Papers by Jessica Velasco
International Journal of Advanced Technology and Engineering Exploration
Weather defines the short-term condition of the atmosphere in a certain region, while climate is ... more Weather defines the short-term condition of the atmosphere in a certain region, while climate is the statistical weather condition at a given place during a specified period of time. Climate change describes the change of weather patterns over time within the range of decades to millions of years. According to studies, earth is experiencing climate change due to human activities. This past decade, predicting the weather condition has become a tough problem that humans encounter everywhere around the world. This sometimes results in an inaccurate weather prediction. But in order to predict and lessen the possibilities that risk and harm people's lives, developing marine weather information like buoys is done. Deploying weather buoys in the ocean helps predict weather conditions in a specific location in real-time. It is used to monitor the conditions of the ocean's surface and deep below it. *Author for correspondence The buoys also help to forecast natural phenomena such as earthquakes and storms by using sensors to gather different parameters such as air temperature, air density, relative humidity, wind speed, rainfall, solar radiation, water temperature and salinity profile [1]. In predicting weather conditions, deploying weather buoy can now be deployed together with Wireless Sensor Networks (WSNs). WSNs are used in different areas of technology involving environment monitoring, medicine fields, logistics, etc. New Internet of Things (IoT) innovations, such as Long Range (LoRa), is evolving, allowing for very long wavelengths of power-efficient wireless connectivity [1]. LoRa is a technology is rapidly turning up and is used because of its technical advantages such as the lifetime of battery, long range, security and more [2]. LoRa has a good resistance to interference and provides
arXiv (Cornell University), Oct 30, 2019
This paper presents a study conducted to allow urban farmers to remotely monitor their farm throu... more This paper presents a study conducted to allow urban farmers to remotely monitor their farm through the design and development of an Internet of Things-based (IoT) microfarm prototype which utilized wick system as planting method. The system involves the detection of three environmental parameters namely, light intensity, soil moisture and temperature through the use of respective sensors which were connected to the Arduino microcontroller, the sensor node of the system. Irregularities in the aforementioned parameters were neutralized through the use of parameter regulators such as LED growlight strips, water pump and air cooler. The data collected by these sensors were gathered by the Arduino microcontroller and were sent to the Web database through the IoT gateway which was the Raspberry Pi computer chip. These data were also sent to an Android unit installed with the Microfarm Companion application which was capable of monitoring and controlling the environmental parameters observed in the microfarm. The application allows the user to view the current value of the parameter involved and to choose whether to control the parameter regulators automatically or manually. The microfarm system runs autonomously which reduces the labor required to produce healthy plants and crops. Mustard greens samples were used in testing the system. After a month of monitoring the height of the samples, it was observed that the average height of the samples is about 0.23 cm taller than the standard height. The proponents has also tested the system functionality by evaluating the sensor data log that provides the values gathered by the sensors and the turnon times of the parameter regulators. From these data, it can be observed that whenever the values obtained by the sensors fall outside the threshold range, the parameter regulators turns on, indicating that the system is working properly.
International Journal of Integrated Engineering, Mar 7, 2022
Smart farming is the practice of intelligent agricultural management based on technological data ... more Smart farming is the practice of intelligent agricultural management based on technological data gathered from farm practice for the purpose of increased levels of quality, production and environmental protection [1]. Smart Dairy Farming (SDF) is a concept that meets the growing demand for quality dairy products. This practice includes sensor applications, data analysis, and cloud-based data centers. Farmers increases milk productivity and cattle production, improve the management of livestock, and detect standing-heat activities through the integration of smart farming technology.
2021 IEEE International Conference on Mobile Networks and Wireless Communications (ICMNWC), 2021
This study presents the use of a wireless data acquisition system and the power management system... more This study presents the use of a wireless data acquisition system and the power management system for the development of mooring buoys. The Data Acquisition System is a system for controlling more than one group of sensors and reporting the findings of each sensor through microcontroller. The Power Management System oversees controlling the electrical system of the buoy. The main task is to ensure the electrical system of the buoy is safe and efficient. The proposed study consists of seven sensors gathering different parameters namely: air temperature, air pressure, relative humidity, wind speed, rainfall, solar radiation, water temperature, and salinity profile. For more precise data, three (3) moored buoys are stationed one kilometer from the shore and apart each other to collect information from different areas of the deployment area. It gathers climate characteristics of different areas, which records data accurately. The construction of the device consists of a tower, a polystyrene, and a rope. Its tower has beacon light that serves as an indicator and solar panels as the primary energy source of the buoy. The buoy carries approximately 15 to 20 kilograms of load, and it sustain three (3) solar panels and a 12-V battery. This device has a long battery life and uses idle mode between continuous samples to conserve power. Sleep mode is activated if the information gathered following 15 minutes of samples are consistent, and the power starts again after an additional 15 minutes. The buoys for weather monitoring were deployed under the CGSS-CCP of the Philippine Coast Guard. The results are transmitted to the base station and analyzed by the forecasting system.
2021 IEEE International Conference on Mobile Networks and Wireless Communications (ICMNWC), 2021
Global warming is one of the characteristics of climate change; the impacts of global warming mak... more Global warming is one of the characteristics of climate change; the impacts of global warming make it more difficult to plant in an uncontrolled environment. Traditional farming methods need producers to have high-quality soil and a lot of space and water. On the other hand, the yield does not correspond to or meet the demands of the consumers. As a result, it is important to employ a farming approach that has a reduced cost factor need and to preserve and manage critical factors such as light, water level temperature, and humidity. This article discusses HyLo, a smart vertical hydroponics farming system that eliminates the need for soil. Instead of underground soil, this approach cultivates crops by exposing their roots to a combination of solutions and water in the form of vertical nutrient film technique (NFT) pipes. Vertical farming is advantageous in terms of space and plant layout, and it is also successful when used in conjunction with hydroponics. The evolution of technology in terms of automation and data transmission resulted in the evolution of smart hydroponics, since detection, correction, and monitoring of key parameters are all present. Additionally, it was combined with the LoRaWAN technology, which enables long-range, low-power data transmission over a wide area network (WAN). The number of leaves and circumference of lettuce grown in the suggested hydroponics system were compared to those grown in the traditional system. The results indicated that the suggested hydroponics arrangement produced more lettuce leaves and a larger diameter than the traditional configuration.
2018 IEEE 10th International Conference on Humanoid, Nanotechnology, Information Technology,Communication and Control, Environment and Management (HNICEM), 2018
This paper presents the development of a voice-controlled navigational system that could assist t... more This paper presents the development of a voice-controlled navigational system that could assist the visually impaired people in travelling indoors independently. The system provides audible directions to the users in navigating from a specific location going to the desired destination. This system uses passive radio frequency identification (RFID) tags strategically located along the hallways of the facilities. These tags contain audible directions and they are detected by an RFID reader attached at the tip of a customized cane. The reader is connected to the Raspberry Pi 3 that serves as the brain of the system. It processes the data from the reader, validates the voice input of the user and provides the audio response. The adjustable customized cane measures from 88 cm to 130 cm with an approximate weight of 165 grams, which is lighter than commercially available canes that weigh around 300 grams. The speech recognition feature of the system is evaluated and an accuracy rate of 75.76% is obtained. Its response time in reading the tags is 1.38 seconds for a maximum distance of 1 inch. Overall, the system runs autonomously which helps the visually impaired people in navigating independently inside a specific establishment.
International Journal of Computing and Digital Systems, 2021
The Philippines, surveyed as part of the 23 chosen countries worldwide, is producing 80% of globa... more The Philippines, surveyed as part of the 23 chosen countries worldwide, is producing 80% of global mortality burden due to chronic diseases and 50% full disorder burden because of Noncommunicable diseases (NCDs) throughout the world. To prevent the growth of diseases, and in certain cases to prevent worsening of health conditions, screening is strongly recommended which can identify the symptoms while at their early stages. There are some laboratory tests that a patient can undergo. If it is determined that a disease has emerged, further examinations will also be done to confirm the diagnosis. However, for people in rural areas, it is just additional burden because of the cost and time consumption. The aim of smart health screening system is to ease and enhance the quality of life in rural communities. In this paper, a system was introduced that screens specific health parameters related to cardiovascular system of an individual. The developed mobile application can monitor the patient's health parameters using commercially available medical devices and sensors integrated to the mobile application. The parameters include: Blood Pressure (BP), Heart Rate (HR), Oxygen Saturation (SPO2), Body Mass Index (BMI), Blood Glucose (BG), Cholesterol Level (Chol), and Uric Acid Level. An offline database of the gathered data was established for maintaining data privacy and for the admins to have access in medical records anytime.
SSRN Electronic Journal, 2021
Experimentation has been an essential part of teaching and learning biological concepts. Science ... more Experimentation has been an essential part of teaching and learning biological concepts. Science experiments provide opportunities for students to learn scientific concepts, experience natural phenomena, and explore the world around them. However, this COVID-19 pandemic has disrupted the educational system in the Philippines, particularly science education. School facilities and laboratories are temporarily closed or inaccessible for teachers and students. These events hinder the conventional process of doing experiential learning activities, experiments, and scientific investigations. Because of this major disruption, the International Baccalaureate Organization released a memorandum that encourages teachers and students from IB World Schools to utilize other activities other than laboratory experiments such as online simulations, analysis of secondary data, or doing safe and appropriate experiments at home. In response, the biology students of the International Baccalaureate Diplo...
2017 International Conference on Computer and Applications (ICCA), 2017
Controlling blood glucose is a way to avoid complications of diabetes. Blood glucose monitoring i... more Controlling blood glucose is a way to avoid complications of diabetes. Blood glucose monitoring is a way to test the concentration of glucose in the blood. This study aims to determine the suitability of Artificial Raindrop Algorithm (ARA) and capacitance method in measuring the blood glucose. ARA is a new search algorithm that produces very promising results on the nonlinear function approximation. Blood samples were obtained from 65 different individuals. The sample was placed in a glass slide and the blood glucose is measured using the developed prototype. The results were compared to the laborotary result. The developed device showed 96.92% accuracy.
World Congress on Engineering and Technology; Innovation and its Sustainability 2018, 2019
This paper presents the development of a test paper checker that will recognize a handwritten tex... more This paper presents the development of a test paper checker that will recognize a handwritten text using Intelligent Character Recognition (ICR) for Alphanumeric Characters. An examination can be conducted in two ways—digital and manual—and each way has a different approach in checking. In this study, the main objective is to recognize alphanumeric handwritten characters accurately using intelligent character recognition. OpenCV is used in the Python programming language and Support Vector Machine as a tool in machine learning for ICR. Answer sheet was designed with 120 items for MCQ and problem-solving questions. Item analysis and printing of results are included in the device. Experiments were conducted by giving an actual examination from the 131 participants in Technological University of the Philippines for testing the accuracy of the device. The results obtained from comparing manual and machine checking had an accuracy of 93.0769%. Thus, the proposed method is applicable for ...
Local Government Units (LGUs) in the Philippines are mandated to conduct land classification mapp... more Local Government Units (LGUs) in the Philippines are mandated to conduct land classification mapping of their areas which brings up an issue about a time-consuming and expensive data gathering. This paper aims at achieving a land use classification system that correlates with the traditional way of mapping of LGUs. This study introduces the development of a web application that can classify land use (Agricultural, Commercial, Residential, and Industrial) in different areas of Greater Manila. The system involves the utilization of freely accessible satellite images from Google Maps and benchmark dataset from the EuroSAT dataset for the categorization of the areas through deep learning using Convolutional Neural Network (CNN). Evaluation results show that the system in a web application could help with the mapping of the Greater Manila area with the web application being simple yet informative and efficient.
Microelectronics Journal, 2021
AGRIVITA Journal of Agricultural Science, 2021
Journal of Agricultural Science www.agrivita.ub.ac.id (2014). This Microcontroller was programmed... more Journal of Agricultural Science www.agrivita.ub.ac.id (2014). This Microcontroller was programmed in an accessible Integrated Development Environment (IDE) to outline a cost-effective "open hardware" platform. The designed platform will be used to measure parameters including soil water content at different levels and the temperature of the soil and air. Meanwhile, Chung, Caya, & Chen (2013) discussed the "open hardware" platform. This platform was designed with sensors that are being observed with Zigbee wireless network. The measurements of critical parameters in a ARTICLE INFO
SSRN Electronic Journal, 2019
A user authentication system for unlocking and security of desktop computer using bone conduction... more A user authentication system for unlocking and security of desktop computer using bone conduction through skull is presented in this study. It is an electronic device that outputs an identity based on the characteristic frequency response gathered. White noise will be used as an input provided that the external noise is filtered successfully using a laryngophone. It will enter the skull through the bone conduction speakers and the microphone will pick up the recorded frequency characteristic response. This response is then fed to the computer and will be processed by the Sound-to-Feature algorithm for its feature extraction. This noise will be classified by the Artificial Neural Network (ANN) algorithm so that it will identify and authenticate the user. For testing and validation, thirty persons, who were used as subjects, wore laryngophones which are placed at the back of their heads for gathering of audio samples in WAV format. Each person has thirty samples with a total of 900 samples. The samples were all trained in a database wherein the proponents can set who among the thirty people can unlock the desktop computer. To be able to test the significant difference and similarity between the WAV files of each person, the Explore and Score method of the Sound Analysis Pro (SAP) 2011 was used. A round-robin test which is equal to 435 tests was initiated to show that each subject has a unique wav file. From the 435 comparisons, all were proven unique and failed the similarity test achieving an accurate way of identifying the user.<br>
International Journal of Emerging Trends in Engineering Research, 2020
This paper has experimented different architectures of transfer learning models (TLM) for canine ... more This paper has experimented different architectures of transfer learning models (TLM) for canine semen evaluation and improving the performance of Deep Learning algorithms. There are 332 total datasets used for training and testing of different convolutional network models. These models are: MobileNetV1, InceptionV2, ResNet50, ResNet101 and Inception_ResNetV2. The canine sperm classification is successfully executed. In the evaluation of these models, a comparison of the manual method to the systems accuracy and error was made. Through these evaluations, the highest accuracy of 87% is obtained by Inception_ResNetV2 and the lowest accuracy of 40% is the MobileNetv1.
International Journal of Advanced Computer Science and Applications, 2020
Thorough and precise estrus detection plays a crucial role in the fertility of dairy cows. Farmer... more Thorough and precise estrus detection plays a crucial role in the fertility of dairy cows. Farmers commonly used direct visual monitoring in recognizing estrus signs which demands time and effort and causes misinterpretations. The primary sign of estrus is the standing heat, where the dairy cows stand to be mounted by other cows for a few seconds. Through the years, researchers developed various detection methods, yet most of these methods involve contact and invasive approaches that affect the estrus behaviors of cows. So, the proponents developed a non-invasive and non-contact estrus detection system using image processing to detect standing heat behaviors. Through the TensorFlow Object Detection API, the proponents trained two custom neural network models capable of visualizing bounding boxes of the predicted cow objects on image frames. The proponents also developed an object overlapping algorithm that utilizes the bounding box corners to detect estrus activities. Based on the conducted tests, an estrus event occurs when the centroids of the detected objects measure a distance of less than 360px and have two interior angles with another fixed point of less than 25° and greater than 65° for Y and X axes, respectively. If the conditions are met, the program will save the image frame and will declare an estrus activity. Otherwise, it will restart its estrus detection and counting. The system observed 17 cows, a carabao, and a bull through the cameras installed atop of a cowshed, and detects the estrus events with an efficiency of 50%.
International Journal of Advanced Computer Science and Applications, 2020
Cardiovascular diseases cover a large quantity of worldwide disease load, setting it to top leadi... more Cardiovascular diseases cover a large quantity of worldwide disease load, setting it to top leading cause of death. In the Philippines, given the rapid economic advancement and urbanization, the most vulnerable sector has not been impacted by this development. Data from the Philippine Statistical Authority (PSA) in 2016 revealed that of the country's total recorded deaths, six out of ten were medically unattended and of which the largest portion are from the rural population. Consequently, medical analysis is needed to perform effectively and precisely however, most developing countries have limited resources and lack medical expert for specialized field such as cardiologists. The proponents essentially seeks to address the issues Philippine health sector specifically in rural and remote populace by executing efficient and low-cost health screening and diseases prediction system using commercially available medical devices and machine learning algorithms for the prediction of three of the most heart diseases (Hypertension, Heart Attack, Diabetes). The system is composed of CAREdio mobile app, prototype hardware consists of different health sensors and devices, and a machine learning model that is applied to determine the user's individual probability of having a specific heart disease. The machine learning models used were trained using the data gathered from Rosario Reyes Health Center and Ospital ng Sampaloc (Sampaloc Hospital), both located in Manila City, Philippines. CAREdio achieves accuracy values over 0.80 for all diseases. The system can diagnose multiple cardiovascular diseases in a single app that will benefit people rural communities.
Indonesian Journal of Electrical Engineering and Computer Science, 2020
This study presents a system that combines a conventional refrigerator, microcontrollers and a sm... more This study presents a system that combines a conventional refrigerator, microcontrollers and a smart phone to create an inventory monitoring that can monitor the stocks inside the refrigerator wirelessly by accessing an Android application. The developed refrigerator uses a sensor network system that is installed in a respective compartment inside the refrigerator. Each sensor will transmit data to the microcontrollers, such as Arduino Yun and Arduino Uno, which are interconnected by the I2C communications. All data and images will be processed to provide the user an Internet of Things application through the cloud-based website Temboo. Temboo will have access to send data to the Dropbox. A smartphone is connected to the Dropbox where all the data and images are stored. The user can monitor the stocks or contents of the refrigerator wirelessly using an Android Application.
International Journal of Advanced Trends in Computer Science and Engineering, 2019
Electronic systems tend to simplify the tedious traditional scheme and basically focuses on the p... more Electronic systems tend to simplify the tedious traditional scheme and basically focuses on the platform design and process organization. The integrity of the output of an automated system is not left behind but the possibility of internal manipulation is still high. This paper presents the current issues in company procurements and the solution in the form of blockchain technology. Several individuals and professionals were asked to evaluate a blockchain-based procurement system in comparison to the current electronic (e-procurement) system. A blockchain-based system has the capability to hold transactional data with complete decentralization and eliminate the growing number of fraud cases in companies and organizations. This paper mainly focuses on the effectiveness of a blockchain-based system in company procurements.
International Journal of Advanced Trends in Computer Science and Engineering, 2019
The MobileNet model was used by applying transfer learning on the 7 skin diseases to create a ski... more The MobileNet model was used by applying transfer learning on the 7 skin diseases to create a skin disease classification system on Android application. The proponents gathered a total of 3,406 images and it is considered as imbalanced dataset because of the unequal number of images on its classes. Using different sampling method and preprocessing of input data was explored to further improved the accuracy of the MobileNet. Using under-sampling method and the default preprocessing of input data achieved an 84.28% accuracy. While, using imbalanced dataset and default preprocessing of input data achieved a 93.6% accuracy. Then, researchers explored oversampling the dataset and the model attained a 91.8% accuracy. Lastly, by using oversampling technique and data augmentation on preprocessing the input data provide a 94.4% accuracy and this model was deployed on the developed Android application.
Uploads
Papers by Jessica Velasco