Incomplete Dissolved Oxygen Data Interpolation Based on Lagged Causality Analysis and Improved SSIM
Abstract
Based on the industrial development demands of intelligent aquaculture production operations in aquaculture facilities, an incomplete dissolved oxygen data imputation algorithm was proposed based on lag causality analysis and an improved sequence-to-sequence imputation model (SSIM) to address issues related to systematic or accidental loss of aquaculture environmental data. Firstly, environmental data such as water quality and meteorological data were collected at fixed sampling frequencies. Using the granger causality (GC) theory, the component-wise long short-term memory (cLSTM) method was employed to analyze the lag correlation between different environmental variables and dissolved oxygen time series data. The environmental variables with significant causal relationships were selected to construct the training sample set. Secondly, the SSIM framework was used to implement the imputation of missing dissolved oxygen data, and an optimization method of the SSIM model was proposed by combining a two-layer bidirectional long short-term memory (BiLSTM) structure and Dropout regularization to improve the model’s ability to represent complex features. Experimental results showed that the proposed method effectively improved the data imputation accuracy. The mean absolute error (MAE) and root mean square error (RMSE) for 1 hour missing data reached 0.04 and 0.05, respectively;for 3 hour missing data, the errors were 0.16 and 0.17, and for 5 hour missing data, the errors were 0.43 and 0.45. The research result can provide effective technical support for data quality control in aquaculture.
Keywords: smart aquaculture, dissolved oxygen content prediction, SSIM, NGC, BiLSTM, data interpolation algorit
Download Full Text:
PDFReferences
ROY S M, JAYRAIJ P, MACHAVARAM R, et al. Diversified aeration facilities for effective aquaculture systems a comprehensive review[J]. Aquaculture International, 2021(4): 1181 -1217.
RAFAEL A, CORDOVA L, NUEZ J, et al. Implementation and evaluation of open-source hardware to monitor water quality in precision aquaculturef. Sensors, 2020, 20(21) :6112.
YUAN II, XU G, YAO Z, et al. Imputation of missing data in time series for air pollutants using long short-term memory recurrent neural networks. ACM, 2018( 18) : 1293 - 1300.
MORRIS T, WHITE I, ROYSTON P. Tuning multiple imputation by predictive mean matching and local residual draws. Bmc Medical Research Methodology, 2014, 14(1) ; 75.
ZUBIR A, HUDHA K, KADIR Z. Impact behaviour modelling of magnetorheological elastomer using a non-parametric polynomial model optimized with gravitational search algorithm [J]. Journal of Mechanical Engineering, 2023, 69(11/12); 471 -482.
JAHANGIRI M, KAZEMNEJAD A, GOLDFELD К S, et al. A wide range of missing imputation approaches in longitudinal data: a simulation study and real data analysis. BMC Medical Research Methodology, 2023, 23(1) : 161.
FEKADE B, MAKSYMYUK T, KYRYK M, et al. Probabilistic recovery of incomplete sensed data in IoT [J]. IEEE Internet of Things Journal, 2017, 5(4) : 2282 -2292.
LEKE C, TWALA B, MARWALA T. Missing data prediction and classification: the use of auto-associative neural networks and optimization algorithmsf. Arxiv Preprint, arxiv; 1403.5488, 2014.
FIERO M H, HUANG S, OREN E, et al. Statistical analysis and handling of missing data in cluster randomized trials; a systematic review[J]. Trials, 2016, 17: 1 -10.
SHAN S, WANG Y, XIE X Y, et al. Analysis of regional climate variables by using neural Granger causality. Neural Computing and Applications, 2023, 35(22) : 16381 - 16402.
SIIOJAIE A, FOX E B. Granger causality: a review and recent advances. Annual Review of Statistics and Its Application, 2022, 9(1) : 289 -319.
MAZIARZ M. A review of the Granger-causality fallacy . The Journal of Philosophical Economics, 2015 , 8(2) ; 86 - 105.
STOKES P A, PURDON P L. A study of problems encountered in Granger causality analysis from a neuroscience perspective [J]. Proceedings of the National Academy of Sciences, 2017, 114(34) ; E7063 - E7072.
TANK A, COVERT I, FOTI N, et al. Neural Granger causality [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021 , 44(8) : 4267 -4279.
VATHSALA M, IIOLI G. RNN based machine translation and transliteration for Twitter data. International Journal of Speech Technology, 2020, 23(3) ; 499 -504.
KIRAN S, PATIL U, SHANKAR P, et al. Subtitle generation and video scene indexing using recurrent neural networks[ С] // 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, 2021 ; 847 -854.
SUNDER V, THOMAS S, KUO H, et al. Fine-grained textual knowledge transfer to improve RNN transducers for speech recognition and understanding [С] // ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2023 : 1-5.
CAHUANTZI R, CHEN X, GUTTEL S. A comparison of LSTM and GRU networks for learning symbolic sequences[С] // Science and Information Conference. Cham: Springer Nature Switzerland, 2023; 771 -785.
ZAHEER S, ANJUM N, HUSSAIN S, et al. A multi parameter forecasting for stock time series data using LSTM and deep learning model J . Mathematics, 2023 , 11(3): 590.
YUAN II, XU G, YAO Z,et al. Imputation of missing data in time series for air pollutants using long short-term memory recurrent neural networks[С]// Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, 2018:1293 - 1300.
VERM A II, KUMAR S. An accurate missing data prediction method using LSTM based deep learning for health care[C] // Proceedings of the 20th International Conference on Distributed Computing and Networking, 2019: 371 -376.
ZHANG Y, THORBLRN P, XIANG W, et al. SSIM—a deep learning approach for recovering missing time series sensor data [J]. IEEE Internet of Things Journal, 2019, 6(4) : 6618 -6628.
AHMED S, NIELSEN I E, TRIPATHI A, et al. Transformers in time-series analysis; a tutorial[ J]. Circuits, Systems, and Signal Processing, 2023, 42
CHEN Hong, XIA Qing, ZUO Ting, et al. Determination of shiitake mushroom grading based machine vision [J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(1) : 281 -287.
ARCHITH S, YUKTA C, ARCHANA II, et al. Analysis of M - SEIR and LSTM models for the prediction of COVID - 19 using RMSLEf M / SINGH P. Fundamentals and methods of machine and deep learning: algorithms, tools and applications. Hoboken: John Wiley & Sons, 2022; 101 - 119.
WANNINKHOF R, LEDWELL J R, BROECKER W S. GAS exchange-wind speed relation measured with sulfur hexafluoride on a lake[J]. Science, 1985,227(4691): 1224 - 1226.
GALLAGHER В К, GEARGEOURA S, FRASER D J. Effects of climate on salmonid productivity: a global meta-analysis across freshwater ecosystems [J]. Global Change Biology, 2022, 28(24) : 7250 -7269.
Refbacks
- There are currently no refbacks.
