ATMAJA, GEOVANNY FIRDAUS (2023) CAFFEINE CONTENT OF DRINK CLASSIFICATION USING KNN AND SVM. Other thesis, Universitas Katholik Soegijapranata Semarang.
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-COVER_a.pdf Download (272kB) | Preview |
|
![[img]](https://repository.unika.ac.id/style/images/fileicons/text.png) |
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB I_a.pdf Restricted to Registered users only Download (114kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB II_a.pdf Restricted to Registered users only Download (118kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB III_a.pdf Restricted to Registered users only Download (120kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB IV_a.pdf Restricted to Registered users only Download (312kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB V_a.pdf Restricted to Registered users only Download (481kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-BAB VI_a.pdf Restricted to Registered users only Download (110kB) |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-DAPUS_a.pdf Download (116kB) | Preview |
|
|
Text
16.K1.0035-GEOVANNY FIRDAUS ATMAJA-LAMP_a.pdf Restricted to Registered users only Download (161kB) |
Abstract
Caffeine is popular worldwide and has many health benefits due to the presence and number of compounds. The compound is a xanthine alkaloid in the form of crystals and tastes bitter which works as a psychoactive stimulant and mild diuretic. Caffeine was discovered by a German chemist, Friedrich Ferdinand Runge in 1819. Caffeine is found naturally in foods such as coffee beans, tea leaves, colas, guarana, and maté.In plants, it acts as a natural pesticide that paralyzes and kills certain insects that eat these plants.The first process is how to process some drink data that will be classified using the KNN and SVM algorithms to get accurate results for the comparison of the two algorithms by programming processing using the orange data mining application and how the application works to produce which accuracy has higher accuracy.The results of the implementation of the two algorithms with Orange have a conclusion. Orange has deficiencies when determining detailed results on ca, f1-score, precision, and recall. Then there are many features whose functions are unknown and only show instantly. Therefore, there are many features that must be studied further according to the needs we want. Then when processing the application it only states that the data is true and false. So it can''t be as detailed as using processing with coding. So we cannot determine where the TN, FN, TP, and FP are located. But the strengths of Orange are that it''s easy to use and does it instantly.The processing results reveal that the two methods provide virtually identical outputs. It''s only that the K-NN method has a better degree of precision than SVM since the two algorithms have the same qualities, particularly the "Supervised Algorithm" property that both algorithms require training data
| Item Type: | Thesis (Other) |
|---|---|
| Subjects: | 000 Computer Science, Information and General Works |
| Divisions: | Faculty of Computer Science > Department of Informatics Engineering |
| Depositing User: | mr AM. Pudja Adjie Sudoso |
| Date Deposited: | 04 Apr 2023 05:57 |
| Last Modified: | 18 Sep 2024 02:56 |
| URI: | http://repository.unika.ac.id/id/eprint/31390 |
Actions (login required)
 |
View Item |
