Sensors, Volume 20, Issue 4 (February-2 2020) – 289 articles

A low noise interface ASIC for micro gyroscope with ball-disc rotor is realized in 0.5µm CMOS technology. The interface circuit utilizes a transimpedance pre-amplifier which reduces input noise. The proposed interface achieves 0.003°/s/Hz^1/2 noise density and 0.003°/s sensitivity with ±100°/s measure range. The functionality of the full circuit, including circuit analysis, noise analysis and measurement results, has been demonstrated. Full article

Infrared maritime target detection is the key technology of maritime target search systems. However, infrared images generally have the defects of low signal-to-noise ratio and low resolution. At the same time, the maritime environment is complicated and changeable. Under the interference of islands, waves and other disturbances, the brightness of small dim targets is easily obscured, which makes them difficult to distinguish. This is difficult for traditional target detection algorithms to deal with. In order to solve these problems, through the analysis of infrared maritime images under a variety of sea conditions including small dim targets, this paper concludes that in infrared maritime images, small targets occupy very few pixels, often do not have any edge contour information, and the gray value and contrast values are very low. The background such as island and strong sea wave occupies a large number of pixels, with obvious texture features, and often has a high gray value. By deeply analyzing the difference between the target and the background, this paper proposes a detection algorithm (SRGM) for infrared small dim targets under different maritime background. Firstly, this algorithm proposes an efficient maritime background filter for the common background in the infrared maritime image. Firstly, the median filter based on the sensitive region selection is used to extract the image background accurately, and then the background is eliminated by image difference with the original image. In addition, this article analyzes the differences in gradient features between strong interference caused by the background and targets, proposes a small dim target extraction operator with two analysis factors that fit the target features perfectly and combines the adaptive threshold segmentation to realize the accurate extraction of the small dim target. The experimental results show that compared with the current popular small dim target detection algorithms, this paper has better performance for target detection in various maritime environments. Full article

Beam pattern measurement is essential to verifying the performance of an array sonar. However, common problems in beam pattern measurement of arrays include constraints on achieving the far-field condition and reaching plane waves mainly due to limited measurement space as in acoustic water tank. For this purpose, the conventional method of measuring beam patterns in limited spaces, which transform near-field measurement data into far-field results, is used. However, the conventional method is time-consuming because of the dense spatial sampling. Hence, we devised a method to measure the beam pattern of a discrete line array in limited space based on the subarray method. In this method, a discrete line array with a measurement space that does not satisfy the far-field condition is divided into several subarrays, and the beam pattern of the line array can then be determined from the subarray measurements by the spatial convolution that is equivalent to the multiplication of beam pattern. The proposed method was verified through simulation and experimental measurement on a line array with 256 elements of 16 subarrays. Full article

The diagnosis of psychogenic nonepileptic seizures (PNES) by means of electroencephalography (EEG) is not a trivial task during clinical practice for neurologists. No clear PNES electrophysiological biomarker has yet been found, and the only tool available for diagnosis is video EEG monitoring with recording of a typical episode and clinical history of the subject. In this paper, a data-driven machine learning (ML) pipeline for classifying EEG segments (i.e., epochs) of PNES and healthy controls (CNT) is introduced. This software pipeline consists of a semiautomatic signal processing technique and a supervised ML classifier to aid clinical discriminative diagnosis of PNES by means of an EEG time series. In our ML pipeline, statistical features like the mean, standard deviation, kurtosis, and skewness are extracted in a power spectral density (PSD) map split up in five conventional EEG rhythms (delta, theta, alpha, beta, and the whole band, i.e., 1–32 Hz). Then, the feature vector is fed into three different supervised ML algorithms, namely, the support vector machine (SVM), linear discriminant analysis (LDA), and Bayesian network (BN), to perform EEG segment classification tasks for CNT vs. PNES. The performance of the pipeline algorithm was evaluated on a dataset of 20 EEG signals (10 PNES and 10 CNT) that was recorded in eyes-closed resting condition at the Regional Epilepsy Centre, Great Metropolitan Hospital of Reggio Calabria, University of Catanzaro, Italy. The experimental results showed that PNES vs. CNT discrimination tasks performed via the ML algorithm and validated with random split (RS) achieved an average accuracy of 0.97 ± 0.013 (RS-SVM), 0.99 ± 0.02 (RS-LDA), and 0.82 ± 0.109 (RS-BN). Meanwhile, with leave-one-out (LOO) validation, an average accuracy of 0.98 ± 0.0233 (LOO-SVM), 0.98 ± 0.124 (LOO-LDA), and 0.81 ± 0.109 (LOO-BN) was achieved. Our findings showed that BN was outperformed by SVM and LDA. The promising results of the proposed software pipeline suggest that it may be a valuable tool to support existing clinical diagnosis. Full article

A target angular information in 3-dimensional space consists of an elevation angle and azimuth angle. Acoustic signals propagating along multiple paths in underwater environments usually have different elevation angles. Target motion analysis (TMA) uses the underwater acoustic signals received by a passive horizontal line array to track an underwater target. The target angle measured by the horizontal line array is, in fact, a conical angle that indicates the direction of the signal arriving at the line array sonar system. Accordingly, bottom bounce paths produce inaccurate target locations if they are interpreted as azimuth angles in the horizontal plane, as is commonly assumed in existing TMA technologies. Therefore, it is necessary to consider the effect of the conical angle on bearings-only TMA (BO-TMA). In this paper, a target conical angle causing angular ambiguity will be simulated using a ray tracing method in an underwater environment. A BO-TMA method using particle swarm optimization (PSO) is proposed for batch processing to solve the angular ambiguity problem. Full article

The gear fault signal under different working conditions is non-linear and non-stationary, which makes it difficult to distinguish faulty signals from normal signals. Currently, gear fault diagnosis under different working conditions is mainly based on vibration signals. However, vibration signal acquisition is limited by its requirement for contact measurement, while vibration signal analysis methods relies heavily on diagnostic expertise and prior knowledge of signal processing technology. To solve this problem, a novel acoustic-based diagnosis (ABD) method for gear fault diagnosis under different working conditions based on a multi-scale convolutional learning structure and attention mechanism is proposed in this paper. The multi-scale convolutional learning structure was designed to automatically mine multiple scale features using different filter banks from raw acoustic signals. Subsequently, the novel attention mechanism, which was based on a multi-scale convolutional learning structure, was established to adaptively allow the multi-scale network to focus on relevant fault pattern information under different working conditions. Finally, a stacked convolutional neural network (CNN) model was proposed to detect the fault mode of gears. The experimental results show that our method achieved much better performance in acoustic based gear fault diagnosis under different working conditions compared with a standard CNN model (without an attention mechanism), an end-to-end CNN model based on time and frequency domain signals, and other traditional fault diagnosis methods involving feature engineering. Full article

A readily synthesizable fluorescent probe DMAT-π-CAP was evaluated for sensitive and selective detection of human serum albumin (HSA). DMAT-π-CAP showed selective turn-on fluorescence at 730 nm in the presence of HSA with more than 720-fold enhancement in emission intensity ([DMAT-π-CAP] = 10 μM), and rapid detection of HSA was accomplished in 3 s. The fluorescence intensity of DMAT-π-CAP was shown to increase in HSA concentration-dependent manner (K_d = 15.4 ± 3.3 μM), and the limit of detection of DMAT-π-CAP was determined to be 10.9 nM (0.72 mg/L). The 1:1 stoichiometry between DMAT-π-CAP and HSA was determined, and the displacement assay revealed that DMAT-π-CAP competes with hemin for the unique binding site, which rarely accommodates drugs and endogenous compounds. Based on the HSA-selective turn-on NIR fluorescence property as well as the unique binding site, DMAT-π-CAP was anticipated to serve as a fluorescence sensor for quantitative detection of the HSA level in biological samples with minimized background interference. Thus, urine samples were directly analyzed by DMAT-π-CAP to assess albumin levels, and the results were comparable to those obtained from immunoassay. The similar sensitivity and specificity to the immunoassay along with the simple, cost-effective, and fast detection of HSA warrants practical application of the NIR fluorescent albumin sensor, DMAT-π-CAP, in the analysis of albumin levels in various biological environments. Full article

Crop yield is related to national food security and economic performance, and it is therefore important to estimate this parameter quickly and accurately. In this work, we estimate the yield of winter wheat using the spectral indices (SIs), ground-measured plant height (H), and the plant height extracted from UAV-based hyperspectral images (H_CSM) using three regression techniques, namely partial least squares regression (PLSR), an artificial neural network (ANN), and Random Forest (RF). The SIs, H, and H_CSM were used as input values, and then the PLSR, ANN, and RF were trained using regression techniques. The three different regression techniques were used for modeling and verification to test the stability of the yield estimation. The results showed that: (1) H_CSM is strongly correlated with H (R² = 0.97); (2) of the regression techniques, the best yield prediction was obtained using PLSR, followed closely by ANN, while RF had the worst prediction performance; and (3) the best prediction results were obtained using PLSR and training using a combination of the SIs and H_CSM as inputs (R² = 0.77, RMSE = 648.90 kg/ha, NRMSE = 10.63%). Therefore, it can be concluded that PLSR allows the accurate estimation of crop yield from hyperspectral remote sensing data, and the combination of the SIs and H_CSM allows the most accurate yield estimation. The results of this study indicate that the crop plant height extracted from UAV-based hyperspectral measurements can improve yield estimation, and that the comparative analysis of PLSR, ANN, and RF regression techniques can provide a reference for agricultural management. Full article

The 24 GHz continuous-wave (CW) Doppler radar sensor (DRS) is widely used for measuring the instantaneous speed of moving objects by using a non-contact approach, and has begun to be used in train-borne movable speed measurements in recent years in China because of its advanced performance. The architecture and working principle of train-borne DRSs with different structures including single-channel DRSs used for freight train speed measurements in railway freight dedicated lines and dual-channel DRSs used for speed measurements of high-speed and urban rail trains in railway passenger dedicated lines, are first introduced. Then, the disadvantages of two traditional speed calibration methods for train-borne DRS are described, and a new speed calibration method based on the Doppler shift signal simulation by imposing a signal modulation on the incident CW microwave signal is proposed. A 24 GHz CW radar target simulation system for a train-borne DRS was specifically realized to verify the proposed speed calibration method for a train-borne DRS, and traceability and performance evaluation on simulated speed were taken into account. The simulated speed range of the simulation system was up to (5~500) km/h when the simulated incident angle range was within the range of (45 ± 8)°, and the maximum permissible error (MPE) of the simulated speed was ±0.05 km/h. Finally, the calibration and uncertainty evaluation results of two typical train-borne dual-channel DRS samples validated the effectiveness and feasibility of the proposed speed calibration approach for a train-borne DRS with full range in the laboratory as well as in the field. Full article

Monitoring breathing is important for a plethora of applications including, but not limited to, baby monitoring, sleep monitoring, and elderly care. This paper presents a way to fuse both vision-based and RF-based modalities for the task of estimating the breathing rate of a human. The modalities used are the F200 Intel^® RealSense^TM RGB and depth (RGBD) sensor, and an ultra-wideband (UWB) radar. RGB image-based features and their corresponding image coordinates are detected on the human body and are tracked using the famous optical flow algorithm of Lucas and Kanade. The depth at these coordinates is also tracked. The synced-radar received signal is processed to extract the breathing pattern. All of these signals are then passed to a harmonic signal detector which is based on a generalized likelihood ratio test. Finally, a spectral estimation algorithm based on the reformed Pisarenko algorithm tracks the breathing fundamental frequencies in real-time, which are then fused into a one optimal breathing rate in a maximum likelihood fashion. We tested this multimodal set-up on 14 human subjects and we report a maximum error of $0.5$ BPM compared to the true breathing rate. Full article

This study carries out a detailed full-scale investigation on the strong wind characteristics at a cable-stayed bridge site and associated buffeting response of the bridge structure during construction, using a field monitoring system. It is found that the wind turbulence parameters during the typhoon and monsoon conditions share a considerable amount of similarity, and they can be described as the input turbulence parameters for the current wind-induced vibration theory. While the longitudinal turbulence integral scales are consistent with those in regional structural codes, the turbulence intensities and gust factors are less than the recommended values. The wind spectra obtained via the field measurements can be well approximated by the von Karman spectra. For the buffeting response of the bridge under strong winds, its vertical acceleration responses at the extreme single-cantilever state are significantly larger than those in the horizontal direction and the increasing tendencies with mean wind velocities are also different from each other. The identified frequencies of the bridge are utilized to validate its finite element model (FEM), and these field-measurement acceleration results are compared with those from the FEM-based numerical buffeting analysis with measured turbulence parameters. Full article

In this paper, the seismic assessments of two footbridges, i.e., a single-span steel frame footbridge and a three-span cable-stayed structure, to the spatial variation of earthquake ground motion (SVEGM) are presented. A model of nonuniform kinematic excitation was used for the dynamic analyses of the footbridges. The influence of SVEGM on the dynamic performance of structures was assessed on both experimental and numerical ways. The comprehensive tests were planned and carried out on both structures. The investigation was divided into two parts: in situ experiment and numerical analyses. The first experimental part served for the validation of both the finite element (FE) modal models of structures and the theoretical model of nonuniform excitation as well as the appropriateness of the FE procedures used for dynamic analyses. First, the modal properties were validated. The differences between the numerical and the experimental natural frequencies, obtained using the operational modal analysis, were less than 10%. The comparison of the experimental and numerical mode shapes also proved a good agreement since the modal assurance criterion values were satisfactory for both structures. Secondly, nonuniform kinematic excitation was experimentally imposed using vibroseis tests. The apparent wave velocities, evaluated from the cross-correlation functions of the acceleration-time histories registered at two consecutive structures supports, equaled 203 and 214 m/s for both structures, respectively. Also, the coherence functions proved the similarity of the signals, especially for the frequency range 5 to 15 Hz. Then, artificial kinematic excitation was generated on the basis of the adopted model of nonuniform excitation. The obtained power spectral density functions of acceleration-time histories registered at all supports as well as the cross-spectral density functions between registered and artificial acceleration-time histories confirmed the strong similarity of the measured and artificial signals. Finally, the experimental and numerical assessments of the footbridges performance under the known dynamic excitation generated by the vibroseis were carried out. The FE models and procedures were positively validated by linking full-scale tests and numerical calculations. In the numerical part of the research, seismic analyses of the footbridges were conducted. The dynamic responses of structures to a representative seismic shock were calculated. Both the uniform and nonuniform models of excitation were applied to demonstrate and quantify the influence of SVEGM on the seismic assessment of footbridges. It occurred that SVEGM may generate non-conservative results in comparison with classic uniform seismic excitation. For the stiff steel frame footbridge the maximum dynamic response was obtained for the model of nonuniform excitation with the lowest wave velocity. Especially zones located closely to stiff frame nodes were significantly more disturbed. For the flexible cable-stayed footbridge, in case of nonuniform excitation, the dynamic response was enhanced only at the points located in the extreme spans and in the midspan closely to the pillars. Full article

Remote sensing image scene classification has a high application value in the agricultural, military, as well as other fields. A large amount of remote sensing data is obtained every day. After learning the new batch data, scene classification algorithms based on deep learning face the problem of catastrophic forgetting, that is, they cannot maintain the performance of the old batch data. Therefore, it has become more and more important to ensure that the scene classification model has the ability of continual learning, that is, to learn new batch data without forgetting the performance of the old batch data. However, the existing remote sensing image scene classification datasets all use static benchmarks and lack the standard to divide the datasets into a number of sequential learning training batches, which largely limits the development of continual learning in remote sensing image scene classification. First, this study gives the criteria for training batches that have been partitioned into three continual learning scenarios, and proposes a large-scale remote sensing image scene classification database called the Continual Learning Benchmark for Remote Sensing (CLRS). The goal of CLRS is to help develop state-of-the-art continual learning algorithms in the field of remote sensing image scene classification. In addition, in this paper, a new method of constructing a large-scale remote sensing image classification database based on the target detection pretrained model is proposed, which can effectively reduce manual annotations. Finally, several mainstream continual learning methods are tested and analyzed under three continual learning scenarios, and the results can be used as a baseline for future work. Full article

Passive microwave sensors use a radiative transfer model (RTM) to retrieve soil moisture (SM) using brightness temperatures (T_B) at low microwave frequencies. Vegetation optical depth (VOD) is a key input to the RTM. Retrieval algorithms can analytically invert the RTM using dual-polarized T_B measurements to retrieve the VOD and SM concurrently. Algorithms in this regard typically use the τ-ω types of models, which consist of two third-order polynomial equations and, thus, can have multiple solutions. Through this work, we find that uncertainty occurs due to the structural indeterminacy that is inherent in all τ-ω types of models in passive microwave SM retrieval algorithms. In the process, a new analytical solution for concurrent VOD and SM retrieval is presented, along with two widely used existing analytical solutions. All three solutions are applied to a fixed framework of RTM to retrieve VOD and SM on a global scale, using X-band Advanced Microwave Scanning Radiometer-Earth Observing System (AMSR-E) T_B data. Results indicate that, with structural uncertainty, there ensues a noticeable impact on the VOD and SM retrievals. In an era where the sensitivity of retrieval algorithms is still being researched, we believe the structural indeterminacy of RTM identified here would contribute to uncertainty in the soil moisture retrievals. Full article

The tracking accuracy of a traditional Frequency Lock Loop (FLL) decreases significantly in a complex environment, thus reducing the overall performance of a satellite receiver. In order to ensure high tracking accuracy of a receiver in a complex environment, this paper proposes a new tracking loop combining the vector FLL (VFLL) with a robust least squares method, which accurately matches the weights of received signals of different qualities to ensure high positioning accuracy. The weights of received signals are selected at the signal level, not at the observation level. In this paper, the ranges of strong and weak signals of the loop are determined according to the different expressions of the distribution function at different signal strengths, and the concept of loop segmentation is introduced. The segmentation results of the FLL are taken as a basis of the weight selection, and then combined with the Institute of Geodesy and Geophysics (IGGIII) weight function to obtain the equivalent weight matrix; the experiments are conducted to prove the advantages of the proposed method over the traditional methods. The experimental results show that the proposed VFLL tracking method has strong denoising capability under both normal- signal and harsh application environment conditions. Accordingly, the proposed model has a promising application perspective. Full article

In this paper, a comparative study of the effectiveness of deep neural networks (DNNs) in the classification of pure and impure purees is conducted. Three different types of deep neural networks (DNNs)—the Gated Recurrent Unit (GRU), the Long Short Term Memory (LSTM), and the temporal convolutional network (TCN)—are employed for the detection of adulteration of strawberry purees. The Strawberry dataset, a time series spectroscopy dataset from the UCR time series classification repository, is utilized to evaluate the performance of different DNNs. Experimental results demonstrate that the TCN is able to obtain a higher classification accuracy than the GRU and LSTM. Moreover, the TCN achieves a new state-of-the-art classification accuracy on the Strawberry dataset. These results indicates the great potential of using the TCN for the detection of adulteration of fruit purees in the future. Full article

In this paper, we investigated a buffer-aided decode-and-forward (DF) wireless relaying system over fading channels, where the source and relay harvest radio-frequency (RF) energy from a power station for data transmissions. We derived exact expressions for end-to-end throughput considering half-duplex (HD) and full-duplex (FD) relaying schemes. The numerical results illustrate the throughput and energy efficiencies of the relaying schemes under different self-interference (SI) cancellation levels and relay deployment locations. It was demonstrated that throughput-optimal relaying is not necessarily energy efficiency-optimal. The results provide guidance on optimal relaying network deployment and operation under different performance criteria. Full article

Automated wireless sensing of force dynamics during a visuomotor control task was used to rapidly assess residual motor function during finger pinch (right and left hand) and lower lip compression in a cohort of seven adult males with chronic, unilateral middle cerebral artery (MCA) stroke with infarct confirmed by anatomic magnetic resonance imaging (MRI). A matched cohort of 25 neurotypical adult males served as controls. Dependent variables were extracted from digitized records of ‘ramp-and-hold’ isometric contractions to target levels (0.25, 0.5, 1, and 2 Newtons) presented in a randomized block design; and included force reaction time, peak force, and dF/dt_max associated with force recruitment, and end-point accuracy and variability metrics during the contraction hold-phase (mean, SD, criterion percentage ‘on-target’). Maximum voluntary contraction force (MVCF) was also assessed to establish the force operating range. Results based on linear mixed modeling (LMM, adjusted for age and handedness) revealed significant patterns of dissolution in fine force regulation among MCA stroke participants, especially for the contralesional thumb-index finger followed by the ipsilesional digits, and the lower lip. For example, the contralesional thumb-index finger manifest increased reaction time, and greater overshoot in peak force during recruitment compared to controls. Impaired force regulation among MCA stroke participants during the contraction hold-phase was associated with significant increases in force SD, and dramatic reduction in the ability to regulate force output within prescribed target force window (±5% of target). Impaired force regulation during contraction hold-phase was greatest in the contralesional hand muscle group, followed by significant dissolution in ipsilateral digits, with smaller effects found for lower lip. These changes in fine force dynamics were accompanied by large reductions in the MVCF with the LMM marginal means for contralesional and ipsilesional pinch forces at just 34.77% (15.93 N vs. 45.82 N) and 66.45% (27.23 N vs. 40.98 N) of control performance, respectively. Biomechanical measures of fine force and MVCF performance in adult stroke survivors provide valuable information on the profile of residual motor function which can help inform clinical treatment strategies and quantitatively monitor the efficacy of rehabilitation or neuroprotection strategies. Full article

We propose a free-resolution probability distributions map (FRPDM) and an FRPDM-based precise vehicle localization method using 3D light detection and ranging (LIDAR). An FRPDM is generated by Gaussian mixture modeling, based on road markings and vertical structure point cloud. Unlike single resolution or multi-resolution probability distribution maps, in the case of the FRPDM, the resolution is not fixed and the object can be represented by various sizes of probability distributions. Thus, the shape of the object can be represented efficiently. Therefore, the map size is very small (61 KB/km) because the object is effectively represented by a small number of probability distributions. Based on the generated FRPDM, point-to-probability distribution scan matching and feature-point matching were performed to obtain the measurements, and the position and heading of the vehicle were derived using an extended Kalman filter-based navigation filter. The experimental area is the Gangnam area of Seoul, South Korea, which has many buildings around the road. The root mean square (RMS) position errors for the lateral and longitudinal directions were 0.057 m and 0.178 m, respectively, and the RMS heading error was 0.281°. Full article

In this work, polyurethane sponge is employed as the structural substrate of the sensor. Graphene oxide (GO) and polypyrrole (PPy) are alternately coated on the sponge fiber skeleton by charge layer-by-layer assembly (LBL) to form a multilayer composite conductive layer to prepare the piezoresistive sensors. The 2D GO sheet is helpful for the formation of the GO layers, and separating the PPy layer. The prepared GO/PPy@PU (polyurethane) conductive sponges still had high compressibility. The unique fragmental microstructure and synergistic effect made the sensor reach a high sensitivity of 0.79 kPa⁻¹. The sensor could detect as low as 75 Pa, exhibited response time less than 70 ms and reproducibility over 10,000 cycles, and could be used for different types of motion detection. This work opens up new opportunities for high-performance piezoresistive sensors and other electronic devices for GO/PPy composites. Full article

An acousto-optic (AO) holographic display unit based on a suspended waveguide membrane was developed. The AO unit consists of a wide bandwidth chirp interdigital transducer (IDT) on a 20 µm thick suspended crystalline 128° YX LiNbO₃ membrane, a light blocker with a 20 µm hole near the entrance, and an active lens near the exit. The 20 µm thickness of the floating membrane significantly enhanced surface acoustic wave (SAW) confinement. The light blocker was installed in front of the AO unit to enhance the coupling efficiency of the incident light to the waveguide membrane and to remove perturbations to the photodetector during measurement at the exit region. The active lens was vertically attached to the waveguide sidewall to collect the diffracted beam without loss and to modulate the focal length in free space through the applied voltage. As SAWs were radiated from the IDT, a Bragg grating with periodic refractive indexes was formed along the waveguide membrane. The grating diffracted incident light. The deflection angle and phase, and the intensity of the light beam were controlled by the SAW frequency and input power, respectively. The maximum diffraction efficiency achieved was approximately 90% for a 400 MHz SAW. COMSOL simulation and coupling of mode modeling were performed to optimize design parameters and predict device performance. Full article

Accurate, rapid and non-destructive disease identification in the early stage of infection is essential to ensure the safe and efficient production of greenhouse cucumbers. Nevertheless, the effectiveness of most existing methods relies on the disease already exhibiting obvious symptoms in the middle to late stages of infection. Therefore, this paper presents an early identification method for cucumber diseases based on the techniques of hyperspectral imaging and machine learning, which consists of two procedures. First, reconstruction fidelity terms and graph constraints are constructed based on the decision criterion of the collaborative representation classifier and the desired spatial distribution of spectral curves (391 to 1044 nm) respectively. The former constrains the same-class and different-class reconstruction residuals while the latter constrains the weighted distances between spectral curves. They are further fused to steer the design of an offline algorithm. The algorithm aims to train a linear discriminative projection to transform the original spectral curves into a low dimensional space, where the projected spectral curves of different diseases own better separation trends. Then, the collaborative representation classifier is utilized to achieve online early diagnosis. Five experiments were performed on the hyperspectral data collected in the early infection stage of cucumber anthracnose and Corynespora cassiicola diseases. Experimental results demonstrated that the proposed method was feasible and effective, providing a maximal identification accuracy of 98.2% and an average online identification time of 0.65 ms. The proposed method has a promising future in practical production due to its high diagnostic accuracy and short diagnosis time. Full article

This research mainly aims at the construction of the novel acceleration pedal, the brake pedal and the steering system by mechanical designs and mechatronics technologies, an approach of which is rarely seen in Taiwan. Three highlights can be addressed: 1. The original steering parts were removed with the fault tolerance design being implemented so that the basic steering function can still remain in case of the function failure of the control system. 2. A larger steering angle of the front wheels in response to a specific rotated angle of the steering wheel is devised when cornering or parking at low speed in interest of drivability, while a smaller one is designed at high speed in favor of driving stability. 3. The operating patterns of the throttle, brake, and steering wheel can be customized in accordance with various driving environments and drivers’ requirements using the self-developed software. The implementation of a steer-by-wire system in the remote driving control for a go kart is described in this study. The mechatronic system is designed in order to support the conversion from human driving to autonomous driving for the go kart in the future. The go kart, using machine vision, is wirelessly controlled in the WiFi frequency bands. The steer-by-wire system was initially modeled as a standalone system for one wheel and subsequently developed into its complete form, including front wheel steering components, acceleration components, brake components, a microcontroller, drive circuit and digital to analog converter. The control output section delivers the commands to the subsystem controllers, relays and converters. The remote driving control of the go kart is activated when proper commands are sent by the vehicle control unit (VCU). All simulation and experiment results demonstrated that the control strategies of duel motors and the VCU control were successfully optimized. The feasibility study and performance evaluation of Taiwan’s go karts will be conducted as an extension of this study in the near future. Full article

In recent years, the Internet of Things (IoT) has exploded in popularity. The smart home, as an important facet of IoT, has gained its focus for smart intelligent systems. As users communicate with smart devices over an insecure communication medium, the sensitive information exchanged among them becomes vulnerable to an adversary. Thus, there is a great thrust in developing an anonymous authentication scheme to provide secure communication for smart home environments. Most recently, an anonymous authentication scheme for smart home environments with provable security has been proposed in the literature. In this paper, we analyze the recent scheme to highlight its several vulnerabilities. We then address the security drawbacks and present a more secure and robust authentication scheme that overcomes the drawbacks found in the analyzed scheme, while incorporating its advantages too. Finally, through a detailed comparative study, we demonstrate that the proposed scheme provides significantly better security and more functionality features with comparable communication and computational overheads with similar schemes. Full article

The aim of this paper was the detection of pathologies through respiratory sounds. The ICBHI (International Conference on Biomedical and Health Informatics) Benchmark was used. This dataset is composed of 920 sounds of which 810 are of chronic diseases, 75 of non-chronic diseases and only 35 of healthy individuals. As more than 88% of the samples of the dataset are from the same class (Chronic), the use of a Variational Convolutional Autoencoder was proposed to generate new labeled data and other well known oversampling techniques after determining that the dataset classes are unbalanced. Once the preprocessing step was carried out, a Convolutional Neural Network (CNN) was used to classify the respiratory sounds into healthy, chronic, and non-chronic disease. In addition, we carried out a more challenging classification trying to distinguish between the different types of pathologies or healthy: URTI, COPD, Bronchiectasis, Pneumonia, and Bronchiolitis. We achieved results up to 0.993 F-Score in the three-label classification and 0.990 F-Score in the more challenging six-class classification. Full article

With the continuous development of science and engineering technology, our society has entered the era of the mobile Internet of Things (MIoT). MIoT refers to the combination of advanced manufacturing technologies with the Internet of Things (IoT) to create a flexible digital manufacturing ecosystem. The wireless communication technology in the Internet of Things is a bridge between mobile devices. Therefore, the introduction of machine learning (ML) algorithms into MIoT wireless communication has become a research direction of concern. However, the traditional key-based wireless communication method demonstrates security problems and cannot meet the security requirements of the MIoT. Based on the research on the communication of the physical layer and the support vector data description (SVDD) algorithm, this paper establishes a radio frequency fingerprint (RFF or RF fingerprint) authentication model for a communication device. The communication device in the MIoT is accurately and efficiently identified by extracting the radio frequency fingerprint of the communication signal. In the simulation experiment, this paper introduces the neighborhood component analysis (NCA) method and the SVDD method to establish a communication device authentication model. At a signal-to-noise ratio (SNR) of 15 dB, the authentic devices authentication success rate (ASR) and the rogue devices detection success rate (RSR) are both 90%. Full article

To understand the characteristics of longitudinal grouting quality, this paper developed a stress wave-based active sensing method using piezoceramic transducers to detect longitudinal grouting quality of the prestressed curved tendon ducts. There were four lead zirconate titanate (PZT) transducers installed in the same longitudinal plane. One of them, mounted on the bottom of the curved tendon duct, was called as an actuator for generating stress waves. The other three, pasted on the top of the curved tendon duct, were called as sensors for detecting the wave responses. The experimental process was divided into five states during the grouting, which included 0%, 50%, 75%, 90%, and 100% grouting. The voltage signals, power spectral density (PSD) energy and wavelet packet energy were adopted in this research. Experimental results showed that all the amplitudes of the above analysis indicators were small before the grouting reached 90%. Only when the grouting degree reached the 100% grouting, these parameters increased significantly. The results of different longitudinal PZT sensors were mainly determined by the distance from the generator, the position of grouting holes, and the fluidity of grouting materials. These results showed the longitudinal grouting quality can be effectively evaluated by analyzing the difference between the signals received by the PZT transducers in the curved tendon duct. The devised method has certain application value in detecting the longitudinal grouting quality of prestressed curved tendon duct. Full article

With the wide deployment of commercial WiFi devices, the fine-grained channel state information (CSI) has received widespread attention with broad application domain including indoor localization and intrusion detection. From the perspective of practicality, dynamic intrusion may be confused under non-line-of-sight (NLOS) conditions and the continuous operation of passive positioning system will bring much unnecessary computation. In this paper, we propose an enhanced CSI-based indoor positioning system with pre-intrusion detection suitable for NLOS scenarios (C-InP). It mainly consists of two modules: intrusion detection and positioning estimation. The introduction of detection module is a prerequisite for positioning module. In order to improve the discrimination of features under NLOS conditions, we propose a modified calibration method for phase transformation while the amplitude outliers are filtered by the variance distribution with the median sequence. In addition, binary and improved multiple support vector classification (SVC) models are established to realize NLOS intrusion detection and high-discrimination fingerprint localization, respectively. Comprehensive experimental verification is carried out in typical indoor scenarios. Experimental results show that C-InP outperforms the existing system in NLOS environments, where the mean distance error (MDE) reached 0.49 m in the integrated room and 0.81 m in the complex garage, respectively. Full article

Wireless networks have been widely deployed with a high demand for wireless data traffic. The ubiquitous availability of wireless signals brings new opportunities for non-intrusive human activity sensing. To enhance a thorough understanding of existing wireless sensing techniques and provide insights for future directions, this survey conducts a review of the existing research on human activity sensing with wireless signals. We review and compare existing research of wireless human activity sensing from seven perspectives, including the types of wireless signals, theoretical models, signal preprocessing techniques, activity segmentation, feature extraction, classification, and application. With the development and deployment of new wireless technology, there will be more sensing opportunities in human activities. Based on the analysis of existing research, the survey points out seven challenges on wireless human activity sensing research: robustness, non-coexistence of sensing and communications, privacy, multiple user activity sensing, limited sensing range, complex deep learning, and lack of standard datasets. Finally, this survey presents four possible future research trends, including new theoretical models, the coexistence of sensing and communications, awareness of sensing on receivers, and constructing open datasets to enable new wireless sensing opportunities on human activities. Full article

Spectral imaging is a promising technique for detecting the quality of rice seeds. However, the high cost of the system has limited it to more practical applications. The study was aimed to develop a low-cost narrow band multispectral imaging system for detecting rice false smut (RFS) in rice seeds. Two different cultivars of rice seeds were artificially inoculated with RFS. Results have demonstrated that spectral features at 460, 520, 660, 740, 850, and 940 nm were well linked to the RFS. It achieved an overall accuracy of 98.7% with a false negative rate of 3.2% for Zheliang, and 91.4% with 6.7% for Xiushui, respectively, using the least squares-support vector machine. Moreover, the robustness of the model was validated through transferring the model of Zheliang to Xiushui with the overall accuracy of 90.3% and false negative rate of 7.8%. These results demonstrate the feasibility of the developed system for RFS identification with a low detecting cost. Full article