Claim Missing Document
Check
Articles

Found 7 Documents
Search

Pengembangan Model Jaringan Syaraf Tiruan untuk Penentuan Kandungan Kimia Biji Kopi Arabika Gayo dengan NIRS Hafiz Fajrin Aditama; I Wayan Budiastra; Slamet Widodo
Warta Industri Hasil Pertanian Vol 36, No 1 (2019)
Publisher : Balai Besar Industri Agro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (890.399 KB) | DOI: 10.32765/warta ihp.v36i1.4767

Abstract

Penelitian ini bertujuan untuk mengembangkan model jaringan syaraf tiruan (JST) terbaik untuk memprediksi kandungan kimia biji kopi arabika Gayo dan memvalidasi model. Data input yang digunakan adalah data principal component (PC) spektra yang terlebih dahulu telah dilakukan pre-treatment data menggunakan multiplicative scatter correction (MSC), Normalisasi (N-1,1), dan turunan pertama Savitzky-Golay (dg1). Model JST menggunakan Multilayer Perceptron (MLP) feed forward neural network dengan algoritma pelatihan dasar Levenberg-Marquard. Penggunaan 10 jumlah neuron lapisan tersembunyi sudah cukup untuk dapat memprediksi kandungan kimia biji kopi Gayo. Kadar air dapat diprediksi dengan model JST menggunakan 8 jumlah PC dan normalisasi (r = 0,96; CV = 1,77%; RPD = 3,79). Kafein dapat diprediksi dengan 8 jumlah PC dan kombinasi normalisasi dengan dg1 (r = 0,98; CV = 2,15%; RPD = 4,44). Karbohidrat dapat diprediksi dengan menggunakan 5 jumlah PC dan dg1 (r = 0,99; CV = 0,27%; RPD = 9,55). Lemak dapat diprediksi dengan menggunakan 8 jumlah PC dan kombinasi MSC dengan dg1 (r = 1; CV = 0,41%; RPD = 19,11). Protein dapat diprediksi dengan menggunakan 5 jumlah PC dan kombinasi MSC dengan dg1 (r = 0,99; CV = 0,84%; RPD = 7,08). 
Studi Model Kinetika Ekstraksi Berbantu Ultrasonik pada Lada (Piper nigrum L.) Anggie Yulia Sari; I Wayan Budiastra; Slamet Widodo
Jurnal Keteknikan Pertanian Vol. 9 No. 3 (2021): Jurnal Keteknikan Pertanian
Publisher : PERTETA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19028/jtep.09.3.127-134

Abstract

Ultrasonic Assisted Extraction (UAE) is used to extract oleoresin from pepper that offer a competitive method compared to maceration. This research was aimed to study and to validate a second order of kinetics model of UAE white pepper extraction that can describe the relationship between oleoresin yield, UAE amplitude, and extraction time. Pepper is milled to particle size of 100 mesh. Then the 200 g of powder of pepper is poured to ethanol of 800 ml (1:4) to subjected to UAE extraction. A maceration process is also carried out as control. Amplitude and extraction times used in the UAE extraction are 45, 60, 75, and 90%; and 45, 60, 75, and 90 minutes. The value of white pepper oleoresin concentration experiment (Ct) with model calculations is closely related to the extraction capacity at saturation (Cs) and the resulting extraction rate constant (k). The value of Cs between 29,24–34,48 g/l and the value of k ​​between l/g.minute. The results from the two Ct obtained produce a correlation coefficient value of 0.85 and the error value between 0,18–14,09 %. The second-order kinetic model developed can be used to predict the yield of UAE-assisted white pepper oleoresin with UAE amplitude limit conditions of 45–90 % and extraction time of 45–90 minutes.
Prediksi Indeks Panen Jambu “Kristal” secara Non Destruktif Menggunakan Portable Near Infrared Spectrometer Ayu Putri Ana; Y. Aris Purwanto; Slamet Widodo
Jurnal Keteknikan Pertanian Vol. 9 No. 3 (2021): Jurnal Keteknikan Pertanian
Publisher : PERTETA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19028/jtep.09.3.103-110

Abstract

“Crystal” guava (Psidium guajava L.) is a climacteric fruit that is generally harvested by farmers based on cultivation experience. In this study, portable 740-1070 nm of near-infrared spectrometer was employed to rapidly predict harvest indices of “crystal” guava, by means of non-contact and non-destructive approach. Samples of guava fruit were collected at days after anthesis (DAS) of 91, 94, 97, and 100. The total number of each sample were 30 fruits. The firmness, soluble solid content, acidity and sugar acid ration were evaluated as quality parameters. Partial least square (PLS) method was utilized for data processing. It was found that Standard Normal Variate (SNV) resulted the best pre-processing for all quality parameters. Performances of best models were demonstrated by coefficient of corraltion (R), standard error of calibration (SEC) and standard error of prediction (SEP), which were respectively 0.88, 6.21, 5.92 for firmness prediction, 0.74, 0.84, 0.79 for soluble solid content prediction, 0.59, 0.19, 0.26 for acidity prediction, and 0.71, 1.21, 1.58 for sugar acid ratio prediction model.
Portable/Handheld NIR sebagai Teknologi Evaluasi Mutu Bahan Pertanian secara Non-Destruktif Widyaningrum Widyaningrum; Yohanes Aris Purwanto; Slamet Widodo; Supijatno; Evi Savitri Iriani
Jurnal Keteknikan Pertanian Vol. 10 No. 1 (2022): Jurnal Keteknikan Pertanian
Publisher : PERTETA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19028/jtep.010.1.59-68

Abstract

Perkembangan teknologi NIR saat ini telah mencapai tingkatan yang lebih tinggi. Peralihan dari analisis kimia yang membutuhkan banyak waktu dan biaya menjadikan teknologi NIR sebagai salah satu pilihan teknologi yang hemat, cepat dan tidak menghasilkan residu limbah. Pada mulanya, NIR dibuat dalam tipe benchtop dengan ukuran yang besar, namun saat ini sudah berkembang menjadi handheld dan portable NIR. Hal ini didasari oleh keperluan untuk melakukan deteksi kandungan bahan pertanian secara real-time di lapangan yang tidak mungkin dilakukan oleh NIR tipe benchtop. Pemanfaatan teknologi handheld/portable NIR banyak diaplikasikan pada bidang pertanian untuk mengukur kadar air, total padatan terlarut, pH, sifat mekanik bahan pertanian dan lain sebagainya. Portable/handheld NIR memiliki dimensi yang kecil dan ringan sehingga memberikan kemudahan dalam melakukan analisis secara langsung dibandingkan dengan menggunakan NIR tipe benchtop yang berukuran besar. Namun demikian, tingkat akurasi, sensitivitas pengukuran, tingkat kebisingan, serta stabilitas pembacaan optik tidak lebih baik jika dibandingkan dengan NIR tipe benchtop. Sehingga potensi pengembangan portable/handheld NIR sebagai instrumen penginderaan berbasis IoT masih terbuka untuk dilakukan.
Sistem Kontrol Tinggi Muka Air Untuk Budidaya Padi - Nurfaijah; Budi Indra Setiawan; Chusnul Arif; Slamet Widodo
Jurnal Irigasi Vol 10, No 2 (2015): Jurnal Irigasi
Publisher : Balai Teknik Irigasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (858.532 KB) | DOI: 10.31028/ji.v10.i2.97-110

Abstract

This research aims to design a control system to keep the water level and soil moisture at a level that is suitable to the plant requirment and determines the optimum water level and soil moisture in each growth phase of paddy field cultivation. The water level control system was formed based on on-off controls system using Arduino Uno ATMega328P microcontroller. When the sensor gives input that the water level is below the set points, then microcontroller will command the irrigation valve to open and the drainage valve to close. The volume and time of irrigation and drainage control are dependent to set point. Set point was controlled based on water regime treatment. Water regime consisted of three treatments, which are wet regime (RB), slightly wet regime (RAB), and dry regime (RK). The research result showed that control system was very effective and efficient in controlling the water regime according to the control algorithms. Besides, the research result showed that the water regimes affected the plant growth, land productivity, and water productivity. Treatment of wet regime (RAB) gave the highest number of tiller (138 tillers), yield 194.7 g/hill (equal to 21 ton/ha with assumption of 30 cm x 30 cm spacing) and water productivity 3.16 kg/m3.
Evaluasi Koefisien Tanaman Padi Pada Berbagai Perlakuan Muka Air Nur Aini Iswati Hasanah; Budi Indra Setiawan; Chusnul Arif; Slamet Widodo
Jurnal Irigasi Vol 10, No 2 (2015): Jurnal Irigasi
Publisher : Balai Teknik Irigasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1567.879 KB) | DOI: 10.31028/ji.v10.i2.57-68

Abstract

Paddy is the main agricultural commodity in Indonesia that needs a large amount of water. Accurate prediction of crop water use is essential to have an efficient irrigation system. The actual evapotranspiration (ETc) is an important factor for estimating water use. Moreover, crop coefficient (Kc) is one of the important parameters in ETc calculation. In this study, Kc of paddy is estimated by using experimental pots under various water tables treatments. The water table is controlled by using mariotte tube and set at -12 cm, -7 cm, -5 cm, -3 cm, 0 cm, and +2 cm from the soil surface. From the experimental sets, the value Kc is calculated by using modified water balance equation and Kalman Filter. The result shows that water table treatment in paddy farming influences soil moisture ( ) and soil temperature (Tsoil). Soil physic parameter fluctuation due to water table treatment affects the plant growth and potential evapotranspiration. Kc value at each water table treatment is different, and varies with plant growth phase. The average Kc for all water table treatments are 0.77-1.27 (initial season), 0.90-1.11 (crop development), 1.10-1.39 (mid-season), and 1.17-1.40 (late season).
Pengembangan Model Jaringan Saraf Tiruan untuk Menduga Emisi Gas Rumah Kaca dari Lahan Sawah dengan berbagai Rejim Air Chusnul Arif; Budi Indra Setiawan; Slamet Widodo; - Rudiyanto; Nur Aini Iswati Hasanah; Masaru Mizoguchi
Jurnal Irigasi Vol 10, No 1 (2015): Jurnal Irigasi
Publisher : Balai Teknik Irigasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (662.168 KB) | DOI: 10.31028/ji.v10.i1.1-10

Abstract

The paper proposes the artificial neural networks (ANN) model to predict methane (CH4) and Nitrous Oxide (N2O) emissions under different irrigation system based on easily measurable environmental biophysics parameters such as soil moisture, soil temperature and soil electrical conductivity. To verify the model, two experiments were conducted in the pot experiments in two different locations. The first location was in the greenhouse of Meiji University, Kanagawa Prefecture, Japan from 4 June to 21 September 2012, and the second location was in water resources engineering laboratory, Department of Civil and Environmental Engineering-IPB from 2 July to 10 October 2014. In each location, there were three different irrigation systems adopted with the System of Rice Intensification (SRI) principles. We called the experiment as SRI Basah (SRI B1 and SRI B2 for the first and second locations, respectively), SRI Sedang (SRI S1 dan SRI S2) dan SRI Kering (SRI K1 dan SRI K2). Each treatment has different water level during growth stages. As the results, the developed ANN model can predict CH4 and N2O emissions accurately with determination coefficients of 0.93 and 0.70 for CH4 and N2O prediction, respectively. From the model, characteristics of those greenhouse gas emissions can be well identified. For the mitigation strategy, SRI B1 and SRI B2 treatments in which the water level was kept at nearly soil surface are the best strategy with highest yield production and lowest GHG emission.