Scopus ID: 85159479494
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
Pork meat is a very important source of proteins and other nutrients, so it requires a high level of quality. There is a serious health risk associated with the consumption of spoiled or contaminated pork meat, which is why it is extremely important to monitor its freshness. In this study, sensor arrays consisting of RGB IR sensors, thermal sensors, electronic noses (gas sensors) for detecting the color, temperature, and carbon dioxide and ammonia level of the pork meat were used to evaluate pork meat quality and estimate shelf life. The use of various supervised machine learning approaches has been applied with optimization to perform classification as to whether the meat was fresh or not, as well as regression analysis to predict the amount of exposure time for the meat that can be used in computing shelf-life estimates. Several high-performance algorithms were then tested, evaluated, and compared after hyperparameters of each model were optimized using grid search. As a result of a comparative analysis of the machine learning used, gentle boost ensembles outperformed other machine learning methods in detecting pork meat quality with 92.8% accuracy, while gaussian process regression predicted shelf life with the lowest RMSE, MSE and MAE.
Scopus ID: 85159468687
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
Earthquakes or seismic events cause several disturbances in the ground which can harm or damage the structural stability and could turn fatal. Liquefaction causes a sudden movement shift that is out of sync with the rest of the structure. This might cause several structural damages to the property leading to casualties. In the Philippine geographical context, the West Valley Fault which traverses Metro Manila is a seismic threat capable of producing a maximum magnitude of 7.2. This study aims to assess the probability of liquefaction in Farnecio St., Quaipo, Manila as well as the determination whether the structures present will suffer from critical failure or not. Probabilistic Seismic Hazard Analysis and Monte Carlo Simulation were used to determine the seismic hazard. Recorded earthquake history from the Philippine Institute of Volcanology and Seismology was used as part of the seismic analysis. The seismic hazard analysis shows that a magnitude 5.3 earthquake has a 44.44 % probability of occurrence within the 10-to-20-kilometer distance from the seismic source. A peak ground acceleration of 0.458g and 0.548g was also determined for return periods of 500 and 2500 years for which a Uniform Hazard Response Spectrum was generated. The probability of damage for 2% in 50 years and 10% in 50 years is 39.63% and 30.41%, respectively.
Scopus ID: 85159408581
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
When it comes to learning, there are beneficial effects of incorporating gestures in learning mathematics especially within the early ages of life. At first, we learn Math by counting and incorporating our fingers as a guide, as well as writing numbers along on a piece of paper. These gestures are known to be examples of hands-on learning experience for children. Aside from counting, they learn basic mathematical operations as well.Teaching children mathematics is not an easy task. The child’s attentiveness plays a huge factor in the learning process. The average attention span of the child from 2 to 10 years of age is 20 to 30 minutes only. Making the learning interactive can help in maximizing the learning experience of the child within the timespan. Thus, we aim to develop a compact device that is interactive with children when it comes to learning basic mathematical operations such as addition, subtraction, and multiplication.This device has software that uses computer-vision and image detection as a way of teaching children math in an interactive way. The child has two different options of answering, by using hand gestures or premade printed numbers. The child is asked five random basic mathematical questions within a time limit. It has three levels of difficulty which the child must pass in order to progress each level. Furthermore, the software also has audio feedback as a way of letting the child know the correct answer. With these features, children are engaged in an interactive learning opportunity in mathematics.
Scopus ID: 85159386039
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Tony Rey R. Escalona, Diana Rose T. Rivera, ... Vee Jay Ramos
Conference Paper | Published: January 1, 2022
Abstract
The solar-powered smart waste segregation trash bin with image processing can help in managing the solid waste generated in a community. This device is designed to segregate four types of recyclable solid waste materials namely; plastic, glass, metallic, and paper with the help of image processing and a series of sensors installed in the device for detection, selection, and feedback. The solid waste material is scanned using a camera and compared to the waste images datasets that have been tested and trained model by the researchers, using TensorFlow and python 3.7. The smart waste segregation trash bin can also sense the amount of solid waste inside the compartment with the help of an ultrasonic sensor. Aside from that, through the GSM module, it can generate an SMS notification to the authorized personnel once the bin reaches its maximum capacity. The device is also equipped with a solar panel that is capable of generating the required energy for the system. The result of the testing shows a 100% success rate for paper and plastics, 70% for metals, and 50% for glass. In terms of generating an SMS message to the user when the bins are full, all trials performed for the device to display real-time level monitoring had a favorable outcome indicated by a 100% success rate.
Scopus ID: 85159468457
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-4
Conference Paper | Published: January 1, 2022
Abstract
In this paper, the analysis of metal and plastic straw choice of individuals residing in Metro Manila is conducted using discrete choice modelling. The mathematical model was correlated with the key factors determined in the study. Using the RStudio software as tool, a discrete choice model is generated. The key factors for straw choice of plastic and metal were hygiene, comfortability, trend, habituation, value, and willingness to buy their choice of straw.
Scopus ID: 85159411512
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
Determination of relay pairs from breakpoints in a given network is essential for maintaining the current protection system. Pairs of relays as primary or backup maintain the operation of the protection scheme within its zone of protection in tandem. All calculations and assumptions that are made in protection systems are based on breakpoints. It is inadequately documented that machine learning can be used to determine breakpoint sets and relay pairs. This paper presents the implementation of supervised decision tree machine learning approach for determining directional overcurrent relay breakpoint set in 3-bus networks. Using the one-hot encoding method, 45 input features are extracted from a matrix derived from 3-bus, 5-line network data. Bayesian optimization is used to further optimize the hyperparameters of each model for each of the break point set outputs. Tree diagrams are also provided here to assist in the interpretation of the decision rule resulting from the regression analysis. Experiment tests indicated that the proposed method shows promising results in determining breakpoint set in terms of RMSE.
Scopus ID: 85159430839
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-5
Conference Paper | Published: January 1, 2022
Abstract
The paper aims to examine the factors that affects the successful implementation of the Mastery-based Individualized Learning Enhancement System (MILES) in the Far Eastern University (FEU) Institute of Technology. Two periods were analyzed which are the initial implementation, and this is the start of the pandemic period, and the year after the initial implementation of MILES. The Artificial Neural Network (ANN)-Particle Swarm Optimization (PSO)-based Sensitivity Analysis (SA) was utilized to determine the relative importance (RI) index among the influencing factors that affects the students’ level of satisfaction of the MILES implementation. Survey questionnaires were deployed through the canvas platforms and were answered by the students. In the initial survey, a total of 5763 students responded. For the SY 2020-2021, it was observed that the most influential variable to the student’s performance during the MILES Implementation is Course Adviser Rating while the parameters with the least impact to the student’s performance is the Student’s Status as regular or irregular student. For the survey on SY 2021-2022, the highest relative index is for the lesson preference while the lowest importance index is for the opportunities. Findings of the study shows that the use of NN-PSO based sensitivity analysis is an effective tool for establishing the significance of each variable to a target output.
Scopus ID: 85159442221
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
This project aims to aid students, teachers, and even non-teaching staff in terms of managing technological inquiries and maintaining communication to perform academic-related transactions by developing Tissa – a web-based helpdesk support system for tertiary institutions that integrates various time series analysis techniques in forecasting the estimated number of tickets to be filed by the stakeholders based on historical records. Specifically, it explores the effects of developing a dedicated ticket management system that incorporates both analytics and enhanced user experience to the users’ satisfaction, especially in a tertiary school setting. A total of 62 respondents were selected through purposive sampling. These respondents helped in evaluating the system's overall quality based on the ISO/IEC 25010 software quality model. The respondents' evaluation of the system's overall quality received an above-average score which means that the system passed the testing in terms of system requirements. The results gathered also suggest that 95.2% of the respondents agree that the inclusion of data visualization serves as valuable insights in performing strategic business decisions. Additionally, the system's user experience evaluation received the highest mean score of 4.82. The results for exponential smoothing yielded an 88% accuracy, linear regression was 80% accurate, simple moving techniques had an 85% accuracy rate, and 84% for the weighted moving average, which suggest that techniques used in this study can be considered reliable for future references.
Scopus ID: 85159477384
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
Carbonation is a dangerous threat to concrete since it reduces the alkalinity of normal or self-compacting concrete (SCC), allowing iron to corrode and spall the cover. The goal of this research is to use an artificial neural network to create a corrosion prediction model for steel in self-compacting concrete that has been subjected to carbonation. In this study, MATLABR2019a was used to create a feedforward back propagation neural network. As a training function, the researchers utilized the Levenberg-Marquardt back propagation (TRAINLM) which adjusts weights and bias values using Levenberg-Marquardt optimization. The researchers used gradient descent with momentum weight/bias learning (LEARNGDM) for the adaptation learning function, which is a technique that aids the gradient in determining which way to go. The network’s performance was measured using the mean square error (MSE). The Hyperbolic tangent sigmoid transfer function (TANSIG) was also employed as the transfer function since the values obtained by this function range from +1 to -1, considering both the positive and negative aspects of the parameter. To minimize overfitting, the number of hidden nodes should be fewer than the number of input parameters. The researchers tested 4-12 hidden nodes. Modeling was done using data from 102 experimental studies of self-compacting concrete exposed to corrosion. Using feed-forward back propagation ANN with 1 hidden layer and 8 hidden nodes, a Pearson R-value of 0.98748 and a mean square error of 0.5725 were obtained. The factor that most affect the carbonation depth were water-cement ratio and fly ash content. The suggested model was able to analytically describe the connection and behaviors of the various mixtures to the carbonation depth in the parametric investigation. The parameters characteristics were likewise described by the model.
Scopus ID: 85159416860
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-5
Conference Paper | Published: January 1, 2022
Abstract
Online sexual harassment has been an ongoing problem in this technological era. Gender-based violence has transformed online, making it more difficult for users to act on, as resources and knowledge about the issue are limited. Therefore, the study aims to contribute to introducing a safe space for the victims and an informational aid for potential perpetrators using animation series. They are composed of hybrid animations, a digital campaign through social media sites, and a website–that will serve as a medium for victims/potential victims to agencies that will help them assess their situations and publish multimedia materials. In order to assess the effectiveness of the materials produced for the target audience, which was the youth population, a pretest and posttest evaluation was conducted. The results showed that prior of the evaluation the youth were aware of online sexual harassment, but after assessing our digital campaign and its components they were now fully aware of the issue. This concludes that educating people using modern solutions of disseminating information through our digital campaign was effective. The key solution corresponds to the research main goals which are: A hybrid animation series, digital campaign, and the website, which to educate and raise awareness to online sexual harassment.