Indoor Wireless Localization Using Consumer-Grade 60 GHz Equipment with Machine Learning for Intelligent Material Handling

Vashist, Abhishek; Bhanushali, Darshan; Relyea, Robert; Hochgraf, Clark; Ganguly, Amlan; Manoj, P K; Ptucha, Raymond; Kwasinski, Alexis; Kühl, Michael

doi:10.1109/icce46568.2020.9043072

Cited by 19 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, it does not meet the performances in term of complexity since it requires a large number of neurons and numerous hidden layers to converge. These performances and these architectural complexity agree with the work of Vashist et al 43 Moreover, it is difficult to implement it in an embedded system such as a field‐programmable gate array (FPGA) device. The objective is the design of an IPS 3D hardware by an electronic realization, which will allow the parallelization of its operations.…”

Section: Implementation Evaluation and Discussionsupporting

confidence: 86%

A novel advanced 3D‐IPS based on mmWaves and SOM‐MLP neural network

TamazirtLotfi

AlilatFarid

AgoulmineNazim

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

This article proposes a new approach for intelligent indoor 3D positioning that works in the millimeter waves (that constitutes a cornerstone of 5G networks). The solution is based on a combination of a multilayer perceptron network and a self‐organizing map. The solution relies on a precise model of the millimeter frequency channel at 60 GHz and the building of a database of fingerprinting of localization data. The solution approach is based on two parts. In the first part, we specified the target environment for positioning as well as the set of millimeter wave (mmWave) access points (APs) to be deployed in predefined positions. Then, we built a reference database of received signal strengths, azimuths of arrival, and elevations of arrival at each 3D position of the target environment (with a predefined step). The second part of the approach consists of designing a novel neural network architecture that is first trained using the database data and then used to estimate any position in the environment based on the information of the received mmWave signals sent by the different mmWave installed APs. In a normal scenario (without loss of data), the obtained results indicate a millimeter level of the generalization error of the estimated 3D positions. In the case of missing data that may due to potential failures in the system, the obtained accuracy is of the order of 34 cm.

show abstract

Section: Implementation Evaluation and Discussionsupporting

confidence: 86%

A novel advanced 3D‐IPS based on mmWaves and SOM‐MLP neural network

TamazirtLotfi

AlilatFarid

AgoulmineNazim

2021

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…This incurs significant latencies, and thus it is limited to few tens of nodes due to involved complexity. The large execution time and memory consumption of simulation-based models motivate us to consider data-driven-based models in machine learning (ML) domain [40]. Motivated by the most recent progress of self-supervised learning in ML community, cutting-edge deep learning methods are able to learn the transformation mapping of complex data from one status to another [41].…”

Section: ) Scalability Of Traditional Malware Confinement Methodsmentioning

confidence: 99%

Cognitive and Scalable Technique for Securing IoT Networks Against Malware Epidemics

et al. 2020

View full text Add to dashboard Cite

The sheer volume of IoT networks being deployed today presents a major "attack surface" and poses significant security risks at a scale never encountered before. In other words, a single IoT device/node that gets infected with malware has the potential to spread the malicious activities across the network, eventually ceasing the network functionality or compromising the network. Simply detecting and quarantining the malware in IoT networks does not guarantee preventing malware propagation. On the other hand, use of traditional control theory for malware confinement is not effective, as most of the existing works do not consider real-time malware control strategies that can be implemented using uncertain infection information from the nodes in the network or have the containment problem decoupled from network performance. In response, in this work, we propose a two-pronged approach with malware detection at nodelevel, and confinement of malware at network-level. We deploy a recently proposed lightweight runtime malware detector at the node-level that employs Hardware Performance Counter (HPC) values for malware detection. This node-level malware information is combined with the malware propagation information and then fed during runtime to a stochastic predictive controller to confine the malware propagation without hampering the network performance. Synthesizing the node-level malware information with the model predictive containment strategy leads to achieving an average network throughput of nearly 200% of that of IoT network without any defense, and up to 160% of that of network with commonly employed state-ofthe-art heuristic approaches for malware confinement. Furthermore, to scale with ever-increasing network topology sizes, we introduce a novel multi-attribute graph translation that can predict the network topology and node state information when provided with a snapshot of topology and node-level malware infection. The proposed multi-attribute graph translation has <5.88 Root Mean Square Error (RMSE) compared to the model predictive containment strategy and has shown nearly constant graph translation time and limited resource utilization independent of the network size.

show abstract

“…Finally, we see that the SNR parameter is starting to be used, in particular in combination with those WiFi networks that use mmWave [9,21] instead of the classic networks that broadcast on traditional frequency channels, 2.4 GHz and 5 GHz. We also see better positioning accuracy with these technologies, with which the best and the third best results are obtained.…”

Section: B Types Of Wifi Signal Parameter Usedmentioning

confidence: 99%

New trends in indoor positioning based on WiFi and machine learning: A systematic review

Bellavista-Parent,

Torres-Sospedra,

Perez-Navarro

2021

Preprint

View full text Add to dashboard Cite

Currently there is no standard indoor positioning system, similar to outdoor GPS. However, WiFi signals have been used in a large number of proposals to achieve the above positioning, many of which use machine learning to do so. But what are the most commonly used techniques in machine learning? What accuracy do they achieve? Where have they been tested? This article presents a systematic review of works between 2019 and 2021 that use WiFi as the signal for positioning and machine learning models to estimate indoor position. 64 papers have been identified as relevant, which have been systematically analyzed for a better understanding of the current situation in different aspects. The results show that indoor positioning based on WiFi trends use neural network-based models, evaluated in empirical experiments. Despite this, many works still conduct an assessment in small areas, which can influence the goodness of the results presented.

show abstract

Indoor Wireless Localization Using Consumer-Grade 60 GHz Equipment with Machine Learning for Intelligent Material Handling

Cited by 19 publications

References 14 publications

A novel advanced 3D‐IPS based on mmWaves and SOM‐MLP neural network

A novel advanced 3D‐IPS based on mmWaves and SOM‐MLP neural network

Cognitive and Scalable Technique for Securing IoT Networks Against Malware Epidemics

New trends in indoor positioning based on WiFi and machine learning: A systematic review

Contact Info

Product

Resources

About