Neural-Intelligent Water Drops algorithm to select relevant textural features for developing precision irrigation system using machine vision     

Yusuf Hendrawan  Haruhiko Murase 《Computers and Electronics in Agriculture》2011,77(2):214-228

Sunagoke moss Rachomitrium japonicum is a good potential for greening material. One of the primary determinants of Sunagoke moss growth is water availability. Too much or too little water can cause water stress in plants. Water stress in plants can be detected by imaging. This study is part of on-going research aimed at developing machine vision-based precision irrigation system in a closed bio-production system for cultured Sunagoke moss. The objective of this study is to propose nature-inspired feature selection techniques to find the most significant set of Textural Features (TFs) suitable for predicting water content of cultured Sunagoke moss. The proposed Feature Selection (FS) methods include Neural-Intelligent Water Drops (N-IWD), Neural-Simulated Annealing (N-SA), Neural-Genetic Algorithms (N-GAs) and Neural-Discrete Particle Swarm Optimization (N-DPSO). TFs consist of 120 features extracted from grey, RGB, HSV, HSL and L^∗a^∗b^∗ colour spaces using ten Haralick’s textural equations. Back-Propagation Neural Network (BPNN) model performance was tested successfully to describe the relationship between water content of Sunagoke moss and TFs. Red Colour Co-occurrence Matrix (CCM) TFs, L^∗ CCM TFs, grey CCM TFs, value_(HSV) CCM TFs, green CCM TFs and lightness_(HSL) CCM TFs are recommended as individual feature-subset to be used for predicting water content of Sunagoke moss using Artificial Neural Networks. However, FS methods improve the prediction performance. The results show a significant difference between model using FS and models using individual feature-subsets or without FS. Comparative analysis shows the superiority of Neural-Intelligent Water Drops (N-IWD) compared to the other FS methods, since it achieve better prediction performance. The best N-IWD’s fitness function converged with the lowest validation-set Root Mean Square Error (RMSE) of 1.07 × 10⁻² when using 36 TFs.  相似文献   

Chemical composition and <Emphasis Type="Italic">in sacco</Emphasis> degradability of four varieties of cassava leaves grown in Southwestern Nigeria in the rumen of sheep     

A. O. Oni  C. F. I. Onwuka  O. M. Arigbede  O. O. Oni  U. Y. Anele  K. O. Yusuf  B. O. Oduguwa  O. S. Onifade 《Tropical animal health and production》2010,42(7):1385-1393

The nutritive value of leaves of four varieties of cassava (MS 6, TMS 30555, Idileruwa and TMS 30572) were studied through analysis of their chemical components and degradability of their dry matter (DM) and crude protein (CP) in the rumen of sheep. Results of the chemical analyses showed that the leaves of the four varieties contained different proportions of organic matter which was significantly (P < 0.05) highest in TMS 30572 with value of 935 g/kg DM, while CP (gramme per kilogramme DM) was significantly highest in TMS 30555 (240), followed by MS 6 (235), TMS 30572 (208) and least in Idileruwa (177). Mean metabolisable energy (megajoules per kilogramme DM) was significantly (P < 0.05) highest in TMS 30572 (8.2) and similar with Idileruwa (8.0) but different from TMS 30555 and MS 6, respectively (7.8 and 7.6). The mineral contents (gramme per kilogramme DM) showed that leaves of MS 6 and Idileruwa had the highest concentrations of K (2.86) and a significantly lowest value (1.83) in TMS 30555. Also, the highest concentration of Ca and Fe (6.81 and 6.23) was recorded in MS 6. The highest Ca:P of 3.20 was obtained in TMS 30555. DM degradation characteristics and effective degradability varied significantly (P < 0.05) and were consistently highest in TMS 30572. The washing loss (a) ranged from 15.9% in MS 6 to 21.3% in TMS 30572. TMS 30572 tended to have higher (P = 0.546) insoluble but fermentable fraction (b) than all other varieties. Moreover, the potential degradability (a + b) tended to be higher (P = 0.041) in TMS 30572 (69.5%) followed by TMS 30555 (67.1%) and the lowest was in Idileruwa (42.7%). The highest effective degradability was recorded in TMS 30572 (63.9%) and the lowest in Idileruwa (40.7%). The degradation rate constants (c) of Idileruwa was significantly higher (P = 0.001) than those of MS6, TMS 30555 and TMS 30572. The results generally indicated that the leaves could be ranked for their potential feeding value as TMS 30572 (71.5%) > MS6 (65.8%) > Idileruwa (63.0%) > TMS 30555 (50.4%). It is therefore concluded from this study that leaves of TMS 30572 and MS 6 have good potential as feed resources for ruminant animals and could be used in ruminant feeding as protein source ingredient.  相似文献   

Characterization ofRhizoctonia solani isolates from potatoes in turkey and screening potato cultivars for resistance to AG-3 isolates   总被引：1，自引：0，他引：1  

Yusuf Yanar  Gungor Yılmaz  Ibrahim Cesmeli  Sinasi Coskun 《Phytoparasitica》2005,33(4):370-376

A total of 304Rhizoctonia solani isolates and 60 binucleateRhizoctonia-like fungi were recovered from stems and tubers of infected potato plants over a 2-yr period in northeast Turkey.R. solani isolates were identified to 11 anastomosis groups (AGs): AG-1 (0.66%), AG-2-1 (5.6%), AG-2-2 (0.99%), AG-3 (83.9%), AG-5 (4.6%), AG-6 (0.66%), AG-8 (1.32%), AG-9 (0.33%), AG-10 (1.32%), AG-12 (0.33%), and AG-13 (0.33%). In the greenhouse tests, most of the AG-3 isolates were significantly more virulent than isolates belonging to other AGs on potato cv. Batum. Isolates of other anastomosis groups differed in their virulence. Results indicated that AG-3 is an important pathogen on potatoes grown in the study area. Five of 22 commercial and local potato cultivars evaluated for their reaction toR. solani AG-3 isolates (TP-2) under greenhouse conditions were highly resistant; the remaining cultivars exhibited different levels of susceptibility to the pathogen isolate. http://www.phytoparasitica.org posting July 14, 2005.  相似文献   

<Emphasis Type="Italic">Rhizobium</Emphasis>,<Emphasis Type="Italic"> Bradyrhizobium</Emphasis> and<Emphasis Type="Italic"> Agrobacterium</Emphasis> strains isolated from cultivated legumes     

Sohail?Hameed  Sumera?Yasmin  Kauser?A.?Malik  Yusuf?Zafar  Fauzia?Y.?HafeezEmail author 《Biology and Fertility of Soils》2004,39(3):179-185

The present study was conducted to isolate and characterize rhizobial strains from root nodules of cultivated legumes, i.e. chickpea, mungbean, pea and siratro. Preliminary characterization of these isolates was done on the basis of plant infectivity test, acetylene reduction assay, C-source utilization, phosphate solubilization, phytohormones and polysaccharide production. The plant infectivity test and acetylene reduction assay showed effective root nodule formation by all the isolates on their respective hosts, except for chickpea isolate Ca-18 that failed to infect its original host. All strains showed homology to a typical Rhizobium strain on the basis of growth pattern, C-source utilization and polysaccharide production. The strain Ca-18 was characterized by its phosphate solubilization and indole acetic acid (IAA) production. The genetic relationship of the six rhizobial strains was carried out by random amplified polymorphic DNA (RAPD) including a reference strain of Bradyrhizobium japonicum TAL-102. Analysis conducted with 60 primers discriminated between the strains of Rhizobium and Bradyrhizobium in two different clusters. One of the primers, OPB-5, yielded a unique RAPD pattern for the six strains and well discriminated the non-nodulating chickpea isolate Ca-18 from all the other nodulating rhizobial strains. Isolate Ca-18 showed the least homology of 15% and 18% with Rhizobium and Bradyrhizobium, respectively, and was probably not a (Brady)rhizobium strain. Partial 16S rRNA gene sequence analysis for MN-S, TAL-102 and Ca-18 strains showed 97% homology between MN-S and TAL-102 strains, supporting the view that they were strains of B. japonicum species. The non-infective isolate Ca-18 was 67% different from the other two strains and probably was an Agrobacterium strain.  相似文献   

Comparative Analysis of MLR,ANN, and ANFIS Models for Prediction of Field Capacity and Permanent Wilting Point for Bafra Plain Soils     

Sevda Taşan  Yusuf Demir 《Communications in Soil Science and Plant Analysis》2020,51(5):604-621

ABSTRACT

Soil hydraulic parameters like moisture content at field capacity and permanent wilting point constitute significant input parameters of various biophysical models and agricultural practices (irrigation timing and amount of irrigation to be applied). In this study, the performance of three different methods (Multiple linear regression – MLR, Artificial Neural Network – ANN and Adaptive Neuro-Fuzzy Inference System – ANFIS) with different input parameters in prediction of field capacity and permanent wilting point from easily obtained soil characteristics were compared. Correlation analysis indicated that clay content, sand content, cation exchange capacity, CaCO₃, and organic matter had significant correlations with FC and PWP (p < .01). Validation results revealed that the ANN model with the greatest R² and the lowest MAE and RMSE value exhibited better performance for prediction of FC and PWP than the MLR and ANFIS models. ANN model had R² = 0.83, MAE = 2.36% and RMSE = 3.30% for FC and R² = 0.81, MAE = 2.15%, RMSE = 2.89% for PWP in training dataset; R² = 0.80, MAE = 2.27%, RMSE = 3.12% for FC and R² = 0.83, MAE = 1.84%, RMSE = 2.40% for PWP in testing dataset. Also, Bayesian Regularization (BR) algorithm exhibited better performance for both FC and PWP than the other training algorithms.  相似文献   

An Alternative Sucker Management Method in Hazelnut: Application of Nitrogen Fertilizer Solution     

Serdar  Ümit  Gülser  Coşkun  Akyüz  Burak  Balta  Ayşegül  Çil  Yusuf  Yilmaz Figen  Fatma 《Erwerbs-Obstbau》2022,64(2):237-244

The goal of this study was to determine the usability of nitrogen solution for hazelnut sucker management. This study was carried out from 2015 to 2016?at two hazelnut orchards; one established with the shrub (ocak) system in Atakum district and the other established with the multi-stemmed system in the Carsamba district, both in Samsun province. For sucker management, 21% ammonium sulphate (AS) and 26% calcium ammonium nitrate (CAN) fertilizer solutions were used. Doses of 0, 10, 15 and 20% of solutions for both fertilizers were tested. In the study, hazelnut suckers were removed by knife in July 2015 and March 2016. Nitrogen solution applications were started in September 2015 when suckers reached 20–30?cm length. In 2016 four applications were made from April to August. Fifteen days after the applications, the wilting ratio (starting from the tip) and newly emerged suckers per bush were determined. Nitrate, pH, and EC analyses were made with soil samples collected at the beginning of the experiment and compared to those taken 15 days after each application. As a result, a 10% dose of 21% ammonium sulphate fertilizer gave the best results for hazelnut sucker management. Nitrogen solution application should be started 1 to 1.5 months after removal of suckers by cutting with a knife. Suckers should be removed when they reach 15–20?cm length and before they are lignified. For effective sucker management, nitrogen solution application should be applied at least three times in a year.

  相似文献   

Tetraselmis chuii biomass as a potential feed additive to improve survival and oxidative stress status of Pacific white-leg shrimp Litopenaeus vannamei postlarvae     

Rahman  Norazira Abdu  Khatoon  Helena  Yusuf  Norhayati  Banerjee  Sanjoy  Haris  Noor Azilah  Lananan  Fathurrahman  Tomoyo  Katayama 《International Aquatic Research》2017,9(3):235-247

International Aquatic Research - Shrimp is an important traded fishery commodity. When subjected to stress, shrimp usually suffers from oxidative stress, which leads to cell injury, senescence, and...  相似文献