MENU

Sex: Female
Education:

  • Doctor in Information Technology, Technological Institute of the Philippines, 2019\
  • Master of Science in Computer Science, Mapua University, 2015
  • Master of Information Technology, Technological University of the Philippines, 2004
  • Bachelor of Science in Information Technology, 1999

Field of Specialization

Information Technology
Knowledge Management
E-Business
IT Project Management
Information System Management
Information Management
Information Technology Management
Business Process Management
Information Technologies
Emphatic Computing

Researches:

Article title: A Flexible Learning Framework Implementing Asynchronous Course Delivery for Philippine Local Colleges and Universities
Authors: Mideth Abisado
Publication title: International Journal of Advanced Trends in Computer Science and Engineering 9(1.3):413-421, June 2020

Abstract:
The Corona Virus 19 (COVID 19) pandemic has brought challenges and opportunities in the world and the Philippine educational system. While there are universities that are doing online learning in the past decades, over 100 local universities and colleges are left with traditional instruction, face-to-face learning sessions. The traditional universities have no choice but to become adaptive to the “new normal” once declared by the World Health Organization. Philippine data on the effect of pandemic suggest that the student populace are prone to carry the virus through interaction and traveling to and from the schools. Classes cannot be delivered in traditional ways anymore, to mitigate the spread of the virus, until a vaccine is available. This paper provides a framework for local universities and colleges in implementing flexible learning procedures. The asynchronous course delivery consists of the design of outcomes-based teaching and learning plan, course materials, scheduled on-line and face-to-face meetings, technology, and center for technology education.
Full text link https://tinyurl.com/yfhaf5m6

Papers Presented:

Article title: Science Mapping of Social Media Analytics in Health Through Artificial Intelligence
Authors: Rogelio Ruzcko Tobias, Rachel Edita Roxas, Mideth Abisado
Conference title: TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON)

Abstract:
This paper presents a systematic literature review and bibliometric analyses of Scopus-indexed documents in social media analytics in health during the CoVid-19 pandemic that used artificial intelligence methodologies. From the 179 extracted Scopus-indexed publications in August 2021, 128 were left after removing 51 documents using the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) procedure. Analyses and visualizations using VOSviewer reveal research productivity, affiliation and collaboration networks, and the corresponding relationship between research productivity and the research networks. Conclusions and recommendations for future work are presented to further nurture the current research environment of social media analytics through artificial intelligence methodologies.
Full text available upon request to the author

Article title: Towards the Development of Music Mood Classification of Original Pilipino Music (OPM) Songs Based on Audio and Lyrics Keyword
Authors: Mideth Abisado, Mardyon Yongson, Ma.Ian De Los Trinos
Conference title: ICSET 2021: 2021 5th International Conference on E-Society, E-Education and E-Technology

Abstract:
This paper presents music mood classification of Original Pilipino Music (OPM) songs, particularly Filipino songs using audio and lyrics information. The song's mood is expressed utilizing musical features, but a relevant part also seems to be conveyed by the keywords to its lyrics. The study evaluates with the help of two music teachers and music analysts each factor independently. It explores the possibility of combining both, using Natural Language Processing and Music Information Retrieval techniques. It shows that standard separation-based strategies and Latent Semantic Analysis can group the verses essentially superior to random. Yet, the exhibition is still very substandard compared to that of sound-based systems. The study presents a technique dependent on contrasts between language models that gives performances closer to sound-based classifiers—in addition, interwinding this in a multimodal framework, which is audio and text. It permits an improvement in the general execution. We exhibit that verses and sound data are corresponding and can be joined to improve an ordered framework.
Full text available upon request to the author

Article title: Academic Student Progression Predictive Analysis Application in Secondary Education Institution
Authors: Mideth Abisado, Peejay Vargas, Ma.Ian De Los Trinos
Conference title: ICSET 2021: 2021 5th International Conference on E-Society, E-Education and E-Technology

Abstract:
The study developed an Academic Student Progression Predictive Analysis Application for Dr. Josefa Jara Martinez High School (DJJMHS) to provide an intranet platform for the centralized collection of data records and management of school forms. The system includes school details, school forms, real-time records of attendance, student academic progress, prediction, visualization, monitoring of employee performance, and report generation. It has enhanced security protection and can provide all users with a secured network connection. The system uses a graphical user interface to display all the functions to access all system features. The system was developed using standards and tools such as HTML5, CSS3, JavaScript, and Phyton-MySQL. It creates an interface of system transactions in utilizing technology issuance of School Forms such as SF1, SF2, SF4, SF5, SF6, SF9, and SF10. The information can be encoded once a database connection is established. It is ready to create records into the database tables using the execute method of the developed system. All required features signified functionality and reliability based on test cases performed in two cycles in a live environment. The system was evaluated “Very Good” by 30 respondents using the ISO 25010 Software Quality Matrix. This indicates that the system can be an accurate and reliable tool for accessing an end-user's data and other services.
Full text available upon request to the author

Article title: Development of an Information-Based Dashboard: Automation of Barangay Information Profiling System (BIPS) for Decision Support towards e-Governance
Authors: Angelique D. Lacasandile, Mideth B. Abisado, Rogel M. Labanan, Lalaine P. Abad
Conference title: ICSET'20: 2020 The 4th International Conference on E-Society, E-Education and E-Technology

Abstract:
The need to address societal issues of every community is a salient aspect that demands attention from the people in authority. These are important responsibilities of every barangay and its official in the Philippines. Profiling each household in the community using information and communication technology could achieve good governance through E-government as its core. Once profile data is aggregated, essential information could provide statistics in labor and employment, family income and expenditures, demography by (population) and (age), water and sanitation, type of housing and education. The focus is based on the profiling of Zone 42 and adding other facets as mentioned above was initiated, with the idea that educational institution around the barangay can help towards the areas included. This paper intends to aid barangay official in budget allocation and decision making in their respective governed area with the use of Barangay Information Profiling System (BIPS). Building an Information-Based Dashboard was initiated last 2016 and assessed by IT expert, was given readiness for beta launch to its target users. The functionality criteria were given a mean score of 4.47, which means that the respondents agreed that the system sequence of operation is easy to understand, and the result of their queries is correct and accurate. The system testing had a favorable result with a mean of 4.50 which means that the system passed the standard of completing, processing of a request, response time and the usage of computer resources for all of its function.
Full text available upon request to the author

Article title: An Academic Affect Dataset: Spontaneous Facial Expressions and Head poses Collected during Online Examination
Authors: Mideth B. Abisado, Ma. Ian P. De Los Trinos, Ramon L. Rodriguez, Antero Rosauro V. Arias Jr.
Conference title: ICSET'20: 2020 The 4th International Conference on E-Society, E-Education and E-Technology

Abstract:
The learning engagement in most studies is focused on identifying learner affect during class discussion and content delivery. This study an academic affect dataset from spontaneous facial expressions and head poses during an online learning. Using thematic analysis and expert opinion, the study identified five emotions relative to learning. The dataset was correctly annotated with a kappa value of 0.62. Annotation by the coders were mapped with the features extracted from OpenFace 2.0 that produced the Academic Affect Dataset. The multi-modal affect model referred to the students' facial expressions and head pose gestures as they took and answered questions during online learning examination. An accuracy of 92.66% was measured from the model.
Full text available upon request to the author

Article title: Knowledge-Based and Crowdsourcing Fault Analysis Toolkit for Unexpected Vehicle Malfunction
Authors: Johnathan Richard A. Barrios; Ma. Ian P. Delos Trinos; Mideth B. Abisado
Conference title: 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM )

Abstract:
Mobile gadgets such as phones and tablets are used not only to communicate but also handy and a need to access applications that improves daily people’s lives. Considering not all drivers have enough knowledge of what car mishaps they will encounter on the road or even idea on where is the location of the nearest mechanic shop plus what numbers to call for help like towing services. The research suggests solutions to unexpected vehicle malfunction by implementing a mobile application that has access to an updated knowledge base for basic car mishaps and available services. Providing the best functionality, the mobile application undergoes a variety of functional test procedures that satisfies the required parameters needed. The tests were successfully conducted, proving that the project is functional.
Full text available upon request to the author

Article title: Doctor’s Cursive Handwriting Recognition System Using Deep Learning
Authors: Lovely Joy Fajardo; Niño Joshua Sorillo; Jaycel Garlit; Cia Dennise Tomines; Mideth B. Abisado, et al.
Conference title: 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM )

Abstract:
Handwriting is a skill to express thoughts, ideas, and language. Over the years, medical doctors have been well-known for having illegible cursive handwritings and has been a generally accepted matter. The datasets used in this paper are samples of doctors cursive handwriting collected from several clinics and hospitals of Metro Manila, Quezon City and Taytay, Rizal. In this paper, we present the Handwriting Recognition System using Deep Convolutional Recurrent Neural Network that is developed in order to identify the text in the image of prescriptions written by the doctors and show the readable text conversion of the cursive handwriting. In this study two models were evaluated and based on the experimentation CRNN with model-based normalization scheme than the CRNN alone. This study achieved 76% training accuracy rate and the developed model was found successfully implemented in a mobile application, having achieved a validation accuracy of 72% for the validation set from the remaining 540 images of prescription. The mobile application was validated for the second time using the captured 48 handwriting samples written by the researchers and correctly identified 17 images out of 48 this gives us a 35% validation accuracy.
Full text available upon request to the author

Article title: Real-time Class Attendance Monitoring using Smart Face Recognition
Authors: Ma. Ian P. Delos Trinos; Jozar H. Rios; Keith Gabriel O. Portades; Paulo Rae O. Portades; Renielle Miguel P. Langreo; Mideth B. Abisado
Conference title: 2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM )

Abstract:
Student attendance in classroom-based learning usually becomes a pain stake for teachers in terms of monitoring and records keeping. The study provides a solution to this by using the technology of image processing applied in facial recognition. A software was developed to check the student attendance in real-time. The ISO 9126 gauges for functional stability, usability, reliability, portability, efficiency, and maintainability. The functionalities and user acceptance were measured within the bounds of software engineering and measured acceptable to a mean very acceptable rating of 3.74
Full text available upon request to the author

Article title: Modeling Filipino Academic Affect during Online Examination using Machine Learning
Authors: Mideth B. Abisado, Ramon L. Rodriguez, Antero Rosauro V. Arias, Cheryl Mari M. Isip, James Darryl D. Bungay, John Mark V. Cipriano, Larry A. Vea
Conference title: the 20th Annual SIG Conference

Abstract:
A learning environment is comprised of emotional and cognitive activities. The need to incorporate the measurement of student affect during the learning assessment is necessary. This study measured academic affect during assessment and developed an online examination multi-modal academic affect model. Using thematic analysis and expert opinion, the study generated the presence of the following academic affect: relaxed, curious, bored, frustrated, and distracted. The academic affects were annotated with a computed interrater kappa value of 0.62. Annotation by the coders was mapped with the features extracted from a behavior analysis toolkit that produced the Filipino Online Examination Multi-Modal Affect Dataset. The model yielded an accuracy of 92.66%.
Full text available upon request to the author

Article title: Experimental Facial Expression and Gesture Training Towards Academic Affect Modeling
Authors: Mideth Abisado; Bobby Gerardo; Larry Vea; Ruji Medina
Conference title: 2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management (HNICEM)

 Abstract:
The engagement of students during examination can be evaluated by their emotion. This relates to the application of affective computing in education. This paper reports the basis and status of designing an academic affect model towards engagement identification of students taking on-line examination. The initial status defined academic affect that relates to student affect during on-line examination and the validation of data sets are created for use of this study and future work. Status on progress includes video data collected and expert annotated data set.
Full text available upon request to the author

Article title: Towards academic affect modeling through experimental hybrid gesture recognition algorithm
Authors: Mideth B. Abisado, Bobby D. Gerardo, Larry A. Vea, Ruji P. Medina
Conference title: The 2018 International Conference

Abstract:
The identification of learner engagement is an important aspect of assessment. Aside from facial expressions, gesture is a key feature in the identification of student engagement. The costly video invigilation during assessment shows the need to find other ways to define student engagement during an online examination. For this purpose, this study proposed gesture modeling to classify and identify affect. The research defines student disengagement affect using head poses as gesture during the online examination. The divide-and-conquer algorithm implementation on object detection using Haar Cascade feature extraction and HMM classification resulted in 78.77% accuracy level to classify disengaged behavior during an online examination. The experimental results show that head-poses when properly modeled can be used to define affect as applied to examination behavior.
Full text available upon request to the author

Article title: Towards Keystroke Analysis using Neural Network for Multi-Factor Authentication of Learner Recognition in On-Line Examination
Authors: Mideth Abisado
Conference title: 2017 Manila International Conference on “Trends in Engineering and Technology” (MTET-17)

Abstract:
Technology often tries to mimic nature. Therefore, the idea to recognize a user based on several of their traits, as it is done in real life, logically comes to mind. In this case, the motive of this study focuses on behavioral biometrics. The opportunity to use biometrics and pattern classification to develop a new solution using keystroke analysis and recognition to address online examination fraud and cheating issues. This framework could be a new non-intrusive recognition approach, taking a valuable part in the information system's security chain. User's keystrokes are recorded as they take the exam. The Multi-Layer Perceptron Neural Network is utilized to classify learner keystroke as they take an on-line examination.
Full text available upon request to the author

Article title: Tutoring System Implementing Facial Expression Recognition Through Learner's Affect Classification
Authors: Mideth Abisado and Noel Linsangan
Conference title: CAITE 2016 4th National Conference

Abstract:
The scope of this study is to identify the relationship of the learner's facial expression during the use of a tutoring system and the result of assessment. The study uses facial expression as a tool to interpret comprehension after electronic lesson is delivered. The Scale Invariant Feature Transformation algorithm was implemented in a tutoring system. The tutoring system discussed a topic on learning C++ Programming Language. The study employed one hundred twenty exemplars with an average of 9000 frames as data correlated with test results. The results of the study indicated a positive relationship between the learner's affect and garnered test result.
Full text available upon request to the author