Banana is a significant crop,and three banana leaf diseases,including Sigatoka,Cordana and Pestalotiopsis,have the potential to have a serious impact on banana production.Existing studies are insufficient to provide a...Banana is a significant crop,and three banana leaf diseases,including Sigatoka,Cordana and Pestalotiopsis,have the potential to have a serious impact on banana production.Existing studies are insufficient to provide a reliable method for accurately identifying banana leaf diseases.Therefore,this paper proposes a novel method to identify banana leaf diseases.First,a new algorithm called K-scale VisuShrink algorithm(KVA)is proposed to denoise banana leaf images.The proposed algorithm introduces a new decomposition scale K based on the semi-soft and middle course thresholds,the ideal threshold solution is obtained and substituted with the newly established threshold function to obtain a less noisy banana leaf image.Then,this paper proposes a novel network for image identification called Ghost ResNeSt-Attention RReLU-Swish Net(GR-ARNet)based on Resnet50.In this,the Ghost Module is implemented to improve the network's effectiveness in extracting deep feature information on banana leaf diseases and the identification speed;the ResNeSt Module adjusts the weight of each channel,increasing the ability of banana disease feature extraction and effectively reducing the error rate of similar disease identification;the model's computational speed is increased using the hybrid activation function of RReLU and Swish.Our model achieves an average accuracy of 96.98%and a precision of 89.31%applied to 13,021 images,demonstrating that the proposed method can effectively identify banana leaf diseases.展开更多
Comparing to some other fibers,the mechanical andsome physical properties of banana fiber,constituent ofbanana fiber have been studied in this paper,mean-while,for improving some characteristics of banana fi-ber,the c...Comparing to some other fibers,the mechanical andsome physical properties of banana fiber,constituent ofbanana fiber have been studied in this paper,mean-while,for improving some characteristics of banana fi-ber,the chemical treatments were used to modify the fi-ber.The results show that the coarse and brittle bananafiber,will be difficult to process in traditional spinningsystem.展开更多
Bananas demand high amounts of potassium for optimal growth and productivity, yet deficiencies are widespread amid the low input production strategy of smallholder farmers in Uganda. Of the potassium pool in the soil,...Bananas demand high amounts of potassium for optimal growth and productivity, yet deficiencies are widespread amid the low input production strategy of smallholder farmers in Uganda. Of the potassium pool in the soil, 90% - 98% is unavailable for plant uptake. Judicious application of fertilisers is required to alleviate soil fertility problems complemented with manures and biofertilisers in an integrated nutrient management (INM) package. Biofertilisers such as potassium solubilising bacteria (KSB) have potential to solubilise unavailable forms of K in soil to forms that are readily absorbed by the plants. However, the added value of each component in this integrated K management package in apple bananas is not known. Therefore, an experiment was set up to quantify the relative contribution of mineral K, manure and KSB on the growth of apple bananas. Potted tissue culture plantlets of apple banana (cv. Sukali ndiizi) were used. The treatments comprised of a full factorial combination of mineral fertiliser (Muriate of potash, 60% K<sub>2</sub>O), animal manure and KSB (<em>Frateuria auranta</em>). The manure and muriate of potash were applied to supply a total of 150 kg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>ha<span style="white-space:nowrap;"><sup>−</sup></span>. Soil microbiological assays were run to evaluate the contribution of indigenous microbial K solubilising activity in the soil to the experimental INM package. Data on pseudostem height, girth at collar and 30-cm height, leaf length and width at the widest point were collected once a week for 24 weeks. <em>Bacillus, Pseudomonas</em> and <em>Frateuria</em> were present as indigenous KSBs in the soil. The biofertiliser applied as <em>F. auranta</em> solubilised 7.4 mg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>l<sup><span style="white-space:nowrap;">−</span>1</sup> (6.2 mg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>kg<sup><span style="white-space:nowrap;">−</span>1</sup>) from soil minerals. The integrated K management package significantly (p < 0.001) increased the above ground biomass and leaf area of potted apple bananas by up to 57.5% compared to no input. The Study recommends an economic analysis study to determine the integrated K management package that would suit the resource constrained smallholder farmers.展开更多
基金supported by the Changsha Municipal Natural Science Foundation,China(kq2014160)in part by the Key Projects of Department of Education of Hunan Province,China(21A0179)+1 种基金the Hunan Key Laboratory of Intelligent Logistics Technology,China(2019TP1015)the National Natural Science Foundation of China(61902436)。
文摘Banana is a significant crop,and three banana leaf diseases,including Sigatoka,Cordana and Pestalotiopsis,have the potential to have a serious impact on banana production.Existing studies are insufficient to provide a reliable method for accurately identifying banana leaf diseases.Therefore,this paper proposes a novel method to identify banana leaf diseases.First,a new algorithm called K-scale VisuShrink algorithm(KVA)is proposed to denoise banana leaf images.The proposed algorithm introduces a new decomposition scale K based on the semi-soft and middle course thresholds,the ideal threshold solution is obtained and substituted with the newly established threshold function to obtain a less noisy banana leaf image.Then,this paper proposes a novel network for image identification called Ghost ResNeSt-Attention RReLU-Swish Net(GR-ARNet)based on Resnet50.In this,the Ghost Module is implemented to improve the network's effectiveness in extracting deep feature information on banana leaf diseases and the identification speed;the ResNeSt Module adjusts the weight of each channel,increasing the ability of banana disease feature extraction and effectively reducing the error rate of similar disease identification;the model's computational speed is increased using the hybrid activation function of RReLU and Swish.Our model achieves an average accuracy of 96.98%and a precision of 89.31%applied to 13,021 images,demonstrating that the proposed method can effectively identify banana leaf diseases.
文摘Comparing to some other fibers,the mechanical andsome physical properties of banana fiber,constituent ofbanana fiber have been studied in this paper,mean-while,for improving some characteristics of banana fi-ber,the chemical treatments were used to modify the fi-ber.The results show that the coarse and brittle bananafiber,will be difficult to process in traditional spinningsystem.
文摘Bananas demand high amounts of potassium for optimal growth and productivity, yet deficiencies are widespread amid the low input production strategy of smallholder farmers in Uganda. Of the potassium pool in the soil, 90% - 98% is unavailable for plant uptake. Judicious application of fertilisers is required to alleviate soil fertility problems complemented with manures and biofertilisers in an integrated nutrient management (INM) package. Biofertilisers such as potassium solubilising bacteria (KSB) have potential to solubilise unavailable forms of K in soil to forms that are readily absorbed by the plants. However, the added value of each component in this integrated K management package in apple bananas is not known. Therefore, an experiment was set up to quantify the relative contribution of mineral K, manure and KSB on the growth of apple bananas. Potted tissue culture plantlets of apple banana (cv. Sukali ndiizi) were used. The treatments comprised of a full factorial combination of mineral fertiliser (Muriate of potash, 60% K<sub>2</sub>O), animal manure and KSB (<em>Frateuria auranta</em>). The manure and muriate of potash were applied to supply a total of 150 kg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>ha<span style="white-space:nowrap;"><sup>−</sup></span>. Soil microbiological assays were run to evaluate the contribution of indigenous microbial K solubilising activity in the soil to the experimental INM package. Data on pseudostem height, girth at collar and 30-cm height, leaf length and width at the widest point were collected once a week for 24 weeks. <em>Bacillus, Pseudomonas</em> and <em>Frateuria</em> were present as indigenous KSBs in the soil. The biofertiliser applied as <em>F. auranta</em> solubilised 7.4 mg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>l<sup><span style="white-space:nowrap;">−</span>1</sup> (6.2 mg<span style="white-space:nowrap;">⋅</span>K<span style="white-space:nowrap;">⋅</span>kg<sup><span style="white-space:nowrap;">−</span>1</sup>) from soil minerals. The integrated K management package significantly (p < 0.001) increased the above ground biomass and leaf area of potted apple bananas by up to 57.5% compared to no input. The Study recommends an economic analysis study to determine the integrated K management package that would suit the resource constrained smallholder farmers.
