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

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.

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

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.

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

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.

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.

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.

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

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.

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

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.

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

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".

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

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.

Document-Image Related Visual Sensors and Machine Learning Techniques.

Document imaging/scanning approaches are essential techniques for digitalizing documents in various real-world contexts, e.g.,  libraries, office communication, managementof workflows, and electronic archiving [...].

Intelligent Transportation Related Complex Systems and Sensors.

Building around innovative services related to different modes of transport and traffic management, intelligent transport systems (ITSs) are being widely adopted worldwide to improve the efficiency and safety of the transportation system [...].

Emotion and Stress Recognition Related Sensors and Machine Learning Technologies.

Intelligent sociotechnical systems are gaining momentum in today's information-rich society, where different technologies are used to collect data from such systems and mine this data to make useful insights about our daily activities [...].

A Visual Sensing Concept for Robustly Classifying House Types through a Convolutional Neural Network Architecture Involving a Multi-Channel Features Extraction.

The core objective of this paper is to develop and validate a comprehensive visual sensing concept for robustly classifying house types. Previous studies regarding this type of classification show that this type of classification is not simple (i.e., tough) and most classifier models from the related literature have shown a relatively low performance. For finding a suitable model, several similar classification models based on convolutional neural network have been explored. We have found out that adding/involving/extracting better and more complex features result in a significant accuracy related performance improvement. Therefore, a new model taking this finding into consideration has been developed, tested and validated. The model developed is benchmarked with selected state-of-art classification models of relevance for the "house classification" endeavor. The test results obtained in this comprehensive benchmarking clearly demonstrate and validate the effectiveness and the superiority of our here developed deep-learning model. Overall, one notices that our model reaches classification performance figures (accuracy, precision, etc.) which are at least 8% higher (which is extremely significant in the ranges above 90%) than those reached by the previous state-of-the-art methods involved in the conducted comprehensive benchmarking.

Contribution to Speeding-Up the Solving of Nonlinear Ordinary Differential Equations on Parallel/Multi-Core Platforms for Sensing Systems.

Solving ordinary differential equations (ODE) on heterogenous or multi-core/parallel embedded systems does significantly increase the operational capacity of many sensing systems in view of processing tasks such as self-calibration, model-based measurement and self-diagnostics. The main challenge is usually related to the complexity of the processing task at hand which costs/requires too much processing power, which may not be available, to ensure a real-time processing. Therefore, a distributed solving involving multiple cores or nodes is a good/precious option. Also, speeding-up the processing does also result in significant energy consumption or sensor nodes involved. There exist several methods for solving differential equations on single processors. But most of them are not suitable for an implementation on parallel (i.e., multi-core) systems due to the increasing communication related network delays between computing nodes, which become a main and serious bottleneck to solve such problems in a parallel computing context. Most of the problems faced relate to the very nature of differential equations. Normally, one should first complete calculations of a previous step in order to use it in the next/following step. Hereby, it appears also that increasing performance (e.g., through increasing step sizes) may possibly result in decreasing the accuracy of calculations on parallel/multi-core systems like GPUs. In this paper, we do create a new adaptive algorithm based on the Adams-Moulton and Parareal method (we call it PAMCL) and we do compare this novel method with other most relevant implementations/schemes such as the so-called DOPRI5, PAM, etc. Our algorithm (PAMCL) is showing very good performance (i.e., speed-up) while compared to related competing algorithms, while thereby ensuring a reasonable accuracy. For a better usage of computing units/resources, the OpenCL platform is selected and ODE solver algorithms are optimized to work on both GPUs and CPUs. This platform does ensure/enable a high flexibility in the use of heterogeneous computing resources and does result in a very efficient utilization of available resources when compared to other comparable/competing algorithm/schemes implementations.

Assessment of the Speed Management Impact on Road Traffic Safety on the Sections of Motorways and Expressways Using Simulation Methods.

Methods used to evaluate the impact of Intelligent Transport System (ITS) services on road safety are usually based on expert assessments or statistical studies. However, commonly used methods are challenging to apply in the planning process of ITS services. This paper presents the methodology of research using surrogate safety measures calculated and calibrated with the use of simulation techniques and a driving simulator. This approach supports the choice of the type of ITS services that are beneficial for traffic efficiency and road safety. This paper presents results of research on the influence of selected scenarios of variable speed limits on the efficiency and safety of traffic on the sections of motorways and expressways in various traffic conditions. The driving simulator was used to estimate the efficiency of lane-keeping by the driver. The simulation traffic models were calibrated using driving simulator data and roadside sensor data. The traffic models made it possible to determine surrogate safety measures (number of conflicts and their severity) in selected scenarios of using ITS services. The presented studies confirmed the positive impact of Variable Speed Limits (VSLs) on the level of road safety and traffic efficiency. This paper also presents recommendations and plans for further research in this area.

Zero-Shot Human Activity Recognition Using Non-Visual Sensors.

Due to significant advances in sensor technology, studies towards activity recognition have gained interest and maturity in the last few years. Existing machine learning algorithms have demonstrated promising results by classifying activities whose instances have been already seen during training. Activity recognition methods based on real-life settings should cover a growing number of activities in various domains, whereby a significant part of instances will not be present in the training data set. However, to cover all possible activities in advance is a complex and expensive task. Concretely, we need a method that can extend the learning model to detect unseen activities without prior knowledge regarding sensor readings about those previously unseen activities. In this paper, we introduce an approach to leverage sensor data in discovering new unseen activities which were not present in the training set. We show that sensor readings can lead to promising results for zero-shot learning, whereby the necessary knowledge can be transferred from seen to unseen activities by using semantic similarity. The evaluation conducted on two data sets extracted from the well-known CASAS datasets show that the proposed zero-shot learning approach achieves a high performance in recognizing unseen (i.e., not present in the training dataset) new activities.

A Novel Recurrent Neural Network-Based Ultra-Fast, Robust, and Scalable Solver for Inverting a "Time-Varying Matrix".

The concept presented in this paper is based on previous dynamical methods to realize a time-varying matrix inversion. It is essentially a set of coupled ordinary differential equations (ODEs) which does indeed constitute a recurrent neural network (RNN) model. The coupled ODEs constitute a universal modeling framework for realizing a matrix inversion provided the matrix is invertible. The proposed model does converge to the inverted matrix if the matrix is invertible, otherwise it converges to an approximated inverse. Although various methods exist to solve a matrix inversion in various areas of science and engineering, most of them do assume that either the time-varying matrix inversion is free of noise or they involve a denoising module before starting the matrix inversion computation. However, in the practice, the noise presence issue is a very serious problem. Also, the denoising process is computationally expensive and can lead to a violation of the real-time property of the system. Hence, the search for a new 'matrix inversion' solving method inherently integrating noise-cancelling is highly demanded. In this paper, a new combined/extended method for time-varying matrix inversion is proposed and investigated. The proposed method is extending both the gradient neural network (GNN) and the Zhang neural network (ZNN) concepts. Our new model has proven that it has exponential stability according to Lyapunov theory. Furthermore, when compared to the other previous related methods (namely GNN, ZNN, Chen neural network, and integration-enhanced Zhang neural network or IEZNN) it has a much better theoretical convergence speed. To finish, all named models (the new one versus the old ones) are compared through practical examples and both their respective convergence and error rates are measured. It is shown/observed that the novel/proposed method has a better practical convergence rate when compared to the other models. Regarding the amount of noise, it is proven that there is a very good approximation of the matrix inverse even in the presence of noise.

A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors.

One of the main objectives of Active and Assisted Living (AAL) environments is to ensure that elderly and/or disabled people perform/live well in their immediate environments; this can be monitored by among others the recognition of emotions based on non-highly intrusive sensors such as Electrodermal Activity (EDA) sensors. However, designing a learning system or building a machine-learning model to recognize human emotions while training the system on a specific group of persons and testing the system on a totally a new group of persons is still a serious challenge in the field, as it is possible that the second testing group of persons may have different emotion patterns. Accordingly, the purpose of this paper is to contribute to the field of human emotion recognition by proposing a Convolutional Neural Network (CNN) architecture which ensures promising robustness-related results for both subject-dependent and subject-independent human emotion recognition. The CNN model has been trained using a grid search technique which is a model hyperparameter optimization technique to fine-tune the parameters of the proposed CNN architecture. The overall concept's performance is validated and stress-tested by using MAHNOB and DEAP datasets. The results demonstrate a promising robustness improvement regarding various evaluation metrics. We could increase the accuracy for subject-independent classification to 78% and 82% for MAHNOB and DEAP respectively and to 81% and 85% subject-dependent classification for MAHNOB and DEAP respectively (4 classes/labels). The work shows clearly that while using solely the non-intrusive EDA sensors a robust classification of human emotion is possible even without involving additional/other physiological signals.

A Globally Generalized Emotion Recognition System Involving Different Physiological Signals.

Machine learning approaches for human emotion recognition have recently demonstrated high performance. However, only/mostly for subject-dependent approaches, in a variety of applications like advanced driver assisted systems, smart homes and medical environments. Therefore, now the focus is shifted more towards subject-independent approaches, which are more universal and where the emotion recognition system is trained using a specific group of subjects and then tested on totally new persons and thereby possibly while using other sensors of same physiological signals in order to recognize their emotions. In this paper, we explore a novel robust subject-independent human emotion recognition system, which consists of two major models. The first one is an automatic feature calibration model and the second one is a classification model based on Cellular Neural Networks (CNN). The proposed system produces state-of-the-art results with an accuracy rate between 80% and 89% when using the same elicitation materials and physiological sensors brands for both training and testing and an accuracy rate of 71.05% when the elicitation materials and physiological sensors brands used in training are different from those used in training. Here, the following physiological signals are involved: ECG (Electrocardiogram), EDA (Electrodermal activity) and ST (Skin-Temperature).

A universal concept based on cellular neural networks for ultrafast and flexible solving of differential equations.

This paper develops and validates a comprehensive and universally applicable computational concept for solving nonlinear differential equations (NDEs) through a neurocomputing concept based on cellular neural networks (CNNs). High-precision, stability, convergence, and lowest-possible memory requirements are ensured by the CNN processor architecture. A significant challenge solved in this paper is that all these cited computing features are ensured in all system-states (regular or chaotic ones) and in all bifurcation conditions that may be experienced by NDEs.One particular quintessence of this paper is to develop and demonstrate a solver concept that shows and ensures that CNN processors (realized either in hardware or in software) are universal solvers of NDE models. The solving logic or algorithm of given NDEs (possible examples are: Duffing, Mathieu, Van der Pol, Jerk, Chua, Rössler, Lorenz, Burgers, and the transport equations) through a CNN processor system is provided by a set of templates that are computed by our comprehensive templates calculation technique that we call nonlinear adaptive optimization. This paper is therefore a significant contribution and represents a cutting-edge real-time computational engineering approach, especially while considering the various scientific and engineering applications of this ultrafast, energy-and-memory-efficient, and high-precise NDE solver concept. For illustration purposes, three NDE models are demonstratively solved, and related CNN templates are derived and used: the periodically excited Duffing equation, the Mathieu equation, and the transport equation.