Showing papers in "IEEE Transactions on Instrumentation and Measurement in 2017"

Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network

Abstract: To assess health conditions of rotating machinery efficiently, multiple accelerometers are mounted on different locations to acquire a variety of possible faults signals. The statistical features are extracted from these signals to identify the running status of a machine. However, the acquired vibration signals are different due to sensor’s arrangement and environmental interference, which may lead to different diagnostic results. In order to improve the fault diagnosis reliability, a new multisensor data fusion technique is proposed. First, time-domain and frequency-domain features are extracted from the different sensor signals, and then these features are input into multiple two-layer sparse autoencoder (SAE) neural networks for feature fusion. Finally, fused feature vectors can be regarded as the machine health indicators, and be used to train deep belief network (DBN) for further classification. To verify the effectiveness of the proposed SAE-DBN scheme, the bearing fault experiments were conducted on a bearing test platform, and the vibration data sets under different running speeds were collected for algorithm validation. For comparison, different feature fusion methods were also applied to multisensor fusion in the experiments. Experimental results demonstrated that the proposed approach can effectively identify the machine running conditions and significantly outperform other fusion methods.

Energy-Fluctuated Multiscale Feature Learning With Deep ConvNet for Intelligent Spindle Bearing Fault Diagnosis

Abstract: Considering various health conditions under varying operational conditions, the mining sensitive feature from the measured signals is still a great challenge for intelligent fault diagnosis of spindle bearings. This paper proposed a novel energy-fluctuated multiscale feature mining approach based on wavelet packet energy (WPE) image and deep convolutional network (ConvNet) for spindle bearing fault diagnosis. Different from the vector characteristics applied in intelligent diagnosis of spindle bearings, wavelet packet transform is first combined with phase space reconstruction to rebuild a 2-D WPE image of the frequency subspaces. This special image can reconstruct the local relationship of the WP nodes and hold the energy fluctuation of the measured signal. Then, the identifiable characteristics can be further learned by a special architecture of the deep ConvNet. Other than the traditional neural network architecture, to maintain the global and local information simultaneously, deep ConvNet combines the skipping layer with the last convolutional layer as the input of the multiscale layer. The comparisons of clustering distribution and classification accuracy with six other features show that the proposed feature mining approach is quite suitable for spindle bearing fault diagnosis with multiclass classification regardless of the load fluctuation.

Comparing Ubisense, BeSpoon, and DecaWave UWB Location Systems: Indoor Performance Analysis

Abstract: Most ultrawideband (UWB) location systems already proposed for position estimation have only been individually evaluated for particular scenarios. For a fair performance comparison among different solutions, a common evaluation scenario would be desirable. In this paper, we compare three commercially available UWB systems (Ubisense, BeSpoon, and DecaWave) under the same experimental conditions, in order to do a critical performance analysis. We include the characterization of the quality of the estimated tag-to-sensor distances in an indoor industrial environment. This testing space includes areas under line-of-sight (LOS) and diverse non-LOS conditions caused by the reflection, propagation, and the diffraction of the UWB radio signals across different obstacles. The study also includes the analysis of the estimated azimuth and elevation angles for the Ubisense system, which is the only one that incorporates this feature using an array antenna at each sensor. Finally, we analyze the 3-D positioning estimation performance of the three UWB systems using a Bayesian filter implemented with a particle filter and a measurement model that takes into account bad range measurements and outliers. A final conclusion is drawn about which system performs better under these industrial conditions.

Analysis of Three IoT-Based Wireless Sensors for Environmental Monitoring

Abstract: The recent changes in climate have increased the importance of environmental monitoring, making it a topical and highly active research area. This field is based on remote sensing and on wireless sensor networks for gathering data about the environment. Recent advancements, such as the vision of the Internet of Things (IoT), the cloud computing model, and cyber-physical systems, provide support for the transmission and management of huge amounts of data regarding the trends observed in environmental parameters. In this context, the current work presents three different IoT-based wireless sensors for environmental and ambient monitoring: one employing User Datagram Protocol (UDP)-based Wi-Fi communication, one communicating through Wi-Fi and Hypertext Transfer Protocol (HTTP), and a third one using Bluetooth Smart. All of the presented systems provide the possibility of recording data at remote locations and of visualizing them from every device with an Internet connection, enabling the monitoring of geographically large areas. The development details of these systems are described, along with the major differences and similarities between them. The feasibility of the three developed systems for implementing monitoring applications, taking into account their energy autonomy, ease of use, solution complexity, and Internet connectivity facility, was analyzed, and revealed that they make good candidates for IoT-based solutions.

ECG Signal Analysis Using DCT-Based DOST and PSO Optimized SVM

Abstract: Signal processing techniques are an obvious choice for real-time analysis of electrocardiography (ECG) signals. However, classical signal processing techniques are unable to deal with the nonstationary nature of the ECG signal. In this context, this paper presents a new approach, i.e., discrete orthogonal stockwell transform using discrete cosine transform for efficient representation of the ECG signal in time–frequency space. These time–frequency features are further reduced in lower dimensional space using principal component analysis, representing the morphological characteristics of the ECG signal. In addition, the dynamic features (i.e., RR-interval information) are computed and concatenated to the morphological features to constitute the final feature set, which is utilized to classify the ECG signals using support vector machine (SVM). In order to improve the classification performance, particle swarm optimization technique is employed for gradually tuning the learning parameters of the SVM classifier. In this paper, ECG data exhibiting 16 classes of the most frequently occurring arrhythmic events are taken from the benchmark MIT-BIH arrhythmia database for the validation of the proposed methodology. The experimental results yielded an improved overall accuracy, sensitivity (Sp), and positive predictivity (Pp) of 98.82% in comparison with the existing approaches available in the literature.

Stacked Multilevel-Denoising Autoencoders: A New Representation Learning Approach for Wind Turbine Gearbox Fault Diagnosis

Abstract: Currently, vibration analysis has been widely considered as an effective way to fulfill the fault diagnosis task of gearboxes in wind turbines (WTs) However, vibration signals are usually with abundant noise and characterized as nonlinearity and nonstationarity Therefore, it is quite challenging to extract robust and useful fault features from complex vibration signals to achieve an accurate and reliable diagnosis This paper proposes a novel feature representation learning approach, named stacked multilevel-denoising autoencoders (SMLDAEs), with the aim to learn robust and discriminative fault feature representations through a deep network architecture for diagnosis accuracy improvement In our proposed approach, we design an MLD training scheme, which uses multiple noise levels to train AEs It enables to learn more general and detailed fault feature patterns simultaneously at different scales from the complex frequency spectra of the raw vibration data, and therefore helps enhance the feature learning and fault diagnosis capability Furthermore, SMLDAE-based fault diagnosis is performed with an unsupervised representation learning procedure followed by a supervised fine-tuning process with label information for classification Our approach is evaluated by using the field vibration data collected from a self-designed WT gearbox test rig The results show that our proposed approach learned more robust and discriminative fault feature representations and achieved the best diagnosis accuracy compared with the traditional approaches

Evaluation of the IoT LoRaWAN Solution for Distributed Measurement Applications

Abstract: Internet of Things (IoT) is based on data collection, where billions of sensors sample the real world; in other words, the IoT includes a giant distributed measurement system (DMS). A question still requiring an answer is: Are the IoT technologies usable to enhance traditional measurement systems, since they have been developed for a very similar objective? In this paper, the use of a long-range (LoRa) technology, originally developed for IoT, is investigated with the aim of implementing DMSs. After the conclusion that LoRa and LoRa wide area network architectures show a good match with measurement systems, this paper focuses on the characterization of time-related performance indicators that are important for distributed systems. The experimental results show the capability of low-cost transceiver to schedule the transmission of frames with a standard uncertainty less than $3~\mu \text{s}$ ; and an acceptable long-term clock stability (Allan Deviation) of commercial available devices (nodes and packet forwarders) for application such as smart metering, smart building, and process industry.

Hyperspectral Image Classification via Multiple-Feature-Based Adaptive Sparse Representation

Abstract: A multiple-feature-based adaptive sparse representation (MFASR) method is proposed for the classification of hyperspectral images (HSIs). The proposed method mainly includes the following steps. First, four different features are separately extracted from the original HSI and they reflect different kinds of spectral and spatial information. Second, for each pixel, a shape adaptive (SA) spatial region is extracted. Third, an adaptive sparse representation algorithm is introduced to obtain the sparse coefficients for the multiple-feature matrix set of pixels in each SA region. Finally, these obtained coefficients are jointly used to determine the class label of each test pixel. Experimental results demonstrated that the proposed MFASR method can outperform several well-known classifiers in terms of both qualitative and quantitative results.

Matching Synchrosqueezing Wavelet Transform and Application to Aeroengine Vibration Monitoring

Abstract: This paper presents a new time–frequency (TF) analysis method called matching synchrosqueezing wavelet transform (MSWT) to signals with fast varying instantaneous frequency (IF). The original synchrosqueezing wavelet transform (SWT) can effectively improve the readability of TF representation (TFR) of signals with slowly varying IF. However, SWT still suffers from TF blurs for signals with fast varying IF. Moreover, the variable operating conditions of the aeroengine always make the vibration a signal with fast varying IF, especially when it comes to significant speed changes, which results in the obscure TFR for aeroengine vibration monitoring. In this paper, the MSWT introduces a chirp rate estimation into a comprehensive IF estimation to match the TF structure of the signals with fast varying IF and thus to achieve a highly concentrated TFR as the standard TF reassignment methods. Most importantly, the MSWT retains the reconstruction benefit like the SWT. The proposed MSWT is validated by both numerical simulation and applications in a bat echolocation signal analysis. Finally, a case study of a dual-rotor turbofan engine is given to illustrate the effectiveness of the proposed method for aeroengine vibration monitoring.

Arc Fault Detection Method Based on CZT Low-Frequency Harmonic Current Analysis

Abstract: This paper presents a method for the detection of series arc faults in electrical circuits, which has been developed starting from an experimental characterization of the arc fault phenomenon and an arcing current study in several test conditions. Starting from this, the authors have found that is it possible to suitably detect arc faults by means of a high-resolution low-frequency harmonic analysis of current signal, based on chirp zeta transform, and a proper set of indicators. The proposed method effectiveness is shown by means of experimental tests, which were carried in both arcing and nonarcing conditions and in the presence of different loads, chosen according to the UL 1699 standard requirements.

Particle Learning Framework for Estimating the Remaining Useful Life of Lithium-Ion Batteries

Abstract: As an important part of prognostics and health management, accurate remaining useful life (RUL) prediction for lithium (Li)-ion batteries can provide helpful reference for when to maintain the batteries in advance. This paper presents a novel method to predict the RUL of Li-ion batteries. This method is based on the framework of improved particle learning (PL). The PL framework can prevent particle degeneracy by resampling state particles first with considering the current measurement information and then propagating them. Meanwhile, PL is improved by adjusting the number of particles at each iteration adaptively to reduce the running time of the algorithm, which makes it suitable for online application. Furthermore, the kernel smoothing algorithm is fused into PL to keep the variance of parameter particles invariant during recursive propagation with the battery prediction model. This entire method is referred to as PLKS in this paper. The model can then be updated by the proposed method when new measurements are obtained. Future capacities are iteratively predicted with the updated prediction model until the predefined threshold value is triggered. The RUL is calculated according to these predicted capacities and the predefined threshold value. A series of case studies that demonstrate the proposed method is presented in the experiment.

Discriminative Deep Belief Networks with Ant Colony Optimization for Health Status Assessment of Machine

Abstract: On-line health status monitoring, a key part of prognostics and health management, provides various benefits, such as preventing unexpected failure and improving safety and reliability. In this paper, a data-driven approach for health status assessment is presented. A novel method based on discriminative deep belief networks (DDBN) and ant colony optimization (ACO) is used to predict health status of machine. DDBN is a new paradigm that utilizes a deep architecture to combine the advantages of deep belief networks and discriminative ability of back-propagation strategy. DDBN works through a greedy layer-by-layer training with multiple stacked restricted Boltzmann machines, which preserves information well when embedding features from high-dimensional space to low-dimensional space. However, selecting the parameters of DDBN is quite challenging. To address the problem, ACO is introduced to DDBN in this paper. By optimization, the structure of DDBN model is determined automatically without prior knowledge and the performance is enhanced. To evaluate the proposed approach, two case studies were carried out, which shows that it can achieve a good result. The performance of this model is also compared with support vector machine. It is concluded that the proposed method is very promising in the field of prognostics.

Injurious or Noninjurious Defect Identification From MFL Images in Pipeline Inspection Using Convolutional Neural Network

Abstract: This paper proposes an injurious or noninjurious defect identification method from magnetic flux leakage (MFL) images based on convolutional neural network. Different from previous approaches, this method is fed by the MFL images instead of the features of the MFL measurements, and thus it can skip the procedure of feature extraction. Moreover, for convenience, a normalization layer is added to the front of model. In the convolution layers, the rectified linear units are employed as the activation functions to shorten the training period and improve the performance. In addition, two local response normalization layers are also embedded into the proposed structure. We demonstrate the performance of the proposed model using real MFL data collected from experimental pipelines. Benefited from the special structure of the proposed model, this method is robust for shift, scale, and distortion variances of input MFL images. We also present a comparative result of the proposed model and other methods. The results prove that the proposed method can achieve higher accuracy than the traditional approaches.

Soft Sensor Modeling of Nonlinear Industrial Processes Based on Weighted Probabilistic Projection Regression

Abstract: Probabilistic principal component regression (PPCR) has been introduced for soft sensor modeling as a probabilistic projection regression method, which is effective in handling data collinearity and random noises. However, the linear limitation of data relationships may cause its performance deterioration when applied to nonlinear processes. Therefore, a novel weighted PPCR (WPPCR) algorithm is proposed in this paper for soft sensing of nonlinear processes. In WPPCR, by including the most relevant samples for local modeling, different weights will be assigned to these samples according to their similarities with the testing sample. Then, a weighted log-likelihood function is constructed, and expectation-maximization algorithm can be carried out iteratively to obtain the optimal model parameters. In this way, the nonlinear data relationship can be locally approximated by WPPCR. The effectiveness and flexibility of the proposed method are validated on a numerical example and an industrial process.

Random Triggering-Based Sub-Nyquist Sampling System for Sparse Multiband Signal

Abstract: We propose a novel random triggering-based modulated wideband compressive sampling (RT-MWCS) method to facilitate efficient realization of sub-Nyquist rate compressive sampling systems for sparse wideband signals. Under the assumption that the signal is repetitively (not necessarily periodically) triggered, RT-MWCS uses random modulation to obtain measurements of the signal at randomly chosen positions. It uses multiple measurement vector method to estimate the nonzero supports of the signal in the frequency domain. Then, the signal spectrum is solved using least square estimation. The distinct ability of estimating sparse multiband signal is facilitated with the use of level triggering and time-to-digital converter devices previously used in random equivalent sampling scheme. Compared to the existing compressive sampling (CS) techniques, such as modulated wideband converter (MWC), RT-MWCS is with simple system architecture and can be implemented with one channel at the cost of more sampling time. Experimental results indicate that, for sparse multiband signal with unknown spectral support, RT-MWCS requires a sampling rate much lower than Nyquist rate, while giving great quality of signal reconstruction.

Nonlinear Cuffless Blood Pressure Estimation of Healthy Subjects Using Pulse Transit Time and Arrival Time

Abstract: This paper presents a novel blood pressure (BP) estimation method based on pulse transit time (PTT) and pulse arrival time (PAT) to estimate the systolic BP (SBP) and the diastolic BP (DBP). A data acquisition hardware is designed for high-resolution sampling of phonocardiogram (PCG), photoplethysmogram, and electrocardiogram (ECG). PCG and ECG perform as the proximal timing reference to obtain PTT and PAT indices, respectively. In order to derive a BP estimator model, a calibration procedure, including a supervised physical exercise, is conducted for each individual, which causes changes in their BP, and then, a number of reference BPs are measured alongside the acquisition of the signals per subject. It is suggested to use a force-sensing resistor that is placed under the cuff of the BP reference device to mark the exact moments of reference BP measurements, which are corresponding to the inflation of the cuff. Additionally, a novel BP estimator nonlinear model, based on the theory of elastic tubes, is introduced to estimate the BP using PTT/PAT values precisely. The proposed method is evaluated on 32 subjects. Using the PTT index, the correlation coefficients for SBP and DBP estimation are 0.89 and 0.84, respectively. Using the PAT index, the correlation coefficients for SBP and DBP estimation are 0.95 and 0.84, respectively. The results show that the proposed method, exploiting the introduced nonlinear model with the use of PAT index or PTT index, provides a reliable estimation of SBP and DBP.

Steel Surface Defect Detection Using a New Haar–Weibull-Variance Model in Unsupervised Manner

Abstract: Automatic defect detection on the steel surface is a challenging task in computer vision, owing to miscellaneous patterns of the defects, low contrast between the defect and background, the existence of pseudo defects, and so on. In this paper, a new Haar-Weibull-variance (HWV) model is proposed for steel surface defect detection in an unsupervised manner. First, an anisotropic diffusion model is utilized to eliminate the influence of pseudodefects. Second, a new HWV model is established to characterize the texture distribution of each local patch in the image. The proposed model can project the texture distribution of each patch into the low-dimensional space with only two parameters. The parameter distribution of the whole image can also be unified into the form of linear radiation in an Euclidean space. The reliable background can be extracted via the formation of parameter distribution, by which the model parameter can be optimized further. Finally, the adaptive threshold can be determined to distinguish the defect from the background. Experimental results show that the proposed method can detect an arbitrary type of defect on the homogeneously textured surface and achieve an average detection rate of 96.2% on the data set, which outperforms the previous methods.

Medical Image Fusion and Denoising with Alternating Sequential Filter and Adaptive Fractional Order Total Variation

Abstract: Medical image fusion aims at integrating information from multimodality medical images to obtain a more complete and accurate description of the same object, which provides an easy access for image-guided medical diagnostic and treatment Unfortunately, medical images are often corrupted by noise in acquisition or transmission, and the noise signal is easily mistaken for a useful characterization of the image, making the fusion effect drop significantly Thus, the existence of noise presents a great challenge for most of traditional image fusion methods To address this problem, an effective variation model for multimodality medical image fusion and denoising is proposed First, a multiscale alternating sequential filter is exploited to extract the useful characterizations (eg, details and edges) from noisy input medical images Then, a recursive filtering-based weight map is constructed to guide the fusion of main features of input images Additionally, total variation (TV) constraint is developed by constructing an adaptive fractional order $p$ based on the local contrast of fused image, further effectively suppressing noise while avoiding the staircase effect of the TV The experimental results indicate that the proposed method performs well with both noisy and normal medical images, outperforming conventional methods in terms of fusion quality and noise reduction

Kalman-Filtering-Based In-Motion Coarse Alignment for Odometer-Aided SINS

Abstract: In this paper, the in-motion coarse alignment (IMCA) for odometer-aided strap-down inertial navigation system (SINS) is investigated with the main focus on compensating for the dynamic errors of gyroscope induced by severe maneuvering. A new Kalman-filtering-based IMCA method for an odometer-aided SINS is presented. A novel closed-loop approach to estimating the attitude matrix from the current body frame to the initial body frame is proposed, in which the attitude error between the closed-loop calculation and the true attitude matrix is first estimated, and then, the estimated attitude matrix is obtained by refining the closed-loop calculation with the estimated attitude error. A linear state-space model for the attitude error is derived, and then, a Kalman filter is employed to track the attitude error. Experimental results illustrate that the proposed closed-loop approach can estimate the attitude matrix from the current body frame to the initial body frame better than the existing open-loop approach, which results in improved alignment accuracy as compared with the existing optimization-based alignment method for the odometer-aided SINS when the vehicle maneuvers severely.

Millimeter Wave Reflectometry and Imaging for Noninvasive Diagnosis of Skin Burn Injuries

Abstract: Accurate assessment of the degree of burn in human skin is critically important for burn technicians and physicians when making treatment decisions. Millimeter wave reflectometry and imaging are potential diagnostic tools capable of distinguishing between healthy and burned skin, as the dielectric properties of the latter are significantly different from that of the former. In this paper, the commonly used layered model of human skin is used to simulate the reflection properties of skin with varying degrees of burn, at Ka-band (26.5–40 GHz), to demonstrate the potential for such diagnosis. Measurements of complex reflection coefficient are also conducted on a pigskin with and without medical dressing, which is a close mimic to human skin. Good agreement is obtained, in amplitude and variation trends in the reflection coefficient results, between simulation and measurement results, indicating the potential effectiveness and feasibility of burn degree diagnosis by localized millimeter wave reflectometry and complex reflection coefficient $L^{{\mathrm {2}}}$ -Norm analysis. Finally, synthetic aperture radar imaging technique is used to examine the efficacy of imaging for burn wound at V-band (50–75 GHz). In addition, the effectiveness of localized and imaging methods for evaluating burns covered by medical dressings is also demonstrated.

Short-Frequency Fourier Transform for Fault Diagnosis of Induction Machines Working in Transient Regime

Abstract: Transient-based methods for fault diagnosis of induction machines (IMs) are attracting a rising interest, due to their reliability and ability to adapt to a wide range of IM’s working conditions. These methods compute the time–frequency (TF) distribution of the stator current, where the patterns of the related fault components can be detected. A significant amount of recent proposals in this field have focused on improving the resolution of the TF distributions, allowing a better discrimination and identification of fault harmonic components. Nevertheless, as the resolution improves, computational requirements (power computing and memory) greatly increase, restricting its implementation in low-cost devices for performing on-line fault diagnosis. To address these drawbacks, in this paper, the use of the short-frequency Fourier transform (SFFT) for fault diagnosis of induction machines working under transient regimes is proposed. The SFFT not only keeps the resolution of traditional techniques, such as the short-time Fourier transform, but also achieves a drastic reduction of computing time and memory resources, making this proposal suitable for on-line fault diagnosis. This method is theoretically introduced and experimentally validated using a laboratory test bench.

Robotic Room-Level Localization Using Multiple Sets of Sonar Measurements

Abstract: In this paper, we aim to achieve robust and cost-effective room-level localization for the indoor mobile robot. It is unrealistic to obtain precise localization information from the sonar sensors because of the sparseness and uncertainty. Our attempts show that the room-level localization can be achieved using sonar sensors by accumulating the sonar data to overcome the limitations of sensor performance. To this end, we formulate the room-level localization as a joint sparse coding problem, which encourages the coding vectors to share the common room sparsity, but different locations. We systematically evaluate the performance of the different coding strategies on the collected sonar measurement data set.

A Distributed FMCW Radar System Based on Fiber-Optic Links for Small Drone Detection

Abstract: This paper discusses a distributed frequency modulation continuous wave radar system. This K-band radar system has high sensitivity, linearity, and flatness to detect low-radar cross section targets and measure their range and velocity. To reduce the leakage between a transmitter and a receiver, the system uses not RF cables but fiber-optic links that have low distortion characteristics and low propagation loss. The transmitter and the receiver are each mounted on a designed fixture to reduce the ground reflections. In addition, they are located on different platforms to reduce the leakage signal flowing directly from the transmitter to the receiver. Measurements in terms of the range and the velocity of a small drone have been carried out to evaluate the proposed distributed radar system. The results show that we can clearly detect the small drone within a 500 m range, which demonstrates the high sensitivity of the system and high isolation between the transmitter and the receiver.

Event-Based Energy Disaggregation Algorithm for Activity Monitoring From a Single-Point Sensor

Abstract: The massive deployment of smart meters and other customized meters has motivated the development of nonintrusive load monitoring (NILM) systems. This is the process of disaggregating the total energy consumption in a building into individual electrical loads using a single-point sensor. Most literature is oriented to energy saving. Nevertheless, activity of daily livings monitoring through NILM is recently receiving much interest. This proposal presents an event-based NILM algorithm of high performance for activity monitoring applications. This is divided into two stages: 1) an event detector and 2) an event classification algorithm. The first one does not need to be trained and shows a detection rate up to 94%. The event classification algorithm uses a novel load signature based on trajectories of active, reactive, and distortion power (PQD) to obtain general models of appliance classes using principal component analysis. The F1 score and the F0.5 score (the last one is more relevant to activity monitoring) draw values of 90.6% and 98.5, respectively.

A Cubature Kalman Filter Based Power System Dynamic State Estimator

Abstract: This paper proposes an application of the cubature Kalman filter (CKF) to the power system dynamic state estimation (PSDSE) utilizing the measurements from the remote terminal units as well as the phasor measurement units. The CKF process utilizes the spherical cubature and Gaussian quadrature rules to estimate the probability density functions of the state space and the measurement space. This helps in linearization of the nonlinear measurement function without loss of accuracy. The CKF does not require formation of the Jacobian and Hessian matrices to execute the PSDSE, which saves the execution time. A state forecasting technique is utilized to forecast the states during the interval between two time instants of receiving the measurement sets from the field. This helps in estimating the states of the power system during the period when the field measurements are not available. The effectiveness of the application of the CKF to the PSDSE has been demonstrated on IEEE 30 bus system and 246 bus Northern Regional Power Grid Indian system.

Multiple Visual Features Measurement With Gradient Domain Guided Filtering for Multisensor Image Fusion

Abstract: Multisensor image fusion technologies, which convey image information from different sensor modalities to a single image, have been a growing interest in recent research. In this paper, we propose a novel multisensor image fusion method based on multiple visual features measurement with gradient domain guided filtering. First, a Gaussian smoothing filter is employed to decompose each source image into two components: approximate component formed by homogeneous regions and detail component with sharp edges. Second, an effective decision map construction model is presented by measuring three key visual features of the input sensor image: contrast saliency, sharpness, and structure saliency. Third, a gradient domain guided filtering-based decision map optimization technique is proposed to make full use of spatial consistency and generate weight maps. Finally, the resultant image is fused with the weight maps and then is experimentally verified through multifocus image, multimodal medical image, and infrared-visible image fusion. The experimental results demonstrate that the proposed method can achieve better performance than state-of-the-art methods in terms of subjective visual effect and objective evaluation.

Odor Recognition in Multiple E-Nose Systems With Cross-Domain Discriminative Subspace Learning

Abstract: In this paper, we propose an odor recognition framework for multiple electronic noses (E-noses), machine olfaction odor perception systems. Straight to the point, the proposed transferring odor recognition model is called cross-domain discriminative subspace learning (CDSL). General odor recognition problems with E-nose are single domain oriented, that is, recognition algorithms are often modeled and tested on the same one domain data set (i.e., from only one E-nose system). Different from that, we focus on a more realistic scenario: the recognition model is trained on a prepared source domain data set from a master E-nose system ${A}$ , but tested on another target domain data set from a slave system ${B}$ or ${C}$ with the same type of the master system ${A}$ . The internal device parameter variance between master and slave systems often results in data distribution discrepancy between source domain and target domain, such that single-domain-based odor recognition model may not be adapted to another domain. Therefore, we propose domain-adaptation-based odor recognition for addressing the realistic recognition scenario across systems. Specifically, the proposed CDSL method consists of three merits: 1) an intraclass scatter minimization- and an interclass scatter maximization-based discriminative subspace learning is solved on source domain; 2) a data fidelity and preservation constraint of the subspace is imposed on target domain without distortion; and 3) a minipatch feature weighted domain distance is minimized for closely connecting the source and target domains. Experiments and comparisons on odor recognition tasks in multiple E-noses demonstrate the efficiency of the proposed method.

An Efficient and Accurate Solution for Distribution System State Estimation with Multiarea Architecture

Abstract: Distribution system state estimation (DSSE) is an essential tool for the management and control of future distribution networks. Distribution grids are usually characterized by a very large number of nodes and different voltage levels. Moreover, different portions of the system can be operated by different distribution system operators. In this context, multiarea approaches are key tools to efficiently perform DSSE. This paper presents a novel approach for multiarea state estimation in distribution systems. The proposed algorithm is based on a two-step procedure, where the first-step local estimations are refined through a newly designed second step that allows the integration of the measurement information available in the adjacent areas. The main novelty in this paper is the mathematical analysis of the impact brought by possible measurements shared among different areas, which drives the design of a new efficient weighted least squares formulation of the second step to maximize the achievable estimation accuracy. Tests performed on the unbalanced IEEE 123-bus network prove the goodness of the new multiarea estimator proposed and show the accuracy and efficiency enhancements obtainable with respect to previous literature.

A Driver State Detection System—Combining a Capacitive Hand Detection Sensor With Physiological Sensors

Abstract: With respect to automotive safety, the driver plays a crucial role. Stress level, tiredness, and distraction of the driver are therefore of high interest. In this paper, a driver state detection system based on cellular neural networks (CNNs) to monitor the driver’s stress level is presented. We propose to include a capacitive-based wireless hand detection (position and touch) sensor for a steering wheel utilizing ink-jet printed sensor mats as an input sensor in order to improve the performance. A driving simulator platform providing a realistic virtual traffic environment is utilized to conduct a study with 22 participants for the evaluation of the proposed system. Each participant is driving in two different scenarios, each representing one of the two no-stress/stress driver states. A “threefold” cross validation is applied to evaluate our concept. The subject dependence is considered carefully by separating the training and testing data. Furthermore, the CNN approach is benchmarked against other state-of-the-art machine learning techniques. The results show a significant improvement combining sensor inputs from different driver inherent domains, giving a total related detection accuracy of 92%. Besides that, this paper shows that in case of including the capacitive hand detection sensor, the accuracy increases by 10%. These findings indicate that adding a subject-independent sensor, such as the proposed capacitive hand detection sensor, can significantly improve the detection performance.

Radar Sensor Signal Acquisition and Multidimensional FFT Processing for Surveillance Applications in Transport Systems

Abstract: The design and test of a radio detection and ranging (Radar) sensor signal acquisition and processing platform is presented in this paper. The Radar sensor operates in real time and is suited for surveillance applications in transport systems. It includes a front-end with a continuous-wave frequency-modulated transceiver operating in X-band, with a single transmitter and multiple receivers, and a multichannel high-speed A/D converter. Sensor signal processing and data communication tasks with external hosts are managed by a field-programmable gate array. The signal processing chain includes region of interest selection, multidimensional fast Fourier transform, peak detection, alarm decision logic, data calibration, and diagnostic. By configuring the Radar sensing platform in low-power mode (7-dBm transmitted power), it is possible to detect still and moving targets with a covered range up to 300-m and 30-cm resolution. The measuring range can be increased up to 2 km by adding an extra 34.5-dBm power amplifier. The Radar sensing platform can be configured for a maximum detected speed of 200 km/h, with a resolution of 1.56 km/h, or a speed up to 50 km/h with a resolution of 0.4 km/h. The cross-range resolution depends on the number of receiving channels; a tradeoff can be found between cross-range resolution of the Radar sensor and its complexity and power consumption. With respect to the state of the art of surveillance Radar sensors and light detection and ranging, the proposed solution stands for its high configurability and for the better tradeoff that can be found in terms of covered distance and power consumption.