Arnel C. Fajardo

Arnel C. Fajardo

Auto-generated profile, based on publicly available information

Arnel C. Fajardo

Manuel L. Quezon University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 January 2020 in IEEE Access
Verified
Journal Article
Open access
Ying-Yi HongYing-Yi Hong
Ying-Yi Hong
JMJohn Joel F. Martinez
John Joel F. Martinez
AFArnel C. Fajardo
Arnel C. Fajardo
The operations of power systems are becoming more challenging on account of the high penetration of renewable power generation, including photovoltaic systems. One method for improving the power system operation involves making accurate forecasts of day-ahead solar irradiation, enabling operators to minimize uncertainty in managing the balance between generation and load. To overcome the limitations of Long Short-term Memory (LSTM) in a one-dimensional forecasting problem, this work proposes a novel method in forecasting solar irradiation by encoding time-series data into images using the Gramian Angular Field and the Convolutional LSTM (ConvLSTM) network. The pre-processed data become a five-dimensional input tensor that is perfectly suitable for ConvLSTM. The ConvLSTM network uses convolution operations in its input-to-state transition and state-to-state transition. The network thus enables time-series forecasting by a feature-rich approach, which ultimately provides competitive forecasting performance despite the use of a small dataset. The proposed method was evaluated in day-ahead solar irradiation forecasting using a univariate dataset of Global Horizontal Irradiation (GHI) data from Fuhai in Taiwan. The proposed method was resampled using 5×2-fold cross-validation, and assessed using the Wilcoxon signed-rank test to determine the statistical significance of the result. It outperformed benchmark methods such as Autoregressive Integrated Moving Average (ARIMA), Convolutional Neural Network cascaded with Long Short-term Memory (CNN-LSTM), and LSTM cascaded with a fully-connected (FC) network.

1 May 2018
Verified
Conference Paper
Closed access
EAEdwin Arboleda
Edwin Arboleda
AFArnel C. Fajardo
Arnel C. Fajardo
RMRuji P. Medina
Ruji P. Medina
The quality of coffee beans differs from each other based on the geographic locations of its sources. The coffee bean quality is conventionally determined by visual inspection, which is subjective, requiring considerable effort and time and prone to error. This calls for the development of an alternative method that is precise, non-destructive and objective. This paper was conducted with the objective of developing an appropriate computer routine that can characterize coffee beans from the different towns of Cavite, Philippines. Imaging techniques were employed to automatically classify the coffee bean samples according to their specie. Important coffee bean features based in morphology such as area of the bean, perimeter, equivalent diameter, and percentage of roundness were extracted from 195 training images and 60 testing images. Artificial neural network (ANN) and K nearest neighbor (KNN) were employed to automatically categorize the coffee beans. Using ANN, classification scores of 96.66% were achieved while using KNN the following classification scores were achieved 84.12%(k=1), 84.10%(k=2), 81.53%(k=3), 82.56%(k=4), 75.38%(k=5),80.35% (k=6), 38.79%(k=7), 77.44%(k=8), 72.82%(k=9) and 78.45% (k=10). In conclusion, the results of this study have revealed that imaging technique could be used as an effective method to classify coffee bean species. ANN is the more preferred method over KNN in classifying coffee beans.

1 May 2018
Verified
Conference Paper
Closed access
EAEdwin Arboleda
Edwin Arboleda
AFArnel C. Fajardo
Arnel C. Fajardo
RMRuji P. Medina
Ruji P. Medina
The quality of a coffee bean is determined by several factors including color, texture, and size. High quality beans are carefully refined where defects, such as black beans, are removed. The assessment through visual inspection may be subjected to external factors such as light and the amount of beans to be inspected. This study presents a method of controlling the coffee bean quality using Image Processing techniques. Normal beans are identified through the extraction of RGB color components of training image. The RGB values were integrated in an image processing technique that eliminated the black beans in the image. Using the technique in this study, a classification of 100% were achieved for eliminating the black beans in the testing images.

1 January 2020 in IEEE Access
Verified
Journal Article
Open access
Ying-Yi HongYing-Yi Hong
Ying-Yi Hong
JTJonathan Vidal Taylar
Jonathan Vidal Taylar
AFArnel C. Fajardo
Arnel C. Fajardo
The convolutional neural network (CNN) is commonly used in visual recognitions and classifications. However, CNN can also be applied as a forecaster that can extract features from spatiotemporal data. This paper proposes a 24h ahead electricity price forecasting method, which integrates CNN with an evolutionary algorithm and utilizes spatiotemporal data. The optimal structure of the CNN network for the locational marginal price (LMP) forecasting was obtained using a genetic algorithm (GA). A gene mapping scheme was initially encoded to represent the search space and the process of selection, mutation, and crossover eliminated structures that did not satisfy the validation fitness function and then competitive individuals were generated. The evolution process uses the root mean square error (RMSE) as the validation fitness function, which is optimzed by training the created CNN network. The proposed gene mapping scheme can be used to design an optimal CNN structure once the mapping between gene binary bits and parameters/hyperparameters of CNN is given. Day-ahead LMP and demand datasets from Pennsylvania-New Jersey-Maryland (PJM) power market were used to demonstrate the evolutionary capability of the proposed method and the finding of optimal CNN structures. Each studied dataset was grouped into 4 subsets corresponding to various seasonal characteristics (different types of situations in real life). Experimental results revealed that the proposed GA-CNN always yielded a higher forecasting accuracy and lower error rates than other forecasting methods.

1 November 2018
Verified
Conference Paper
Closed access
JMJunrie Matias
Junrie Matias
AFArnel C. Fajardo
Arnel C. Fajardo
RMRuji P. Medina
Ruji P. Medina
Course scheduling is a common problem of all higher educational institutions in several developing countries. Most of these institutions experience a shortage of resources such as teachers and infrastructures. Having small time to recruit, institutions likely to resort in employing beginners to avoid overloading and to fill vacancies immediately. However, directly reassigning classes from senior teacher to the new teacher may lead to unmatched skills required to teach a particular course and more constraints violations. This study presents a hybrid genetic algorithm for course scheduling and teaching workload management. The genetic algorithm is employed with four neighboring operators identified using self-adaptive mechanism during the search process. A data structure of unused resources is used to guide the operators to unused periods. Repair operator is applied to increase the optimality of the solutions. Results show that the proposed algorithm generates feasible and optimized workloads and timetables. The automated system can relieve the decision-makers from the burden of tedious and time-consuming scheduling task in every semester. Hiring additional teaching staff and managing workloads are now much more convenient.

25 January 2019
Verified
Conference Paper
Open access
PDF file
EPEdmarlyn M. Porras
Edmarlyn M. Porras
AFArnel C. Fajardo
Arnel C. Fajardo
RMRuji P. Medina
Ruji P. Medina