Development of waste segregation system using machine learning/ Charlene A. Agpuldo, Rayna A. Glory, John Rogel A. Perucho, and Karlo R. Salas .--

By:

Agpuldo, Charlene A [author ]

Contributor(s):

Material type: Text

TextPublication details: Manila: Technological University of the Philippines, 2023.Description: x, 95pages: 29cmContent type:

Media type:

Carrier type:

Subject(s):

LOC classification:

BTH TK 870 A37 2023

Dissertation note: College of Industrial Technology .-- Bachelor of Engineering Technology major in Electronics Engineering Technology: Technological University of the Philippines, 2023. Summary: The amount of waste is continuously rising and is expected to further increase in the succeeding years. Moreover, people are becoming more irresponsible about throwing their own trash. Proper waste management is very important in society because it helps the environment. There are related studies, technologies, and solutions that the researchers need to address waste management which they are using robotic arms with image processing, web applications, SMS notifications and has a metal detection system. However, they are found to be expensive, can only segregate waste one at a time, no monitoring features, among others. The smart waste segregation was designed, developed, tested, and evaluated to resolve improper waste disposal. In this project study, the researchers simulated an adaptive machine learning algorithm using convolutional neural network. To further enhance waste segregation management, the system integrated an AI camera to effectively segregate the type of waste and a GSM module to send an SMS notification. The testing result in the hypothesis proves that there is a significant correlation of the two sensors’ accuracy and timeliness: metal sensor (r = .966, p=<.001) and image sensor (r = .943, p=<.001); and a sample size of n=10 using the Correlation Analysis. This means that there is a strong correlation between the accuracy and timeliness of metal sensor and AI camera. As such, while the accuracy level of the system is increasing, its timeliness in recognizing, metal and image sensor is also increasing. The system was evaluated using ISO 25010: 2011- System and software quality of 4.68 which is interpreted as excellent, and responses from the students, professors, and maintenance personnel in the university. By incorporating smart technologies, image processing, and waste management systems, the study aligns with the United Nations Sustainable Development Goals (UN-SDGs) 3 and 12, which focus on ensuring healthy lives and responsible consumption and production and target and focus on all waste through prevention, reduction, recycling, and reuse.

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Copy number	Status	Date due	Barcode
Bachelor's Thesis CIT	TUP Manila Library	Thesis Section-2nd floor	BTH TK 870 A37 2023 (Browse shelf(Opens below))	c.1.	Not for loan		BTH0005500

Bachelor's thesis

College of Industrial Technology .-- Bachelor of Engineering Technology major in Electronics Engineering Technology: Technological University of the Philippines, 2023.

Includes bibliography:

The amount of waste is continuously rising and is expected to further increase in the
succeeding years. Moreover, people are becoming more irresponsible about throwing their
own trash. Proper waste management is very important in society because it helps the
environment. There are related studies, technologies, and solutions that the researchers
need to address waste management which they are using robotic arms with image
processing, web applications, SMS notifications and has a metal detection system.
However, they are found to be expensive, can only segregate waste one at a time, no
monitoring features, among others. The smart waste segregation was designed, developed,
tested, and evaluated to resolve improper waste disposal. In this project study, the
researchers simulated an adaptive machine learning algorithm using convolutional neural
network. To further enhance waste segregation management, the system integrated an AI
camera to effectively segregate the type of waste and a GSM module to send an SMS
notification. The testing result in the hypothesis proves that there is a significant correlation
of the two sensors’ accuracy and timeliness: metal sensor (r = .966, p=<.001) and image
sensor (r = .943, p=<.001); and a sample size of n=10 using the Correlation Analysis. This
means that there is a strong correlation between the accuracy and timeliness of metal sensor
and AI camera. As such, while the accuracy level of the system is increasing, its timeliness
in recognizing, metal and image sensor is also increasing. The system was evaluated using
ISO 25010: 2011- System and software quality of 4.68 which is interpreted as excellent,
and responses from the students, professors, and maintenance personnel in the university.
By incorporating smart technologies, image processing, and waste management systems,
the study aligns with the United Nations Sustainable Development Goals (UN-SDGs) 3
and 12, which focus on ensuring healthy lives and responsible consumption and production
and target and focus on all waste through prevention, reduction, recycling, and reuse.

There are no comments on this title.

to post a comment.

Click on an image to view it in the image viewer