Antipas T. Teologo, Jr.
11 Publications
Scopus ID: 105030165309
2024 IEEE 16th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2025), pp. 1-5
Conference Paper | Published: December 3, 2025
Abstract
The development of reliable wireless networks is crucial for advancing sustainability. Not only does it facilitate remote work and telecommunication which are critical remote services such as telemedicine and distance education, they are also essential in supporting sustainable practices like the application of IoT in monitoring environmental conditions and energy usage. To ensure that these networks work optimally, it is essential that the datasets used in their development are not only accurate but are also distinct. This study contributes to this end by analyzing the datasets generated by the COST 2100, a model that is used extensively in wireless communications. Using ANOVA, the researchers determined if the dataset are indeed distinct as signals bounce about multiple clustering which use Multiple Input, Multiple Output (MIMO) Technology similar to modern wireless systems like 5G. Results show that the different variables or dimensions are distinct from each other. Thus, the datasets generated by COST2100 are suitable to be utilized in further preprocessing methods of wireless multipath clustering, ultimately contributing to building a more sustainable wireless communication system.
Scopus ID: 105008218295
2025 IEEE Global Engineering Education Conference (EDUCON), (2025), pp. 1-6
Conference Paper | Published: January 1, 2025
Abstract
The fast progression of Artificial Intelligence (AI) technology has elicited substantial ethical issues, especially within engineering fields that directly impact society. This study seeks to establish a framework for integrating Ethical AI ideas into engineering curriculum, therefore preparing future engineers to address the moral, social, and legal ramifications of AI. The framework incorporates Ethical AI principles into current course formats, encompassing introductory, enabling, and demonstrative courses, with particular focus on subjects like Science, Technology, and Society, Professional Engineering Ethics, and thesis/capstone projects. The paper recommends a curriculum update that complies with industry norms and equips students to embrace responsible AI practices, based on a thorough analysis of pertinent Commission on Higher Education (CHED) Memorandum Orders (CMOs) and literature. The research also presents evaluation rubrics to gauge students' comprehension and implementation of Ethical AI concepts in their academic projects. The paper suggests that integrating Ethical AI into engineering education enables universities to cultivate engineers who possess both technical proficiency and a robust ethical framework about AI technology.
Scopus ID: 85148209090
Journal of Communications, (2023), pp. 135-139
Antipas T. Teologo, Jr.
& Lawrence MaterumJournal Article | Published: February 1, 2023
Abstract
Over the past decade, several studies have been conducted to discover a better-performing multipath clustering technique. Developing a multipath clustering technique with better accuracy performance is a big challenge considering the varying properties of the multipath propagations that change over time. In this study, several clustering techniques have been investigated and compared to the newly-developed technique for performance analysis. Using the Jaccard score as a metric for the accuracy of grouping correctly the wireless multipaths, the performance of the different clustering techniques has been determined and compared to the newly-developed technique. The proposed clustering algorithm shows improved performance in the indoor channel scenarios but needs further investigation in the semi-urban environment.
Scopus ID: 85199879034
2023 IEEE 15th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2023), pp. 1-5
Conference Paper | Published: January 1, 2023
Abstract
Diabetes mellitus is a disease incorporated with carbohydrate metabolism whereas the body becomes unable to generate or react with insulin which leads to abnormal levels of blood sugar (glucose). In a worldwide perspective, Diabetes mellitus is ranked as the 9th leading cause of death based on the records of the World Health Organization and according to the International Diabetes Federation, there are about 463 million diabetic people worldwide in 2019 which is projected to increase to 700 million diabetic people by year 2045. In a regional perspective, about 251 million (45%) diabetic people resides on the Western Pacific and Southeast Asian region, whereas about 140 million people are undiagnosed of the disease. In this study, a genetic algorithm-optimized neural network using MATLAB was developed based on the risk factors. The experimental results show that the best validation performance has a value of 0.014129 and with a regression model coefficient R2 value of 0.95864.
Scopus ID: 85159458476
2022 IEEE 14th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2022), pp. 1-6
Conference Paper | Published: January 1, 2022
Abstract
The liver is the human body's largest internal organ. Globally, liver disease is considered the cause of approximately 2 million yearly death – whereas the 11th and 16th worldwide leading causes of death are cirrhosis and liver cancer. In the Philippines, according to the Department of Health (DOH), liver cancer is ranked as the 3rd leading cause of death. In most cases, surgery may be considered a possible cure if detected at an early stage. However, there is no efficient early detection method for liver cancer. In this paper, multiple machine learning methodologies are modeled to provide diagnosis classification of liver disease based on the laboratory parameter readings. Based on the results for all models, the most accurate prediction is made by ANN at 89%, followed by SVM at 79.5%. The results establish that AI-based machine learning approaches may be utilized for assisting medical-related diagnosis.
Scopus ID: 85116802657
Journal of Information and Communication Technology, (2021), Vol. 20
Lawrence Materum &
Antipas T. Teologo, Jr.
Antipas T. Teologo, Jr.
Journal Article | Published: October 1, 2021
Abstract
Wireless multipath clustering is an important area in channel modeling, and an accurate channel model can lead to a reliable wireless environment. Finding the best technique in clustering wireless multipath is still challenging due to the radio channels’ time-variant characteristics. Several clustering techniques have been developed that offer an improved performance but only consider one or two parameters of the multipath components. This study improved the K-PowerMeans technique by incorporating weights or loads based on the principal component analysis and utilizing the Minkowski distance metric to replace the Euclidean distance. K-PowerMeans is one of the several methods in clustering wireless propagation multipaths and has been widely studied. This improved clustering technique was applied to the indoor datasets generated from the COST 2100 channel Model and considered the multipath components’ angular domains and their delay. The Jaccard index was used to determine the new method’s accuracy performance. The results showed a significant improvement in the clustering of the developed algorithm than the standard K-PowerMeans.
Scopus ID: 85127578555
2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2021), pp. 1-6
Conference Paper | Published: January 1, 2021
Abstract
This device can be useful by rice field owners to decrease the number of pests in rice fields, also this will provide a non-chemical and energy saving way utilizing UV LEDs to attract bugs and capturing them then the system will be controlled by a microcontroller. Rice, the staple food of over half of the world’s population, is locally known in the Philippines as palay, bigas, or kanin. As population grows, demand for rice increases. Thus, the need for sufficient rice production is also needed. Different agrarian problems come with the production of rice the most destructive are pests. The results we’ve yield were, the pests were attracted best in UV light. Also, the laser sensors we’re effective in detecting and capturing the pests. Basically this device won’t harm the rice crops resulting to a greater production and more profit because it is a non-chemical device and energy saving way utilizing UV LEDs to attract bugs and capturing them.
Scopus ID: 85125815284
Journal of Engineering Science and Technology, (2021), pp. 33-45
Journal Article | Published: January 1, 2021
Abstract
Data analysis is an integral part of research. Most researchers examine their results by using graphs, tables, charts, and figures. These methods are effective, but knowledge transfer is limited because it only depends on what the authors or researchers have presented. The need to scrutinise further the given data is essential. One way of addressing this problem is to utilise a graphical user interface (GUI), wherein a user can manually choose some parameters of an extensive dataset to display and analyse. In this paper, the results of the four variants of clustering techniques, namely the Ant Colony Optimization (ACO), Gaussian Mixture Model (GMM), K-Power Means (KPM), and Kernel-Power Density-Based Estimation (KPD), in grouping the wireless multipath propagations, are evaluated through the use of a GUI. The accuracy performance of each clustering algorithm can be obtained by choosing in the GUI the corresponding channel scenario that the user would like to investigate. A deeper analysis of the clustering characteristics can also be done by selecting other parameters in the GUI. This selection gives a better understanding of the behaviour of each clustering technique and provides an effective way of presenting and analysing the different sets of data.
Scopus ID: 85084759812
2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM ), (2019), pp. 1-6
Conference Paper | Published: November 1, 2019
Abstract
Pulsars enabled astronomers to study neutron stars and verify general relativity under intense gravitational field conditions. However, finding pulsars is not as easy as it seems because most of them have weak pulses that get drowned in the background noise and hence do not get detected. This paper presents a novel way of classifying radio emission patterns collected from a radio telescope whether it is from a pulsar or not through machine learning and genetic algorithm. The dataset was acquired from the High Time Resolution Universe (HTRU) survey two which contains eight numerical features and one target variable describing the pulse profile. Synthetic Minority Oversampling Technique (SMOTE) was applied to the dataset to fix the imbalance between classes. A genetic algorithm library was used to automatically select the best feature preprocessing method, feature selection/reduction technique, machine learning model inside the scikit-learn library, and hyperparameter settings. The genetic algorithm suggested using a single stack and multiple stack classifiers for different sets of features. The optimum level of hyperparameters was also given with the help of the same algorithm. The selected pipelines consistently reported a score of more than 99% in all the evaluation metrics used.
Scopus ID: 85084747218
2019 IEEE 11th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management ( HNICEM ), (2019), pp. 1-5
Conference Paper | Published: November 1, 2019
Abstract
The electroencephalogram (EEG) signals being a recording of the electrical activity of the brain provides valuable information in the analysis of its function and disorder. Epilepsy is a brain disorder characterized by uncontrolled excessive activity. Repeated abnormal disturbance or seizure causes epilepsy. Hence, EEG signals act as a diagnostic tool for epilepsy. An approach based on tree-based pipeline optimization tool (TPOT) is presented for classification of EEG signals as either seizure or normal activity in the brain. A binarized dataset with sampled signal levels and the corresponding class is subjected to a genetic approach for acquiring an optimized predictive model. In TPOT, the tedious process involved in machine learning being repeatedly performed until arriving at the best solution is automated using genetic algorithm, i.e., evaluate-select-crossover-mutate is repeated to tune the pipeline. In the settings used in this paper, there are 90 pipeline configurations for evaluation for which around 450 models are fitted and evaluated against the training data in one grid search. The best pipeline is the one with the highest cross-validation score in the run at 95.94%. The test accuracy is at 95.27% which is just a little lower than the cross-validation score. The predictive model consists of pre-processing steps Maximum Absolute Scaler and Function Transformer which is utilized by a Gaussian Naïve Bayes classifier. The system is trained and tested for epileptic seizure detection using raw EEG signals. The optimized features and predictor obtained via TPOT resulted to a high-performance accuracy for epileptic seizure detection.