DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data

• URL: http://arxiv.org/abs/2008.02397v4
• Date: Thu, 12 Aug 2021 09:08:29 GMT
• Title: DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data
• Authors: Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi
• Abstract summary: Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates. Deep neural networks (DNNs) process incoming data from a fixed set of sensors with a fixed sampling rate. We introduce a dimension-adaptive pooling layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate.
• Score: 37.01965391878387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates, enabling several applications, such as power management and data-sharing control. While deep neural networks (DNNs) achieve competitive accuracy in sensor data classification, DNNs generally process incoming data from a fixed set of sensors with a fixed sampling rate, and changes in the dimensions of their inputs cause considerable accuracy loss, unnecessary computations, or failure in operation. We introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate. DAP operates on convolutional filter maps of variable dimensions and produces an input of fixed dimensions suitable for feedforward and recurrent layers. We also propose a dimension-adaptive training (DAT) procedure for enabling DNNs that use DAP to better generalize over the set of feasible data dimensions at inference time. DAT comprises the random selection of dimensions during the forward passes and optimization with accumulated gradients of several backward passes. Combining DAP and DAT, we show how to transform non-adaptive DNNs into a Dimension-Adaptive Neural Architecture (DANA), while keeping the same number of parameters. Compared to existing approaches, our solution provides better classification accuracy over the range of possible data dimensions at inference time and does not require up-sampling or imputation, thus reducing unnecessary computations. Experiments on seven datasets (four benchmark real-world datasets for human activity recognition and three synthetic datasets) show that DANA prevents significant losses in classification accuracy of the state-of-the-art DNNs and, compared to baselines, it better captures correlated patterns in sensor data under dynamic sensor availability and varying sampling rates.

Related papers

• DCP: Learning Accelerator Dataflow for Neural Network via Propagation [52.06154296196845]
  This work proposes an efficient data-centric approach, named Dataflow Code Propagation (DCP), to automatically find the optimal dataflow for DNN layers in seconds without human effort. DCP learns a neural predictor to efficiently update the dataflow codes towards the desired gradient directions to minimize various optimization objectives. For example, without using additional training data, DCP surpasses the GAMMA method that performs a full search using thousands of samples.
  arXiv  Detail & Related papers  (2024-10-09T05:16:44Z)
• Algorithm-Hardware Co-Design of Distribution-Aware Logarithmic-Posit Encodings for Efficient DNN Inference [4.093167352780157]
  We introduce Logarithmic Posits (LP), an adaptive, hardware-friendly data type inspired by posits. We also develop a novel genetic-algorithm based framework, LP Quantization (LPQ), to find optimal layer-wise LP parameters.
  arXiv  Detail & Related papers  (2024-03-08T17:28:49Z)
• SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classification [17.052624039805856]
  We propose SMORE, a novel resource-efficient domain adaptation (DA) algorithm for multi-sensor time series classification. SMORE achieves on average 1.98% higher accuracy than state-of-the-art (SOTA) DNN-based DA algorithms with 18.81x faster training and 4.63x faster inference.
  arXiv  Detail & Related papers  (2024-02-20T18:48:49Z)
• Digital Twin-Based User-Centric Edge Continual Learning in Integrated Sensing and Communication [12.78137871351962]
  We propose a digital twin (DT)-based user-centric approach for processing sensing data in an ISAC system. A DT of the ISAC device is constructed to predict the impact of potential decisions on the long-term computation cost of the server. Experiments on executing DNN-based human motion recognition tasks are conducted to demonstrate the outstanding performance of the proposed DT-based approach.
  arXiv  Detail & Related papers  (2023-11-20T22:27:14Z)
• A distributed neural network architecture for dynamic sensor selection with application to bandwidth-constrained body-sensor networks [53.022158485867536]
  We propose a dynamic sensor selection approach for deep neural networks (DNNs) It is able to derive an optimal sensor subset selection for each specific input sample instead of a fixed selection for the entire dataset. We show how we can use this dynamic selection to increase the lifetime of a wireless sensor network (WSN) by imposing constraints on how often each node is allowed to transmit.
  arXiv  Detail & Related papers  (2023-08-16T14:04:50Z)
• DOMINO: Domain-invariant Hyperdimensional Classification for Multi-Sensor Time Series Data [14.434647668734184]
  We propose DOMINO, a novel HDC learning framework addressing the distribution shift problem in noisy multi-sensor time-series data. DOMINO achieves on average 2.04% higher accuracy than state-of-the-art (SOTA) DNN-based domain generalization techniques, and delivers 16.34x faster training and 2.89x faster inference.
  arXiv  Detail & Related papers  (2023-08-07T04:44:12Z)
• Convolutional Monge Mapping Normalization for learning on sleep data [63.22081662149488]
  We propose a new method called Convolutional Monge Mapping Normalization (CMMN) CMMN consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture.
  arXiv  Detail & Related papers  (2023-05-30T08:24:01Z)
• Adaptive Anomaly Detection for Internet of Things in Hierarchical Edge Computing: A Contextual-Bandit Approach [81.5261621619557]
  We propose an adaptive anomaly detection scheme with hierarchical edge computing (HEC) We first construct multiple anomaly detection DNN models with increasing complexity, and associate each of them to a corresponding HEC layer. Then, we design an adaptive model selection scheme that is formulated as a contextual-bandit problem and solved by using a reinforcement learning policy network.
  arXiv  Detail & Related papers  (2021-08-09T08:45:47Z)
• Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data with Spatial Information [52.635997570873194]
  This work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to process complex multi-dimensional time series data with spatial information. The proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.
  arXiv  Detail & Related papers  (2021-01-12T20:08:18Z)

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.