A two-stage feature aggregation network for multi-category soybean leaf disease identification

Pan, Renyong; Lin, Jie; Cai, Jitong; Zhang, Licai; Liu, Jiaming; Wen, Xingtian; Chen, Xiaoyulong; Zhang, Xin

doi:10.1016/j.jksuci.2023.101669

Cited by 3 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Merr. ), a crucial legume and oil crop recognized for its high nutritional value, is extensively grown globally [1,2]. The widespread cultivation of soybean is driven by its importance in agribusiness and the food industry and by its contribution to enhancing food security and soil fertility [3,4].…”

Section: Introductionmentioning

confidence: 99%

“…Conversely, opting for higher volumes of chemical fertilizers would prove economically impractical for farmers and could adversely affect the environment and soil properties. Therefore, in this study, we aimed (1) to study the individual and integrated application of inorganic fertilizer (urea) and organic fertilizer (cow manure) on the growth and yield of soybeans in Afghanistan, (2) to find out the effectively integrated amounts of organic and inorganic fertilizers, and (3) to determine the usability of this method for farmers within the county.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Soybean Crop Performance through the Integrated Application of Organic and Chemical Fertilizers: A Study on Alkaline Soil in Afghanistan

Turabi,

Habibi,

Kakar

et al. 2024

Crops

View full text Add to dashboard Cite

The excess application of chemical fertilizer contributes to environmental pollution. Therefore, this study aims to explore the integrated use of animal manure and chemical fertilizer to identify a more sustainable and environmentally friendly alternative to nitrogen fertilizer. Two experiments were conducted in 2018 and 2019 at Kabul University, Afghanistan, using an LD04-13265 soybean variety. The integration of animal manure and chemical fertilizer was categorized into six treatments: (1) control (no fertilizer), (2) animal manure low dose (AMLD), (3) animal manure high dose (AMHD), (4) chemical fertilizer (CF), (5) CF 50% + AMLD, and (6) CF 75% + AMLD. The results revealed that AMHD and its integration with 75% chemical fertilizer greatly influenced the vegetative growth of soybean plants in experiments I and II. The number of pods per plant and pod length significantly (p < 0.05) increased under the CF 75% + AMLD treatment. In experiment I, soybean yield increased the most with the CF treatment, followed by CF 75% + AMLD. In contrast, in experiment II, the highest yield per hectare was observed in the CF 75% + AMLD treatment, followed by CF. The CF 75% + AMLD treatment significantly increased the SPAD value in both experiments. Consequently, a strong relationship was observed between the SPAD value and yield (r = 0.74) in experiment I and between SPAD and pod length (r = 0.82) in experiment II. Incorporating animal manure with chemical fertilizer significantly impacted soybean growth and yield, offering a potential possibility for reducing reliance on nitrogen fertilizer application to mitigate environmental pollution.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optimizing Soybean Crop Performance through the Integrated Application of Organic and Chemical Fertilizers: A Study on Alkaline Soil in Afghanistan

Turabi,

Habibi,

Kakar

et al. 2024

Crops

View full text Add to dashboard Cite

show abstract

Identification of Tea Disease Under Complex Backgrounds Based on Minimalism Neural Network Architecture and Channel Reconstruction Unit

Li,

Zhang,

2024

IEEE Access

View full text Add to dashboard Cite

Tea production plays a crucial role in maintaining agricultural output, and the prompt diagnosis and efficient management of tea diseases are essential for ensuring a healthy tea industry. Traditional machine learning techniques for disease identification often require time-consuming feature engineering tasks, which can be a bottleneck in achieving accurate and efficient results. In contrast, deep learning approaches have shown superior performance in disease identification by eliminating the need for manual feature engineering. However, in complex backgrounds, such as when environmental variables and multi-scale changes interact with the imaging of tea diseases, feature extraction becomes extremely challenging. In this study, a novel technique for tea diseases recognition in a complex setting is proposed, including the channel reconstruction unit (CRU) and the minimalism neural network model VanillaNet, named VCRUNet, to address the aforementioned issues. VCRUNet incorporates the channel reconstruction unit (CRU), which effectively reduces channel redundancy between features in the convoluted neural network, thereby improving the model's ability to extract relevant features. To overcome the limitations of limited sample data, we fine-tuned the model parameters using transfer learning on a self-built tea disease dataset, supplemented with the Plant Village dataset for pre-training. The experimental results demonstrate that our proposed technique achieves an impressive accuracy of 92.48% in accurately detecting tea diseases in complex environments. This significant improvement in accuracy outperforms current methods and enhances the efficacy of tea disease identification. Meanwhile, the detection speed is 4.5 seconds per 100 images. The outcomes of this research have a direct impact on the early diagnosis and effective management of tea diseases. By providing a more accurate and efficient approach, our technique contributes to the overall agricultural output and promotes the long-term expansion of the tea industry.INDEX TERMS Tea diseases, image recognition, minimal neural network model, channel reconstruction unit, transfer learning.

show abstract

An Automated Rice Leaf Disease Identification using Deep Learning

Ali,

Agarwal,

Garg

et al. 2023

2023 International Conference on Emerging Research in Computational Science (ICERCS)

View full text Add to dashboard Cite

A two-stage feature aggregation network for multi-category soybean leaf disease identification

Cited by 3 publications

References 30 publications

Optimizing Soybean Crop Performance through the Integrated Application of Organic and Chemical Fertilizers: A Study on Alkaline Soil in Afghanistan

Optimizing Soybean Crop Performance through the Integrated Application of Organic and Chemical Fertilizers: A Study on Alkaline Soil in Afghanistan

Identification of Tea Disease Under Complex Backgrounds Based on Minimalism Neural Network Architecture and Channel Reconstruction Unit

An Automated Rice Leaf Disease Identification using Deep Learning

Contact Info

Product

Resources

About