Pocholo James M. Loresco
29 Publications
Scopus ID: 85127555156
2021 IEEE 13th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2021), pp. 1-5
Conference Paper | Published: January 1, 2021
Abstract
Shrimp species belong to the class of Crustacea under order Decapoda under suborder Natantia. The shrimp species are characterized with semi-transparent body which grow up to more than 20 cm. In terms of economic impact, the shrimp industry is considered highly profitable based on the studies by WorldAtlas and Philippine Statistics Authority. Therefore, as part of the necessary better management principles (BMPs), shrimp growth should be monitored. However, for the shrimp length is typically measured by a manual tool like rulers or calipers which is known to be a tedious process most especially when large number of samples are considered. Hence, in this study, image processing via OpenCV was utilized to estimate the length of shrimp species. The performance of the image-based approach is compared with the manual measurement and yielded a relative percent error of 6.23%. Based on the results, it can be concluded that the image-based approach can be utilized to determine the shrimp length.
Scopus ID: 85104983562
2020 IEEE 12th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2020), pp. 1-6
Conference Paper | Published: December 3, 2020
Abstract
Controlled environment agriculture are being developed with the purpose of increasing production yield in farms. For optimal yield, it is very important to have an understanding about the relationship of environmental factors such as radiation, temperature, nutrients, water, and in relation with the growth state of the crop. Growth monitoring of cherry tomato crops in traditional methods are extremely labor-intensive, destructive, and costly in terms of time and money. Thus, application of computer vision has become an area of interest in the study of monitoring tomatoes' growth. In this study, image processing techniques are employed to identify the growth stage of cherry tomato as fruiting, flowering, and leafing stage. Confusion matrix with True Positive rate and False negative rate, and ROC are used to evaluate the decision support system developed. Experimental results show a high performance in determining the growth stage of test cherry tomato images.
Scopus ID: 85105008189
2020 IEEE 12th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM), (2020), pp. 1-5
Conference Paper | Published: December 3, 2020
Abstract
Diabetes is a disease which chronic in nature, which is caused by an elevated blood sugar (or blood glucose) level. The metabolic disease is linked to several potential serious organ complications including nerves, kidneys, eyes, blood vessels, and the heart. According to the International Diabetes Federation, in 2019, about 2 million deaths were recorded worldwide due to diabetes. Furthermore, according to Philippine Statistics Authority (PSA), Diabetes Mellitus is considered as the fifth main cause of in the Philippines in the past years and in a 2015 study, about 1.7 million Filipinos are still undiagnosed of diabetes. Therefore, several machine learning-based techniques were developed for diabetes risk prediction. However, these works have yet to utilize artificial neural networks using the symptom information of suspected diabetic patients. This research paper demonstrated an ANN-based diabetes risk classification based on the symptom information of patients. The scaled conjugate gradient backpropagation technique was utilized for neural network training process. The classification system showed 99.2% overall correctness in determining the likelihood of diabetes.
Scopus ID: 85084746978
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
Shrimp farming is a highly profitable business in the aquaculture industry. The farming profitability can be achieved by the implementation of better management practices in conjunction with optimal shrimp feed management and growth monitoring. Manual measurement for shrimp growth on a large population is a tedious and difficult task. Underfeeding results to lower growth rate, and overfeeding results to environmental pollution. Automated, continuous, and non-invasive methods therefore such as computer vision are being increasingly employed. However, existing researches of vision-based measurement of growth parameters are not yet incorporated to shrimp feed management. This paper presented an Artificial Neural Network-based decision support system of classifying feed type whether starter, grower or finisher using area, length and weight derived from image processing techniques. The neural network was trained using scaled conjugate gradient back propagation. The decision support system exhibited promising results in feed type classification.
Scopus ID: 85084754357
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
Primary and backup relays pairs are protection schemes for power systems which are set in conjunction to one another to ensure that the protection system operates by limiting an abnormality within its zone of protection. Breakpoints are the starting points of all assumptions and calculations done in protection systems. Previous methods of determining breakpoints favor linear graph theory and expert theory system rather than machine learning. In this study, an adaptive neuro-fuzzy inference (ANFIS) approach is used to determine the breakpoint set for directional overcurrent relays of a given 3-bus network. The two most influential input variables from 15 inputs affecting breakpoint set are determined by Exhaustive Search. The reduced inputs are then used to design the Sugeno type ANFIS. Experimental results show promising results in terms of Root Mean Square Error.
Scopus ID: 85077723193
TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON), (2019), pp. 2408-2412
Conference Paper | Published: October 1, 2019
Abstract
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.
Scopus ID: 85063188183
TENCON 2018 - 2018 IEEE Region 10 Conference, (2018)
Conference Paper | Published: July 2, 2018
Abstract
One of the predominant cause of the diminishing productivity of the Philippines that affects its residents and industry sectors alike is no other than the unresolved traffic. Numerous efforts have been implemented in the country to regulate traffic including road expansion, highway development and application of several traffic schemes. One of the research thrust being studied is the solution to the limitation of traditional traffic light systems. Existing literatures in traffic light system embarked on intelligent transportation system (ITS) that is typically based its operation on real-time traffic density data, however implemented in limited control. This paper discussed an approach in developing traffic signaling system capable of prioritizing congested lanes based on real-time traffic density data and integrated with an automated and manual control ported in a mobile android-based application. The system worked with CCTV cameras positioned at every lane of the intersection for the acquisition of traffic images transmitted to the Raspberry Pi 3 microcontroller for traffic density calculation using image processing. It utilized a traffic monitoring system and traffic lights operation control via a mobile android-based application. The system was tested and yielded an average of 92.83% and 85.77% vehicle detection rate for daytime and nighttime respectively. Moreover, an overall system reliability of 92.82% and 85.77% were obtained during daytime and nighttime testing based on the android GUI, lane prioritization and traffic light response. Future work involved integrating the Internet of Things (IoT) on the traffic light system for a wider scope interconnected implementation.
Scopus ID: 85064126672
2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management (HNICEM), (2018), pp. 1-6
Conference Paper | Published: July 2, 2018
Scopus ID: 85045215426
Journal of Telecommunication, Electronic and Computer Engineering, (2018), pp. 15-20
Pocholo James M. Loresco
& Aaron Don Munsayac AfricaJournal Article | Published: January 1, 2018
Abstract
Analyzing cardiovascular activity of patients using ECG clinical paper printouts requires prior knowledge and practice. This research used spatial-oriented image processing methods for analyzing ECG readings by retrieving only the essential features, and not all ECG data, to assist physicians in diagnosis. Different values such as Atrial (rate/min) and Ventricular (rate/min), QRS interval (sec), QT interval (sec), QTc (sec), and PR interval (sec) were successfully extracted with indication as to whether the values are within the accepted normal values, given the patient’s gender and age. Performance of the system was tested based on accuracy, RMSE and normalized RMSE. The methodology achieved average accuracy as high as 95.424 % while the PR interval feature extraction achieved a relatively low average accuracy of 87.196%.