In this paper, we analyze the effect of the representative spectral indices, normalized difference vegetation index (NDVI), normalized difference water index (NDWI) and normalized difference built-up index (NDBI) on classification accuracies of Landsat-8 OLI image. After creating these spectral index images, we propose five methods to select the spectral index images as classification features together with Landsat-8 OLI bands from 1 to 7. From the experiments we observed that when the spectral index image of NDVI or NDWI is used as one of the classification features together with the Landsat-8 OLI bands from 1 to 7, we can obtain higher overall accuracy and kappa coefficient than the method using only Landsat-8 OLI 7 bands. In contrast, the classification method, which selected only NDBI as classification feature together with Landsat-8 OLI 7 bands did not show the improvement in classification accuracies.

Microalgae offer promising and multifaceted solutions to the ongoing issues regarding energy security and climate change. One of the major bottlenecks in utilizing algal biomass is the excessive amount of moisture to be managed after harvest, which translates to costs in the dewatering step. Newer strategies have been developed to be able to convert algal biomass feedstock to biodiesel without the need for extraction and drying, such as in-situ transesterification. This process can be improved by concurrently subjecting the system under subcritical conditions, which could also potentially remove the use of catalysts as well as offer tolerance to free fatty acid content of the feedstock. A definitive screening design of experiment was utilized to provide an acceptable prediction on the effects of key process parameters – temperature, reaction time, and solvent-to-solid ratio to the obtainable fatty acid methyl ester (FAME) yield and process power consumption. The optimum operating condition, which combines the benefits of maximizing the FAME yield and minimizing the process power consumption was found to be at 220 °C, 2 h, and 8 ml methanol per gram of biomass (80 wt% moisture). This produces a FAME yield of 74.6% with respect to the maximum obtainable FAME. Sensitivity analysis discussed the implications regarding the weight of importance between the two responses of interest. The benefits of the proposed process can be observed when compared to its conventional transesterification counterpart in terms of energy savings and reduced environmental impact. Hence, this process offers a feasible alternative to produce biodiesel from microalgae.

This study utilized data mining and geo-mapping methods to develop a fire risk management system for the Bureau of Fire Protection (BFP) in the city of Manila. This system was integrated into a web portal where the BFP personnel can log and view fire incident reports, which are then evaluated and mined for marking fire “hot spots” on a customized map of the city, as well as for producing recommendations based on the risk level assessment of any location for a given date. Based on results of experimentation, the Decision Tree classifier model was selected, with 95.92% accuracy. Geocoding produced 92% output of geographical coordinates from address information in the data set. The system can help the fire agency in raising the fire risk awareness of the community country and in facilitating their fire risk reduction planning.

Organizations are challenged to achieve effective and competent results, rising to imminent importance of measuring the performance efficiency. Data Envelopment Analysis (DEA) is an approach that measures performance efficiency of organizations. It is a non-parametric method, which uses linear programming to calculate efficiency in a given set of decision-making units (DMUs). It has widespread application in identifying efficiency and discovering benchmark. In the study, it utilized DEA in identifying School-Based Management (SBM) performance efficiency of one (1) division comprising of elementary and secondary schools - under Department of Education (DepEd) in the Philippines. Efficient schools were used as benchmark for improvement of inefficient schools. The schools had also undergone clustering, which is the process of grouping in accordance to similar characteristics. K-Means clustering algorithm was used to group the schools according to their respective profile. K-Means clustering is a simple unsupervised learning algorithm that follows a simple procedure of classifying a given data set into a number of clusters. The study also encompasses the development of an application system that utilizes data from DEA and K-Means clustering algorithm. The application system also provided recommendations to help inefficient schools improve.

Advances in computing and the availability of massive health data are opening up new possibilities for the generation of helpful decision-support tools. Forecasting the incidence of medical cases, which is one of the first steps in institutional planning, plays an important role in planning health control strategies in order to develop intervention programs and allocate resources. This study focused on medical cases forecasting for the development of resource allocation recommender system. Data cleaning was performed in the historical data of medical cases from Mabalacat City Health Office in order to detect and removing corrupt and inaccurate records. The forecasting models used are Seasonal Auto-Regressive Integrated Moving Average (S-ARIMA) and Exponential Smoothing (ES). Factor values of twelve (12) for monthly seasonality and four (4) for quarterly seasonality were used for the S-ARIMA models. The alpha values used in ES are 0.1, 0.3, 0.5, 0.7 and 0.9. The computed Mean Absolute Deviation (MAD) and the Mean Absolute Percent Error (MAPE) results of S-ARIMA and ES were compared and the forecasting model with the better accuracy was used for a particular medical case forecast value. The use of the mentioned forecasting algorithms and accuracy tests were embedded in the development of an online information system with resource allocation recommender for Mabalacat City health units.

The production of fiber-reinforced concrete presents a complex reaction system, posing significant challenges in determining appropriate material proportions to achieve targeted mechanical properties. To address this issue, this study proposes novel Artificial Neural Network (ANN) models for predicting the compressive and flexural strengths of fiber-reinforced concrete using a backpropagation feed-forward algorithm. A wide range of concrete mix designs was prepared and tested using cylindrical samples for compressive strength and beam samples for flexural strength. Polypropylene fibers were incorporated into the mixes, and all specimens were cured for 28 days in a water-saturated lime solution. The results demonstrated that the ANN models produced strength predictions that closely aligned with experimental data, yielding high correlation values of 99.46% and 98.57% for compressive and flexural strengths, respectively. The best-fit models exhibited mean squared errors of 0.0024 (compressive) and 0.44 (flexural). Furthermore, parametric analysis indicated that the proposed models effectively captured the constitutive relationships among the concrete components and successfully represented the dominant mechanical behavior of the tested specimens.

A trigeneration system consists of interdependent technologies for power generation, heat generation, and the generation of cooling effect which leads to the overall improved thermodynamic efficiency of the system. However, the optimal design of a trigeneration system also depends on the product price variability of the energy streams which are highly dependent on the price of the raw materials and the product demand. Taking into consideration expected price fluctuations of streams, it is then possible for plant owners and engineers to evaluate the investment risk associated with the design capacity of a trigeneration system. The study proposes the use of a 2k factorial design of experiments together with fuzzy linear programming to conduct a price sensitivity analysis in the optimal design of a trigeneration system. This type of analysis can provide plant owners information on possible configurations for optimal capacity given uncertainty in the price parameters.

A trend arises among industrial and government sectors to transition from the conventional economic system to the new Circular Economy. Its benefit of material security, resource efficiency, and economic growth has attracted government institutions and business sectors to adopt the new trend. However, its challenge falls on the real complexities of economic systems. Adoption of the Circular Economy requires careful consideration of possible challenges. Previous works have aimed to identify the drivers of Circular Economy through surveys based on the frequency of data. The results provided useful information for the decision making of the transition. However, it is also limiting as it does not address a plausible chain-like effect of the drivers which can aid stakeholders determine which course of action is necessary for an efficient transition. Hence, this study is focused in determining these causal drivers by using the DEMATEL approach. DEMATEL is a methodology that identifies the cause and effect relationship between drivers, of which, it can then determine the top causal driver. The study uses a case study in the Philippines to illustrate the capability of the methodology of determining the causality between drivers of Circular Economy. The results of the case study were able to identify ‘economic attractiveness’, with a net cause/effect value of 1.22, and ‘consumer demand’, with a net cause/effect value of 0.87, as the main causal driver while ‘company culture’, with a net cause/effect value of -1.22, as the main effect. The result implies that the improvement in the circular business models and increase in customer awareness are the top priority for the transition. The application of this work is intended to provide researchers an alternative approach in identifying the critical causal drivers of Circular Economy.

Electric vehicle offers a cleaner and sustainable alternative to transportation as it eliminates direct carbon dioxide emission through the conventional internal combustion engine. With the increase in the global population and economic development, the demand for transportation and the adoption of electric vehicles is unprecedented. However, the adoption of electric vehicle on a national-scale requires long-term planning of infrastructure development, and energy generation and distribution. The study focuses on the development of a systematic mathematical programming approach in the optimal planning of the energy mix of the additional power generation capacity arising from the adoption of the electric vehicle in a developing country. The study considers the 2030 horizon which includes, the cost of power generation and distribution per energy mix, and the forecasted commissioning and decommissioning of energy plants. The study proposes a fuzzy mixed-integer non-linear programming model in the optimal planning of the energy mix for the adoption of EV while minimizing carbon footprint, minimizing the total capital cost, and minimizing the electricity cost. A case study in the adoption of electric vehicle in the Philippines will be utilized to demonstrate the capability of the model. In addition, a comparison of the electricity cost of the business as usual (BAU) scenario and this study has been evaluated. The results show that the various renewable energy technologies for power generation are selected initially from 2019 to 2022 and 2029 to 2030, while the fossil-fuel based power plants were utilized from 2023 to 2028. The results revealed the electricity cost from the study is relatively lower than the BAU scenario. The results of the model are intended to aid and guide policymakers in the potential adoption of electric vehicles, especially in the energy planning sector.