The use of Cocos nucifera (coconut shell) ash as a supplementary cementitious material has shown potential in enhancing the compressive strength of concrete. However, the optimal calcination temperature and duration for producing effective ash remain uncertain. This study employs a Central Composite Design (CCD) to investigate the effect of calcination on concrete strength. Nine combinations of temperatures 550°. to 800°C) and durations (1 to 3 hours) were tested, producing 13 samples, which were cured for 28 days before compressive strength testing. X-ray Fluorescence (XRF) analysis identified 15 elements, with iron significantly influencing strength. The highest compressive strength (24.9 MPa) was achieved at 675°C for 2 hours, where iron content reached 16.63 %. A full quadratic regression model was developed, with an R2 of 79.47 %, and backward elimination refined the model to a predicted R2 of 67.32 %. Sensitivity analysis revealed temperature as the most significant factor, with a sensitivity value of 14.53 compared to 1.48 for duration. Optimization indicated the ideal calcination temperature to be 672.81° C. This study supports sustainable development goals by advancing innovative materials for infrastructure and by promoting the use of agricultural waste, reducing the environmental footprint of concrete production.

This study aimed to develop models for predicting trip frequency in San Jose City, Province of Nueva Ecija, Philippines incorporating socio-demographic factors (SDF) and attitudinal factors (AF) through the use of artificial neural network (ANN). Socio-demographic factors in the model include age, sex, civil status (CS), number of children (NOC), barangay, number of household members (NHM), educational attainment (EA), employment status (ES), household income (HI), number of driver license holder (DLH), number of personal vehicles owned (PVO), and number of vehicles owned by the household (VOH) while the attitudinal factors in the model include car dependency (CD), convenience, speed, privacy and safety (PS), health and environment (HE), cost, and comfort. The collected data were processed to develop ANN model in different pandemic stages with 19-19-1 (input-hidden-output) network structure used for these models. The sensitivity analysis (SA) results indicate that in the pre-pandemic period, employment status is the most influential parameter (MIP) to the trip frequency in the study area, while the educational attainment is the MIP during the pandemic period and in the post-pandemic period. The findings of the study signify the effectiveness of ANN in forecasting trip frequency as evident to the low mean absolute percentage error (MAPE) values obtained for the three models. The results can be used by policymakers in making informed strategies in further improving the travel experience of the population in the study area.

The inclusion of Artificial Intelligence (AI) and Machine Learning (ML) into cybersecurity education offers a significant opportunity to customize learning, improve engagement, and connect theoretical concepts with practical applications. This study presents the Dynamic Integration and Optimization of NetCyber Activities (DIONA) system which is an AI-enhanced educational tool developed from the NetFusion Learning Academy (NLA) to tackle ongoing issues in conventional cybersecurity education, including restricted adaptability, absence of real-time feedback, and inadequate practical skill application. The study employs a systematic methodology based on four distinct objectives: (1) to assess the efficacy of NLA in improving student learning across five critical domains— knowledge retention, practical skills, engagement, conceptual understanding, and problem-solving; (2) to examine student and faculty perceptions of its educational value; (3) to develop the ACTIVE AI Framework for AI-driven pedagogy; and (4) to create and validate DIONA as an AI/ML-based experiential learning platform. Statistical and thematic analyses indicated that although NLA effectively enhances knowledge and engagement, deficiencies persist in practical skills and problem-solving, necessitating the incorporation of AI-powered tools. The ACTIVE AI Framework and DIONA system offer customized learning trajectories, AI-generated feedback, and immersive simulations that correspond with authentic cybersecurity challenges. Results endorse the significance of intelligent learning analytics and specialized AI systems in transforming technical education and equipping students for changing digital environments.

The construction sector is a substantial generator of waste and carbon dioxide emissions worldwide. The use of sustainable materials in construction could minimize its negative effects on the environment. This research is intended to offer a soft computing model for predicting the deformation and parallel bending strength (PBS) of Guadua angustifolia applying an artificial neural network (ANN)-particle swarm optimization (PSO) approach and employing the data obtained from the experimental tests performed in the study. The input parameters (IP) utilized in the modeling process include the outside diameter, wall thickness, minimum length, external taper, perpendicular distance of bow, ISO ovality, eccentricity, actual shear span, area, modulus of elasticity, density, and linear mass. The resulting models showed R values of 0.99076 and 0.99976 and MAPE of 0.936% and 0.345% for deformation and PBS, respectively. The findings of the sensitivity analysis (SA) also exhibited that ISO ovality and eccentricity were the most important parameters to the deformation and PBS models. Research outcomes demonstrated the effectiveness of the ANN-PSO approach for predicting the deformation and parallel bending strength characteristics of Guadua angustifolia. The modeling approach proposed in this study could be utilized for speeding up the material characterization phase of similar construction materials.

The world is rapidly changing and experiencing a rapid increase in population, especially in cities and urban areas. The growth in population in these urban areas results in a need for a more competitive and sustainable system. In the onset of the fourth industrial revolution, the trend in equipping these cities with advanced mechanisms in improving the quality of life and service in these cities is needed. In this study, a neural network - based approach for factor prioritization was implemented to determine the most influential factor in the smart city (SC) development implementation in the Philippines. Using the neural network internal characteristics including the Levenberg-Marquardt (LM) as the training algorithm (TA) and the hyperbolic tangent sigmoid (HTS) as the transfer function (TF). The study utilized the 18-37-1 network structure for the neural network model with an R value of 0.95003 and MSE of 0.032609. The connection weights (CW) from this network were utilized to calculate the relative importance (RI) of the factors affecting the smart city implementation through Garson's Algorithm (GA). The results of the study revealed that the most influential parameter (MIP) to the smart city implementation is the SCPD2 - analyzing solutions fit with strategic objectives. Moreover, the results and findings of the study could assist the city planners and SC strategy development authorities in the integration of different systems in the SC implementation.

As part of economic progress, there has been a surge in construction projects in the past few years. It is known that construction has negative and detrimental effects on the environment. The use of sustainable practices needs to be integrated into the construction processes to minimize these negative impacts. This paper introduces a prioritization method for determining the most influential factor to the implementation of environmental smart guidelines for sustaining environmentally friendly programs using sensitivity index (SI) method. Several areas were considered in this study including environmental, ecological, social, and economic impacts. Using the backpropagation-neural network (BPNN) modeling, four models for environmental, ecological, social, and economic impact ratings were developed with 15-31-1, 4-9-1, 9-19-1, and 2-5-1 network topologies (input neuron-hidden neuron-output neuron) for environmental, ecological, social, and economic impact rating, respectively. The R values for the models were observed to range from 0.97652 to 0.99901. To determine the trend of the impact of the subsets of each areas, sensitivity index method was used and the findings revealed that the water pollution reduction in the project is the most influential subset to the environmental impact rating, presence of planting area in the project for the ecological impact rating, fair sharing of benefits of the project for the social impact rating, and self-liquidation capacity of the project for the economic impact rating. The results of the study could assist managers and planners in addressing key areas and concerns in the effective implementation of smart and sustainable practices in projects.

crucial component of growth in infrastructure is estimating construction costs (CC) for pipelaying projects (PP) related to water distribution networks, which guarantees the effective and long-term provision of safe drinking water to communities. In this paper, an artificial neural network (ANN) and multiple linear regression (MLR) model was developed for predicting construction cost for pipelaying projects. The governing model (GM) has a model structure of 9-20-1 (input-hidden-output) with an R = 0.99992. The findings revealed that the ANN-based network was 13.127 times better than the MLR model, based on its MAPE of 3.214 and 42.194%, for ANN and MLR, respectively. The best network also has the lowest Akaike Information Criterion (AIC) among the simulated network structures indicating that it is the best network. The relative importance (RI) of the independent variables including the length, diameter, material type, hydrotesting works, disinfection works, demolition works, restoration works, duration delay, and liquidated damages were calculated utilizing the Garson’s algorithm (GA). It was seen using GA to compute the relative importance of each parameter that the order of influence is seen as restoration works (RW) > length > demolition works (DeW) > material type (MT) > diameter > disinfection works (DiW) > hydrotesting works (HW) > duration delay (D%) > liquidated damages (LD) wherein the restoration works is the most influential parameter. The findings of the study could be used as a reference for better planning and managing pipelaying project activities.

In this paper, the performance of feed-forward backpropagation (BP)—artificial neural network (ANN) was evaluated in predicting the construction project cost (CPC). The models include several factors involving the floor area (FA), number of floors (NF), structural material type of the building (MT), height of the building (HB), number of columns (NC), area of the concrete hollow blocks wall (CHB), volume of concrete (VC), weight of steel (WS), and contract duration (CD). The developed neural network model was evaluated based on several accuracy metrics such as correlation coefficient (R), mean squared error (MSE), mean absolute percentage error (MAPE), and Akaike Information Criterion (AIC). The simulation results showed that the governing model has an excellent R value of 0.99885 and a MAPE of 2.5826%. The comparison results between the ANN and multiple linear regression (MLR) suggest that the ANN model provided superior performance with MAPE which is 4.777 times better than that of the MLR model. Moreover, the lowest AIC value was observed in the 9–21-1 network structure suggesting that this is the governing network model for predicting the CPC. The sensitivity analysis (SA) using Garson’s Algorithm (GA) quantitatively determines the relative contribution (RC) of the input parameters (IP) to the construction project cost. The developed model could be utilized as a support instrument for minimizing the cost overruns and losses that may have been incurred in a construction project (CP).

Transportation is critical, especially in rural areas as it provides the mobility to people to access different activities satisfying their daily needs. The purpose of this research is to create an artificial neural network (ANN) trip generation model (TGM). 500 households (HH) were surveyed to obtain the independent variables used in the modeling process including the HH size (HHS), number of children in the HH below 7 years old (NCHHBS), number of HH member from 7 to 59 years old (NHHMSF), number of HH member above 59 years old (NHHAF), number of working member of the HH (NWMHH), number of school children in the HH (NSCHH), number of helpers in the HH (NHHH), number of motorize vehicles in the HH (NMVHH), HH income (HHI), highest educational attainment (HEA), head of HH age (HHHA), and number of driver’s license holder in the HH (NDLHHH). Using the Levenberg–Marquardt algorithm (LMA) as the training algorithm (TA) and hyperbolic tangent sigmoid (HTS) function as the activation function (AF), the governing TGM was observed in the 12–25-1 network structure with the highest R value = 0.98476 and least Mean Absolute Percentage Error (MAPE) of 9.04%. Moreover, the governing network structure achieved the minimized Akaike Information Criterion (AIC) value at 25 hidden neurons (HN) indicating that the network has already been generalized and was the best model among those observed in this study. The outcomes of the research showed the efficacy of artificial neural networks in developing trip generation prediction models (PM).

The COVID-19 pandemic disrupted work systems, family, and social life. The mandatory lockdown forced employees to shift to work-from-home (WFH) setup which exposes them to WFH conflicts. This study provides a machine learning—based approach for prioritization of factors affecting WFH conflicts during the COVID-19 pandemic. These factors include time spent with the family (F1), leisure activities (F2), household task (F3), family quality of life (F4), agitation and anger from work (F5), financial obligations (F6), family presence (F7), family issues (F8), health-related (F9), and work burn-out (F10). Using the backpropagation (BP)-artificial neural network (ANN) modeling and Olden’s connection weights (CW) approach, the order of influence of these parameters to the productivity rating (PR) was observed. Based on the results, the 10-21-1 network structure is the best performing model (BPM) with correlation coefficient (R) = 0.98173 and mean squared error (MSE) of 0.02607. This network topology also provided the least Akaike Information Criterion (AIC) value showing that it is the best model. Using its connection weights (CW) through Olden’s approach, the results showed that the financial obligations are the most influential parameter (MIP) while the household task is the least influential parameter to the productivity model. The utilization of machine learning techniques proved to be effective in determining the influence of predictors on the target output. The obtained findings from the study could assist the organization and managers in resolving work-from-home conflict and productivity issues.