Claim Missing Document
Check
Articles

Found 41 Documents
Search
Journal : Jurnal Gaussian

PERBANDINGAN ANALISIS KLASIFIKASI ANTARA DECISION TREE DAN SUPPORT VECTOR MACHINE MULTICLASS UNTUK PENENTUAN JURUSAN PADA SISWA SMA Rizky Ade Putranto; Triastuti Wuryandari; Sudarno Sudarno
Jurnal Gaussian Vol 4, No 4 (2015): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (528.268 KB) | DOI: 10.14710/j.gauss.v4i4.10236

Abstract

Data mining is a process that employs one or more of Machine Learning techniques to analyze and extract knowledge automatically. Analysis of data mining is to determine the classification of a new data record into one of several categories that have been defined previously, also known as Supervised Learning. Classification Decision Tree is one of the well-known technique in data mining and is one of the popular methods in the decision making process of a case in which the method is obtained entropy criteria, information gain and gain ratio. Classification Support Vector Machine Multiclass (SVMM) is known as the most advanced machine learning techniques to handle multi-class case where the output of the data set has more than two classes or categories. This final project aims to compare the level of accuracy and error rate of Decision Tree classification and prediction majors SVMM for high school students at SMAN 1 Jepara. The total accuracy of 88,57% and 11,43% error rate for the classification decision tree and the total accuracy of 87,14% and the error rate for the classification SVMM 12,86%. Keywords :   Data Mining, Machine Learning, Supervised Learning, Decision Tree, Support Vector Machine   Multiclass
REGRESI SPLINE SEBAGAI ALTERNATIF DALAM PEMODELAN KURS RUPIAH TERHADAP DOLAR AMERIKA SERIKAT Sulton Syafii Katijaya; Suparti Suparti; Sudarno Sudarno
Jurnal Gaussian Vol 2, No 3 (2013): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (652.651 KB) | DOI: 10.14710/j.gauss.v2i3.3668

Abstract

Exchange rate is the ratio of value or price of the currency between two countries. Many factors are thought to affect change in the inflation rate, the activity balance of payments, interest rate differentials, the relative level of income, government control and expectations. Therefore the method that can be used to analyze the exchange rate is needed such as the classical time series analysis (parametric). However the fluctuated data rate doesn’t occupy the assumption of stationarity often. Another alternative for this study is the spline regression. Spline is a nonparametric regression that doesn’t hold any assumption of regression curves. Spline regression has high flexibility and ability to estimate the data behavior which is likely to be different at every point of the interval, with the help of knots. The best model depends on the determination of the optimal point knots, that is has a minimum value of Generalized Cross Validation (GCV). Using data daily exchange rate of the rupiah against the dollar in the period of January 2, 2012 until October 15, 2012, the best spline model in this study is when using 2 to 3 order of approaching knots point, those points are 9512, 9517 and 9522 with the GCV = 1036.38.
IDENTIFIKASI BREAKPOINT DAN PEMODELAN AUTOREGRESSIVE STRUCTURAL CHANGE PADA DATA RUNTUN WAKTU (Studi Kasus Indeks Harga Konsumen Umum Kota Semarang Tahun 1994 – 2010) Mamuroh Mamuroh; Sudarno Sudarno; Hasbi Yasin
Jurnal Gaussian Vol 3, No 1 (2014): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (604.16 KB) | DOI: 10.14710/j.gauss.v3i1.4779

Abstract

Perubahan Indeks Harga Konsumen (IHK) merupakan  indikator ekonomi makro yang cukup penting untuk memberikan gambaran tentang laju inflasi suatu daerah/wilayah serta pola konsumsi masyarakat. IHK Umum Kota Semarang dalam kurun waktu tahun 1994-2010  terlihat mengalami kenaikan terus menerus. Plot data menunjukkan IHK bergerak naik perlahan sebelum bulan Januari 1998 dan setelahnya IHK meningkat secara curam. Untuk mengetahui apakah dalam  kurun waktu tersebut terdapat perubahan struktur pola data dan untuk mengetahui titik-titik patah (breakpoints / titik perubahan struktur)  yang terjadi pada IHK maka perlu dilakukan uji perubahan struktur, hal ini dilakukan dengan pendekatan autoregressive structural change. Hasil penelitian menunjukkan terjadi perubahan struktur dengan titik patah pada t=47 yaitu Januari 1998 bertepatan dengan krisis moneter 1998 dan t=79 yaitu September 2000 bertepatan dengan kenaikan tarif angkutan per 1 September 2000, sehingga data memiliki 3 segmen model. Metode ini sesuai untuk mengidentifikasi titik-titik patah IHK serta dapat digunakan untuk memodelkan IHK Umum Kota Semarang tahun 1994-2010. 
PREDIKSI NILAI KURS DOLLAR AMERIKA MENGGUNAKAN EXPONENTIAL SMOOTHING DENGAN KAJIAN GRAFIK MOVING AVERAGE (MA) DAN EXPONENTIALLY WEIGHTED MOVING AVERAGE (EWMA) (Studi Kasus: Kurs Jual dan Kurs Beli Dollar Amerika) Nova Yanti Gultom; Sudarno Sudarno; Triastuti Wuryandari
Jurnal Gaussian Vol 4, No 4 (2015): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (470.619 KB) | DOI: 10.14710/j.gauss.v4i4.10231

Abstract

The exchange rate is an exchange between two different currencies, it will receive the value or price comparisons between two currencies. It is to determine the predictive value of the exchange rate in the next period is done by using Exponential Smoothing. The quality control can be done by forming graphics controllers. The exchange rate can be done in small shifts, so the exchange rate can use graphics controller Moving Average and Exponentially Weighted Moving Average (EWMA). At the selling rate is found value trial and error alpha is 0,9 and gamma is 0,01 with value of MAPE is 0,37; MAD is 46,94 and value of MSD is 4515,27. At the buying rate is found value trial and error alpha is 0,84 and gamma is 0,01 with value of MAPE is 0,37; MAD is 46,57 and value of MSD is 4524,48. In the graph MA and EWMA most sensitive is the MA control chart so in the weekly chart MA selling rate with w is 5 and L is 2,8 obtainable UCL is 13132,52; CL is 12654, LCL is 12175,47. On the weekly chart MA buying rate with w is 5 and  L is 2,8 obtainable UCL is 13002,08; CL is 12528, LCL is 12053,91. Then the possibility of the exchange rate for the next period will be increased or decreased to the rupiah.Keywords: Exchange Rate, Exponential Smoothing, Graphic control, Moving Average (MA), Exponentially Weighted Moving Average (EWMA).
PENENTUAN MODEL DAN UKURAN KINERJA PROSES ANTRIAN PADA UNIT PELAYANAN TEKNIK DINAS PUSKESMAS LIMBANGAN KABUPATEN KENDAL Fatkhan Arissetya; Sugito Sugito; Sudarno Sudarno
Jurnal Gaussian Vol 3, No 3 (2014): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (335.937 KB) | DOI: 10.14710/j.gauss.v3i3.6447

Abstract

The UPTD (Unit Pelayanan Teknik Dinas) of Local Government Clinic of Limbangan in Kendal Regency is the only health-service in Limbangan Sub-district although there is another health-service such as doctors and midwifes. Since there are many people coming to the Local Clinic of Limbangan, it causes quite long queue. Therefore, it is needed to analyze the queuing model to finding out the system of the activity measure, so it can be concluded the queuing description and the service. If the distributrion of the arrival or the service is poisson or exponential, so the model is Markovial (M). However, if the distribution is not poisson or exponential, so the model is General (G). The queuing model of outpatients includes Regristrtion-Counter (M/G/1):(GD/∞/∞) , Medical Service (M/M/3):(GD/∞/∞)  and Medicine-Counter (M/G/1):(GD/∞/∞). Meanwhile, the queuing model of hospitalized patients covers Hospitalized Rooms (M/M/16):(GD/∞/∞) and Payment Counter (M/G/1):(GD/∞/∞). It has been found out the best queue from the analysis in UPTD Local Government Clinic of Limbangan that is registration counter because the service time is quick and there are few queuing patients, so it won’t be hoarding
KETEPATAN KLASIFIKASI STATUS KERJA DI KOTA TEGAL MENGGUNAKAN ALGORITMA C4.5 DAN FUZZY K-NEAREST NEIGHBOR IN EVERY CLASS (FK-NNC) Atika Elsadining Tyas; Dwi Ispriyanti; Sudarno Sudarno
Jurnal Gaussian Vol 4, No 4 (2015): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (379.616 KB) | DOI: 10.14710/j.gauss.v4i4.10127

Abstract

Unemployment is a very crucial problem that always deal a developing country and affected a national foundation. It used two methods for classifying a employment status on productive society in Tegal City on August 2014, the methods are C4.5 Algorithm and Fuzzy K-Nearest Neighbor in every Class (FK-NNC). C4.5 Algorithm is a way of classifying methods from data mining that use to construct a decision tree. FK-NNC is another classification technique that predict using the amount of closest neighbor of K in every class from a testing data. The predictor variables that used on classifying an employment status are neighborhood status, sex, age, marriage status, education, and a work training. To evaluate the result of classification use APER calculation. Based on this analysis, classification of employment status using C4.5 Algorithm obtained APER = 28,3784% and 71,6216% of accuracy, while FK-NNC methods obtained APER = 21,62% and 78,38% of accuracy. So, it can be concluded that FK-NNC is better than C4.5 Algorithm. Keywords: Classification, C4.5 Algorithm, Fuzzy K-Nearest Neighbor in every Class ­(FK-NNC), APER
ANALISIS JALUR TERHADAP FAKTOR-FAKTOR YANG MEMPENGARUHI INDEKS PRESTASI KUMULATIF (IPK) MAHASISWA STATISTIKA UNDIP Malik Hakam; Sudarno Sudarno; Abdul Hoyyi
Jurnal Gaussian Vol 4, No 1 (2015): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (414.358 KB) | DOI: 10.14710/j.gauss.v4i1.8146

Abstract

Education is a priority thing everyone today. Education is implemented in learning, by learning humans can develop all the potential there is in him. Learning is always related to the achievement of learning, because learning is a process while learning achievement is the result of the learning process. In the course of learning achievement levels measured by GPA (Grade Point Average). Factors that influence GPA among allowance, age, value of the UN Senior High School, many organizations, the internet long, long time to learn. Path analysis is the development of multiple regression which the independent variables affect the dependent variable not only directly but also indirectly affect. Based on the results of the discussion of the factors that affect the GPA is concluded that the allowance has indirect effect of   -0,211, age has  direct effect of age at 0,1901, the UN has direct effect of 0,258, many organizations have a direct effect of -0,3582 and has indirect effect of -0,132, the  internet long direct effect of -0,2376 and has indirect effect of -0,038, long learning has a direct effect of 0,2344. Keywords: Education, GPA, Path analysis, Direct effect, Indirect effect
ANALISIS JALUR TERHADAP FAKTOR-FAKTOR YANG MEMPENGARUHI INDEKS PRESTASI KUMULATIF (IPK) MAHASISWA STATISTIKA UNDIP Malik Hakam; Sudarno Sudarno; Abdul Hoyyi
Jurnal Gaussian Vol 4, No 2 (2015): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.v4i2.8581

Abstract

Education is a priority thing everyone today. Education is implemented in learning, by learning humans can develop all the potential there is in him. Learning is always related to the achievement of learning, because learning is a process while learning achievement is the result of the learning process. In the course of learning achievement levels measured by GPA (Grade Point Average). Factors that influence GPA among allowance, age, value of the UN Senior High School, many organizations, the internet long, long time to learn. Path analysis is the development of multiple regression which the independent variables affect the dependent variable not only directly but also indirectly affect. Based on the results of the discussion of the factors that affect the GPA is concluded that the allowance has indirect effect of   -0,211, age has  direct effect of age at 0,1901, the UN has direct effect of 0,258, many organizations have a direct effect of -0,3582 and has indirect effect of -0,132, the  internet long direct effect of -0,2376 and has indirect effect of -0,038, long learning has a direct effect of 0,2344. Keywords: Education, GPA, Path analysis, Direct effect, Indirect effect
OPTIMALISASI PORTOFOLIO MENGGUNAKAN CAPITAL ASSET PRICING MODEL (CAPM) DAN MEAN VARIANCE EFFICIENT PORTFOLIO (MVEP) (Studi Kasus: Saham-Saham LQ45) Mardison Purba; Sudarno Sudarno; Moch. Abdul Mukid
Jurnal Gaussian Vol 3, No 3 (2014): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (573.138 KB) | DOI: 10.14710/j.gauss.v3i3.6483

Abstract

Investment is planting some funds to get profit. However, there is a positive relationship between risk and return that is High Risk High Return. So, the investor seeks to maximize expected return using portfolio optimization. The nature of the stock fluctuates over time, often times it poses a risk to lose money. In the science of finance, the fluctuations of stock returns is known as volatility. Then the stock volatility measurement uses Exponentially Weighted Moving Average (EWMA). Methods of Capital Assets Pricing Model (CAPM) is used for the selection of the best stocks of the nine sectors LQ45. Portfolios are formed of nine sectors were weighted using the Mean-Variance optimal Efficient Portfolio (MVEP). The weight placed on the largest fund shares at IMAS 25.12%, amounting to 19.53% BDMN, BWPT by 6.40%, 9.75% for INCO, SMCB by 7.72%, amounting to 9.37% INDF, BKSL for 2.27%, 16.87% and TLKM of MAPI by 2.98%. Based on analysis, volatility measurement of IMAS, TLKM and BDMN especially using EWMA. Risk measurement tool used for stock portfolio is Value at Risk (VaR) and Risk measurement tool used for stocks is Component Value at Risk (CVaR). With a confidence level of 95% and an investment of IDR 100.000.000 the loss investment using VaR for one day in the future is IDR 1.799.824. Meanwhile, if using CVaR then the maximum loss investment for the day ahead is IDR 1.523.000,73.
PEMILIHAN MODEL REGRESI LINIER MULTIVARIAT TERBAIK DENGAN KRITERIA MEAN SQUARE ERROR Aminuddin Aminuddin; Sudarno Sudarno; Sugito Sugito
Jurnal Gaussian Vol 2, No 1 (2013): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (913.495 KB) | DOI: 10.14710/j.gauss.v2i1.2125

Abstract

Regresi linier multivariat merupakan salah satu metode analisis regresi yang melibatkan lebih dari satu variabel respon, dengan model regresinya adalah . Penggunaan banyak variabel dalam analisis regresi linier multivariat dapat menjadi hal yang menyulitkan untuk menentukan besarnya pengaruh variabel prediktor terhadap variabel respon. Oleh karena itu, dilakukan penyeleksian variabel guna mendapatkan model regresi terbaik. Prosedur seleksi variabel dengan kriteria Mean Square Error (MSE) merupakan suatu metode untuk mendapatkan model terbaik dengan cara mencari model yang memiliki nilai MSE terkecil dari seluruh model yang mungkin
Co-Authors Abdul Hoyyi Achmad Tavip Junaedi Ade Lenty Hoya Adimulya Nurrahman Aditya Eka Laksana Adiwirman Adiwirman Afianti Sonya Kurniasari Agung Santoso Agus Sudrajat Ahmad Reza Aditya Ajeng Arum Sari Alan Prahutama Aldila Khairina Sissandhy Alfita Rakhmayani Amin Nursudi Aminuddin Aminuddin Anak Agung Istri Sri Wiadnyani Angga Saputra Desti Anik Waryanti Anissa Pangastuti Anya Amabell Syukuri Arifah Wulansari Ariffandita Nuri Muttaqin Ashri Febrina Rahmasari Atika Elsadining Tyas Avida Anugraheni Avida Nugraheni C. Ayu Ambarsari bagus aji Bambang Wasito Adi Bayu Ariawan Bayyina Zidni Falah Boedi Setya Rahardja Budi Warsito Chiarakania Chaniago Cut Nur Aisyah Darari Rahma Lalita Dedy Haryanto Despriyanti Despriyanti diah novitasari Diah Safitri Dian Ika Pratiwi Dita Oktavia Ningrum Dwi Ispriyansti Dwi Ispriyanti Dwi Safrudin Dwi Siwi Handayani Eka Triakuntini Endang Dewi Masithah Endro Sutrisno Erna Puspitasari evelyn wijaya Farid Abdu Salam Fathimatuzzahra Syahrozad Nuroqi Fatkhan Arissetya Febriane Paulina Makalew Feri Setyowibowo Fifi Puspita Fuad Muhammad Galih Maraseta W H Prasaja Galuh Ayu Prameshti Gusti Rusmayadi Harini Harini Hasbi Yasin Hasmuri Hasmuri Huriyah Huriyah Ibnu Athoillah Irawan Wisnu Wardhana Johan Adi Wicaksana Joko Purnomo Julidian Julidian Julius E. Tenda Junaidi Junaidi Khalida Hanum Khersna Bayu Sangka Khresna Bayu Sangka Kikis Dinar Yuliesti Kristiani Kristiani Kussigit Santosa Lintang Afdianti Nurkhasanah Lulut Fadhilah Lundu Bontor Sihite Luthfi Rachma Dita M. Husni Arifin Maidiah Dwi Naruri Saida Malik Hakam Maluw, Fandel Mamuroh Mamuroh Mardison Purba Mario Moningka Martha Ng Mintasih Indriayu Mintasih Indriayu Moch. Abdul Mukid Mohammad Al Hazmi Mohammad Rama Fadillah Soeroso Muhammad Amin Muhammad Fachri Maulana Mustafid Mustafid Nailatis Shofia Nany Yuliastuti Nesvi Intan Oktajayanti Nonik Brilliana Primastuti Nourma Yulia Nova Yanti Gultom Novi Melawati Nur Aeniatus Solekakh Nur Musrifah Rohmaningsih Pradana Sahid Akbar Pranata Anggakara Priska Rialita Hardani Putu Handoko Murti Putu Jaya Permana Qomaruddin, Mochammad Ramdhan Febrianto Rangkang, Jeanely Retza Bahtiar Anugrah Ridha Ramandhani Ririn Khoiriyah Rita Rahmawati Rizka Asri Brilliani Rizky Ade Putranto Rukun Santoso Rumbayan, Rilya S. Suripin Salman Alfarisy Totalia Sandy Kristiara Sarwanto Sarwanto Satrio Adi Wibowo Sekar Niken Kartika Sheny Nurul Aini Shofiyatul Afidah Sholikhah Septiarti Khusnul Wardatus SITI NURLATIFAH Slamet Effendy Yusuf Sudenroy Mentang Sugito Sugito Suhardjo Suhardjo Sukrismiati Sukrismiati Sulton Syafii Katijaya Sunarto Sunarto Suparti Suparti Supriyanto Supriyanto Sutrisno Anggoro Syanne Pangemanan Tampanatu P. F. Sompie Tarina Rahmayani Tarno Tarno Tatik Widiharih Taufan Fahmi Taufik Dani Testian Yushli Ana Tiani Wahyu Utami Titin Nurfiatin Tri Retnaning Nur Amanah Triastuti Wuryandari Veronika Ellyana Vica Nurani Wahyu Nugraha Widha Sunarno WINARTI WINARTI Winda Rosiana Pratiwi Wulan Merdeka Sari Yanuar Luqman Yovina Mulyadi Yuciana Wilandari