As the educational technology director of our institution, I often find myself at the forefront of discussions surrounding the integration of artificial intelligence (AI) and its impact on our lives. Recently, a former student approached me with a thought-provoking question: "In times of grief and loss, can ChatGPT offer the comfort and consolation we seek?" The weight of this inquiry bore down on me, for I realized that answering it was not a task I could take lightly. I hesitated, acutely aware that I was not a health professional equipped with the expertise to navigate the depths of grief and loss. Moreover, my role as an educational technology director means that I have had the opportunity to witness the transformative potential of AI, leading me to wonder whether I possess a natural inclination to embrace technology as a solution. Therefore, I felt compelled to engage health professionals, the true authorities on matters of emotional well-being and mental health, to join me in an open and honest exploration of this complex question.

Rainfall is crucial for flood prevention and comprehending the correlation between rainfall and flooding. Cavite province in the Philippines is vulnerable to flooding caused by heavy rainfall and climate change impacts. Early detection of flooding through early warning systems can prevent excessive damage loss and potentially save lives. It can also provide major savings in terms of monetary benefit and increased interagency coordination for rapid decision-making. Machine learning is an important tool for predicting rainfall which can be used to predict rainfall in the province. The objective of this study is to conduct a comparative analysis of various models for predicting daily rainfall, using relevant atmospheric features such as maximum, minimum, and mean temperature, relative humidity, wind speed, wind direction, cloud cover, pressure, and evaporation. The study seeks to identify the most effective model for accurately predicting rainfall in the Cavite Province to benefit the local community. Among the five machine learning models evaluated, the Gaussian Process Regression model demonstrated the highest accuracy in predicting daily rainfall. The findings of this study can be leveraged to mitigate the damage caused by flooding in the Cavite Province and serve as a useful reference for similar studies in other regions prone to flooding.

Diabetic retinopathy is a serious complication needing prompt diagnosis and medication to avert vision loss. Lesions caused by the condition are difficult to track because they are hidden behind the eye's structure in small and subtle forms. To extract relevant features., we created a robust pipeline using multiple preprocessing techniques., image segmentation architecture (DR-UNet) with atrous spatial pyramid pooling., and an attention-aware deep learning convolutional network with different modules based on ResidualNet. Empirical results show that our framework has segmentation accuracies of 87.10% (intersection over union) and 84.50% (dice similarity coefficient). Moreover., classification performance of 99.20% provided better results than existing schemes., as reinforced by the smooth convergence of training/validation loss and accuracy. This study has the potential to supplement traditional diagnosis to identify better the ailment in its early and advanced stages.

Nanolearning (NL) is a promising approach to education and training as it delivers small, bite-sized chunks of learning content that can be easily consumed and retained by learners. This allows quickly accessing specific pieces of information and knowledge, which can be delivered through a variety of mediums, such as videos, podcasts, or mobile applications, etc. NL has significant potential in educational and training settings, where learners or trainers can quickly upskill or reskill in specific contexts, improving their productivity and mastering some topics. This study provides an overview of NL, addressing the design of NL educational materials and its implementation in several educational applications. It also highlights some considerations and issues. In conclusion, it is recommended that reliable learning resources be used by teachers, the content be closely assessed, the source format be considered, bias be checked for, and learner feedback be obtained to ensure the quality of NL materials. By following the proposed NL framework, teachers can provide their learners with top-notch and productive NL resources.

When it comes to asynchronous online learning, the literature recommends multimedia content like videos of lectures and demonstrations. However, the lack of emotional connection and the absence of teacher support in these video materials can be detrimental to student success. We proposed incorporating talking heads and annotations to alleviate these weaknesses. In this study, we investigated the cognitive and affective effects of integrating these solutions in asynchronous video lectures. Guided by the theoretical lens of Cognitive Theory of Multimedia Learning and Cognitive-Affective Theory of Learning with Media, we produced a total of 72 videos (average = four videos per subtopic) with a mean duration of 258 seconds (range = 193 to 318 seconds). To comparatively assess our video treatments (i.e., regular videos, videos with face, videos with annotation, or videos with face and annotation), we conducted an educational-based cluster randomized controlled trial within a 14-week academic period with four cohorts of students enrolled in an introductory web design and development course. We recorded a total of 42,425 total page views (212.13 page views per student) for all web browsing activities within the online learning platform. Moreover, 39.92% (16,935 views) of these page views were attributed to the video pages accumulating a total of 47,665 minutes of watch time. Our findings suggest that combining talking heads and annotations in asynchronous video lectures yielded the highest learning performance, longest watch time, and highest satisfaction, engagement, and attitude scores. These discoveries have significant implications for designing video lectures for online education to support students’ activities and engagement. Therefore, we concluded that academic institutions, curriculum developers, instructional designers, and educators should consider these findings before relocating face-to-face courses to online learning systems to maximize the benefits of video-based learning.

The impact of digital games on chemistry education has received less attention compared to other scientific fields. This research gap resulted in a limited understanding of how to effectively design mobile chemistry games (MCG) distinct from non-science mobile learning games (MLG). This study aims to explore students' attitudes toward MCG and gather their opinions on the game components using a mixed-methods research design. A total of 698 students from urban universities, categorized into technology, chemistry, and education cohorts based on their academic majors, participated to provide diverse perspectives. The results revealed significant disparities in gameplay experience, particularly in competence and relatedness, between MLG and MCG. Students' educational background significantly influenced their confidence and leisure levels. Concerningly, students exhibited a negative attitude towards MCG. The study provides game developers with a guideline for developing MCG and offers chemistry teachers a framework for selecting appropriate MLG in the context of chemistry education.

Wind power is a challenge in power generation. The tortuous process stages in generating voltage become a significant problem to be solved properly. One indicator of the process is the determination of the right wind speed because it always changes at any time and under circumstances. For this reason, accurate predictions are needed so as to maintain the smooth integration of wind power into the overall system. Machine learning is used as a promising approach to dealing with wind intermittent power because wind speed prediction methods have been developed in recent years. This study explores climate patterns in the Philippines using data collected from PAGASA. The data is trained and tested with a machine learning model to predict wind speed. This research resulted in the Gaussian Process Regression (GPR) model outperforming other models and is very suitable for datasets in achieving accurate and reliable predictions.

Relative humidity is an important environmental parameter and is widely used in various fields. Prediction of humidity levels is crucial for climate modeling, heat stress, air quality forecasting, and public health. Machine learning techniques have shown potential for predicting humidity due to their nonlinear nature. However, there is a research gap in humidity prediction in the Philippines, specifically the lack of studies utilizing the available parameters provided by PAGASA, presenting an opportunity for further investigation and development of models for predicting humidity levels in the country. In this study, the researchers used a publicly available dataset from PAGASA containing weather measurements from 2000 to 2022 in the Philippines. Various machine learning models were trained and tested, with hyperparameter tuning performed using Bayesian optimization. The Gaussian Process Regression model with optimized hyperparameters achieved the best performance in predicting relative humidity, with the lowest RMSE and highest R-squared values. This study provides a reliable way to predict humidity levels in the Philippines based on weather parameters.

The education sector is constantly progressing its competency paradigm by establishing a nexus between practical, theoretical, and technical dimensions of teaching and learning. In the modern age of education, hackathons are becoming increasingly prominent in providing an optimal academic environment that connects classroom learnings to real‐life scenarios. This study explored the motivational orientation behind student participation in hackathons through the framework provided by self‐determination theory. Specifically, it investigated the role of intrinsic and extrinsic motivations in encouraging initial and continuous hackathon participation. The partial least squares‐structural equation modeling method was used to analyze data collected from 437 students in 12 countries. According to the findings, although intrinsic motivation influences participation intention, extrinsic motivation drives continuance participation. When intrinsic and extrinsic motivational constructs were analyzed individually, it was found that continuance participation demands both motivational orientations. Comparisons of demographic characteristics indicate that older students with more extensive educational experience may have higher intentions to participate and continue participating in these events. This study offers insights into how the education sector can increase hackathon participation by tapping on students’ motivational orientation. From a methodological point of view, it is apparent to recommend the promotion of hackathons as a core extracurricular activity at a school level, and more indispensably, as pedagogy at a classroom level. In a world where students are encouraged to fail early, fast, and often, participating in hackathons is a tactical preparation for eventual success.

Automated chess is an emerging challenge from the field of robotics to human interaction. Customarily, chess playing robots use video camera for detecting the state of the board and robotic arm to manipulate the pieces, which makes it either expensive or too fragile to move. In this study, an automated chess board called “Chessbot” was built by combining a multitude of technologies and techniques such as voice command recognition, x and y plotting and recognition of chess pieces in a Cartesian plane, artificial intelligence algorithm, and Android mobile application. To properly execute chess moves either from a human player or computer via voice commands or a mobile game interface, the microcontroller provides motors the current and landing squares of chess pieces on the board. For the evaluation, several matches were simulated to perform various testing procedures such as voice command recognition, move log accuracy, display and user input acceptance accuracy, self-arrangement, and chess move reliability. Upon testing, Chessbot performs all the necessary tasks efficiently and accurately, which indicates the possibility of using this automated device for chess games at a hobbylevel or professional matches.