All Issue

2025 Vol.7, Issue 2 Preview Page

Research Article

Radish mass estimation using simulated harvester dynamics using GA-ELM modeling
Md Sazzadul Kabir1
,
Md Nasim Reza23
,
Kyu-Ho Lee23
,
Md Ashrafuzzaman Gulandaz4
,
Milon Chowdhury5*
1Department of Biological System Engineering, University of California Davis, Davis, CA 95616, USA
2Department of Smart Agricultural Systems, Graduate School, Chungnam National University, Daejeon 34134, Republic of Korea
3Department of Agricultural Machinery Engineering, Graduate School, Chungnam National University, Daejeon 34134, Republic of Korea
4Farm Machinery and Post-Harvest Process Engineering Division, Bangladesh Agricultural Research Institute, Joydebpur, Gazipur 1701, Bangladesh
5Biological and Agricultural Engineering Program, Kentucky State University, Frankfort, KY 40601, United States
*Corresponding Author
30 June 2025. pp. 134-149
PDF XML Citation
Abstract

Achieving precise yield mapping is a pivotal requirement for precision agriculture, but terrain-induced disturbances often complicate accurate infield measurements. To address this challenge, a computervisionbased approach was developed to estimate the massume of radishes under varying slopes and vibrations similar to field harvesting conditions using extreme learning machine (ELM), optimized via a genetic algorithm (GA) modeling. A laboratory test bench was constructed to simulate realistic harvester dynamics by incorporating adjustable slope angles (3°, 6°, and 9°) and vibration intensities (0.43, 0.78, and 0.98 m/s2). An overhead RGB camera captured images of the radishes as they passed along a conveyor exposed to these conditions. The images were then analyzed to extract relevant size parameters, and an extreme learning machine (ELM), optimized via a genetic algorithm (GA), was applied to predict the radish masses. These results were compared with the actual mass measured by the weight measuring method. Although the imagebased estimates tended to slightly underpredict across all experimental conditions, statistical analyses revealed no significant differences from the actual mass measurements. The proposed method achieved a coefficient of determination (R2) of 0.94 at 9° slope, 0.97 at 0.43 m/s2 vibration, and 0.98 when both 6° slope and 0.43 m/s2 vibration were combined. This approach demonstrates the feasibility of automated yield estimation for radishes and real-time field applicaiton for similarly shaped crops under challenging field conditions.

Keywords
Precision agriculture
Computer vision
Vibration effect
Slope
Non-destructive measurement
Yield mapping
References
1

Abdullah, S.S., Malek, M.A., Abdullah, N.S., Kisi, O., Yap, K.S. 2015. Extreme learning machines: a new approach for prediction of reference evapotranspiration. Journal of Hydrology 527: 184-195.

10.1016/j.jhydrol.2015.04.073
2

Abdullah-Al-Wadud, M., Kabir, M.H., Dewan, M.A.A., Chae, O. 2007. A dynamic histogram equalization for image contrast enhancement. IEEE Transactions on Consumer Electronics 53(2): 593-600.

10.1109/TCE.2007.381734
3

Bhujle, H.V., Chaudhuri, S. 2013. Laplacian based non-local means denoising of MR images with Rician noise. Magnetic resonance imaging 31(9): 1599-1610.

10.1016/j.mri.2013.07.00124012306
4

Bi, L., Hu, G. 2021. A genetic algorithm-assisted deep learning approach for crop yield prediction. Soft Computing 25: 10617-10628.

10.1007/s00500-021-05995-9
5

Chowdhury, M., Islam, M.N., Iqbal, M.Z., Islam, S., Lee, D.H., Kim, D.-G., Jun, H.-J., Chung, S.O. 2020. Analysis of Overturning and Vibration during Field Operation of a Tractor-Mounted 4-Row Radish Collector toward Ensuring User Safety. Machines, 8(4): 77.

10.3390/machines8040077
6

Corner, B.R., Narayanan, R.M., Reichenbach, S.E. 2003. Noise estimation in remote sensing imagery using data masking. International Journal of Remote Sensing 24(4): 689-702.

10.1080/01431160210164271
7

Ehsani, R., Karimi, D. 2010. Yield monitors for specialty crops. Landbauforsch. Völkenrode 340: 31-44.

8

Fan, G., Li, J., Hao, H. 2020. Vibration signal denoising for structural health monitoring by residual convolutional neural networks. Measurement 157: 107651.

10.1016/j.measurement.2020.107651
9

Franch, B., Vermote, E.F., Skakun, S., Roger, J.C., Becker-Reshef, I., Murphy, E., Justice, C. 2019. Remote sensing based yield monitoring: Application to winter wheat in United States and Ukraine. International Journal of Applied Earth Observation and Geoinformation 76: 112-127.

10.1016/j.jag.2018.11.012
10

Hong, S., Lee, K., Kang, D., Park, W. 2017. Analysis of static lateral stability using mathematical simulations for 3-axis tractor-baler system. Journal of Biosystems Engineering 42(2): 86-97.

11

Huang, G.B., Zhu, Q.Y., Siew, C.K. 2004. Extreme learning machine: a new learning scheme of feedforward neural networks. In 2004 IEEE international joint conference on neural networks (IEEE) 2: 985-990.

10.1109/IJCNN.2004.1380068
12

Jang, H.S., Muhammad, M.S., Choi, T.S. 2018. Removal of jitter noise in 3D shape recovery from image focus by using Kalman filter. Microscopy Research and Technique 81(2): 207-213.

10.1002/jemt.2296629114993
13

Jang, H.S., Muhammad, M.S., Kang, M.K. 2020. Removal of non-gaussian jitter noise for shape from focus through improved maximum correntropy criterion kalman filter. IEEE Access 8: 36244-36255.

10.1109/ACCESS.2020.2975274
14

Kabir, M.S., Gulandaz, M.A., Ali, M., Reza, M.N., Kabir, M.S.N., Chung, S.O., Han, K. 2024. Yield monitoring systems for non-grain crops: A review. Korean Journal of Agricultural Science, 51(1): 63-77.

10.7744/kjoas.510106
15

Kiraga, S., Reza, M.N., Chowdhury, M., Gulandaz, M.A., Ali, M., Kabir, M.S., Habineza, E., Kabir, M.S.N. and Chung, S.O. 2023. Vibration and slope conditions during harvesting affect radish mass measurements for yield monitoring: An experimental study using a laboratory test bench. Sensors 23(24): 9744.

10.3390/s2324974438139590PMC10748095
16

Kiraga, S., Reza, M.N., Lee, K.H., Gulandaz, M.A., Karim, M.R., Habineza, E., Kabir, M.S., Lee, D.H., Chung, S.O. 2025. Vibration and slope harvesting conditions affect real-time vision-based radish volume measurements: experimental study using a laboratory test bench. Journal of Biosystems Engineering 50(2): 193-209.

10.1007/s42853-025-00259-y
17

Koc, A.B. 2007. Determination of watermelon volume using ellipsoid approximation and image processing. Postharvest Biology and Technology 45(3): 366-371.

10.1016/j.postharvbio.2007.03.010
18

Lee, K., Man, Z., Wang, D., Cao, Z. 2013. Classification of bioinformatics dataset using finite impulse response extreme learning machine for cancer diagnosis. Neural Computing and Applications 22(3-4): 457-468.

10.1007/s00521-012-0847-z
19

Liu, W.C., Chung, C.E. 2014. Enhancing the predicting accuracy of the water stage using a physical-based model and an artificial neural network-genetic algorithm in a river system. Water 6(6): 1642-1661.

10.3390/w6061642
20

Mailander, M., Benjamin, C., Price, R. and Hall, S. 2010. Sugar cane yield monitoring system. Applied engineering in agriculture 26(6): 965-969.

10.13031/2013.35905
21

Nyalala, I., Okinda, C., Nyalala, L., Makange, N., Chao, Q., Chao, L., Yousaf, K., Chen, K. 2019. Tomato volume and mass estimation using computer vision and machine learning algorithms: Cherry tomato model. Journal of Food Engineering 263: 288-298.

10.1016/j.jfoodeng.2019.07.012
22

Örnek, M.N., Kahramanlı Örnek, H. 2021. Developing a deep neural network model for predicting carrots volume. Journal of Food Measurement and Characterization 15(4): 3471-3479.

10.1007/s11694-021-00923-9
23

Pathak, S.S., Pradhan, R.C., Mishra, S. 2019. Physical characterization and mass modeling of dried TERMINALIA CHEBULA fruit. Journal of Food Process Engineering 42(3): e12992.

10.1111/jfpe.12992
24

Peerlinck, A., Sheppard, J., Pastorino, J., Maxwell, B. 2019. Optimal Design of Experiments for Precision Agriculture Using a Genetic Algorithm. 2019 IEEE Congress on Evolutionary Computation (CEC), 1838-1845.

10.1109/CEC.2019.8790267
25

Pelletier, G., Upadhyaya, S.K. 1999. Development of a tomato load/yield monitor. Computers and Electronics in Agriculture 23(2): 103-117.

10.1016/S0168-1699(99)00025-3
26

UN. 2022. United Nations The Population Division of the Department of Economic and Social Affairs. Availabe online: https://www.un.org/development/desa/pd/ (accessed on 1 January 2022)

27

Vogel, E., Donat, M.G., Alexander, L.V., Meinshausen, M., Ray, D.K., Karoly, D., Meinshausen, N., Frieler, K. 2019. The effects of climate extremes on global agricultural yields. Environmental Research Letters 14(5): 054010.

10.1088/1748-9326/ab154b
28

Wang, X., Han, M. 2014. Online sequential extreme learning machine with kernels for nonstationary time series prediction. Neurocomputing 145: 90-97.

10.1016/j.neucom.2014.05.068
29

Xiong, Q., Xiong, H., Yuan, C., Kong, Q. 2023. A novel deep convolutional image-denoiser network for structural vibration signal denoising. Engineering Applications of Artificial Intelligence 117: 105507.

10.1016/j.engappai.2022.105507
30

Yousefi, J., 2011. Image binarization using Otsu thresholding algorithm. Ontario, Canada: University of Guelph, 10: 9.

31

Zhou, J., Cong, B., Liu, C. 2014. Elimination of vibration noise from an impact-type grain mass flow sensor. Precision Agriculture 15(6): 627-638.

10.1007/s11119-014-9359-4
Information
  • Publisher :Korean Society of Precision Agriculture
  • Publisher(Ko) :한국정밀농업학회
  • Journal Title :Precision Agriculture Science and Technology
  • Journal Title(Ko) :정밀농업과학기술
  • Volume : 7
  • No :2
  • Pages :134-149
  • Received Date : 2025-06-25
  • Revised Date : 2025-06-28
  • Accepted Date : 2025-06-28
  • DOI :https://doi.org/10.22765/pastj.20250011
Journal Informaiton Precision Agriculture Science and Technology Precision Agriculture Science and Technology
Online Submission & Review System
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • KCI 문헌 유사도 검사
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close