Classification of Indoor Environments for IoT Applications: A Machine Learning Approach

AlHajri, Mohamed I.; Ali, Nazar; Shubair, Raed M.

doi:10.1109/lawp.2018.2869548

Cited by 106 publications

(51 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [29], the SVM was used for antenna selection, while in [30], both the SVM and Naive Bayesian were utilized for antenna selection. Other applications include caching [31]- [33], resource allocation [34]- [36], interference management [37], channel estimation [38]- [40], modulation classification [41], scenario classification [42], user clustering [43], etc.…”

Section: Machine Learning In Wireless Communicationsmentioning

confidence: 99%

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

Huang

Wang

Bai

et al. 2020

IEEE Trans. Big Data

View full text Add to dashboard Cite

The standardization process of the fifth generation (5G) wireless communications has recently been accelerated and the first commercial 5G services would be provided as early as in 2018. The increasing of enormous smartphones, new complex scenarios, large frequency bands, massive antenna elements, and dense small cells will generate big datasets and bring 5G communications to the era of big data. This paper investigates various applications of big data analytics, especially machine learning algorithms in wireless communications and channel modeling. We propose a big data and machine learning enabled wireless channel model framework. The proposed channel model is based on artificial neural networks (ANNs), including feed-forward neural network (FNN) and radial basis function neural network (RBF-NN). The input parameters are transmitter (Tx) and receiver (Rx) coordinates, Tx-Rx distance, and carrier frequency, while the output parameters are channel statistical properties, including the received power, root mean square (RMS) delay spread (DS), and RMS angle spreads (ASs). Datasets used to train and test the ANNs are collected from both real channel measurements and a geometry based stochastic model (GBSM). Simulation results show good performance and indicate that machine learning algorithms can be powerful analytical tools for future measurement-based wireless channel modeling.

show abstract

Section: Machine Learning In Wireless Communicationsmentioning

confidence: 99%

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

Huang

Wang

Bai

et al. 2020

IEEE Trans. Big Data

View full text Add to dashboard Cite

show abstract

“…This section is based on prior work by the authors [24], [25] where a machine learning approach was used for indoor environment classification based on real measurements of the RF signal. Extensive numerical investigations [24], [25] showed that a machine learning algorithm using k-NN method, utilizing a hybrid combination of CTF and FCF, outperforms other methods such as Decision Tree [33] and Support Vector Machine (SVM) [34] in identifying the type of the indoor environment with a classification accuracy of 99.3%. The required time was found to be less than 10µs, which verifies that the adopted k-NN machine learning algorithm is a successful candidate for real-time IoT deployment scenarios.…”

Section: A Machine Learning For Indoor Environment Identificationmentioning

confidence: 99%

“…This paper presents a novel method based on a cascaded two-stage machine learning approach for highly-accurate and robust localization in indoor environments using adaptive selection and combination of RF features. In the proposed method, and based on the authors prior work [24], [25], machine learning is first used to identify the type of the indoor environment based on real data measurements of the RF signal in different indoor scenarios. Then, in the second stage, machine learning is employed to identify the most appropriate selection and combination of RF features that yield the highest localization accuracy.…”

Section: Introductionmentioning

confidence: 99%

Indoor Localization for IoT Using Adaptive Feature Selection: A Cascaded Machine Learning Approach

AlHajri¹,

Ali²,

Shubair³

2019

Antennas Wirel. Propag. Lett.

Self Cite

View full text Add to dashboard Cite

Evolving Internet-of-Things (IoT) applications often require the use of sensor-based indoor tracking and positioning, for which the performance is significantly improved by identifying the type of the surrounding indoor environment. This identification is of high importance since it leads to higher localization accuracy. This paper presents a novel method based on a cascaded two-stage machine learning approach for highly-accurate and robust localization in indoor environments using adaptive selection and combination of RF features. In the proposed method, machine learning is first used to identify the type of the surrounding indoor environment. Then, in the second stage, machine learning is employed to identify the most appropriate selection and combination of RF features that yield the highest localization accuracy. Analysis is based on k-Nearest Neighbor (k-NN) machine learning algorithm applied on a real dataset generated from practical measurements of the RF signal in realistic indoor environments.Received Signal Strength, Channel Transfer Function, and Frequency Coherence Function are the primary RF features being explored and combined. Numerical investigations demonstrate that prediction based on the concatenation of primary RF features enhanced significantly as the localization accuracy improved by at least 50% to more than 70%.

show abstract

“…Com a maior mobilidade trazida pela ausência de conexões físicas em redes de sensores sem fio, esses dispositivos podem ser utilizados em diversos ambientes. Em muitos casos, a determinação do tipo de ambiente, onde o sensor está localizado desempenha um papel importante na eficiência da rede de sensores, uma vez que permite um ajuste mais adequado do consumo de energia dos sensores que a compõe [Alhajri et al 2018].…”

Section: Introductionunclassified

“…Diversos trabalhos na literatura têm sido propostos com o intuito de se classificar, de forma automática e em tempo real, o tipo de ambiente que circunda um determinado sensor, baseado principalmente na análise das assinaturas do canal de RF utilizado na comunicação com o sensor através da aplicação de sistemas baseados em aprendizagem de máquina [Alhajri et al 2016], [Zhang et al 2008], [Alhajri et al 2018].…”

Section: Introductionunclassified

Self-Organizing Fuzzy Rule-Based Approach for Dealing with the Classification of Indoor Environments for IoT Applications

Dias

Aguiar

Hell

et al. 2019

Anais Do XVI Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2019)

View full text Add to dashboard Cite

Atualmente, grande parte dos sensores utilizados em Internet das Coisas adota tecnologia sem fio, a fim de facilitar a construção de redes de sensoriamento. Neste sentido, a classificação do tipo de ambiente no qual estes sensores estão localizados exerce um importante papel no desempenho de tais redes de sensoriamento, uma vez que pode ser utilizada na determinação de níveis mais eficientes de consumo de energia dos sensores que as compõe. Assim, neste trabalho é apresentada uma abordagem baseada em Classificadores Fuzzy Auto-organizáveis para a classificação de ambientes internos a partir de medições em tempo real do sinal de radiofrequência de uma rede de sensoriamento sem fio em um ambiente real. Os resultados experimentais apresentados mostram que a abordagem proposta obteve alto desempenho com baixo custo computacional na solução do problema apresentado.

show abstract

Classification of Indoor Environments for IoT Applications: A Machine Learning Approach

Cited by 106 publications

References 25 publications

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

A Big Data Enabled Channel Model for 5G Wireless Communication Systems

Indoor Localization for IoT Using Adaptive Feature Selection: A Cascaded Machine Learning Approach

Self-Organizing Fuzzy Rule-Based Approach for Dealing with the Classification of Indoor Environments for IoT Applications

Contact Info

Product

Resources

About