Editorial

Jump to: Research

2 pages, 175 KiB

Open AccessEditorial

Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications

by Felipe Ortega and Emilio L. Cano

Entropy 2022, 24(7), 850; https://0-doi-org.brum.beds.ac.uk/10.3390/e24070850 - 21 Jun 2022

Cited by 1 | Viewed by 1078

Abstract

Sensors have become a key element for the development of the Information Society [...] Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

Research

Jump to: Editorial

18 pages, 1375 KiB

Open AccessArticle

Analysis of Accelerometer and GPS Data for Cattle Behaviour Identification and Anomalous Events Detection

by Javier Cabezas, Roberto Yubero, Beatriz Visitación, Jorge Navarro-García, María Jesús Algar , Emilio L. Cano and Felipe Ortega

Entropy 2022, 24(3), 336; https://0-doi-org.brum.beds.ac.uk/10.3390/e24030336 - 26 Feb 2022

Cited by 25 | Viewed by 3895

Abstract

In this paper, a method to classify behavioural patterns of cattle on farms is presented. Animals were equipped with low-cost 3-D accelerometers and GPS sensors, embedded in a commercial device attached to the neck. Accelerometer signals were sampled at 10 Hz, and data [...] Read more.

In this paper, a method to classify behavioural patterns of cattle on farms is presented. Animals were equipped with low-cost 3-D accelerometers and GPS sensors, embedded in a commercial device attached to the neck. Accelerometer signals were sampled at 10 Hz, and data from each axis was independently processed to extract 108 features in the time and frequency domains. A total of 238 activity patterns, corresponding to four different classes (grazing, ruminating, laying and steady standing), with duration ranging from few seconds to several minutes, were recorded on video and matched to accelerometer raw data to train a random forest machine learning classifier. GPS location was sampled every 5 min, to reduce battery consumption, and analysed via the k-medoids unsupervised machine learning algorithm to track location and spatial scatter of herds. Results indicate good accuracy for classification from accelerometer records, with best accuracy (0.93) for grazing. The complementary application of both methods to monitor activities of interest, such as sustainable pasture consumption in small and mid-size farms, and to detect anomalous events is also explored. Results encourage replicating the experiment in other farms, to consolidate the proposed strategy. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

16 pages, 3825 KiB

Open AccessArticle

Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters

by Javier Esteban-Escaño, Berta Castán, Sergio Castán, Marta Chóliz-Ezquerro, César Asensio, Antonio R. Laliena, Gerardo Sanz-Enguita, Gerardo Sanz, Luis Mariano Esteban and Ricardo Savirón

Entropy 2022, 24(1), 68; https://0-doi-org.brum.beds.ac.uk/10.3390/e24010068 - 30 Dec 2021

Cited by 9 | Viewed by 1983

Abstract

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, [...] Read more.

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

15 pages, 4093 KiB

Open AccessArticle

An Information Gain-Based Model and an Attention-Based RNN for Wearable Human Activity Recognition

by Leyuan Liu, Jian He, Keyan Ren, Jonathan Lungu, Yibin Hou and Ruihai Dong

Entropy 2021, 23(12), 1635; https://0-doi-org.brum.beds.ac.uk/10.3390/e23121635 - 06 Dec 2021

Cited by 11 | Viewed by 2450

Abstract

Wearable sensor-based HAR (human activity recognition) is a popular human activity perception method. However, due to the lack of a unified human activity model, the number and positions of sensors in the existing wearable HAR systems are not the same, which affects the [...] Read more.

Wearable sensor-based HAR (human activity recognition) is a popular human activity perception method. However, due to the lack of a unified human activity model, the number and positions of sensors in the existing wearable HAR systems are not the same, which affects the promotion and application. In this paper, an information gain-based human activity model is established, and an attention-based recurrent neural network (namely Attention-RNN) for human activity recognition is designed. Besides, the attention-RNN, which combines bidirectional long short-term memory (BiLSTM) with attention mechanism, was tested on the UCI opportunity challenge dataset. Experiments prove that the proposed human activity model provides guidance for the deployment location of sensors and provides a basis for the selection of the number of sensors, which can reduce the number of sensors used to achieve the same classification effect. In addition, experiments show that the proposed Attention-RNN achieves F1 scores of 0.898 and 0.911 in the ML (Modes of Locomotion) task and GR (Gesture Recognition) task, respectively. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

17 pages, 42853 KiB

Open AccessArticle

Toward Accelerated Training of Parallel Support Vector Machines Based on Voronoi Diagrams

by Cesar Alfaro, Javier Gomez, Javier M. Moguerza, Javier Castillo and Jose I. Martinez

Entropy 2021, 23(12), 1605; https://0-doi-org.brum.beds.ac.uk/10.3390/e23121605 - 29 Nov 2021

Cited by 3 | Viewed by 1601

Abstract

Typical applications of wireless sensor networks (WSN), such as in Industry 4.0 and smart cities, involves acquiring and processing large amounts of data in federated systems. Important challenges arise for machine learning algorithms in this scenario, such as reducing energy consumption and minimizing [...] Read more.

Typical applications of wireless sensor networks (WSN), such as in Industry 4.0 and smart cities, involves acquiring and processing large amounts of data in federated systems. Important challenges arise for machine learning algorithms in this scenario, such as reducing energy consumption and minimizing data exchange between devices in different zones. This paper introduces a novel method for accelerated training of parallel Support Vector Machines (pSVMs), based on ensembles, tailored to these kinds of problems. To achieve this, the training set is split into several Voronoi regions. These regions are small enough to permit faster parallel training of SVMs, reducing computational payload. Results from experiments comparing the proposed method with a single SVM and a standard ensemble of SVMs demonstrate that this approach can provide comparable performance while limiting the number of regions required to solve classification tasks. These advantages facilitate the development of energy-efficient policies in WSN. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

20 pages, 2108 KiB

Open AccessArticle

Optimal 3D Angle of Arrival Sensor Placement with Gaussian Priors

by Rongyan Zhou, Jianfeng Chen, Weijie Tan, Qingli Yan and Chang Cai

Entropy 2021, 23(11), 1379; https://0-doi-org.brum.beds.ac.uk/10.3390/e23111379 - 21 Oct 2021

Cited by 6 | Viewed by 1417

Abstract

Sensor placement is an important factor that may significantly affect the localization performance of a sensor network. This paper investigates the sensor placement optimization problem in three-dimensional (3D) space for angle of arrival (AOA) target localization with Gaussian priors. We first show that [...] Read more.

Sensor placement is an important factor that may significantly affect the localization performance of a sensor network. This paper investigates the sensor placement optimization problem in three-dimensional (3D) space for angle of arrival (AOA) target localization with Gaussian priors. We first show that under the A-optimality criterion, the optimization problem can be transferred to be a diagonalizing process on the AOA-based Fisher information matrix (FIM). Secondly, we prove that the FIM follows the invariance property of the 3D rotation, and the Gaussian covariance matrix of the FIM can be diagonalized via 3D rotation. Based on this finding, an optimal sensor placement method using 3D rotation was created for when prior information exists as to the target location. Finally, several simulations were carried out to demonstrate the effectiveness of the proposed method. Compared with the existing methods, the mean squared error (MSE) of the maximum a posteriori (MAP) estimation using the proposed method is lower by at least

25 %

when the number of sensors is between 3 and 6, while the estimation bias remains very close to zero (smaller than 0.15 m). Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

12 pages, 7108 KiB

Open AccessArticle

A Proposal of a Motion Measurement System to Support Visually Impaired People in Rehabilitation Using Low-Cost Inertial Sensors

by Karla Miriam Reyes Leiva, Milagros Jaén-Vargas, Miguel Ángel Cuba, Sergio Sánchez Lara and José Javier Serrano Olmedo

Entropy 2021, 23(7), 848; https://0-doi-org.brum.beds.ac.uk/10.3390/e23070848 - 01 Jul 2021

Cited by 2 | Viewed by 2608

Abstract

The rehabilitation of a visually impaired person (VIP) is a systematic process where the person is provided with tools that allow them to deal with the impairment to achieve personal autonomy and independence, such as training for the use of the long cane [...] Read more.

The rehabilitation of a visually impaired person (VIP) is a systematic process where the person is provided with tools that allow them to deal with the impairment to achieve personal autonomy and independence, such as training for the use of the long cane as a tool for orientation and mobility (O&M). This process must be trained personally by specialists, leading to a limitation of human, technological and structural resources in some regions, especially those with economical narrow circumstances. A system to obtain information about the motion of the long cane and the leg using low-cost inertial sensors was developed to provide an overview of quantitative parameters such as sweeping coverage and gait analysis, that are currently visually analyzed during rehabilitation. The system was tested with 10 blindfolded volunteers in laboratory conditions following constant contact, two points touch, and three points touch travel techniques. The results indicate that the quantification system is reliable for measuring grip rotation, safety zone, sweeping amplitude and hand position using orientation angles with an accuracy of around 97.62%. However, a new method or an improvement of hardware must be developed to improve gait parameters’ measurements, since the step length measurement presented a mean accuracy of 94.62%. The system requires further development to be used as an aid in the rehabilitation process of the VIP. Now, it is a simple and low-cost technological aid that has the potential to improve the current practice of O&M. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

22 pages, 1624 KiB

Open AccessArticle

Driving Risk Assessment Using Near-Miss Events Based on Panel Poisson Regression and Panel Negative Binomial Regression

by Shuai Sun, Jun Bi, Montserrat Guillen and Ana M. Pérez-Marín

Entropy 2021, 23(7), 829; https://0-doi-org.brum.beds.ac.uk/10.3390/e23070829 - 29 Jun 2021

Cited by 7 | Viewed by 2558

Abstract

This study proposes a method for identifying and evaluating driving risk as a first step towards calculating premiums in the newly emerging context of usage-based insurance. Telematics data gathered by the Internet of Vehicles (IoV) contain a large number of near-miss events which [...] Read more.

This study proposes a method for identifying and evaluating driving risk as a first step towards calculating premiums in the newly emerging context of usage-based insurance. Telematics data gathered by the Internet of Vehicles (IoV) contain a large number of near-miss events which can be regarded as an alternative for modeling claims or accidents for estimating a driving risk score for a particular vehicle and its driver. Poisson regression and negative binomial regression are applied to a summary data set of 182 vehicles with one record per vehicle and to a panel data set of daily vehicle data containing four near-miss events, i.e., counts of excess speed, high speed brake, harsh acceleration or deceleration and additional driving behavior parameters that do not result in accidents. Negative binomial regression (

A I C_{o v e r s p e e d}

= 997.0,

B I C_{o v e r s p e e d}

= 1022.7) is seen to perform better than Poisson regression (

A I C_{o v e r s p e e d}

= 7051.8,

B I C_{o v e r s p e e d}

= 7074.3). Vehicles are separately classified to five driving risk levels with a driving risk score computed from individual effects of the corresponding panel model. This study provides a research basis for actuarial insurance premium calculations, even if no accident information is available, and enables a precise supervision of dangerous driving behaviors based on driving risk scores. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

19 pages, 978 KiB

Open AccessArticle

Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear

by Rocío Aznar-Gimeno, Gorka Labata-Lezaun, Ana Adell-Lamora, David Abadía-Gallego, Rafael del-Hoyo-Alonso and Carlos González-Muñoz

Entropy 2021, 23(6), 777; https://0-doi-org.brum.beds.ac.uk/10.3390/e23060777 - 19 Jun 2021

Cited by 13 | Viewed by 4218

Abstract

The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting [...] Read more.

The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in order to prevent possible health problems in the elderly, facilitating their urban life as independently and safety as possible. This brings with it the challenge of handling the large amounts of data generated, transmitting and pre-processing that information and analysing it with the aim of obtaining useful information in real/near-real time. This is the basis of information theory. This work presents a complete system aiming at elderly people that can detect different user behaviours/events (sitting, standing without imbalance, standing with imbalance, walking, running, tripping) through information acquired from 20 types of sensor measurements (16 piezoelectric pressure sensors, one accelerometer returning reading for the 3 axis and one temperature sensor) and warn the relatives about possible risks in near-real time. For the detection of these events, a hierarchical structure of cascading binary models is designed and applied using artificial neural network (ANN) algorithms and deep learning techniques. The best models are achieved with convolutional layered ANN and multilayer perceptrons. The overall event detection performance achieves an average accuracy and area under the ROC curve of 0.84 and 0.96, respectively. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures

Figure 1

27 pages, 1529 KiB

Open AccessArticle

Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption

by Krzysztof Gajowniczek, Marcin Bator and Tomasz Ząbkowski

Entropy 2020, 22(12), 1414; https://0-doi-org.brum.beds.ac.uk/10.3390/e22121414 - 15 Dec 2020

Cited by 5 | Viewed by 2175

Abstract

Data from smart grids are challenging to analyze due to their very large size, high dimensionality, skewness, sparsity, and number of seasonal fluctuations, including daily and weekly effects. With the data arriving in a sequential form the underlying distribution is subject to changes [...] Read more.

Data from smart grids are challenging to analyze due to their very large size, high dimensionality, skewness, sparsity, and number of seasonal fluctuations, including daily and weekly effects. With the data arriving in a sequential form the underlying distribution is subject to changes over the time intervals. Time series data streams have their own specifics in terms of the data processing and data analysis because, usually, it is not possible to process the whole data in memory as the large data volumes are generated fast so the processing and the analysis should be done incrementally using sliding windows. Despite the proposal of many clustering techniques applicable for grouping the observations of a single data stream, only a few of them are focused on splitting the whole data streams into the clusters. In this article we aim to explore individual characteristics of electricity usage and recommend the most suitable tariff to the customer so they can benefit from lower prices. This work investigates various algorithms (and their improvements) what allows us to formulate the clusters, in real time, based on smart meter data. Full article

(This article belongs to the Special Issue Sensor Data Analytics: Challenges and Methods for Data-Intensive Applications)

► Show Figures