| 1. |
- Kaler, Nikhil, et al.
(författare)
-
Deep learning-based robust analysis of laser bio-speckle data for detection of fungal-infected soybean seeds
- 2023
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 11, s. 89331-89348
-
Tidskriftsartikel (refereegranskat)abstract
- T Seed-borne diseases play a crucial role in affecting the overall quality of seeds, efficient disease management, and crop productivity in agriculture. Detection of seed-borne diseases using machine learning (ML) and deep learning (DL) can automate the process at large-scale industrial applications for providinghealthy and high-quality seeds. ML-based methods are accurate for detecting and classifying fungal infectionin seeds; however, their performance degrades in the presence of noise. In this work, we propose a laser biospeckle based DL framework for detection and classification of disease in seeds under varying experimental parameters and noises. We develop a DL-based spatio-temporal analysis technique for bio-speckle data using DL networks, including neural networks (NN), convolutional neural networks (CNN) with long-short-termmemory (LSTM), three-dimensional convolutional neural networks (3D CNN), and convolutional LSTM (ConvLSTM). The robustness of the DL models to noise is a key aspect of this spatio-temporal analysis.In this study, we find that the ConvLSTM model has an accuracy of 97.72% on the test data and is robust to different types of noises with an accuracy of 97.72%, 94.31%, 98.86%, and 96.59% . Furthermore, the robust model (ConvLSTM) is evaluated for variations in experimental data parameters such as frame rate, frame size, and number of frames used. This model is also sensitive towards detecting bio-speckle activity of different order, and it shows average test accuracy of 99% for detecting four different classes.
|
|
| 2. |
- Ravindran, Gobinath, et al.
(författare)
-
Global Research Trends in Engineered Soil Development through Stabilisation: Scientific Production and Thematic Breakthrough Analysis
- 2023
-
Ingår i: Buildings. - : MDPI. - 2075-5309. ; 13:10
-
Tidskriftsartikel (refereegranskat)abstract
- Soil, a naturally occurring resource, is increasingly used as a construction material. Stabilisation strengthens soil, which is weak as an engineering material. Stabilising soil changes its physical qualities, enhancing its strength. Soil stabilisation increases the shear strength and load-bearing capacity. Soil stabilisation refers to any endeavour to change natural soil for engineering purposes using physical, chemical, mechanical, or biological methods, or a mix of these. Strengthening road pavements includes improving the load-bearing capacity, tensile strength, and performance of unstable subsoils, sands, and waste materials. Due to market demands and scientific advances, the number of soil-stabilising additives has increased. These innovative stabilisers include reinforcing fibres, calcium chloride, sodium chloride, and cross-linking water-based styrene acrylic polymers, which are geopolymers that boost the load-bearing capacity and tensile strength of soil. Many materials are being explored for soil stabilisation. In this article, the authors investigated the direction of soil stabilisation research. Scientometric analysis identifies stabilisation challenges and research trends in the field. This study analysed research patterns by countries, authors, institutions, keywords, and journals from 1959 to 2023; in 2021, 150 articles were published, which was the highest number in a year. Citations peaked at 3084 in 2022. With 253 publications and 3084 citations, India was the most productive country. Iran and France published the fewest, 34 and 33, respectively. The Islamic Azad University and the National Institute of Technology had the fewest published articles with 17 articles. This work can help track soil stabilisation research and will serve as an information document for future research.
|
|
