymetry. Moreover, specific band ratios derived from GF-6 data—such as Blue/NIR (BN), Violet/NIR (VN), Blue/Red-edge2 (BE), Violet/Red-edge2 (VE), Green/NIR (GN), and Green/Red-edge2 (GE)—showed promising outcomes, particularly in turbid nearshore waters. When comparing models, the random forest regression (RFR) model outperformed the classification and regression trees (CART) model in turbid nearshore areas, showing higher R2 values and lower RMSE. Notably, both models demonstrated higher accuracy in March compared to May and October. Incorporating the Normalized Difference Turbidity Index (NDTI) notably improved bathymetric results, especially in turbid sea regions. Furthermore, nearshore bathymetry proved highly susceptible to natural processes, seasonal variations, and human activities. The significant discrepancies in bathymetry among coastal areas emphasize the need for tailored management strategies to enhance coastal management and foster sustainable marine economic development.

Predicting high-resolution air quality using machine learning: Integration of large eddy simulation and urban morphology data

Accurately predicting air pollutants, especially in urban areas with well-defined spatial structures, is crucial. Over the past decade, machine learning techniques have been widely used to forecast urban air quality. However, traditional machine learning approaches have limitations in accuracy and interpretability for predicting pollutants. In this study, we propose a convolutional neural network (CNN) model to predict the spatial distribution of CO concentration in Nanjing urban area at 10 m resolution. Our model incorporates various factors as input, such as building height, topography, emissions, and is trained against the outputs simulated by the parallelized large-eddy simulation model (PALM). The PALM model has 48 different scenarios that varied in emissions, wind speeds, and wind directions. The results display a strong consistency between the two models. Furthermore, we evaluate the performance of our model using a 10-fold cross-validation and out-of-sample cross-validation approach. This yields a robust correlation (with both R2 > 0.8) and a low RMSE between the CO predicted by the PALM and CNN models, which demonstrates the generalization capability of our CNN model. The CNN can extract crucial features from the resulted weight contribution map. This map indicates that the CO concentration at a location is more influenced by nearby buildings and emissions than distant ones. The interpretable patterns uncovered by our model are related to neighborhood effects, wind speeds, directions, and the impact of orientation on urban CO distribution. The model also shows high prediction accuracy (R > 0.8) when applied to another city. Overall, the integration of our CNN framework with the PALM model enhances the accuracy of air quality predictions, while enabling a fluid dynamic laws interpretation, providing effective tools for air quality management.

Extraction of single diode PV cell/module model parameters using a hybrid BMO approach with Lambert's W function

The accurate estimation of photovoltaic (PV) system parameters is crucial for effective simulation. Evaluation, modelling, and control of solar energy systems. The performance of photovoltaic installations is significantly influenced by the variability of model parameters and the difficulties in accessing them. As a result, the continuous objective is to consistently strive to search for and identify these parameters. This study proposes a hybrid algorithm that combines Bird Mating Optimiser algorithm with Lambert W-function (LBMO) with Wang's analytical method called (WLBMO) to optimise the parameters of the single diode model (SDM). The algorithm utilises a fast and precise iterative method for extracting I0 and Iph , and a Bird Mating Optimiser with Lambert W-function for extracting α, Rsh and Rs . The effectiveness of the proposed method is evaluated on the RTC solar cell and three commercial photovoltaic models. The specific results demonstrate the superior performance of our proposed WLBMO algorithm compared to known alternatives. For the R.T.C. France solar cell's single diode model, WLBMO achieves the smallest RMSE of 9.8630E-04, and similarly for the PWP201 model, yielding a low RMSE of 2.3845E-03. Comparative analysis, including Wang and LBMO, further validates our approach. Additionally, WLBMO excels among other methods for the STM6-120/36 commercial PV module, with a lowest RMSE of 1.7599E-03 and an exceptional minimum power error of 3.2270E-05. Similarly, for the KC200GT model, our method produces the smallest RMSE of 4.7569E-03. These consistent findings affirm the accuracy and efficacy of our WLBMO algorithm for PV model parameter estimation, emphasising its capacity to achieve significant error rate reductions of 92.856%, 1.147%, 49.732%, and 89.221% for the R.T.C France solar cell, Photowatt-PWP201, STM6-40/36, and KC200GT modules, respectively, and highlighting its pivotal role in optimising solutions.

Machine learning guided constitutive model and processing map for Fe2Ni2CrAl1.2 multi-principle element alloys

The present work provides a systematical investigation on the hot deformation behavior of Fe2Ni2CrAl1.2 multi-principle element alloys (MPEAs). Hot compression tests were carried out at various temperatures ranging from 800 °C to 1100 °C at different strain rates from 0.001 s-1 to 1 s-1. The stress–strain curves obtained under different processing conditions were used to develop the constitutive model for the alloy. The advanced machine learning (ML) models including Support Vector Regression (SVR), Artificial Neural Network (ANN), Generalized Regression Neural Network (GRNN) and Random Forest (RF) were trained to predict the flow behavior of Fe2Ni2CrAl1.2 MPEAs. The predictive capability of ML algorithms were estimated, the SVR model performed better among the developed four algorithms. Then Particle Swarm Optimization (PSO) was imposed to SVR model to further enhance its prediction accuracy. The developed PSO-SVR model achieved an average testing R2 of 0.9819, as well as low RMSE and MAPE values, demonstrating its strong predictive performance. Then the PSO-SVR model was applied to generate the flow curves at various temperature and strain rate for the development of the hot processing maps. The flow instability and the optimum processing conditions were identified, indicating that instability (ζ<0) occurred at temperatures below 850 °C and the specific temperature range (950–1050 °C) is desirable for hot working. This work promoted the optimization of hot working process of Fe2Ni2CrAl1.2 MPEAs.

Identifying stress scores from gait biometrics captured using a camera: A cross-sectional study

BackgroundStress is a critical risk factor for various health issues, but an objective, non-intrusive and effective measurement approach for stress has not yet been established. Gait, the pattern of movements in human locomotion, has been proven to be a valid behavioral indicator for recognizing various mental states in a convenient manner. Research QuestionThis study aims to identify the severity of stress by assessing human gait recorded through an objective, non-intrusive measurement approach. MethodsOne hundred and fifty-two participants with an average age of 23 years old (SD = 1.07) were recruited. The Chinese version of the Perceived Stress Scale with 10 items (PSS-10) was used to assess participants’ stress levels. The participants were then required to walk naturally while being recorded with a regular camera. A total of 1320 time-domain and 1152 frequency-domain gait features were extracted from the videos. The top 40 contributing features, confirmed by dimensionality reduction, were input into models consisting of four machine-learning regression algorithms (i.e., Gaussian Process Regressor, Linear Regression, Random Forest Regressor, and Support Vector regression), to assess stress levels. ResultsThe models that combined time- and frequency-domain features performed best, with the lowest RMSE (4.972) and highest validation (r = 0.533). The Gaussian Process Regressor and Linear Regression outperformed the others. The greatest contribution to model performance was derived from gait features of the waist, hands, and legs. SignificanceThe severity of stress can be accurately detected by machine learning models using two-dimensional (2D) video-based gait data. The machine learning models used for assessing perceived stress were reliable. Waist, hand, and leg movements were found to be critical indicator in detecting stress.

Forecasting PM10 Caused by Bangkok’s Leading Greenhouse Gas Emission Using the SARIMA and SARIMA-GARCH Model

This paper analyzes the relationship between air pollutants and the amount of PM10 measured in Bangkok. It forecasts the amount of PM10 in Bangkok by using the SARIMA and SARIMA-GARCH models to formulate policies to reduce the occurrence of PM10 and guidelines for further prevention. PM's data is from January 2008 to July 2023. First, the process is to build the SARIMA Model and SARIMA-GARCH Model Estimation. We perform model comparisons that SARIMA (3,1,3)(1,1,2)12 and SARIMA(3,1,3)(1,1,2)12-GARCH(1,1), which model gives lower MAE and RMSE values, which indicates good prediction accuracy than another model. The results show that the MAE and RMSE predictions of the SARIMA (3,1,3) (1,1,2)12 model are 15.303 and 20.839 better than those of the SARIMA (3,1,3) (1,1,2)12-GARCH (1,1) model are 17.280 and 22.677. Therefore, the SARIMA (3,1,3) (1,1,2)12 forecast results are better precise. Thus, in summary, we will choose the first model to use in forecasting for policy making. Moreover, in the study results, we found the relationship between air pollutants and PM10 in Bangkok and found that the elements of NO2 and O3 will require quite a lot of attention because they affect the relationship with PM10 at a moderate level.

Groundwater Quality Assessment and Irrigation Water Quality Index Prediction Using Machine Learning Algorithms

The evaluation of groundwater quality is crucial for irrigation purposes; however, due to financial constraints in developing countries, such evaluations suffer from insufficient sampling frequency, hindering comprehensive assessments. Therefore, associated with machine learning approaches and the irrigation water quality index (IWQI), this research aims to evaluate the groundwater quality in Naama, a region in southwest Algeria. Hydrochemical parameters (cations, anions, pH, and EC), qualitative indices (SAR,RSC,Na%,MH,and PI), as well as geospatial representations were used to determine the groundwater’s suitability for irrigation in the study area. In addition, efficient machine learning approaches for forecasting IWQI utilizing Extreme Gradient Boosting (XGBoost), Support vector regression (SVR), and K-Nearest Neighbours (KNN) models were implemented. In this research, 166 groundwater samples were used to calculate the irrigation index. The results showed that 42.18% of them were of excellent quality, 34.34% were of very good quality, 6.63% were good quality, 9.64% were satisfactory, and 4.21% were considered unsuitable for irrigation. On the other hand, results indicate that XGBoost excels in accuracy and stability, with a low RMSE (of 2.8272 and a high R of 0.9834. SVR with only four inputs (Ca2+, Mg2+, Na+, and K) demonstrates a notable predictive capability with a low RMSE of 2.6925 and a high R of 0.98738, while KNN showcases robust performance. The distinctions between these models have important implications for making informed decisions in agricultural water management and resource allocation within the region.

Early Mapping Method for Different Planting Types of Rice Based on Planet and Sentinel-2 Satellite Images

In Northeast China, transplanted rice cultivation has been adopted to extend the rice growing season and boost yields, responding to the limitations of the cumulative temperature zone and high food demand. However, direct-seeded rice offers advantages in water conservation and labour efficiency. The precise and timely monitoring of the distribution of different rice planting types is key to ensuring food security and promoting sustainable regional development. This study explores the feasibility of mapping various rice planting types using only early-stage satellite data from the rice growing season. We focused on Daxing Farm in Fujin City, Jiamusi City, Heilongjiang Province, for cropland plot extraction using Planet satellite imagery. Utilizing Sentinel-2 satellite imagery, we analysed the differences in rice’s modified normalized difference water index (MNDWI) during specific phenological periods. A multitemporal Gaussian mixture model (GMM) was developed, integrated with the maximum expectation algorithm, to produce binarized classification outcomes. These results were employed to detect surface changes and map the corresponding rice cultivation types. The probability of various rice cultivation types within arable plots was quantified, yielding a plot-level rice-cultivation-type mapping product. The mapping achieved an overall accuracy of 91.46% in classifying rice planting types, with a Kappa coefficient of 0.89. The area extraction based on arable land parcels showed a higher R2 by 0.1109 compared to pixel-based area extraction and a lower RMSE by 0.468, indicating more accurate results aligned with real statistics and surveys, thus validating our study’s method. This approach, not requiring labelled samples or many predefined parameters, offers a new method for rapid and feasible mapping, especially suitable for direct-seeded rice areas in Northeast China. It fills the gap in mapping rice distribution for different planting types, supporting water management in rice fields and policies for planting-method changes.

Traffic prediction for 5G: A deep learning approach based on lightweight hybrid attention networks

The maturity of 5G technology provides a guarantee for increasingly large communication networks, while the resources required for communication and computation are also increasing, and reasonable resource allocation can improve the efficiency of network communication and reduce the consumption of communication resources. Existing deep learning methods have been able to predict network traffic to a certain extent, so as to solve the communication efficiency and resource consumption problems in the field of integrated sensing, communication and computation (ISCC) through rational resource allocation. However, the following problems still exist: (1) The feature learning ability of the prediction model is insufficient, and the prediction accuracy needs to be improved. (2) Powerful and complex deep learning methods lead to an increase in the prediction cost of the model. To address these problems, this paper proposes a deep learning method based on a lightweight hybrid attention network. In order to capture the key features of 5G data more effectively, an efficient hybrid attention mechanism (EHA) is proposed. After this attention is applied to convolution, the key information can be well enhanced. We use depthwise separable convolution in feature extraction, which greatly improves the efficiency of lightweight convolution layer (LC) in feature extraction. Combined with the efficient hybrid attention mechanism (EHA), the proposed model has better lightweight properties. Experimental results show that the model proposed in this paper has lower RMSE and MAE values on the three datasets, as well as fewer parameters and computational effort compared to the baseline scheme.

An optimized deep learning approach for blood-brain barrier permeability prediction with ODE integration

Blood-brain barrier (BBB) permeability prediction plays a pivotal role in drug discovery for neurological disorders which is essential for the development of central nervous system (CNS) drugs. Compounds having high permeability must be found to synthesize brain drugs for the treatment of different brain disorders such as Alzheimer's, Parkinson's, and brain tumors. Developing an accurate mathematical computational model to determine the exact brain permeability value for a possible drug is essential for advancing and improving the success rate of the development of drugs for neurological treatment. We developed a combined method capable of forecasting the logBB value of the compound in question for lightBBB and B3DB datasets by using the Convolutional neural network (CNNs), Recurrent Neural Networks (RNNs) and Ordinary Differential Equations (ODEs). The results demonstrate the overall assessment of the prediction ability of BBB permeability. CNN-LSTM model tests the performance for the prediction of logBB values in two different datasets LightBBB and B3DB. In both datasets, CNN-LSTM achieves lower RMSE values as compared to other models, showing that it has better predictive performance. Specifically, in the LightBBB dataset, the CNN-LSTM model achieves an RMSE of 0.59, while in the B3DB datasets, it achieves an even lower RMSE of 0.85. CNN-LSTM model shows highly effective in accurately predicting logBB values in both datasets.

WITHDRAWN: Utilization of waste coffee ground ash as fine aggregates in concrete: Enhancing shear strength through activated carbon reinforcement

This study addresses burgeoning environmental concerns amid rising global coffee consumption amid rising global coffee consumption by exploring the viability of utilizing waste coffee ground ash (SCG) as a sustainable fine aggregate in concrete production. Significant improvements are noted by investigating the impact of SCG on the shear strength of standard concrete and enhancing properties through activated carbon reinforcement derived from SCG via physical activation. Experimental results reveal that incorporating up to 1.5% activated carbon by weight markedly boosts early shear strength. Moreover, composites with a small inclusion of activated carbon demonstrate superior shear power during curing compared to conventional mixes. The study employs Teaching-Learning Optimization (TLBO) and Extreme Learning Machine (ELM) techniques to forecast shear strength accurately. ELM emerges superior, showcasing heightened accuracy, lower RMSE, and superior r and R2 values compared to TLBO. Conclusively, leveraging waste coffee ground ash as a fine aggregate in concrete not only presents an effective method for enhancing shear strength but also underscores a promising pathway toward sustainable waste management and reduced environmental impact, reflecting a pivotal stride in harmonizing concrete performance enhancement with eco-friendly practices.

Avaliação do modelo AquaCrop para simulação da resposta da soja sob estresse hídrico

ABSTRACT: Lately, irrigated soybean production has increased; therefore, tools that can aid water resources management must be improved. Two experiments were carried out, the first one from May to August and the second one from September to December 2019. The experimental design included randomized blocks with five treatments and four replicates. In the control treatment (SE), irrigation was carried out to meet the crop’s water demand during all growth stages. In the other treatments, irrigation was interrupted at specific crop growth stages (TI = VC-V4, TII = V5-R1, TIII = R1-R5, and TIV = R5-R7), and then restored. After calibration, the model satisfactorily estimated the canopy cover, biomass, and soybean yield, with high values of determination coefficients (r² &gt; 0.90), low RMSE and MBE values, and high values of EF. In experiment 1, the soil water content was overestimated in the SE, TI, and TIV treatments by 0.24%, 0.78%, and 0.23%, respectively, and underestimated by 3.3% and 5.5% in the TII and TIII treatments, respectively. In experiment 2, in the SE, TI, TII, TIII, and TIV treatments, the soil water content was underestimated by 6%, 3%, 4.6%, 5.9%, and 6.7%, respectively. Real evapotranspiration was overestimated in all treatments in both experiments, with low r² values in both experiments 1 (0.11- 0.23) and 2 (0.04 - 0.21).

Mapping soil organic carbon in northern France using adaptive zoning regression kriging based on LUCAS dataset

To improve the accuracy of soil organic carbon (SOC) mapping, an adaptive zoning regression kriging (AZ_RK) framework was proposed, which simultaneously considers spatial heterogeneity and the influence of multiple environmental variables. In AZ_RK, the study area was first adaptively divided into several spatially homogeneous zones. Then, the SOC distribution was mapped in each zone separately considering the relationships between SOC and environmental variables. The results indicated that the influence of environmental variables on SOC in different zones differed. The proposed zoning strategy was proven to be valid, which can account for 36.6% of the spatial variance in SOC. Furthermore, AZ_RK outperformed other methods with the lowest RMSE and the highest R 2 ( R cv 2 = 0.495 and R p 2 = 0.481). We concluded that AZ_RK can effectively cluster spatially homogeneous zones and adaptively map SOC with high estimation accuracy, which can serve as a valuable model reference for precise fertilization in regions characterized by spatial heterogeneity.

Comparison Between ARIMA and EEMD+ARIMA Models in Forecasting Electricity Consumption

Accurate forecasting of future electricity consumption is necessary to create a satisfactory design for an electricity distribution system. To enhance forecasting accuracy, autoregressive integrated moving average (ARIMA) was compared with hybrid of ensemble empirical mode decomposition (EEMD) plus autoregressive integrated moving average (ARIMA) denoted by (EEMD+ARIMA), to know which model is better performing a historical US monthly electricity consumption from DEC-2000 to SEP-2022 were used. The data were divided into training set (90%) and testing set (10%) to insure the model accuracy. The mean absolute square error, root mean square error, mean absolute error and mean absolute percentage error measurements were used to test the ARIMA and hybrid EEMD+ARIMA performance, the results show that the hybrid EEMD+ARIMA outperforms ARIMA model with the lowest RMSE, MAE, MPE, MAPE, MASE. For the best model, Akaike Information Criterion and Bayesian Information Criterion were applied to choose the best. The results show that the AIC and BIC of the EEMD+ARIMA were lower than the ARIMA model, which indicates that the EEMD+ARIMA is better than the single ARIMA in forecasting of electricity consumption. The conclusion reveals that the hybrid EEMD+ARIMA provides more accurate forecasting and performs significantly better than the ARIMA in forecasting of electricity.

Modeling of Release Mechanism of Sage (Salvia fruticosa Miller) Phenolics Encapsulated in Alginate Capsule: Physicochemical Properties

Alginate capsules are promising delivery systems for encapsulation and release of phenolics since they can be fabricated from food‐grade biopolymers using mild processes. On the other hand, knowing the release kinetic of the phenolic in the capsules is critical for capsule fabrication and product quality improvement This study is aimed at mathematically modeling the transfer of encapsulated sage (Salvia fruticosa Miller) phenolics in alginate particles to water and to determine some physicochemical properties of capsules containing different concentrations of phenolics. The water activity values (aw) of the capsule varied between 0.9976 and 0.9990. Sphericity factors of 1 (37.5 ppm), 2 (75 ppm), 3 (150 ppm), 4 (300 ppm), and control (0 ppm) samples were determined as 0.042, 0.044, 0.043, 0.273, and 0.039, respectively. The yellowness (+b ∗) value of the samples increased significantly as the added sage extract concentration increased. While the phenolic content of the samples was determined between 0.174 and 1.1831 mg/kg GAE, the antioxidant activity values were determined between 0.9602 and 6.6930. To understand the mechanism of phenolic release from the capsules, six different mathematical models were used (First Order, Higuchi, Korsmeyer-Peppas, Hixson and Crowell, The Peppas-Sahlin, and Gompertz). The highest R2 (0.9952‐0.9979) and the lowest RMSE (1.0171‐1.7032) values were calculated in The Peppas‐Sahlin among the six models. The Peppas‐Sahlin model kinetic parameters indicated the dominance of Fickian diffusion and the minor effect of relaxation process in the mechanism of phenolic release.

Oyster mushroom drying in tray dryer: Parameter optimization using response surface methodology, drying kinetics, and characterization

In this study, the drying of oyster mushrooms (P. ostreatus) in a tray dryer was optimized. The parameters used to optimize the drying process were drying temperature, airspeed, mass loading, and moisture content. Its drying kinetics were investigated at the optimum drying parameters. A quadratic equation was obtained to predict the moisture content of mushrooms at the given drying temperature, airspeed, and mass loading, and it was validated against experimental results. A minimum moisture content (9.99 wt%) was obtained at the optimum conditions of 60 °C, 3 m/s airspeed, and mass loading of 200 g using a tray dryer. Proximate analysis, shelf-life analysis, inorganic elemental analysis, and functional group analysis were done as a characterization method for mushrooms after drying at the optimum drying conditions. About 27.8 wt% protein and 50.2 wt% carbohydrates were found in proximate results. Besides, potassium and sodium were the dominant elements as estimated by spectrophotometry analysis. The induction period (IP) of dried mushrooms at room temperature is 3520:47 (hour: minute) from the oxidation stability analysis, and the water activity of dried mushrooms was found to be 0.36. The drying kinetics of oyster mushrooms were studied at various temperatures (50–75 °C), optimum airspeed (3 m/s), and mass loading (200 g). The best-fit model describing the mushrooms drying kinetics was found to be Midilli et al., with the lowest RMSE (0.008749), X2 (0.0014), and the highest R2(0.9993) values. The kinetic triplet activation energy, effective diffusivity, and diffusivity constant (Ea, Deff, D0) for oyster mushrooms drying were determined and found to lay in the general range for foodstuffs. The value of Deff results lies within the range of 10−8 to 10−12 m2/s, with Ea of 15.32 kJ/mol and D0 value 2.263 × 10−6 m2/s.

Evaluation of formal waste reduction facility location compared to recyclable plastic waste generation in Denpasar City, Bali, Indonesia

This paper aims to evaluate the location of formal waste reduction facilities in comparison to the distribution of recyclable plastic waste generation in Denpasar City, Bali Province, Indonesia. The distribution of recyclable plastic waste generation was carried out by conducting primary sampling from 200 houses, following the guidelines of SNI-19-3964-1994. Socioeconomic variables, including house size, population density, Gross Domestic Product (GDP), and area classification, were obtained through interviews and the use of remote sensing data products. The distribution of recyclable plastic waste is modeled using the best of six machine learning models: LGBM (Light Gradient Boosting Machine), Linear Regression, Random Forest, and SVM (Support Vector Machine), XGBoost, and Adaboost. The LGBM model was selected with an R2 of 0.939 in the training dataset, an R2 of 0.954 in the testing dataset, and the lowest RMSE and MAE. The map of recyclable plastic waste generation distribution is created through a spatial analysis that consists of three classes with ranges of &lt;248.5, &gt;248.5 and &lt;732.5, and &gt;732.5 grams/household/week. The effectiveness of the coverage area and capacity through spatial analysis indicates that the waste reduction facilities in Denpasar City are 32% and 46%, respectively.

Deep Learning Based Micro-RNA Analysis of Lipopolysaccharide Exposed Periodontal Ligament Stem Cells Exosomes Reveal Apoptotic and Inflammasome Derived Pathway Activation.

The production of inflammatory factors in periodontium is increased by LPS, particularly from P. gingivalis, and the damage to periodontal tissues is exacerbated. Exosomes from periodontal ligament stem cells change regeneration and repair brought on by bacterial LPS. MiRNAs are carried by exosomes to recipient cells to affect epigenetic functions. Thus, this study aims to utilize deep learning algorithms to uncover novel micro-RNA biomarkers in bacterial LPS-exposed PDLSC stem cells to understand the activation pathway. Using NCBI GEO DATA SET GSE163489, the most differentially expressed micro RNAs were found to differ between healthy and LPS-induced PDLSC cells. Deep learning analysis, employing a Random Forest, Artificial Neural Network c, a Support Vector Machine (SVM), and a Linear Regression model implemented within the orange data mining toolkit, identified novel microRNA biomarkers. The orange data mining toolkit was utilized for deep learning analysis of microRNA expression data, providing a user-friendly environment for machine learning tasks like classification, regression, and clustering. Random Forest emerged as the superior model, achieving the highest R 2 score (.985) and the lowest RMSE (0.189) compared to Neural Networks (R 2 = .952, RMSE = 0.332), Linear Regression (R 2 = .949, RMSE = 0.343), and SVM (R 2 = .931, RMSE = 0.398). This suggests its superior ability to capture the underlying patterns in the microRNA expression data. Given its robust performance, Random Forest holds promise for identifying novel biomarkers, developing more accurate diagnostic tools, and potentially guiding the stratification of patients for targeted therapeutic interventions in periodontal disease. The current study utilizes deep learning analysis of microRNA expression data to identify novel biomarkers associated with inflammasome activation and anti-apoptotic pathways. These findings hold promise for guiding the development of novel therapeutic strategies for periodontal disease. However, future studies are warranted to validate these biomarkers using independent datasets and experimental methods.

Geostatistical approach in estimating the capacity volume of the mudflow reservoir

Mudflow reservoirs play a crucial role in mitigating flood risks triggered by natural events like heavy rains and snowmelt, safeguarding surrounding areas from potential inundation. However, sedimentation poses a significant challenge by reducing the capacity and effectiveness of these mudflow reservoirs over time. This study focused on estimating the capacity of the Kalkama mudflow reservoir, constructed in 1987, using a geostatistical approach. Bathymetric survey data were analyzed using various interpolation methods. Kriging (Ordinary Kriging) provided the best performance with the lowest RMSE (0.28) and a high R² (0.99), indicating it is the most accurate method for this dataset. Based on this method, a spatial model of the mudflow reservoir was developed to assess its current capacity. Findings indicate a capacity loss of 2.33 million m³ (23.6%) over 36 years, alongside a 22% reduction in surface area at Full Storage Level, and the dead volume was completely filled with sediment.