Alvin Sarraga Alon | Batangas State University (original) (raw)
Papers by Alvin Sarraga Alon
2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2021
Nowadays, road accidents have become a major concern. The drowsiness of drivers owing to overfati... more Nowadays, road accidents have become a major concern. The drowsiness of drivers owing to overfatigue or tiredness, driving while intoxicated, or driving too quickly is some of the primary causes of this. Drowsy driving contributes to or increases the number of traffic accidents each year. The study presented a technique for detecting driver drowsiness in response to this issue. The sleep states of the drivers in the driving environment were detected using a deep learning approach. To assess if the eyes of particular constant face images of drivers are closed, a convolutional neural network (CNN) model has been developed. The suggested model has a wide range of possible applications, including human-computer interface design, facial expression detection, and determining driver tiredness and drowsiness. The YOLOv3 algorithm, as well as additional tools like Pascal VOC and LabelImg, were used to build this approach, which collects and trains a driver dataset that feels drowsy. The study's total detection accuracy was 100%, with detection per frame accuracy ranging from 49% to 89%.
2020 IEEE 7th International Conference on Engineering Technologies and Applied Sciences (ICETAS), 2020
The ocean and any form of bodies of water must be protected and secure from any intruders and to ... more The ocean and any form of bodies of water must be protected and secure from any intruders and to monitor our ocean, technology must be used and integrated for more efficient monitoring. Automatic boat detection plays an important role in maritime surveillance. However, the maritime environment represents lots of challenges such as the wave of water, boat movements, and weather condition. This paper presents a method for detecting moving boats from a sequence of images using a deep learning approach. In this study, the researchers proposed a detection system for the boats in the ocean using optical aerial images. The researchers conducted testing and the results were favorable. Upon testing the researchers obtained a 90% accuracy of detection of the ship in the ocean using the single images, video feeds, and live feeds. The experiments show promising results.
KSII Transactions on Internet and Information Systems, 2021
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Gamefowl owners and cockfighters have a variety of ways to tell whether a gamefowl is battle-read... more Gamefowl owners and cockfighters have a variety of ways to tell whether a gamefowl is battle-ready or not. One of these is through the condition of the gamefowl droppings. A dropping that is not too wet and not too dry indicates that the gamefowl is at its peak condition. This paper presents an image processing based gamefowl dropping's color composition system that aims to recognize a dropping from a peaked gamefowl. This system will make use of a recognition algorithm and a color composition algorithm (using RGB) to solve the problems encountered using the manual method of dropping monitoring. Different samples were used to verify the system's accuracy and based on the analysis, the system was able to get a success rate of 100%. This shows that the system is fully functional and effective in providing a solution to solve the common problem of gamefowl owners and cockfighters.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
This study deals with the construction of a device that uses Arduino to assist in the classificat... more This study deals with the construction of a device that uses Arduino to assist in the classification of tomatoes for catsup production. The method intends to identify the tomato that is ideally adapted for Ketchup production, for improved product consistency. Using Arduino, the device can sense tomato resistance and check whether the frequency resistance for Catsup tomato is below the threshold. The device should be able to determine from this method whether or not its better suited for Catsup production.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
A smoke detector is an instrument that detects smoke usually as a fire warning. The devices avail... more A smoke detector is an instrument that detects smoke usually as a fire warning. The devices available are placed in the ceiling and they take too long to respond to smoke. These smoke alarms are helpful when the smoke is big enough to reach the ceiling and alarm that there is a fire in the area. It takes a big fire and a lot of smoke before it can be detected and before the alarm goes on. In this study, the detection of smoke will be done by using an object-detection algorithm. It detects smoke early even if there is only a small amount to be detected. These detected smokes are then analyzed and will then inform the user about the detected smoke. This study can help a lot in fire prevention because of the detection of smoke inside the house and can prevent fire as early as the smoke has been recognized by the camera. The system produced an overall 89% testing accuracy.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
This paper aims in developing a piece ranking detection of game of the generals board game that h... more This paper aims in developing a piece ranking detection of game of the generals board game that has low power consumption. Watch dog timer was used to build a low power board game that was applied in game of the generals. Experiments were performed to calculate the power savings, resulted in about 50 per cent power savings were achieved. The proponents concluded that, on the basis of identification and fair decision and operational standards, the system configuration consisted of introducing sleep modes to reduce the power usage of the proposed system. The proponent conducted a survey sample consists of a group of 30 people with varying level of strategies in playing the Game of the Generals whose age from 18 to 40 years old. Based on the statistical treatment applied in the datasets collected, the average time to spent to complete the game is 24.97 with a frequency of 28. And with a standard deviation (8.98). This resulted to a negative skew. For the number of times that the device turns into idle time, the average is 8.2 with a frequency of 11 and the 50th percentile of 10. The standard deviation of (5.28) from the normal of 8.2. The proponents concluded that the greater the number of times that the device turn into idle time or sleep mode the higher the power savings.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
A smoke detector is an instrument that detects smoke usually as a fire warning. The devices avail... more A smoke detector is an instrument that detects smoke usually as a fire warning. The devices available are placed in the ceiling and they take too long to respond to smoke. These smoke alarms are helpful when the smoke is big enough to reach the ceiling and alarm that there is a fire in the area. It takes a big fire and a lot of smoke before it can be detected and before the alarm goes on. In this study, the detection of smoke will be done by using an object-detection algorithm. It detects smoke early even if there is only a small amount to be detected. These detected smokes are then analyzed and will then inform the user about the detected smoke. This study can help a lot in fire prevention because of the detection of smoke inside the house and can prevent fire as early as the smoke has been recognized by the camera. The system produced an overall 89% testing accuracy.
International Journal of Emerging Trends in Engineering Research, 2020
Fire detection systems are implemented and intended to detect fires early so it can help the peop... more Fire detection systems are implemented and intended to detect fires early so it can help the people on a building or house for safe evacuation and immediately notify the firemen. After the firemen put out the fire, that will be the time that they can conduct an investigation in determining the source or cause of fire which they often experience some difficulties. Therefore, this study proposed an algorithm for identification of combustible and fluid fire with hybrid feature extraction techniques. The algorithm use RGB model, applying HSV conversion and Canny edge detection for the growth of fire. Then combine the results of HSV and Canny edge detection and used image segmentation of color space for combustible and fluid fire. The algorithm got an accuracy of 94% for 50 fire images demonstrated usefulness and effectiveness. .
International Journal of Emerging Trends in Engineering Research, 2020
Car Accident is one of the causes of death in every country. The problem is that the way of assis... more Car Accident is one of the causes of death in every country. The problem is that the way of assistance for the victim is un-established in the Philippines. This paper develops an embedded system that will help detect a car accident and afterward send a notification to the nearest Police Station and Emergency Response Team for immediate assistance. This system will also send an SMS to the Family of the victim. It was utilizing the Accelerometer, Piezoelectric Sensor, and GPS module to track the location of a car that encounters an accident. Also, with the use of the Google Map API, a notification message will be sent automatically to the nearest Police Station and Emergency Response Team web server so they can take action immediately. Other works that are somewhat similar to this paper prove the effectivity and good outcome it can give to society. Therefore, this system contributes to saving lives through immediate action from the nearest Police Station and Emergency Response Team that this study aims to do.
International Journal of Emerging Trends in Engineering Research, 2020
Lettuce provides vitamin C, calcium, potassium, and folate. Within iceberg lettuce, the nutrients... more Lettuce provides vitamin C, calcium, potassium, and folate. Within iceberg lettuce, the nutrients will help you fulfill the normal daily requirements for many vitamins and minerals. It is most commonly cultivated as a vegetable leaf, but sometimes for its stem and seeds. Lettuce is most widely used for salads, but it can also be used in other foods, such as soups, sandwiches, and wraps; it can be grilled too. Many farmers produce lettuces on the farm. Producing lettuces isn’t that an easy task it requires manpower and hard work. People who buy lettuce don’t have the skill to determine if the lettuce is healthy or have a disease, they just based only on the color of the lettuce. The study developed a system project that focuses on lettuce health recognition. The system determines if the lettuce is healthy or disease. It is based on machine vision using deep learning, it is connected to a microcontroller raspberry pi 4b. Lettuce health recognition has been done with an overall testing accuracy of 97.59%.
International Journal of Emerging Trends in Engineering Research, 2020
The study developed a cost-effective framework for unauthorized parking detection using a machine... more The study developed a cost-effective framework for unauthorized parking detection using a machine-vision based deep learning method. The system was introduced on a Raspberry Pi 4b using the MobileNet SSD algorithm to detect vehicles illegally parked based on the live feed received from a Pi camera. The system was introduced to monitor unauthorized parking on a specific barangay simulated-roadside-parking lot. Results of the assessment indicate that the study was capable of identifying illegally parked vehicles with an overall performance rate of 96.16% and 98.93% respectively for legally and illegally parked vehicles, with a combined test resulting in 97.56%. The study showed that the detection was robust to changes in light intensity and the presence of shadow effects in varying environmental conditions, due to the deep learning strength.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Many kinds of research focused on the flood detection and monitoring, flood management, flood ris... more Many kinds of research focused on the flood detection and monitoring, flood management, flood risk management and flood forecasting in urban areas, wherein a large number of populations lies chaos in mobility is high. Owing to natural disasters, flooding in these regions can lead to an increase in mortality rates. This project is primarily focused on the detection of a flood by installing a flood detector device with a camera beside the bridge column. The camera is facing the three lines with different colors. If one of the colors was tempered by the river water, the device will send an alarm to the community that the water level in the river is high. This aims to alert the community and the authorities to be aware and be ready for the approaching flood. Flood-Level Detection and Alert System proved 87.1%, 73.6%, and 95.69% testing accuracy of Green, Blue, and Red respectively. Overall, the accuracy of the whole system produced 85.46%.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
The adverse effect of sleepy driving is a big concern and is closely related to numerous near-mis... more The adverse effect of sleepy driving is a big concern and is closely related to numerous near-misses and driving accidents. Detection of drowsiness using wearable sensors leads to attempts to identify driver sleepiness by incorporating emerging technology for real-time sleepiness detection. This paper presents a wearable pre-frontal single-channel Electroencephalogram (EEG) tool that will determine the state of the mind of the driver automatically, drowsy which focus on the transition from awake to asleep and non-drowsy. A driving experimental setup was designed and conducted using 10 participant participants. The system is integrated with an alarm system which will activate when the brain activity fluctuates that utilized Arduino module. Collected data included the continuous driving time prior to detection of drowsiness. Numerical labels 1 and 0 are applied to the performance of the system. A value of 1 is given to the point at which the participant is already in the drowsy state and 0 to the attention state (non-drowsy). The results of all the trails made were compared to the output of the expected and actual results. The error explains whether the system was able to provide a correct output or not. Generally, the accuracy gathered 93.33%.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Soil moisture volume is the greatest attribute of soil. Irrigated farms rely on controlling the t... more Soil moisture volume is the greatest attribute of soil. Irrigated farms rely on controlling the two fundamental raw materials; water and soil. Putting excessive water enlarges the pumping costs, decreasing the water effects to the soil, and cause contamination or pollutant. The study aims to develop an irrigation water management system that controls the volume and frequency of irrigation water applied to the soil and to use low-cost sensor device that measures the soil moisture level accurately like the high price sensor in the market. The FC-28 soil moisture sensor was also validated conducting (60) sixty trials with different soil and the readings are the same for soil moisture measurement devices in the market. Based on the testing, the whole system resulted in a 100% success rate in system and functionality testing. This study proves that the automatic irrigation system controlled by soil moisture sensor
is efficiently and accurately.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Humidity is blamed for harmful things of all kinds. I this study it aims at creating an automatic... more Humidity is blamed for harmful things of all kinds. I this study it aims at creating an automatic controller for humidifier and dehumidifier. It helps to regulate and monitor the level of humidity to minimize the room humidity and to make the user comfortable. The study uses a humidity sensor to measure the room’s humidity and provide the device with two choices to automatically humidify or dehumidify the air. This helps minimize odors that can surround mold and mildew to rid your house of the “musty” or “rotting” smell, it also decrease dust and the risk of forming molds on your clothing, furniture and other linens, and eventually reduces inflammation of your skin and respiratory system, making it easier to breathe and feel comfortable at home. Controller used in this study is Arduino Uno. An input supply to the Arduino Uno is then connected to its pin by a humidity sensor, and the LCD will display the humidity value. A relay that was used to power humidifier and dehumidifier operations. The study was done after the testing procedure shows the result of different longer-term data when the dehumidifier and humidifier turns on and turn off if it’s become normal, depending on the size of room and weather temperature.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
In this study, a Takagi Sugeno Fuzzy Expert system were developed to monitor the temperature, moi... more In this study, a Takagi Sugeno Fuzzy Expert system were developed to monitor the temperature, moisture and nutrient level to enhanced the decomposition of the rice straw. The input parameters of the Fuzzy Expert model that were used such as temperature, nutrient content, availability of oxygen and free moisture. In this study the Takagi Sugeno approach fuzzy expert system for easy monitoring of the temperature, nutrient content, oxygen, moisture and particle size of rice straw to enhanced decomposition were used. Upon conducting the experiments the fuzzy expert system improved the decomposition process as a result of testing where two experiments conducted one with Fuzzy expert system and the other one is the traditional decomposition process, the first experiment obtained 14 days to decompose the rice straw compared to the latter it took 24 days to decomposed the rice straw. It only shows that Fuzzy Inference expert system can be a great tool to monitor the decomposition process.
International Journal of Emerging Trends in Engineering Research, 2020
Fire detection systems are implemented and intended to detect fires early so it can help the peop... more Fire detection systems are implemented and intended to detect fires early so it can help the people on a building or house for safe evacuation and immediately notify the firemen. After the firemen put out the fire, that will be the time that they can conduct an investigation in determining the source
or cause of fire which they often experience some difficulties.
Therefore, this study proposed an algorithm for identification of combustible and fluid fire with hybrid feature extraction techniques. The algorithm use RGB model, applying HSV conversion and Canny edge detection for the growth of fire. Then combine the results of HSV and Canny edge detection and used image segmentation of color space for combustible and fluid fire. The algorithm got an accuracy of 94% for 50 fire images demonstrated usefulness and effectiveness.
International Journal of Emerging Trends in Engineering Research, 2020
In the constant advancement of technology, protection of one’s property becomes a major concern f... more In the constant advancement of technology, protection of one’s property becomes a major concern for each individual. To secure one’s property the protection such as locks and keys mechanism were used but this mechanism can be easily replicated. This study aims to developed a device and a security system that replaced the conventional lock and keys mechanism to secure one’s property. This device also established a strong security based on the secret knock pattern security system. This security system consists of Arduino Mega, Piezo Sensor, and uses a Secret Knock that is known only to the owner. The researchers conducted hardware and system functionality. Thirty (30) trials were made in checking the accuracy of changing knock patterns where they obtained a 100% accuracy. Thirty-one (31) trials were made to check the accuracy of detecting incorrect patter. The experiments conducted obtained a 100% accuracy in detecting incorrect pattern.
International Journal of Emerging Trends in Engineering Research, 2020
Copra in the Philippines is one of the by-products from coconut which contributes as one of the m... more Copra in the Philippines is one of the by-products from coconut which contributes as one of the major sources of income of Filipino farmers. During the process of selling the Copra in the market, farmers usually lose in the price competition from the buyers due to the unidentified quality of their Copra. Copra which commonly either overcooked or undercooked are paid as half of the price of the perfectly cooked. This happened due to the lack of information of the farmers in assessing the quality of the processed copra meat. In this study, a Convolutional Neural Network had been evaluated in terms of its accuracy by varying the numbers of convolutional layer filters, the size of filters, and its activation function. The identified best parameters were used to develop a CNN algorithm that classifies the quality of Copra. The algorithm was implemented using Tensorflow in a python environment. A series of tests were applied to the final CNN model. Random images of Copra with identified quality were used as testing data. Out of 120 sample images, the final CNN model performs an overall 86% accuracy. The model was also implemented into a simple android application for validation. The confusion matrix and f-score were used to evaluate the performance of the system.
2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2021
Nowadays, road accidents have become a major concern. The drowsiness of drivers owing to overfati... more Nowadays, road accidents have become a major concern. The drowsiness of drivers owing to overfatigue or tiredness, driving while intoxicated, or driving too quickly is some of the primary causes of this. Drowsy driving contributes to or increases the number of traffic accidents each year. The study presented a technique for detecting driver drowsiness in response to this issue. The sleep states of the drivers in the driving environment were detected using a deep learning approach. To assess if the eyes of particular constant face images of drivers are closed, a convolutional neural network (CNN) model has been developed. The suggested model has a wide range of possible applications, including human-computer interface design, facial expression detection, and determining driver tiredness and drowsiness. The YOLOv3 algorithm, as well as additional tools like Pascal VOC and LabelImg, were used to build this approach, which collects and trains a driver dataset that feels drowsy. The study's total detection accuracy was 100%, with detection per frame accuracy ranging from 49% to 89%.
2020 IEEE 7th International Conference on Engineering Technologies and Applied Sciences (ICETAS), 2020
The ocean and any form of bodies of water must be protected and secure from any intruders and to ... more The ocean and any form of bodies of water must be protected and secure from any intruders and to monitor our ocean, technology must be used and integrated for more efficient monitoring. Automatic boat detection plays an important role in maritime surveillance. However, the maritime environment represents lots of challenges such as the wave of water, boat movements, and weather condition. This paper presents a method for detecting moving boats from a sequence of images using a deep learning approach. In this study, the researchers proposed a detection system for the boats in the ocean using optical aerial images. The researchers conducted testing and the results were favorable. Upon testing the researchers obtained a 90% accuracy of detection of the ship in the ocean using the single images, video feeds, and live feeds. The experiments show promising results.
KSII Transactions on Internet and Information Systems, 2021
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Gamefowl owners and cockfighters have a variety of ways to tell whether a gamefowl is battle-read... more Gamefowl owners and cockfighters have a variety of ways to tell whether a gamefowl is battle-ready or not. One of these is through the condition of the gamefowl droppings. A dropping that is not too wet and not too dry indicates that the gamefowl is at its peak condition. This paper presents an image processing based gamefowl dropping's color composition system that aims to recognize a dropping from a peaked gamefowl. This system will make use of a recognition algorithm and a color composition algorithm (using RGB) to solve the problems encountered using the manual method of dropping monitoring. Different samples were used to verify the system's accuracy and based on the analysis, the system was able to get a success rate of 100%. This shows that the system is fully functional and effective in providing a solution to solve the common problem of gamefowl owners and cockfighters.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
This study deals with the construction of a device that uses Arduino to assist in the classificat... more This study deals with the construction of a device that uses Arduino to assist in the classification of tomatoes for catsup production. The method intends to identify the tomato that is ideally adapted for Ketchup production, for improved product consistency. Using Arduino, the device can sense tomato resistance and check whether the frequency resistance for Catsup tomato is below the threshold. The device should be able to determine from this method whether or not its better suited for Catsup production.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
A smoke detector is an instrument that detects smoke usually as a fire warning. The devices avail... more A smoke detector is an instrument that detects smoke usually as a fire warning. The devices available are placed in the ceiling and they take too long to respond to smoke. These smoke alarms are helpful when the smoke is big enough to reach the ceiling and alarm that there is a fire in the area. It takes a big fire and a lot of smoke before it can be detected and before the alarm goes on. In this study, the detection of smoke will be done by using an object-detection algorithm. It detects smoke early even if there is only a small amount to be detected. These detected smokes are then analyzed and will then inform the user about the detected smoke. This study can help a lot in fire prevention because of the detection of smoke inside the house and can prevent fire as early as the smoke has been recognized by the camera. The system produced an overall 89% testing accuracy.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
This paper aims in developing a piece ranking detection of game of the generals board game that h... more This paper aims in developing a piece ranking detection of game of the generals board game that has low power consumption. Watch dog timer was used to build a low power board game that was applied in game of the generals. Experiments were performed to calculate the power savings, resulted in about 50 per cent power savings were achieved. The proponents concluded that, on the basis of identification and fair decision and operational standards, the system configuration consisted of introducing sleep modes to reduce the power usage of the proposed system. The proponent conducted a survey sample consists of a group of 30 people with varying level of strategies in playing the Game of the Generals whose age from 18 to 40 years old. Based on the statistical treatment applied in the datasets collected, the average time to spent to complete the game is 24.97 with a frequency of 28. And with a standard deviation (8.98). This resulted to a negative skew. For the number of times that the device turns into idle time, the average is 8.2 with a frequency of 11 and the 50th percentile of 10. The standard deviation of (5.28) from the normal of 8.2. The proponents concluded that the greater the number of times that the device turn into idle time or sleep mode the higher the power savings.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
A smoke detector is an instrument that detects smoke usually as a fire warning. The devices avail... more A smoke detector is an instrument that detects smoke usually as a fire warning. The devices available are placed in the ceiling and they take too long to respond to smoke. These smoke alarms are helpful when the smoke is big enough to reach the ceiling and alarm that there is a fire in the area. It takes a big fire and a lot of smoke before it can be detected and before the alarm goes on. In this study, the detection of smoke will be done by using an object-detection algorithm. It detects smoke early even if there is only a small amount to be detected. These detected smokes are then analyzed and will then inform the user about the detected smoke. This study can help a lot in fire prevention because of the detection of smoke inside the house and can prevent fire as early as the smoke has been recognized by the camera. The system produced an overall 89% testing accuracy.
International Journal of Emerging Trends in Engineering Research, 2020
Fire detection systems are implemented and intended to detect fires early so it can help the peop... more Fire detection systems are implemented and intended to detect fires early so it can help the people on a building or house for safe evacuation and immediately notify the firemen. After the firemen put out the fire, that will be the time that they can conduct an investigation in determining the source or cause of fire which they often experience some difficulties. Therefore, this study proposed an algorithm for identification of combustible and fluid fire with hybrid feature extraction techniques. The algorithm use RGB model, applying HSV conversion and Canny edge detection for the growth of fire. Then combine the results of HSV and Canny edge detection and used image segmentation of color space for combustible and fluid fire. The algorithm got an accuracy of 94% for 50 fire images demonstrated usefulness and effectiveness. .
International Journal of Emerging Trends in Engineering Research, 2020
Car Accident is one of the causes of death in every country. The problem is that the way of assis... more Car Accident is one of the causes of death in every country. The problem is that the way of assistance for the victim is un-established in the Philippines. This paper develops an embedded system that will help detect a car accident and afterward send a notification to the nearest Police Station and Emergency Response Team for immediate assistance. This system will also send an SMS to the Family of the victim. It was utilizing the Accelerometer, Piezoelectric Sensor, and GPS module to track the location of a car that encounters an accident. Also, with the use of the Google Map API, a notification message will be sent automatically to the nearest Police Station and Emergency Response Team web server so they can take action immediately. Other works that are somewhat similar to this paper prove the effectivity and good outcome it can give to society. Therefore, this system contributes to saving lives through immediate action from the nearest Police Station and Emergency Response Team that this study aims to do.
International Journal of Emerging Trends in Engineering Research, 2020
Lettuce provides vitamin C, calcium, potassium, and folate. Within iceberg lettuce, the nutrients... more Lettuce provides vitamin C, calcium, potassium, and folate. Within iceberg lettuce, the nutrients will help you fulfill the normal daily requirements for many vitamins and minerals. It is most commonly cultivated as a vegetable leaf, but sometimes for its stem and seeds. Lettuce is most widely used for salads, but it can also be used in other foods, such as soups, sandwiches, and wraps; it can be grilled too. Many farmers produce lettuces on the farm. Producing lettuces isn’t that an easy task it requires manpower and hard work. People who buy lettuce don’t have the skill to determine if the lettuce is healthy or have a disease, they just based only on the color of the lettuce. The study developed a system project that focuses on lettuce health recognition. The system determines if the lettuce is healthy or disease. It is based on machine vision using deep learning, it is connected to a microcontroller raspberry pi 4b. Lettuce health recognition has been done with an overall testing accuracy of 97.59%.
International Journal of Emerging Trends in Engineering Research, 2020
The study developed a cost-effective framework for unauthorized parking detection using a machine... more The study developed a cost-effective framework for unauthorized parking detection using a machine-vision based deep learning method. The system was introduced on a Raspberry Pi 4b using the MobileNet SSD algorithm to detect vehicles illegally parked based on the live feed received from a Pi camera. The system was introduced to monitor unauthorized parking on a specific barangay simulated-roadside-parking lot. Results of the assessment indicate that the study was capable of identifying illegally parked vehicles with an overall performance rate of 96.16% and 98.93% respectively for legally and illegally parked vehicles, with a combined test resulting in 97.56%. The study showed that the detection was robust to changes in light intensity and the presence of shadow effects in varying environmental conditions, due to the deep learning strength.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Many kinds of research focused on the flood detection and monitoring, flood management, flood ris... more Many kinds of research focused on the flood detection and monitoring, flood management, flood risk management and flood forecasting in urban areas, wherein a large number of populations lies chaos in mobility is high. Owing to natural disasters, flooding in these regions can lead to an increase in mortality rates. This project is primarily focused on the detection of a flood by installing a flood detector device with a camera beside the bridge column. The camera is facing the three lines with different colors. If one of the colors was tempered by the river water, the device will send an alarm to the community that the water level in the river is high. This aims to alert the community and the authorities to be aware and be ready for the approaching flood. Flood-Level Detection and Alert System proved 87.1%, 73.6%, and 95.69% testing accuracy of Green, Blue, and Red respectively. Overall, the accuracy of the whole system produced 85.46%.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
The adverse effect of sleepy driving is a big concern and is closely related to numerous near-mis... more The adverse effect of sleepy driving is a big concern and is closely related to numerous near-misses and driving accidents. Detection of drowsiness using wearable sensors leads to attempts to identify driver sleepiness by incorporating emerging technology for real-time sleepiness detection. This paper presents a wearable pre-frontal single-channel Electroencephalogram (EEG) tool that will determine the state of the mind of the driver automatically, drowsy which focus on the transition from awake to asleep and non-drowsy. A driving experimental setup was designed and conducted using 10 participant participants. The system is integrated with an alarm system which will activate when the brain activity fluctuates that utilized Arduino module. Collected data included the continuous driving time prior to detection of drowsiness. Numerical labels 1 and 0 are applied to the performance of the system. A value of 1 is given to the point at which the participant is already in the drowsy state and 0 to the attention state (non-drowsy). The results of all the trails made were compared to the output of the expected and actual results. The error explains whether the system was able to provide a correct output or not. Generally, the accuracy gathered 93.33%.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Soil moisture volume is the greatest attribute of soil. Irrigated farms rely on controlling the t... more Soil moisture volume is the greatest attribute of soil. Irrigated farms rely on controlling the two fundamental raw materials; water and soil. Putting excessive water enlarges the pumping costs, decreasing the water effects to the soil, and cause contamination or pollutant. The study aims to develop an irrigation water management system that controls the volume and frequency of irrigation water applied to the soil and to use low-cost sensor device that measures the soil moisture level accurately like the high price sensor in the market. The FC-28 soil moisture sensor was also validated conducting (60) sixty trials with different soil and the readings are the same for soil moisture measurement devices in the market. Based on the testing, the whole system resulted in a 100% success rate in system and functionality testing. This study proves that the automatic irrigation system controlled by soil moisture sensor
is efficiently and accurately.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
Humidity is blamed for harmful things of all kinds. I this study it aims at creating an automatic... more Humidity is blamed for harmful things of all kinds. I this study it aims at creating an automatic controller for humidifier and dehumidifier. It helps to regulate and monitor the level of humidity to minimize the room humidity and to make the user comfortable. The study uses a humidity sensor to measure the room’s humidity and provide the device with two choices to automatically humidify or dehumidify the air. This helps minimize odors that can surround mold and mildew to rid your house of the “musty” or “rotting” smell, it also decrease dust and the risk of forming molds on your clothing, furniture and other linens, and eventually reduces inflammation of your skin and respiratory system, making it easier to breathe and feel comfortable at home. Controller used in this study is Arduino Uno. An input supply to the Arduino Uno is then connected to its pin by a humidity sensor, and the LCD will display the humidity value. A relay that was used to power humidifier and dehumidifier operations. The study was done after the testing procedure shows the result of different longer-term data when the dehumidifier and humidifier turns on and turn off if it’s become normal, depending on the size of room and weather temperature.
International Journal of Advanced Trends in Computer Science and Engineering, 2020
In this study, a Takagi Sugeno Fuzzy Expert system were developed to monitor the temperature, moi... more In this study, a Takagi Sugeno Fuzzy Expert system were developed to monitor the temperature, moisture and nutrient level to enhanced the decomposition of the rice straw. The input parameters of the Fuzzy Expert model that were used such as temperature, nutrient content, availability of oxygen and free moisture. In this study the Takagi Sugeno approach fuzzy expert system for easy monitoring of the temperature, nutrient content, oxygen, moisture and particle size of rice straw to enhanced decomposition were used. Upon conducting the experiments the fuzzy expert system improved the decomposition process as a result of testing where two experiments conducted one with Fuzzy expert system and the other one is the traditional decomposition process, the first experiment obtained 14 days to decompose the rice straw compared to the latter it took 24 days to decomposed the rice straw. It only shows that Fuzzy Inference expert system can be a great tool to monitor the decomposition process.
International Journal of Emerging Trends in Engineering Research, 2020
Fire detection systems are implemented and intended to detect fires early so it can help the peop... more Fire detection systems are implemented and intended to detect fires early so it can help the people on a building or house for safe evacuation and immediately notify the firemen. After the firemen put out the fire, that will be the time that they can conduct an investigation in determining the source
or cause of fire which they often experience some difficulties.
Therefore, this study proposed an algorithm for identification of combustible and fluid fire with hybrid feature extraction techniques. The algorithm use RGB model, applying HSV conversion and Canny edge detection for the growth of fire. Then combine the results of HSV and Canny edge detection and used image segmentation of color space for combustible and fluid fire. The algorithm got an accuracy of 94% for 50 fire images demonstrated usefulness and effectiveness.
International Journal of Emerging Trends in Engineering Research, 2020
In the constant advancement of technology, protection of one’s property becomes a major concern f... more In the constant advancement of technology, protection of one’s property becomes a major concern for each individual. To secure one’s property the protection such as locks and keys mechanism were used but this mechanism can be easily replicated. This study aims to developed a device and a security system that replaced the conventional lock and keys mechanism to secure one’s property. This device also established a strong security based on the secret knock pattern security system. This security system consists of Arduino Mega, Piezo Sensor, and uses a Secret Knock that is known only to the owner. The researchers conducted hardware and system functionality. Thirty (30) trials were made in checking the accuracy of changing knock patterns where they obtained a 100% accuracy. Thirty-one (31) trials were made to check the accuracy of detecting incorrect patter. The experiments conducted obtained a 100% accuracy in detecting incorrect pattern.
International Journal of Emerging Trends in Engineering Research, 2020
Copra in the Philippines is one of the by-products from coconut which contributes as one of the m... more Copra in the Philippines is one of the by-products from coconut which contributes as one of the major sources of income of Filipino farmers. During the process of selling the Copra in the market, farmers usually lose in the price competition from the buyers due to the unidentified quality of their Copra. Copra which commonly either overcooked or undercooked are paid as half of the price of the perfectly cooked. This happened due to the lack of information of the farmers in assessing the quality of the processed copra meat. In this study, a Convolutional Neural Network had been evaluated in terms of its accuracy by varying the numbers of convolutional layer filters, the size of filters, and its activation function. The identified best parameters were used to develop a CNN algorithm that classifies the quality of Copra. The algorithm was implemented using Tensorflow in a python environment. A series of tests were applied to the final CNN model. Random images of Copra with identified quality were used as testing data. Out of 120 sample images, the final CNN model performs an overall 86% accuracy. The model was also implemented into a simple android application for validation. The confusion matrix and f-score were used to evaluate the performance of the system.