Garuda - Garba Rujukan Digital

Adaptive Moment Estimation On Deep Belief Network For Rupiah Currency Forecasting Abram Setyo Prabowo; Agus Sihabuddin; Azhari SN
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 1 (2019): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.39071

One approach that is often used in forecasting is artificial neural networks (ANN), but ANNs have problems in determining the initial weight value between connections, a long time to reach convergent, and minimum local problems.Deep Belief Network (DBN) model is proposed to improve ANN's ability to forecast exchange rates. DBN is composed of a Restricted Boltzmann Machine (RBM) stack. The DBN structure is optimally determined through experiments. The Adam method is applied to accelerate learning in DBN because it is able to achieve good results quickly compared to other stochastic optimization methods such as Stochastic Gradient Descent (SGD) by maintaining the level of learning for each parameter.Tests are carried out on USD / IDR daily exchange rate data and four evaluation criteria are adopted to evaluate the performance of the proposed method. The DBN-Adam model produces RMSE 59.0635004, MAE 46.406739, MAPE 0.34652. DBN-Adam is also able to reach the point of convergence quickly, where this result is able to outperform the DBN-SGD model.

TOPSIS and SLR methods on the Decision Support System for Selection the Management Strategies of Funeral Land Yayang Eluis Bali Mawartika; Azhari SN; Agus Sihabuddin
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 2 (2019): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.39788

The funeral land is one of the public facilities that must be provided by Local Government to support community activities. The need for funeral land in Lubuklinggau continues to increase while the availability of funeral land is decreasing, this is because the number of deaths of the population continues to increase every year. Forecasting the land availability of funeral for the coming year and applying the management strategies of funeral land can overcome the needs of the cemetery. Forecasting the land availability of funeral using Simple Linear Regression. TOPSIS to choose the management strategies of funeral land. Forecasting uses two variables that are the variable number of the population deaths and the variable amount of funeral land in the last 5 years. Forecasting results will be used as one of the assessment criteria in the decision support system for selection of the management strategies of funeral land. The alternative of the funeral management strategy that will be applied and assessed in accordance with Local Regulation of Town of Lubuklinggau. The highest value of the end result of the system will be used as a recommendation for the selection of management strategies.

Extended Kalman Filter In Recurrent Neural Network: USDIDR Forecasting Case Study Muhammad Asaduddin Hazazi; Agus Sihabuddin
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 3 (2019): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.47802

Artificial Neural Networks (ANN) especially Recurrent Neural Network (RNN) have been widely used to predict currency exchange rates. The learning algorithm that is commonly used in ANN is Stochastic Gradient Descent (SGD). One of the advantages of SGD is that the computational time needed is relatively short. But SGD also has weaknesses, including SGD requiring several hyperparameters such as the regularization parameter. Besides that SGD relatively requires a lot of epoch to reach convergence. Extended Kalman Filter (EKF) as a learning algorithm on RNN is used to replace SGD with the hope of a better level of accuracy and convergence rate. This study uses IDR / USD exchange rate data from 31 August 2015 to 29 August 2018 with 70% data as training data and 30% data as test data. This research shows that RNN-EKF produces better convergent speeds and better accuracy compared to RNN-SGD.

Bidirectional Long Short Term Memory Method and Word2vec Extraction Approach for Hate Speech Detection Auliya Rahman Isnain; Agus Sihabuddin; Yohanes Suyanto
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 14, No 2 (2020): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.51743

Currently, the discussion about hate speech in Indonesia is warm, primarily through social media. Hate speech is communication that disparages a person or group based on characteristics such as (race, ethnicity, gender, citizenship, religion and organization). Twitter is one of the social media that someone uses to express their feelings and opinions through tweets, including tweets that contain expressions of hatred because Twitter has a significant influence on the success or destruction of one's image.This study aims to detect hate speech or not hate Indonesian speech tweets by using the Bidirectional Long Short Term Memory method and the word2vec feature extraction method with Continuous bag-of-word (CBOW) architecture. For testing the BiLSTM purpose with the calculation of the value of accuracy, precision, recall, and F-measure.The use of word2vec and the Bidirectional Long Short Term Memory method with CBOW architecture, with epoch 10, learning rate 0.001 and the number of neurons 200 on the hidden layer, produce an accuracy rate of 94.66%, with each precision value of 99.08%, recall 93, 74% and F-measure 96.29%. In contrast, the Bidirectional Long Short Term Memory with three layers has an accuracy of 96.93%. The addition of one layer to BiLSTM increased by 2.27%.

Face Image Generation and Enhancement Using Conditional Generative Adversarial Network Ainil Mardiah; Sri Hartati; Agus Sihabuddin
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 16, No 1 (2022): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.58327

The accuracy and speed of a single image super-resolution using a convolutional neural network is often a problem in improving finer texture details when using large enhancement factors. Some recent studies have focused on minimal mean square error, resulting in a high peak signal to noise ratio. Generally, although the peak signal to noise ratio has a high value, the output image is less detailed. This shows that the determination of super-resolution is not optimal. Conditional Generative Adversarial Network based on Boundary Equilibrium Generative Adversarial Network, by combining Mean Square Error Loss and GAN Loss as a loss function to optimize the super-resolution model and produce super-resolution images. Also, the generator network is designed with skip connection architecture to increase convergence speed and strengthen feature distribution. Image quality value parameters used in this study are Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The results showed the highest image quality values using dataset validation were 26.55 for PSNR values and 0.93 for SSIM values. The highest image quality values using the testing dataset are 24.56 for the PSNR value and 0.91 for the SSIM value.

Reccomendations on Selecting The Topic of Student Thesis Concentration using Case Based Reasoning Annisaa Utami; Yohanes Suyanto; Agus Sihabuddin
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 15, No 1 (2021): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.58919

Case Based Reasoning (CBR) is a method that aims to resolve a new case by adapting the solutions contained in previous cases that are similar to the new case. The system built in this study is the CBR system to make recommendations on the topic of student thesis concentration. This study used data from undergraduate students of Informatics Engineering IST AKPRIND Yogyakarta with a total of 115 data consisting of 80 training data and 35 test data. This study aims to design and build a Case Based Reasoning system using the Nearest Neighbor and Manhattan Distance Similarity Methods, and to compare the results of the accuracy value using the Nearest Neighbor Similarity and Manhattan Distance Similarity methods. The recommendation process is carried out by calculating the value of closeness or similarity between new cases and old cases stored on a case basis using the Nearest Neighbor Method and Manhattan Distance. The features used in this study consisted of GPA and course grades. The case taken is the case with the highest similarity value. If a case doesnt get a topic recommendation or is less than the trashold value of 0.8, a case revision will be carried out by an expert. Successfully revised cases are stored in the system to be made new knowledge. The test results using the Nearest Neighbor Method get an accuracy value of 97.14% and Manhattan Distance Method 94.29%.

Ontology-based Complementary Breastfeeding Search Model Astrid Noviana Paradhita; Anny Kartika Sari; Agus Sihabuddin
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 16, No 3 (2022): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.71963

Children's nutritional requirements differ from those of adults. The health ministry's Indonesian data shows that in 2017, there were 17.8% of malnourished children under five years old (toddlers), one of which was related to complementary breastfeeding problems. Complementary breastfeeding is given to babies starting at 6–24 months of age. This research aims to build a complementary breastfeeding search model and be able to present it as a treatment for malnourished babies. A search model is built to understand natural language input given by a user. Also, it can do reasoning by applying a set of rules to obtain implicit knowledge about the complementary breastfeeding menu recommended for babies. The methods used in this research are data collection, designing a search model, building an ontology model, building SWRL, natural language processing, and usability testing by users and nutritionists. This research succeeded in building an ontology-based complementary breastfeeding search model in the form of a semantic web. The testing result shows that the web can provide an alternative complementary breastfeeding menu according to the baby’s nutritional needs and has a high usability capability of 4.01 on a scale of 1 to 5.

Combining Multiple Text Representations for Improved Automatic Evaluation of Indonesian Essay Answers Wibowo, Moh Edi; Rokhman, Nur; Sihabudin, Agus
Scientific Journal of Informatics Vol. 11 No. 3: August 2024
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v11i3.9440

multiple-choices, regarding students’ learning achievement. When the number of students in a class is huge, however, examinations using essay questions become hard to conduct and take a long evaluation time. Automatic essay evaluation has, therefore, become a potential approach in this situation. Various methods have been proposed, however, optimal solutions for such evaluation in the Indonesian language are less known. Furthermore, with the rapid development of machine learning approaches, in particular deep learning approaches, the investigation of such optimal solutions becomes more necessary. Method: To address the aforementioned issue, this study proposed the investigation of text representation approaches for optimal automatic evaluation of Indonesian essay answers. The investigation compared pre-trained word embedding methods such as Word2vec, GloVe, FastText, and RoBERTa, as well as compared text encoding methods such as long short-term memories (LSTMs) and transformers. LSTMs are able to capture temporal semantics by employing state variables, while transformers are able to capture long-term dependency between parts of their input sequences. Additionally, we investigated classification-based and similarity-based training to build text encoders. We expected that these training approaches allowed encoders to extract different views of information. We compared classification results produced by different text encoders and combinations of text encoders. Result: We evaluated various text representation approaches using the UKARA dataset. Our experiments showed that the FastText word embedding method outperformed the Word2vec, GloVe, and RoBERTa methods. The FastText method achieved an F1-score of 75.43% on validation sets, while the Word2vec, GloVe, and RoBERTa methods achieved F1-scores of 69.56%, 74.53%, and 72.87%, respectively. In addition, the experiments showed that combinations of text encoders outperformed individual encoders. The combination of the LSTM encoder, the transformer encoder, and the TF-IDF encoder obtained an F1-score of 77.22% in the best case, which is better than the best F1-scores of the individual LSTM encoders (75.35%), the best combination of transformer encoders (71.49%), and the individual TF-IDF encoder (76.69%). We observed that LSTM encoders produced better performance when they were built using classification-based training. Meanwhile, the transformer encoders obtained better performance when built using similarity-based training. Novelty: The novelty proposed in this research is the optimal combination of text encoders specifically constructed for the evaluation of essay answers in the Indonesian language. Our experiments showed that the combination of three encoders - namely the LSTM encoder built using classification-based training, the transformer encoder built using classification-based and similarity-based training, and the TF-IDF encoder - obtained the best classification performance.

Personality Classification of Myers Briggs Type Indicators (MBTI) Using BERT and Machine Learning Sihabuddin, Agus; Ekapratiwi, Dian
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 19, No 2 (2025): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.104126

Personality classification using textual data from social media or online forums is a complex task due to the unstructured text and the multifaceted nature of personality. While the Myers-Briggs Type Indicator (MBTI) provides a comprehensive framework, adapting it to media data and handling diverse linguistic patterns requires effective algorithms. The psychological basis of MBTI is intricate, especially when using complex methods like deep learning, which can be challenging. This study classifies personality types based on each individual's behavior on an online forum by observing the linguistic patterns of posted textual data using the SVM, Random Forest, BERT, and Word2Vec algorithms. The SVM and Random Forest algorithms are traditional machine learning algorithms known for their capabilities and effectiveness in text classification. Meanwhile, BERT and Word2Vec identify semantic relationships and contextual information from textual data. In addition, the IndoBERT model will be used for the BERT model because this study focuses on the classification of Indonesian language texts.Testing was carried out using textual data from posts on the PersonalityCafe forum. The test results showed that the combination of the SVM and IndoBERT models outperformed other models with an accuracy rate of 82% and an F1 score of 75%.

Title

Found 9 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 9 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 9 Documents
Search