From Cloud Down to Things: An Overview of Machine Learning in Internet of Things

Samie, Farzad; Bauer, Lars; Henkel, Jörg

doi:10.1109/jiot.2019.2893866

Cited by 193 publications

(99 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…They skip the inputs with a specified stride, and their dilation doubled for every layer. In our case, an 8-layers model with a dilation of 1,2,4,8,16,32,64,128 for each layer respectively, is enough to process a sequence of 200 frames of inertial data.…”

Section: Lightweight Inertial Odometry Neural Networkmentioning

confidence: 99%

“…The L-IONet models, i.e. WaveNet (32) and WaveNet (16) performed faster inference than the LSTM-based IONet models. Even at the swartwatch device equipped with very limited CPU and memory, our proposed L-IONet is capable of realising real-time inference, producing outputs within only 56.78 ms (WaveNet (32)) and 27 ms (WaveNet (16)) for each step.…”

Section: B Model Performance At the Edgementioning

confidence: 99%

See 1 more Smart Citation

Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference

Chen

Zhao

et al. 2020

IEEE Internet Things J.

100

View full text Add to dashboard Cite

Modern inertial measurements units (IMUs) are small, cheap, energy efficient, and widely employed in smart devices and mobile robots. Exploiting inertial data for accurate and reliable pedestrian navigation supports is a key component for emerging Internet-of-Things applications and services. Recently, there has been a growing interest in applying deep neural networks (DNNs) to motion sensing and location estimation. However, the lack of sufficient labelled data for training and evaluating architecture benchmarks has limited the adoption of DNNs in IMU-based tasks. In this paper, we present and release the Oxford Inertial Odometry Dataset (OxIOD), a first-ofits-kind public dataset for deep learning based inertial navigation research, with fine-grained ground-truth on all sequences. Furthermore, to enable more efficient inference at the edge, we propose a novel lightweight framework to learn and reconstruct pedestrian trajectories from raw IMU data. Extensive experiments show the effectiveness of our dataset and methods in achieving accurate data-driven pedestrian inertial navigation on resource-constrained devices.

show abstract

Section: Lightweight Inertial Odometry Neural Networkmentioning

confidence: 99%

Section: B Model Performance At the Edgementioning

confidence: 99%

Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference

Chen

Zhao

et al. 2020

IEEE Internet Things J.

100

View full text Add to dashboard Cite

show abstract

“…Wang machine learning and in particular neural networks (NNs) is their flexibility that makes them suitable for a wide range of applications, including computer vision [2], natural language processing [3], biomedical [4], and several others [5]- [7]. Today, machine learning on IoT devices is applied with the traditional cloud computing paradigm where the whole data processing is performed in the cloud, and the IoT devices stream the data out in raw form or possibly after simple filtering and/or compression [8], [9]. However, the number of IoT devices is expanding rapidly, and the massive amount of collected data is hard to manage by central clouds.…”

Section: Introductionmentioning

confidence: 99%

“…The new trend of IoT devices is to be "smart" to make decisions on their own, without streaming all the raw data to the cloud [11]. The edge computing paradigm is pushing the data processing to the edge of the IoT (comprising gateways and embedded end-devices) close to the sensors where the data is collected [9]. In many IoT applications, the computation can be distributed on different layers.…”

Section: Introductionmentioning

confidence: 99%

FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things

Wang

Magno

Cavigelli

et al. 2020

IEEE Internet Things J.

125

View full text Add to dashboard Cite

The growing number of low-power smart devices in the Internet of Things is coupled with the concept of "Edge Computing", that is moving some of the intelligence, especially machine learning, towards the edge of the network. Enabling machine learning algorithms to run on resource-constrained hardware, typically on low-power smart devices, is challenging in terms of hardware (optimized and energy-efficient integrated circuits), algorithmic and firmware implementations. This paper presents FANN-on-MCU, an open-source toolkit built upon the Fast Artificial Neural Network (FANN) library to run lightweight and energy-efficient neural networks on microcontrollers based on both the ARM Cortex-M series and the novel RISC-Vbased Parallel Ultra-Low-Power (PULP) platform. The toolkit takes multi-layer perceptrons trained with FANN and generates code targeted to low-power microcontrollers. This paper also presents detailed analyses of energy efficiency across the different cores, and the optimizations to handle different network sizes. Moreover, it provides a detailed analysis of parallel speedups and degradations due to parallelization overhead and memory transfers. Further evaluations include experimental results for three different applications using a self-sustainable wearable multi-sensor bracelet. Experimental results show a measured latency in the order of only a few microseconds and power consumption of a few milliwatts while keeping the memory requirements below the limitations of the targeted microcontrollers. In particular, the parallel implementation on the octa-core RISC-V platform reaches a speedup of 22x and a 69% reduction in energy consumption with respect to a single-core implementation on Cortex-M4 for continuous real-time classification.

show abstract

“…The recent developments for the internet of things (IoT) [7] and wearable computing led to the development of various types of health monitoring systems, which use data collected from various sources [8]. Moreover, these systems enable the continuous monitoring of elders; however, there are still challenges that must be considered, such as the need for high processing power and the low latency.…”

Section: Introductionmentioning

confidence: 99%

Adapted Binary Particle Swarm Optimization for Efficient Features Selection in the Case of Imbalanced Sensor Data

et al. 2020

View full text Add to dashboard Cite

Daily living activities (DLAs) classification using data collected from wearable monitoring sensors is very challenging due to the imbalance characteristics of the monitored data. A major research challenge is to determine the best combination of features that returns the best accuracy results using minimal computational resources, when the data is heterogeneous and not fitted for classical algorithms that are designed for balanced low-dimensional datasets. This research article: (1) presents a modification of the classical version of the binary particle swarm optimization (BPSO) algorithm that introduces a particular type of particles called sensor particles, (2) describes the adaptation of this algorithm for data generated by sensors that monitor DLAs to determine the best positions and features of the monitoring sensors that lead to the best classification results, and (3) evaluates and validates the proposed approach using a machine learning methodology that integrates the modified version of the algorithm. The methodology is tested and validated on the Daily Life Activities (DaLiAc) dataset.

show abstract

From Cloud Down to Things: An Overview of Machine Learning in Internet of Things

Cited by 193 publications

References 77 publications

Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference

Deep-Learning-Based Pedestrian Inertial Navigation: Methods, Data Set, and On-Device Inference

FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things

Adapted Binary Particle Swarm Optimization for Efficient Features Selection in the Case of Imbalanced Sensor Data

Contact Info

Product

Resources

About