Claim Missing Document
Check
Articles

Found 23 Documents
Search

PREDIKSI TINGKAT LOYALITAS PELANGGAN MENGUNAKAN ALGORITMA C4.5 BERBASIS BACKWARD ELIMINATION Syaifuddin Syaifuddin; Purwanto Purwanto; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 2 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (85.294 KB)

Abstract

Customer loyalty is one of the capital to maintain the company's business strategy in the long run. In thelast two decades of Customer Relationship Management (CRM) has grown to become one of the majortrends in marketing, both in education and in the world practice. CRM is a comprehensive businessstrategy of a company that enables the company to effectively manage the company's relationship with thecustomer. Automatic feature selection algorithm is used with the aim of selecting a subset of the featuresin the dataset in order to reach the maximum level of accuracy in classification. The use of data miningtechniques to predict customer loyalty combines C4.5 algorithm with feature selection BackwardElimination. C4.5 algorithm based backward elimination can improve the accuracy in the prediction ofcustomer loyalty, compared with C4.5 algorithm without feature selection. C4.5 algorithm basedbackward elimination generate income per month attribute, type of subscription, registration fee, the costof the bill, and the old subscription
PREDIKSI PENYAKIT KANKER PAYUDARA MENGGUNAKAN ARTIFICIAL NEURAL NETWORK Supriyadi Supriyadi; Vincent Suhartono; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 1 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (615.246 KB)

Abstract

Breast cancer is a malignant tumor that begins in the cells of the breast. A malignant tumor is a group of cancer cells that can grow and invade surrounding tissues or spread (metastasize) to distant areas of the body. This disease occurs almost entirely in women, but men can also get it. The hypothesis of this study is the method of Artificial Neural Network which is expected to increase the accuracy in the prediction of breast cancer patients. Results of testing to be performed by measuring method and compared with the Artificial Neural Network algorithm C.45. The dataset taken from UCI with a total number of 699 and it is found benign tumors or as many as 458 (65.5%) whereas malignant cancer or 241 (34.5%), with 699 data and 10 attributes which are processed are the thickness of breast cancer, cell size, cell shape, adhesion Margina, single epi cell size, cell nuclei, bland chromatin, normal nucleoli, myth, and the class of breast cancer benign and malignant breast cancer. From various experiments conducted with the Artificial Neural Network algorithm best results are with 500 Cycle Training and Learning Rate 0.5 to obtain an accuracy value of 95.57%, 93.00% presicion, recall 94.62% and AUC 0.986 with time 38s. So based on grouping by comparing the accuracy and AUC values of experiments shows that the algorithm has a classification Artificial Neural Network with a very good, and when compared with the C4.5 algorithm with the result 0.963 is better than Artificial Neural Network algorithm. To be able to increase the level of accuracy of previous studies that only 93.00% to 95.57% gain research or an increase of 2.57%. For computing the level of accuracy with 94.42% and the standard reached by using computational experiments that change the value of Learning Rate it generated 95.57%, an increase of 1.42%.
PREDIKSI HARGA KOMODITAS EMAS DAN BATUBARA DI PASAR DUNIA DENGAN ALGORITMA SUPPORT VECTOR MACHINE Eko Pudjianto; Purwanto Purwanto; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 1 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (798.184 KB)

Abstract

Changes in commodity prices of gold and coal in the world market is very influential on the Indonesian government's policy, especially in the country's revenue in the foreign exchange sector. By predicting the price of gold and coal in the world market expected the government to determine important strategy especially in the fields of mining, trade (exports), Energy and Mineral Resources in Indonesia. By applying the method of SVM (Support Vector Machine) can be found a configuration that is able to predict the prediction of gold and coal prices in the coming period.Data processing using SVM algorithm based on k - fold validation , C (cost) and its kernel , then searched the level RMSE (root mean square error) is the smallest. RMSE is the smallest design that is used in predicting the price of gold and coal. Gold commodity price prediction method with RMSE (root mean square error) is at best 43 509 + / - 37 487 with data input 7 (seven) months earlier , k - fold 10 , C (cos ) of 0.3 and using a kernel -type dot . So the commodity price forecast gold in the world market for the period December 2013 amounted to U.S. $ 1,298.33 and for coal commodities with RMSE (root mean square error) is best at 3,185 + / - 3,591 with data input 2 (two) months earlier , k - 10 fold , C (cost) of 0.3 and using a kernel-type dot. So the prediction of coal commodity prices on the world market for the period from December 2013 is U.S. $ 81.58
PENERAPAN PEMBOBOTAN ATRIBUT PADA ALGORITMA NAIVE BAYES UNTUK ANALISIS SENTIMEN REVIEW APLIKASI ANDROID DARI GOOGLE PLAY Aris Tri Jaka Harjanta; Abdul Syukur; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 11 No 1 (2015): Jurnal Teknologi Informasi CyberKU Vol.11 no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (410.429 KB)

Abstract

Fast growing technology corelate with the demand of faster information access. Recently, the information technology dominate by android (open source) based smartphone, it makes many application developer build the application base on this operating system. With so many existing applications, users need a reference to see the application in general, although it has been provided a facility user review for this application, large number of users review are make the user difficult to be able read one by one. Thus it is necessary to know how the sentiment classification of users on the application. In this experiment, algorithms naïve bayes classifications applied are shown to have good performance on large data and have proven reliable in a variety of domains. As well as adding a attribute weighting use algoritm of weight by correlation, weight by chi squered statistical and weight by SVM on the data, so expect a good accuracy of the sentiment analysis android application to use in Indonesian sentiment.
METODE FASTICA UNTUK REDUKSI DATA DIMENSI TINGGI PADA ANALISIS SENTIMEN PARIWISATA KOTA SEMARANG MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE Mochamad Amry Assiva; Heru Agus Santoso; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 15 No 1 (2019): Jurnal Teknologi Informasi CyberKU Vol. 15, no 1
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (534.402 KB)

Abstract

Some communities have a voice attractions via Twitter. The opinion can be used as sentiment analysis to determine the ratings of a tourist attraction. Results of sentiment analysis is expected to assist in the improvement and evaluation of the attraction. In related research sentiment analysis previously used linear dimension reduction method, but has the disadvantage produce a linear combination of all the features that will have difficulty if dealing with data that is non-linear. Therefore, in this study used methods of non-linear dimension reduction, namely FastICA in order to improve the accuracy of Support Vector Machine classifier that can handle high-dimensional and non-linear data. This study uses the Indonesian language text contained on the social networking site Twitter. Validation is done by using a 10-Fold Cross Validation. While the measurement accuracy is measured by the Confusion Matrix and ROC curves. Results application of dimension reduction FastICA gain accuracy of 92.90% and the AUC 0.9157 which means the accuracy of 0.95% better than on Support Vector Machine itself, is proven to increase the accuracy of the SVM algorithm on the non-linier tweet data of attractions in the city of Semarang that can be classified by both in positive and negative class.
PENGGABUNGAN METODE U-CONTROL CHART DAN METODE AUTOMATIC CLUSTERING DIFFERENTIAL EVOLUTION UNTUK PENENTUAN JUMLAH KLASTER PADA METODE K-MEANS Ahmad Ilham; Romi Satria Wahono; Catur Supriyanto
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 2 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (743.081 KB)

Abstract

Penentuan jumlah klaster K-Means adalah masalah utama yang paling popular di kalangan peneliti data mining karena sulitnya menentukan informasi dari data secara apriori akibatnya dimungkinkan hasil klaster tidak optimal dan cepat terjebak ke dalam minimum lokal. Metode pengklasteran otomatis dengan pendekatan evolutionary computation (EC) dapat menyelesaikan masalah K-Means. Metode automatic clustering differential evolution (ACDE) adalah salah satu metode pendekatan EC yang terkenal karena dapat menangani data berdimensi tinggi dan meningkatkan kinerja penglasteran K-Means dengan nilai validitas klaster yang rendah. Namun, proses penentuan ambang batas aktivasi k pada ACDE masih bergantung pada pertimbangan pengguna sehingga proses penentuan jumlah klaster K-Means belum efisien. Pada penelitian ini, masalah ACDE akan diperbaiki menggunakan metode u-control chart (UCC) yang terbukti efisien digunakan untuk mengatasi masalah penentuan jumlah klaster K-Means secara otomatis. Model yang diusulkan dievaluasi menggunakan kumpulan data terkini seperti data sintetik dan data real (iris, glass, wine, vowel, ruspini) dari repositori UCI serta menggunakan davies bouldin index (DBI) dan cosine similarity measure (CS) sebagai metode evaluasinya. Hasil dari penelitian ini menunjukkan bahwa metode UCC berhasil meningkatkan metode K-Means dengan nilai objektif DBI dan CS terendah masing-masing sebesar 0.470 dan 0.577. Nilai objektif DBI dan CS terendah adalah metode terbaik. Model yang diusulkan memiliki kinerja pengklasteran lebih unggul setelah dibandingkan dengan metode terkini lainnya seperti metode genetic clustering for unknown k (GCUK), dynamic clustering pso (DCPSO) dan automatic clustering approach based on differential evolution algorithm combining with K-Means for crisp clustering (ACDE) untuk hampir seluruh evaluasi fungsi objektif DBI dan CS. Dapat disimpulkan bahwa, metode UCC mampu memperbaiki kelemahan metode ACDE pada penentuan jumlah klaster K-Means dengan menentukan ambang batas aktivasi k secara otomatis.
OPTIMASI KLASIFIKASI STATUS GIZI BALITA BERDASARKAN INDEKS ANTROPOMETRI MENGGUNAKAN ALGORITMA NAIVE BAYES CLASSIFICATION ADABOOST Achmad Ridwan; Catur Supriyanto; Pulung Nurtantio Andono
Jurnal Teknologi Informasi - Cyberku (JTIC) Vol 14 No 2 (2018): Jurnal Teknologi Informasi CyberKU Vol.14 no 2
Publisher : Program Pascasarjana Magister Teknik Informatika, Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (310.243 KB)

Abstract

Body Mass Index (BMI) is commonly used as a measure to assess the nutritional status of infants. If there are two babies whose weight and height are the same may have different nutritional status. If it happens then the use BMI to measure nutritional status less relevant. Anthropometric measurement tool to be very instrumental for determining the nutritional status. The guidelines for determining the nutritional status Anthropometric parameters are selected and recommended which includes an assessment of the age, weight, height. On the contrary, along with the development of technology, increasing the amount of data that requires some methods to process and draw conclusions from such data and information. NBC algorithm is an algorithm of decision tree method has good performance in dealing with the classification of Toddler Nutritional Status based index Anthropometry, but NBC has a weakness in the class imbalance. Adaboost one boosting methods that could reduce imbalances class by giving weight to the level of classification Error which may alter the distribution of data. The use of Adaboost with reason this method can improve the accuracy in the process of classification and prediction by means generate a combination of a model, select the model that has the greatest weight. These experiments will apply the NBC algorithm used for classification of Toddler Nutritional Status based index Anthropometry and will be increased again by Adaboost method for being able to overcome the imbalance class thus increasing the probability value of each class and improve accuracy, it also lowers Error Classification. While that would be classified are five classes: normal, fat, very fat, thin, or very thin. The results of the experiment were obtained from NBC method to an accuracy of 88.60% and a classification Error of 11.40%, while the method by Adaboost (NBC + Adaboost) to an accuracy of 88.84% and 11.16% of the classification Error. So we can conclude NBC with Adaboost algorithm implementation on the Classification of Toddler Nutritional Status based index Anthropometry proved capable of overcoming the class imbalance and improve accuracy also lowers Error Classification.
Pengaruh Circuit Training Terhadap Motivasi Santri Putra Dalam Melaksanakan Aktivitas Olahraga di Pondok Pesantren Nurul Jadid Khoirul Mawahib; Catur Supriyanto; Made Pramono; Fatkur Rohman Kafrawi
Journal Innovation In Education Vol. 2 No. 1 (2024): Maret : Journal Innovation in Education (INOVED)
Publisher : STIKes Ibnu Sina Ajibarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59841/inoved.v2i1.892

Abstract

Sport for all is a movement that emerged to bring awareness to the importance of sport for all. This movement is based on the community's need for sports regardless of all kinds of differences, including for someone who is in an Islamic boarding school environment. This research aims to determine the effect of Circuit Training exercises on students' motivation in carrying out sports activities at the Nurul Jadid Islamic Boarding School, Probolinggo. The method used in this research is a quasi-experiment or quasi-experiment with a one group Pretest and Posttest Design research design. In this research, the number of samples used was 15 respondents using a purposive sampling technique or determining certain criteria. The instrument in this research uses a questionnaire. Then the data that has been obtained and collected will be analyzed using descriptive tests with the help of the SPSS VERSION 25 application program. Next, the data will be tested using the Kolmogorov-Smirnov normality test, this test is used to find out whether the data obtained in the research is normally distributed or not. Then, to test the hypothesis, use the T Paired Sample Test to determine the effect of providing treatment in each treatment group. After analyzing the research data. The results of the research show that there is a significant influence on Circuit Training exercises on students' motivation in carrying out sports activities at the Nurul Jadid Islamic Boarding School, Probolinggo.
Pengaruh Latihan Pliometrik Standing Jump Over Barrier dan Squat Depth Jump Terhadap Kemampuan Rebound Bola Basket Ragil Ar Rasyid; Dwi Cahyo Kartiko; Himawan Wismanadi; Achmad Widodo; Irmantara Subagio; Catur Supriyanto
Jurnal Ilmu Keolahragaan Undiksha Vol. 12 No. 3 (2024): October
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/jiku.v12i3.80292

Abstract

Rendahnya kemampuan rebound dalam permainan bola basket mempengaruhi tingkat performa dan prestasi yang ada dalam cabang olahraga basket. Penelitian ini dilaksanakan dengan tujuan untuk memperoleh data yang signifikan dan perbedaan hasil tentang pengaruh latihan Pliometrik Standing Jump Over Barrier dan Squat Depth Jump terhadap kemampuan rebound dan vertical jump dalam bola basket. Penelitian ini merupakan penelitian kuantitatif, pengambilan data dilakukan melalui pengamatan secara langsung dan pelatihan di lapangan untuk mengetahui beberapa faktor-faktor penting guna menunjang ketahap selanjutnya. Populasi dalam penelitian ini adalah 20 atlet putra. Kelompok 1 berjumlah 10 atlet dan kelompok 2 berjumlah 10 atlet. Metode pengumpulan data yang digunakan berupa test. Dalam penelitian ini nilai suatu tes dari dua kelompok eksperimen yang sudah dipasangkankan pada masing-masing individunya, maka dalam ujinya menggunakan t-test dengan rumus pendek (short methode). Hasil dari penelitian ini pelatihan Standing Jump Over Barrier dan pelatihan Squat Depth Jump memberikan pengaruh yang signifikan. Pada Uji Anava F hitung tidak ada perbedaan yang signifikan di antara Standing Jump Over Barrier dengan Squat Depth Jump. Tetapi Standing Jump Over Barrier lebih baik dari Squat Depth Jump.
Survei Kepuasan Konsumen Terhadap Kualitas Pelayanan Antares Fitness & Aerobic Surabaya Brighaza Gayoeh Arsyanadi; Catur Supriyanto; Himawan Wismanadi; Soni Sulistyarto
NUSANTARA SPORTA: Jurnal Pendidikan dan Ilmu Keolahragaan Vol. 3 No. 02 (2025): NUSANTARA SPORTA: Jurnal Pendidikan dan Ilmu Keolahragaan
Publisher : CV. Nusantara Sporta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.2024/ns.v3i02.2025_P233-247

Abstract

Penelitian ini bertujuan untuk mengetahui tingkat kepuasan konsumen pusat kebugaran Antares Fitness & Aerobic Surabaya terhadap kualitas pelayanan yang diterimanya melalui 5 faktor yaitu tangibles, responsiveness, assurance, empathy, reliability. Deskriptif kuantitatif serta dengan metode survei dan kuesioner. Populasi penelitian 20 responden dengan teknik purposive sampling. Uji validitas instrumen menggunakan korelasi product moment dan mendapatkan hasil dari 30 pertanyaan dapat dikatakan valid apabila nilai korelasi ≥ r tabel 0,3598 atau probabilitas output SPSS ≤ 0,05. Uji reliabilitas instrumen dengan menggunakan rumus Alpha Cronbach dan diperoleh hasil koefisien reliabilitas antara 0,00 – 0,200. Analisis deskriptif diuraikan dalam bentuk persentase. Berdasarkan hasil perhitungan data penelitian secara keseluruhan tingkat kepuasan konsumen terhadap kualitas pelayanan yaitu sebanyak 6 orang (30%) masuk dalam kategori kepuasan Sangat Tinggi, sebanyak 2 orang (10%) kategori kepuasan Tinggi, 1 orang (5%), dan 11 orang (55%) kategori kepuasan Sangat Rendah. Kesimpulan tingkat kepuasan konsumen terhadap kualitas pelayanan Antares Fitness & Aerobic Surabaya dalam kategori kepuasan Sangat Rendah dengan presentase sebesar 55% yaitu 11 orang