Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : The Indonesian Journal of Computer Science

Probability Prediction for Graduate Admission Using CNN-LSTM Hybrid Algorithm Zuhri, Burhanudin; Harani, Nisa Hanum; Prianto, Cahyo
The Indonesian Journal of Computer Science Vol. 12 No. 3 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i3.3248

Abstract

Currently, the prediction of student admissions still uses conventional machine learning algorithms where there is no algorithm for optimization. This study aims to produce a model that can predict student acceptance of ownership more optimally by using an optimization hybrid learning algorithm, namely the Convolutional Neural Network Long Short Term Memory (CNN-LSTM). This study uses the Microsoft Team Data Science Process method which consists of business understanding, data acquisition & understanding, modeling, and implementation as well as using the acceptance dataset obtained from the kaggle.com website as much as 500 data. The results showed that the CNN-LSTM hybrid learning model could optimize the prediction of students' chances of success in exposure as evidenced by the evaluation results of RMSE of 6.31%, MAE of 4.4%, and R2 of 80.52%. This model is implemented in a website application using the Python language, the Django framework, and the MySQL database.
Performance Analysis and Development of QnA Chatbot Model Using LSTM in Answering Questions Ilyas Tri Khaqiqi, M; Harani, Nisa Hanum; Prianto, Cahyo
The Indonesian Journal of Computer Science Vol. 12 No. 3 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i3.3249

Abstract

This research aims to evaluate the performance of a Long Short-Term Memory (LSTM) based chatbot in answering questions (QnA). LSTM is a type of Recurrent Neural Network (RNN) architecture specifically designed to overcome vanishing gradient problems and can store long-term information. The method used is 5-fold cross-validation to train the chatbot model with 15 epochs at each fold using the dataset provided. The results showed variations in model performance at each fold. At the 5th fold, there was a decrease in performance with 84.63% accuracy, 96.36% precision, 64.9% recall, and 69.84% loss value. This finding shows that there is variability in the performance of the QnA chatbot model at each fold. In conclusion, the LSTM chatbot model can provide good answers with high accuracy and precision. Still, performance variations need to be considered in the use of this chatbot.