Check the preview of 2nd version of this platform
being developed by the open MLCommons taskforce on automation and reproducibility
as a free, open-source and technology-agnostic on-prem platform.
Association Rule Based Flexible Machine Learning Module for Embedded System Platforms like Android
lib:87c16d94fcdb48d1 (v1.0.0)
Authors: Amiraj Dhawan,Shruti Bhave,Amrita Aurora,Vishwanathan Iyer
ArXiv: 1411.4076
Document: PDF DOI
Abstract URL: http://arxiv.org/abs/1411.4076v1
The past few years have seen a tremendous growth in the popularity of smartphones. As newer features continue to be added to smartphones to increase their utility, their significance will only increase in future. Combining machine learning with mobile computing can enable smartphones to become 'intelligent' devices, a feature which is hitherto unseen in them. Also, the combination of machine learning and context aware computing can enable smartphones to gauge user's requirements proactively, depending upon their environment and context. Accordingly, necessary services can be provided to users. In this paper, we have explored the methods and applications of integrating machine learning and context aware computing on the Android platform, to provide higher utility to the users. To achieve this, we define a Machine Learning (ML) module which is incorporated in the basic Android architecture. Firstly, we have outlined two major functionalities that the ML module should provide. Then, we have presented three architectures, each of which incorporates the ML module at a different level in the Android architecture. The advantages and shortcomings of each of these architectures have been evaluated. Lastly, we have explained a few applications in which our proposed system can be incorporated such that their functionality is improved.
ArXiv: 1411.4076
Document: PDF DOI
Abstract URL: http://arxiv.org/abs/1411.4076v1
The past few years have seen a tremendous growth in the popularity of smartphones. As newer features continue to be added to smartphones to increase their utility, their significance will only increase in future. Combining machine learning with mobile computing can enable smartphones to become 'intelligent' devices, a feature which is hitherto unseen in them. Also, the combination of machine learning and context aware computing can enable smartphones to gauge user's requirements proactively, depending upon their environment and context. Accordingly, necessary services can be provided to users. In this paper, we have explored the methods and applications of integrating machine learning and context aware computing on the Android platform, to provide higher utility to the users. To achieve this, we define a Machine Learning (ML) module which is incorporated in the basic Android architecture. Firstly, we have outlined two major functionalities that the ML module should provide. Then, we have presented three architectures, each of which incorporates the ML module at a different level in the Android architecture. The advantages and shortcomings of each of these architectures have been evaluated. Lastly, we have explained a few applications in which our proposed system can be incorporated such that their functionality is improved.
Relevant initiatives
Related knowledge about this paper
Reproduced results (crowd-benchmarking and competitions)
Artifact and reproducibility checklists
- ACM/cTuning artifact appendix and reproducibility checklist
- NeurIPS reproducibility checklist
- SIGPLAN's checklist for empirical evaluation
- Collective Knowledge (organizing research projects based on FAIR principles)