Teodoro Revano

The Virtual Dietitian (VD) application is a nutrition knowledge-based system that generates personalized meal plans in accordance with the one-size-does-not-fit-all concept of precision nutrition. A subset of the population that was not involved in its four-part developmental study was gym and fitness enthusiasts despite them being important target users. As part of our quality improvement (QI) plan, we initiated a two-phase user testing to inform modifications to VD. We recruited a total of 30 users with prior experience in nutrition applications. In phase 1, they used the current version of VD for a week and answered a mixed-form questionnaire afterward. We used the same questionnaire from our previous study, which is composed of System Usability Scale (SUS) items and open-ended questions. After months of system modification, the same set of users evaluated again the new VD version after another week of use. A paired-sample t-test showed a statistically significant difference in SUS scores before (SUS = 79) and after (SUS = 82) modifying VD based on the suggestions of the participants (p = 0.005). Some new features include water tracker and reminder modules, Google Fit integration, and other nutrition support services (e.g., teleconsultation with registered dietitians). Although further refinements to VD are still needed, we were able to incorporate a QI initiative typically employed by healthcare organizations into software development for a better and improved personalized nutrition application.

It is clear that since the COVID-19 pandemic started in the Philippines, education is one of the most affected areas. After more than a year of struggling with different community lockdowns and the alarming consistency with the increasing number of confirmed cases each day, students and teachers are now left with the choice to voice out their frustrations, activism, opinions, and ideas regarding online classes through different social networking sites, most especially Twitter. With the influx of tweets available in the internet sphere, the authors of this study decided to conduct a sentiment analysis to categorize the overall opinions of Filipino citizens about the current state of education after more than a year of adapting with the distance learning practices that are now considered as the new normal. The authors utilized rtweet, a built-in package available in R programming to perform opinion mining on Twitter data collected through the package related to online class during pandemic. Through sentiment lexicons available in R such as bing and afinn, the results show that most of the tweets about online learning in the Philippines turned out to be neutral. The positive responses are 55.77% while 44.23% of the sentiments collected are negative. To evaluate the accuracy rates of results, the authors used three classification techniques namely Naïve Bayes, logistic regression, and random forest. Naïve bayes and logistic regression both show 69.23% accuracy rate and random forest calculated 71.15% accuracy in identifying whether the given tweet is a positive, negative, or neutral sentiment.

The sudden transition to emergency remote education (ERE) caused by the pandemic has been a highly complex undertaking for teachers and students alike. For developing countries, such a disruption only aggravates the pre-existing global education crisis and influences the sector in unprecedented ways. Thus, we explored how teachers and students from higher education in a developing country adapt to ERE during the pandemic. Specifically, we attempted to identify the common challenges faced by teachers and students and their coping strategies to handle pandemic-induced stress. To this end, we conducted a comparative cross-sectional study from October to November 2021 with 78 teachers and 94 students from a higher education institution in Manila, Philippines. Our results show that while self-regulation is the greatest challenge among students, it is the conduciveness of the home environment for teachers. Interestingly, although teachers and students have varying concerns, both groups rely on acceptance, humor, and positive reframing as their coping strategies. By painting a holistic picture of the challenges and coping strategies of both teachers and students, education policymakers and administrators can make an informed decision on how to best continue ERE and prepare in advance for the resumption of school in the new normal. © 2022 Association for Computing Machinery. All rights reserved.

Speech2Spell: A Voice-Enabled Spell-Out Game Using Voice Recognition Algorithm using Android platform is a mobile game using voice recognition. Voice recognition are used in security reasons to protect or secure one’s property, some are used in voice command machines like televisions, lights, air conditioners and other appliances even in small devices help the users in asking directions and many other things that you didn’t know it can be done by voice recognition. The game speech2spell is a voice recognition game that simply recognizes all single word that is being spoken by the user, the game is played only by a single player; also the game must be played at a quiet environment or user can also use their headphone to limit the noise that has been absorbed or heard by the mobile. The game can help users to improve their knowledge in speaking the right word. The game has a custom mode setting for the user. On custom mode game, the user can take a picture on the object and can be use...

Evaluation has always been a vital part of any organization primarily to assess its current programs or activities and to determine if such programs or activities are able to cater to the needs of the customers. New plans developed by the organization are results of a constant evaluation of their programs. Organizations are enabled to utilize their resources more efficiently to provide for the needs of their clientele. In TIP, the faculty evaluation is being done manually, where the HR staff members are in charge of locating the instructor to conduct an evaluation. After finding the instructor, an evaluation sheet, pencil and comment and suggestion paper are given to the students. This current method takes a lot of personnel to accomplish the tasks involved. The Human Resources Department needs to hire additional employees just to accomplish the task of evaluating the faculty members which usually takes around two months. The advancement of technology in the evaluation system can aid the proponents in gathering more accurate data in the fastest possible manner. The proposed system can provide the HR staff and the students a much easier and state-of-the-art technology type of faculty evaluating system. The results gathered from the software evaluation became the basis in developing the proposed system. The results of the software evaluation conducted have met the objectives of the researchers and therefore worthy enough to be continued and developed. The overall mean of the system evaluation implied that the developed study was very useful and can be of great help to the institution. A rating of "4.3" means that the proposed study has been greatly appreciated by the users. The results of evaluation from the faculty members brought improvement for their usage. Therefore, the researchers recommended its usage and implementation in the next semester of the current school year at the Technological Institute of the Philippines.

Myocardial Infarction (MI) better known as heart attack, is considered as one of the most alarming diseases that used to harm a great percentage of the male populace. However, the number of female patients suffering from the condition that was formerly known as the “old-man disease” is gradually increasing at the present time. Taking that into consideration, the researchers gathered enough data to come up with a predictive model that could be utilized in identifying the risk indicators for the mortality of female patients suffering from MI. By using different tools in data mining that contribute to a lot of great data discoveries up to date, the researchers made use of logistic regression, random forest, and decision tree to evaluate which technique can generate a diagnostic model with a higher accuracy rate. The generated prognostic models were based on a total of 9 significant attributes that were used to determine the risk indicators for the mortality of female patients suffering...

Assistive technologies gained traction in the medical field over the last few decades. Novel approaches have been developed in order to aid people with disability to communicate effectively. However, little research has been conducted on the other side of the coin, that is, assistive technologies to help people who do not have a disability to understand and comprehend the language of disabled. This study describes the early development of a hand alphabet recognition that intends to accomplish a functioning dactylology conversion from sign language to English print in a live streaming video. Through a video analysis, each frame is processed using a video segmentation technique to partition it into different segments (e.g., pixels of hand gesture). The dactylology conversion algorithm was implemented in a mobile application where users can watch video containing an on-screen sign language interpreter and understand fingerspelling used as a communication by hearing- and speech-impaired people.

The combination of multimedia technology and Internet provides an amiss channel for pornographic contents accessible by certain sensitive groups of people. Furthermore, the same channel provides the easiest medium to distribute illicit images and videos without an autonomous content supervision process. In this study, an application was developed grounded from a pixel-based approach and a skin tone detection filter to identify images and videos with a large skin color count and considered as pornographic in nature. With nudity detection algorithm as the foundation of the system, all multimedia files were preprocessed, segmented, and filtered to analyze skin-colored pixels by processing in YCbCr space and then classifying it as skin or non-skin pixels. Afterwards, the percentage of skin pixels relative to the size of the frames is calculated to be part of the mean baseline for nudity and non-nudity materials. Lastly, the application classifies the files as nude or not, and then filter it. The application was evaluated by supplying a dataset of 1,239 multimedia files (Images = 986; Videos = 253) collected from the Web. On the final testing set, the application obtained a precision of 90.33% and accuracy of 80.23% using the supplied dataset.