Sex: Male
Education:

• Doctor of Philosophy in Electrical Engineering, Universitat Polytecnica de Catalunya (UPC), ongoing
• Master of Science in Electrical Engineering, National Taiwan University of Science and Technology, Taipei Taiwan, 2019
• Bachelor of Science in Electrical Engineering, Mindanao State University-Iligan Institute of Technology, 2015

Field of Specialization:
Electrical Engineering

Researches:

Article title: Teamwork competency and satisfaction in online group project-based engineering course: The cross-level moderating effect of collective efficacy and flipped instruction
Authors: Nicholas O. Awuor, Cathy Weng, Eduardo Piedad, Jr., RoelMilitarb
Publication title: Computers & Education 176:104357

Abstract:
This study examined the relationship between students’ teamwork competency and satisfaction in a synchronous online flipped group project-based course, focusing on the possibility of group collective efficacy and flipped learning to moderate this relationship. We collected data from 19 teams (N = 75 college engineering students) at a science and technology university in Cebu, central Philippines, through a questionnaire survey over a 12-week synchronous online course. Multi-level hierarchical linear modeling test of hypotheses revealed a significant positive relationship between teamwork competency and satisfaction. Similarly, group collective efficacy recorded a significant relationship with satisfaction. At the team level, group collective efficacy and flipped learning moderated the relationship between teamwork competency and satisfaction. Learners in groups with high collective efficacy and online flipped learning showed a stronger relationship than those with low efficacy and conventional online instruction. The findings and discussions provide practical implications and possible interventions teachers could apply to enhance collective efficacy and boost learning satisfaction in synchronous collaborative online learning settings.
Full text available upon request to the author

Article title: Frequency Occurrence Plot-Based Convolutional Neural Network for Motor Fault Diagnosis
Authors: Eduardo Piedad, Jr., Yu-Tung Chen, Hong-Chan Chang, Cheng-Chien Kuo
Publication title: Electronics 9(10), 1711, 2020

Abstract:
A novel motor fault diagnosis using only motor current signature is developed using a frequency occurrence plot-based convolutional neural network (FOP-CNN). In this study, a healthy motor and four identical motors with synthetically applied fault conditions—bearing axis deviation, stator coil inter-turn short circuiting, a broken rotor strip, and outer bearing ring damage—are tested. A set of 150 three-second sampling stator current signals from each motor fault condition are taken under five artificial coupling loads (0, 25%, 50%, 75% and 100%). The sampling signals are collected and processed into frequency occurrence plots (FOPs) which later serve as CNN inputs. This is done first by transforming the time series signals into its frequency spectra then convert these into two-dimensional FOPs. Fivefold stratified sampling cross-validation is performed. When motor load variations are considered as input labels, FOP-CNN predicts motor fault conditions with a 92.37% classification accuracy. It precisely classifies and recalls bearing axis deviation fault and healthy conditions with 99.92% and 96.13% f-scores, respectively. When motor loading variations are not used as input data labels, FOP-CNN still satisfactorily predicts motor condition with an 80.25% overall accuracy. FOP-CNN serves as a new feature extraction technique for time series input signals such as vibration sensors, thermocouples, and acoustics.
Full text link https://tinyurl.com/dcjvjjdk

Article title: Determining Philippine coconut maturity level using machine learning algorithms based on acoustic signal
Authors: June Anne Caladcad, Shiela Cabahug, Mary Rose Catamco, Paul Elyson Villaceran, Leizel Cosgafa, Karl Norbert Cabizares, Marfe Hermosilla, Eduardo Jr. Piedad
Publication title: Computers and Electronics in Agriculture 172:105327, 2020

Abstract:
Advanced intelligent systems are becoming significant to many sectors, including farming. In agriculture, the intelligent classification of post-harvested fruits seems to have a direct impact on farmers, mainly for export products. Unlike other popular fruits, coconuts tend to have limited studies due to its tropical nature grown in developing countries as well as its unique physical structure. In this study, a classification of real coconut datasets is performed based on acoustic signals acquired through a developed tapping system and learned by three widely-used machine learning techniques - artificial neural network (ANN), random forest (RF) and support vector machine (SVM). There are 129 coconuts samples, each classified into three maturity levels – pre-mature, mature, and over-mature. A three-second tapping system gathered from each sample a total of 132,300 data points, which underwent noise reduction and signal processing. Each machine learning model predicts the class of the fruit by learning the patterns of the transformed frequency spectrums of each sample signal. Based on ten times cross-validated results, the three machine learning algorithms satisfactorily predicted the maturity level of coconuts with at least 80% classification accuracy. All models correctly predicted over-mature coconuts but confused in classifying pre-mature with mature and mature with over-mature coconuts. RF model outperformed the other models with efficiencies of 90.98% and 83.48% accuracies for training and testing, respectively. The imbalance data for each coconut class can be addressed to give better results. Additionally, the prepared coconut dataset may use more advanced deep learning techniques.
Full text available upon request to the author

Article title: Deep learning for noninvasive classification of clustered horticultural crops – A case for banana fruit tiers
Authors: Tuan-Tang Le, Chyi-Yeu Lin, Eduardo Jr Piedad
Publication title: Postharvest Biology and Technology

Abstract:
Practical classification of some horticultural crops such as banana tiers, lanzones and grapes come into clusters instead of individual classification. Unlike most of classification studies, clustered crops are rarely studied due to their complex physical structure. A noninvasive deep learning classification of clustered banana given only a single image feature has been developed as a pioneering deep learning study for clustered horticultural crops. In recent deep learning developments, mask region-based convolution neural networks, also known as Mask R-CNN, show unique applications in image recognition by detecting objects within an image while simultaneously generating segmentation masks. With Mask R-CNN, detection of the complex banana fruit within an image predicts the banana class while at the same time generating a mask separating the fruit from its background. A real dataset is used based on banana tiers and the developed model discriminates normal from abnormal tiers. Unlike the previous general machine learning study, which discriminates reject class from normal class with classification accuracy of 79%, our deep learning model obtained a better averaged accuracy of 92.5%. The previous average weighted accuracy of 94.2% also improved to 96.1% with only a single image feature instead of tedious multiple image and size features. With data augmentation, the model slightly improved into 93.8% accuracy on classifying reject class and 96.5% for overall accuracy. Having successfully implemented in banana tiers, this deep learning classification can also serve as basis for other clustered horticultural crops.
Full text available upon request to the author

Article title: Energy Consumption Load Forecasting Using a Level-Based Random Forest Classifier
Authors: Yu-Tung Chen, Eduardo Piedad, Jr, Cheng-Chien Kuo
Publication title: Symmetry 11(8), 956, 2019

Abstract:
Energy consumers may not know whether their next-hour forecasted load is either high or low based on the actual value predicted from their historical data. A conventional method of level prediction with a pattern recognition approach was performed by first predicting the actual numerical values using typical pattern-based regression models, hen classifying them into pattern levels (e.g., low, average, and high). A proposed prediction with pattern recognition scheme was developed to directly predict the desired levels using simpler classifier models without undergoing regression. The proposed pattern recognition classifier was compared to its regression method using a similar algorithm applied to a real-world energy dataset. A random forest (RF) algorithm which outperformed other widely used machine learning (ML) techniques in previous research was used in both methods. Both schemes used similar parameters for training and testing simulations. After 10-time cross training validation and five averaged repeated runs with random permutation per data splitting, the proposed classifier shows better computation speed and higher classification accuracy than the conventional method. However, when the number of its desired levels increases, its prediction accuracy seems to decrease and approaches the accuracy of the conventional method. The developed energy level prediction, which is computationally inexpensive and has a good classification performance, can serve as an alternative forecasting scheme
Full text link https://tinyurl.com/59zfuddv

Article title: Postharvest classification of banana (Musa acuminata) using tier-based machine learning
Authors: Eduardo Jr Piedad, Julaiza I. Larada, Glydel J. Pojas, Laura Vithalie V. Ferrer
Publication title: Postharvest Biology and Technology 145

Abstract:
Manual classification of horticultural products contributes to postharvest losses but technology and emerging algorithms offer solutions to reduce such losses. A practical fruit classification of banana (Musa acuminata AA Group 'Lakatan') using machine learning is developed based on tier-based classification instead of classifying individually (“finger”) for practical purpose. Fruit were classified into extra class, class I, class II and reject class, and compared using three widely-used machine learning classifiers – artificial neural network, support vector machines and random forest. Given only four features of banana tier, the red, green, blue (RGB) color values and the length size of the top middle finger of the banana tier, all three models performed satisfactorily. The highest classification accuracy of 94.2% was achieved using random forest classifier. In addition, ignoring the reject class, which cannot be easily predicted using only the given features, at least 97% accuracy can be achieved in all other three classes. Non-invasive tier-based classification is a practical postharvest technique that can be applied not only for banana but also for other fruit and horticultural products.
Full text available upon request to the author

Article title: A Sound-based Machine Learning to Predict Traffic Vehicle Density
Authors: Geoferleen Flores, Eduardo Jr. Piedad, Anzeneth Figueroa, Romari Tumamak, Nesrah Jane Marie Berdon
Publication title: Recoletos Multidisciplinary Research Journal 9(1): 55–62, 2021

Abstract:
Traffic flow mismanagement is a significant challenge in all countries especially in crowded cities. An alternative solution is to utilize smart technologies to predict traffic flow. In this study, frequency spectrum describing traffic sound characteristics is used as an indicator to predict the next five-minute vehicle density. Sound frequency and vehicle intensity are collected during a thirteen-hour data gathering. The collected sound intensity and frequency are then used to learn three machine-learning models - support vector machine, artificial neural network, and random forest and to predict vehicle intensity. It was found out that the performances of the three models based on root-mean-square-error values are 12.97, 16.01, and 10.67, respectively. These initial and satisfactory results pave a new way to predict traffic flow based on traffic sound characteristics which may serve as a better alternative to conventional features.
Full text available upon request to the author

Article title: A Computer Vision Application for Measuring the Deflection in a Two-dimensional View of Reinforced Concrete Beams
Authors: Eduardo Jr. Piedad, Barne Roxette Carpio, Kristine Sanchez, Marven Jabian
Publication title: Recoletos Multidisciplinary Research Journal 9(1): 13–21, 2021

Abstract:
A novel computer vision application is developed to measure the deflection of two-dimensional (2D) reinforced concrete structural members. Eight beam samples, with dimensions of 160 mm x 150 mm x 1400 mm are loaded and simulated under a four-point loading test until failure using a reaction framework machine. A camera is fixed at the center front view of the concrete beams to capture the deflection of the samples while testing. In each test, a dial indicator is installed and the maximum deflection is manually recorded. Based on the results, the maximum deflection values recorded by the proposed application obtained an average error of 18.38 % when compared to the manual measured results. This indicates that computer vision-based application can provide a beam-wide scale deflection performance, compared to the traditional point-based deflection reading. This study paves a new possibility of aiding manual measurements of concrete beams and all other structural studies.
Full text available upon request to the author

Article title: Optimal Scheduling of Battery Energy Storage for Grid-Connected Load Using Photovoltaic System (PV) via Binary Particle Swarm Optimization (BPSO)
Authors: Eduardo D. Piedad Jr., Marc Edwin F. Montilla, Mark Joseph E. Ortega
Publication title: Recoletos Multidisciplinary Research Journal, 4(2), 2016

Abstract:
This paper presents an optimal dispatch of battery storage and its economic viability with a photovoltaic system. There are four modelled scenarios based on the combination of interruptible load program and the time-of-use scheme. The scenarios were modelled using a Binary Particle Swarm Optimization and were simulated using Matlab v6. In all the scenarios, this model successfully optimizes the battery dispatch scheduling while simultaneously minimizes the DU’s penalty from exceeding the maximum allowable power demand. This algorithm also optimizes the linearly forecasted demand for the next six year for all the scenarios. Then, an economic analysis for the possible investment to the combined BESS and PV system is conducted through the comparison of the payback periods of each scenario. The first scenario is implemented without ILP and a ToU scheme and has 79.86 payback years. With ILP scheme only, the second scenario has 33.37 payback years. Then the third scenario with ToU scheme only has a 30.29 payback years. Finally, the fourth scenario, with both ILP and ToU schemes, shows the fastest recovery of the investment with 21.57 payback years. Thus the combination of both ILP and ToU schemes provide the best economic benefit. Though the current proposed system is still not economically feasible however the foreseen positive trends on solar and battery technologies will make this system viable.
Full text available upon request to the author

Article title: Displacement and Illumination Levels Effect on Short-distance Measurement Errors of Using a Camera
Authors: Eduardo D. Piedad Jr. and Ricky B. Villeta
Publication title: Recoletos Multidisciplinary Research Journal 4(1)., 2016

Abstract:
Using a camera for measurement reading is simplified through the incorporation of computer vision application. The variations in the environmental’s setting, however, may constitute to the occurrence of measurement errors. A study investigated the significant effect of changing the camera-to-lens displacements and the variations of the illumination level on the short-distance measurement reading. This is performed initially by developing an actual setup calibrated though the comparison with the hypothesized values. Then, an experiment on this calibrated setup generates the measurement results of varying the displacement positions and the illumination levels. Through descriptive and comparative statistical analysis, there is evidence that the variations of the displacement alone do not significantly change the measurement results. Similarly, the variations in the illumination levels do not also constitute significant changes on the measurement results. Hence, each of the variables bears no contribution on the occurrence of the measurement error of using camera. It is further confirmed through the two way analysis of variance that there is no significant difference on the displacement positions and illumination levels, and on their interactions. These results verified that a camera can be used as a short-distance measurement tool adequately regardless on the object-to-lens displacement positions and on the illumination levels.
Full text available upon request to the author

Article title: Various Trends on the National Development of Renewable Energy Source Affecting the Natural Resource Depletion
Authors: Eduardo D. Piedad Jr.
Publication title: Recoletos Multidisciplinary Research Journal 4(1), 2016

Abstract:
Renewable energy sources are foreseen to rise as they become scarce and expensive fossil fuels. Considering this thought, each country implements different strategies and national policies to support the development of renewable sources. However, these emerging developments may contribute to its depletion of natural sources. In this paper, an exploratory pattern analysis was used on 125 selected countries to determine the underlying trends on the effect of the development of renewable energy (RE) sources while utilizing the countries’ natural resources. Due to different status of each country, the trends were grouped in similar associations such as negative, positive and bell-like relationships. Developed countries showed a negative relationship where the natural resources are heavily utilized in the early stages but rapidly decreased as the RE progresses. This reflects the capability of these countries with high to very-high human development index (HDI) to invest more on advanced technologies which utilize fewer natural resources. On the other hand, the underdeveloped countries with low to moderate HDI behave in a positive relationship showing their heavily dependence on its natural resources as RE progresses. Moreover, a group of developing countries between developed and underdeveloped categories and without direct relationship to HDI showed a transition between positive to negative transition as the RE progresses.

These findings support the international policymakers, developers and investors on RE market justifications and entrustments, and fair RE policies such as the integration of Carbon Footprint Policy.
Full text available upon request to the author

Papers Presented:

Article title: Vehicle Count System based on Time Interval Image Capture Method and Deep Learning Mask R-CNN
Authors: Eduardo Jr Piedad; Tuan-Tang Le; Kimberly Aying; Fhenyl Kristel Pama; Ianny Tabale
Conference title: : TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)

Article title: Energy Consumption Level Prediction Based on Classification Approach with Machine Learning Technique
Authors: Hong-Chan Chang, Cheng-Chien Kuo, Yu-Tung Chen, Wei-Bin Wu, Eduardo Jr Piedad
Conference title: Proceedings of the 4th World Congress on New Technologies (NewTech'18)
Madrid, Spain – August 19 – 21, 2018

Contact details: This email address is being protected from spambots. You need JavaScript enabled to view it.