Novel encoder for ambient data compression applied to microcontrollers in agricultural robots

Yueting Wang, Minzan Li, Ronghua Ji, Minjuan Wang, Yao Zhang, Lihua Zheng

Abstract


Agricultural robots are flexible to obtain ambient information across large areas of farmland. However, it needs to face two major challenges: data compression and filtering noise. To address these challenges, an encoder for ambient data compression, named Tiny-Encoder, was presented to compress and filter raw ambient information, which can be applied to agricultural robots. Tiny-Encoder is based on the operation of convolutions and pooling, and it has a small number of layers and filters. With the aim of evaluating the performance of Tiny-Encoder, different three types of ambient information (including temperature, humidity, and light) were selected to show the performance of compressing raw data and filtering noise. In the task of compressing raw data, Tiny-Encoder obtained higher accuracy (less than the maximum error of sensors ±0.5°C or ±3.5% RH) and more appropriate size (the largest size is 205 KB) than the other two auto-encoders based convolutional operations with different compressed features (including 20, 60, and 200 features). As for filtering noise, Tiny-Encoder has comparable performance with three conventional filtering approaches (including median filtering, Gaussian filtering, and Savitzky-Golay filtering). With large kernel size (i.e., 5), Tiny-Encoder has the best performance among these four filtering approaches: the coefficients of variation with the large kernel (i.e., 5) were 8.6189% (temperature), 10.2684% (humidity), 57.3576% (light), respectively. Overall, Tiny-Encoder can be used for ambient information compression applied to microcontrollers in agricultural information acquisition robots.
Keywords: agricultural information, robot, ambient information, data compression, embedded machine learning methods
DOI: 10.25165/j.ijabe.20221504.6911

Citation: Wang Y T, Li M Z, Ji R H, Wang M J, Zhang Y, Zheng L H. Novel encoder for ambient data compression applied to microcontrollers in agricultural robots. Int J Agric & Biol Eng, 2022; 15(4): 197–204.

Keywords


agricultural information, robot, ambient information, data compression, embedded machine learning methods

Full Text:

PDF

References


Quint M, Delker C, Franklin K A, Wigge P H, Halliday K J, van Zanten M. Molecular and genetic control of plant thermomorphogenesis. Nature Plants, 2016; 2: 15190. doi: 10.1038/nplants.2015.190.

Liu H J, Gao Z Z, Zhang L W, Liu Y. Stomatal conductivity, canopy temperature and evapotranspiration of maize (Zea mays L.) to water stress in Northeast China. Int J Agric & Biol Eng, 2021; 14(2): 112–119.

Sun Y C, Bao E C, Zhu C M, Yan L L, Cao Y F, Zhang X H, et al. Effects of window opening style on inside environment of solar greenhouse based on CFD simulation. Int J Agric & Biol Eng, 2020; 13(6): 53–59.

Shrestha S, Sharma S. Assessment of climate change impact on high flows in a watershed characterized by flood regulating reservoirs. Int J Agric & Biol Eng, 2021; 14(1): 178–191.

Li H Y, Wang Y H, Xue J, Xie R Z, Wang K R Zhao Rl, et al. Allocation of maize varieties according to temperature for use in mechanical kernel harvesting in Ningxia, China. Int J Agric & Biol Eng, 2021; 14(1): 20–28.

Abade A, Ferreira P A, de Barros Vidal F. Plant diseases recognition on images using convolutional neural networks: A systematic review. Computers and Electronics in Agriculture, 2021; 185: 106125.

Xie C J, Zhang D X, Yang L, Cui T, Zhong X J, Li Y H, et al. Remote monitoring system for maize seeding parameters based on android and wireless communication. Int J Agric & Biol Eng, 2020; 13(6): 159–165.

Wang Y T, Li M Z, Ji R H, Wang M J, Zhang Y, et al. A convolutional operation-based online computation offloading approach in wireless powered multi-access edge computing networks. Computers and Electronics in Agriculture, 2022; 197: 106967. doi: 10.1016/ j.compag.2022.106967.

Hosny K M, Khashaba M M, Khedr W I, Amer F A. New vertical handover prediction schemes for LTE-WLAN heterogeneous networks. Plos One, 2019; 14(4): 0215334. doi: 10.1371/journal.pone.0215334.

Guo S T, Xiao B, Yang Y Y, Yang Y. Energy-efficient dynamic offloading and resource scheduling in mobile cloud computing. In: IEEE INFOCOM 2016, 2016; pp.1-9. doi: 10.1109/INFOCOM.2016.7524497.

Tao W, Zhao L, Wang G W, Liang R B. Review of the internet of things communication technologies in smart agriculture and challenges. Computers and Electronics in Agriculture, 2021; 189: 106352. doi: 10.1016/j.compag.2021.106352.

Perera T D P, Jayakody D N K, Chatzinotas S, Sharma V. Wireless information and power transfer: Issues, advances, and challenges. In: 2017 IEEE 86th. Technol. Conf. 2017-Septe (2018) 1–7. https://doi.org/Vehicular Technology Conference (VTV-Fall), 2017; pp.1-7. doi: 10.1109/VTCFall.2017.8288396.

ARandelhoff A, Lacour L, Marec C, Leymarie E, Lagunas J, Xing X G, Darnis G, et al. Arctic mid-winter phytoplankton growth revealed by autonomous profilers. Science Advances, 2020; 6(39): abc2678. doi: 10.1126/sciadv.abc2678.

Huffman D A. A method for the construction of minimum-redundancy codes. Resonance, 2006; 11: 91–99.

Lee H, Kim K, Choi O, Yeh H. Code based compression method for effectively using the memory of embedded devices. International Journal of Communication Systems, 2013; 26(6): 747–756.

Erguzen A, Erdal E. An efficient middle layer platform for medical imaging archives. Journal of Healthcare Engineering, 2018; Article ID 3984061. doi: 10.1155/2018/3984061.

Chen C A, Chen S L, Huang H Y, Luo C H. An efficient micro control unit with a reconfigurable filter design for wireless body sensor networks (WBSNs). Sensors, 2012; 12(21): 16211-16227.

Wang Y T, Li M Z, Ji R H, Wang M J, Zhang Y, Zheng L H. Mark-Spectra : A convolutional neural network for quantitative spectral analysis overcoming spatial relationships. Computers and Electronics in Agriculture, 2022; 192: 106624. doi: 10.1016/j.compag.2021.106624.

Li Z B, Guo R H, Li M, Chen Y R, Li G Y. A review of computer vision technologies for plant phenotyping. Computers and. Electronics in Agriculture, 2020; 176: 105672. doi: 10.1016/j.compag.2020.105672.

Jin W, Lim S, Woo S, Park C, Kim D. Decision-making of IoT device operation based on intelligent-task offloading for improving environmental optimization. Complex & Intelligent Systems, 2022. doi: 10.1007/ s40747-022-00659-z.

Porumb M, Stranges S, Pescape A, Pecchia L. Precision medicine and artificial intelligence: A pilot study on deep learning for hypoglycemic events detection based on ECG. Scientific Reports, 2020; 10: 170. doi: 10.1038/s41598-019-56927-5.

Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997; 9(8): 1735–1780.

Ai D M, Wang Y Du, Li X X, Pan H F. Colorectal cancer prediction based on weighted gene co-expression network analysis and variational auto-encoder. Biomolecules, 2020; 10(9): 1207. doi: 10.3390/ biom10091207.

Yu Y, Long J, Cai Z P. Network intrusion detection through stacking dilated convolutional autoencoders. Security and Communication Networks, 2017; Article ID 4184196. doi: 10.1155/2017/4184196.

Moran A, Alonso S, Perez D, Prada M A, Fuertes J J, Dominguez M. Feature extraction from building submetering networks using deep learning. Sensors, 2020; 20(13): 3665. doi: 10.3390/s20133665.

Shelhamer E, Long J, Darrel T. Fully convolutional networks for semantic segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017; 39(4): 640–651.

Zhou Y T, Li S H, Zhang D, Chen Y K. Seismic noise attenuation using an online subspace tracking algorithm. Geophysical Journal International, 2018; 212 (2): 1072–1097.

You Z Z, Balbastre Y, Bouvier C, Herard A-S, Gipchtein P, Hantraye P, et al. Automated individualization of size-varying and touching neurons in macaque cerebral microscopic images. Frontiers in Neuroanatomy, 2019;

: 98. doi: 10.3389/fnana.2019.00098.

Gupta S, Huang C H, Singh G P, Park B S, Chua N H, Ram R J. Portable Raman leaf-clip sensor for rapid detection of plant stress. Scientific Reports, 2020; 10: 20206. doi: 10.1038/s41598-020-76485-5.

Wang Y T, Li M Z, Ji R H, Wang M, Zhang Y, Zheng L H. Construction of complex features for predicting soil total nitrogen content based on convolution operations. Soil and Tillage Research, 2021; 213: 105109. doi: 10.1016/j.still.2021.105109.

Szegedy C, Liu W, Jia Y Q, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recogniction, 2015; pp. 1–9. doi: 10.1109/ CVPR.2015.7298594.




Copyright (c) 2022 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office