Articles
Deteksi User Berpengaruh Berdasarkan Kombinasi Fitur Popularitas User Dan Topik Monomorphism Pada Data Twitter untuk Promosi Produk
Wijoyo, Satrio Hadi;
Fatichah, Chastine;
Purwitasari, Diana
Inspiration: Jurnal Teknologi Informasi dan Komunikasi Vol 6, No 1 (2016): Jurnal Inspiration Volume 6 Issue 1
Publisher : STMIK AKBA
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35585/inspir.v6i1.87
User berpengaruh merupakan sebuah user yang biasanya populer di twitter dengan ditandai memiliki banyak follower, isi tweet atau pendapatnya sering dikutip atau diikuti oleh akun lainnya dengan ditandai tweet yang sering di retweet, dan namanya sering disebut atau di-mention. Akan tetapi, ketertarikan tweet user berpengaruh tidak dapat dilihat hanya dari fitur retweet dan mention saja, melainkan dapat dilihat dari fitur topik monomorphism.Berdasarkan permasalahan tersebut, suatu metode diusulkan kombinasi fitur popularitas user dan topik monomorphism untuk mendeteksi user berpengaruh pada data twitter untuk promosi produk. Berdasarkan hasil ujicoba, nilai rata-rata akurasi algoritma fuzzy inference system dari produk Iphone sebesar 75,75%, produk Samsung sebesar 79,25%, dan produk Apple sebesar 74,5%. Hasil ini menunjukkan bahwa deteksi user berpengaruh berdasarkan kombinasi fitur popularitas user dan topik monomorphism menghasilkan keluaran cukup baik.
New Lossless Compression Method using Cyclic Reversible Low Contrast Mapping (CRLCM)
Hendra Mesra;
Handayani Tjandrasa;
Chastine Fatichah
International Journal of Electrical and Computer Engineering (IJECE) Vol 6, No 6: December 2016
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (752.749 KB)
|
DOI: 10.11591/ijece.v6i6.pp2836-2845
In general, the compression method is developed to reduce the redundancy of data. This study uses a different approach to embed some bits of datum in image data into other datum using a Reversible Low Contrast Mapping (RLCM) transformation. Besides using the RLCM for embedding, this method also applies the properties of RLCM to compress the datum before it is embedded. In its algorithm, the proposed method engages Queue and Recursive Indexing. The algorithm encodes the data in a cyclic manner. In contrast to RLCM, the proposed method is a coding method as Huffman coding. This research uses publicly available image data to examine the proposed method. For all testing images, the proposed method has higher compression ratio than the Huffman coding.
The Tomatoes and Chilies Type Classifications by Using Machine Learning Methods: Classifications using Machine Learning Methods
Irzal Ahmad Sabilla;
Chastine Fatichah
Journal of Development Research Vol. 4 No. 1 (2020): Volume 4, Number 1, May 2020
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Nahdlatul Ulama Blitar
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (751.481 KB)
|
DOI: 10.28926/jdr.v4i1.93
Vegetables are ingredients for flavoring, such as tomatoes and chilies. A Both of these ingredients are processed to accompany the people's staple food in the form of sauce and seasoning. In supermarkets, these vegetables can be found easily, but many people do not understand how to choose the type and quality of chilies and tomatoes. This study discusses the classification of types of cayenne, curly, green, red chilies, and tomatoes with good and bad conditions using machine learning and contrast enhancement techniques. The machine learning methods used are Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), Linear Discriminant Analysis (LDA), and Random Forest (RF). The results of testing the best method are measured based on the value of accuracy. In addition to the accuracy of this study, it also measures the speed of computation so that the methods used are efficient.
Automatic Leukemia Cell Counting using Iterative Distance Transform for Convex Sets
Nenden Siti Fatonah;
Handayani Tjandrasa;
Chastine Fatichah
International Journal of Electrical and Computer Engineering (IJECE) Vol 8, No 3: June 2018
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (23.667 KB)
|
DOI: 10.11591/ijece.v8i3.pp1731-1740
The calculation of white blood cells on the acute leukemia microscopic images is one of the stages in the diagnosis of Leukemia disease. The main constraint on calculating the number of white blood cells is the precision in the area of overlapping white blood cells. The research on the calculation of the number of white blood cells overlapping generally based on geometry. However, there was still a calculation error due to over segment or under segment. This paper proposed an Iterative Distance Transform for Convex Sets (IDTCS) method to determine the markers and calculate the number of overlapping white blood cells. Determination of marker was performed on every cell both in single and overlapping white blood cell area. In this study, there were tree stages: segmentation of white blood cells, marker detection and white blood cell count, and contour estimation of every white blood cell. The used data testing was microscopic acute leukemia image data of Acute Lymphoblastic Leukemia (ALL) and Acute Myeloblastic Leukemia (AML). Based on the test results, Iterative Distance Transform for Convex Sets IDTCS method performs better than Distance Transform (DT) and Ultimate Erosion for Convex Sets (UECS) method.
AN EXPERIMENTAL STUDY ON BANK PERFORMANCE PREDICTION BASE ON FINANCIAL REPORT
Chastine Fatichah;
Nurina Indah Kemalasari
CCIT Journal Vol 5 No 1 (2011): CCIT JOURNAL
Publisher : Universitas Raharja
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (184.137 KB)
|
DOI: 10.33050/ccit.v5i1.490
This paper presents an experimental study on bank performance prediction base on financial report. This research use Support Vector Machine (SVM), Probabilistic Neural Network (PNN) and Radial Basis Function Neural Network (RBFN) methods to experiment the bank performance prediction. To improve accuracy prediction of both neural network methods, this research use Principal Component Analysis (PCA) to get best feature. This research work based on the bank’s financial report and financial variables predictions of several banks that registered in Bank Indonesia. The experimental results show that the accuracy rate of bank performance prediction of PCA-PNN or PCA-RBFN methods are higher than SVM method for Bank Persero, Bank Non Devisa and Bank Asing categories. But, the accuracy rate of SVM method is higher than PCA-PNN or PCA-RBFN methods for Bank Pembangunan Daerah and Bank Devisa categories. The accuracy rate of PCA-PNN method for all bank categories is comparable to that PCA-RBFN method.
Ekstraksi Fitur Produktivitas Dinamis berdasarkan Topik Artikel Ilmiah untuk Klasterisasi Peneliti
Addien Haniefardy;
Diana Purwitasari;
Chastine Fatichah
Techno.Com Vol 20, No 2 (2021): Mei 2021
Publisher : LPPM Universitas Dian Nuswantoro
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.33633/tc.v20i2.4512
Pengelompokkan peneliti seringkali menggunakan informasi tekstual yang terdapat pada artikel ilmiah peneliti, contohnya judul, abstrak, dan kata kunci sehingga menghasilkan kelompok peneliti dengan kemiripan informasi tekstual pada artikel ilmiah mereka. Pengelompokkan peneliti juga seringkali menggunakan jumlah publikasi dan sitasi sehingga menghasilkan kelompok peneliti yang memiliki jumlah publikasi dan sitasi yang cenderung sama. Berdasarkaan kedua metode di atas, penelitian ini mencoba untuk menganalisis penggunaan topik artikel ilmiah pada proses ekstraksi fitur produktivitas. Fitur ini merupakan fitur yang didapatkan melalui penghitungan kinerja peneliti berdasarkan jumlah publikasi dan sitasi. Hasil ekstraksi fitur akan digunakan untuk klasterisasi peneliti menggunakan metode K-Means++. Sebelum data peneliti diklasterisasi, terlebih dahulu data peneliti dianalisis untuk menghilangkan kemungkinan adanya outlier. Evaluasi hasil klaster dilakukan dengan mempertimbangkan nilai Sum Squared Error dan Silhouette. Hasilnya, klaster optimal didapatkan dengan nilai K sama dengan 8 dan nilai silhouette sama dengan 0.15396. Kemudian, hasil klaster dianalisis untuk dapat memberikan label terhadap masing-masing klaster dengan mempertimbangkan topik artikel ilmiah, jumlah publikasi dan jumlah sitasi.
Multi-feature Fusion Using SIFT and LEBP for Finger Vein Recognition
Hardika Khusnuliawati;
Chastine Fatichah;
Rully Soelaiman
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 15, No 1: March 2017
Publisher : Universitas Ahmad Dahlan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.12928/telkomnika.v15i1.4443
In this paper, multi-feature fusion using Scale Invariant Feature Transform (SIFT) and Local Extensive Binary Pattern (LEBP) was proposed to obtain a feature that could resist degradation problems such as scaling, rotation, translation and varying illumination conditions. SIFT feature had a capability to withstand degradation due to changes in the condition of the image scale, rotation and translation. Meanwhile, LEBP feature had resistance to gray level variations with richer and discriminatory local characteristics information. Therefore the fusion technique is used to collect important information from SIFT and LEBP feature.The resulting feature of multi-feature fusion using SIFT and LEBP feature would be processed by Learning Vector Quantization (LVQ) method to determine whether the testing image could be recognized or not. The accuracy value could achieve 97.50%, TPR at 0.9400 and FPR at 0.0128 in optimum condition. That was a better result than only use SIFT or LEBP feature.
Multi-class K-support Vector Nearest Neighbor for Mango Leaf Classification
Eko Prasetyo;
R. Dimas Adityo;
Nanik Suciati;
Chastine Fatichah
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 16, No 4: August 2018
Publisher : Universitas Ahmad Dahlan
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.12928/telkomnika.v16i4.8482
K-Support Vector Nearest Neighbor (K-SVNN) is one of methods for training data reduction that works only for binary class. This method uses Left Value (LV) and Right Value (RV) to calculate Significant Degree (SD) property. This research aims to modify the K-SVNN for multi-class training data reduction problem by using entropy for calculating SD property. Entropy can measure the impurity of data class distribution, so the selection of the SD can be conducted based on the high entropy. In order to measure performance of the modified K-SVNN in mango leaf classification, experiment is conducted by using multi-class Support Vector Machine (SVM) method on training data with and without reduction. The experiment is performed on 300 mango leaf images, each image represented by 260 features consisting of 256 Weighted Rotation- and Scale-invariant Local Binary Pattern features with average weights (WRSI-LBP-avg) texture features, 2 color features, and 2 shape features. The experiment results show that the highest accuracy for data with and without reduction are 71.33% and 71.00% respectively. It is concluded that K-SVNN can be used to reduce data in multi-class classification problem while preserve the accuracy. In addition, performance of the modified K-SVNN is also compared with two other methods of multi-class data reduction, i.e. Condensed Nearest Neighbor Rule (CNN) and Template Reduction KNN (TRKNN). The performance comparison shows that the modified K-SVNN achieves better accuracy.
Solution of class imbalance of k-nearest neighbor for data of new student admission selection
Siti Mutrofin;
Ainul Mu'alif;
Raden Venantius Hari Ginardi;
Chastine Fatichah
International Journal of Artificial Intelligence Research Vol 3, No 2 (2019): December 2019
Publisher : STMIK Dharma Wacana
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (354.75 KB)
|
DOI: 10.29099/ijair.v3i2.92
The objective of this research is to correct the inconsistencies associated with the response differences by each examiner with respect to the assessment of each hafiz candidate. To carry out this research, 259 students were selected within a week using 4testers. However, the examiners are also tasked with another essential mandate which must be immediately fulfilled asides testing candidates for hafiz. In order to overcome this problem, the Educational Data Mining (EDM) system is applied during classification. The problems associated with the use of this technique however, is the limited number of attributes and the imbalance data class. This study was proposed to apply the kNN (k-Nearest Neighbor) technique. The results obtained indicates that kNN can provide recommendations to testers who are students and it is suitable for the solving the problem associated with class imbalance as indicated by the application of Shuffled and Stratified sampling techniques which has values of accuracy, precision, recall and AUC > 0.8%.
Optimasi Penjadwalan Penugasan Crane dengan Algoritma Branch and Price
Yudhi Purwananto;
Chastine Fatichah;
Anna Kholilah;
Rully Soelaiman
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2006
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Perusahaan persewaan crane merupakan perusahaan jasa yang berprinsip memenuhi pesanan dari pelanggan. Karena keterbatasan sumber daya yang dimiliki, maka tidak semua pesanan yang datang dapat diterima. Pesanan dapat diterima apabila sebuah perusahaan sanggup memenuhinya tanpa mengabaikan pesanan-pesanan yang datang terlebih dahulu, karena pesanan yang datang terlebih dahulu seharusnya dilayani terlebih dahulu. Untuk menyelesaikan pesanan-pesanan yang diterimanya, sebuah perusahaan persewaan memiliki seorang planner yang bertugas untuk mendistribusikan semua sumber daya yang ada. Salah satu biaya operasional adalah biaya pengoperasian sumber daya yang dimiliki perusahaan persewaan. Untuk dapat memaksimalkan keuntungan, maka salah satunya adalah dengan meminimalkan biaya operasional yang dikeluarkan.Permasalahan tersebut dapat dirumuskan sebagai permasalahan integer programming yang dapat diselesaikan dengan menggunakan algoritma branch and price. Dua proses yang akan dilakukan yaitu percabangan pada variabel keputusan yang belum integer dan pengecekan adanya reduced cost negatif pada tiap variabel keputusannya. Pengecekan reduced cost ini dilakukan agar tidak melakukan penelusuran pada semua kemungkinan solusi integer, seperti yang dilakukan pada algoritma branch and price. Hasil optimal dicapai pada solusi integer yang semua variabel keputusannya tidak memiliki reduced cost negatif.Uji coba dan evaluasi dilakukan dengan menggunakan data yang didapatkan dari sebuah perusahaan persewaan crane pada NRL. Dari beberapa hasil uji coba yang dilakukan menunjukkan bahwa aplikasi dapat merumuskan integer programming dan dengan algoritma branch and price permasalahan penjadwalan penugasan crane dapat diselesaikan. Dari hasil uji coba yang dilakukan pada data NRL dibuktikan adanya peningkatan solusi optimal lebih dari 10%.Kata kunci: Graph, Integer Programming, Branch and Price, Column Generation