Lower Root Mean Square Error Values Research Articles

A feasible framework to downscale NPP-VIIRS nighttime light imagery using multi-source spatial variables and geographically weighted regression

The cloud-free monthly composite of global nighttime light (NTL) data of the Suomi National Polar-orbiting Partnership with the Visible Infrared Imaging Radiometer Suite (NPP-VIIRS) day/night band (DNB) provides indispensable indications of human activities and settlements. However, the coarse spatial resolution (15 arc sec) of NTL imagery greatly restricts its application potential. This study proposes a feasible framework to downscale NPP-VIIRS NTL using muti-source spatial variables and geographically weighted regression (GWR) method. High-resolution auxiliary variables were acquired from the Landsat 8 OLI/ TIRS and social media platforms. GWR-based downscaling procedures were consequently implemented to obtain NTL at a 100-m resolution. The downscaled NTL data were validated against Loujia1-01 imagery based on the coefficient of determination (R2) and root-mean-square error (RMSE). The results suggest that the data quality was suitably improved after downscaling, yielding higher R2 (0.604 vs. 0.568) and lower RMSE (8.828 vs. 9.870 nW/cm2/sr) values than those of the original NTL data. Finally, the NTL was extendedly applied to detect impervious surfaces, and the downscaled NTL had higher accuracy than the original NTL. Therefore, this study facilitates data quality improvement of NPP-VIIRS NTL imagery by downscaling, thus enabling more accurate applications.

Investigation of acquisition time for harmonization of image quality between PET/CT and PET/MRI systems: A phantom study

The positron emission tomography (PET) system has technological differences between PET/computed tomography (CT) and PET/magnetic resonance imaging (MRI). It is important to compare image quality on acquisition time for equal diagnostic performance. Therefore, the aim of study was to investigate acquisition time as a factor for harmonizing the image quality. NEMA image quality phantom experiments were performed using Siemens Biograph PET/CT and PET/MRI. The phantom was filled with 18F-solution at a 10:1 of sphere-to-background ratio and scanned in the list-mode. PET images were reconstructed with increasing time frames of 1 min. To compare image quality and measure difference, the contrast recovery (CR), background variability (BV), and measure root mean square error (RMSE) of BVs were used. PET/CT and PET/MRI showed similar CR for spheres regardless of acquisition time, whereas the BV was higher with PET/MRI than with PET/CT at the same acquisition time. The BV decreased with increasing acquisition time. The difference of BV by RMSE showed small values at an acquisition time delay of 2 min for PET/MRI. The PET images on visual analysis were also comparable at the lowest RMSE values. In conclusion, the image quality between PET/CT and PET/MRI was harmonized at a PET/MRI acquisition time of PET/CT acquisition time plus 2 min

Stochastic modelling of the oral cancer proliferation and death in the presence of Thymoquinone as anticancer therapeutics

Oral cancer is one of the most commonly known cancer worldwide. Thymoquinone (TQ) an extract from Nigella sativa, has clinically been proven as an anticancer therapeutic agent for oral cancer due to its intrinsic pharmacological characteristics. Understanding the mechanisms of oral cancer proliferation and death in the presence of TQ is crucial so that the insight of the interaction of cancer cells and TQ can be discovered. Cancer cells in the presence of TQ is subjected to the uncontrolled factors of the environmental noise. Deterministic model is inadequate to explain this behaviour. Herein, a stochastic model is proposed to illustrate the dynamics of HSC-3 oral cancer cell lines in the presence of TQ. The deterministic model is perturbed with the noisy behaviour which then leads to the stochastic model. The model is simulated by using a four-stage stochastic Runge-Kutta (SRK4) method and the kinetic parameters are estimated by using the maximum likelihood estimation (MLE) method. The prediction quality of the model is measured by using root mean square error (RMSE). The low values of RMSE show the best-fit of the stochastic model.

Predicting municipal solid waste using a coupled artificial neural network with archimedes optimisation algorithm and socioeconomic components

Solid Waste (SW) is one of the critical challenges of urban life. These SWs are considered environmental pollutants that are a threat to ecology and human health. Predicting SW generation is an essential topic for scholars to better manage SWs. This study investigates the application of optimised ANN models for predicting monthly SW generation in Iran using datasets about seven Iranian megacities. The Archimedes Optimisation Algorithm (AOA), Sine Cosine Algorithm (SCA), Particle Swarm Optimisation (PSO) technique, and Genetic Algorithms (GA) were used for training the ANN model. The enhanced gamma test was used to determine the best input combination. AOA and the gamma test were used concurrently to reduce the time needed for choosing the best input combination. Gross domestic product (GDP), population, household size, and numbers of months were the best input combination set. This best input combination was then inputted into the hybrid and standalone ANN models for predicting monthly SW generation. During the final phase, the outputs of ANN-AOA, ANN-SCA, ANN-PSO, ANN-GA, and ANN models were used as inputs for an inclusive multiple model (IMM) in order to enhance model accuracy. The IMM model reduced the training phase root mean square error (RMSE) of ANN-AOA, ANN-SCA, ANN-PSO, ANN-GA, and ANN models by 55%, 59%, 68%, 72%, and 73%, respectively. Although ANN-AOA provided higher R2 and lower RMSE values than ANN-PSO, ANN-SCA, ANN-GA and ANN models, the IMM model outperformed ANN-AOA, considering that it integrates the advantages of all models used in the current study. The current study also used the fuzzy reasoning concept for modifying ANN model structures. The results indicated that such ANN models' time requirement was lower than those without fuzzy reasoning concept. The general results of the current study indicate that the ANN-AOA and the fuzzy-reasoning based Inclusive Multiple Model have a high ability for predicting different target variables.

Predicting river dissolved oxygen time series based on stand-alone models and hybrid wavelet-based models

Accurate prediction of dissolved oxygen time series is important for improving the water environment and aiding water resource management. In this study, four stand-alone models including multiple linear regression (MLR), support vector machine (SVM), artificial neural network (ANN) and random forest (RF), and four hybrid models based on wavelet transform (WT) including WT-MLR, WT-SVM, WT-ANN and WT-RF were used to predict the daily dissolved oxygen (DO) at 1–5-day lead times in the Dongjiang River Basin, China. To make the prediction robust, the maximal information coefficient (MIC) was used to capture comprehensive information between DO and explanatory variables. The 5-fold cross validation grid search approach was used to optimize parameters of machine learning tools. Two types of frameworks of WT: direct framework (i.e., only the explanatory variables were decomposed) and multicomponent framework (i.e., both explanatory variables and target variables were decomposed) were used to construct hybrid models. The results show that MIC extracts four optimal explanatory variables: previous DO, water temperature, air temperature and air pressure. Four evaluation parameters including correlation coefficient (R), Nash-Sutcliffe efficiency (NSE), mean absolute error (MAE) and root mean square error (RMSE) indicate that the prediction accuracy decreases as the lead time changes from 1 to 5 days. In terms of the stand-alone models, MLR model outperforms the other three models with higher NSE values of 0.616–0.921, and lower RMSE values of 0.503–1.111. With regard to the hybrid models, WT-ANN and WT-MLR models exhibit higher performance, and multicomponent framework performs better than direct framework in all hybrid models. In general, the multicomponent framework of WT can improve the prediction accuracy of stand-alone models at a certain degree, while the direct framework shows no obvious advantage.

Mild Pretreatments to Increase Fructose Consumption in Saccharomyces cerevisiae Wine Yeast Strains.

The present research investigates the effect of different pretreatments on glucose and fructose consumption and ethanol production by four Saccharomyces cerevisiae wine strains, three isolated and identified from different wine regions in Turkey and one reference strain. A mild stress temperature (45 °C, 1 h) and the presence of ethanol (14% v/v) were selected as pretreatments applied to cell cultures prior to the fermentation step in synthetic must. The goodness fit of the mathematical models was estimated: linear, exponential decay function and sigmoidal model were evaluated with the model parameters R2 (regression coefficient), RMSE (root mean square error), MBE (mean bias error) and χ2 (reduced Chi-square). Sigmoidal function was determined as the most suitable model with the highest R2 and lower RMSE values. Temperature pretreatment allowed for an increase in fructose consumption rate by two strains, evidenced by a t90 value 10% lower than the control. One of the indigenous strains showed particular promise for mild temperature treatment (45 °C, 1 h) prior to the fermentation step to reduce residual glucose and fructose in wine. The described procedure may be effective for indigenous yeasts in preventing undesirable sweetness in wines.

Novel Weight-Based Approach for Soil Moisture Content Estimation via Synthetic Aperture Radar, Multispectral and Thermal Infrared Data Fusion.

Though current remote sensing technologies, especially synthetic aperture radars (SARs), exhibit huge potential for soil moisture content (SMC) retrievals, such technologies also present several performance disadvantages. This study explored the merits of proposing a novel data fusion methodology (partly decision level and partly feature level) for SMC estimation. Initially, individual estimations were derived from three distinct methods: the inversion of an Empirically Adapted Integral Equation Model (EA-IEM) applied to SAR data, the Perpendicular Drought Index (PDI), and the Temperature Vegetation Dryness Index (TVDI) determined from Landsat-8 data. Subsequently, three feature level fusions were performed to produce three different novel salient feature combinations where said features were extracted from each of the previously mentioned methods to be the input of an artificial neural network (ANN). The latter underwent a modification of its performance function, more specifically from absolute error to root mean square error (RMSE). Eventually, all SMC estimations, including the feature level fusion estimation, were fused at the decision level through a novel weight-based estimation. The performance of the proposed system was analysed and validated by measurements collected from three study areas, an agricultural field in Blackwell farms, Guildford, United Kingdom, and two different agricultural fields in Sidi Rached, Tipasa, Algeria. Those measurements contained SMC levels and surface roughness profiles. The proposed SMC estimation system yielded stronger correlations and lower RMSE values than any of the considered SMC estimation methods in the order of 0.38%, 1.4%, and 1.09% for the Blackwell farms, Sidi Rached 1, and Sidi Rached 2 datasets, respectively.

Statistical prediction of the drying behavior of blanched ginger rhizomes

ARS-680 environmental chamber was employed in this study to determine the drying behavior of sliced ginger rhizomes. Blanched and unblanched treated ginger rhizomes were considered at drying temperature of 40 °C for a period of 2 – 24 h. Linear and non-linear regression analyses were employed to establish the correlation that exits between the drying time and the moisture ratio. Correlation analysis, root mean square error (RMSE) and standard error of estimate (SEE) analysis were chosen in selecting the best thin layer drying models. Higher values of determination coefficient (R2) show goodness of fit and lower values of SEE implies better correlation; and RMSE values were also utilized in determining the goodness of fit. The drying data of the variously treated ginger samples were fitted into the twelve thin layer drying models and the data obtained were fitted by multiple non-linear regression technique. Blanched treated sample exhibited a better drying behavior losing about 82.87 % moisture content compared with unbleached sample that lost about 62.03 % of moisture content. Two-term exponential drying model proved to be the most suitable model for predicting the drying behavior of ginger rhizome. The model exhibited high R2 values of 0.9349-0.9792 (which are close to unity) for both blanched and unbleached samples. Also, it recorded relatively low values of RMSE and SEE (3.6865 - 2.0896 and 3.6564-2.7486 respectively) for both treatments.

HPLC fingerprint and UV–Vis spectroscopy coupled with chemometrics for Curcumae radix species discrimination and three bioactive compounds prediction

Curcumae Radix with four botanical origins (Wenyujin, Huangyujin, Guiyujin, Lvyujin) has a long medical history in China. The four species have not been differentiated well in clinical application, though there were differences in pharmacological effects among them. For the aim of fast discrimination and quantitative analysis of Yujin, HPLC (high performance liquid chromatography) fingerprint and UV–Vis (ultraviolet–visible) spectroscopy technologies coupled with chemometrics were employed. The HPLC fingerprints of 26 Guiyujin, 11 Huangyujin, 11 Lvyujin, 29 Wenyujin and full 77 samples were separately established, with good similarities among same species except Wenyujin and poor consistence in full samples. UV–Vis spectra showed obvious three absorption peaks in the spectra of Huangyujin samples and only one in that of the rest samples. LDA (linear discriminant analysis) and Bagged Trees models established based on HPLC fingerprint data attained higher than 90% discrimination accuracy. Based on the spectral data, complete separation for the four species of Yujin was failed to achieve by PCA (principal component analysis), and the KNN (k-nearest neighbors) and SVM (support vector machine) models achieved no<90% discrimination accuracies. Furthermore, the SVMR (support vector machine regression) and Bagged Trees Regression models used to quickly predict the contents of germacrone, curcumenol and curdione performed well, with relatively lower RMSE (root mean square error) and higher R2 (coefficient of determination) values. The present study proposed relatively rapid methods for the determination of bioactive compounds and discrimination of Yujin.

Applying deep learning and benchmark machine learning algorithms for landslide susceptibility modelling in Rorachu river basin of Sikkim Himalaya, India

Landslide is considered as one of the most severe threats to human life and property in the hilly areas of the world. The number of landslides and the level of damage across the globe has been increasing over time. Therefore, landslide management is essential to maintain the natural and socio-economic dynamics of the hilly region. Rorachu river basin is one of the most landslide-prone areas of the Sikkim selected for the present study. The prime goal of the study is to prepare landslide susceptibility maps (LSMs) using computer-based advanced machine learning techniques and compare the performance of the models. To properly understand the existing spatial relation with the landslide, twenty factors, including triggering and causative factors, were selected. A deep learning algorithm viz. convolutional neural network model (CNN) and three popular machine learning techniques, i.e., random forest model (RF), artificial neural network model (ANN), and bagging model, were employed to prepare the LSMs. Two separate datasets including training and validation were designed by randomly taken landslide and non-landslide points. A ratio of 70:30 was considered for the selection of both training and validation points. Multicollinearity was assessed by tolerance and variance inflation factor, and the role of individual conditioning factors was estimated using information gain ratio. The result reveals that there is no severe multicollinearity among the landslide conditioning factors, and the triggering factor rainfall appeared as the leading cause of the landslide. Based on the final prediction values of each model, LSM was constructed and successfully portioned into five distinct classes, like very low, low, moderate, high, and very high susceptibility. The susceptibility class-wise distribution of landslides shows that more than 90% of the landslide area falls under higher landslide susceptibility grades. The precision of models was examined using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve and statistical methods like root mean square error (RMSE) and mean absolute error (MAE). In both datasets (training and validation), the CNN model achieved the maximum AUC value of 0.903 and 0.939, respectively. The lowest value of RMSE and MAE also reveals the better performance of the CNN model. So, it can be concluded that all the models have performed well, but the CNN model has outperformed the other models in terms of precision.

Digital image processing technology under backpropagation neural network and K-Means Clustering algorithm on nitrogen utilization rate of Chinese cabbages.

The purposes are to monitor the nitrogen utilization efficiency of crops and intelligently evaluate the absorption of nutrients by crops during the production process. The research object is Chinese cabbage. The Chinese cabbage population with different agricultural parameters is constructed through different densities and nitrogen fertilizer application rates based on digital image processing technology, and an estimation NC (Nitrogen Content) model is established. The population is classified through the K-Means Clustering algorithm using the feature extraction method, and the Chinese cabbage population quality BPNN (Backpropagation Neural Network) model is constructed. The nonlinear mapping relationship between different agricultural parameters and population quality, and the contribution rate of each indicator, are studied. The nitrogen utilization of Chinese cabbage is monitored effectively. Results demonstrate that the proposed NC estimation model has correlation coefficients above 0.70 in different growth stages. This model can accurately estimate the NC of the Chinese cabbage population. The results of the Chinese cabbage population quality BPNN model show that the population planting density based on the seedling number is reasonable. The constructed population quality evaluation model has a high R2 value and a comparatively low RMSE (Root Mean Square Error) value for the quality evaluation of Chinese cabbage in different periods, showing that it applies to evaluate the population quality of Chinese cabbage in different growth stages. The constructed nitrogen utilization model and quality evaluation model can monitor the nutrient utilization of crops in different growth stages, ascertain the agricultural characteristics of other yield groups in different growth stages, and clarify the performance of agricultural parameters in different growth stages. The above results can provide some ideas for crop growth intelligent detection.

Temporal flood forecasting for trans-boundary Jhelum River of Greater Himalayas

Flood forecasting is a significant tool for river basin management and early flood warning systems. The aim of the present study was to develop annual time series flood forecasting models for River Jhelum in Kashmir Valley by the application of autoregressive integrated moving average (ARIMA) modelling approach. Annual peak flow at three principal flood monitoring sites of Jhelum, namely, Sangam, Ram Munshi Bagh and Asham were predicted using historical peak flow time series data. ARIMA models were developed for forecasting 1-year ahead floods. The prediction accuracy of the developed models was evaluated in terms of root mean square error (RMSE), the mean absolute error (MAE), the mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency (NSE). RMSE values for Sangam, Ram Munshi Bagh and Asham stations were 112.31, 61.08 and 126.12 cumecs, respectively, and MAE values were 83.00, 48.50 and 104.25 cumecs at these stations. Also, the MAPE values were 10.70%, 6.19% and 10.78% for Sangam, Ram Munshi Bagh and Asham stations, respectively. NSE values for Sangam, Ram Munshi Bagh and Asham stations were 0.84, 0.87 and 0.85, respectively. Low values of RMSE, MAE and MAPE along with high values of NSE at all sites suggest the suitability of the developed models for flood forecasting in River Jhelum. The lead time of forecast obtained by this method was 1 year, which is much longer as compared to the conventional rainfall-runoff models.

Estimating the Compressive Strength of Cement‐Based Materials with Mining Waste Using Support Vector Machine, Decision Tree, and Random Forest Models

To estimate the compressive strength of cement‐based materials with mining waste, the dataset based on a series of experimental studies was constructed. The support vector machine (SVM), decision tree (DT), and random forest (RF) models were developed and compared. The beetle antennae search (BAS) algorithm was employed to tune the hyperparameters of the developed machine learning models. The predictive performances of the three models were compared by the evaluation of the values of correlation coefficient (R) and root mean square error (RMSE). The results showed that the BAS algorithm can effectively tune these artificial intelligence models. The SVM model can obtain the minimum RMSE, while the BAS algorithm is inefficient in DT and RF models. The SVM, DT, and RF models can be used to predict the compressive strength of cement‐based materials using solid mining waste as aggregate effectively and accurately, with high R values and lower RMSE values. The RF algorithm can obtain the highest value of R and the lowest value of RMSE, demonstrating the highest accuracy. The solid mining waste to cement ratio is the most important variable to affect the compressive strength. Curing time was also an important parameter in the compressive strength of cemented materials, followed by the water‐solid ratio of mining waste and fine sand ratio.

PM2.5 Forecasting Model Using a Combination of Deep Learning and Statistical Feature Selection

This paper proposed a PM 2.5 forecasting model using Long Short-Term Model (LSTM) sequence to sequence combined with the statistical method. Correlation Analysis, XGBoost, and Chemical processed are used as the methods to select the essential features. The air pollution data is extracted from Taiwan Environmental Protection Agency (EPA) for the Taichung City dataset in 2014–2018. The study points out that chemical processed model of particulate matter 10 micrometers or less in diameter (PM10), Sulfur Dioxide (SO2), and Nitrogen Dioxide (NO2) have the highest accuracy or lowest Root Mean Square Error (RMSE) and more short training and testing time among the other models. The chemical processed model of PM10, SO2, and NO2 (model B) has the highest accuracy (lowest RMSE), approximately 1 point lower RMSE values, and the shortest training and testing period among the other models. Furthermore, RMSE calculations based on the stations reveal that training with the entire station dataset has a 3 point higher RMSE value than training with each station dataset.

Challenging the spread of COVID-19 in Thailand

Coronavirus disease (COVID-19) has been identified as a pandemic by the World Health Organization (WHO). It was initially detected in Wuhan, China and spread to other cities of China and all countries. It has caused many deaths and the number of infections became greater than 18 million as of 5 August 2020. This study aimed to analyze the situation of COVID-19 in Thailand and the challenging disease control by employing a dynamic model to determine prevention approaches. We employed a statistical technique to analyze the ambient temperature influencing the cases. We found that temperature was significantly associated with daily infected cases (p-value <0.01). The SEIR (Susceptible Exposed Infectious and Recovered) dynamic approach and moving average estimation were used to forecast the daily infected and cumulative cases until 16 June as a base run analysis using STELLA dynamic software and statistical techniques. The movement of people, both in relation to local (Thai people) and foreign travel (both Thai and tourists), played a significant role in the spread of COVID-19 in Thailand. Enforcing a state of emergency and regulating social distancing were the key factors in reducing the growth rate of the disease. The SEIR model reliably predicted the actual infected cases, with a root mean square error (RMSE) of 12.8. In case of moving average approach, RMSE values were 0.21, 0.21, and 0.35 for two, three and five days, respectively. The previous records were used as input for prediction that caused lower values of RMSE. Two-days and three-days moving averages gave the better results than SEIR model. The SEIR model is suitable for longer period prediction, whereas the moving average approach is suitable for short term prediction. The implementation of interventions, such as governmental regulation and restrictions, through collaboration among various sectors was the key factor for controlling the spreading of COVID-19 in Thailand.

Evaluation of Historical CMIP6 Model Simulations of Seasonal Mean Temperature over Pakistan during 1970–2014

This work employed recent model outputs from coupled model intercomparison project phase six to simulate surface mean temperature during the June–July–August (JJA) and December–January–February (DJF) seasons for 1970–2014 over Pakistan. The climatic research unit (CRU TS4.03) dataset was utilized as benchmark data to analyze models’ performance. The JJA season exhibited the highest mean temperature, whilst DJF displayed the lowest mean temperature in the whole study period. The JJA monthly empirical cumulative distribution frequency (ECDF) range (26 to 28 °C) was less than that of DJF (7 to 10 °C) since JJA matched closely to CRU. The JJA and DJF seasons are warming, with higher warming trends in winters than in summers. On temporal scale, models performed better in JJA with overall low bias, low RMSE (root mean square error), and higher positive CC (correlation coefficient) values. DJF performance was undermined with higher bias and RMSE with weak positive correlation estimates. Overall, CanESM5, CESM2, CESM2-WACCM, GFDL-CM4, HadGEM-GC31-LL, MPI-ESM1-2-LR, MPI-ESM1-2-HR, and MRI-ESM-0 performed better for JJA and DJF.

Evaluation of reconstruction algorithms for a stationary digital breast tomosynthesis system using a carbon nanotube X-ray source array.

Breast cancer is the most frequently diagnosed cancer in women worldwide. Digital breast tomosynthesis (DBT), which is based on limited-angle tomography, was developed to solve tissue overlapping problems associated with traditional breast mammography. However, due to the problems associated with tube movement during the process of data acquisition, stationary DBT (s-DBT) was developed to allow the X-ray source array to stay stationary during the DBT scanning process. In this work, we evaluate four widely used and investigated DBT image reconstruction algorithms, including the commercial Feldkamp-Davis-Kress algorithm (FBP), the simultaneous iterative reconstruction technique (SIRT), the simultaneous algebraic reconstruction technique (SART) and the total variation regularized SART (SART-TV) for an s-DBT imaging system that we set up in our own laboratory for studies using a semi-elliptical digital phantom and a rubber breast phantom to determine the most superior algorithm for s-DBT image reconstruction among the four algorithms. Several quantitative indexes for image quality assessment, including the peak signal-noise ratio (PSNR), the root mean square error (RMSE) and the structural similarity (SSIM), are used to determine the best algorithm for the imaging system that we set up. Image resolutions are measured via the calculation of the contrast-to-noise ratio (CNR) and artefact spread function (ASF). The experimental results show that the SART-TV algorithm gives reconstructed images with the highest PSNR and SSIM values and the lowest RMSE values in terms of image accuracy and similarity, along with the highest CNR values calculated for the selected features and the best ASF curves in terms of image resolution in the horizontal and vertical directions. Thus, the SART-TV algorithm is proven to be the best algorithm for use in s-DBT image reconstruction for the specific imaging task in our study.

Landslide susceptibility modeling based on ANFIS with teaching-learning-based optimization and Satin bowerbird optimizer

As threats of landslide hazards have become gradually more severe in recent decades, studies on landslide prevention and mitigation have attracted widespread attention in relevant domains. A hot research topic has been the ability to predict landslide susceptibility, which can be used to design schemes of land exploitation and urban development in mountainous areas. In this study, the teaching-learning-based optimization (TLBO) and satin bowerbird optimizer (SBO) algorithms were applied to optimize the adaptive neuro-fuzzy inference system (ANFIS) model for landslide susceptibility mapping. In the study area, 152 landslides were identified and randomly divided into two groups as training (70%) and validation (30%) dataset. Additionally, a total of fifteen landslide influencing factors were selected. The relative importance and weights of various influencing factors were determined using the step-wise weight assessment ratio analysis (SWARA) method. Finally, the comprehensive performance of the two models was validated and compared using various indexes, such as the root mean square error (RMSE), processing time, convergence, and area under receiver operating characteristic curves (AUROC). The results demonstrated that the AUROC values of the ANFIS, ANFIS-TLBO and ANFIS-SBO models with the training data were 0.808, 0.785 and 0.755, respectively. In terms of the validation dataset, the ANFIS-SBO model exhibited a higher AUROC value of 0.781, while the AUROC value of the ANFIS-TLBO and ANFIS models were 0.749 and 0.681, respectively. Moreover, the ANFIS-SBO model showed lower RMSE values for the validation dataset, indicating that the SBO algorithm had a better optimization capability. Meanwhile, the processing time and convergence of the ANFIS-SBO model were far superior to those of the ANFIS-TLBO model. Therefore, both the ensemble models proposed in this paper can generate adequate results, and the ANFIS-SBO model is recommended as the more suitable model for landslide susceptibility assessment in the study area considered due to its excellent accuracy and efficiency.

Statistical Examination of Uncaria gambir Roxb Drying Modeling

This study investigates the drying modeling of Uncaria gambir Roxb using convective desiccant examined by statistical parameters. Three types of drying modeling are investigated, i.e. the Newton, Page and Henderson-Pabis models. The drying conditions of Uncaria gambir Roxb were set at 35oC, 45oC and 55oC and air velocity of 1.2 m/s. The results show that the Page modeling is the best fit model for this investigation based on values of R2 (coefficient of determinant), RMSE (root mean square error) and χ2 (chi-square) goodness of fit test derived from (MR) moisture ratio equation. The Page modeling shows R2 value nearest to unity and lowest values of RMSE and χ2 are obtained for all given temperatures (35oC, 45oC and 55oC) at air velocity of 1.2 m/s. The drying modeling is useful for optimization in design process encountered with product quality and cost of production.

An adaptive GP-based memetic algorithm for symbolic regression

Symbolic regression is a process to find a mathematical expression that represents the relationship between a set of explanatory variables and a measured variable. It has become a best-known problem for GP (genetic programming), as GP can use the tree representation to represent solutions as expression trees. Since the success of memetic algorithms (MAs (Memetic algorithms (MAs) can be regarded as a class of methods that combine population-based global search and local search [6, 30])) has proved the importance of local search in augmenting the global search ability of GP, GP with local search is investigated to solve symbolic regression tasks in this work. An important design issue of MAs is the balance between the global exploration of GP and the local exploitation, which has a great influence on the performance and efficiency of MAs. This work proposes a GP-based memetic algorithm for symbolic regression, termed as aMeGP (a daptive Me metic GP), which can balance global exploration and local exploitation adaptively. Compared with GP, two improvements are made in aMeGP to invoke and stop local search adaptively during evolution. The proposed aMeGP is compared with GP-based and nonGP-based symbolic regression methods on both benchmark test functions and real-world applications. The results show that aMeGP is generally better than both GP-based and nonGP-based reference methods with its evolved solutions achieving lower root mean square error (RMSE) for most test cases. Moreover, aMeGP outperforms the reference GP-based methods in the convergence ability, which can converge to lower RMSE values with faster or similar speeds.