9 results on '"Machavaram, Rajendra"'
Search Results
2. A Two-Stage Deep-Learning Model for Detection and Occlusion-Based Classification of Kashmiri Orchard Apples for Robotic Harvesting
- Author
-
Rathore, Divya, Divyanth, L. G., Reddy, Kaamala Lalith Sai, Chawla, Yogesh, Buragohain, Mridula, Soni, Peeyush, Machavaram, Rajendra, Hussain, Syed Zameer, Ray, Hena, and Ghosh, Alokesh
- Abstract
Purpose: The process of robotic harvesting has revolutionized the agricultural industry, allowing for more efficient and cost-effective fruit picking. Developing algorithms for accurate fruit detection is essential for vision-based robotic harvesting of apples. Although deep-learning techniques are popularly used for apple detection, the development of robust models that can accord information about the fruit’s occlusion condition is important to plan a suitable strategy for end-effector manipulation. Apples on the tree experience occlusions due to leaves, stems (branches), trellis wire, or other fruits during robotic harvesting. Methods: A novel two-stage deep-learning-based approach is proposed and successfully demonstrated for detecting on-tree apples and identifying their occlusion condition. In the first stage, the system employs a cutting-edge YOLOv7 model, meticulously trained on a custom Kashmiri apple orchard image dataset. The second stage of the approach utilize the powerful EfficientNet-B0 model; the system is able to classify the apples into four distinct categories based on their occlusion condition, namely, non-occluded, leaf-occluded, stem/wire-occluded, and apple-occluded apples. Results: The YOLOv7 model achieved an average precision of 0.902 and an F1-score of 0.905 on a test set for detecting apples. The size of the trained weights and detection speed were observed to be 284 MB and 0.128 s per image. The classification model produced an overall accuracy of 92.22% with F1-scores of 94.64%, 90.91%, 86.87%, and 90.25% for non-occluded, leaf-occluded, stem/wire-occluded, and apple-occluded apple classes, respectively. Conclusion: This study proposes a novel two-stage model for the simultaneous detection of on-tree apples and classify them based on occlusion conditions, which could improve the effectiveness of autonomous apple harvesting and avoid potential damage to the end-effector due to the objects causing the occlusion.
- Published
- 2023
- Full Text
- View/download PDF
3. A Comprehensive Review of Sustainable Soil Organic Growing Media for Mat-Type Paddy Seedling Nurseries Under Indian Agronomical Condition
- Author
-
Choudhary, Vinod and Machavaram, Rajendra
- Abstract
Soil organic growing media for mat-type paddy seedling cultivation is considered the best option in the country for its capacity to help proficient and concentrated paddy plant production rapidly and uniformly. The primary goal of this review is to describe an examination of the effects of soil organic growing media on paddy seedling growth, development, quality, and quantity in mat-type paddy nurseries. According to a review of the research, paddy yield is higher for plants grown in multiple growing media than for plants grown in soil alone. Until relatively recently, the fundamental intention in choosing the growing materials in the growing media depended on performance and monetary opinions. Expanding dread over the ecological effects to evaluate more environmentally seedling growth materials. It is critical to recognize emphatic and environmentally sustainable growing materials for paddy seedling growing media in order to ensure sustained growth and development of soil organic cultivation. In this review, we describe the factors that influence the selection of growing media and remark on the most often employed soil organic elements in relation to them. We explain some of the renewable, elementary, and waste materials that have been investigated thus far, emphasizing their benefits and defiance. We explain a confirmation-based logic for a more compatible perspective to characterizing growing media and for a refiner discerning the practical and economic tangibility of modern soil organic growing media cultivation system for mat-type paddy seedling nurseries in response to the need for researchers to recognize promising new growing materials.
- Published
- 2023
- Full Text
- View/download PDF
4. An image processing approach for measurement of chili plant height and width under field conditions.
- Author
-
Gupta, Chanchal, Tewari, V.K., Machavaram, Rajendra, and Shrivastava, Prateek
- Abstract
Plant height and width is an essential phenotypic parameter that can be used not only as an indicator of overall plant growth but also used to estimate the advanced parameters such as the design of agricultural machines, estimation of yield, and site-specific applications. Presently, chili plant height and width are mostly measured manually, which is laborious and time-consuming process. The goal of this study was to develop and evaluate a real-time phenotyping system using an image processing approach to measure chili plant height and width under field conditions. The image processing algorithm was developed and compiled in the open-source computer vision library (OpenCV) and Python language using PyCharm as an integrated development environment (IDE). The developed image processing algorithm was evaluated in both static and field conditions in two plots of chili plants. The developed system was able to capture a valid image of the chili plant under field conditions and accurately estimate the height and width of the plant with a RMSE in the ranges of 0.30-0.60 cm. The height and width measured by the proposed image processing algorithm were strongly correlated (R
2 = 0.80–0.95) with manually measured values. Furthermore, the image processing approach has much more advanced features to measure the more complex geometric traits of plants. [ABSTRACT FROM AUTHOR]- Published
- 2022
- Full Text
- View/download PDF
5. Need of Automation in Paddy Nurseries for Raising Paddy Seedlings in India: a Review
- Author
-
Choudhary, Vinod and Machavaram, Rajendra
- Abstract
Purpose: Paddy seedling raising is a time-consuming, laborious, and high-energy input operation in nurseries with a systematic approach, repetitive motion, and a well-suited structured environment. The semi-automatic paddy seedling preparation units are cumbersome due to the limitations on manual feeding of feed material for desired quantity, watering, discharging, and tray stacking with respect to work duration and skill of the worker. Automation in paddy seedling preparation has allowed the farmers for saving in labor, energy input, and time required for raising seedlings and also monitoring all the variables in uniform distribution of feeding material, viz., soil organic mixture, paddy seeds, watering, tray discharging, tray stacking, and growth environment under paddy nurseries. Methods: Mat-type paddy seedling preparation using recent IoT or embedded electronic system-based technologies have been extensively surveyed for working on automatic tray discharging, tray stacking, and feed mechanisms to set up the desired quantity of material in paddy nurseries. Apart from this, we have reviewed different existing practices for paddy seedling preparation. Results: The automated systems have helped ease the paddy seedling preparation operation, efficient vigor, and healthy seedlings growth by preserving the precision, accuracy, and effectiveness in raising paddy seedlings with minimal human interference. Conclusions: This review highlights the research gaps and development in smart paddy seedling preparation technologies used in paddy transplanting with proper management and monitoring. The above advances will improve the efficiency of paddy seedling mat preparation to increase the quality and quantity of the product and pose an opportunity for the growth of the mat preparation market in the near future in paddy cultivation.
- Published
- 2022
- Full Text
- View/download PDF
6. Evaluation of a Laboratory-based Prototype of a Comb-type Picking Mechanism for Chili Pepper Harvester
- Author
-
Gupta, Chanchal, Tewari, V. K., and Machavaram, Rajendra
- Abstract
Purpose: Chili is a spice cum vegetable crop popular for the production of dry chili powder, canned or frozen chili sauces, pickles, etc. However, its conventional manual harvesting practice is time-consuming method and the unavailability of labor during the picking season causes a delay in the harvesting period which directly impart poor-quality product. Methods: In this study, a comb-type picking mechanism was developed for multiple-pass harvesting and the optimal working conditions were evaluated considering picking mechanism rotational speed and plant conveying speed. The comb-type picking mechanism was designed by considering the physical and mechanical properties of chili cultivar and the laboratory setup consists of a plant conveying system, picking mechanism, real-time operating system (RTOS), and power transmission system. Results: Picking efficiency increased significantly under higher picking unit rotational speeds and lower plant conveying speed. On the other side, chili pepper damage decreased significantly under lower picking unit rotational speeds and higher plant conveying speed. The plant conveying speed was 1.47 km/h and rotational speed of picking unit was 177.55 rpm considered for optimum performance output with a maximum picking efficiency of 78.17 % and minimum chili pepper damage of 2.62 %. Conclusions: It has been observed that the comb-type picking mechanism was efficient in picking of chili pepper from chili plant with a maximum picking efficiency at optimal settings. Further retrofitting of such picking unit to a self-propelled agriculture machine to harvest chili pepper in actual field conditions and a replacement to conventional harvesting process.
- Published
- 2022
- Full Text
- View/download PDF
7. Optimizing Energy Expenditure in Agricultural Autonomous Ground Vehicles through a GPU-Accelerated Particle Swarm Optimization-Artificial Neural Network Framework
- Author
-
Ambuj and Machavaram, Rajendra
- Abstract
•Novel GPU-accelerated PSO framework for accurate AGV energy prediction•Overcomes the high computational burden of traditional optimization techniques, enabling real-world applications•The utilization of GPU/CUDA parallel techniques expedites the execution process of neural networks•Preliminary results demonstrate remarkable improvement in prediction accuracy compared to existing methods
- Published
- 2024
- Full Text
- View/download PDF
8. Prediction of Particle Damping Parameters Using RBF Neural Network.
- Author
-
Veeramuthuvel, P., Shankar, K., Sairajan, K.K., and Machavaram, Rajendra
- Abstract
Particle damping is one of the recent passive damping methods used for effective vibration suppression. This paper discusses two different Artificial Neural Networks - Feed Forward Back Propagation Network and Radial Basis Function - applied to determine the relationship between the damping ratio and system parameters based on extensive experiments carried out on an aluminium alloy beam. The experiments are carried out with different combinations of system parameters for the estimation of damping ratio. Based on the Neural Network predictions, the factors which affect the damping performances are studied in detail for the given combination of system parameters. [ABSTRACT FROM AUTHOR]
- Published
- 2014
- Full Text
- View/download PDF
9. Joint damage identification using Improved Radial Basis Function (IRBF) networks in frequency and time domain.
- Author
-
Machavaram, Rajendra and Shankar, K.
- Subjects
RADIAL basis functions ,TIME-domain analysis ,ARTIFICIAL neural networks ,FINITE element method ,LATIN hypercube sampling ,AUTOMATIC identification - Abstract
Abstract: In this paper, a novel two-stage Improved Radial Basis Function (IRBF) neural network technique is proposed to predict the joint damage of a fifty member frame structure with semi-rigid connections in both frequency and time domain. The effective input patterns as normalized design signature indices (NDSIs) in frequency domain and acceleration responses in time domain are simulated numerically from finite element analysis (FEA) by considering different levels of damage severity using Latin hypercube sampling (LHS) technique. The conventional RBF network is used in the first stage of IRBF network and in the second stage reduced search space moving technique is employed for accurate prediction with less than 3% error. The numerical simulation of the substructural joint damage identification of a fifty member frame structure with and without addition of 5% Gaussian random noise to the input patterns is presented and compared with conventional CPN–BPN hybrid method. The two-stage IRBF method is found to be superior in accuracy to conventional hybrid methods as well as to conventional RBF method. An important benefit of the proposed novel IRBF method is the significant reduction in the computational time with good accuracy of joint damage identification. [Copyright &y& Elsevier]
- Published
- 2013
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.