Felicito Caluyo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Felicito Caluyo has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jeffrey Sarmiento
Department of Electrical Engineering, Batangas State University, The National Engineering University, Alangilan, Batangas City 4200, Philippines
3 shared publications - Cristina Amor Rosales
Batangas State University–The National Engineering University
2 shared publications - Rowell Marquez Hernandez
College of Engineering, Batangas State University, the National Engineering Alangilan Campus, Batangas City 4200, Philippines
2 shared publications - Anton Louise De Ocampo
Batangas State University, Philippines
1 shared publication - Chen Zhenyang
Batangas State University, Batangas, Philippines
1 shared publication - Liu Zigui1 shared publication
Latest Publications
- Open Access
- 30 October 2024
- Published by Iskenderun Technical University in Natural and Engineering Sciences
- Vol. 9 (2) , 198-212
Improving Communication Networks to Transfer Data in Real Time for Environmental Monitoring and Data Collection
Integrated communication networks (CN) have proven successful in tracking environmental activities, wherein several sensors are installed throughout diverse surroundings to gather data or observe certain events. CNs, comprising several interacting detectors, have proven effective in various applications by transmitting data via diverse transmission methods inside the communication system. The erratic and constantly changing surroundings necessitate conventional CNs to engage in frequent conversations to disseminate the latest data, potentially incurring substantial connection expenses through joint data gathering and dissemination. High-frequency communications are prone to failure due to the extensive distance of data transfer. This research presents a unique methodology for multi-sensor environmental monitoring networks utilizing autonomous systems. The transmission system can mitigate elevated communication costs and Single Point of Failing (SPOF) challenges by employing a decentralized method that facilitates in-network processing. The methodology employs Boolean systems, enabling a straightforward verification process while preserving essential details about the dynamics of the communication system. The methodology further simplifies the data collection process and employs a Reinforcement Learning (RL) technique to forecast future events inside the surroundings by recognizing patterns.
- 30 October 2024
- Published by Iskenderun Technical University in Natural and Engineering Sciences
- Vol. 9 (2) , 198-212
Open AccessImproving Communication Networks to Transfer Data in Real Time for Environmental Monitoring and Data Collection
Integrated communication networks (CN) have proven successful in tracking environmental activities, wherein several sensors are installed throughout diverse surroundings to gather data or observe certain events. CNs, comprising several interacting detectors, have proven effective in various applications by transmitting data via diverse transmission methods inside the communication system. The erratic and constantly changing surroundings necessitate conventional CNs to engage in frequent conversations to disseminate the latest data, potentially incurring substantial connection expenses through joint data gathering and dissemination. High-frequency communications are prone to failure due to the extensive distance of data transfer. This research presents a unique methodology for multi-sensor environmental monitoring networks utilizing autonomous systems. The transmission system can mitigate elevated communication costs and Single Point of Failing (SPOF) challenges by employing a decentralized method that facilitates in-network processing. The methodology employs Boolean systems, enabling a straightforward verification process while preserving essential details about the dynamics of the communication system. The methodology further simplifies the data collection process and employs a Reinforcement Learning (RL) technique to forecast future events inside the surroundings by recognizing patterns.
- Open Access
- 30 October 2024
- Published by Iskenderun Technical University in Natural and Engineering Sciences
- Vol. 9 (2) , 184-197
Automatic Classification and Identification of Plant Disease Identification by Using a Convolutional Neural Network
The prompt detection of plant diseases mitigates adverse effects on plants. Convolutional neural networks (CNN) and intense learning are extensively utilized in computer vision and recognition of pattern tasks. Scientists presented several DL algorithms for the detection of plant illnesses. Deep learning (DL) models need many parameters, resulting in extended training durations and complicated implementation on compact devices. This research presents a unique DL model utilizing the inception tier and residual connections. Depthwise differentiated convolution is employed to decrease the variable count. The suggested model has undergone training and evaluation using three distinct plant disease databases. The level of accuracy achieved on the PlantVillage database is 97.2%, on the rice disease database is 98.4%, and on the cassava database is 96.3%. The suggested model attains superior accuracy relative to state-of-the-art DL methods while utilizing fewer variables.
- 30 October 2024
- Published by Iskenderun Technical University in Natural and Engineering Sciences
- Vol. 9 (2) , 184-197
Open AccessAutomatic Classification and Identification of Plant Disease Identification by Using a Convolutional Neural Network
The prompt detection of plant diseases mitigates adverse effects on plants. Convolutional neural networks (CNN) and intense learning are extensively utilized in computer vision and recognition of pattern tasks. Scientists presented several DL algorithms for the detection of plant illnesses. Deep learning (DL) models need many parameters, resulting in extended training durations and complicated implementation on compact devices. This research presents a unique DL model utilizing the inception tier and residual connections. Depthwise differentiated convolution is employed to decrease the variable count. The suggested model has undergone training and evaluation using three distinct plant disease databases. The level of accuracy achieved on the PlantVillage database is 97.2%, on the rice disease database is 98.4%, and on the cassava database is 96.3%. The suggested model attains superior accuracy relative to state-of-the-art DL methods while utilizing fewer variables.
- Open Access
- 1 January 2024
- Published by Salud, Ciencia y Tecnologia in Salud, Ciencia y Tecnología - Serie de Conferencias
- Vol. 3, .760
Badminton Service Foul System based on machine vision
Introduction: In today's sports activity landscape, the identity of fouls and misguided moves in badminton poses extensive challenges. A badminton carrier foul takes place when a player fails to stick to the guidelines in the course of a serve. Common fouls such as improper position, foot placement and racket position.Aim: The purpose of this study is to improve an advanced machine version system using Archerfish looking Optimization-driven intelligent ResNet50 (AHO-IResNet50) to enhance the accuracy of service foul identification in badminton, thereby improving match score analysis and decision-making for the Badminton practices.Methodology: The dataset were obtained that incorporates numerous images capturing various phases of badminton matches, with racket positions and player movements during service, to train the proposed model. A discrete Wavelet rework (DWT) algorithm is utilized to extract the huge features. The proposed method includes an AHO algorithm to fine-tune the IResNet50 model for more desirable badminton service foul identification. This proposed approach leverages the adaptability of Archerfish hunting strategies to optimize IResNet50's parameters, enhancing accuracy and reducing errors in badminton foul recognition.Results: The suggested recognition model is applied in a Python software program. During the result analysis phase, we evaluated the model's efficacy across diverse parameters along with accuracy (94.7%), precision (86.7%), recall (84.9%), and specificity (93.5%). We additionally conduct comparative analyses with existing methodologies to examine the effectiveness of our suggested classification. Conclusion: The acquired findings show the efficacy and superiority of the proposed framework, significantly lowering errors and improving the accuracy of foul identification
- 1 January 2024
- Published by Salud, Ciencia y Tecnologia in Salud, Ciencia y Tecnología - Serie de Conferencias
- Vol. 3, .760
Open AccessBadminton Service Foul System based on machine vision
Introduction: In today's sports activity landscape, the identity of fouls and misguided moves in badminton poses extensive challenges. A badminton carrier foul takes place when a player fails to stick to the guidelines in the course of a serve. Common fouls such as improper position, foot placement and racket position.Aim: The purpose of this study is to improve an advanced machine version system using Archerfish looking Optimization-driven intelligent ResNet50 (AHO-IResNet50) to enhance the accuracy of service foul identification in badminton, thereby improving match score analysis and decision-making for the Badminton practices.Methodology: The dataset were obtained that incorporates numerous images capturing various phases of badminton matches, with racket positions and player movements during service, to train the proposed model. A discrete Wavelet rework (DWT) algorithm is utilized to extract the huge features. The proposed method includes an AHO algorithm to fine-tune the IResNet50 model for more desirable badminton service foul identification. This proposed approach leverages the adaptability of Archerfish hunting strategies to optimize IResNet50's parameters, enhancing accuracy and reducing errors in badminton foul recognition.Results: The suggested recognition model is applied in a Python software program. During the result analysis phase, we evaluated the model's efficacy across diverse parameters along with accuracy (94.7%), precision (86.7%), recall (84.9%), and specificity (93.5%). We additionally conduct comparative analyses with existing methodologies to examine the effectiveness of our suggested classification. Conclusion: The acquired findings show the efficacy and superiority of the proposed framework, significantly lowering errors and improving the accuracy of foul identification