Current Issue : July-September Volume : 2022 Issue Number : 3 Articles : 5 Articles
Plant diseases pose a significant challenge for food production and safety. Therefore, it is indispensable to correctly identify plant diseases for timely intervention to protect crops from massive losses. The application of computer vision technology in phytopathology has increased exponentially due to automatic and accurate disease detection capability. However, a deep convolutional neural network (CNN) requires high computational resources, limiting its portability. In this study, a lightweight convolutional neural network was designed by incorporating different attention modules to improve the performance of the models. The models were trained, validated, and tested using tomato leaf disease datasets split into an 8:1:1 ratio. The efficacy of the various attention modules in plant disease classification was compared in terms of the performance and computational complexity of the models. The performance of the models was evaluated using the standard classification accuracy metrics (precision, recall, and F1 score). The results showed that CNN with attention mechanism improved the interclass precision and recall, thus increasing the overall accuracy (>1.1%). Moreover, the lightweight model significantly reduced network parameters (~16 times) and complexity (~23 times) compared to the standard ResNet50 model. However, amongst the proposed lightweight models, the model with attention mechanism nominally increased the network complexity and parameters compared to the model without attention modules, thereby producing better detection accuracy. Although all the attention modules enhanced the performance of CNN, the convolutional block attention module (CBAM) was the best (average accuracy 99.69%), followed by the self-attention (SA) mechanism (average accuracy 99.34%)....
In order to meet the requirements of multi-crop harvesting, reduce the loss of harvesting, and improve the quality of harvesting, the device and method of matching and adjusting the rotation speed and forward speed of the pulling reel were designed. On the premise of satisfying the matching regulation, the parameters of the rotary wheel and the cutting table were adjusted so that the rotational speed ratio λ of the harvest crop was in the suitable range of the rotational speed ratio of the crop. The speed ratio was designed as a suitable interval of different crops by experiments and experience, and, in order to meet the requirements, it was designed to optimize the wheel speed. The speed-matching was designed, and through the experiments on the wheel-speed-adjustment error, which was less than 2%, it was designed to meet the design requirements. Crop-harvesting experiments were carried out under rotational speed-matching and a random speed, and the experimental results showed that the loss rate under rotational speed-matching was significantly lower than that under random speeds; the tests showed that the wheel speed designed with speed-matching can effectively reduce the loss rate....
Bread wheat germplasm has wide genetic diversity, which means it can withstand a lot of biotic and abiotic stresses. Despite the presence of bread wheat germplasm diversity in Ethiopia, wheat production in the Kafa Zone is significantly lower than the national average. The ultimate goal of this research was to determine the genetic diversity of grain yield and yield components of bread wheat. One hundred bread wheat accessions with 3 local checks were evaluated in augmented randomized complete block design at Kafa Zone, Gewata Woreda Shupa site, during the 2018–19 growing season. The mean performance of the accessions revealed that accession number 29812 yielded more grain than the others. Spike length, number of seeds per spike, biomass yield, and harvest index all had moderate genotypic coefficients of variation. Spike length, number of seeds per spike, thousand seed weight, biomass yield, and harvest index all had moderate-to-high heritability and also all the above-listed traits had moderate-tohigh genetic advance as a percentage of the mean. This means that practical improvement of these essential traits can be achieved by effective and satisfactory selection. Grain yield has positive correlations with grain filling period, number of productive tillers, spike length, number of seeds per spike, thousand seed weight, and biomass yield. The principal component analysis grouped all of the traits into four main components. Seven clusters and one ungrouped accession were formed from the accessions. Cluster IV and cluster VI had the greatest intercluster distance (D2 104.77) among the clustered groups, suggesting the probability of selecting a parental genotype for hybridization. However, the current result is merely indicative and cannot be used to draw firm conclusions. As a result, the experiment should be replicated in different locations and seasons for greater consistency....
In this study, 12 maize hybrids were planted and evaluated to determine the effect of genotype and genotype-environment interaction (GEI) base GGE (genotype plus genotype-by-environment) using a Graphical biplot technique in four research stations (Arak, Birjand, Shiraz and Karaj) within two years using a Randomized Complete Blocks Design (RCBD). The combined analysis of variance showed that the effects of the environment, genotype and genotype-environment interaction (GEI) were significant in the one percent probability level. GGE biplot results indicated that the first and second principal components (PC1 and PC2) explained more than 83% of the grain performance variation. Simultaneous study of grain performance and hybrid stability using the biplot of average environment coordinates showed that the KSC705 genotype had the highest yield and stability. Polygon view divided the studied areas into two mega-environments (MEs) and identified the best genotypes in each mega-environment (ME). In the first mega-environment (ME1), the Karaj and Shiraz with KSC706 and KSC400 genotypes were detected, and were the best; and in the second mega-environment (ME2), Arak and Birjand with KSC704 and KSC707 genotypes performed better. The biplot graph for the correlation between the genotypes categorized the studied hybrids into four groups positively related to each other based on the angles between vectors. The KSC704 and KSC707 genotypes were desirable in the yield in Shiraz and Karaj and KSC706 were in Arak and Birjand. Additionally, Arak-Birjand, Karaj-Shiraz showed a positive and significant correlation. Birjand and Karaj had most genotype interaction with each other....
The inadequate management of agro-waste in intensive agriculture has a severe negative impact on the environment. The valorization of crop residue as a source of crop nutrients is a valid alternative to close the nutrient cycle and reduce the use of external input. In this study, plant material was incorporated into the soil as fresh crop residue, after either composting and vermicomposting processes, to evaluate their effects on tomato yield and nutritional status (petiole sap analysis: NO3 and K+ concentration) over three crop cycles. A control treatment with mineral fertigation and an organic control treatment with goat manure were also included. Enzymatic activity and microbial population in the soil were evaluated. Although no differences between treatments were observed in the first cycle, in the second and third cycles, the yield obtained with the application of organic amendments derived from agro-waste was comparable to the yield obtained with mineral fertilizers. Overall, the sap analysis did not reveal a clear relationship with yield performances. The compost treatment resulted in higher microorganism presence in the soil. Soil dehydrogenase activity (DHA), acid phosphatase activity (ACP), and β-glucosidase activity (β-GLU) were generally more stimulated when organic amendments were used. The study confirms the applicability of soil fertilizers derived from agro-waste as a good alternative to mineral fertilizers....
Loading....