Search

This research paper explores the realm of fault detection in distributed motors through the vision of the Internet of electrical drives. This paper aims at employing artificial neural networks supported by the data collected by the Internet of distributed devices. Cross-verification of results offers reliable diagnosis of industrial motor faults. The proposed methodology involves the development of a cyber–physical system architecture and mathematical modeling framework for efficient fault detection. The mathematical model is designed to capture the intricate relationships within the cyber–physical system, incorporating the dynamic interactions between distributed motors and their edge controllers. Fast Fourier transform is employed for signal processing, enabling the extraction of meaningful frequency features that serve as indicators of potential faults. The artificial neural network based fault detection system is integrated with the solution, utilizing its ability to learn complex patterns and adapt to varying motor conditions. The effectiveness of the proposed framework and model is demonstrated through experimental results. The experimental setup involves diverse fault scenarios, and the system's performance is evaluated in terms of accuracy, sensitivity, and false positive rates. [ABSTRACT FROM AUTHOR]

The primary objective of the research presented in this article is to introduce an artificial neural network that demands less computational power than a conventional deep neural network. The development of this ANN was achieved through the application of Ordered Fuzzy Numbers (OFNs). In the context of Industry 4.0, there are numerous applications where this solution could be utilized for data processing. It allows the deployment of Artificial Intelligence at the network edge on small devices, eliminating the need to transfer large amounts of data to a cloud server for analysis. Such networks will be easier to implement in small-scale solutions, like those for the Internet of Things, in the future. This paper presents test results where a real system was monitored, and anomalies were detected and predicted. [ABSTRACT FROM AUTHOR]

Fingerprinting localization is a promising indoor positioning methods thanks to its advantage of using preinstalled infrastructure. For example, WiFi signal strength can be measured by pre-existing WiFi routers. In the offline phase, the fingerprinting localization method first stores of position and RSSI measurement pairs in a dataset. Second, it predicts a target's location by comparing the stored fingerprint database to the current measurement. The database size is normally huge, and data patterns are complicated; thus, an artificial neural network is used to model the relationship of fingerprints and locations. The existing fingerprinting locations, however, have been developed to predict only single locations. In practice, many users may require positioning services, and as such, the core algorithm should be capable of multiple localizations, which is the main contribution of this paper. In this paper, multiple fingerprinting localization is developed based on an artificial neural network and an analysis of the number of targets that can be estimated without loss of accuracy is conducted by experiments. [ABSTRACT FROM AUTHOR]

Time-space four-dimensional motion target localization is a fundamental and challenging task in the field of intelligent driving, and an important part of achieving the upgrade in existing target localization technologies. In order to solve the problem of the lack of localization of moving targets in a spatio-temporal four-dimensional environment in the existing spatio-temporal data model, this paper proposes an optical imaging model in the four-dimensional time-space system and a mathematical model of the object-image point mapping relationship in the four-dimensional time-space system based on the central perspective projection model, combined with the one-dimensional "time" and three-dimensional "space". After adding the temporal dimension, the imaging system parameters are extended. In order to solve the nonlinear mapping problem of complex systems, this paper proposes to construct a time-space four-dimensional object-image mapping relationship model based on a BP artificial neural network and demonstrates the feasibility of the joint time-space four-dimensional imaging model theory. In addition, indoor time-space four-dimensional localization prediction experiments verify the performance of the model in this paper. The maximum relative error rates of the predicted motion depth values, time values, and velocity values of this localization method compared with the real values do not exceed 0.23%, 2.03%, and 1.51%, respectively [ABSTRACT FROM AUTHOR]

Organizations managing high-performance computing systems face a multitude of challenges, including overarching concerns such as overall energy consumption, microprocessor clock frequency limitations, and the escalating costs associated with chip production. Evidently, processor speeds have plateaued over the last decade, persisting within the range of 2 GHz to 5 GHz. Scholars assert that brain-inspired computing holds substantial promise for mitigating these challenges. The spiking neural network (SNN) particularly stands out for its commendable power efficiency when juxtaposed with conventional design paradigms. Nevertheless, our scrutiny has brought to light several pivotal challenges impeding the seamless implementation of large-scale neural networks (NNs) on silicon. These challenges encompass the absence of automated tools, the need for multifaceted domain expertise, and the inadequacy of existing algorithms to efficiently partition and place extensive SNN computations onto hardware infrastructure. In this paper, we posit the development of an automated tool flow capable of transmuting any NN into an SNN. This undertaking involves the creation of a novel graph-partitioning algorithm designed to strategically place SNNs on a network-on-chip (NoC), thereby paving the way for future energy-efficient and high-performance computing paradigms. The presented methodology showcases its effectiveness by successfully transforming ANN architectures into SNNs with a marginal average error penalty of merely 2.65%. The proposed graph-partitioning algorithm enables a 14.22% decrease in inter-synaptic communication and an 87.58% reduction in intra-synaptic communication, on average, underscoring the effectiveness of the proposed algorithm in optimizing NN communication pathways. Compared to a baseline graph-partitioning algorithm, the proposed approach exhibits an average decrease of 79.74% in latency and a 14.67% reduction in energy consumption. Using existing NoC tools, the energy-latency product of SNN architectures is, on average, 82.71% lower than that of the baseline architectures. [ABSTRACT FROM AUTHOR]

Dealing with the islanded operation of a microgrid (MG), the micro sources must cooperate autonomously to regulate the voltage and frequency of the local power grid. Droop controller-based primary control is a method typically used to self-regulate voltage and frequency. The first problem of the droop method is that in a steady state, the microgrid's frequency and voltage deviate from their nominal values. The second concerns the power-sharing issue related to mismatched power line impedances between Distribution Generators (DGs) and MGs. A Secondary Control Unit (SCU) must be used as a high-level controller for droop-based primary control to address the first problem. This paper proposed a decentralized SCU scheme to deal with this issue using optimized PI controllers based on a Genetic Algorithm (GA) and Artificial Neural Networks (ANNs). The GA provides the appropriate adjustment parameters for all adopted PI controllers in the primary control-based voltage and current control loops and SCU-based voltage and frequency loops. ANNs are additionally activated in SCUs to provide precise online control parameter modification. In the proposed control structure, a virtual impedance method is adopted in the primary control scheme to address the power-sharing problem of parallel DGs. Further, in this paper, one of the main objectives includes electricity transmission over long distances using Low-Voltage DC Transmission (LVDCT) systems to reduce power losses and eradicate reactive power problems. Voltage Source Inverters (VSIs) are adopted to convert the DC electrical energy into AC near the consumer loads. The simulation results illustrated the feasibility of the proposed solutions in restoring voltage and frequency deviations, reducing line losses, as well as achieving active and reactive power sharing among the DGs connected to the MG. [ABSTRACT FROM AUTHOR]

Bridge strikes by over-height vehicles or ships are critical sudden events. Due to their unpredictable nature, many events go unnoticed or unreported, but they can induce structural failures or hidden damage that accelerates the bridge's long-term degradation. Therefore, always-on monitoring is essential for deployed systems to enhance bridge safety through the reliable detection of such events and the rapid assessment of bridge conditions. Traditional bridge monitoring systems using wired sensors are too expensive for widespread implementation, mainly due to their significant installation cost. In this paper, an intelligent wireless monitoring system is developed as a cost-effective solution. It employs ultralow-power, event-triggered wireless sensor prototypes, which enables on-demand, high-fidelity sensing without missing unpredictable impact events. Furthermore, the proposed system adopts a smart artificial intelligence (AI)-based framework for rapid bridge assessment by utilizing artificial neural networks. Specifically, it can identify the impact location and estimate the peak force and impulse of impacts. The obtained impact information is used to provide early estimation of bridge conditions, allowing the bridge engineers to prioritize resource allocation for the timely inspection of the more severe impacts. The performance of the proposed monitoring system is demonstrated through a full-scale field test. The test results show that the developed system can capture the onset of bridge impacts, provide high-quality synchronized data, and offer a rapid damage assessment of bridges under impact events, achieving the error of around 2 m in impact localization, 1 kN for peak force estimation, and 0.01 kN·s for impulse estimation. Long-term deployment is planned in the future to demonstrate its reliability for real-life impact events. [ABSTRACT FROM AUTHOR]

In the oil and gas industries, predicting and classifying oil and gas production for hydrocarbon wells is difficult. Most oil and gas companies use reservoir simulation software to predict future oil and gas production and devise optimum field development plans. However, this process costs an immense number of resources and is time consuming. Each reservoir prediction experiment needs tens or hundreds of simulation runs, taking several hours or days to finish. In this paper, we attempt to overcome these issues by creating machine learning and deep learning models to expedite the process of forecasting oil and gas production. The dataset was provided by the leading oil producer, Saudi Aramco. Our approach reduced the time costs to a worst-case of a few minutes. Our study covered eight different ML and DL experiments and achieved its most outstanding R2 scores of 0.96 for XGBoost, 0.97 for ANN, and 0.98 for RNN over the other experiments. [ABSTRACT FROM AUTHOR]

The 5G deployment brings forth the usage of Unmanned Aerial Vehicles (UAV) to assist wireless networks by providing improved signal coverage, acting as relays or base-stations. Another technology that could help achieve 5G massive machine-type communications (mMtc) goals is the Long Range Wide-Area Network (LoRaWAN) communication protocol. This paper studied these complementary technologies, LoRa and UAV, through measurement campaigns in suburban, densely forested environments. Downlink and uplink communication at different heights and spreading factors (SF) demonstrate distinct behavior through our analysis. Moreover, a neural network was trained to predict the measured signal-to-noise ratio (SNR) behavior and results compared with SNR regression models. For the downlink scenario, the neural network results show a root mean square error (RMSE) variation between 1.2322–1.6623 dB, with an error standard deviation (SD) less than 1.6730 dB. For the uplink, the RMSE variation was between 0.8714–1.3891 dB, with an error SD less than 1.1706 dB. [ABSTRACT FROM AUTHOR]

Structural anomaly diagnosis, such as damage identification, is a continuously interesting issue. Artificial neural networks have an excellent ability to model complex structure dynamics. In this paper, an artificial neural network model is used to describe the relationship between structural responses and anomalies such as stiffness reduction due to damages. Random acceleration and displacement responses as generally measured data are used as the input to the artificial neural network, and the output of the artificial neural network is the anomaly severity. The artificial neural network model is set up by training and then validated using random vibration responses with different structural anomalies. The structural anomaly diagnosis method based on the artificial neural network model using random acceleration and displacement responses is applied to a five-story building structure under random base excitations (seismic loading). Anomalies in the structure are denoted by stiffness reduction. Structural anomaly diagnosis using random acceleration responses is compared with that using random displacement responses. The numerical results show the effects of different random vibration responses used on the accuracy of predicting stiffness reduction. The actual incomplete measurements include intensive noise, finite sampling time length, and limited measurement points. The effects of the incomplete measurements on the accuracy of predicting results are also discussed. [ABSTRACT FROM AUTHOR]

In the current study, our research group proposed an asymmetric lower extremity exoskeleton to enable above-knee amputees to walk with a load. Due to the absence of shank and foot, the knee and ankle joint at the amputation side of the exoskeleton lack tracking targets, so it is difficult to realize the function of assisted walking when going up and downstairs. Currently, the use of lower-limb electromyography to predict the angles of lower limb joints has achieved remarkable results. However, the prediction effect was poor when only using electromyography from the thigh. Therefore, this paper introduces hip-angle and plantar pressure signals for improving prediction effect and puts forward a joint prediction method of knee- and ankle-joint angles by electromyography of the thigh, hip-joint angle, and plantar pressure signals. The generalized regression neural network optimized by the golden section method is used to predict the joint angles. Finally, the parameters (the maximum error, the Root-Mean-Square error (RMSE), and correlation coefficient (γ)) were calculated to verify the feasibility of the prediction method. [ABSTRACT FROM AUTHOR]

Monitoring the integrity of aeronautical structures is fundamental for safety. Structural Health Monitoring Systems (SHMSs) perform real-time monitoring functions, but their performance must be carefully assessed. This is typically done by introducing artificial damages to the components; however, such a procedure requires the production and testing of a large number of structural elements. In this work, the damage detection performance of a strain-based SHMS was evaluated on a composite helicopter rotor blade root, exploiting a Finite Element (FE) model of the component. The SHMS monitored the bonding between the central core and the surrounding antitorsional layer. A damage detection algorithm was trained through FE analyses. The effects of the load's variability and of the damage were decoupled by including a load recognition step in the algorithm, which was accomplished either with an Artificial Neural Network (ANN) or a calibration matrix. Anomaly detection, damage assessment, and localization were performed by using an ANN. The results showed a higher load identification and anomaly detection accuracy using an ANN for the load recognition, and the load set was recognized with a satisfactory accuracy, even in damaged blades. This case study was focused on a real-world subcomponent with complex geometrical features and realistic load conditions, which was not investigated in the literature and provided a promising approach to estimate the performance of a strain-based SHMS. [ABSTRACT FROM AUTHOR]

A map of the environment is the basis for the robot's navigation. Multi-robot collaborative autonomous exploration allows for rapidly constructing maps of unknown environments, essential for application areas such as search and rescue missions. Traditional autonomous exploration methods are inefficient due to the repetitive exploration problem. For this reason, we propose a multi-robot autonomous exploration method based on the Transformer model. Our multi-agent deep reinforcement learning method includes a multi-agent learning method to effectively improve exploration efficiency. We conducted experiments comparing our proposed method with existing methods in a simulation environment, and the experimental results showed that our proposed method had a good performance and a specific generalization ability. [ABSTRACT FROM AUTHOR]

This paper addresses the improvement of tracking of the maximum power point upon the variations of the environmental conditions and hence improving photovoltaic efficiency. Rather than the traditional methods of maximum power point tracking, artificial intelligence is utilized to design a high-performance maximum power point tracking control system. In this paper, two artificial intelligence-based maximum power point tracking systems are proposed for grid-connected photovoltaic units. The first design is based on an optimized fuzzy logic control using genetic algorithm and particle swarm optimization for the maximum power point tracking system. In turn, the second design depends on the genetic algorithm-based artificial neural network. Each of the two artificial intelligence-based systems has its privileged response according to the solar radiation and temperature levels. Then, a novel combination of the two designs is introduced to maximize the efficiency of the maximum power point tracking system. The novelty of this paper is to employ the metaheuristic optimization technique with the well-known artificial intelligence techniques to provide a better tracking system to be used to harvest the maximum possible power from photovoltaic (PV) arrays. To affirm the efficiency of the proposed tracking systems, their simulation results are compared with some conventional tracking methods from the literature under different conditions. The findings emphasize their superiority in terms of tracking speed and output DC power, which also improve photovoltaic system efficiency. [ABSTRACT FROM AUTHOR]

Electromyography (EMG) signals are becoming increasingly important in many applications, including clinical/biomedical, prosthesis or rehabilitation devices, human machine interactions, and more. However, noisy EMG signals are the major hurdles to be overcome in order to achieve improved performance in the above applications. Detection, processing and classification analysis in electromyography (EMG) is very desirable because it allows a more standardized and precise evaluation of the neurophysiological, rehabitational and assistive technological findings. This paper reviews two prominent areas; first: the pre-processing method for eliminating possible artifacts via appropriate preparation at the time of recording EMG signals, and second: a brief explanation of the different methods for processing and classifying EMG signals. This study then compares the numerous methods of analyzing EMG signals, in terms of their performance. The crux of this paper is to review the most recent developments and research studies related to the issues mentioned above. [ABSTRACT FROM AUTHOR]

Biologically-inspired models and algorithms are considered as promising sensor array signal processing methods for electronic noses. Feature selection is one of the most important issues for developing robust pattern recognition models in machine learning. This paper describes an investigation into the classification performance of a bionic olfactory model with the increase of the dimensions of input feature vector (outer factor) as well as its parallel channels (inner factor). The principal component analysis technique was applied for feature selection and dimension reduction. Two data sets of three classes of wine derived from different cultivars and five classes of green tea derived from five different provinces of China were used for experiments. In the former case the results showed that the average correct classification rate increased as more principal components were put in to feature vector. In the latter case the results showed that sufficient parallel channels should be reserved in the model to avoid pattern space crowding. We concluded that 6~8 channels of the model with principal component feature vector values of at least 90% cumulative variance is adequate for a classification task of 3~5 pattern classes considering the trade-off between time consumption and classification rate. [ABSTRACT FROM AUTHOR]

Most of classification, quality evaluation or grading of the flue-cured tobacco leaves are manually operated, which relies on the judgmental experience of experts, and inevitably limited by personal, physical and environmental factors. The classification and the quality evaluation are therefore subjective and experientially based. In this paper, an automatic classification method of tobacco leaves based on the digital image processing and the fuzzy sets theory is presented. A grading system based on image processing techniques was developed for automatically inspecting and grading flue-cured tobacco leaves. This system uses machine vision for the extraction and analysis of color, size, shape and surface texture. Fuzzy comprehensive evaluation provides a high level of confidence in decision making based on the fuzzy logic. The neural network is used to estimate and forecast the membership function of the features of tobacco leaves in the fuzzy sets. The experimental results of the two-level fuzzy comprehensive evaluation (FCE) show that the accuracy rate of classification is about 94% for the trained tobacco leaves, and the accuracy rate of the non-trained tobacco leaves is about 72%. We believe that the fuzzy comprehensive evaluation is a viable way for the automatic classification and quality evaluation of the tobacco leaves. [ABSTRACT FROM AUTHOR]

In this paper a modified wavelet synthesis algorithm for continuous wavelet transform is proposed, allowing one to obtain a guaranteed approximation of the maternal wavelet to the sample of the analyzed signal (overlap match) and, at the same time, a formalized representation of the wavelet. What distinguishes this method from similar ones? During the procedure of wavelets' synthesis for continuous wavelet transform it is proposed to use splines and artificial neural networks. The paper also suggests a comparative analysis of polynomial, neural network, and wavelet spline models. It also deals with feasibility of using these models in the synthesis of wavelets during such studies like fine structure of signals, as well as in analysis of large parts of signals whose shape is variable. A number of studies have shown that during the wavelets' synthesis, the use of artificial neural networks (based on radial basis functions) and cubic splines enables the possibility of obtaining guaranteed accuracy in approaching the maternal wavelet to the signal's sample (with no approximation error). It also allows for its formalized representation, which is especially important during software implementation of the algorithm for calculating the continuous conversions at digital signal processors and microcontrollers. This paper demonstrates the possibility of using synthesized wavelet, obtained based on polynomial, neural network, and spline models, during the performance of an inverse continuous wavelet transform. [ABSTRACT FROM AUTHOR]

Capability assessment plays a crucial role in the demonstration and construction of equipment. To improve the accuracy and stability of capability assessment, we study the neural network learning algorithms in the field of capability assessment and index sensitivity. Aiming at the problem of overfitting and parameter optimization in neural network learning, the paper proposes an improved machine learning algorithm—the Ensemble Learning Based on Policy Optimization Neural Networks (ELPONN) with the policy optimization and ensemble learning. This algorithm presents an optimized neural network learning algorithm through different strategies evolution, and builds an ensemble learning model of multi-intelligent algorithms to assess the capability and analyze the sensitivity of the indexes. Through the assessment of capabilities, the algorithm effectively avoids parameter optimization from entering the minimum point in performance to improve the accuracy of equipment capability assessment, which is significantly better than previous neural network assessment methods. The experimental results show that the mean relative error is 4.10%, which is better than BP, GABP, and early stopping. The ELPONN algorithm has better accuracy and stability performance, and meets the requirements of capability assessment. [ABSTRACT FROM AUTHOR]

One of the most powerful techniques to diagnose cardiovascular diseases is to analyze the electrocardiogram (ECG). To increase diagnostic sensitivity, the ECG might need to be acquired using an ambulatory system, as symptoms may occur during a patient's daily life. In this paper, we propose using an ambulatory ECG (aECG) recording device with a low number of leads and then estimating the views that would have been obtained with a standard ECG location, reconstructing the complete Standard 12-Lead System, the most widely used system for diagnosis by cardiologists. Four approaches have been explored, including Linear Regression with ECG segmentation and Artificial Neural Networks (ANN). The best reconstruction algorithm is based on ANN, which reconstructs the actual ECG signal with high precision, as the results bring a high accuracy (RMS Error < 13 μ V and CC > 99.7%) for the set of patients analyzed in this paper. This study supports the hypothesis that it is possible to reconstruct the Standard 12-Lead System using an aECG recording device with less leads. [ABSTRACT FROM AUTHOR]

Load forecasting plays a crucial role in the world of smart grids. It governs many aspects of the smart grid and smart meter, such as demand response, asset management, investment, and future direction. This paper proposes time-series forecasting for short-term load prediction to unveil the load forecast benefits through different statistical and mathematical models, such as artificial neural networks, auto-regression, and ARIMA. It targets the problem of excessive computational load when dealing with time-series data. It also presents a business case that is used to analyze different clusters to find underlying factors of load consumption and predict the behavior of customers based on different parameters. On evaluating the accuracy of the prediction models, it is observed that ARIMA models with the (P, D, Q) values as (1, 1, 1) were most accurate compared to other values. [ABSTRACT FROM AUTHOR]

The direct-sequence spread-spectrum (DSSS) technique has been widely used in wireless secure communications. In this technique, the baseband signal is spread over a wider bandwidth using pseudo-random sequences to avoid interference or interception. In this paper, the authors propose methods to adaptively detect the DSSS signals based on knowledge-enhanced compressive measurements and artificial neural networks. Compared with the conventional non-compressive detection system, the compressive detection framework can achieve a reasonable balance between detection performance and sampling hardware cost. In contrast to the existing compressive sampling techniques, the proposed methods are shown to enable adaptive measurement kernel design with high efficiency. Through the theoretical analysis and the simulation results, the proposed adaptive compressive detection methods are also demonstrated to provide significantly enhanced detection performance efficiently, compared to their counterpart with the conventional random measurement kernels. [ABSTRACT FROM AUTHOR]

European legislation is driving the development of methods for river ecosystem protection in light of concerns over water quality and ecology. Key to their success is the accurate and rapid characterisation of physical features (i.e., hydromorphology) along the river. Image pattern recognition techniques have been successfully used for this purpose. The reliability of the methodology depends on both the quality of the aerial imagery and the pattern recognition technique used. Recent studies have proved the potential of Unmanned Aerial Vehicles (UAVs) to increase the quality of the imagery by capturing high resolution photography. Similarly, Artificial Neural Networks (ANN) have been shown to be a high precision tool for automated recognition of environmental patterns. This paper presents a UAV based framework for the identification of hydromorphological features from high resolution RGB aerial imagery using a novel classification technique based on ANNs. The framework is developed for a 1.4 km river reach along the river Dee in Wales, United Kingdom. For this purpose, a Falcon 8 octocopter was used to gather 2.5 cm resolution imagery. The results show that the accuracy of the framework is above 81%, performing particularly well at recognising vegetation. These results leverage the use of UAVs for environmental policy implementation and demonstrate the potential of ANNs and RGB imagery for high precision river monitoring and river management. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to predicting self-calibration in a pressure sensor using a proposed Levenberg Marquardt Back Propagation Artificial Neural Network (LMBP-ANN) model. The self-calibration algorithm should be able to fix major problems in the pressure sensor such as hysteresis, variation in gain and lack of linearity with high accuracy. The traditional calibration process for this kind of sensor is a time-consuming task because it is usually done through manual and repetitive identification. Furthermore, a traditional computational method is inadequate for solving the problem since it is extremely difficult to resolve the mathematical formula among multiple confounding pressure variables. Accordingly, this paper describes a new self-calibration methodology for nonlinear pressure sensors based on an LMBP-ANN model. The proposed method was achieved using a collected dataset from pressure sensors in real time. The load cell will be used as a reference for measuring the applied force. The proposed method was validated by comparing the output pressure of the trained network with the experimental target pressure (reference). This paper also shows that the proposed model exhibited a remarkable performance than traditional methods with a max mean square error of 0.17325 and an R-value over 0.99 for the total response of training, testing and validation. To verify the proposed model’s capability to build a self-calibration algorithm, the model was tested using an untrained input data set. As a result, the proposed LMBP-ANN model for self-calibration purposes is able to successfully predict the desired pressure over time, even the uncertain behaviour of the pressure sensors due to its material creep. This means that the proposed model overcomes the problems of hysteresis, variation in gain and lack of linearity over time. In return, this can be used to enhance the durability of the grasping mechanism, leading to a more robust and secure grasp for paralyzed hands. Furthermore, the exposed analysis approach in this paper can be a useful methodology for the user to evaluate the performance of any measurement system in a real-time environment. [ABSTRACT FROM AUTHOR]

This paper proposes a parallel fixed point radial basis function (RBF) artificial neural network (ANN), implemented in a field programmable gate array (FPGA) trained online with a least mean square (LMS) algorithm. The processing time and occupied area were analyzed for various fixed point formats. The problems of precision of the ANN response for nonlinear classification using the XOR gate and interpolation using the sine function were also analyzed in a hardware implementation. The entire project was developed using the System Generator platform (Xilinx), with a Virtex-6 xc6vcx240t-1ff1156 as the target FPGA. [ABSTRACT FROM AUTHOR]

Vehicle detection and classification have become important tasks for traffic monitoring, transportation management and pavement evaluation. Nowadays there are sensors to detect and classify the vehicles on road. However, on one hand, most sensors rely on direct contact measurement to detect the vehicles, which have to interrupt the traffic. On the other hand, complex road scenes produce much noise to consider when to process the signals. In this paper, a data-driven methodology for the detection and classification of vehicles using strain data is proposed. The sensors are well arranged under the bridge deck without traffic interruption. Next, a cascade pre-processing method is applied for vehicle detection to eliminate in-situ noise. Then, a neural network model is trained to identify the close-range following vehicles and separate them by Non-Maximum Suppression. Finally, a deep convolutional neural network is designed and trained to identify the vehicle types based on the axle group. The methodology was applied in a long-span bridge. Three strain sensors were installed beneath the bridge deck for a week. High robustness and accuracy were obtained by these algorithms. The methodology proposed in this paper is an adaptive and promising method for vehicle detection and classification under complex noise. It would serve as a supplement to current transportation systems and provide reliable data for management and decision-making. [ABSTRACT FROM AUTHOR]

Many human activities are tactile. Recognizing how a person touches an object or a surface surrounding them is an active area of research and it has generated keen interest within the interactive surface community. In this paper, we compare two machine learning techniques, namely Artificial Neural Network (ANN) and Hidden Markov Models (HMM), as they are some of the most common techniques with low computational cost used to classify an acoustic-based input. We employ a small and low-cost hardware design composed of a microphone, a stethoscope, a conditioning circuit, and a microcontroller. Together with an appropriate surface, we integrated these components into a passive gesture recognition input system for experimental evaluation. To perform the evaluation, we acquire the signals using a small microphone and send it through the microcontroller to MATLAB's toolboxes to implement and evaluate the ANN and HMM models. We also present the hardware and software implementation and discuss the advantages and limitations of these techniques in gesture recognition while using a simple alphabet of three geometrical figures: circle, square, and triangle. The results validate the robustness of the HMM technique that achieved a success rate of 90%, with a shorter training time than the ANN. [ABSTRACT FROM AUTHOR]

Vibrations of complex structures such as bridges mostly present nonlinear and non-stationary behaviors. Recently, one of the most common techniques to analyze the nonlinear and non-stationary structural response is Hilbert–Huang Transform (HHT). This paper aims to evaluate the performance of HHT based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) technique using an Artificial Neural Network (ANN) as a proposed damage detection methodology. The performance of the proposed method is investigated for damage detection of a scaled steel-truss bridge model which was experimentally established as the case study subjected to white noise excitations. To this end, four key features of the intrinsic mode function (IMF), including energy, instantaneous amplitude (IA), unwrapped phase, and instantaneous frequency (IF), are extracted to assess the presence, severity, and location of the damage. By analyzing the experimental results through different damage indices defined based on the extracted features, the capabilities of the CEEMDAN-HT-ANN model in detecting, addressing the location and classifying the severity of damage are efficiently concluded. In addition, the energy-based damage index demonstrates a more effective approach in detecting the damage compared to those based on IA and unwrapped phase parameters. [ABSTRACT FROM AUTHOR]

Traffic simulations are valuable tools for urban mobility planning and operation, particularly in large cities. Simulation-based microscopic models have enabled traffic engineers to understand local transit and transport behaviors more deeply and manage urban mobility. However, for the simulations to be effective, the transport network and user behavior parameters must be calibrated to mirror real scenarios. In general, calibration is performed manually by traffic engineers who use their knowledge and experience to adjust the parameters of the simulator. Unfortunately, there is still no systematic and automatic process for calibrating traffic simulation networks, although some methods have been proposed in the literature. This study proposes a methodology that facilitates the calibration process, where an artificial neural network (ANN) is trained to learn the behavior of the transport network of interest. The ANN used is the Multi-Layer Perceptron (MLP), trained with back-propagation methods. Based on this learning procedure, the neural network can select the optimized values of the simulation parameters that best mimic the traffic conditions of interest. Experiments considered two microscopic models of traffic and two psychophysical models (Wiedemann 74 and Wiedemann 99). The microscopic traffic models are located in the metropolitan region of São Paulo, Brazil. Moreover, we tested the different configurations of the MLP (layers and numbers of neurons) as well as several variations of the backpropagation training method: Stochastic Gradient Descent (SGD), Adam, Adagrad, Adadelta, Adamax, and Nadam. The results of the experiments show that the proposed methodology is accurate and efficient, leading to calibration with a correlation coefficient greater than 0.8, when the calibrated parameters generate more visible effects on the road network, such as travel times, vehicle counts, and average speeds. For the psychophysical parameters, in the most simplified model (W74), the correlation coefficient was greater than 0.7. The advantage of using ANN for the automatic calibration of simulation parameters is that it allows traffic engineers to carry out comprehensive studies on a large number of future scenarios, such as at different times of the day, as well as on different days of the week and months of the year. [ABSTRACT FROM AUTHOR]

A hybrid deep learning approach was designed that combines deep learning with enhanced short-time Fourier transform (STFT) spectrograms and continuous wavelet transform (CWT) scalograms for pipeline leak detection. Such detection plays a crucial role in ensuring the safety and integrity of fluid transportation systems. The proposed model leverages the power of STFT and CWT to enhance detection capabilities. The pipeline's acoustic emission signals during normal and leak operating conditions undergo transformation using STFT and CWT, creating scalograms representing energy variations across time–frequency scales. To improve the signal quality and eliminate noise, Sobel and wavelet denoising filters are applied to the scalograms. These filtered scalograms are then fed into convolutional neural networks, extracting informative features that harness the distinct characteristics captured by both STFT and CWT. For enhanced computational efficiency and discriminatory power, principal component analysis is employed to reduce the feature space dimensionality. Subsequently, pipeline leaks are accurately detected and classified by categorizing the reduced dimensional features using t-distributed stochastic neighbor embedding and artificial neural networks. The hybrid approach achieves high accuracy and reliability in leak detection, demonstrating its effectiveness in capturing both spectral and temporal details. This research significantly contributes to pipeline monitoring and maintenance and offers a promising solution for real-time leak detection in diverse industrial applications. [ABSTRACT FROM AUTHOR]

Damage detection based on modal parameter changes has become popular in the last few decades. Nowadays, there are robust and reliable mathematical relations available to predict natural frequency changes if damage parameters are known. Using these relations, it is possible to create databases containing a large variety of damage scenarios. Damage can be thus assessed by applying an inverse method. The problem is the complexity of the database, especially for structures with more cracks. In this paper, we propose two machine learning methods, namely the random forest (RF), and the artificial neural network (ANN), as search tools. The databases we developed contain damage scenarios for a prismatic cantilever beam with one crack and ideal and non-ideal boundary conditions. The crack assessment was made in two steps. First, a coarse damage location was found from the networks trained for scenarios comprising the whole beam. Afterwards, the assessment was made involving a particular network trained for the segment of the beam on which the crack was previously found. Using the two machine learning methods, we succeeded in estimating the crack location and severity with high accuracy for both simulation and laboratory experiments. Regarding the location of the crack, which was the main goal of the practitioners, the errors were less than 0.6%. Based on these achievements, we concluded that the damage assessment we propose, in conjunction with the machine learning methods, is robust and reliable. [ABSTRACT FROM AUTHOR]

The paper presents a new security aspect for a Mobile Ad-Hoc Network (MANET)-based IoT model using the concept of artificial intelligence. The Black Hole Attack (BHA) is considered one of the most affecting threats in the MANET in which the attacker node drops the entire data traffic and hence degrades the network performance. Therefore, it necessitates the designing of an algorithm that can protect the network from the BHA node. This article introduces Ad-hoc On-Demand Distance Vector (AODV), a new updated routing protocol that combines the advantages of the Artificial Bee Colony (ABC), Artificial Neural Network (ANN), and Support Vector Machine (SVM) techniques. The combination of the SVM with ANN is the novelty of the proposed model that helps to identify the attackers within the discovered route using the AODV routing mechanism. Here, the model is trained using ANN but the selection of training data is performed using the ABC fitness function followed by SVM. The role of ABC is to provide a better route for data transmission between the source and the destination node. The optimized route, suggested by ABC, is then passed to the SVM model along with the node's properties. Based on those properties ANN decides whether the node is a normal or an attacker node. The simulation analysis performed in MATLAB shows that the proposed work exhibits an improvement in terms of Packet Delivery Ratio (PDR), throughput, and delay. To validate the system efficiency, a comparative analysis is performed against the existing approaches such as Decision Tree and Random Forest that indicate that the utilization of the SVM with ANN is a beneficial step regarding the detection of BHA attackers in the MANET-based IoT networks. [ABSTRACT FROM AUTHOR]

The progress of technology on energy and IoT fields has led to an increasingly complicated electric environment in low-voltage local microgrid, along with the extensions of electric vehicle, micro-generation, and local storage. It is required to establish a home energy management system (HEMS) to efficiently integrate and manage household energy micro-generation, consumption and storage, in order to realize decentralized local energy systems at the community level. Domestic power demand prediction is of great importance for establishing HEMS on realizing load balancing as well as other smart energy solutions with the support of IoT techniques. Artificial neural networks with various network types (e.g., DNN, LSTM/GRU based RNN) and other configurations are widely utilized on energy predictions. However, the selection of network configuration for each research is generally a case by case study achieved through empirical or enumerative approaches. Moreover, the commonly utilized network initialization methods assign parameter values based on random numbers, which cause diversity on model performance, including learning efficiency, forecast accuracy, etc. In this paper, an evolutionary ensemble neural network pool (EENNP) method is proposed to achieve a population of well-performing networks with proper combinations of configuration and initialization automatically. In the experimental study, power demand predictions of multiple households are explored in three application scenarios: optimizing potential network configuration set, forecasting single household power demand, and refilling missing data. The impacts of evolutionary parameters on model performance are investigated. The experimental results illustrate that the proposed method achieves better solutions on the considered scenarios. The optimized potential network configuration set using EENNP achieves a similar result to manual optimization. The results of household demand prediction and missing data refilling perform better than the naïve and simple predictors. [ABSTRACT FROM AUTHOR]

This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR) images. The feature sets consisted of span image, the H/A/a decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features were reduced by principle component analysis (PCA). Finally, a two-hidden-layer forward neural network (NN) was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO). K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP), adaptive BP (ABP), momentum BP (MBP), Particle Swarm Optimization (PSO), and Resilient back-propagation (RPROP) methods. Moreover, the computation time for each pixel is only 1.08 × 10-7 s. [ABSTRACT FROM AUTHOR]

Over the past decade, the artificial neural networks domain has seen a considerable embracement of deep neural networks among many applications. However, deep neural networks are typically computationally complex and consume high power, hindering their applicability for resource-constrained applications, such as self-driving vehicles, drones, and robotics. Spiking neural networks, often employed to bridge the gap between machine learning and neuroscience fields, are considered a promising solution for resource-constrained applications. Since deploying spiking neural networks on traditional von-Newman architectures requires significant processing time and high power, typically, neuromorphic hardware is created to execute spiking neural networks. The objective of neuromorphic devices is to mimic the distinctive functionalities of the human brain in terms of energy efficiency, computational power, and robust learning. Furthermore, natural language processing, a machine learning technique, has been widely utilized to aid machines in comprehending human language. However, natural language processing techniques cannot also be deployed efficiently on traditional computing platforms. In this research work, we strive to enhance the natural language processing traits/abilities by harnessing and integrating the SNNs traits, as well as deploying the integrated solution on neuromorphic hardware, efficiently and effectively. To facilitate this endeavor, we propose a novel, unique, and efficient sentiment analysis model created using a large-scale SNN model on SpiNNaker neuromorphic hardware that responds to user inputs. SpiNNaker neuromorphic hardware typically can simulate large spiking neural networks in real time and consumes low power. We initially create an artificial neural networks model, and then train the model using an Internet Movie Database (IMDB) dataset. Next, the pre-trained artificial neural networks model is converted into our proposed spiking neural networks model, called a spiking sentiment analysis (SSA) model. Our SSA model using SpiNNaker, called SSA-SpiNNaker, is created in such a way to respond to user inputs with a positive or negative response. Our proposed SSA-SpiNNaker model achieves 100% accuracy and only consumes 3970 Joules of energy, while processing around 10,000 words and predicting a positive/negative review. Our experimental results and analysis demonstrate that by leveraging the parallel and distributed capabilities of SpiNNaker, our proposed SSA-SpiNNaker model achieves better performance compared to artificial neural networks models. Our investigation into existing works revealed that no similar models exist in the published literature, demonstrating the uniqueness of our proposed model. Our proposed work would offer a synergy between SNNs and NLP within the neuromorphic computing domain, in order to address many challenges in this domain, including computational complexity and power consumption. Our proposed model would not only enhance the capabilities of sentiment analysis but also contribute to the advancement of brain-inspired computing. Our proposed model could be utilized in other resource-constrained and low-power applications, such as robotics, autonomous, and smart systems. [ABSTRACT FROM AUTHOR]

The paper presents the development of the IMUMETER sensor, designed to study the dynamics of aircraft movement, in particular, to measure the ground performance of the aircraft. A motivation of this study was to develop a sensor capable of airplane motion measurement, especially for airfield performance, takeoff and landing. The IMUMETER sensor was designed on the basis of the method of artificial neural networks. The use of a neural network is justified by the fact that the automation of the measurement of the airplane's ground distance during landing based on acceleration data is possible thanks to the recognition of the touchdown and stopping points, using artificial intelligence. The hardware is based on a single-board computer that works with the inertial navigation platform and a satellite navigation sensor. In the development of the IMUMETER device, original software solutions were developed and tested. The paper describes the development of the Convolution Neural Network, including the learning process based on the measurement results during flight tests of the PZL 104 Wilga 35A aircraft. The ground distance of the test airplane during landing on a grass runway was calculated using the developed neural network model. Additionally included are exemplary measurements of the landing distance of the test airplane during landing on a grass runway. The results obtained in this study can be useful in the development of artificial intelligence-based sensors, especially those for the measurement and analysis of aircraft flight dynamics. [ABSTRACT FROM AUTHOR]

This paper aims to present the analysis and development of a complete electronic smart meter that is able to perform four-quadrant measurements, act as a three-phase shunt active power filter (APF), and control three-phase induction motors by stator flux estimation. A transmission control protocol together with Internet protocol (TCP/IP) communication protocol for the remote access of measurement data is embedded into the application to securely transmit reliable information. An artificial neural network trained with particle swarm optimization is used for stator flux estimation, and a fuzzy logic controller is adopted to regulate the power converter DC bus voltage. The present work gathers knowledge from multidisciplinary fields, and all applied techniques have not been proposed altogether before. All control functions are embedded into a field-programmable gate array (FPGA) device, using VHSIC Hardware Description Language (VHDL), to enhance efficiency taking advantage of parallelism and high speed. An FPGA-in-the-loop cosimulation technique was first applied to prove the control functions' functionality, and, later, experimental evaluations are conducted to finally prove equipment operation and reliability. [ABSTRACT FROM AUTHOR]

The main objective of this paper is to describe a building process of a model predicting the soil strength at unpaved airport surfaces (unpaved runways, safety areas in runway proximity, runway strips, and runway end safety areas). The reason for building this model is to partially substitute frequent and meticulous inspections of an airport movement area comprising the bearing strength evaluation and provide an efficient tool to organize surface maintenance. Since the process of building such a model is complex for a physical model, it is anticipated that it might be addressed by a statistical model instead. Therefore, fuzzy logic (FL) and artificial neural network (ANN) capabilities are investigated and compared with linear regression function (LRF). Large data sets comprising the bearing strength and meteorological characteristics are applied to train the likely model variations to be subsequently compared with the application of standard statistical quantitative parameters. All the models prove that the inclusion of antecedent soil strength as an additional model input has an immense impact on the increase in model accuracy. Although the M7 model out of the ANN group displays the best performance, the M3 model is considered for practical implications being less complicated and having fewer inputs. In general, both the ANN and FL models outperform the LRF models well in all the categories. The FL models perform almost equally as well as the ANN but with slightly decreased accuracy. [ABSTRACT FROM AUTHOR]

Existing government air quality monitoring networks consist of static measurement stations, which are highly reliable and accurately measure a wide range of air pollutants, but they are very large, expensive and require significant amounts of maintenance. As a promising solution, low-cost sensors are being introduced as complementary, air quality monitoring stations. These sensors are, however, not reliable due to the lower accuracy, short life cycle and corresponding calibration issues. Recent studies have shown that low-cost sensors are affected by relative humidity and temperature. In this paper, we explore methods to additionally improve the calibration algorithms with the aim to increase the measurement accuracy considering the impact of temperature and humidity on the readings, by using machine learning. A detailed comparative analysis of linear regression, artificial neural network and random forest algorithms are presented, analyzing their performance on the measurements of CO, NO2 and PM10 particles, with promising results and an achieved R 2 of 0.93–0.97, 0.82–0.94 and 0.73–0.89 dependent on the observed period of the year, respectively, for each pollutant. A comprehensive analysis and recommendations on how low-cost sensors could be used as complementary monitoring stations to the reference ones, to increase spatial and temporal measurement resolution, is provided. [ABSTRACT FROM AUTHOR]

The feasibility and usefulness of frequency domain fusion of data from multiple vibration sensors installed on typical industrial rotating machines, based on coherent composite spectrum (CCS) as well as poly-coherent composite spectrum (pCCS) techniques, have been well-iterated by earlier studies. However, all previous endeavours have been limited to rotor faults, thereby raising questions about the proficiency of the approach for classifying faults related to other critical rotating machine components such as gearboxes. Besides the restriction in scope of the founding CCS and pCCS studies on rotor-related faults, their diagnosis approach was manually implemented, which could be unrealistic when faced with routine condition monitoring of multi-component industrial rotating machines, which often entails high-frequency sampling at multiple locations. In order to alleviate these challenges, this paper introduced an automated framework that encompassed feature generation through CCS, data dimensionality reduction through principal component analysis (PCA), and faults classification using artificial neural network (ANN). The outcomes of the automated approach are a set of visualised decision maps representing individually simulated scenarios, which simplifies and illustrates the decision rules of the faults characterisation framework. Additionally, the proposed approach minimises diagnosis-related downtime by allowing asset operators to easily identify anomalies at their incipient stages without necessarily possessing vibration monitoring expertise. Building upon the encouraging results obtained from the preceding part of this approach that was limited to well-known rotor-related faults, the proposed framework was significantly extended to include experimental and open-source gear fault data. The results show that in addition to early established rotor-related faults classification, the approach described here can also effectively and automatically classify gearbox faults, thereby improving the robustness. [ABSTRACT FROM AUTHOR]

In this paper, an artificial neural network is applied for enhancing the resolution of images from an optical microscope based on a network trained with the images acquired from a scanning electron microscope. The resolution of microscopic images is important in various fields, especially for microfluidics because the measurements, such as the dimension of channels and cells, largely rely on visual information. The proposed method is experimentally validated with microfluidic structure. The images of structural edges from the optical microscope are blurred due to optical effects while the images from the scanning electron microscope are sharp and clear. Intensity profiles perpendicular to the edges and the corresponding edge positions determined by the scanning electron microscope images are plugged in a neural network as the input features and the output target, respectively. According to the results, the blurry edges of the microstructure in optical images can be successfully enhanced. The average error between the predicted channel position and ground truth is around 328 nanometers. The effects of the feature length are discussed. The proposed method is expected to significantly contribute to microfluidic applications, such as on-chip cell evaluation. [ABSTRACT FROM AUTHOR]

Buildings account for a majority of the primary energy consumption of the human society, therefore, analyses of building energy consumption monitoring data are of significance to the discovery of anomalous energy usage patterns, saving of building utility expenditures, and contribution to the greater environmental protection effort. This paper presents a unified framework for the automatic extraction and integration of building energy consumption data from heterogeneous building management systems, along with building static data from building information models to serve analysis applications. This paper also proposes a diagnosis framework based on density-based clustering and artificial neural network regression using the integrated data to identify anomalous energy usages. The framework and the methods have been implemented and validated from data collected from a multitude of large-scale public buildings across China. [ABSTRACT FROM AUTHOR]

Gait patterns are a result of the complex kinematics that enable human two-legged locomotion, and they can reveal a lot about a person's state and health. Analysing them is useful for researchers to get new insights into the course of diseases, and for physicians to track the progress after healing from injuries. When a person walks and is interfered with in any way, the resulting disturbance can show up and be found in the gait patterns. This paper describes an experimental setup for capturing gait patterns with a capacitive sensor floor, which can detect the time and position of foot contacts on the floor. With this setup, a dataset was recorded where 42 participants walked over a sensor floor in different modes, inter alia, normal pace, closed eyes, and dual-task. A recurrent neural network based on Long Short-Term Memory units was trained and evaluated for the classification task of recognising the walking mode solely from the floor sensor data. Furthermore, participants were asked to do the Unilateral Heel-Rise Test, and their gait was recorded before and after doing the test. Another neural network instance was trained to predict the number of repetitions participants were able to do on the test. As the results of the classification tasks turned out to be promising, the combination of this sensor floor and the recurrent neural network architecture seems like a good system for further investigation leading to applications in health and care. [ABSTRACT FROM AUTHOR]

Instrumental odour monitoring systems (IOMS) are intelligent electronic sensing tools for which the primary application is the generation of odour metrics that are indicators of odour as perceived by human observers. The quality of the odour sensor signal, the mathematical treatment of the acquired data, and the validation of the correlation of the odour metric are key topics to control in order to ensure a robust and reliable measurement. The research presents and discusses the use of different pattern recognition and feature extraction techniques in the elaboration and effectiveness of the odour classification monitoring model (OCMM). The effect of the rise, intermediate, and peak period from the original response curve, in collaboration with Linear Discriminant Analysis (LDA) and Artificial Neural Networks (ANN) as a pattern recognition algorithm, were investigated. Laboratory analyses were performed with real odour samples collected in a complex industrial plant, using an advanced smart IOMS. The results demonstrate the influence of the choice of method on the quality of the OCMM produced. The peak period in combination with the Artificial Neural Network (ANN) highlighted the best combination on the basis of high classification rates. The paper provides information to develop a solution to optimize the performance of IOMS. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) is a promising direction in automated parking systems (APSs), as integrating planning and tracking control using RL can potentially maximize the overall performance. However, commonly used model-free RL requires many interactions to achieve acceptable performance, and model-based RL in APS cannot continuously learn. In this paper, a data-efficient RL method is constructed to learn from data by use of a model-based method. The proposed method uses a truncated Monte Carlo tree search to evaluate parking states and select moves. Two artificial neural networks are trained to provide the search probability of each tree branch and the final reward for each state using self-trained data. The data efficiency is enhanced by weighting exploration with parking trajectory returns, an adaptive exploration scheme, and experience augmentation with imaginary rollouts. Without human demonstrations, a novel training pipeline is also used to train the initial action guidance network and the state value network. Compared with path planning and path-following methods, the proposed integrated method can flexibly co-ordinate the longitudinal and lateral motion to park a smaller parking space in one maneuver. Its adaptability to changes in the vehicle model is verified by joint Carsim and MATLAB simulation, demonstrating that the algorithm converges within a few iterations. Finally, experiments using a real vehicle platform are used to further verify the effectiveness of the proposed method. Compared with obtaining rewards using simulation, the proposed method achieves a better final parking attitude and success rate. [ABSTRACT FROM AUTHOR]

Due to the growing public awareness of cardiovascular disease (CVD), blood pressure (BP) estimation models have been developed based on physiological parameters extracted from both electrocardiograms (ECGs) and photoplethysmograms (PPGs). Still, in order to enhance the usability as well as reduce the sensor cost, researchers endeavor to establish a generalized BP estimation model using only PPG signals. In this paper, we propose a deep neural network model capable of extracting 32 features exclusively from PPG signals for BP estimation. The effectiveness and accuracy of our proposed model was evaluated by the root mean square error (RMSE), mean absolute error (MAE), the Association for the Advancement of Medical Instrumentation (AAMI) standard and the British Hypertension Society (BHS) standard. Experimental results showed that the RMSEs in systolic blood pressure (SBP) and diastolic blood pressure (DBP) are 4.643 mmHg and 3.307 mmHg, respectively, across 9000 subjects, with 80.63% of absolute errors among estimated SBP records lower than 5 mmHg and 90.19% of absolute errors among estimated DBP records lower than 5 mmHg. We demonstrated that our proposed model has remarkably high accuracy on the largest BP database found in the literature, which shows its effectiveness compared to some prior works. [ABSTRACT FROM AUTHOR]

Flooding risk is a threat to many sea-level cities and residential areas in the world. In the city Kristianstad in southern Sweden, a large number of sensors of different types have been deployed to monitor rain and other weather conditions, water levels at sea and lakes, ground water levels, and water flows in the city's storm-water and sewage systems. All the sensors are enabled by battery and wireless communication, and allow real-time data to be transferred and visualized on a cloud-based Internet of Things (IoT) portal. To better enable the system with capacity of foreseeing upcoming flooding threats and to allow early response from decision-makers, it is desired to build a real-time flood forecast system by utilizing the massive sensor data collected at the IoT portal and data from 3rd party weather forecast service. In this article, we have developed a smart flood forecast system using machine learning and artificial neural networks. The developed forecast system has successfully integrated data from multiple sources and can make accurate flood forecast at distributed locations for the coming days. After being successfully implemented as software product and integrated with the city's IoT portal, our developed flood forecast system has significantly extended the basic monitoring functions of the city's IoT infrastructure. This article presents the context of this work, the challenges that have been encountered during our development, our solutions and performance evaluation results. To the best of our knowledge, this is the first large-scale IoT-based real-time flood forecast system that has been enabled by artificial intelligence (AI) and deployed in real world. [ABSTRACT FROM AUTHOR]

The gas sweetening process removes hydrogen sulfide (H2S) in an acid gas removal unit (AGRU) to meet the gas sales' specification, known as sweet gas. Monitoring the concentration of H2S in sweet gas is crucial to avoid operational and environmental issues. This study shows the capability of artificial neural networks (ANN) to predict the concentration of H2S in sweet gas. The concentration of N-methyldiethanolamine (MDEA) and Piperazine (PZ), temperature and pressure as inputs, and the concentration of H2S in sweet gas as outputs have been used to create the ANN network. Two distinct backpropagation techniques with various transfer functions and numbers of neurons were used to train the ANN models. Multiple linear regression (MLR) was used to compare the outcomes of the ANN models. The models' performance was assessed using the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). The findings demonstrate that ANN trained by the Levenberg–Marquardt technique, equipped with a logistic sigmoid (logsig) transfer function with three neurons achieved the highest R2 (0.966) and the lowest MAE (0.066) and RMSE (0.122) values. The findings suggested that ANN can be a reliable and accurate prediction method in predicting the concentration of H2S in sweet gas. [ABSTRACT FROM AUTHOR]

Knowledge of surface reflection of an object is essential in many technological fields, including graphics and cultural heritage. Compared to direct multi- or hyper-spectral capturing approaches, commercial RGB cameras allow for a high resolution and fast acquisition, so the idea of mapping this information into a reflectance spectrum (RS) is promising. This study compared two modelling approaches based on a training set of RGB-reflectance pairs, one implementing artificial neural networks (ANN) and the other one using multivariate polynomial approximation (PA). The effect of various parameters was investigated: the ANN learning algorithm—standard backpropagation (BP) or Levenberg-Marquardt (LM), the number of hidden layers (HLs) and neurons, the degree of multivariate polynomials in PA, the number of inputs, and the training set size on both models. In the two-layer ANN with significantly fewer inputs than outputs, a better MSE performance was found where the number of neurons in the first HL was smaller than in the second one. For ANNs with one and two HLs with the same number of neurons in the first layer, the RS reconstruction performance depends on the choice of BP or LM learning algorithm. RS reconstruction methods based on ANN and PA are comparable, but the ANN models' better fine-tuning capabilities enable, under realistic constraints, finding ANNs that outperform PA models. A profiling approach was proposed to determine the initial number of neurons in HLs—the search centre of ANN models for different training set sizes. [ABSTRACT FROM AUTHOR]

This work presents the simultaneous quantification of four non-steroidal anti-inflammatory drugs (NSAIDs), paracetamol, diclofenac, naproxen, and aspirin, in mixture solutions, by a laboratory-made working electrode based on carbon paste modified with multi-wall carbon nanotubes (MWCNT-CPE) and Differential Pulse Voltammetry (DPV). Preliminary electrochemical analysis was performed using cyclic voltammetry, and the sensor morphology was studied by scanning electronic microscopy and electrochemical impedance spectroscopy. The sample set ranging from 0.5 to 80 µmol L−1 was prepared using a complete factorial design (34) and considering some interferent species such as ascorbic acid, glucose, and sodium dodecyl sulfate to build the response model and an external randomly subset of samples within the experimental domain. A data compression strategy based on discrete wavelet transform was applied to handle voltammograms' complexity and high dimensionality. Afterward, Partial Least Square Regression (PLS) and Artificial Neural Networks (ANN) predicted the drug concentrations in the mixtures. PLS-adjusted models (n = 12) successfully predicted the concentration of paracetamol and diclofenac, achieving correlation values of R ≥ 0.9 (testing set). Meanwhile, the ANN model (four layers) obtained good prediction results, exhibiting R ≥ 0.968 for the four analyzed drugs (testing stage). Thus, an MWCNT-CPE electrode can be successfully used as a potential sensor for voltammetric determination and NSAID analysis. [ABSTRACT FROM AUTHOR]