An ideal library makes every last patron feels what it is like to have their own library where one can traverse a world of knowledge, and then build their personal learning environment. Parallel to this conception is the intensification of fine-tuning the conventional librarianship to transform it into a center for new digital learning. As a contribution to this digital revolution, this paper presents an innovative way of renovating the house of dusty books into the center of creativity, research, and partnership through the fusion of traditional librarianship, self-service solutions, and human-computer interaction. The self-service system employs technologies and modalities such as touch screen-assistive technology for the kiosk terminal with the inclusion of a built-in camera, speaker, microphone, and lights, Automatic Speech Recognition, Radio-Frequency Identification and Content-Based Image Retrieval for holdings circulation and monitoring. In conformance with the ISO 9241-210 (Human-centred design for interactive systems), a series of user-centered evaluations were accomplished to obtain early feedback, and to validate that the user requirements have been satisfied at a later stage of the project cycle. To integrate a humanistic approach, the HCSDLC, or Human-Centered Systems Development Life Cycle Methodology, was utilized to complement the four main user-centered design activities specified in the ISO 9241-210 standard. The prototype designs and final self-service library system were assessed in terms of efficiency, effectiveness, and user satisfaction using metrics defined in the ISO/IEC 25022.

Ideally, instruction is best done one on one. However, due to the scarcity of public school teachers, this ideal remains just that, only an ideal. This ideal, however, can be realized by using a computer-assisted language learning system. One such language that this system can be applied to is the Pangasinense - one of the top ten languages of the Philippines. Using this system, any Filipino can now learn Pangasinense. Creating this involves developing the speech corpus for the Pangasinense language and designing a reading miscue detector (RMD) that employs hidden markov models (HMM) and artificial neural network (ANN). The RMD uses the reference verification (RV) method that compares the input speech to the reference speech found in the Pangasinense speech corpus. The collection of the speech corpus involved 10 native Pangasinense speakers who each recorded a total of 21 phrases and 309 words that were considered as common conversational phrases or words for Pangasinense. The system was initially tested by 10 native Pangasinense speakers, who also speak Filipino, and their scores were set as the reference scores. The system was then put to test by conducting a six-week pilot study participated by 10 Filipino speakers. The system's effectiveness was then evaluated through the progress trends of all learners' scores for each module. All learners' progress curves showed to have a positive slope. In addition, the system's efficiency was determined by its false alarm rate (FAR), misdetection rate (MdR), and accuracy. The system was able to get a FAR of 26.67% and 30%, MdR of 30.0% and 6.67%, and accuracy of 71.66% and 81.67%, for males and females group, respectively.

This paper illustrates the impacts of mining disaster after more than 20 years. A two – day rapid assessment was carried out at Mogpog and Boac River catchment in Marinduque Island in March 2019. The target site included Maguilaguila Pit that connects the river catchment and formerly used as mining wastes pit. This is to understand the impacts of 1993 and 1996 mining disasters in the Boac-Mogpog river basin at Marinduque, Philippines. The island of Marinduque has been considered as among the top ten most vulnerable islands in the country due to its environmental condition and geographical location which affected the island demography. The island has suffered the impacts of one of the country’s biggest mining disasters. The instruments used to conduct rapid site assessment were SciAps X-300 Handheld X-ray Fluorescence (XRF), Unmanned Air Vehicle (UAV) Model DJI Mavic Air, Google Earth, Hannah Multiparameter HI 9811-5 with HI 1285-5 probe and HI 70007, 70031, 70032 and 700661 solutions. The DJI Mavic Air captured images of Mogpog and Boac River catchment which helped direct the research team to take the right sampling locations. The DJI Mavic Air captured site images of the two rivers as dead rivers and use as land transportation route during dry season. The Google Earth captured the historical images of the target areas. The recorded data showed that the pit and nearby river water is acidic with pH equivalent to 2.9 and 4.1, respectively. The range of concentration of total dissolved solids in Mogpog and Boac river water was 100–1360 and 160–1150 ppm, respectively. The recorded concentration of iron near the pit was 125,587 ppm, and chromium concentration range was 80–99 ppm. The concentration of copper and manganese in the sediments was 5 and 158 times higher (respectively) than the 1998 detected concentrations. Based on the recorded data and images, the Maguilaguila pit, Boac and Mogpog River catchment need immediate attention. It could be concluded that based on the recent assessment results, leaks at the pit are likely. Also, the combination of areal-aerial and ground technique produced two – day rapid site assessment for areas contaminated by mine tailings. The information could aid in preparing prompt action and setting strategies that are helpful in carrying out risk reduction programs in the island.

Geographical Information System helps everyone in many industries on a regular basis. “iReportMo” is an android mobile application that uses GIS-based to let a citizen report an incident right from the mobile device. This application will serve as an easy access that caters emergency concern such as fire, accident, crime and barangay incident in Metro manila. The user may provide details such as location, date, time, and images when reporting an incident. There are few existing literatures have focused on providing assistance to any emergency event using the newest technology, but few have not touched on providing a centralized system that caters all the emergency in one application. Thus, this paper automates the efforts of the manual transaction to effectively respond to an emergency hazard in City of Manila thus makes it more efficient to gather important information in real time.

Braille is one of the major tools for teaching the visually impaired. Sufficient number of teachers engaged in special education involved in Filipino Braille is not available. One of the possible approaches to address this problem is the use of computers in automation of extracting information in Braille that can facilitate teaching. Other countries have taken their initiative to develop similar technology capable of teaching Braille however the Filipino Braille code including its contractions, and the Filipino language per se has features that are distinct to other languages. This research proposes a system that use machine vision in recognizing one-cell Filipino Braille contractions. Scanned Braille images undergo image processing and HOG feature extraction to train the system classifier thru SVM. Performance evaluation results reflect a high accuracy of recognition.

Essay writing examination is commonly used learning activity in all levels of education and disciplines. It is advantageous in evaluating the student’s learning outcomes because it gives them the chance to exhibit their knowledge and skills freely. For these reasons, a lot of researchers turned their interest in Automated essay scoring (AES) is one of the most remarkable innovations in text mining using Natural Language Processing and Machine learning algorithms. The purpose of this study is to develop an automated essay scoring that uses ontology and Natural Language Processing. Different learning algorithms showed agreeing prediction outcomes but still regression algorithm with the proper features incorporated with it may produce more accurate essay score. This study aims to increase the accuracy, reliability and validity of the AES by implementing the Gradient ridge regression with the domain ontology and other features. Linear regression, linear lasso regression and ridge regression were also used in conjunction with the different features that was extracted. The different features extracted are the domain concepts, average word length, orthography (spelling mistakes), grammar and sentiment score. The first dataset used is the ASAP dataset from Kaggle website is used to train and test different machine learning algorithms that is consist of linear regression, linear lasso regression, ridge regression and gradient boosting regression together with the different features identified. The second dataset used is the one extracted from the student’s essay exam in Human Computer Interaction course. The results show that the Gradient Boosting Regression has the highest variance and kappa scores. However, we can tell that there are similarities when it comes to performances for Linear, Ridge and Lasso regressions due to the dataset used which is ASAP. Furthermore, the results were evaluated using Cohen Weighted Kappa (CWA) score and compared the agreement between the human raters. The CWA result is 0.659 that can be interpreted as Strong level of agreement between the Human Grader and the automated essay score. Therefore, the proposed AES has 64-81% reliability level.

In this paper, we analyze the effect of the representative spectral indices, normalized difference vegetation index (NDVI), normalized difference water index (NDWI) and normalized difference built-up index (NDBI) on classification accuracies of Landsat-8 OLI image. After creating these spectral index images, we propose five methods to select the spectral index images as classification features together with Landsat-8 OLI bands from 1 to 7. From the experiments we observed that when the spectral index image of NDVI or NDWI is used as one of the classification features together with the Landsat-8 OLI bands from 1 to 7, we can obtain higher overall accuracy and kappa coefficient than the method using only Landsat-8 OLI 7 bands. In contrast, the classification method, which selected only NDBI as classification feature together with Landsat-8 OLI 7 bands did not show the improvement in classification accuracies.

Microalgae offer promising and multifaceted solutions to the ongoing issues regarding energy security and climate change. One of the major bottlenecks in utilizing algal biomass is the excessive amount of moisture to be managed after harvest, which translates to costs in the dewatering step. Newer strategies have been developed to be able to convert algal biomass feedstock to biodiesel without the need for extraction and drying, such as in-situ transesterification. This process can be improved by concurrently subjecting the system under subcritical conditions, which could also potentially remove the use of catalysts as well as offer tolerance to free fatty acid content of the feedstock. A definitive screening design of experiment was utilized to provide an acceptable prediction on the effects of key process parameters – temperature, reaction time, and solvent-to-solid ratio to the obtainable fatty acid methyl ester (FAME) yield and process power consumption. The optimum operating condition, which combines the benefits of maximizing the FAME yield and minimizing the process power consumption was found to be at 220 °C, 2 h, and 8 ml methanol per gram of biomass (80 wt% moisture). This produces a FAME yield of 74.6% with respect to the maximum obtainable FAME. Sensitivity analysis discussed the implications regarding the weight of importance between the two responses of interest. The benefits of the proposed process can be observed when compared to its conventional transesterification counterpart in terms of energy savings and reduced environmental impact. Hence, this process offers a feasible alternative to produce biodiesel from microalgae.

This study utilized data mining and geo-mapping methods to develop a fire risk management system for the Bureau of Fire Protection (BFP) in the city of Manila. This system was integrated into a web portal where the BFP personnel can log and view fire incident reports, which are then evaluated and mined for marking fire “hot spots” on a customized map of the city, as well as for producing recommendations based on the risk level assessment of any location for a given date. Based on results of experimentation, the Decision Tree classifier model was selected, with 95.92% accuracy. Geocoding produced 92% output of geographical coordinates from address information in the data set. The system can help the fire agency in raising the fire risk awareness of the community country and in facilitating their fire risk reduction planning.

Advances in computing and the availability of massive health data are opening up new possibilities for the generation of helpful decision-support tools. Forecasting the incidence of medical cases, which is one of the first steps in institutional planning, plays an important role in planning health control strategies in order to develop intervention programs and allocate resources. This study focused on medical cases forecasting for the development of resource allocation recommender system. Data cleaning was performed in the historical data of medical cases from Mabalacat City Health Office in order to detect and removing corrupt and inaccurate records. The forecasting models used are Seasonal Auto-Regressive Integrated Moving Average (S-ARIMA) and Exponential Smoothing (ES). Factor values of twelve (12) for monthly seasonality and four (4) for quarterly seasonality were used for the S-ARIMA models. The alpha values used in ES are 0.1, 0.3, 0.5, 0.7 and 0.9. The computed Mean Absolute Deviation (MAD) and the Mean Absolute Percent Error (MAPE) results of S-ARIMA and ES were compared and the forecasting model with the better accuracy was used for a particular medical case forecast value. The use of the mentioned forecasting algorithms and accuracy tests were embedded in the development of an online information system with resource allocation recommender for Mabalacat City health units.