Volume of Imbalance Container Prediction using Kalman Filter and Long Short-Term Memory

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

This paper develops a hybrid prediction model KALSTM that is a combination of a Kalman filter and a well-known neural network-based prediction model, Long Short-Term Memory (LSTM), to generate prediction results from the data, more specifically the weekly number of imbalance 20 general (GE) dry cargo container at Hamburg depots in Germany. The given data has been split into training and testing set. The training set has been used as input for the LSTM model to forecast the future weekly number of imbalance 20 GE containers. Even if the result from the LSTM model normally outperforms other existing forecasting models, it is still an approximation to the future because there are factors such as international political situations, overseas economic trends, and any kind of unexpected cases which increase the uncertainty of the prediction. Therefore, the output of LSTM has been used as container model xk, x^k of Kalman filter which filters the noise out with container measurement zk applying other forecasting models. Thus, a Kalman filter has been applied to improve the output of LSTM by correcting the noise of it. The prediction results of KALSTM demonstrate improved predictive performance based on common metrics such as mean squared error (MSE), root mean squared error (RMSE), and R2. Thus, the results can help decision-makers to improve tracking the volume of imbalance containers and to better prepare for further investigation to deal with the uncertainty of imbalance container volume.

Original languageEnglish
Title of host publicationArtificial Intelligence : Theory and Applications - Proceedings of AITA 2023
EditorsHarish Sharma, Antorweep Chakravorty, Shahid Hussain, Rajani Kumari
Number of pages11
Place of PublicationSingapore
PublisherSpringer Science and Business Media Deutschland
Publication date28.02.2024
Pages53-63
ISBN (print)978-981-99-8475-6
ISBN (electronic)978-981-99-8476-3
DOIs
Publication statusPublished - 28.02.2024
EventInternational Conference on Artificial Intelligence - AITA 2023: Theory and Applications - Bangalore, India
Duration: 11.08.202312.08.2023
https://scrs.in/conference/aita2023

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

    Research areas

  • Hybrid prediction model, Machine learning, State-observation model
  • Engineering

Recently viewed

Publications

  1. Improving short-term academic performance in the flipped classroom using dynamic geometry software
  2. Analysis of long-term statistical data of cobalt flows in the EU
  3. Effectiveness of a guided multicomponent internet and mobile gratitude training program - A pragmatic randomized controlled trial
  4. A Quality Data Model Based on Asset Administration Shell Technology to Enable Autonomous Quality Control Loops
  5. Probabilistic approach to modelling of recession curves
  6. A statistical study of the spatial evolution of shock acceleration efficiency for 5 MeV protons and subsequent particle propagation
  7. Finding Creativity in Predictability: Seizing Kairos in Chronos Through Temporal Work in Complex Innovation Processes
  8. 'SPREAD THE APP, NOT THE VIRUS’ – AN EXTENSIVE SEM-APPROACH TO UNDERSTAND PANDEMIC TRACING APP USAGE IN GERMANY
  9. The effects of different on-line adaptive response time limits on speed and amount of learning in computer assisted instruction and intelligent tutoring
  10. Automated Invoice Processing: Machine Learning-Based Information Extraction for Long Tail Suppliers
  11. Training effects of two different unstable shoe constructions on postural control in static and dynamic testing situations
  12. Partitioned beta diversity patterns of plants across sharp and distinct boundaries of quartz habitat islands
  13. Modeling Conditional Dependencies in Multiagent Trajectories
  14. An Interactive Layers Model of Self-Regulated Learning and Cognitive Load
  15. The Low-Code Phenomenon: Mapping the Intellectual Structure of Research
  16. Understanding Partnering Strategies in the Low-Code Platform Ecosystem
  17. Duration of Organizational Decision Processes in Organizations in View of Simulation Calculations
  18. Challenges and boundaries in implementing social return on investment
  19. Tree diversity and mycorrhizal type co-determine multitrophic ecosystem functions
  20. Is sensitivity for the complexity of mathematics teaching measurable?
  21. Wozu in Tönen denken?
  22. Formative Perspectives on the Relation Between CSR Communication and CSR Practices
  23. PID Controller Application in a Gimbal Construction for Camera Stabilization and Tracking
  24. Embarrassment as a public vs. private emotion and symbolic coping behaviour
  25. Comparing Empirical Methodologies in Pragmatics
  26. Are Acute Effects of Foam-Rolling Attributed to Dynamic Warm Up Effects? A Comparative Study
  27. Construct- and criterion-related validity of the German Core Self-Evaluations Scale
  28. Neural correlates of the enactment effect in the brain