An Accurate and Low-Parameter Machine Learning Architecture for Next Location Prediction
Preprint
Abstract
Next location prediction is a discipline that involves predicting a users next location. Its applications include resource allocation, quality of service, energy efficiency, and traffic management. This paper proposes an energy-efficient, small, and low parameter machine learning (ML) architecture for accurate next location prediction, deployable on modest base stations and edge devices. To accomplish this we ran a hundred hyperparameter experiments on the full human mobility patterns of an entire city, to determine an exact ML architecture that reached a plateau of accuracy with the least amount of model parameters. We successfully achieved a reduction in the number of model parameters within published ML architectures from 202 million down to 2 million. This reduced the total size of the model parameters from 791 MB down to 8 MB. Additionally, this decreased the training time by a factor of four, the amount of graphics processing unit (GPU) memory needed for training by a factor of twenty, and the overall accuracy was increased from 80.16% to 82.54%. This improvement allows for modest base stations and edge devices which do not have a large amount of memory or storage, to deploy and utilize the proposed ML architecture for next location prediction.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- A survey on next location prediction techniques, applications, and challengesEURASIP Journal on Wireless Communications and Networking, 2022
- Next location prediction using transformersInternational Journal of Business Intelligence and Data Mining, 2022
- Predicting the next location: A self‐attention and recurrent neural network model with temporal contextTransactions on Emerging Telecommunications Technologies, 2020
- PECS: Towards personalized edge caching for future service-centric networksChina Communications, 2019
- Assessing the Energy Consumption of Proactive Mobile Edge Caching in Wireless NetworksIEEE Access, 2019
- Exploring Trajectory Prediction Through Machine Learning MethodsIEEE Access, 2019
- Modeling the Total Energy Consumption of Mobile Network Services and ApplicationsEnergies, 2019
- The temporal network of mobile phone users in Changchun Municipality, Northeast ChinaScientific Data, 2018
- Network-Wide Vehicle Trajectory Prediction in Urban Traffic Networks using Deep LearningTransportation Research Record: Journal of the Transportation Research Board, 2018
- Destination Prediction by Trajectory Distribution-Based ModelIEEE Transactions on Intelligent Transportation Systems, 2017