Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 DAFTAR ISI
HAL
PERUBAHAN POLA PENYEBARAN KADAR AIR MEDIA TANAM ARANG SEKAM DAN PERTUMBUHAN TANAMAN KANGKUNG DARAT (Ipomoea reptans Poir.) PADA PEMBERIAN AIR SECARA TERUS MENERUS DENGAN IRIGASI TETES Asep Sapei dan Irma Kusmawati
1~6
PENERAPAN BEBERAPA MODEL EVAPOTRANSPIRASI DI DAERAH TROPIKA (Studi Kasus di Sub DAS Ciriung, Cidanau Hulu) Application of Some Evapotranspiration Models at Tropical Region Slamet Suprayogi, Budi Indra Setiawan, Lilik Budi Prasetyo
7~13
EVALUASI MUTU KETIMUN JEPANG (Cucumis sativus L.) BERDASARKAN BENTUK DENGAN PERCEPTRON (Quality Evaluation of Cucumber (Cucumis sativus L.) Based on Its Shape Using Perceptron) Suroso, Fadlilah Maulani
14~21
PERSAMAAN KORELASI KADAR AIR KESEIMBANGAN UNTUK LADA Agus Supriatna Somantri Balai Penelitian Tanaman Rempah dan Obat
22~28
PENGEMBANGAN ALGORITMA IMAGE PROCESSING UNTUK MENDUGA KEMASAKAN BUAH MANGGIS SEGAR (Development of Image Processing Algorithm for Determining the Maturity of Fresh Mangosteen) Diding Suhandy, Usman Ahmad
29~38
APLIKASI JARINGAN SYARAF TIRUAN DAN ANALISIS KOMPONEN UTAMA UNTUK SORTASI MENTIMUN (The Application of Artificial Neural Network and Principal Component Analysis for Cucumbers Selection and Grading) Kudang B. Seminar, Marimin dan Teguh Ferianto
39~51
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 PERUBAHAN POLA PENYEBARAN KADAR AIR MEDIA TANAM ARANG SEKAM DAN PERTUMBUHAN TANAMAN KANGKUNG DARAT (Ipomoea reptans Poir.) PADA PEMBERIAN AIR SECARA TERUS MENERUS DENGAN IRIGASI TETES Asep Sapei1 dan Irma Kusmawati2
Abstract Drip/trickle irrigation is an irrigation method, which gives high efficiency, high effectivity and assures high productivity/yield. This method, is often used for horticulture and vegetable crops. The objective of this research is to study the effect of drip irrigation by continuous water application using 1 and 2 emitters on water distribution and crop growth. The results show that irrigation water by using 2 emitters was spread horizontally more, gave taller crops and more leaves than that using 1 emitter. In general, the effect of continuous water application was better than intermittent water application. Key words : Drip/trickle irrigation, continuous water application
1 2
Staf pengajar Bagian Teknik Tanah dan Air, Jurusan Teknik Pertanian FATETA-IPB Alumni Jurusan Teknik Pertanian FATETA-IPB
1~6
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 PENERAPAN BEBERAPA MODEL EVAPOTRANSPIRASI DI DAERAH TROPIKA (Studi Kasus di Sub DAS Ciriung, Cidanau Hulu) Application of Some Evapotranspiration Models at Tropical Region Slamet Suprayogi1, Budi Indra Setiawan2, Lilik Budi Prasetyo
Absract Potential evapotranspiration (ETp) can be calculated by ETp models using climatological parameters. Among them, the Penman model is most frequently used for ETp estimation. The Penman models requires five climatic parameters: temperature, relative humidity, wind, saturation vapor pressure, and net radiation. It also uses complicated unit conversions and lengthy calculation. There are a simple models such us: Jensen - Haise models, Hargreaves, Radiation, Turc’s, and Makkink’s model. These models that requires only two climatic parameters, temperature and incident radiation. The purpose of this study is to find the simplest and effective model among seven models (Penman models, Penman-Monteith, Jensen- Haise, Hargreaves, Radiation, Turc’s, and Makkink’s models). Such model will be found by comparing of those seven models of calculated ETp based on daily climatic data collected in one year using automatic weather station located at the Ciriung sub cachtment.The error indicators to evaluate the effectiveness of the ETp models are Root Mean Square Error (RMSE), Mean Average Error (MAE), and Logaritmic RMSE (LOG), and the determination coefficient (R2). The result show that Turc model is the most effective along with Hargreaves and Jensen-Haise models. Key words : Evapotranspiration models, Climatic parameters.
1 2
Mahasiswa Pascasarjana IPB Staf Pengajar Pascasarjana IPB
7~13
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 EVALUASI MUTU KETIMUN JEPANG (Cucumis sativus L.) BERDASARKAN BENTUK DENGAN PERCEPTRON (Quality Evaluation of Cucumber (Cucumis sativus L.) Based on Its Shape Using Perceptron) Suroso1, Fadlilah Maulani2
Abstract Quality evaluation of cucumber usually is done manually based on visual appearances. Increasing demand on high quality cucumber of export, has led to greater effort to develop methods that would enhance the precision of the evaluation. In this study, the combination of a perceptron artificial neural network and an image processing method applied to evaluate the cucumber quality. Perceptrons are the neural networks were intended to be computational models of the retina. The objective of this study was to develop an algorithm of cucumber quality evaluation based on their shapes using the image processing and perceptron. Cucumber images were processed by an image processing algorithm, which is coded in Visual BASIC 6.0. The images of cucumber were divided into 84 rectangular grids. Each rectangular has a binary value (0 or 1); value of 0 belongs to the background, while value of 1 belongs to the cucumber. In the perceptron, binary number values of 84 rectangular were used as the inputs. The perceptron had three nodes of output, which was representing by bipolar number. The combinations of three bipolar numbers represent quality of the cucumber. The A, B, and C quality grades represented by (1,-1,-1), (-1,1,-1) and (-1,-1,1) respectively. Sixty data were used fro training of the perceptron, while thirty data were used to validity the perceptron. The perceptron was trained to adjust their weights. The weights were initialized as 0, the learning rate was 0.5 and the threshold in the transfer function was 0.4. The training was converging after 10 iterations. The validation results showed that the perceptron could predict well the cucumber quality with the prediction rate of 86.7 %. Keywords : Perceptron, neural network, cucumber, image processing, quality evalution
1 2
Staf Pengajar Jurusan Teknik Pertanian, Fateta IPB
14~21
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 PERSAMAAN KORELASI KADAR AIR KESEIMBANGAN UNTUK LADA Agus Supriatna Somantri Balai Penelitian Tanaman Rempah dan Obat
Abstrak Kadar air keseimbangan atau EMC (Equilibrium of Moisture Content) merupakan faktor penting yang berperan dalam proses pengeringan dan penyimpanan. Penelitian ini dilakukan di Laboratorium Pasca Panen, Balai Penelitian Tanaman Rempah dan Obat dari tanggal 2 sampai dengan 30 Juni 2001. Penelitian ini bertujuan untuk menentukan model sorpsi isotermi yang sesuai untuk lada, sehingga model yang terpilih bisa diaplikasikan pada proses pengeringan dan penyimpanan di lapangan. Metode yang digunakan adalah metode statik pada temperatur 40, 45 dan 50oC serta rentang aktivitas air (Aw) 0.20 – 0.64. Model-model yang dipilih adalah model Henderson, model Chung-Pfost, model Oswin dan model Halsey dengan menggunakan metode numerik. Hasil penelitian menunjukkan bahwa model matematik dua parameter (temperatur dan kelembaban) telah dapat memberikan hasil yang baik dibandingkan dengan data percobaan. Model Halsey memiliki ketepatan yang terbaik di antara keempat model yang dipilih, sehingga lebih jauh model ini dapat dipergunakan untuk memprediksi sorpsi isotermi untuk lada hitam dan model Oswin untuk lada putih. Kata kunci : Sorpsi isotermi, lada, model korelasi, Kadar air keseimbangan.
22~28
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 PENGEMBANGAN ALGORITMA IMAGE PROCESSING UNTUK MENDUGA KEMASAKAN BUAH MANGGIS SEGAR
(Development of Image Processing Algorithm for Determining the Maturity of Fresh Mangosteen) Diding Suhandy1 and Usman Ahmad2 Abstract One of important factor in post harvest handling is cropping at correct maturity level. Fruit maturity relates to age pluck vegetable or fruit to be harvested have old enough or not yet. Grading represent dissociation of product becomes some group quality of pursuant to maturity level, size measure, color, form, heavy, texture, aroma and freedom from foreign object or dirt. The objective of this research is to predict the maturity of fresh mangosteen by means of an image processing algorithm. In this study, four stages of maturity (120, 126, 132 and 138 days after flowering) were used as objects with 30,37,40,40 samples for each stages of maturity.The images data were collected using a CCD Camera and then processed by an image processing program to analyze the relationship between the maturity and the color, size, and shape of fruits. The result showed linear relationship between the maturity and the color index (RGB) with a coefficient determination of 0.8159 for blue, but not for red and green. As a result, the developed image processing program can be used to classify the fresh mangosteens based on their maturity using blue index with 70% precicion. Key words : Mangosteen, image processing, color index, maturity
1 2
Staf Pengajar Jurusan Teknik Pertanian, Universitas Lampung Staf Pengajar Jurusan Teknik Pertanian, Institut Pertanian Bogor
29~38
Jurnal KETEKNIKAN PERTANIAN, Vol.17, No.2, Agustus 2003 APLIKASI JARINGAN SYARAF TIRUAN DAN ANALISIS KOMPONEN UTAMA UNTUK SORTASI MENTIMUN
(The Application of Artificial Neural Network and Principal Component Analysis for Cucumbers Selection and Grading) Kudang B. Seminar1, Marimin2 dan Teguh Ferianto3
Abstract This paper discusses the development of a software prototype for cucumbers selection and grading by applying Standard Backpropagation Neural Network (SBPNN) and Principal Component Analysis (PCA). The prototype has been tested to recognize cucumbers based on their shapes (i.e. straight or non-staright cucumbers). Cucumbers’ images data were expressed in eight position of rotational axes: 0o, 45o, 90o, 135o, 180o, 225o, 270o, 315o. The implemented system can recognized 100 % of all tested straight cucumbers and 75% of all tested non-straight cucumbers. The performance implemented SBPNN was also compared to another system called Probabilistic Nural Network (PNN). The results shows that SBPNN is better than PNN in time execution; however PNN is better than SBPNN in generalization or recognition accuracy. Keywords : Backpropagation Neural Network, Principal Component Analysis, cucumber sortation.
1
Jurusan Teknik Pertanian, Fakultas Teknologi Pertanian IPB Jurusan Teknologi Industri Pertanian, Fakultas Teknologi Pertanian IPB 3 Jurusan Ilmu Komputer, Fakultas Matematika dan Ilmu Pengetahuan Alam IPB 2
39~51
