1D-Convnet Model for Detection of Antidepressant Drugs

Pasfica, Gracia Rizka and Ramadhan, Nur ghaniaviyanto and Adhinata, Faisal Dharma 1D-Convnet Model for Detection of Antidepressant Drugs. 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom).

[img] Text (Peer Review)
[FIX] Peer Prosiding CybernaticsCom.pdf

Download (1MB)
[img] Text (Similarity)
Similarity IEEE Cybernatics.pdf

Download (507kB)
[img] Text (Conference)
Fix Cybernatics.pdf

Download (2MB)


A drug is a substance or mixture of materials to be used in determining the diagnosis, preventing, reducing, eliminating, curing disease or symptoms of disease, bodily or spiritual injury or disorder in humans or animals, including to beautify the body or parts of the human body. Problems begin to arise when a patient is wrong in consuming the target drug used, which is not by the type of disease suffered. For example, suppose a person suffers from a psychological disorder that requires taking different types of drugs, if it turns out that the type of drug consumed is not by the disease, it is very dangerous. This problem is certainly very dangerous because it can cause death for those who consume it. Currently, many researchers are using the deep learning Convolutional Neural Network (CNN) model for drug detection problems. The CNN model has a higher level, namely 1D-Convolutional Neural Network (1DConvnet) which is still rarely used for drug detection problems. So, the purpose of this study was to detect the classification of atypical antidepressants and SSRIs antidepressants using a deep learning model of the 1D-Convolutional Network (1DConvnet) type. The results obtained using this model are 98.3% with the most influential parameter, namely dropout. The proposed research model also produces higher accuracy than the Naive Bayes supervised learning model.

Item Type: Article
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Depositing User: Faisal Dharma Adhinata, S.Kom., M.Cs.
Date Deposited: 09 Feb 2023 03:13
Last Modified: 11 Feb 2023 00:06
URI: http://repository.ittelkom-pwt.ac.id/id/eprint/8892

Actions (login required)

View Item View Item