scholarly journals Jaringan Saraf Radial Basis Probabilistic untuk Identifikasi Morfologi Benih Padi Rawa Kalimantan Selatan

2017 ◽  
Vol 4 (1) ◽  
pp. 14
Author(s):  
Oni Soesanto ◽  
Akhmad Yusuf ◽  
Dindin H Mursyidin ◽  
M Syahid Pebriadi
Keyword(s):  
Aspect Ratio ◽  
Machine Vision ◽  
Major Axis ◽  
Minor Axis ◽  
Least Square ◽  
Radial Basis ◽  
Orthogonal Least Square

Machine vision berbasis jaringan saraf tiruan dan pemrosesan gambar digital merupakan metode alternatif yang dapat dilakukan untuk mengidentifikasi dan mengevaluasi keragaman varietas padi. Berbeda dengan metode pengamatan langsung yang memiliki tingkat subjektivitas tinggi dan metode kimiawi (PCR) yang bersifat destruktif dan mahal, machine vision berbasis jaringan saraf tiruan menawarkan sistem identifikasi dan evaluasi secara cepat, praktis, murah, akurat, serta bersifat non-destruktif. Paper ini membahas machine vision berbasis jaringan saraf tiruan sebagai teknologi alternatif untuk identifikasi varietas padi rawa Kalimantan Selatan berdasarkan ciri morfologinya, yaitu area, perimeter, major axis, minor axis, circularity, aspect ratio, roundness, dan feret untuk setiap sampel benih padi. Dalam paper ini, sistem identifikasi varietas benih padi menggunakan jaringan saraf radial basis probabilistic dengan optimalisasi bobot hidden center menggunakan algoritme orthogonal least square. Dari proses learning dihasilkan performa pelatihan sebesar 88.32% dan performa pengujian sebesar 88.21% dengan tingkat keberhasilan pada proses pelatihan dari masing-masing varietas bayar papuyu, bayar putih, benih kuning, benih putih, ketan, siam gadis, siam unus, dan karan dukuh masing-masing sebesar 100.00%, 92.59%, 88.89%, 92.59%, 92.59%, 81.48%, 100.00%, dan 100.00%. Untuk proses pengujian, tingkat keberhasilan masing-masing varietas ialah 100.00%, 87.50%, 88.89%, 100.00%, 88.89%, 88.89%, 100.00%, dan 100.00%.<br /><br />Kata Kunci: benih padi, machine vision, morfologi, RBP-OLS

scholarly journals Determining the AMSR-E SST Footprint from Co-located MODIS SSTs

2018 ◽  
Author(s):  
Brahim Boussidi ◽  
Peter Cornillon ◽  
Gavino Puggioni ◽  
Chelle Gentemann
Keyword(s):  
Aspect Ratio ◽  
Ground Truth ◽  
Major Axis ◽  
Sampling Procedure ◽  
Least Square ◽  
Gaussian Kernel ◽  
Bootstrap Sampling ◽  
Semi Major Axis ◽  
Linear Inversion ◽  
Precise Knowledge

This study was undertaken to derive and analyze the Advanced Microwave Scanning Radiometer - EOS (AMSR-E) sea surface temperature (SST) footprint associated with the Remote Sensing Systems (RSS) Level-2 (L2) product. The footprint, in this case, is characterized by the weight attributed to each 4 4 km square contributing to the SST value of a given AMSR-E pixel. High-resolution L2 SST fields obtained from the MODerate-resolution Imaging Spectroradiometer (MODIS), carried on the same spacecraft as AMSR-E, are used as the sub-resolution &ldquo;ground truth&ldquo; from which the AMSR-E footprint is determined. Mathematically, the approach is equivalent to a linear inversion problem, and its solution is pursued by means of a constrained least square approximation based on the bootstrap sampling procedure. The method yielded an elliptic-like Gaussian kernel with an aspect ratio 1.58, very close to the AMSR-E 6.93GHz channel aspect ratio, 1.7. (The 6.93GHz channel is the primary spectral frequency used to determine SST.) The semi-major axis of the estimated footprint is found to be alignedwith the instantaneous field-of-view of the sensor as expected fromthe geometric characteristics of AMSR-E. Footprintswere also analyzed year-by-year and as a function of latitude and found to be stable &ndash; no dependence on latitude or on time. Precise knowledge of the footprint is central for any satellite-derived product characterization and, in particular, for efforts to deconvolve the heavily oversampled AMSR-E SST fields and for studies devoted to product validation and comparison. A preliminarly analysis suggests that use of the derived footprint will reduce the variance between AMSR-E and MODIS fields compared to the results obtained.

Bubble Formation in a DC Electric Field

2008 ◽  
Author(s):  
Feng Chen ◽  
Yaozu Song ◽  
Yao Peng
Keyword(s):  
Aspect Ratio ◽  
Field Strength ◽  
Electric Field ◽  
Electric Field Strength ◽  
Bubble Growth ◽  
Growth Process ◽  
Major Axis ◽  
Minor Axis ◽  
Electric Stress ◽  
Dc Electric Field

The effect of a DC electric field on the formation and the characteristics of a nitrogen bubble injected from an orifice were studied experimentally and theoretically. This study was the first to divide the bubble growth process into four stages (waiting, expansion, deformation and detachment) according to the variation of the bubble shape in order to analyze the bubble behavior in the electric field. During the waiting stage, the waiting interval decreases significantly as the electric field strength rises. In the expansion stage, the minor axis reaches a maximum that decreases with increasing the electric field strength. Within the deformation stage, the major axis achieves its maximum and so does the aspect ratio. As the electric field strength rises, both the maximums of the major axis and the aspect ratio increase. At the detachment stage, as the electric field strength is intensified, the major axis lengthens, the minor axis shortens and the aspect ratio lengthens. From the waiting stage to the detachment stage, the effect of the electric field on the major axis of the bubble is marginal, while with increasing the electric field strength, the minor axis decreases distinctly and thus the aspect ratio increases. To employ the four-stage model, the bubble growth process was analyzed in detail under the electric field. The electric stress exerted on the bubble surface was calculated. The results show that the electric stress compresses the bubble equator and elongates the poles of the bubble, causing the bubble to elongate along the electric field direction.

scholarly journals Penerapan Metode Jaringan Syaraf Tiruan Radial Basis Function Untuk Identifikasi Jenis Mangga Berdasarkan Pola Daun

J-INTECH ◽  
2019 ◽  
Vol 7 (01) ◽  
pp. 90-96
Author(s):  
Rhesal Mahadyanto ◽  
Diah Arifah Prastiningtyas ◽  
Febry Eka Purwiantono
Keyword(s):  
Radial Basis Function ◽  
Basis Function ◽  
Radial Basis Function Network ◽  
Major Axis ◽  
Minor Axis ◽  
Radial Basis ◽  
Function Network

Daun merupakan salah satu bagian tanaman yang dapat menjadi acuan klasifikasi. Selain itu, daun lebih mudah diperoleh karena tidak tergantung pada musim. Karena memiliki perbedaan fitur pada setiap jenis mangga. Penerapan Jaringan Syaraf Tiruan Radial Basis Function Network merupakan salah satu cara untuk dapat mengklasifikasikan. Dengan cara pengumpulan data melalui pengolahan citra digital. yang berfokus terhadap ekstraksi fitur pada sebuah citra daun. Hasil dari informasi citra daun yang nantinya akan menjadi fitur fitur dalam metode klasifikasi. Fitur-fitur tersebut adalah Hue, Saturation, Value, Luas, Keliling, Major Axis dan Minor axis. Pada tahap pengujian hasil menunjukkan bahwa nilai persentase keberhasilan kurang dari 50% pada percobaan pelatihan 4 citra dan pengujian 4 citra dengan total 32 data latih dan 32 data uji. Dan pada percobaan pelatihan 7 dan pengujian 1 tingkat keberhasilan masih dibawah 50%. Untuk pengembangan selanjutnya dapat ditambahkan fitur / ciri agar persentase identifikasinya meningkat. Dan juga dibutuhkan penelitian dengan metode pemabanding agar dapat diketahui metode terbaik yang sesuai dengan penelitian ini. Dengan penelitian ini nantinya dapat dikembangkan lagi sebuah aplikasi mobile yang dapat mengidentifikasi jenis tanaman mangga berdasarkan daun, tidak hanya jenis mangga saja melainkan berbagai jenis tanaman. Sehingga bermanfaat juga sebagai media berbagi informasi bagi yang membutuhkan informasi mengenai jenis tanaman.

Radial Basis Function (RBF) for Non–Linear Dynamic System Identification

2012 ◽  
Author(s):  
Robiah Ahmad ◽  
Hishamuddin Jamaluddin
Keyword(s):  
System Identification ◽  
Radial Basis Function ◽  
Basis Function ◽  
Least Square ◽  
System Modelling ◽  
Suitable Model ◽  
Non Linear ◽  
Radial Basis ◽  
Orthogonal Least Square ◽  
Non Linear System

Masalah utama dalam pengenalpastian sistem ialah memilih struktur model yang sesuai. Dalam artikel ini, rangkaian fungsi asas jejarian menggunakan pelbagai fungsi asas dilatih untuk mewakili sistem dinamik tak linear masa diskrit dan keputusannya dibandingkan. Algoritma kuasa dua terkecil ortogon digunakan untuk memilih model rangkaian asas jejarian termudah. Untuk menerangkan tatacara pengenalpastian, dua contoh pemodelan sistem tak linear dibincangkan. Kata kunci: fungsi asas jejarian; pengenalpastian sistem; pemodelan sistem tak linear; algoritma kuasa dua terkecil ortogon One of the key problem in system identification is finding a suitable model structure. In this paper, radial basis function (RBF) network using various basis functions are trained to represent discrete-time nonlinear dynamic systems and the results are compared. The orthogonal least square algorithm is employed to select parsimonious RBF models. To demonstrate the identification procedure, two examples of modelling nonlinear system were included. Key words: radial basis function; system identification; non-linear system modelling; orthogonal least square algorithm

scholarly journals Determining the AMSR-E SST Footprint from Co-Located MODIS SSTs

2019 ◽  
Vol 11 (6) ◽  
pp. 715 ◽  
Author(s):  
Brahim Boussidi ◽  
Peter Cornillon ◽  
Gavino Puggioni ◽  
Chelle Gentemann
Keyword(s):  
Aspect Ratio ◽  
Ground Truth ◽  
Major Axis ◽  
Sampling Procedure ◽  
Least Square ◽  
Gaussian Kernel ◽  
Bootstrap Sampling ◽  
Semi Major Axis ◽  
Linear Inversion ◽  
Precise Knowledge

This study was undertaken to derive and analyze the advanced microwave scanning radiometer-Earth observing satellite (EOS) (AMSR-E) sea surface temperature (SST) footprint associated with the remote sensing systems (RSS) level-2 (L2) product. The footprint, in this case, is characterized by the weight attributed to each 4 × 4 km square contributing to the SST value of a given (AMSR-E) pixel. High-resolution L2 SST fields obtained from the moderate-resolution imaging spectroradiometer (MODIS), carried on the same spacecraft as AMSR-E, are used as the sub-resolution “ground truth” from which the AMSR-E footprint is determined. Mathematically, the approach is equivalent to a linear inversion problem, and its solution is pursued by means of a constrained least square approximation based on the bootstrap sampling procedure. The method yielded an elliptic-like Gaussian kernel with an aspect ratio ≈1.58, very close to the AMSR-E 6.93 GHz channel aspect ratio, ≈1.74. (The 6.93 GHz channel is the primary spectral frequency used to determine SST.) The semi-major axis of the estimated footprint is found to be aligned with the instantaneous field-of-view of the sensor as expected from the geometric characteristics of AMSR-E. Footprints were also analyzed year-by-year and as a function of latitude and found to be stable—no dependence on latitude or on time. Precise knowledge of the footprint is central for any satellite-derived product characterization and, in particular, for efforts to deconvolve the heavily oversampled AMSR-E SST fields and for studies devoted to product validation and comparison. A preliminary analysis suggests that use of the derived footprint will reduce the variance between AMSR-E and MODIS fields compared to the results obtained ignoring the shape and size of the footprint as has been the practice in such comparisons to date.

Elliptic jet control with triangular tab

2016 ◽  
Vol 231 (8) ◽  
pp. 1460-1477 ◽  
Author(s):  
SM Aravindh Kumar ◽  
Ethirajan Rathakrishnan
Keyword(s):  
Aspect Ratio ◽  
Major Axis ◽  
Minor Axis ◽  
Mixing Enhancement ◽  
Jet Mixing ◽  
Pitot Pressure ◽  
Nozzle Pressure ◽  
Jet Control ◽  
The Waves ◽  
Different Levels

Elliptic jet mixing influenced by triangular tabs is demonstrated in this work. Mixing modification of a Mach 2 jet from a convergent-divergent elliptic nozzle of aspect ratio 2, in the presence of two triangular tabs along the major and minor axis at the nozzle exit, at different levels of nozzle expansion has been studied. The results show that the mixing caused by tabs along the minor axis is impressive compared to the uncontrolled jet at all the pressure ratios. But for tabs along the major axis, mixing enhancement is significant only for nozzle pressure ratios above 5. Tabs along the minor axis cause better mixing than tabs along the major axis. The iso-pitot pressure contours reveal that the tabs along the minor axis enhance the mixing by bifurcating the jet. Shadowgraphs show that the tabs render the waves in the jet weaker. The present study demonstrates the superior mixing promotion caused by triangular tab than rectangular tab, studied by Aravindh Kumar and Rathakrishnan (2015).

Major-Axis Planning Method for Fabrication of High Aspect Ratio Structure Based on Two-Photon Photopolymerization Technology

2018 ◽  
Author(s):  
Chao-Yaug Liao ◽  
Chien-Min Kao ◽  
Po-Kai Chen
Keyword(s):  
Aspect Ratio ◽  
Spatial Resolution ◽  
High Aspect Ratio ◽  
Glass Substrate ◽  
Rotation Axis ◽  
Major Axis ◽  
Minor Axis ◽  
Micro Manufacturing ◽  
Two Photon ◽  
High Aspect Ratio Structure

The smallest forming unit in two-photon photopolymerization (TPP) micro-manufacturing technology is the voxel, the appearance of which resembles a spheroid. Traditional TPP micro-manufacturing is planned using the minor-axis dimension of a spheroid, which is smaller than its major-axis, thus, the spatial resolution can achieve submicron level. TPP can be used to manufacture microstructures with complex shapes. However, such fine spatial resolution inevitably lowers the overall manufacturing speed. For a microstructure with a height of hundred micrometers, the prolonged manufacturing time substantially increases the risk of manufacturing failure. Whereas typical methods use the minor-axis dimension for manufacturing planning, this study developed a novel major-axis planning (MAP) method that uses the longest dimension of the voxel. In this study, the MAP was realized in a 4-axis micro-manufacturing system (i.e., a rotation axis was added to the 3-axis motion stage). Specifically, a specially designed L-type glass substrate was first placed on the rotation axis and was rotated 90°, rendering the working plane parallel to laser beams. Subsequently, horizontal laser scanning was performed, during which the laser focus moved from the working plane horizontally, to polymerize a high-aspect-ratio structure. The commercial polymer OrmoComp was used with the MAP; only 10 s was required to fabricate a microstructure that had a height of 100 μm and an aspect ratio of 17. This study verified that TPP micro-manufacturing on a voxel’s major axis can fabricate microstructures. Moreover, the L-type glass substrate can be controlled programmably to rotate an L-type glass substrate for 4-axis TPP micro-manufacturing in the future.

Sign in / Sign up

Export Citation Format

Share Document