Jurnal Keteknikan Pertanian
Not a member yet
627 research outputs found
Sort by
Macro-Nutrient Prediction of Paddy Field Soil Using Artificial Neural Network and NIR Spectroscopy
Full text linkUnderstanding soil fertility, influenced by macronutrients like nitrogen, phosphorus, and potassium, is essential for adaptive agriculture implementation based on various soil conditions. Near-infrared spectroscopy technology provides non-destructive, rapid soil property measurements without chemicals, applicable both in-field and in-laboratory. However, the wide NIR spectrum range and neural network complexities can hinder Artificial Neural Network (ANN) training and inference, leading to time and resource inefficiency, especially without sophisticated computing devices. This study examines data reduction methods to enhance ANN performance in predicting soil macronutrients using NIR spectra. Multiple Linear Regression (MLR) and Principal Component Analysis (PCA) were applied to select wavelengths from the 1000–2500 nm for ANN input, comparing their performance. About 237 NIR reflectance data from paddy soil were transformed into absorbance data. MLR used forward selection to identify wavelengths with correlations higher than 0.9, while PCA selected wavelengths corresponding to the loading factor peaks for each principal component. These selected wavelengths served as inputs for the ANN model. The ANN’s performance was assessed using correlation and determination coefficients, RMSE, RPD, and model consistency. For nitrogen, the PCA+ANN model with reflectance spectra performed better (RPD 2.4-4.8) than the MLR+ANN model (RPD 2.2-2.6) using fewer wavelengths (5-9 for PCA+ANN vs. 9-12 for MLR+ANN). For phosphorus estimation, the PCA+ANN model also excelled (RPD 2.3-7.0 vs. 2.3-2.4) with fewer wavelengths (4-7 vs. 7). For potassium estimation, the PCA+ANN model showed superior performance (RPD 4.3-9.5 vs. 4.2-4.4), using the same number of wavelengths (4-8 vs. 4-6)
Physical Characteristics of Flakes with Variations Kepok Banana Bud (Musa paradisiaca Linn.) and Mocaf Flour
Full text linkYellow Kepok banana buds (KBB) are well-known for their high dietary fiber content and prospective use as functional food additives. High fiber consumption has been linked to diabetes prevention. The production of flakes derived from KBB has the potential to facilitate individuals in incorporating high-fiber food items into their daily diets. Nevertheless, the utilization of just Yellow KBB flour yields flakes that are deemed undesirable by consumers due to their firm consistency and deep hue. The substitution of Yellow KBB flour with a combination of wheat flour and mocaf has the potential to enhance the physical characteristics of the resulting flakes. The objective of this study is to assess the physical attributes of flakes derived from KBB. This particular flake was produced using a series of five distinct formulations. The present study employed a completely randomized design (CRD) with three replications. The formulas consist the proportions of wheat flour (WF), mocaf flour (MF), and Yellow Kepok banana bud (KBB). The following are the five ratios: (100%:0%:0%), (50%:50%:0%), (50%:37.5%:12.5%), (50%:25%:25%), and (50%:37.5%:12.5%). The water absorption, swelling ability, texture, and color of flakes produced from wheat, mocaf, and KBB flour were examined. The F2 sample, consisting of a composition of 50% wheat flour, 37.5% mocaf flour, and 12.5% yellow KBB flour, exhibited the highest water absorption value (63.19%) among all the samples. In addition to this, F2 can be characterized as a specimen exhibiting a relatively low level of hardness (1.63 N) and a correspondingly low fracture value (2.08 N). The F2 flakes had a much higher brightness value (37.06) in comparison to the other samples used yellow KBB flour
Manufacturing and Feasibility Test of Duck Egg Incubator Machine with Automatic System for Small Industrial Scale
Full text linkPenelitian ini bertujuan untuk membuat dan menguji kelayakan mesin penetas telur bebek sistem otomatis, dengan kandungan bahan lokal (TKDN) 100% dan terjangkau oleh industri kecil penetasan telur bebek. Penetasan telur bebek terus mengalami perkembangan seiring dengan kemajuan teknologi dan meningkatnya kebutuhan telur bebek dan daging bebek potong. Inovasi mesin penetas telur bebek sistem otomatis merupakan upaya untuk membantu industri kecil penetasan telur bebek untuk meningkatkan produksi yang lebih efsien dan ergonomis. Dalam penelitian ini pembuatan mesin penetas telur bebek sistem otomatis menggunakan melalui tahapan antara lain identifikasi masalah, perumusan dan penyempurnaan ide, pemilihan konsep rancangan, analisis dan pembuatan gambar kerja, pembuatan prototipe alat, pengujian dan penyempurnaan prototipe alat, kemudian dilakukan uji kelayakan kestbalinan suhu dan kelembaban, dan uji daya tetas yang dilaksanakan di industri kecil penetasan telur bebek UD.Putra Jember, Puger, Jember. Hasill dari penelitian ini yaitu mesin penetas telur bebek sistem otomatis kapasitas 5000 butir telur, dengan sumber pemanas LPG. Pada uji kelayakan menujukkan fluktuasi suhu dan kelembaban yang stabil dan menghasilkan daya tetas 82%.This research aims to design and test the feasibility of an automatic system duck egg incubator, with 100% local ingredients (TKDN) and affordable for small duck egg hatching industries. Duck egg hatching continues to develop along with advances in technology and the increasing need for duck eggs and cut duck meat. The innovation of the automatic duck egg incubator machine is an effort to help the small duck egg hatching industry to increase production in a more efficient and ergonomic manner. In this research, the creation of an automatic duck egg incubator machine uses stages including problem identification, formulation and refinement of ideas, selection of design concepts, analysis and creation of working drawings, manufacture of tool prototypes, testing and refinement of tool prototypes, then feasibility tests for temperature stability and stability are carried out. humidity, and hatchability tests carried out at the small duck egg hatchery industry UD. Putra Jember, Puger, Jember. The result of this research is an automatic duck egg incubator with a capacity of 5000 eggs, with an LPG heating source. The feasibility test showed stable temperature and humidity fluctuations and produced a hatchability of 82%
Application of Corn Starch and Red Galangal Coating to Extend the Shelf Life of Chrysanthemum Flowers (Chrysanthemum morifolium)
No full textChrysanthemum (Chrysanthemum morifolium) has high economic value. However, fresh Chrysanthemums are perishable and have a short shelf life. High respiration and microorganisms are the main causes of the decline in the quality of chrysanthemums after harvest. The fungus Puccinia horiana causes white rust disease on the leaves which were carried when the flowers are harvested and stored for distribution. Corn starch as an edible coating material combined with red galangal extract was expected to reduce damage by these two factors. The purpose of the research was to determine the best concentration of corn starch and red galangal extract to extend the shelf life of fresh chrysanthemum edible flower. The starch concentration chosen was based on the viscosity of the coating solution which can be applied by spraying and produces the solidness and smallest diameter of droplet. The concentration of 2% corn starch coating solution was chosen to be the best solution concentration for coating. In application, the coating solution used was 2% corn starch combined with 1% and 2% red galangal extract, with spraying done once and twice. The results of the study showed that the L2S2 formulation (2% galangal concentration with spraying 2 times) was the best treatment. This treatment can maintain flower water content at 86.02%, weight loss 19.00%, L value 34.50o, Hue value 347.04o on the 6th day of storage with a panelist assessment of a score of 3.25 (freshness, color, aroma). As a comparison, flowers without treatment (control) were still accepted by panelists up to the 3rd day of storage with a score of 3.01, more than 3 days the score was less than
Penundaan Kematangan Buah Mangga Arumanis Pada Berbagai Umur Petik Menggunakan Etilen Adsorber
Full text linkMangga termasuk buah tropika yang bernilai ekonomi tinggi untuk diekspor. Salah satu teknologi yang dapat digunakan yaitu etilen adsorber yang diaplikasikan sesuai dengan umur petik mangga dan durasi penundaan kematangan (fase green life) yang dibutuhkan untuk ekspor. Penelitian ini bertujuan untuk mengkaji pengaruh penggunaan etilen adsorber dan fase green life mangga terhadap mutu fisik dan eating quality mangga Arumanis pada umur petik yang berbeda, yaitu 100 (P1) dan 110 (P2) HSBM (Hari Setelah Bunga Mekar). Etilen adsorber bag (EAB) diapliaksikan pada buah mangga yang dikemas menggunakan plastik LDPE dengan berat 1.000±50g. Fase green life yang dikaji adalah 32 dan 48 hari sejak EAB di aplikasikan. Selama dalam fase green life, mangga disimpan pada suhu 13±2℃. EAB dikeluarkan dari kemasan sesuai dengan fase green life, kemudian mangga dibiarkan pada suhu ruang untuk proses pematangan alami dan dilanjutkan sampai kondisi mangga tidak dapat diterima oleh konsumen. Hasil penelitian menunjukkan bahwa aplikasi EAB mampu mempertahankan greenlife buah mangga dengan skenario umur simpan 32 hari. Mangga siap di konsumsi sejak hari pertama EAB dilepas. Waktu dari matang sampai dengan mangga tidak diterima panelis yaitu 4 hari, dengan demikian lama waktu 36 hari dari simpan sampai tidak layak dikonsumsi. Eating quality yang dinyatakan dengan oBrix, menunjukkan mangga yang ditunda dengan EAB menghasilkan nilai 12,3oBrix pada P1 dan 17,3oBrix pada P2.Arumanis mango is a tropical fruit with high economic value for export. One of the technologies that can be used is ethylene adsorber which is applied according to the picking date of mango and the duration of the delay in ripeness (green life phase) required for export. The objective of this study was to examine the effect of using ethylene adsorber and mango green life phase on the physical quality and eating quality of Arumanis mangoes at different picking dates, thats 100 (P1) and 110 (P2) HSBM (Days After Flowers Bloom). Ethylene adsorber bag (EAB) was applied to mangoes packaged using LDPE plastic weighing 1,000±50g. The green life phase studied was 32 and 48 days since the EAB was applied. During the green life phase, mangoes were stored at 13±2℃. EAB was removed from the packaging according to the green life phase. The results showed that the EAB application could maintain the green life of mangoes with a shelf-life scenario of 32 days. Mangoes were ready to be consumed from the first day EAB was released. The time from ripe until the panelists did not accept the mangoes was four days, thus the length of time was 36 days from storage until they were not accepted for consumption. Eating quality expressed in oBrix, showed that mangoes delayed with EAB yielded a value of 12,3oBrix for P1 and 17.3oBrix for P1, while the control yielded values of 13,7oBrix for P1 and 16.8oBrix for P2
Optimization of Nata de Coco Industrial Liquid Waste Processing Using Membrane-Based Ultrafine Bubble Diffuser
Full text linkIndustri nata de coco menghasilkan limbah cair yang apabila langsung dibuang ke badan air (sungai) tanpa pengolahan terlebih dahulu akan berpotensi mencemari lingkungan sekitar. Hasil pengujian laboratorium menunjukkan bahwa parameter BOD 1145 mg/L, COD 1737 mg/L, dan TSS 206 mg/l jauh berada diatas ambang batas yang ditetapkan oleh pemerintah. Tujuan dari penelitian ini adalah menentukan kondisi optimum perlakuan fine bubble dan micro bubble terhadap limbah cair nata de coco dalam menurunkan nilai karakteristik limbah cair nata de coco. Penelitian ini dilakukan menggunakan metode ekperimental dengan ampel uji sebanyak 40 liter dan 60 liter. Data yang dikumpulkan melalui pengamatan langsung antara lain DO, TDS, pH, Suhu yang diukur setipa 2 jam sekali sedangkan data yang dikumpulkan melalui pengujian dilaboratorium BOD, COD, dan TSS yang diuji setiap 12 jam dan 24 jam. Data selanjutnya diolah menggunakan metode Taguchi dengan tujuan memperolah optimasi perlakukan fine bubble terhadap perubahan kharakteristik limbah cair nata de coco. Hasil penelitian menunjukkan bahwa kondisi optimum terdapat pada perlakuan fine bubble dengan lama aerasi 24 jam dan volume 40 liter. Penurunan BOD didapatkan persentase penurunan terbaik sebesar 94% atau menjadi 68 mg/L. Penurunan COD didapatkan persentase penurunan terbaik sebesar 93% dan atau menjadi 121 mg/L dan TSS didapatkan persentase penurunan terbaik sebesar 69% atau menjadi 77 mg/L. Hasil tersebut sudah sesuai dengan Peraturan Menteri Lingkungan Hidup Republik Indonesia Nomor 5 Tahun 2014 Tentang Baku Mutu Air Limbah.The nata de coco industry produces liquid waste which, if thrown directly into water bodies (rivers) without prior processing, has the potential to pollute the surrounding environment. Laboratory test results show that the parameters BOD 1145 mg/L, COD 1737 mg/L, and TSS 206 mg/l are far above the thresholds set by the government. The aim of this research is to determine the optimum conditions for fine bubble and micro bubble treatment of nata de coco liquid waste in reducing the characteristic values of nata de coco liquid waste. This research was carried out using experimental methods with test samples of 40 liters and 60 liters. Data collected through direct observation include DO, TDS, pH, temperature which are measured every 2 hours, while data collected through laboratory testing of BOD, COD and TSS which are tested every 12 hours and 24 hours. The data was then processed using the Taguchi method with the aim of optimizing the fine bubble treatment for changes in the characteristics of nata de coco liquid waste. The research results showed that the optimum conditions were found in the fine bubble treatment with an aeration period of 24 hours and a volume of 40 liters. The best percentage reduction in BOD was found to be 94% or 68 mg/L. COD reduction obtained the best percentage reduction of 93% and/or became 121 mg/L and TSS obtained the best percentage reduction of 69% or became 77 mg/L. These results are in accordance with the Regulation of the Minister of Environment of the Republic of Indonesia Number 5 of 2014 concerning Waste Water Quality Standard
Performance profile of Cold Storage Using R32 as Refrigerant for Traditional Fishing Boat with Photovoltaic as Energi Source
Full text linkThis paper discusses the performance of cold storage using R32 refrigerant. R32 is one of the recommended refrigerant with the main advantage low ODP and GWP (Global Warming Potential) value of around 0 and 675. However, because of this refrigerant classified as a new refrigerant, the implementation is limited to air conditioning and heat pump. In this paper, R32 will be tested for cold storage applications. The cold storage performance will be studied about the achieved temperature, power consumption, cooling capacity and Coefficient of Performance without load. The testing was carried out in 2 ways, cold storage testing on a lab scale and direct testing on a 5 GT fishing boat. The performance results show that both tests on a lab scale and tests directly on a fishing boat without a load can reach a cold storage room temperature of -18oC. Meanwhile, the compressor power consumption supplied by photovoltaic is 0.653-0.776 kW. Based on the test results, shows that R32 has a positive possibility of being applied to cold storage
Development and Performance Evaluation of Cyber-Physical Refrigeration System for Fishing Vessel: Optimizing Fisheries Operations through Real-Time Monitoring and Cyber-Physical System Integration
No full textThe rapid advancement of technology in the contemporary era has inspired individuals to contemplate more efficient and appropriate technologies, that potentially offer substantial benefits for many applications. Among these progressive technologies are the Internet of Things (IoT) and Cyber-Physical Systems (CPS). This research aims to develop a cyber-physical system for the supervision and regulation of refrigeration systems for fishing vessels via smartphones. This approach is seamlessly integrated into the fishing industry to enhance operational efficiency and optimize the preservation of fishery products. We have successfully applied IoT and CPS technologies for effective monitoring and control of the refrigeration system. In evaluating the accuracy of this application, two sensors were employed for analysis, specifically the primary temperature sensor and the reference temperature sensor. The principal yardstick for assessing measurement accuracy in this research is the standard deviation in sensor readings. The research findings reveal that the measured data from the primary temperature sensor and reference temperature sensor demonstrates a minimal standard deviation, signifying a high level of measurement precision. The expected outcome of implementing this system is the capability to regulate and monitor the refrigeration system, thus enabling fishermen to minimize losses in the fishery production process and elevate the quality of fishery products
Non-Destructive Prediction of Chemical Content in Palm Oil Fruit Using Near-Infrared Spectroscopy and Artificial Neural Network
Full text linkKadar minyak dan air adalah kriteria kualitas penting dari crude palm oil (CPO) yang dihasilkan dari pengolahan buah kelapa sawit. Biasanya, kandungan tersebut ditentukan menggunakan metode kimia di laboratorium. Metode ini memakan waktu, prosedur panjang, dan bersifat merusak. Beberapa upaya telah dilakukan untuk menentukan kadar minyak dan air buah kelapa sawit secara non-destruktif menggunakan beberapa metode, termasuk Near-Infrared Spectroscopy (NIRS), tetapi hasilnya belum memuaskan. Penelitian ini bertujuan untuk mengevaluasi Artificial Neural Network (ANN) dan metode NIRS untuk memprediksi kadar minyak dan air buah kelapa sawit secara non-destruktif. Sampel yang digunakan adalah buah kelapa sawit dengan sepuluh tingkat kematangan yang diambil dari perkebunan di Bogor. Reflektansi sampel diukur dengan spektrometer NIR-Flex 500 pada panjang gelombang 1000-2500 nm. Setelah itu, kadar minyak dan air ditentukan menggunakan metode kimia. Beberapa pre-treatment spektrum NIR, yaitu normalisasi, turunan pertama savitzky-golay, kombinasi keduanya, dan standard normal variate, diterapkan. Analisis multivariat seperti PLS dilakukan, dan hasil dari factor component (FC) dijadikan input untuk model ANN. Hasilnya menunjukkan bahwa metode terbaik untuk memprediksi kadar minyak adalah kombinasi turunan pertama savitzky-golay dan pre-treatment normalisasi menggunakan PLS-ANN dengan 20 FC (R2=0.99; SEC=0,58%, RPD = 29.89; CV = 2.47%). Untuk kadar air, prediksi terbaik adalah pre-treatment variasi standard normal variate menggunakan PLS-ANN dengan 20 FC (R2=0.99; SEC=1,07%, RPD=20.68; CV=1,73%). Hasil ini menunjukkan bahwa ANN dan NIRS yang dikembangkan dapat memprediksi kadar minyak dan air buah kelapa sawit secara non-destruktif.Oil and water content are an important quality criteria of crude palm oil (CPO) resulted from palm oil fruit processing. Those contents are usually determined using chemical method in the laboratory. This method is time consuming, long procedure, and destructive. Some efforts had been carried out to determine oil and water content of palm oil fruit non-destructively using some methods including Near-Infrared Spectroscopy (NIRS), but the results had not been satisfied. This research aims to assess Artificial Neural Network (ANN) and NIRS method to predict oil and water content of palm oil fruit’s non-destructively. The samples were palm oil fruits with ten maturity levels harvested from plantation in Bogor. Sample’s reflectance was measured with spectrometer NIR-Flex 500 at wavelength of 1000-2500 nm. After that, oil and water content were determined using chemical method. Some pre-treatments of NIR spectra namely normalization, savitzky-golay first derivative, their combinations, and standard normal variate were applied. Multivariate analysis such as PLS were carried out and the results of Factor Component (FC) were input for ANN model. The result showed the best method to predict oil content was combination savitzky-golay first derivative and normalization pre-treatment using PLS-ANN with 20 FC (R2=0.99; SEC=0,58%, RPD = 29.89; CV = 2.47%). For water content, the best prediction was standard normal variate pre-treatment using PLS-ANN with 20 FC (R2=0.99; SEC=1,07%, RPD=20.68; CV=1,73%). The result shows that developed ANN and NIRS can predict oil and water content of palm oil fruit non-destructively
The Development Mask R-CNN Model for Identification of Melon Plant Leaves and Branches
Full text linkMutu buah melon dapat ditingkatkan dan dioptimalkan dengan melakukan pemangkasan pada tanaman melon. Pemangkasan merupakan proses penghilangan yang dilakukan pada bagian tanaman tertentu. Saat ini tanaman melon masih dipangkas secara manual oleh petani, namun cara ini mempunyai banyak kekurangan. Pada penelitian ini pemangkasan dilakukan pada cabang dan daun tanaman melon. Pemangkasan dapat dilakukan dengan bantuan robot yang mampu mengenali daun dan dahan. Pada penelitian ini metode yang digunakan untuk mendeteksi cabang dan daun adalah Mask Region-based Convolutional Neural Network (Mask R-CNN). Teknik tuning hyperparameter digunakan untuk mendapatkan nilai parameter terbaik, termasuk learning rate, peluruhan bobot, dan momentum pembelajaran. Dua skenario dipertimbangkan dalam penelitian ini, satu dengan 10 epoch dan yang lainnya dengan 30 epoch. Nilai Average Precision (AP) yang diperoleh pada 10 epoch sebesar 32,2% untuk objek daun dan 0% untuk objek cabang. Pada 30 epoch, nilai AP adalah 56,8% untuk objek daun dan 4,1% untuk cabang. Rata-rata Presisi Rata-rata (mAP) adalah 16,1% untuk 10 epoch dan 28,4% untuk 30 epochThe quality of melons can be enhanced and optimized by pruning melon plants. Pruning is a removal process carried out on specific parts of the plant. Currently, melon plants are still pruned manually by farmers, but there are many drawbacks to this method. In this research, pruning is conducted on the branches and leaves of melon plants. Pruning can be facilitated with the assistance of a robot capable of recognizing leaves and branches. In this study, the method used to detect branches and leaves is the Mask Region-based Convolutional Neural Network (Mask R-CNN). Hyperparameter tuning technique is employed to obtain the best parameter values, including learning rate, weight decay, and learning momentum. Two scenarios are considered in this research, one with 10 epochs and the other with 30 epochs. The obtained Average Precision (AP) values at 10 epochs are 32.2% for leaf objects and 0% for branches. At 30 epochs, the AP values are 56.8% for leaf objects and 4.1% for branches. The mean Average Precision (mAP) is 16.1% for 10 epochs and 28.4% for 30 epochs