Garuda - Garba Rujukan Digital

PEMODELAN GRAPH DATABASE UNTUK MODA TRANSPORTASI BUS RAPID TRANSIT Wirawan, Panji Wisnu; Riyanto, Djalal Er; Khadijah, Khadijah
Jurnal Informatika Vol 10, No 2 (2016): Juli
Publisher : Universitas Ahmad Dahlan

Bus Rapid Transit (BRT) merupakan salah satu alternatif transportasi massal. Rute BRT memiliki karakteristik khusus yang dapat dimodelkan dengan graph. Ketika rute dan shelter semakin bertambah, dibutuhkan aplikasi komputer untuk melakukan pencarian rute BRT. Hal tersebut akan memudahkan pencarian dan penjelajahanÂ rute-rute BRT. Namun, ketika rute diimplementasikan menggunakan basis data relasional, performa query dapat menurun karena banyaknya operasi JOIN untuk mencari rute. Artikel ini mengusulkan sebuah model graph database untuk BRT dan implementasinya. Identifikasi kebutuhan data dilakukan, dilanjutkan dengan pemodelan menggunakan entity relationship (ER). HasilÂ ER tersebut kemudian dipetakan ke dalam property graph untuk kemudian diimplementasikan menggunakan produk graph database Neo4J. Hasil penelitian ini menunjukkan bahwa model yang dibuat bisa diterapkan dalam basis data graph dan graph dapat menunjukkan rute BRT tertentu. Dari sisi performance, basis data graph menunjukkan kinerja perambatan yang lebih baik dibandingkan dengan basis data relasional.Â Keyword : BRT, graphdatabase

Solid waste classification using pyramid scene parsing network segmentation and combined features Khadijah Khadijah; Sukmawati Nur Endah; Retno Kusumaningrum; Rismiyati Rismiyati; Priyo Sidik Sasongko; Iffa Zainan Nisa
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 19, No 6: December 2021
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v19i6.18402

Solid waste problem become a serious issue for the countries around the world since the amount of generated solid waste increase annually. As an effort to reduce and reuse of solid waste, a classification of solid waste image is needed to support automatic waste sorting. In the image classification task, image segmentation and feature extraction play important roles. This research applies recent deep leaning-based segmentation, namely pyramid scene parsing network (PSPNet). We also use various combination of image feature extraction (color, texture, and shape) to search for the best combination of features. As a comparison, we also perform experiment without using segmentation to see the effect of PSPNet. Then, support vector machine (SVM) is applied in the end as classification algorithm. Based on the result of experiment, it can be concluded that generally applying segmentation provide better source for feature extraction, especially in color and shape feature, hence increase the accuracy of classifier. It is also observed that the most important feature in this problem is color feature. However, the accuracy of classifier increase if additional features are introduced. The highest accuracy of 76.49% is achieved when PSPNet segmentation is applied and all combination of features are used.

Software Defect Prediction Using Synthetic Minority Over-sampling Technique and Extreme Learning Machine Khadijah Khadijah; Priyo Sidik Sasongko
Journal of Telematics and Informatics Vol 7, No 2: JUNE 2019
Publisher : Universitas Islam Sultan Agung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/jti.v7i2.

Software testing is one of the crucial processes in software development life cycle which will influence the software quality. One of the strategies to help testing process is predicting the part or module of software which is prone to defect. Then, the testing process can be more focused to those parts. In this research a classifier model for predicting software defect was built. One of the most important problems in software defect prediction is imbalance data distribution between samples of positive class (prone to defect) and of negative class. Therefore, in this research SMOTE is implemented to handle imbalance data problem and extreme learning machine is implemented as a classification algorithm. As a comparison to SMOTE-ELM, a modification of ELM which directly copes with imbalance problem, weighted-ELM, is also observed. This research used NASA MDP dataset PC1, PC2, PC3 and PC4. The results of experiment using 10-fold cross validation show that directly classification using ELM obtain the worse result compared to SMOTE-ELM and weighted-ELM. When the value of imbalance ratio is not very small, the SMOTE-ELM is better than weighted-ELM. When the value of imbalance ratio is very small, the g-mean of weighted-ELM is higher than the g-mean of SMOTE-ELM, but the accuracy of weighted-ELM is lower than the accuracy of SMOTE-ELM. Therefore, in this software defect prediction case it can be concluded that SMOTE is effective to increase the generalization performance of classifier in minority class as long as the value of imbalance ratio is not very small.

Temperament detection based on Twitter data: classical machine learning versus deep learning Annisa Ulizulfa; Retno Kusumaningrum; Khadijah Khadijah; Rismiyati Rismiyati
International Journal of Advances in Intelligent Informatics Vol 8, No 1 (2022): March 2022
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v8i1.692

Deep learning has shown promising results in various text-based classification tasks. However, deep learning performance is affected by the number of data, i.e., when the number of data is small, deep learning algorithms do not perform well, and vice versa. Classical machine learning algorithms commonly work well for a few data, and their performance reaches an optimal value and does not increase with the increase in sample data. Therefore, this study aimed to compare the performance of classical machine learning and deep learning methods to detect temperament based on Indonesian Twitter. In this study, the proposed Indonesian Linguistic Inquiry and Word Count were employed to analyze the context of Twitter. The classical machine learning methods implemented were support vector machine and K-nearest neighbor, whereas the deep learning method employed was a convolutional neural network (CNN) with three different architectures. Both learning methods were implemented using multiclass classification and one versus all (OVA) multiclass classification. The highest average f-measure was 58.73%, obtained by CNN OVA with a pool size of 3, a dropout value of 0.7, and a learning rate value of 0.0007.

PEMODELAN GRAPH DATABASE UNTUK MODA TRANSPORTASI BUS RAPID TRANSIT Panji Wisnu Wirawan; Djalal Er Riyanto; Khadijah Khadijah
Jurnal Informatika Vol 10, No 2 (2016): Juli
Publisher : Universitas Ahmad Dahlan

Bus Rapid Transit (BRT) merupakan salah satu alternatif transportasi massal. Rute BRT memiliki karakteristik khusus yang dapat dimodelkan dengan graph. Ketika rute dan shelter semakin bertambah, dibutuhkan aplikasi komputer untuk melakukan pencarian rute BRT. Hal tersebut akan memudahkan pencarian dan penjelajahanÂ rute-rute BRT. Namun, ketika rute diimplementasikan menggunakan basis data relasional, performa query dapat menurun karena banyaknya operasi JOIN untuk mencari rute. Artikel ini mengusulkan sebuah model graph database untuk BRT dan implementasinya. Identifikasi kebutuhan data dilakukan, dilanjutkan dengan pemodelan menggunakan entity relationship (ER). HasilÂ ER tersebut kemudian dipetakan ke dalam property graph untuk kemudian diimplementasikan menggunakan produk graph database Neo4J. Hasil penelitian ini menunjukkan bahwa model yang dibuat bisa diterapkan dalam basis data graph dan graph dapat menunjukkan rute BRT tertentu. Dari sisi performance, basis data graph menunjukkan kinerja perambatan yang lebih baik dibandingkan dengan basis data relasional.Â Keyword : BRT, graphdatabase

Ensemble Classifier untuk Klasifikasi Kanker Payudara Khadijah Khadijah; Retno Kusumaningrum
IT Journal Research and Development Vol. 4 No. 1 (2019)
Publisher : UIR PRESS

Kanker payudara merupakan jenis kanker yang paling banyak diderita oleh kaum wanita di Indonesia. Penyakit tersebut dapat berakibat pada kematian jika terlambat ditangani. Oleh karena itu, deteksi dini kanker payudara merupakan langkah awal untuk menyelamatkan nyawa pasien. Pada penelitian ini telah dilakukan klasifikasi kanker payudara berdasarkan data anthopometric serta data dari hasil tes darah rutin menggunakan single classifier (ELM, SVM dan kNN) dan ensemble classifier yang menggabungkan ketiga algoritma tersebut dengan penentuan kelas majority voting. Pembagian data dilakukan dengan three way data split. Hasil eksperimen menunjukkan bahwa saat menggunakan keseluruhan fitur penggunaan ensemble classifier lebih baik daripada single classifier dalam hal akurasi maupun G-mean. Namun, saat menggunakan 4 fitur terbaik (resistin, glucose, age, dan BMI) penggunaan ensemble classifier sedikit lebih baik dalam hal G-mean. Hal ini disebabkan minimnya diversity di antara classifier sehingga saat digabungkan tidak mampu memperbaiki hasil.

SENTIMENT ANALYSIS OF LEAGUE OF LEGENDS: WILD RIFT REVIEWS ON GOOGLE PLAY USING NAÏVE BAYES CLASSIFIER Khadijah Khadijah; Nur Sabilly; Fajar Agung Nugroho
Jurnal Ilmiah Kursor Vol 12 No 1 (2023)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v12i01.328

League of Legends: Wild Rift is a mobile game with more than 48 million downloads worldwide. The game publishers could earn profit from selling item in the game (in-app purchases). Performance of player and players' impressions during the first week usually determine whether players would made in-app purchases or not. Therefore, it is important to understand the player opinions so that the game publisher could encourage the players to increase the in-app purchases. Therefore, this research utilized sentiment analysis to study the player opinions about the League of Legends: Wild Rift game based on the reviews given by the players on the Google Play Store. The sentiment analysis was applied by using Naive Bayes Classifier (NBC) algorithm which was well known for achieving good accuracy in the sentiment analysis task. In addition, data preprocessing and feature extraction should be carried out properly to increase the accuracy of the classifier. Therefore, this research investigated the impact of using stemming and transformation of informal words into formal words in the preprocessing stages, then compared two feature extraction algorithms, namely Term Frequency – Inverse Document Frequency (TF-IDF) and Bag of Words (BOW). From the experiment, it was found that the use of stemming could decrease the accuracy of the classifier, but the use of transformation of non-standard words into standard words could improve the performance of the classifier, for both feature extractions, BOW and TF-IDF. In this case, BOW feature extraction was able to achieve better performance, compared to TF-IDF. The best model was achieved when not using stemming, applying the transformation of informal words into formal words, and using BOW bigram feature extraction, with the accuracy of 79,3%, precision of 82.10%, recall of 83.50%, and f1-score of 82,8.10%.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search