IMPLEMENTASI PERBANDINGAN ALGORITMA K-NEAREST NEIGHBOR DAN ALGORITMA SUPPORT VECTOR MACHINES DALAM MENENTUKAN PREDIKSI KUALITAS UDARA

ROHIMAH, AULYAH NUR and Malik, Reza Firsandaya (2020) IMPLEMENTASI PERBANDINGAN ALGORITMA K-NEAREST NEIGHBOR DAN ALGORITMA SUPPORT VECTOR MACHINES DALAM MENENTUKAN PREDIKSI KUALITAS UDARA. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011381520069.pdf] Text
RAMA_56201_09011381520069.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_TURNITIN.pdf] Text
RAMA_56201_09011381520069_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (12MB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_01_front_ref.pdf]
Preview
Text
RAMA_56201_09011381520069_0025047609_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Preview
[thumbnail of RAMA_56201_09011381520069_0025047609_02.pdf] Text
RAMA_56201_09011381520069_0025047609_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (759kB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_03.pdf] Text
RAMA_56201_09011381520069_0025047609_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (234kB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_04.pdf] Text
RAMA_56201_09011381520069_0025047609_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (539kB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_05.pdf] Text
RAMA_56201_09011381520069_0025047609_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (185kB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_06_ref.pdf] Text
RAMA_56201_09011381520069_0025047609_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (295kB) | Request a copy
[thumbnail of RAMA_56201_09011381520069_0025047609_07_lamp.pdf] Text
RAMA_56201_09011381520069_0025047609_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (234kB) | Request a copy

Abstract

Air pollution is a very big problem for every country, both developed and developing countries. The amount of pollution in the dense population causes an increase in the level of air pollution due to pollutant gases. There are five main parameters that become the standard for gases that cause air pollution in the form of Carbon Monoxide (CO), Nitrogen Dioxide (NO2), Sulfur Dioxide (SO2), Ozone (O3), and Particulate Materials (PM-2,5). This parameter is expressed as a standard index of air pollution or called the ISPU. This research was conducted to predict the level of air quality with parameters CO, NO2, SO2, O3, and PM-2,5 by implementing the K-Nearest Neighbor algorithm and the Support Vector Machines algorithm to make comparisons in calculating the level of accuracy of the prediction results with actual data on testing data. A total of 120 data records in the form of air pollution quality index data in New York City in April 2014-2017 were taken from the United States Environmental Protection Agency (EPA) for use in the training and testing process. The K-Nearest Neighbor algorithm and the Support Vector Machines algorithm are given input for the parameter values of CO, NO2, SO2, O3, and PM-2,5, and the air quality index on the same day). Testing was carried out using Pycharm 2019.3.3 software. The results of the tests conducted show that the K-Nearest Neighbor Algorithm produces an average level of accuracy between the predicted value and actual data based on the ISPU value output of 89.26%, while the Support Vector Machines Algorithm produces an average accuracy rate between the predicted value and actual data based on the output of the ISPU value is 93.16%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Keyword : K-Nearest Neighbor Algorithm, Support Vector Machines Algorithm, Prediction, Air Quality Index, Accuracy Level
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Users 3097 not found.
Date Deposited: 22 Jan 2021 04:11
Last Modified: 22 Jan 2021 04:42
URI: http://repository.unsri.ac.id/id/eprint/40798

Actions (login required)

View Item View Item