Rahmat Gernowo
Departemen Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro, Semarang

Published : 25 Documents
Articles

Found 25 Documents
Search

ANALISA DATA CURAH HUJAN STASIUN KLIMATOLOGI SEMARANG DENGAN MODEL JARINGAN SYARAF TIRUAN Arif, F M; Gernowo, Rahmat; Setyawan, Agus; Febrianty, D
BERKALA FISIKA Vol 15, No 1 (2012): Berkala Fisika
Publisher : BERKALA FISIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (106.795 KB)

Abstract

The major purpose of this research was to applying artificial neural network to predicting rainfall in Semarang climatology station and occurs its accuration. One ofartificial neural network method is back propagation artificial neural network. Withheuristic technique its optimizing to train algorithmic faster and improving net works. Weused rainfall data in 2000-2009 from Semarang climatology station. Artificial neuralnetwork modelling planned in MATLAB R2008b programme. The best model or net viewsfrom correlation level between net?s output, observation data and RMSE point whichproduced by the net. The results shown the best network has 5 neurons in input?s layer, 10in hidden layer and 1 neuron in output layer. Its performance has learning data 66,7%,testing data 33,3%, learning rate 0,7 and momentum 0,4 which has correlated around70,72% to observation data with RMSE point 141,55. The best network will use topredicting rainfalls in 2010, its correlation is 88,43% and its RMSE points is 83,76 tillJuly. Its better than what BMKG has which only reach 84,63% correlation points and87,21 RMSE points.Keywords:  Artificial neural network, optimizing, correlation, RMSE
INTERPRETASI STRUKTUR BAWAH PERMUKAAN DATA GAYABERAT MENGGUNAKAN ALGORITMA JARINGAN SARAF TIRUAN STUDI KASUS DAERAH PANAS BUMI UNGARAN, JAWA TENGAH Utami, Ratih Rundri; Setyawan, Agus; Gernowo, Rahmat
YOUNGSTER PHYSICS JOURNAL Vol 5, No 4 (2016): Youngster Physics Journal Oktober 2016
Publisher : Jurusan Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Artificial neural networks have been used in an application of geophysical such as seismic, electromagnetic, restivity, and gravity. In this study, artificial neural network system used is the method of propagation of gravity to produce anomalies corresponding to the desired anomalies on the geothermal area of Mount Ungaran, Central Java. In the training process to produce the best weight with 4 hidden layer with a correlation coefficient of 0.99 and the testing process using the results of the best training with a correlation coefficient of 0.97 and a yield value that resembles Bouguer anomaly in the research area., so it can be seen under the surface of the structure with the results of the best network where there is a high density value of 2.70 to 2.80 g/cm3 in lava basalt as geothermal systems Mount Ungaran. Density 2.40 to 2.80 g/cm3 Low contained in the surface area of Mount Ungaran with the majority of sedimentary rocks of andesitic pyroclastic products of Mount Ungaran Young.
PEMBUATAN SISTEM KENDALI POSISI AUTOFOKUS EKSPERIMEN LENSA DENGAN MOTOR LANGKAH Gunadi, Isnain; Gernowo, Rahmat; Adi, Kusworo
BERKALA FISIKA 2015: Berkala Fisika Vol. 18 No. 4 Tahun 2015
Publisher : BERKALA FISIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (503.217 KB)

Abstract

The automatic lens experiment with stepper motor position control has been made. Main component of this device are stepper motor which move the lens and screen. Microcontroller is contens the programs of motor movement controller. The screen contain of Light Dependent Resistor (LDR) as voltage sensor. This image will focused when the voltage in the screen is maximum. The result of test show that the automatic measurement is more accurate than manual measurement.Keywords: Auto-Fokus, LDR, IPMC, LSW, EAPs, VCM
IDENTIFIKASI FOKUS MIKROSKOP DIGITAL MENGGUNAKAN METODE OTSU Putranto, Ari Bawono; Adi, Kusworo; Gernowo, Rahmat
BERKALA FISIKA 2014: Berkala Fisika Vol. 17 No. 4 Tahun 2014
Publisher : BERKALA FISIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (607.126 KB)

Abstract

A study to identify focus on a digital microscope has been done using a threshold value of the object microscope image obtained by Otsu method. Microscope image of the object captured by the change from a maximum to a minimum distance between the object and the microscope objective lens to record the amount of movement of a motor stepper and calculates the Otsu threshold value on each image. Based on data from a Otsu threshold value of each microscope image of the object to the changes within the object can be inferred the existence of a relationship between the position of an object to focus the microscope with the image of the threshold value that is increasingly the focus of an image , the image of the Otsu threshold values ??obtained are also getting smaller. In this study done by testing two samples as objects of microscope that single hair samples and samples collection of several hairs were each placed on a microscope glass slide. Data collection and observation results show that for a single hair samples obtained object focus Otsu threshold value T = 97 and sample an object consisting of a collection of some of the hair is obtained Otsu threshold value T = 127. But the testing of two samples showed differences influenced by the ratio between the number of pixels on the image and the background image of an object caused by the influence of the intensity of the light source of the microscope. Keywords: Focus Identification, Digital Microscope, Otsu Threshold
PERANCANGAN SISTEM PENDUKUNG KEPUTUSAN PENERIMAAN TARUNA BARU MENGGUNAKAN BASIS DATA FUZZY - STUDI KASUS DI AKPELNI SEMARANG Hidayat, Eko Nur; Gernowo, Rahmat; Sugiharto, Aris
Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik Vol 1, No 1 (2013): PROSIDING SEMINAR NASIONAL SAINS DAN TEKNOLOGI 4 2013
Publisher : Prosiding Seminar Nasional Sains Dan Teknologi Fakultas Teknik

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Proses  seleksi  penerimaan  taruna  baru  di  Akademi  Pelayaran  Niaga  Indonesia (AKPELNI)  terdapat beberapa ketidakpastian, antara  lain nilai ujian seleksi potensi akademik,  nilai  kesamaptaan,  kesehatan,  tinggi  badan  serta  wawancara  setiap periode tidak pasti, tergantung dari jumlah pendaftar dan daya tampung. Logika fuzzy merupakan  salah  satu metode  penyelesaian masalah  yang mulai  berkembang  pada tahun  1965.  Logika  fuzzy  menggunakan  dasar  teori  himpunan  fuzzy  dimana keberadaan  suatu  elemen  dalam  himpunan  ditentukan  oleh  derajat  keanggotaan elemen  tersebut.    Dengan  sifat  keanggotaan  himpunan  fuzzy  tersebut  maka  logika fuzzy menjadi  lebih  fleksibel  (mampu beradaptasi dengan perubahan-perubahan dan ketidakpastian yang menyertai permasalahan) serta memiliki  toleransi  terhadap data yang  tidak  tepat.  Penelitian  ini  bertujuan  membangun  sebuah  sistem  pendukung keputusan  untuk  menentukan  calon  taruna  yang  diterima  dan  tidak  diterima menggunakan  basis  data  fuzzy  menyesuaikan  dengan  jumlah  pendaftar  dan kapasitas/kuota.    Dengan  memberikan  input  berapa  kapasitas/kuota    yang  akan diterima serta standar nilai  maka panitia penerimaan taruna baru dapat memutuskan siapa yang diterima dan yang tidak diterima.  Kata Kunci :Logika Fuzzy, penerimaan taruna baru, system pendukung keputusan
SISTEM PENGENALAN WAJAH DENGAN METODE EIGENFACE DAN JARINGAN SYARAF TIRUAN (JST) Mulyono, Tri; Adi, Kusworo; Gernowo, Rahmat
BERKALA FISIKA Vol 15, No 1 (2012): Berkala Fisika
Publisher : BERKALA FISIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (200.796 KB)

Abstract

The development of security systems led to the development of face recognition system using image processing techniques.Research was conducted to identify a face image automatically with theeigenface method. The method used is a normalization, eigenface, neural network training and testing.Eigenface is used to reduce the dimension vector face becomes much simpler (eigen vector). Eigen vectorsobtained are used by back propagation neural network training process and recognition. Then do thetesting process using the image of a face that has not been used in the training process.The results showed the use of neural networks and eigenface to face recognition can give a goodaccuracy. The system is able to produce an acuracy of 84.6% with a FAR (False Acceptance Rate) =16.2%, FRR (False Rejection Rate) = 20% and EER (Equal Error Rate) = 0.3.Keywords : face recognition, eigenface, eigen vector, neural network
ANALISIS KORELASI CITRA DATA PRIMER DENGAN DATA SEKUNDER MENGGUNAKAN CITRA GRID ANALYSIS AND DISPLAY SYSTEM (GRADS Jatmiko, Wahyu; Gernowo, Rahmat
YOUNGSTER PHYSICS JOURNAL Vol 3, No 1 (2014): Youngster Physics Journal Januari 2014
Publisher : Jurusan Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Indonesia has 13 (thirteen) the threat of catastrophic earthquakes, tsunamis, floods, landslides, volcanic eruptions, extreme waves and abrasion, extreme weather, drought, forest fires and land, buildings and residential fires, epidemics and disease outbreaks, failed technology, and social conflict. Research related to hydrometeorological predictable by doing a variety of approaches, one using remote sensing methods provided by the World Meteorological Organization (WMO) with the advantages of data is not affected by the location of the location such as the presence of a cliff, lake, or mountain.In the study image correlation analysis of primary data with secondary data using imagery Grid Analysis And Display System (Grads) have been analyzed the correlation between the image of the primary data with secondary data using Grid software image Analisys And Display System. The data used are rainfall, air temperature, and humidity, all of the data is the data on average monthly. Primary data were obtained from Badan Meteorologi, Klimatologi dan Geofisika (BMKG) Semarang and secondary data obtained by downloading from the National Oceanic And Atmospheric Administration (NOAA) website.The value of the correlation between the primary data with secondary data for rainfall data indicate a strong relationship , occurs when the amount of rainfall maximum correlation value is 0,67 and the value of correlation in the event the minimum rainfall is 0,79 . On air temperature data the value of the correlation time of maximum rainfall is 0.69 and the value of correlation in the event of rainfall minimum is -0,37 . Correlation values for air humidity data at the time of maximum precipitation is 0,01 and the magnitude of the correlation value at the time the minimum rainfall is 0,95 .Keywords : GrADS , disaster, correlation, extreme weather, dryness
ANALISIS PERUBAHAN IKLIM BERBAGAI VARIABILITAS CURAH HUJAN DAN EMISI GAS METANA (CH4) DENGAN METODE GRID ANALYSIS AND DISPLAY SYSTEM (GRADS) DI KABUPATEN SEMARANG Kusumawardhani, Ismi Dian; Gernowo, Rahmat
YOUNGSTER PHYSICS JOURNAL Vol 4, No 1 (2015): Youngster Physics Journal Januari 2015
Publisher : Jurusan Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Global climate change as the implications of global warming caused by greenhouse gas increases from time to time. Methane (CH4) is a greenhouse gas that causes the greenhouse effect and has the effect of 20-30 times greater than carbon dioxide. The rate of CH4 emissions to the atmosphere is the fastest among other greenhouse gases.The research was conducted by analyzing climate change using the data of precipitation, air temperature, and methane emissions. Data of Ungaran - kabupaten Semarang precipitation obtained from Badan Meteorologi, Klimatologi dan Geofisika (BMKG) Climatological Station Semarang. Globally available data of precipitation and air temperature, that is downloaded from the website National Oceanic and Atmospheric Administration (NOAA). While the emission data of methane (CH4) is obtained from Badan Lingkungan Hidup (BLH) Central Java with data that covers an area of Central Java. To determine the existence of climate change in the research area of data analysis is carried precipitation and air temperature during the last 30 years. The method used is the method of Grid Analysis and Display System (GrADS) that can be used for processing and visualizing the earth science data.The results of this study, the increase in precipitation and air temperature every year in a period of 30 years in kabupaten Semarang. The average amount of precipitation every year is obtained by 1579.86 mm. Precipitation in Central Java region shown by the pattern of monsoon rainfall. The average maximum precipitation in January, while the minimum in August. The average air temperature increase annually by 0.014oC or 0.051% every year. Similarly, the amount of methane emissions (CH4) in all parts of human activity in the region of Central Java has increased every year. The average increase of CH4 emission obtained annually by 14.99 Gg or 1.36%. On average generated methane emissions from human activities annually by 1104.54 Gg.Keywords: Global warming, climate change, GrADS, precipitation, methane emissions (CH4)
EVALUASI MODEL JARINGAN SYARAF TIRUAN METODE BACKPROPAGATION UNTUK PREDIKSI IKLIM EKSTRIM DENGAN KORELASI CURAH HUJAN DAN TINGGI MUKA LAUT DI SEMARANG Pangestu, Siti Yuniar; Gernowo, Rahmat
YOUNGSTER PHYSICS JOURNAL Vol 4, No 1 (2015): Youngster Physics Journal Januari 2015
Publisher : Jurusan Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Global warming is an event average temperature rise of the atmosphere, ocean, and land. Atmosphere temperature changes cause the physical conditions of the atmosphere becomes unstable, causing anomalies weather parameters that cause climate change. The impact of climate changes is increasing frequency of natural disasters or extreme weather, changes in rainfall patterns, and rising sea level rise. To minimize disaster prediction is carried out by making modeling with artificial neural network method, algorithm of backpropagation models.The research was conducted in Semarang, using data from rainfall, precipitation, temperature, cloud cover, and sea level rise in 2002 until 2012.Artificial neural network modeling was used Matlab R2010a. Network training by using one unit of input layer, two hidden layer units, and one unit of output layer. The first hidden layer with 10 neurons and the second hidden layer used 5 neurons.The best results on the training and testing of the network by using the parameter learning rate 0.3 and a momentum 0.6. The results obtained in the training get a percentage value of correlation is 79.0% and in the testing process to get the percentage correlation is 77.5%. Keywords: Artifical Neural Network, Backpropagation, extreme climate, rainfall, sea level rise
PEMODELAN BAWAH PERMUKAAN DAERAH PANASBUMI KALIULO BERDASARKAN DATA RESISTIVITAS KONFIGURASI SCHLUMBERGER DENGAN ALGORITMA JARINGAN SYARAF TIRUAN-BACKPROPAGATION Muviana, Frysca Putti; Setyawan, Agus; Gernowo, Rahmat
YOUNGSTER PHYSICS JOURNAL Vol 5, No 4 (2016): Youngster Physics Journal Oktober 2016
Publisher : Jurusan Fisika, Fakultas Sains dan Matematika, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research used secondary data configuration Schlumberger geoelectric method in the area of geothermal manifestations Kaliulo Mount Ungaran to implement the use of artificial neural network algorithm in geophysical this case to obtain the actual value of the thickness and resistivity. In this artificial neural networks do two processes, namely the training and testing, the training using synthetic data and on testing using field data Then in training the neural network produced the best architectural which is used train resilient propagation (train rp) with three hidden layers with each neuron in the hidden layer consist of 300 neuron, this architecture will be used in testing. The output of the test data is value of the thickness and true resistivity which can be modeled. Result modeling of data processing from ANN is almost the same with IPI2WIN, MSE value obtained is equal to 0.10519 and 0.088304 respectively on the thickness and resistivity actually. The result of 3D model shows the lower part of the earth's subsurface its rock consists as following: topsoil, clay, volcanic breccias, tuff and limestone.