Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Sensor Intelligence through Neurocomputing

Special Issue Editors
Special Issue Information
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 (30 April 2023) | Viewed by 50079

Share This Special Issue

Special Issue Editors

Prof. Dr. Kyandoghere Kyamakya

E-Mail Website
Guest Editor

Institute for Smart Systems Technologies, University Klagenfurt, A9020 Klagenfurt, Austria
Interests: intelligent transport systems; telecommunications; neuro-computing; machine learning and pattern recognition; nonlinear dynamics
Special Issues, Collections and Topics in MDPI journals

Dr. Fadi Al-Machot

E-Mail Website
Guest Editor

Alpen-Adria-Universität Klagenfurt, Department of Applied Informatics, Klagenfurt, Austria
Interests: machine learning; pattern recognition; image processing; data mining; video understanding; cognitive modeling and recognition
Special Issues, Collections and Topics in MDPI journals

Dr. Ahmad Haj Mosa

E-Mail Website
Guest Editor

Alpen-Adria-Universität Klagenfurt, Klagenfurt, Austria
Interests: machine learning; cognitive neuroscience; applied mathematics; machine vision
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Jean Chamberlain Chedjou

E-Mail Website
Guest Editor

Associate Professor, Department of Smart System Technologies, University of Klagenfurt, 9020 Klagenfurt, Austria
Interests: analog computing; dynamical systems; neuro-computing with applications in systems simulation and ultra-fast differential equations solving; nonlinear oscillatory theory with applications; traffic modeling and simulation; traffic telematics
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Zhong Li

E-Mail Website
Guest Editor

FernUniversität in Hagen, Hagen, Germany
Interests: Computational Intelligence; Fuzzy Logics; Nonlinear Dynamics; Complex Systems; Chaos Theory; Power Electronics

Prof. Dr. Antoine Bagula

E-Mail Website
Guest Editor

University of the Western Cape, ISAT Laboratory, Bellville, South Africa
Interests: internet-of-things; artificial intelligence; blockchain technologies; next generation networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear colleagues,

Sensor intelligence is a key enabler of better-performing, more energy-efficient, more robust (and thus more adaptive to environmental changes), much faster (and better fitting to any real-time constraints), and very data-rate-efficient sensor systems and/or sensor networks. Various highly innovative technical concepts of the future crucially need intelligent sensors. Examples of such contexts include cyber-physical systems, digital twins, IoT (Internet of Things), IIoT (Industrial Internet of Things), smart factories of the future, autonomous driving systems, smart online health systems of the future, etc.

However, sensor intelligence does face a series of difficult research challenges which need to be addressed by the relevant research community. Amongst the core scientific and technical challenges, efficient data compression, compressive sensing, and robust prediction or forecasting capability are some of the most prominent.

Selected keywords (not an exhaustive list):

Neurocomputing-based compressed sensing
Data compression schemes in sensors or in sensor networks
Data compression schemes for power reduction
Joint compressing and caching of data within sensor networks
On-board lossy compression schemes
Image-based compression of sensor data
Spatio-temporal data compression for sensor networks
Data compression and optimization schemes in cloud storage
Compressive sensing in the context of sensor data fusion
Edge machine learning w.r.t. to data compression and/or data forecasting
Combined compression of multiple data streams
Autoencoder techniques for robust and efficient data compression
Quantum data compression
Relational behavior forecasting from sensor data
Deep-learning-based forecasting of sensor data
Forecasting concepts w.r.t. or combined with tracking and state estimation
Data prediction in clustered sensor networks
Data-driven anomaly detection supported by prediction models
Traffic data forecasting (e.g., in transportation or in communication systems)
Sensor intelligence support of predictive maintenance
Sensor events prediction

Prof. Dr. Kyandoghere Kyamakya
Dr. Fadi Al-Machot
Dr. Ahmad Haj Mosa
Prof. Dr. Jean Chamberlain Chedjou
Prof. Dr. Zhong Li
Prof. Dr. Antoine Bagula
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.

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.
e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

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

Published Papers (13 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

20 pages, 2137 KiB

Open AccessArticle

Data Augmentation for a Virtual-Sensor-Based Nitrogen and Phosphorus Monitoring

by Thulane Paepae, Pitshou N. Bokoro and Kyandoghere Kyamakya

Sensors 2023, 23(3), 1061; https://doi.org/10.3390/s23031061 - 17 Jan 2023

Cited by 6 | Viewed by 1836

Abstract

To better control eutrophication, reliable and accurate information on phosphorus and nitrogen loading is desired. However, the high-frequency monitoring of these variables is economically impractical. This necessitates using virtual sensing to predict them by utilizing easily measurable variables as inputs. While the predictive performance of these data-driven, virtual-sensor models depends on the use of adequate training samples (in quality and quantity), the procurement and operational cost of nitrogen and phosphorus sensors make it impractical to acquire sufficient samples. For this reason, the variational autoencoder, which is one of the most prominent methods in generative models, was utilized in the present work for generating synthetic data. The generation capacity of the model was verified using water-quality data from two tributaries of the River Thames in the United Kingdom. Compared to the current state of the art, our novel data augmentation—including proper experimental settings or hyperparameter optimization—improved the root mean squared errors by 23–63%, with the most significant improvements observed when up to three predictors were used. In comparing the predictive algorithms’ performances (in terms of the predictive accuracy and computational cost), k-nearest neighbors and extremely randomized trees were the best-performing algorithms on average. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

20 pages, 4622 KiB

Open AccessArticle

Heart Rate Estimation from Incomplete Electrocardiography Signals

by Yawei Song, Jia Chen and Rongxin Zhang

Sensors 2023, 23(2), 597; https://doi.org/10.3390/s23020597 - 4 Jan 2023

Cited by 3 | Viewed by 3280

Abstract

As one of the most remarkable indicators of physiological health, heart rate (HR) has become an unfailing investigation for researchers. Unlike many existing methods, this article proposes an approach to implement short-time HR estimation from electrocardiography in time series missing patterns. Benefiting from the rapid development of deep learning, we adopted a bidirectional long short-term memory model (Bi-LSTM) and temporal convolution network (TCN) to recover complete heartbeat signals from those with durations are less than one cardiac cycle, and the estimated HR from recovered segment combining the input and the predicted output. We also compared the performance of Bi-LSTM and TCN in PhysioNet dataset. Validating the method over a resting heart rate range of 60–120 bpm in the database without significant arrhythmias and a corresponding range of 30–150 bpm in the database with arrhythmias, we found that networks provide an estimated approach for incomplete signals in a fixed format. These results are consistent with real heartbeats in the normal heartbeat dataset (γ > 0.7, RMSE < 10) and in the arrhythmia database (γ > 0.6, RMSE < 30), verifying that HR could be estimated by models in advance. We also discussed the short-time limits for the predictive model. It could be used for physiological purposes such as mobile sensing in time-constrained scenarios, and providing useful insights for better time series analyses in missing data patterns. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

Figure 1
The diagram of the proposed iHR estimation approach employing time-series forecasting with CNN and RNN, and its main three steps: data preprocessing, sequence forecasting, and HR estimation. Following ECG signal normalization, a pretrained neural network would be able to generate time series for a short period of time in the future. We calculate a complete RRI and estimate HR in advance by combining the restored and original signals. Full article ">Figure 2
System structure of the iHR estimation model using Bi-LSTM. The original signal as input for Bi-LSTM, and hidden units of LSTM capture temporal dependencies in time series. Dropout layer close to each Bi-LSTM layer to reduce overfitting. To generate HR estimation sequences, three layers of Bi-LSTM and dropout, an FC layer, and an output layer were stacked. Full article ">Figure 3
The system structure of the iHR estimation model using TCN in AlexNet style. Stacking residual blocks with dilation casual convolution layers using skip connection (simplified and visualized by the black dash boxed areas), a generic TCN model would be designed for sequence modeling. The bottom boxed areas show an example of a residual connection in a TCN. Two solid black lines indicate that the input of the Dilated Conv1 module in the top boxed area corresponds to the input layer in the bottom boxed area, and the input of Dilated Conv2 module in the top boxed area corresponds to the block output layer in the bottom boxed area. In this example, a dilated causal convolution with dilation factors d = 1,2 and filter size k = 3, the origin lines are filters in the residual function, and the blue lines are identity mappings. Across layers via identity mappings, skip connections effectively mitigate the gradient problem in deep models. To generate forecasting sequences, we also use an FC layer and output layer. Full article ">Figure 4
Examples of data segmenting of the recorded ECG. The time-leading parts are displayed in blue and the time-lagged part are displayed in orange. The elements between the time-leading parts and the time-lagged parts (grey) are deleted. Full article ">Figure 5
Prediction results of two sequences (a,b). Black lines denote the input sequence and green dash lines denote the ground truth ECG. The red imaginary lines denote the predicted ECG from the proposed method. The change in shape does not affect the determination of the extremum point. Full article ">Figure 6
Results comparison on inputs of different lengths. (a) The absolute value of mean error; (b) standard deviation; (c) mean absolute percentage error; (d) root mean square error; and (e) Pearson correlation coefficient. The red line denotes the predicted results of CNN models and the blue line denotes the results of RNN models. As the time duration of input fell from 0.5 s to 0.2 s, a high, similar trend was demonstrated in Bi-LSTM and TCN. Full article ">Figure 7
The statistical histograms of real HR and estimated HR in the test set. The red bar represents the ground truth HR, and the blue bar represents the predicted values by TCN. We also plot the kernel density curves of real HR and estimated HR with the red line and blue line, respectively, in the upper right corner. Full article ">

12 pages, 1751 KiB

Open AccessArticle

A Novel Zernike Moment-Based Real-Time Head Pose and Gaze Estimation Framework for Accuracy-Sensitive Applications

by Hima Deepthi Vankayalapati, Swarna Kuchibhotla, Mohan Sai Kumar Chadalavada, Shashi Kant Dargar, Koteswara Rao Anne and Kyandoghere Kyamakya

Sensors 2022, 22(21), 8449; https://doi.org/10.3390/s22218449 - 3 Nov 2022

Cited by 3 | Viewed by 1899

Abstract

A real-time head pose and gaze estimation (HPGE) algorithm has excellent potential for technological advancements either in human–machine or human–robot interactions. For example, in high-accuracy advent applications such as Driver’s Assistance System (DAS), HPGE plays a crucial role in omitting accidents and road hazards. In this paper, the authors propose a new hybrid framework for improved estimation by combining both the appearance and geometric-based conventional methods to extract local and global features. Therefore, the Zernike moments algorithm has been prominent in extracting rotation, scale, and illumination invariant features. Later, conventional discriminant algorithms were used to classify the head poses and gaze direction. Furthermore, the experiments were performed on standard datasets and real-time images to analyze the accuracy of the proposed algorithm. As a result, the proposed framework has immediately estimated the range of direction changes under different illumination conditions. We obtained an accuracy of ~85%; the average response time was 21.52 and 7.483 ms for estimating head poses and gaze, respectively, independent of illumination, background, and occlusion. The proposed method is promising for future developments of a robust system that is invariant even to blurring conditions and thus reaching much more significant performance enhancement. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

17 pages, 2061 KiB

Open AccessArticle

Short-Term Solar Irradiance Prediction Based on Adaptive Extreme Learning Machine and Weather Data

by Ahmad Alzahrani

Sensors 2022, 22(21), 8218; https://doi.org/10.3390/s22218218 - 27 Oct 2022

Cited by 5 | Viewed by 1908

Abstract

Concerns over fossil fuels and depletable energy sources have motivated renewable energy sources utilization, such as solar photovoltaic (PV) power. Utilities have started penetrating the existing primary grid with renewable energy sources. However, penetrating the grid with photovoltaic energy sources degrades the stability of the whole system because photovoltaic power depends on solar irradiance, which is highly intermittent. This paper proposes a prediction method for non-stationary solar irradiance. The proposed method uses an adaptive extreme learning machine. The extreme learning machine method uses approximated sigmoid and hyper-tangent functions to ensure faster computational time and more straightforward microcontroller implementation. The proposed method is analyzed using the hourly weather data from a specific site at Najran University. The data are preprocessed, trained, tested, and validated. Several evaluation metrics, such as the root mean square error, mean square error, and mean absolute error, are used to evaluate and compare the proposed method with other recently introduced approaches. The results show that the proposed method can be used to predict solar irradiance with high accuracy, as the mean square error is

0.1727

. The proposed approach is implemented using a solar irradiance sensor made of a PV cell, a temperature sensor, and a low-cost microcontroller. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

20 pages, 1046 KiB

Open AccessArticle

A Virtual Sensing Concept for Nitrogen and Phosphorus Monitoring Using Machine Learning Techniques

by Thulane Paepae, Pitshou N. Bokoro and Kyandoghere Kyamakya

Sensors 2022, 22(19), 7338; https://doi.org/10.3390/s22197338 - 27 Sep 2022

Cited by 10 | Viewed by 2428

Abstract

Harmful cyanobacterial bloom (HCB) is problematic for drinking water treatment, and some of its strains can produce toxins that significantly affect human health. To better control eutrophication and HCB, catchment managers need to continuously keep track of nitrogen (N) and phosphorus (P) in the water bodies. However, the high-frequency monitoring of these water quality indicators is not economical. In these cases, machine learning techniques may serve as viable alternatives since they can learn directly from the available surrogate data. In the present work, a random forest, extremely randomized trees (ET), extreme gradient boosting, k-nearest neighbors, a light gradient boosting machine, and bagging regressor-based virtual sensors were used to predict N and P in two catchments with contrasting land uses. The effect of data scaling and missing value imputation were also assessed, while the Shapley additive explanations were used to rank feature importance. A specification book, sensitivity analysis, and best practices for developing virtual sensors are discussed. Results show that ET, MinMax scaler, and a multivariate imputer were the best predictive model, scaler, and imputer, respectively. The highest predictive performance, reported in terms of R², was 97% in the rural catchment and 82% in an urban catchment. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

24 pages, 9449 KiB

Open AccessArticle

A Smart Visual Sensing Concept Involving Deep Learning for a Robust Optical Character Recognition under Hard Real-World Conditions

by Kabeh Mohsenzadegan, Vahid Tavakkoli and Kyandoghere Kyamakya

Sensors 2022, 22(16), 6025; https://doi.org/10.3390/s22166025 - 12 Aug 2022

Cited by 1 | Viewed by 3384

Abstract

In this study, we propose a new model for optical character recognition (OCR) based on both CNNs (convolutional neural networks) and RNNs (recurrent neural networks). The distortions affecting the document image can take different forms, such as blur (focus blur, motion blur, etc.), shadow, bad contrast, etc. Document-image distortions significantly decrease the performance of OCR systems, to the extent that they reach a performance close to zero. Therefore, a robust OCR model that performs robustly even under hard (distortion) conditions is still sorely needed. However, our comprehensive study in this paper shows that various related works can somewhat improve their respective OCR recognition performance of degraded document images (e.g., captured by smartphone cameras under different conditions and, thus, distorted by shadows, contrast, blur, etc.), but it is worth underscoring, that improved recognition is neither sufficient nor always satisfactory—especially in very harsh conditions. Therefore, in this paper, we suggest and develop a much better and fully different approach and model architecture, which significantly outperforms the aforementioned previous related works. Furthermore, a new dataset was gathered to show a series of different and well-representative real-world scenarios of hard distortion conditions. The new OCR model suggested performs in such a way that even document images (even from the hardest conditions) that were previously not recognizable by other OCR systems can be fully recognized with up to 97.5% accuracy/precision by our new deep-learning-based OCR model. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

21 pages, 3159 KiB

Open AccessArticle

Real-Time Anomaly Detection for an ADMM-Based Optimal Transmission Frequency Management System for IoT Devices

by Hongde Wu, Noel E. O’Connor, Jennifer Bruton, Amy Hall and Mingming Liu

Sensors 2022, 22(16), 5945; https://doi.org/10.3390/s22165945 - 9 Aug 2022

Cited by 4 | Viewed by 3484

Abstract

In this paper, we investigate different scenarios of anomaly detection on decentralised Internet of Things (IoT) applications. Specifically, an anomaly detector is devised to detect different types of anomalies for an IoT data management system, based on the decentralised alternating direction method of multipliers (ADMM), which was proposed in our previous work. The anomaly detector only requires limited information from the IoT system, and can be operated using both a mathematical-rule-based approach and the deep learning approach proposed in the paper. Our experimental results show that detection based on mathematical approach is simple to implement, but it also comes with lower detection accuracy (

78.88 %

). In contrast, the deep-learning-enabled approach can easily achieve a higher detection accuracy (

96.28 %

) in the real world working environment. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

24 pages, 7471 KiB

Open AccessArticle

Development of a Smart Chair Sensors System and Classification of Sitting Postures with Deep Learning Algorithms

by Taraneh Aminosharieh Najafi, Antonio Abramo, Kyandoghere Kyamakya and Antonio Affanni

Sensors 2022, 22(15), 5585; https://doi.org/10.3390/s22155585 - 26 Jul 2022

Cited by 14 | Viewed by 9342

Abstract

Nowadays in modern societies, a sedentary lifestyle is almost inevitable for a majority of the population. Long hours of sitting, especially in wrong postures, may result in health complications. A smart chair with the capability to identify sitting postures can help reduce health risks induced by a modern lifestyle. This paper presents the design, realization and evaluation of a new smart chair sensors system capable of sitting postures identification. The system consists of eight pressure sensors placed on the chair’s sitting cushion and the backrest. A signal acquisition board was designed from scratch to acquire data generated by the pressure sensors and transmit them via a Wi-Fi network to a purposely developed graphical user interface which monitors and stores the acquired sensors’ data on a computer. The designed system was tested by means of an extensive sitting experiment involving 40 subjects, and from the acquired data, the classification of the respective sitting postures out of eight possible postures was performed. Hereby, the performance of seven deep-learning algorithms was assessed. The best accuracy of 91.68% was achieved by an echo memory network model. The designed smart chair sensors system is simple and versatile, low cost and accurate, and it can easily be deployed in several smart chair environments, both for public and private contexts. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

18 pages, 497 KiB

Open AccessArticle

Energy Consumption Forecasting for Smart Meters Using Extreme Learning Machine Ensemble

by Paulo S. G. de Mattos Neto, João F. L. de Oliveira, Priscilla Bassetto, Hugo Valadares Siqueira, Luciano Barbosa, Emilly Pereira Alves, Manoel H. N. Marinho, Guilherme Ferretti Rissi and Fu Li

Sensors 2021, 21(23), 8096; https://doi.org/10.3390/s21238096 - 3 Dec 2021

Cited by 14 | Viewed by 5365

Abstract

The employment of smart meters for energy consumption monitoring is essential for planning and management of power generation systems. In this context, forecasting energy consumption is a valuable asset for decision making, since it can improve the predictability of forthcoming demand to energy providers. In this work, we propose a data-driven ensemble that combines five single well-known models in the forecasting literature: a statistical linear autoregressive model and four artificial neural networks: (radial basis function, multilayer perceptron, extreme learning machines, and echo state networks). The proposed ensemble employs extreme learning machines as the combination model due to its simplicity, learning speed, and greater ability of generalization in comparison to other artificial neural networks. The experiments were conducted on real consumption data collected from a smart meter in a one-step-ahead forecasting scenario. The results using five different performance metrics demonstrate that our solution outperforms other statistical, machine learning, and ensembles models proposed in the literature. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

15 pages, 2200 KiB

Open AccessArticle

Sentimental Analysis of COVID-19 Related Messages in Social Networks by Involving an N-Gram Stacked Autoencoder Integrated in an Ensemble Learning Scheme

by Venkatachalam Kandasamy, Pavel Trojovský, Fadi Al Machot, Kyandoghere Kyamakya, Nebojsa Bacanin, Sameh Askar and Mohamed Abouhawwash

Sensors 2021, 21(22), 7582; https://doi.org/10.3390/s21227582 - 15 Nov 2021

Cited by 23 | Viewed by 3307

Abstract

The current population worldwide extensively uses social media to share thoughts, societal issues, and personal concerns. Social media can be viewed as an intelligent platform that can be augmented with a capability to analyze and predict various issues such as business needs, environmental needs, election trends (polls), governmental needs, etc. This has motivated us to initiate a comprehensive search of the COVID-19 pandemic-related views and opinions amongst the population on Twitter. The basic training data have been collected from Twitter posts. On this basis, we have developed research involving ensemble deep learning techniques to reach a better prediction of the future evolutions of views in Twitter when compared to previous works that do the same. First, feature extraction is performed through an N-gram stacked autoencoder supervised learning algorithm. The extracted features are then involved in a classification and prediction involving an ensemble fusion scheme of selected machine learning techniques such as decision tree (DT), support vector machine (SVM), random forest (RF), and K-nearest neighbour (KNN). all individual results are combined/fused for a better prediction by using both mean and mode techniques. Our proposed scheme of an N-gram stacked encoder integrated in an ensemble machine learning scheme outperforms all the other existing competing techniques such unigram autoencoder, bigram autoencoder, etc. Our experimental results have been obtained from a comprehensive evaluation involving a dataset extracted from open-source data available from Twitter that were filtered by using the keywords “covid”, “covid19”, “coronavirus”, “covid-19”, “sarscov2”, and “covid_19”. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

21 pages, 7518 KiB

Open AccessArticle

A Deep-Learning Based Visual Sensing Concept for a Robust Classification of Document Images under Real-World Hard Conditions

by Kabeh Mohsenzadegan, Vahid Tavakkoli and Kyandoghere Kyamakya

Sensors 2021, 21(20), 6763; https://doi.org/10.3390/s21206763 - 12 Oct 2021

Cited by 7 | Viewed by 2526

Abstract

This paper’s core objective is to develop and validate a new neurocomputing model to classify document images in particularly demanding hard conditions such as image distortions, image size variance and scale, a huge number of classes, etc. Document classification is a special machine vision task in which document images are categorized according to their likelihood. Document classification is by itself an important topic for the digital office and it has several usages. Additionally, different methods for solving this problem have been presented in various studies; their respectively reached performance is however not yet good enough. This task is very tough and challenging. Thus, a novel, more accurate and precise model is needed. Although the related works do reach acceptable accuracy values for less hard conditions, they generally fully fail in the face of those above-mentioned hard, real-world conditions, including, amongst others, distortions such as noise, blur, low contrast, and shadows. In this paper, a novel deep CNN model is developed, validated and benchmarked with a selection of the most relevant recent document classification models. Additionally, the model’s sensitivity was significantly improved by injecting different artifacts during the training process. In the benchmarking, it does clearly outperform all others by at least 4%, thus reaching more than 96% accuracy. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

Review

Jump to: Research

38 pages, 8501 KiB

Open AccessReview

A Comprehensive “Real-World Constraints”-Aware Requirements Engineering Related Assessment and a Critical State-of-the-Art Review of the Monitoring of Humans in Bed

by Kyandoghere Kyamakya, Vahid Tavakkoli, Simon McClatchie, Maximilian Arbeiter and Bart G. Scholte van Mast

Sensors 2022, 22(16), 6279; https://doi.org/10.3390/s22166279 - 21 Aug 2022

Cited by 1 | Viewed by 2808

Abstract

Currently, abnormality detection and/or prediction is a very hot topic. In this paper, we addressed it in the frame of activity monitoring of a human in bed. This paper presents a comprehensive formulation of a requirements engineering dossier for a monitoring system of a “human in bed” for abnormal behavior detection and forecasting. Hereby, practical and real-world constraints and concerns were identified and taken into consideration in the requirements dossier. A comprehensive and holistic discussion of the anomaly concept was extensively conducted and contributed to laying the ground for a realistic specifications book of the anomaly detection system. Some systems engineering relevant issues were also briefly addressed, e.g., verification and validation. A structured critical review of the relevant literature led to identifying four major approaches of interest. These four approaches were evaluated from the perspective of the requirements dossier. It was thereby clearly demonstrated that the approach integrating graph networks and advanced deep-learning schemes (Graph-DL) is the one capable of fully fulfilling the challenging issues expressed in the real-world conditions aware specification book. Nevertheless, to meet immediate market needs, systems based on advanced statistical methods, after a series of adaptations, already ensure and satisfy the important requirements related to, e.g., low cost, solid data security and a fully embedded and self-sufficient implementation. To conclude, some recommendations regarding system architecture and overall systems engineering were formulated. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Figure 1

Figure 1
Human in bed monitoring through signals generated by sensors placed under the bed. Under each of the four bed legs, two sensors are placed: one weight sensor and one motion sensor. Thus, eight sensor measurement values are generated continuously over time for further processing by the anomaly detection intelligent system [<a href="#B25-sensors-22-06279" class="html-bibr">25</a>]. Full article ">Figure 2
There is a huge variety of possible static and/or dynamical activities of a human in bed, which are monitored through a sensor system such as the one presented in <a href="#sensors-22-06279-f001" class="html-fig">Figure 1</a>. The intelligent system to process the sensor data is capable of detecting and, eventually, also predict normal activities and abnormal ones. (Source of the different image parts: Freepik). Full article ">Figure 3
Presentation of the four major data-processing levels that were used in the comprehensive ontological framework for defining the general “anomaly” concept. Full article ">Figure 4
A possible and useful comprehensive structuring of the time dimension into regions and sub-regions. The use-case engineer shall fix meaningful durations/lengths of the different sub-regions. Full article ">Figure 5
For illustration, Toy Examples—A comparison of “Conventional Anomaly Detection” (see part (a)) and “Graph Anomaly Detection” (see part (b)). Apart from anomalies shown in part (b) of the figure, graph anomaly detection also identifies graph-level anomalies. Full article ">

35 pages, 2347 KiB

Open AccessReview

From Fully Physical to Virtual Sensing for Water Quality Assessment: A Comprehensive Review of the Relevant State-of-the-Art

by Thulane Paepae, Pitshou N. Bokoro and Kyandoghere Kyamakya

Sensors 2021, 21(21), 6971; https://doi.org/10.3390/s21216971 - 20 Oct 2021

Cited by 51 | Viewed by 6484

Abstract

Rapid urbanization, industrial development, and climate change have resulted in water pollution and in the quality deterioration of surface and groundwater at an alarming rate, deeming its quick, accurate, and inexpensive detection imperative. Despite the latest developments in sensor technologies, real-time determination of certain parameters is not easy or uneconomical. In such cases, the use of data-derived virtual sensors can be an effective alternative. In this paper, the feasibility of virtual sensing for water quality assessment is reviewed. The review focuses on the overview of key water quality parameters for a particular use case and the development of the corresponding cost estimates for their monitoring. The review further evaluates the current state-of-the-art in terms of the modeling approaches used, parameters studied, and whether the inputs were pre-processed by interrogating relevant literature published between 2001 and 2021. The review identified artificial neural networks, random forest, and multiple linear regression as dominant machine learning techniques used for developing inferential models. The survey also highlights the need for a comprehensive virtual sensing system in an internet of things environment. Thus, the review formulates the specification book for the advanced water quality assessment process (that involves a virtual sensing module) that can enable near real-time monitoring of water quality. Full article

(This article belongs to the Special Issue Sensor Intelligence through Neurocomputing)

► Show Figures

Journal Menu

Journal Browser

Sensor Intelligence through Neurocomputing

Share This Special Issue

Special Issue Editors

Special Issue Information

Benefits of Publishing in a Special Issue

Published Papers (13 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI