Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Smart and Predictive Strategies in Data Fusion

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Intelligent Sensors".

Deadline for manuscript submissions: closed (31 December 2022) | Viewed by 72452

Share This Special Issue

Special Issue Editors

Dr. Bruno Marhic

E-Mail Website
Guest Editor

IT Departement, University of Picardie Jules Verne, France
Interests: decision making; smart building; machine learning; data fusion; times series; evidential theories

Dr. Laurent Delahoche

E-Mail Website
Guest Editor

IT Departement, University of Picardie Jules Verne, France
Interests: decision making; logistics; machine learning; data fusion; times series; evidential theories

Special Issue Information

Dear Colleagues,

It has become increasingly common in this day and age to not be able to handle a system that produces huge amounts of different data, especially with the emergence of our hyper-connected and hyper-digitalized world (IoT, ubiquitous sensing, etc.). Tremendous volumes of raw data are available; their smart management, in order to compute decisions or for enriched data, is a new paradigm for data fusion. Embracing this paradigm is the objective of this Special Issue. Data (multi-source information) can be heterogeneous, redundant, erroneous, uncertain, etc., implying the need for complex data-fusion strategies. In this context, smart methods are necessary to provide coherent decisions (predictive or not) or more informative data (high-level information). Moreover, strong predictions of merged data could also serve as data inputs in a smart decision system or for AI approaches. Predictive and smart fusion often outperform basic decisions when complex and/or huge amounts of data are involved. For instance, smart-fusion-based machine learning could allow the weighting of contextual data to take their uncertainty into account.

For this Special Issue, we invite authors to submit academic and industrial research papers dealing with fundamental theoretical analyses as well as engineering applications.

Dr. Bruno Marhic
Dr. Laurent Delahoche
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

autoregressive model
times series analysis
neural network
machine learning
markov models
belief functions
intelligent techniques for data fusion
multi-sensor data fusion
decision systems
smart city
health care
activity recognition
visual recognition
forecasting
econometrics
robotic application
...

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (10 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

16 pages, 710 KiB

Open AccessArticle

Effective Techniques for Multimodal Data Fusion: A Comparative Analysis

by Maciej Pawłowski, Anna Wróblewska and Sylwia Sysko-Romańczuk

Sensors 2023, 23(5), 2381; https://doi.org/10.3390/s23052381 - 21 Feb 2023

Cited by 49 | Viewed by 19318

Abstract

Data processing in robotics is currently challenged by the effective building of multimodal and common representations. Tremendous volumes of raw data are available and their smart management is the core concept of multimodal learning in a new paradigm for data fusion. Although several techniques for building multimodal representations have been proven successful, they have not yet been analyzed and compared in a given production setting. This paper explored three of the most common techniques, (1) the late fusion, (2) the early fusion, and (3) the sketch, and compared them in classification tasks. Our paper explored different types of data (modalities) that could be gathered by sensors serving a wide range of sensor applications. Our experiments were conducted on Amazon Reviews, MovieLens25M, and Movie-Lens1M datasets. Their outcomes allowed us to confirm that the choice of fusion technique for building multimodal representation is crucial to obtain the highest possible model performance resulting from the proper modality combination. Consequently, we designed criteria for choosing this optimal data fusion technique. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

19 pages, 6980 KiB

Open AccessArticle

Vision-Based Damage Detection for One-Fixed-End Structures Based on Aligned Marker Space and Decision Fusion

by Ziemowit Dworakowski, Pawel Zdziebko, Kajetan Dziedziech and Krzysztof Holak

Sensors 2022, 22(24), 9820; https://doi.org/10.3390/s22249820 - 14 Dec 2022

Cited by 2 | Viewed by 1781

Abstract

It is possible to detect damage in structures based only on vision-system-based assessment of their deformation shape under load. There is, however, a gap between available methods designed to detect damage in beam-like structures and engineering needs for monitoring structures of many different shapes. In this article, a new Aligned Marker Space method of morphing vision data is introduced. The method allows damage detection of any engineering object with one fixed support as if it were a cantilever beam. The paper also presents a new fusion technique to combine the results of several damage-detection methods for an increase in accuracy and sensitivity. The methods are tested based on numerical simulation of various structures, a blender-based simulation, and a set of practical experiments in which crane structures are subjected to damage of different sizes and locations. The optimization of damage detection methods’ metaparemeters is performed using an evolutionary algorithm designed to find the Pareto front of the solutions. The assessment of the influence of different factors, like camera position, damage position, or repetition of the experiment, is provided. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

20 pages, 1679 KiB

Open AccessArticle

Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks

by Sameh Mahjoub, Larbi Chrifi-Alaoui, Bruno Marhic and Laurent Delahoche

Sensors 2022, 22(11), 4062; https://doi.org/10.3390/s22114062 - 27 May 2022

Cited by 150 | Viewed by 13901

Abstract

With the steep rise in the development of smart grids and the current advancement in developing measuring infrastructure, short term power consumption forecasting has recently gained increasing attention. In fact, the prediction of future power loads turns out to be a key issue to avoid energy wastage and to build effective power management strategies. Furthermore, energy consumption information can be considered historical time series data that are required to extract all meaningful knowledge and then forecast the future consumption. In this work, we aim to model and to compare three different machine learning algorithms in making a time series power forecast. The proposed models are the Long Short-Term Memory (LSTM), the Gated Recurrent Unit (GRU) and the Drop-GRU. We are going to use the power consumption data as our time series dataset and make predictions accordingly. The LSTM neural network has been favored in this work to predict the future load consumption and prevent consumption peaks. To provide a comprehensive evaluation of this method, we have performed several experiments using real data power consumption in some French cities. Experimental results on various time horizons show that the LSTM model produces a better result than the GRU and the Drop-GRU forecasting methods. There are fewer prediction errors and its precision is finer. Therefore, these predictions based on the LSTM method will allow us to make decisions in advance and trigger load shedding in cases where consumption exceeds the authorized threshold. This will have a significant impact on planning the power quality and the maintenance of power equipment. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

27 pages, 2403 KiB

Open AccessArticle

Multi-Step Hourly Power Consumption Forecasting in a Healthcare Building with Recurrent Neural Networks and Empirical Mode Decomposition

by Daniel Fernández-Martínez and Miguel A. Jaramillo-Morán

Sensors 2022, 22(10), 3664; https://doi.org/10.3390/s22103664 - 11 May 2022

Cited by 11 | Viewed by 2379

Abstract

Short-term forecasting of electric energy consumption has become a critical issue for companies selling and buying electricity because of the fluctuating and rising trend of its price. Forecasting tools based on Artificial Intelligence have proved to provide accurate and reliable prediction, especially Neural Networks, which have been widely used and have become one of the preferred ones. In this work, two of them, Long Short-Term Memories and Gated Recurrent Units, have been used along with a preprocessing algorithm, the Empirical Mode Decomposition, to make up a hybrid model to predict the following 24 hourly consumptions (a whole day ahead) of a hospital. Two different datasets have been used to forecast them: a univariate one in which only consumptions are used and a multivariate one in which other three variables (reactive consumption, temperature, and humidity) have been also used. The results achieved show that the best performances were obtained with the multivariate dataset. In this scenario, the hybrid models (neural network with preprocessing) clearly outperformed the simple ones (only the neural network). Both neural models provided similar performances in all cases. The best results (Mean Absolute Percentage Error: 3.51% and Root Mean Square Error: 55.06) were obtained with the Long Short-Term Memory with preprocessing with the multivariate dataset. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

15 pages, 1395 KiB

Open AccessArticle

Rainfall Prediction System Using Machine Learning Fusion for Smart Cities

by Atta-ur Rahman, Sagheer Abbas, Mohammed Gollapalli, Rashad Ahmed, Shabib Aftab, Munir Ahmad, Muhammad Adnan Khan and Amir Mosavi

Sensors 2022, 22(9), 3504; https://doi.org/10.3390/s22093504 - 4 May 2022

Cited by 114 | Viewed by 11525

Abstract

Precipitation in any form—such as rain, snow, and hail—can affect day-to-day outdoor activities. Rainfall prediction is one of the challenging tasks in weather forecasting process. Accurate rainfall prediction is now more difficult than before due to the extreme climate variations. Machine learning techniques can predict rainfall by extracting hidden patterns from historical weather data. Selection of an appropriate classification technique for prediction is a difficult job. This research proposes a novel real-time rainfall prediction system for smart cities using a machine learning fusion technique. The proposed framework uses four widely used supervised machine learning techniques, i.e., decision tree, Naïve Bayes, K-nearest neighbors, and support vector machines. For effective prediction of rainfall, the technique of fuzzy logic is incorporated in the framework to integrate the predictive accuracies of the machine learning techniques, also known as fusion. For prediction, 12 years of historical weather data (2005 to 2017) for the city of Lahore is considered. Pre-processing tasks such as cleaning and normalization were performed on the dataset before the classification process. The results reflect that the proposed machine learning fusion-based framework outperforms other models. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

19 pages, 2976 KiB

Open AccessArticle

Differences between Systems Using Optical and Capacitive Sensors in Treadmill-Based Spatiotemporal Analysis of Level and Sloping Gait

by Dimitris Mandalidis and Ioannis Kafetzakis

Sensors 2022, 22(7), 2790; https://doi.org/10.3390/s22072790 - 5 Apr 2022

Cited by 1 | Viewed by 2926

Abstract

Modern technology has enabled researchers to analyze gait with great accuracy and in various conditions based on the needs of the trainees. The purpose of the study was to investigate the agreement between systems equipped with optical and capacitive sensors in the analysis of treadmill-based level and sloping gait. The spatiotemporal parameters of gait were measured in 30 healthy college-level students during barefoot walking on 0% (level), −10% and −20% (downhill) and +10% and +20% (uphill) slopes at hiking-related speeds using an optoelectric cell system and an instrumented treadmill. Inter-system agreement was assessed using the Intraclass Correlation Coefficients (ICCs) and the 95% limits of agreement. Our findings revealed excellent ICCs for the temporal and between moderate to excellent ICCs for the spatial parameters of gait. Walking downhill and on a 10% slope demonstrated better inter-system agreement compared to walking uphill and on a 20% slope. Inter-system agreement regarding the duration of gait phases was increased by increasing the number of LEDs used by the optoelectric cell system to detect the contact event. The present study suggests that systems equipped with optical and capacitive sensors can be used interchangeably in the treadmill-based spatiotemporal analysis of level and sloping gait. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

25 pages, 10151 KiB

Open AccessArticle

A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM

by Jinwoong Park and Eenjun Hwang

Sensors 2021, 21(22), 7697; https://doi.org/10.3390/s21227697 - 19 Nov 2021

Cited by 24 | Viewed by 3604

Abstract

An efficient energy operation strategy for the smart grid requires accurate day-ahead electricity load forecasts with high time resolutions, such as 15 or 30 min. Most high-time resolution electricity load prediction techniques deal with a single output prediction, so their ability to cope with sudden load changes is limited. Multistep-ahead forecasting addresses this problem, but conventional multistep-ahead prediction models suffer from deterioration in prediction performance as the prediction range is expanded. In this paper, we propose a novel two-stage multistep-ahead forecasting model that combines a single-output forecasting model and a multistep-ahead forecasting model to solve the aforementioned problem. In the first stage, we perform a single-output prediction based on recent electricity load data using a light gradient boosting machine with time-series cross-validation, and feed it to the second stage. In the second stage, we construct a multistep-ahead forecasting model that applies an attention mechanism to sequence-to-sequence bidirectional long short-term memory (S2S ATT-BiLSTM). Compared to the single S2S ATT-BiLSTM model, our proposed model achieved improvements of 3.23% and 4.92% in mean absolute percentage error and normalized root mean square error, respectively. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

16 pages, 4171 KiB

Open AccessCommunication

Predictive Management Algorithm for Controlling PV-Battery Off-Grid Energy System

by Tareq Alnejaili, Sami Labdai and Larbi Chrifi-Alaoui

Sensors 2021, 21(19), 6427; https://doi.org/10.3390/s21196427 - 26 Sep 2021

Cited by 10 | Viewed by 3807

Abstract

This paper introduces an energy management strategy for an off-grid hybrid energy system. The hybrid system consists of a photovoltaic (PV) module, a LiFePO4 battery pack coupled with a Battery Management System (BMS), a hybrid solar inverter, and a load management control unit. A Long Short-Term Memory network (LSTM)-based forecasting strategy is implemented to predict the available PV and battery power. The learning data are extracted from an African country with a tropical climate, which is very suitable for PV power applications. Using LSTM as a prediction method significantly increases the efficiency of the forecasting. The main objective of the proposed strategy is to control the different loads according to the forecasted energy availability of the system and the forecasted battery state of charge (SOC). The proposed management algorithm and the system are tested using Matlab/Simulink software. A comparative study demonstrates that the reduction in the energy deficit of the system is approximately 53% compared to the system without load management. In addition to this, the reliability of the system is improved as the loss of power supply probability (LPSP) decreases from 5% to 3%. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

37 pages, 8456 KiB

Open AccessArticle

Additive Ensemble Neural Network with Constrained Weighted Quantile Loss for Probabilistic Electric-Load Forecasting

by Manuel Lopez-Martin, Antonio Sanchez-Esguevillas, Luis Hernandez-Callejo, Juan Ignacio Arribas and Belen Carro

Sensors 2021, 21(9), 2979; https://doi.org/10.3390/s21092979 - 23 Apr 2021

Cited by 21 | Viewed by 4610

Abstract

This work proposes a quantile regression neural network based on a novel constrained weighted quantile loss (CWQLoss) and its application to probabilistic short and medium-term electric-load forecasting of special interest for smart grids operations. The method allows any point forecast neural network based on a multivariate multi-output regression model to be expanded to become a quantile regression model. CWQLoss extends the pinball loss to more than one quantile by creating a weighted average for all predictions in the forecast window and across all quantiles. The pinball loss for each quantile is evaluated separately. The proposed method imposes additional constraints on the quantile values and their associated weights. It is shown that these restrictions are important to have a stable and efficient model. Quantile weights are learned end-to-end by gradient descent along with the network weights. The proposed model achieves two objectives: (a) produce probabilistic (quantile and interval) forecasts with an associated probability for the predicted target values. (b) generate point forecasts by adopting the forecast for the median (0.5 quantiles). We provide specific metrics for point and probabilistic forecasts to evaluate the results considering both objectives. A comprehensive comparison is performed between a selection of classic and advanced forecasting models with the proposed quantile forecasting model. We consider different scenarios for the duration of the forecast window (1 h, 1-day, 1-week, and 1-month), with the proposed model achieving the best results in almost all scenarios. Additionally, we show that the proposed method obtains the best results when an additive ensemble neural network is used as the base model. The experimental results are drawn from real loads of a medium-sized city in Spain. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Figure 1

19 pages, 2901 KiB

Open AccessArticle

An Attention-Based Multilayer GRU Model for Multistep-Ahead Short-Term Load Forecasting

by Seungmin Jung, Jihoon Moon, Sungwoo Park and Eenjun Hwang

Sensors 2021, 21(5), 1639; https://doi.org/10.3390/s21051639 - 26 Feb 2021

Cited by 96 | Viewed by 6715

Abstract

Recently, multistep-ahead prediction has attracted much attention in electric load forecasting because it can deal with sudden changes in power consumption caused by various events such as fire and heat wave for a day from the present time. On the other hand, recurrent neural networks (RNNs), including long short-term memory and gated recurrent unit (GRU) networks, can reflect the previous point well to predict the current point. Due to this property, they have been widely used for multistep-ahead prediction. The GRU model is simple and easy to implement; however, its prediction performance is limited because it considers all input variables equally. In this paper, we propose a short-term load forecasting model using an attention based GRU to focus more on the crucial variables and demonstrate that this can achieve significant performance improvements, especially when the input sequence of RNN is long. Through extensive experiments, we show that the proposed model outperforms other recent multistep-ahead prediction models in the building-level power consumption forecasting. Full article

(This article belongs to the Special Issue Smart and Predictive Strategies in Data Fusion)

► Show Figures

Journal Menu

Journal Browser

Smart and Predictive Strategies in Data Fusion

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (10 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI