Search

This study utilized the pre-emptive Goal Programming (GP) model in the optimization problem in the Tower Crane Installation process. Secondary data was collected from an anonymous tower crane installer covering the entire operations in the Philippines. The preemptive GP model contains 4 variables and 12 constraints which and this study showed the preemptive GP results where only 3 out of 12 goals were achieved. The other 9 goals were not satisfied. Priority 1 and Priority 2 were not attained with positive deviations, suggesting that the total tower crane installation hours exceeded beyond 30 hours as well as incurring rental cost reserve of not more than P105,000. Priority 3, meanwhile, was attained with no positive deviation, suggesting that the mast can be installed in around 10 hours. Priority 4,5,6,7,8, and 9 were not attained with slight positive deviations observed, represented in hours, indicating that the goals established by the organization are not attainable. Priority 10 was attained with no deviations observed and Priority 12 was attained with negative deviation, suggesting that the organization can extend the total headcount and deploy additional headcount whenever necessary to ease the cost and duration of the tower crane installation. The results of the preemptive GP model were anchored in the formulation Risk Management Plan, reinforced by Cost-Benefit Analysis (CBA), helping the small to middle-market tower crane operators in the Philippines to mitigate the risk of installation delays and potential wastage in the cost and budget, as induced by this delay. [ABSTRACT FROM AUTHOR]

In this paper, the proponents have utilized the deep learning models of 3dCNN and LSTM along with OpenCV for webcam functionalities and Google's MediaPipe Framework to develop the American Sign Language Interpreter System. The objective of this study is as follows: First is to test the proponents' own dataset on Tran's network model (Tran et al. 2020) and gather experimental results for comparison. Second, The proponents did a modification of Tran's model network by adding an LSTM layer to accommodate the temporal structure of the proponents' dataset. Overall, the metrics of Training Accuracy and F1-Score were used as the basis for the performance of each model network - Tran's network model performed well by achieving an 81.6% accuracy during training and 81.8% on the F1-Score in real-time. In comparison, the proponent model achieved an 89.9% accuracy on training and 89.8% in real-time. The most notable difference is during real-time, as the proponents' model classified the gestures more correctly. It uses the sequence prediction that is made possible by the LSTM layer. [ABSTRACT FROM AUTHOR]

Examination timetabling/scheduling is a complex task in many academic institutions that requires intensive analysis and human scheduling expertise and experience to generate an optimal examination schedule. Without the assistance of modern computers, the accomplishment and process of this task can be tedious, time-consuming, and error-prone. The School of Information Technology (SOIT) department at Mapua University faced a technological problem with their examination scheduling process due to the dependence on manual methods and automated scheduling software with a fixed output for only the 2015 student batch. This study proposes a web-based examination scheduling system as an alternative to the school department's existing examination scheduling method and technology. It will incorporate both the concept of interactive and automated computer-based scheduling methods and is designed to have the capability to adapt and generate optimal schedules based on the dynamic scheduling variables and specified scheduling constraints. Moreover, the proposed system has been successfully demonstrated to and tested, and evaluated by the major stakeholder of the examination scheduling process of the mentioned school department, the Technical Assistant to the Dean and Proctors. Consequently, accepting and recognizing it as an alternative to their existing examination scheduling methods. [ABSTRACT FROM AUTHOR]

With the advancement of technology, Filipinos have a means of connecting to social media mainly to share what they are doing or what they feel now. This could lead to people venting out their stress on platforms such as Twitter. One of the topics that cause people a lot of stress is Politics and many social media users share their opinions in a stressful manner on Twitter. This paper will focus on detecting the reason for stress called stressors from the tweet. This will be done by collecting tweets based on their hashtags and NLP technique called topic modeling specifically LDA to form the topic of stress for stress detection. Then Machine learning algorithms of SVM, XGBoost, and Logistic Regression will be used on the tweets and topics created by the Topic modeling to create and train a model that can predict stressors based on the tweets and topics. [ABSTRACT FROM AUTHOR]

Duck egg quality inspections are done manually in the Philippines which is not reliable due to human subjectivity, visual stress, and tiredness. There is no documentation regarding the general standard on determining the quality of duck eggs and local farmers have different standards. This research aims to classify duck egg quality into 3 classes namely, Balut/Penoy, Salted Egg, and Table egg. Two angles of 600 duck eggs were captured inside an image acquisition setup. Using ResNet-50 as a base model, its last fully connected layer was replaced by a classifier block. Hyperparameter tuning with Stratified 5-fold Cross Validation was utilized. It was observed that batch size of 8, epoch of 110, and learning rate of 0.0001 has given the lowest validation loss which was used to train the final model. Performance Metrics was obtained. Overall, the result of the model yielded 90%, 95%, and 65% for Balut/Penoy, Salted Egg, and Table egg, respectively, averaging an 83.33% overall accuracy of the model. As observed, the model is not able to accurately differentiate between hairline and broken cracks. Additionally, falsely classified images also occur when the size of an egg is close to the threshold to other sizes. [ABSTRACT FROM AUTHOR]

As the internet users in the Philippines have become increasingly rampant, Tagalog Sentiment Analysis is essential when determining general sentiments correlated to a topic. Among Tagalog tweets, backward slang has gained increased popularity on social media. Deep learning algorithms such as Long-Short Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) have been proven more effective than traditional machine learning algorithms. This study explored and evaluated the effects of backward slang on two deep learning models using performance metrics for classification models. Results show that backward slang helps in the expressivity of textual data, given the improvement in overall sentiment scores. [ABSTRACT FROM AUTHOR]

Digital technologies have been bridging the gap in terms of convenience, reliability, and timeliness on these current settings (Kapur 2006). It is extensively used by majority of individuals due to its technical functions n wide array of transactions. Like in education, the use of digital technology is imperative aspects that has gained more prominence due to global pandemic. In Philippines, Digital technology has been adopted by Department of Science and Technology through its Science and Technology Academic and Research-Based Openly Operated Kiosk Station or STARBOOKS. The latter is primarily developed to share digitized resources of S&T library materials specifically to marginalized populations all over the country. This study aims to test the framework of Technology Acceptance Model or TAM feature of DOSTSTARBOOKS such as Perceived Usefulness (PU) and Perceived Ease of Use (PEOU) towards the users in identified sites in the Philippine countryside. There were one hundred seven (107) total respondents of the study from University of Southern Mindanao (USM), – Kabacan Mindanao State University (MSU) – General Santos City, Sultan Kudarat State University (SKSU) – main campus, and Notre Dame Hospital and School of Midwifery (NDHSM) – Cotabato City. The study reveals that there is a significant difference among groups (age, sex, and school) with regards to Perceived Usefulness (PU) of STARBOOKS and Perceived Ease of Use (PEOU) STARBOOKS based on One Way Analysis of Variance or ANOVA Based on the findings generated from Exploratory Factor Analysis is acceptable with a determinant value of 0.005 that is higher than 0.001. This interpret that the respondents’ answer data is free of multicollinearity issues. All of the variables are significant, according to research hypothesis testing based on regression weights using CFA results. The study concluded that undergraduate students found STARBOOKS as a useful (PU) and user-friendly (PEOU) mode of technology most especially for feasibility study and thesis purposes. [ABSTRACT FROM AUTHOR]

Digital technologies have been bridging the gap in terms of convenience, reliability, and timeliness on these current settings (Kapur 2006). It is extensively used by majority of individuals due to its technical functions n wide array of transactions. Like in education, the use of digital technology is imperative aspects that has gained more prominence due to global pandemic. In Philippines, Digital technology has been adopted by Department of Science and Technology through its Science and Technology Academic and Research-Based Openly Operated Kiosk Station or STARBOOKS. The latter is primarily developed to share digitized resources of S&T library materials specifically to marginalized populations all over the country. This study aims to test the framework of Technology Acceptance Model or TAM feature of DOSTSTARBOOKS such as Perceived Usefulness (PU) and Perceived Ease of Use (PEOU) towards the users in identified sites in the Philippine countryside. There were one hundred seven (107) total respondents of the study from University of Southern Mindanao (USM), - Kabacan Mindanao State University (MSU) - General Santos City, Sultan Kudarat State University (SKSU) - main campus, and Notre Dame Hospital and School of Midwifery (NDHSM) - Cotabato City. The study reveals that there is a significant difference among groups (age, sex, and school) with regards to Perceived Usefulness (PU) of STARBOOKS and Perceived Ease of Use (PEOU) STARBOOKS based on One Way Analysis of Variance or ANOVA Based on the findings generated from Exploratory Factor Analysis is acceptable with a determinant value of 0.005 that is higher than 0.001. This interpret that the respondents' answer data is free of multicollinearity issues. All of the variables are significant, according to research hypothesis testing based on regression weights using CFA results. The study concluded that undergraduate students found STARBOOKS as a useful (PU) and user-friendly (PEOU) mode of technology most especially for feasibility study and thesis purposes. [ABSTRACT FROM AUTHOR]