DataLoc+: A Data Augmentation Technique for Machine Learning in
Room-Level Indoor Localization
- URL: http://arxiv.org/abs/2101.10833v1
- Date: Thu, 21 Jan 2021 17:41:41 GMT
- Title: DataLoc+: A Data Augmentation Technique for Machine Learning in
Room-Level Indoor Localization
- Authors: Amr E Hilal, Ismail Arai, Samy El-Tawab
- Abstract summary: We propose DataLoc+, a data augmentation technique for room-level indoor localization.
We evaluate the technique by comparing it to the typical direct snapshot approach using data collected from a field experiment conducted in a hospital.
- Score: 0.6961253535504979
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Indoor localization has been a hot area of research over the past two
decades. Since its advent, it has been steadily utilizing the emerging
technologies to improve accuracy, and machine learning has been at the heart of
that. Machine learning has been increasingly used in fingerprint-based indoor
localization to replace or emulate the radio map that is used to predict
locations given a location signature. The prediction quality of a machine
learning model primarily depends on how well the model was trained, which
relies on the amount and quality of data used to train it. Data augmentation
has been used to improve quality of the trained models by synthetically
producing more training data, and several approaches were used in the
literature that tackles the problem of lack of training data from different
angles. In this paper, we propose DataLoc+, a data augmentation technique for
room-level indoor localization that combines different approaches in a simple
algorithm. We evaluate the technique by comparing it to the typical direct
snapshot approach using data collected from a field experiment conducted in a
hospital. Our evaluation shows that the model trained using the proposed
technique achieves higher accuracy. We also show that the technique adapts to
larger problems using a limited dataset while maintaining high accuracy.
Related papers
- Exploring Data Redundancy in Real-world Image Classification through
Data Selection [20.389636181891515]
Deep learning models often require large amounts of data for training, leading to increased costs.
We present two data valuation metrics based on Synaptic Intelligence and gradient norms, respectively, to study redundancy in real-world image data.
Online and offline data selection algorithms are then proposed via clustering and grouping based on the examined data values.
arXiv Detail & Related papers (2023-06-25T03:31:05Z) - Post-training Model Quantization Using GANs for Synthetic Data
Generation [57.40733249681334]
We investigate the use of synthetic data as a substitute for the calibration with real data for the quantization method.
We compare the performance of models quantized using data generated by StyleGAN2-ADA and our pre-trained DiStyleGAN, with quantization using real data and an alternative data generation method based on fractal images.
arXiv Detail & Related papers (2023-05-10T11:10:09Z) - Simple and Effective Augmentation Methods for CSI Based Indoor
Localization [37.3026733673066]
We propose two algorithms for channel state information based indoor localization motivated by physical considerations.
As little as 10% of the original dataset size is enough to get the same performance as the original dataset.
If we further augment the dataset with the proposed techniques, test accuracy is improved more than three-fold.
arXiv Detail & Related papers (2022-11-19T20:27:46Z) - Invariance Learning in Deep Neural Networks with Differentiable Laplace
Approximations [76.82124752950148]
We develop a convenient gradient-based method for selecting the data augmentation.
We use a differentiable Kronecker-factored Laplace approximation to the marginal likelihood as our objective.
arXiv Detail & Related papers (2022-02-22T02:51:11Z) - Efficient training of lightweight neural networks using Online
Self-Acquired Knowledge Distillation [51.66271681532262]
Online Self-Acquired Knowledge Distillation (OSAKD) is proposed, aiming to improve the performance of any deep neural model in an online manner.
We utilize k-nn non-parametric density estimation technique for estimating the unknown probability distributions of the data samples in the output feature space.
arXiv Detail & Related papers (2021-08-26T14:01:04Z) - ALT-MAS: A Data-Efficient Framework for Active Testing of Machine
Learning Algorithms [58.684954492439424]
We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data.
The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
arXiv Detail & Related papers (2021-04-11T12:14:04Z) - Gradient-guided Loss Masking for Neural Machine Translation [27.609155878513334]
In this paper, we explore strategies that dynamically optimize data usage during the training process.
Our algorithm calculates the gradient alignment between the training data and the clean data to mask out data with negative alignment.
Experiments on three WMT language pairs show that our method brings significant improvement over strong baselines.
arXiv Detail & Related papers (2021-02-26T15:41:48Z) - Variational Information Bottleneck Model for Accurate Indoor Position
Recognition [0.0]
We propose a Variational Information Bottleneck model for accurate indoor positioning.
The proposed model consists of an encoder structure and a predictor structure.
We conduct the validation experiments on a real-world dataset.
arXiv Detail & Related papers (2021-01-26T09:29:53Z) - Bridging the Reality Gap for Pose Estimation Networks using Sensor-Based
Domain Randomization [1.4290119665435117]
Methods trained on synthetic data use 2D images, as domain randomization in 2D is more developed.
Our method integrates the 3D data into the network to increase the accuracy of the pose estimation.
Experiments on three large pose estimation benchmarks show that the presented method outperforms previous methods trained on synthetic data.
arXiv Detail & Related papers (2020-11-17T09:12:11Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z) - Radioactive data: tracing through training [130.2266320167683]
We propose a new technique, emphradioactive data, that makes imperceptible changes to this dataset such that any model trained on it will bear an identifiable mark.
Given a trained model, our technique detects the use of radioactive data and provides a level of confidence (p-value)
Our method is robust to data augmentation and backdoority of deep network optimization.
arXiv Detail & Related papers (2020-02-03T18:41:08Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.