Stepwise Regression Technique Research Articles

Predictive Models to Estimate Construction and Life Cycle Cost of Conventional and Prefabricated Bridges During Early Design Phases

State DOTs often need to decide during the early design phase whether to build their bridges using conventional or prefabricated construction methods based on overall cost-effectiveness. This often requires DOTs to develop reliable cost-estimates of these alternative construction methods with only limited available data during the early design phase. To support DOTs in this challenging task, this paper presents the development of a practical decision support tool that integrates novel bridge cost estimating models. These models were developed using stepwise, LASSO, and best subset regression techniques and a dataset of 241 conventional and prefabricated bridges. The developed LASSO model outperformed the two other models, achieving a mean absolute percentage error of 12.3% for conventional and 14.4% for prefabricated bridge projects. The developed DST and its cost-estimating models are expected to support bridge planners in identifying the most cost-effective bridge construction method during the early design phase.

Development of High-Strength Ceramsite via Sintering of Iron Ore Tailings: Process Optimization and Properties

This study focuses on the utilization of iron ore tailings for synthesizing high-strength concrete aggregate as a sustainable alternative to conventional stone aggregates, which are often obtained through environmentally harmful quarrying practices. The research investigates the feasibility of producing high-strength ceramsite using iron ore tailings, fly ash, and bentonite as primary raw materials. Through a uniform design method, the study deeply explores the role of iron ore tailings. To understand the relationship between compressive strength and the components used, first- and second-order polynomial equations were developed and thoroughly analyzed using stepwise regression techniques. This approach enabled the optimization of material ratios, leading to the achievement of the desired results. Additionally, the study examines the impact of varying sintering temperatures on the compressive strength, density, and water absorption of the ceramsite. Under optimized conditions, the resulting ceramsite exhibited impressive properties, with an average compressive strength of 52.33MPa, an apparent density of 2,600kg/m³, and a water absorption rate of 0%. This research highlights the potential of iron ore tailings as a sustainable alternative in the construction industry, emphasizing the development of eco-friendly building materials while reducing environmental impacts.

Comparative analysis of deep neural network and artificial neural network for predicting wheat water content using UAV multispectral and thermal imagers

Water is a vital component for the growth of wheat and the quality of its grains. The measurement of plant water content (PWC) serves as a crucial indicator for assessing the water status of crops, thereby guiding effective irrigation management practices. Recent advancements in technology, particularly the use of multispectral and thermal imaging from unmanned aerial vehicles (UAVs), offer the capability to capture a comprehensive view of PWC variability across agricultural fields. This study aimed to create predictive models for PWC utilizing artificial neural networks (ANN), deep neural networks (DNN), and traditional stepwise regression techniques, all based on the analysis of multispectral and thermal imagery. To effectively evaluate the protein content in wheat, we combined high-resolution thermal and multispectral imaging techniques with machine learning approaches. This assessment was carried out through three distinct experiments, which included one conducted in a rainout shelter and two performed under rainfed conditions. The findings demonstrated that UAV-derived multispectral imagery, when coupled with machine learning models, can effectively predict wheat plant water content with remarkable precision. Notably by considering all the dataset, DNN model exhibited superior performance (R2=0.96, ENS=0.98, RMSE=1.37%, MAE=0.98%) compared to both the ANN (R2=0.95, ENS=0.95, RMSE=1.88%, MAE=1.46%,) and the stepwise regression model (SRM) (R2=0.67, ENS=0.51, RMSE=10.79%, MAE=9.03%). Across all machine learning approaches, both the DNN and ANN models significantly outperformed the stepwise regression model in predictive accuracy. The statistical outcomes derived from the calibration phase indicate that both the trained Artificial Neural Networks (ANN) and Deep Neural Networks (DNN) serve as effective instruments for accurate prediction of PWC. Notably, the DNN network demonstrates superior accuracy compared to ANN.

Contrast-Enhanced Ultrasound-Based Radiomics for the Prediction of Axillary Lymph Nodes Status in Breast Cancer.

Breast cancer is the leading cause of cancer-related deaths in the female population. Axillary lymph nodes (ALN) are a group of the most common metastatic sites of breast cancer. Timely assessment of ALN status is of paramount clinical importance for medical decision making. To utilize contrast-enhanced ultrasound (CEUS)-based radiomics models for noninvasive pretreatment prediction of ALN status. Clinical data and pretreatment CEUS images of primary breast tumors were retrospectively studied to build radiomics signatures for pretreatment prediction of nodal status between May 2015 and July 2021. The cases were divided into the training cohorts and test cohorts in a 9:1 ratio. The mRMR approach and stepwise forward logistic regression technique were used for feature selection, followed by the multivariate logistic regression technique for building radiomics signatures in the training cohort. The confusion matrix and receiver operating characteristic (ROC) analysis were used for accessing the prediction efficacy of the radiomics models. The radiomics models, which consist of six features, achieved predictive accuracy with the area under the ROC curve (AUC) of 0.713 in the test set for predicting lymph node metastasis. The CEUS-based radiomics is promising to be developed as a reliable noninvasive tool for predicting ALN status.

Forecasting wheat productivity in Punjab, India: A weather-based model approach using detrended data and regression analysis

Weather-based models were developed to forecast the wheat productivity of three districts in Punjab (India) could accurately predict wheat yields two and a half months before the crop harvest. The trends in weather parameters were identified using Mann-Kendal, Sen’s Slope and Pettitt’s test.The logistic model was declared best among linear and non-linear models to remove the effect of technological factors over time. The detrended data was used for forecasting wheat productivity based on fourteen weeks of weather data of the vegetative period. The stepwise regression technique for detrended wheat productivity on weather indices revealed model II best for Amritsar, Ludhiana and Patiala districts, explaining 60%, 67% and 52% variation in the detrended wheat productivity and had root mean square percentage error 8.57%, 6.93% and 6.20% respectively. The model concluded that warm maximum and cool night temperatures of the wheat growing season will increase detrended wheat productivity, whereas an increase in rainfall and relative humidity in the morning will decrease detrended wheat productivity and hence the production.

Feasibility of Vis-NIR spectroscopy approach to predict soil biological attributes in arid land soils.

Visible and near-infrared (Vis-NIR) reflectance spectroscopy has recently emerged as an efficient and cost-effective tool for monitoring soil parameters and provides an extensive array of measurements swiftly. This study sought to predict fundamental biological attributes of calcareous soils using spectral reflectance data in the Vis-NIR range through the application of partial least square regression (PLSR) and stepwise multiple linear regression (SMLR) techniques. The objective was to derive spectrotransfer functions (STFs) to predict selected soil biological attributes. A total of 97 composite samples were collected from three distinct agricultural land uses, i.e., sugarcane, wheat, and date palm, in the Khuzestan Province, Iran. The samples were analyzed using both standard laboratory analysis and proximal sensing approach within the Vis-NIR range (400-2500 nm). Biological status was evaluated by determining soil enzyme activities linked to nutrient cycling including acid phosphatase (ACP), alkaline phosphatase (ALP), dehydrogenase (DEH), soil microbial respiration (SMR), microbial biomass phosphorus (Pmic), and microbial biomass carbon (Cmic). The results indicated that the developed PLSR models exhibited superior predictive performance in most biological parameters compared to the STFs, although the differences were not significant. Specifically, the STFs acceptably accurately predicted ACP, ALP, DEH, SMR, Pmic, and Cmic with R2val (val = validation dataset) values of 0.68, 0.67, 0.65, 0.65, 0.76, and 0.72, respectively. These findings confirm the potential of Vis-NIR spectroscopy and the effectiveness of the associated STFs as a rapid and reliable technique for assessing biological soil quality. Overall, in the context of predicting soil properties using spectroscopy-based approaches, emphasis must be placed on developing straightforward, easily deployable, and pragmatic STFs.

Stand spatial structural diversity: Developing and validating a novel index

Numerous studies related to the diversity-productivity relationships have mainly focused on the effects of species diversity, function diversity, and nonspatial structural diversity (e.g., variations of diameter), but have overlooked the significant roles of spatial structural diversity. Therefore, the motivation of the present study was to develop a comprehensive index of stand spatial structural diversity (H′) by integrating the strengths of the Shannon-Wiener index and the quaternion joint probability distribution of commonly used neighborhood-based parameters, namely the uniform angle index (W), mingling index (M), diameter dominance index (U) and crowdedness index (C). The application abilities of the index were tested using ten 100 m ×100 m sample plots that were distributed in three different climate zones [4 plots in Greater Khingan Mountains (GKM), 2 plots in Lesser Khingan Mountains (LKM), 4 plots in Changbai Mountains (CBM)] in Heilongjiang Province, northeast China. Meanwhile, the potential driving factors on stand spatial structural diversity were also detected using stepwise regression and hierarchical partitioning techniques based on 3000 simulated stands. The results indicated that the average values of H′ at GKM, LKM, and CBM were 0.8436, 0.8079, and 0.8098, suggesting that the stand spatial structural diversities of the forests in GKM were notably higher than those in LKM and CBM. The characteristics of M, C, and W emerged as the three most influential factors driving stand spatial structural diversity. This study contributes significantly not only by providing an effective index for measuring stand spatial structural diversity, but also by streamlining the complex decision processes associated with optimizing stand spatial structure.

IS VIETNAM'S TOURISM DEMAND MODEL COMPATIBLE WITH THE EXTENDED GRAVITY MODEL?

The purpose of this study is to use an extended gravity model to examine the factors that influence the demand for tourism from origin nations to Vietnam. Data from eleven major marketplaces were gathered for the study between 2005 and 2020. The research employs stepwise regression techniques to choose variables and testing procedures to identify the most suitable model among Ordinary Least Squares (OLS), Random Effects Model (REM), Fixed Effects Model (FEM), and Feasible Generalized Least Squares (FGLS) models. The gravity model comprises variables associated with geographic features, tourism supply capacity, demand attributes, and interconnected variables. Surprisingly, geographical distance holds no statistical significance in the international tourist demand model based on the gravity model, a phenomenon bolstered by globalization. Conversely, the emerging investment factor in restaurants and hotels emerges as the most pivotal determinant influencing tourism demand. Hence, the tourism sector must devise nation-specific policies that target key influencing factors and actively appeal to potential source markets to attract visitors.

Transforming waste perlite into super lightweight ceramsite: Ratios optimization via uniform design, and investigating calcium fluoride and silicon carbide effects on foaming

The utilization of waste perlite powder generated from mining operations in the construction industry represents a significant step towards enhancing environmental sustainability. This study applies a uniform design of experiments to delve into the apparent density characteristics of super lightweight ceramsite concerning the proportions of solid waste materials, with a particular focus on waste perlite powder. To gain insights into the apparent density, first- and second-order polynomial equations were developed. These equations are founded on the utilization of five core raw materials, including waste perlite powder, fly ash, bentonite, calcium fluoride, and silicon carbide, and were meticulously analyzed using stepwise regression techniques. This approach led to the successful optimization of test ratios, achieving the envisioned outcomes. Additionally, the research explores the influence of calcium fluoride and silicon carbide on the foaming properties of materials under varying maximum sintering temperature conditions. Ultimately, the optimized conditions yielded super lightweight ceramsite with impressive properties, boasting a bulk density of 281 kg/m³, water absorption efficiency of 1.2%, and a compressive strength of 2.72 MPa. This research showcases the potential for utilizing waste perlite powder in the construction industry, not only as a sustainable alternative but also as a means to reduce environmental impact. The development of super lightweight ceramsite underlines the promise of eco-friendly construction materials, driving forward the agenda of environmentally responsible building practices.

Environmental factors influence the responsiveness of potato tuber yield to growing season precipitation

Understanding how environmental factors influence the responsiveness of crop yield to growing season precipitation (GSP) can reduce the risk of yield fluctuations, ensuring stable crop production. This study involved the cultivation of rainfed potatoes at three locations within the climatic transition zone of Northwest China. We employed stepwise linear regression and machine learning techniques to pinpoint the key environmental factors influencing potato tuber yield and the yield-precipitation relationship. The slope of the water-limited yield potential relationship for potatoes was determined to be 172.1 ​kg ​ha−1 ​mm−1, with an intercept at 121.2 ​mm. The potato tuber yield exhibited an upward trend with increasing GSP but declined once the precipitation exceeded 400 ​mm. However, GSP alone explained up to 30% of the variability in potato tuber yield. Factors such as soil moisture at planting, maximum temperatures during the tuber stolon initiation and bulking stages, diurnal temperature fluctuations at maturity, and excessive precipitation events during the growing season significantly influenced potato tuber yield, and consequently, the relationship between yield and GSP. Conversely, climatic factors accounted for more than 63% of the variation in potato tuber yield, with the multiple linear regression model yielding the best results. This was especially evident when the yield-precipitation relationship was categorized into two groups based on the amount and distribution of GSP, maximum temperature, and radiation levels. This analysis suggested that preventing unnecessary water evaporation when precipitation is low, improving drainage when precipitation is high, and planting potato on an optimal date can advance potato production.

The Effectiveness of the Anti–Drug Program to Drug Reformists of Barangay Bato and its Effect on Their Human Well–Being

This study aims to comprehensively investigate the effectiveness of an anti-drug program and its impact on the human well-being of 35 Drug Reformists residing in Barangay Bato, Toril, Davao City. The research focuses on three key components of the anti-drug program, namely the livelihood program, spiritual program, and educational program, serving as indicators for evaluating their effectiveness in contributing to the well-being of drug reformists. The research considers variables such as the financial, educational, and spiritual aspects to discern their influence on the overall well-being of the participants.
 The comprehensive research method employed in this study involves the collection of quantitative data through structured questionnaires. Descriptive statistics are utilized to present a detailed analysis of the data, providing insights into the demographic characteristics and initial conditions of the participants. Furthermore, regression analysis, specifically the stepwise regression technique, is applied to identify the relationships between the variables and to determine the significant predictors of human well-being among drug reformists.
 The results of the analysis revealed a high correlation between the variables, highlighting the intricate interplay between the effectiveness of the anti-drug program and the human well-being of the participants. Notably, the stepwise regression analysis excluded the educational program indicator, suggesting that it does not significantly influence the human well-being of drug reformists in this context. This finding contributes valuable insights for policymakers and practitioners involved in anti-drug initiatives, emphasizing the need for a nuanced approach that prioritizes certain program components over others based on their impact on human well-being.

The Inheritance and Innovation Path of Wuhua Tea Casting Opera Music under the Perspective of Chinese Modernization

Abstract This study explores the dynamics of inheritance and innovation within opera, focusing specifically on Wuhua Caicha Opera, a key cultural asset in Lotus County. Utilizing a mixed-method approach that includes questionnaire surveys and field interviews, this paper systematically examines the current status of Wuhua Caicha Opera's transmission. We collected and analyzed data using a robust statistical model in SPSS, which integrates principal component analysis and stepwise regression techniques. The findings reveal that the self-factors and governmental influences on the preservation and development of the Wuhua tea-picking opera troupe in Lotus County have statistically significant impacts, with Sig. Values of 0.012 and 0.001, respectively. This indicates a notable effect of both intrinsic and extrinsic factors on the opera's transmission. However, less than half of the participants affirmed the current methods of heritage transmission, protection of cultural bearers, and innovation in the repertoire. The average scores for governmental influence on recognition were all above 3.6, suggesting a strong governmental role. The insights from this study provide empirical evidence that can guide policy formulations and support efforts to foster the sustainable evolution and transmission of Wuhua Caicha Opera.

Modeling the Risk of Liver Cancer in Adults: A Machine Learning Investigation into the Role of Obesity and Overweight

Background: Liver cancer is a global health concern, with overweight and obese individuals exhibiting an increased risk of its development. Understanding the interplay between obesity-related factors and liver cancer incidence is crucial for early prediction and intervention. Aim: The aim of this investigation was to construct and validate an extreme gradient boosting (XGBoost) based machine learning model for the purpose of establishing a one-year liver cancer risk prediction system specifically tailored to overweight and obese patients. In addition, this study sought to compare the predictive performance of the XGBoost model with those of a random forest model and a logistic regression model, while also identifying the most influential predictive features for liver cancer incidence. Methods: A comprehensive retrospective analysis was conducted on MIMIC III data comprising 2,354 patients. To predict the risk of liver cancer development, three machine learning models were developed: XGBoost, random forest, and logistic regression. Feature selection was executed using a stepwise regression procedure encompassing both forward selection and backward elimination. Results: The stepwise regression technique unveiled 14 predictive factors for liver cancer incidence. Among the patient cohort, 132 individuals developed liver cancer within a year of follow-up, while 2,222 did not. Notably, most liver cancer cases occurred in male patients (60%). Statistically significant differences were observed between patients with liver cancer and those without, in terms of age, gender, total bilirubin, platelet, albumin, chloride, potassium, sodium, prothrombin time (PT) and alanine aminotransferase (ALT). The XGBoost model exhibited an impressive area under the receiver operating characteristic curve (AUROC) of 99%, Random Forest (RF) of 99%, and Logistic Regression (LR) of 90%. In a multivariate analysis, total bilirubin, creatinine levels, age, gender, ALT, alkaline phosphate (ALP), PT, calcium, and chloride emerged as independent predictors for liver cancer incidence. Conclusion: The XGBoost model demonstrated superior predictive performance when compared to the RF and LR models. If corroborated through prospective studies, the XGBoost model may prove to be a valuable tool for the early prediction of liver cancer risk in overweight or obese individuals. Such predictive capabilities could, in turn, facilitate the implementation of timely preventive interventions against liver cancer.

Prediction of earth pressure balance for EPB-TBM using machine learning algorithms

Face stability control of excavation with earth pressure balance machine (EPB) approach is the best available method to reduce the ground deformation and settlement of surface structures in a tunneling project in urban areas. In the present paper, several models have proposed through a statistical method, including feed-forward stepwise regression (FSR) and machine learning techniques such as support vector machine (SVM), Takagi–Sugeno fuzzy model (TS), and multilayer perceptron neural network (ANN-MLP), to provide a predictive strategy for EPB machine during the tunnel excavation. For this purpose, a monitoring dataset of machine performance parameters including advance speed, screw conveyor speed, screw conveyor torque, thrust force, and cutterhead rotation speed from Tehran Metro Line 6 Southern Extension Sector (TML6-SE) has been compiled. Then, the relation between the performance parameters and target values were investigated to analyze the available inputs and offer a new equation using the FSR. Moreover, evaluation metrics and loss functions were utilized for the evaluation of the developed models’ efficiency. The results proved the significance of the presented methods in this paper that could be used to predict the earth pressure balance operation with high efficiency.

Assessment of drag prediction techniques based on radar data for supersonic vehicles

Flight testing is probably the most accurate approach for defining the aerodynamic characteristics of a flying vehicle. This is justified by the fact that compared to other approaches, either engineering or computational ones, flight testing is indeed the one that perfectly resembles the real flight environment. Flight data are either obtained by measuring the vehicle’s kinematics via onboard sensors or by tracking the vehicle’s flight via (commonly) radars. The advantages of the latter approach are evident in cases where modifying the vehicle design is not possible or in cases where rival/enemy vehicles are examined. The key issue for this approach is the quality and demands of the technique by which vehicle aerodynamic characteristics are reduced from flight-tracked data. In the open literature, different techniques are used to analyze radar data of vehicle position and utilize them to predict vehicle drag coefficient. Each technique has its strengths and pitfalls. In this paper, the three well-used techniques of drag estimation from radar data namely, Least Square (LS), Maximum Likelihood Estimation (MLE), and Stepwise regression (SR), are considered. The underlying principle, the output, and the range of validity for each technique are addressed with emphasis on what differentiates each of them. The viability and validity of the three techniques are addressed based on the own flight testing of a free-flight supersonic vehicle and using the point-mass flight model. Meteorological data are also recorded and flight conditions are used to enhance the resulting calculations. Based on experimental data available from the literature, a comparison is conducted for the techniques examined. Considering the lack of flight data utilized, and in conjunction with data from the literature, it has been concluded that the SR technique outperforms for a higher sample rate, however, the MLE is more feasible when there is a lack of data.

An Advancing Academic Leadership Preparation: Linking Best Methodological Practices to Leadership Behaviors in Ethiopia’s Public University Context

Linking best methodological practices in leadership preparation to leadership behaviors is a framework for investigating valuable leadership behaviors in learning organizations. However, the best subsets of methodological practices, that account for improving academic leadership behaviors are scant in public university terrain. This study intended to investigate the best subsets of methodological practices, which account for advancing academic leadership behaviors in the public university context. An equal stratified random sampling technique was employed to draw subjects. The author distributed 450 questionnaires to academic leaders in Ethiopia’s six public universities, of which 89%(401) were filled out and returned the questionnaires. Using SPSS-20, the author employed stepwise regression techniques to investigate the best subsets of methodological practices, which predict leadership behaviors. As a result, the investigated best subset of methodological practices are better at improving instructional leadership behaviors (39%) compared to improving transformational (15%), transactional(12%), and laissez-faire (1.5%) leadership behaviors. Multifactor feedbacks and action learning were the best subset, which predict transformational leadership behavior. More importantly, multifactor feedback, counseling, seminar, and action learning were the best subset, those predicting instructional leadership behaviors. Thus, there are best subsets of methodological practices, which account for academic leadership development in public university context. Key Words: Academic Leadership; Leadership Preparation; Best Practices; Public Universities

Towards understanding the type and function of indigenous goats: input for genetic improvement and conservation programme

ABSTRACT This study aimed to provide a better understanding of the type, function, and production potential of Central Highland goats. Morphometric measurements were collected from 510 heads of goats. About 17 biologically important structural indices were computed using morphological trait measurements. The data were analyzed using SAS’s general linear model, principal component analysis, and stepwise multiple regression techniques. Body index value indicate that the Central Highland goat’s shape is rectangular, which is good conformation for meat production. The dactyl thorax, transverse pelvic, longitudinal pelvic, relative depth of thorax, and width indices suggest their suitability for meat production. However, proportionality and length indices showed an aptitude for milk production. Besides, the body ratio and depth indices indicate less susceptibility of this goat breed to dust infestation and arthritis, good walking ability, good foraging capability, and move easily in sloppy areas. In conclusion, structural indices showed that Central Highland goats could be classified as having a dual purpose and better aptitude for meat production. The results of this study could be an input for designing genetic improvement and conservation programmes for the sustainable utilization of indigenous goats.

Weather-Based Rice Crop Yield Forecasting using Different Regression Techniques & Neural Network Approach for Prayagraj Region

Rice crop yield data and weather data were considered in this study, covering the past twenty-nine years (1991-2019) in Prayagraj District, Uttar Pradesh. The data was sourced from DACNET and the College of Forestry, SHUATS Prayagraj. The analysis comprised a calibration period of 26 years (90% of the dataset) and a validation period using the remaining data (10%). In this study, 75.9% of the data were utilized for training the Artificial Neural Network (ANN) model, while the remaining 24.1% were allocated for testing and validation, ensuring comprehensive model assessment. The primary evaluation metric employed for model efficiency was the Normalized Root Mean Squared Error (nRMSE), with a focus on achieving the lowest values. Both a Stepwise Linear Regression technique and a Neural Network were employed for rice yield prediction. Notably, the regression-based model exhibited superior performance compared to the ANN model, as indicated by the nRMSE values. This conclusion was drawn from the observation that the regression-based model yielded the best-fitting results. The study's findings highlight the significance of Bright Sunshine Hours in relation to nRMSE and the coefficient of determination, which were recorded at 0.00025 and 0.94, respectively. This underlines the importance of this meteorological factor in accurately predicting rice crop yield.

Dynamic estimation of rice aboveground biomass based on spectral and spatial information extracted from hyperspectral remote sensing images at different combinations of growth stages

Aboveground biomass (AGB) is an essential factor in rice ecological research. Optical variables (e.g. reflectivity and vegetation index (VI)) are widely adopted in monitoring AGB while spatial information (e.g. texture) is less introduced into research. Limited research is available regarding the impact on the monitoring accuracy caused by the utility of VI and texture in AGB estimation at different combinations of growth stages. To compare the improvements caused by the involvement of texture at different combinations of growth stages, a hyperspectral camera was mounted on an unmanned aerial vehicle (UAV) to obtain images of rice field during the early growth stages (including the tillering, jointing and booting stage) under five nitrogen levels over two years. Spectral and spatial information derived from images was utilized to compute VIs and textures at different combinations of growth stages. After analyzing their correlations with AGB, multiple stepwise regression (MSR) and multiple linear regression (MLR) techniques were employed to establish rice AGB models using vegetation index (VI), vegetation index combined with the corresponding-band texture (VI-CBT) and vegetation index combined with the full-band texture (VI-FBT). It was found that the models using VI and texture enhanced the capability of the conventional VI to estimate AGB at different combinations of growth stages. The combination of VI and FBT achieved the most accurate estimation, followed by the VI-CBT. Different combinations of growth stages had diverse responses to textures. Overall, the tillering stage had the maximum response to the involvement of textures, followed by the booting stage. Models using VI-CBT and VI-FBT significantly improved the AGB estimation at the booting and tillering stage, respectively. The monitoring accuracy of the jointing stage showed a slight response to the involvement of texture. At the multiple growth stages, the monitoring effect of the tillering-booting stages was significantly improved, followed by the jointing-booting stages either using the model based on VI-CBT or VI-FBT. Models using VI and texture tended to yield larger improvements on the error values at the extreme AGB levels. Near-infrared and red-edge bands were the sensitive bands to estimate rice AGB, and MEA, COR were favorable textures to monitor the AGB. This study quantified the model improvements of using VI and texture in rice AGB estimation at different combinations of growth stages, delivering guidance for timely and accurate rice management in the field.

Factors affecting paratransit travel time at route and segment levels

Paratransit users have reportedly been unsatisfied with the quality of service that they receive. Efforts at replacing the service or formalizing operations to meet users’ mobility needs have faced challenges or outrightly resisted. Approaches such as providing travel information and deploying interventions along the roadway infrastructure where the government has authority have been suggested. Deploying any of these approaches will require insights from empirical data. The study considered a key measure of service quality to users and operators alike – travel time. It investigated factors affecting the travel time of paratransit at the route and segment levels. A travel time survey that employed a mobile app (Trands) onboard paratransit vehicle was used to collect travel time, stop, and other related information on a selected route. The backward stepwise regression technique was used to determine factors affecting paratransit travel were. Dwell time, signal delay, recurrent congestion index (RCI), non-trip stops, and deviation from route were significant variables at the route level. All the factors affecting segment travel were also part of those involving route travel time except the segment length. Interestingly, deviation from the route increased overall travel time, which is against its logic. Insights gained from the study were used in suggesting proposals that can reduce travel time and improve the service quality of paratransit.