Search

Online handwritten signature verification is a crucial direction of research in the field of biometric recognition. Recently, many studies concerning online signature verification have attempted to improve performance using multi-feature fusion. However, few studies have provided the rationale for selecting a certain uni-feature to be fused, and few studies have investigated the contributions of a certain uni-feature in the multi-feature fusion process. This lack of research makes it challenging for future researchers in related fields to gain inspiration. Therefore, we use the uni-feature as the research object. In this paper, the uni-feature is one of the X and Y coordinates of the signature trajectory point, pen pressure, pen tilt, and pen azimuth feature. Aiming to solve the unequal length of feature vectors and the low accuracy of signature verification when using uni-features, we innovatively introduced the idea of correlation analysis and proposed a dynamic signature verification method based on the correlation coefficient of uni-features. Firstly, an alignment method of two feature vector lengths was proposed. Secondly, the correlation coefficient calculation formula was determined by analyzing the distribution type of the feature data, and then the correlation coefficient of the same uni-feature between the genuine signatures or between the genuine and forged signatures was calculated. Finally, the signature was verified by introducing a Gaussian density function model and combining it with the signature verification discrimination threshold. Experimental results showed that the proposed method could improve the performance of dynamic signature verification based on uni-features. In addition, the pen pressure feature had the best signature verification performance, with the highest signature verification accuracy of 93.46% on the SVC 2004 dataset.

It is generally accepted that relatively more permanent (i.e., more temporally persistent) traits are more valuable for biometric performance than less permanent traits. Although this finding is intuitive, there is no current work identifying exactly where in the biometric analysis temporal persistence makes a difference. In this paper, we answer this question. In a recent report, we introduced the intraclass correlation coefficient (ICC) as an index of temporal persistence for such features. Here, we present a novel approach using synthetic features to study which aspects of a biometric identification study are influenced by the temporal persistence of features. What we show is that using more temporally persistent features produces effects on the similarity score distributions that explain why this quality is so key to biometric performance. The results identified with the synthetic data are largely reinforced by an analysis of two datasets, one based on eye-movements and one based on gait. There was one difference between the synthetic and real data, related to the intercorrelation of features in real data. Removing these intercorrelations for real datasets with a decorrelation step produced results which were very similar to that obtained with synthetic features.

In the background of all human thinking—acting and reacting are sets of connections between different neurons or groups of neurons. We studied and evaluated these connections using electroencephalography (EEG) brain signals. In this paper, we propose the use of the complex Pearson correlation coefficient (CPCC), which provides information on connectivity with and without consideration of the volume conduction effect. Although the Pearson correlation coefficient is a widely accepted measure of the statistical relationships between random variables and the relationships between signals, it is not being used for EEG data analysis. Its meaning for EEG is not straightforward and rarely well understood. In this work, we compare it to the most commonly used undirected connectivity analysis methods, which are phase locking value (PLV) and weighted phase lag index (wPLI). First, the relationship between the measures is shown analytically. Then, it is illustrated by a practical comparison using synthetic and real EEG data. The relationships between the observed connectivity measures are described in terms of the correlation values between them, which are, for the absolute values of CPCC and PLV, not lower that 0.97, and for the imaginary component of CPCC and wPLI—not lower than 0.92, for all observed frequency bands. Results show that the CPCC includes information of both other measures balanced in a single complex-numbered index.

Vibration sensors are mostly used for fault diagnoses of machines or structures. If more sensors are applied, more accurate fault diagnosis is possible. However, it will obviously cost more. There are many approaches to optimize the number and installation location/point of vibration sensors for more efficient fault diagnosis. Existing methods require a great deal of computational throughput for optimization when considering many mode frequencies with points where vibration sensors are likely to be installed. This paper proposes a practical way of optimizing the sensor installation point considering many mode frequencies with lots of places for sensor installation. FEA was conducted to identify displacement values of each frequency in the candidate points. Then, correlation coefficients were applied to the FEA result to optimize the installation location and number of vibration sensors. Taking into account cases where the number of sensors has been set by users, FIM was applied. The correlation coefficient optimized the candidate points where 24,252 vibration sensors were to be installed and reduced this to 10 points. FIM, which was not suitable for directly optimizing sensor locations because it required a lot of computational throughput and was usually applied to evaluate other methods, is now applicable to candidate points that have been reduced by the correlation coefficient. This paper does not draw the best optimal sensor location but presents a way to apply to large-scale or complicated forms with a little computational throughput.

As the sound signal of ships obtained by sensors contains other many significant characteristics of ships and called ship-radiated noise (SN), research into a denoising algorithm and its application has obtained great significance. Using the advantage of variational mode decomposition (VMD) combined with the correlation coefficient for denoising, a hybrid secondary denoising algorithm is proposed using secondary VMD combined with a correlation coefficient (CC). First, different kinds of simulation signals are decomposed into several bandwidth-limited intrinsic mode functions (IMFs) using VMD, where the decomposition number by VMD is equal to the number by empirical mode decomposition (EMD); then, the CCs between the IMFs and the simulation signal are calculated respectively. The noise IMFs are identified by the CC threshold and the rest of the IMFs are reconstructed in order to realize the first denoising process. Finally, secondary denoising of the simulation signal can be accomplished by repeating the above steps of decomposition, screening and reconstruction. The final denoising result is determined according to the CC threshold. The denoising effect is compared under the different signal-to-noise ratio and the time of decomposition by VMD. Experimental results show the validity of the proposed denoising algorithm using secondary VMD (2VMD) combined with CC compared to EMD denoising, ensemble EMD (EEMD) denoising, VMD denoising and cubic VMD (3VMD) denoising, as well as two denoising algorithms presented recently. The proposed denoising algorithm is applied to feature extraction and classification for SN signals, which can effectively improve the recognition rate of different kinds of ships.

In order to meet the higher accuracy and system reliability requirements, the information fusion for multi-sensor systems is an increasing concern. Dempster–Shafer evidence theory (D–S theory) has been investigated for many applications in multi-sensor information fusion due to its flexibility in uncertainty modeling. However, classical evidence theory assumes that the evidence is independent of each other, which is often unrealistic. Ignoring the relationship between the evidence may lead to unreasonable fusion results, and even lead to wrong decisions. This assumption severely prevents D–S evidence theory from practical application and further development. In this paper, an innovative evidence fusion model to deal with dependent evidence based on rank correlation coefficient is proposed. The model first uses rank correlation coefficient to measure the dependence degree between different evidence. Then, total discount coefficient is obtained based on the dependence degree, which also considers the impact of the reliability of evidence. Finally, the discount evidence fusion model is presented. An example is illustrated to show the use and effectiveness of the proposed method.

It is generally accepted that relatively more permanent (i.e., more temporally persistent) traits are more valuable for biometric performance than less permanent traits. Although this finding is intuitive, there is no current work identifying exactly where in the biometric analysis temporal persistence makes a difference. In this paper, we answer this question. In a recent report, we introduced the intraclass correlation coefficient (ICC) as an index of temporal persistence for such features. Here, we present a novel approach using synthetic features to study which aspects of a biometric identification study are influenced by the temporal persistence of features. What we show is that using more temporally persistent features produces effects on the similarity score distributions that explain why this quality is so key to biometric performance. The results identified with the synthetic data are largely reinforced by an analysis of two datasets, one based on eye-movements and one based on gait. There was one difference between the synthetic and real data, related to the intercorrelation of features in real data. Removing these intercorrelations for real datasets with a decorrelation step produced results which were very similar to that obtained with synthetic features.

Underwater acoustic technology is an important means of detecting the ocean. Due to the complex influence of the marine environment, there is a lot of noise and baseline drift in the signals collected by hydrophones. In order to solve this problem, this paper proposes a denoising and baseline drift removal algorithm for MEMS vector hydrophone based on whale-optimized variational mode decomposition (VMD) and correlation coefficient (CC). Firstly, the power spectrum entropy (PSE), which reflects the variation characteristics of the signal frequency is selected as the fitness function of the whale-optimization algorithm to find the parameters (K,α) of the VMD. It is easier to find the global optimal solution of the parameters by combining the whale-optimization algorithm. Then, using the VMD algorithm after obtaining the parameters, the original signal is decomposed to obtain the intrinsic mode functions (IMFs), and calculating the correlation coefficients (CCs) between the IMFs and the original signal. Finally, the CC threshold is used to remove the noise IMFs, and the rest of the useful IMFs are reconstructed to complete the denoising and baseline drift removal process of the original signals. In the simulation experiments, the algorithm proposed in this paper shows better performance by comparing conventional digital signal-processing methods and the related algorithms proposed recently. Applied in the experiments of a MEMS hydrophone, the effectiveness of the proposed algorithm is also verified. This algorithm can provide new ideas for signal denoising and baseline drift removal.

When analyzing GPS time series, common mode errors (CME) often obscure the actual crustal movement signals, leading to deviations in the velocity estimates of station coordinates. Therefore, mitigating the impact of CME on station positioning accuracy is crucial to ensuring the precision and reliability of GNSS time series. The current approach to separating CME mainly uses signal filtering methods to decompose the residuals of the observation network into multiple signals, from which the signals corresponding to CME are identified and separated. However, this method overlooks the spatial correlation of the stations. In this paper, we improved the Independent Component Analysis (ICA) method by introducing correlation coefficients as weighting factors, allowing for more accurate emphasis or attenuation of the contributions of the GNSS network’s spatial distribution during the ICA process. The results show that the improved Weighted Independent Component Analysis (WICA) method can reduce the root mean square (RMS) of the coordinate time series by an average of 27.96%, 15.23%, and 28.33% in the E, N, and U components, respectively. Compared to the ICA method, considering the spatial distribution correlation of stations, the improved WICA method shows enhancements of 12.53%, 3.70%, and 8.97% in the E, N, and U directions, respectively. This demonstrates the effectiveness of the WICA method in separating CMEs and provides a new algorithmic approach for CME separation methods.

To address the limitations of LiDAR dynamic target detection methods, which often require heuristic thresholding, indirect computational assistance, supplementary sensor data, or postdetection, we propose an innovative method based on multidimensional features. Using the differences between the positions and geometric structures of point cloud clusters scanned by the same target in adjacent frame point clouds, the motion states of the point cloud clusters are comprehensively evaluated. To enable the automatic precision pairing of point cloud clusters from adjacent frames of the same target, a double registration algorithm is proposed for point cloud cluster centroids. The iterative closest point (ICP) algorithm is employed for approximate interframe pose estimation during coarse registration. The random sample consensus (RANSAC) and four-parameter transformation algorithms are employed to obtain precise interframe pose relations during fine registration. These processes standardize the coordinate systems of adjacent point clouds and facilitate the association of point cloud clusters from the same target. Based on the paired point cloud cluster, a classification feature system is used to construct the XGBoost decision tree. To enhance the XGBoost training efficiency, a Spearman’s rank correlation coefficient-bidirectional search for a dimensionality reduction algorithm is proposed to expedite the optimal classification feature subset construction. After preliminary outcomes are generated by XGBoost, a double Boyer–Moore voting-sliding window algorithm is proposed to refine the final LiDAR dynamic target detection accuracy. To validate the efficacy and efficiency of our method in LiDAR dynamic target detection, an experimental platform is established. Real-world data are collected and pertinent experiments are designed. The experimental results illustrate the soundness of our method. The LiDAR dynamic target correct detection rate is 92.41%, the static target error detection rate is 1.43%, and the detection efficiency is 0.0299 s. Our method exhibits notable advantages over open-source comparative methods, achieving highly efficient and precise LiDAR dynamic target detection.

One-shot object detection has been a highly demanded yet challenging task since the early age of convolutional neural networks (CNNs). For some newly started projects, a handy network that can learn the target’s pattern using a single picture and automatically decide its architecture is needed. To specifically address a scenario in which a single or multiple targets are standing in relatively stable circumstances with hardly any training data, where the rough location of the target is required, we propose a one-shot simple target detection model that focuses on two main tasks: (1) deciding if the target is in the testing image, and (2) if yes, outputting the target’s location in the image. This model requires no pre-training and decides its architecture automatically; therefore, it could be applied to a newly started target detection project with unconventionally simple targets and few training examples. We also propose an architecture with a non-training parameter-gaining strategy and correlation coefficient-based feedforward and activation functions, as well as easy interpretability, which might provide a perspective on studies in neural networks. We tested this design on the data we collected in our project, the Brown–Yosemite dataset and part of the Mnist dataset. It successfully returned the target area in our project and obtained an IOU of up to 87.04%, reached 80.28% accuracy on the Brown–Yosemite dataset with disposable networks, and obtained an accuracy of up to 89.4% on part of the Mnist dataset in the detection task.

Due to the characteristics of peroxide explosives, which are difficult to detect via conventional detection methods and have high explosive power, a fluorescent photoelectric detection system based on fluorescence detection technology was designed in this study to achieve the high-sensitivity detection of trace peroxide explosives in practical applications. Through actual measurement experiments and numerical simulation methods, the derivative dynamic time warping (DDTW) algorithm and the Spearman correlation coefficient were used to calculate the DDTW–Spearman distance to achieve time series correlation measurements. The detection sensitivity of triacetone triperoxide (TATP) and H2O2 was studied, and the detection of organic substances of acetone, acetylene, ethanol, ethyl acetate, and petroleum ether was carried out. The stability and specific detection ability of the fluorescent photoelectric detection system were determined. The research results showed that the fluorescence photoelectric detection system can effectively identify the detection data of TATP, H2O2, acetone, acetonitrile, ethanol, ethyl acetate, and petroleum ether. The detection limit of 0.01 mg/mL of TATP and 0.0046 mg/mL of H2O2 was less than 10 ppb. The time series similarity measurement method improves the analytical capabilities of fluorescence photoelectric detection technology.

Circular synthetic aperture radar (CSAR) can obtain higher image resolution and more target information using 360° observation of the target. Due to the anisotropy of target scattering characteristics in the actual scene, the sub-aperture imaging method is usually used for CSAR imaging. However, the uniformly divided overlapping sub-aperture CSAR imaging algorithm only considers phase compensation, ignoring the effect of target scattering characteristics on echo amplitude. In CSAR imaging scenarios carried by small rotor unmanned aerial vehicles (SRUAVs), the size of the observed scene cannot be ignored compared to the distance between the target and the antenna and the effect of the anisotropy of the target scattered energy on the echo amplitude should be considered. In this paper, a sub-aperture CSAR imaging method based on adaptive overlapping sub-aperture is proposed. First, the boundary points of the sub-aperture are determined by analyzing the correlation coefficient and the variation coefficient of the energy function. Next, the overlapping sub-aperture division schemes are automatically generated by screening and combining the boundary points. The sub-aperture images are then generated by a Back Projection (BP) algorithm. Finally, sub-aperture image registration and incoherent superposition are used to generate the final CSAR image. Verified by the CSAR field echo data, the proposed method can realize imaging of the original echo data without the Inertial Navigation System (INS) and Global Positioning System (GPS) observation data. Compared with the CSAR full-aperture BP imaging algorithm, the entropy of the image generated by the proposed method increased by 66.77%. Compared with the sub-aperture CSAR imaging algorithm, the entropy of the image generated by the proposed method was improved by 11.12%, retaining more details of the target, improving the target contour features, and enhancing the focusing effect.

The return-to-zero error of the resistance strain load cell is most obvious in the first zero-return process during loading and unloading. To improve the accuracy of the load cell, it is necessary to figure out the cause of the error. The influence of the temperature, material, and weld cup were analyzed in this paper. It was concluded that the hysteresis is the main factor affecting the return-to-zero error after the first load. The relationship between hysteresis and zero-return error after first load was obtained by a data fitting algorithm. A method to improve the return-to-zero error after the first load was proposed.

A self-decoupled technique is described that enables the radiating elements in the antenna array to be densely packed for multiple-input multiple-output (MIMO) wireless communications systems. High isolation between the adjacent antenna elements is obtained by fixing the radiating elements in an orthogonal configuration with respects to each other. Current from the adjacent ports cancels their impact which results in low mutual coupling. The additional benefit of this configuration is realizing a densely packed array. The ground plane of each radiating element on the array board itself are isolated to mitigate surface wave propagations to suppress mutual coupling between the antenna elements. The radiating elements are based on a modified edge-fed circular patch antenna that includes a curved slot line and open-circuited stub to widen the array’s impedance bandwidth with no impact on the antenna’s footprint size. The proposed technique was verified with the design of an antenna array of matrix size 4 × 4 centered at 3.5 GHz. The array had a measured impedance bandwidth of 4 GHz from 1.5 GHz to 5.5 GHz, which corresponds to a fractional bandwidth of 114%, peak gain of 3 dBi and radiation efficiency of 84%. Its average diversity gain and envelope correlation coefficient (ECC) over its operating band are 9.6 dB and

A compact, four-element planar MIMO (Multiple Input, Multiple Output) antenna that operates in an ultra-wideband is presented for diversity application. The orthogonal position of the unit cells replicates the single antenna thrice, thereby decreasing mutual coupling. A UWB MIMO antenna measuring 35 × 35 × 1.6 mm3 is built using a microstrip line (50 Ω impedance) on an FR4 substrate having a thickness of 1.6 mm. The ground plane and radiator of this antenna are adjusted in several ways to bring it within its operating constraints between the frequencies of 3.1 GHz and 10.6 GHz. This technique makes the antenna small and covers the entire ultra-wideband (UWB) frequency range. The NI USRP was used to test the proposed MIMO antenna to determine its real-time performance. Based on the computed results, we conclude that this proposed antenna has outstanding characteristics in terms of performance and is suitable for wireless ultra-wideband indoor communication and diversity utilization with a small size.

The working environment of rotating machines is complex, and their key components are prone to failure. The early fault diagnosis of rolling bearings is of great significance; however, extracting the single scale fault feature of the early weak fault of rolling bearings is not enough to fully characterize the fault feature information of a weak signal. Therefore, aiming at the problem that the early fault feature information of rolling bearings in a complex environment is weak and the important parameters of Variational Modal Decomposition (VMD) depend on engineering experience, a fault feature extraction method based on the combination of Adaptive Variational Modal Decomposition (AVMD) and optimized Multiscale Fuzzy Entropy (MFE) is proposed in this study. Firstly, the correlation coefficient is used to calculate the correlation between the modal components decomposed by VMD and the original signal, and the threshold of the correlation coefficient is set to optimize the selection of the modal number K. Secondly, taking Skewness (Ske) as the objective function, the parameters of MFE embedding dimension M, scale factor S and time delay T are optimized by the Particle Swarm Optimization (PSO) algorithm. Using optimized MFE to calculate the modal components obtained by AVMD, the MFE feature vector of each frequency band is obtained, and the MFE feature set is constructed. Finally, the simulation signals are used to verify the effectiveness of the Adaptive Variational Modal Decomposition, and the Drivetrain Dynamics Simulator (DDS) are used to complete the comparison test between the proposed method and the traditional method. The experimental results show that this method can effectively extract the fault features of rolling bearings in multiple frequency bands, characterize more weak fault information, and has higher fault diagnosis accuracy.

In the optical system for reconstructing speech signals based on laser speckle images, the resonance between the sound source and nearby objects leads to frequency response problem, which seriously affects the accuracy of reconstructed speech. In this paper, we propose a speech enhancement algorithm to reduce the frequency response. The results show that after using the speech enhancement algorithm, the frequency spectrum correlation coefficient between the reconstructed sinusoidal signal and the original sinusoidal signal is improved by up to 82.45%, and the real speech signal is improved by up to 56.40%. This proves that the speech enhancement algorithm is a valuable tool for solving the frequency response problem and improving the accuracy of reconstructed speech.

In this study, a multiple-input multiple-output (MIMO) antenna for wide scanning is designed. By adding slits to the patches, each element is intended to strengthen the isolation between the radiating elements. The proposed high isolation and wide scanning antenna combine to achieve the desired phased-array antenna. The array has a main beam pointing to the desired scanning region and a minimum side lobe level (SLL) in the undesired direction. A compact and linear eight-element array with an interelement spacing of λ/2 is designed and analyzed for beam scanning in the E-plane. Considering the worst case, the proposed array has a very low mutual coupling of (S21 = −24 dB), and it realizes a gain of 9.3 dBi and an SLL of 11 dB at a scanning angle of 70∘. The antenna performance was studied in terms of the S-parameter, radiation patterns, beam-scanning performance, envelope correlation coefficient (ECC), diversity gain (DG), peak gain, and efficiency. A close agreement was observed between the simulated and measured results.

The normal operation of the engine is of great importance for the safety of life and property, so we need to monitor and analyze the state of the engine. Most of the existing methods only diagnose the type of engine fault without further analysis of the severity of the engine fault. Additionally, the features used for fault diagnosis are not selected according to faults and do not necessarily contain more fault information. In the paper, we propose using Pearson correlation coefficients in combination with faults selects sensors and the corresponding features, and then single-fault diagnosis combined with GRU (gating recurrent unit) is performed by using the selected sensors and features. Since multi-fault diagnosis is more difficult than single-fault diagnosis, more state information is required. Therefore, the multi-fault diagnosis will directly extract the time domain features screened above from all vibration signals, stack them and send them to GRU for multi-fault diagnosis. From the experimental results we can conclude that the feature selection method combining Pearson correlation coefficient and fault state can extract effective features to diagnose the fault type and its severity. Finally, the influence factors of the model are analyzed through comparative experiments, and the results show the effectiveness of the method and the selected model parameters.

A distributed multiple-radar system has natural advantages in anti-deception jamming. However, most of the anti-jamming methods are proposed in full spatial registration. In practice, the registration error is difficult to eliminate, which will seriously degrade the performance of cooperative anti-jamming. Therefore, it is of great significance to consider the problem of cooperative anti-deception jamming under registration error. In this paper, the cooperative anti-deception jamming method is proposed in a distributed multiple-radar system under registration errors. On the premise of the known registration error, target received signal vectors are estimated from an uncertainty region in each channel by maximum likelihood (ML) algorithm. With the estimated received signal vectors, a target discrimination algorithm is introduced based on the difference in target spatial scattering characteristics, which calculate the correlation coefficient between different target received signal vectors and discriminate a false target with a designed threshold. Furthermore, since the registration error depends on the radar site errors, theoretical derivation for the registration error is given as a function of the transmitter and receiver site errors. Finally, simulation results verify the feasibility of the proposed discrimination method, and its performance due to the influence of the jamming-to-noise ratio (JNR), the registration error, the target size, and the discrimination threshold are considered.

This work presents a new technique for enhancing the performance of a multiple-input multiple-output (MIMO) antenna by improving its correlation coefficient ρ. A broadband dielectric structure is designed using the transformation electromagnetics (TE) concept to decorrelate the fields of closely placed radiating elements of an MIMO antenna, thereby decreasing ρ and mutual coupling. The desired properties of the broadband dielectric wave tilting structure (DWTS) are determined by using quasi-conformal transformation electromagnetics (QCTE). Next, the permittivity profile of the DWTS is realized by employing air-hole technology, which is based on the effective medium theory, and the DWTS is fabricated using the additive manufacturing (3D printing) technique. The effectiveness of the proposed technique is verified by designing two-element patch-based MIMO antenna prototypes operating at 3 GHz, 5 GHz, and 7 GHz, respectively. The proposed technique helped to reduce the correlation coefficient ρ in the range of 37% to 99% in the respective operating bandwidth of each MIMO antenna, thereby, in each case, improving the isolation between antenna elements by better than 3 dB, which is an excellent performance.

In this research, a heartbeat classification method is presented based on evolutionary feature optimization using differential evolution (DE) and classification using a probabilistic neural network (PNN) to discriminate between normal and arrhythmic heartbeats. The proposed method follows four steps: (1) preprocessing, (2) heartbeat segmentation, (3) DE feature optimization, and (4) PNN classification. In this method, we have employed direct signal amplitude points constituting the heartbeat acquired from the ECG holter device with no secondary feature extraction step usually used in case of hand-crafted, frequency transformation or other features. The heartbeat types include normal, left bundle branch block, right bundle branch block, premature ventricular contraction, atrial premature, ventricular escape, ventricular flutter and paced beat. Using ECG records from the MIT-BIH, heartbeats are identified to start at 250 ms before and end at 450 ms after the respective R-peak positions. In the next step, the DE method is applied to reduce and optimize the direct heartbeat features. Although complex and highly computational ECG heartbeat classification algorithms have been proposed in the literature, they failed to achieve high performance in detecting some minority heartbeat categories, especially for imbalanced datasets. To overcome this challenge, we propose an optimization step for the deep CNN model using a novel classification metric called the Matthews correlation coefficient (MCC). This function focuses on arrhythmia (minority) heartbeat classes by increasing their importance. Maximum MCC is used as a fitness function to identify the optimum combination of features for the uncorrelated and non-uniformly distributed eight beat class samples. The proposed DE-PNN scheme can provide better classification accuracy considering 8 classes with only 36 features optimized from a 253 element feature set implying an 85.77% reduction in direct amplitude features. Our proposed method achieved overall 99.33% accuracy, 94.56% F1, 93.84% sensitivity, and 99.21% specificity.

In general, the investigation of NN (neural network) computing systems requires the management of a significant number of simultaneous distinct algorithms, such as parallel computing, fault tolerance, classification, and data optimization. Supervised learning for NN originally comes from certain parameters, such as self-revised learning, input learning datasets, and multiple second learning processes. Specifically, the operation continues to adjust the NN connection synapses’ weight to achieve a self-learning computer system. The current article is aimed at developing the CC (correlation coefficient) assignment scheme adaptively joint with the FS (feature selection) categories to pursue the solutions utilized in solving the restrictions of NN computing. The NN computing system is expected to solve high-dimensional data, data overfitting, and strict FS problems. Hence, the Fruits-360 dataset is applied in the current article, that is, the variety of fruits, the sameness of color, and the differences in appearance features are utilized to examine the NN system accuracy, performance, and loss rate. Accordingly, there are 120 different kinds with a total of 20,860 fruit image datasets collected from AlexNet, GoogLeNet, and ResNet101, which were implemented in the CC assignment scheme proposed in this article. The results are employed to verify that the accuracy rate can be improved by reducing strict FS. Finally, the results of accuracy rate from the training held for the three NN frameworks are discussed. It was discovered that the GoogLeNet model presented the most significant FS performance. The demonstrated outcomes validate that the proposed CC assignment schemes are absolutely worthwhile in designing and choosing an NN training model for feature discrimination. From the simulation results, it has been observed that the FS-based CC assignment improves the accurate rate of recognition compared to the existing state-of-the-art approaches.

The irregular pressure exerted by a prosthetic socket over the residual limb is one of the major factors that cause the discomfort of amputees using artificial limbs. By deploying the wearable sensors inside the socket, the interfacial pressure distribution can be studied to find the active regions and rectify the socket design. In this case study, a clustering-based analysis method is presented to evaluate the density and layout of these sensors, which aims to reduce the local redundancy of the sensor deployment. In particular, a Self-Organizing Map (SOM) and K-means algorithm are employed to find the clustering results of the sensor data, taking the pressure measurement of a predefined sensor placement as the input. Then, one suitable clustering result is selected to detect the layout redundancy from the input area. After that, the Pearson correlation coefficient (PCC) is used as a similarity metric to guide the removal of redundant sensors and generate a new sparser layout. The Jenson–Shannon Divergence (JSD) and the mean pressure are applied as posterior validation metrics that compare the pressure features before and after sensor removal. A case study of a clinical trial with two sensor strips is used to prove the utility of the clustering-based analysis method. The sensors on the posterior and medial regions are suggested to be reduced, and the main pressure features are kept. The proposed method can help sensor designers optimize sensor configurations for intra-socket measurements and thus assist the prosthetists in improving the socket fitting.

Climate change, characterized by global warming, is profoundly affecting the global environment, politics, economy, and social security. Finding the main causes of climate change and determining their quantitative contributions are key points to making climate decisions on responses to climate change. The Tibetan Plateau (TP) is sensitive to global climate change. Taking the 100 km buffer zones of 45 meteorological stations in the eastern TP as research objects, we conducted an experimental study on temperature change and its influencing factors. Using the least squares multivariate statistical analysis method, a model between the annual and seasonal standardized temperature change and its dynamic influencing factors in the past 20 years was established. The results showed that, in the eastern TP, temperature change was affected by different factors in different periods. Vegetation cover and snow cover were the most correlated factors to temperature change. The influence of carbon dioxide, vegetation cover, and water cover was subject to seasonal changes. Urban cover and bare land cover did not pass the t-test. This research not only provides a theoretical basis for the analysis of temperature change over the TP, but also points out the direction for the analysis of temperature change causes in three polar regions.

The segmentation of power lines (PLs) from aerial images is a crucial task for the safe navigation of unmanned aerial vehicles (UAVs) operating at low altitudes. Despite the advances in deep learning-based approaches for PL segmentation, these models are still vulnerable to the class imbalance present in the data. The PLs occupy only a minimal portion (1–5%) of the aerial images as compared to the background region (95–99%). Generally, this class imbalance problem is addressed via the use of PL-specific detectors in conjunction with the popular class balanced cross entropy (BBCE) loss function. However, these PL-specific detectors do not work outside their application areas and a BBCE loss requires hyperparameter tuning for class-wise weights, which is not trivial. Moreover, the BBCE loss results in low dice scores and precision values and thus, fails to achieve an optimal trade-off between dice scores, model accuracy, and precision–recall values. In this work, we propose a generalized focal loss function based on the Matthews correlation coefficient (MCC) or the Phi coefficient to address the class imbalance problem in PL segmentation while utilizing a generic deep segmentation architecture. We evaluate our loss function by improving the vanilla U-Net model with an additional convolutional auxiliary classifier head (ACU-Net) for better learning and faster model convergence. The evaluation of two PL datasets, namely the Mendeley Power Line Dataset and the Power Line Dataset of Urban Scenes (PLDU), where PLs occupy around 1% and 2% of the aerial images area, respectively, reveal that our proposed loss function outperforms the popular BBCE loss by 16% in PL dice scores on both the datasets, 19% in precision and false detection rate (FDR) values for the Mendeley PL dataset and 15% in precision and FDR values for the PLDU with a minor degradation in the accuracy and recall values. Moreover, our proposed ACU-Net outperforms the baseline vanilla U-Net for the characteristic evaluation parameters in the range of 1–10% for both the PL datasets. Thus, our proposed loss function with ACU-Net achieves an optimal trade-off for the characteristic evaluation parameters without any bells and whistles. Our code is available at Github.

Hemiparesis is one of the common sequelae of neurological diseases such as strokes, which can significantly change the gait behavior of patients and restrict their activities in daily life. The results of gait characteristic analysis can provide a reference for disease diagnosis and rehabilitation; however, gait correlation as a gait characteristic is less utilized currently. In this study, a new non-contact electrostatic field sensing method was used to obtain the electrostatic gait signals of hemiplegic patients and healthy control subjects, and an improved Detrended Cross-Correlation Analysis cross-correlation coefficient method was proposed to analyze the obtained electrostatic gait signals. The results show that the improved method can better obtain the dynamic changes of the scaling index under the multi-scale structure, which makes up for the shortcomings of the traditional Detrended Cross-Correlation Analysis cross-correlation coefficient method when calculating the electrostatic gait signal of the same kind of subjects, such as random and incomplete similarity in the trend of the scaling index spectrum change. At the same time, it can effectively quantify the correlation of electrostatic gait signals in subjects. The proposed method has the potential to be a powerful tool for extracting the gait correlation features and identifying the electrostatic gait of hemiplegic patients.

In an indoor environment, object identification and localization are paramount for human-object interaction. Visual or laser-based sensors can achieve the identification and localization of the object based on its appearance, but these approaches are computationally expensive and not robust against the environment with obstacles. Radio Frequency Identification (RFID) has a unique tag ID to identify the object, but it cannot accurately locate it. Therefore, in this paper, the data of RFID and laser range finder are fused for the better identification and localization of multiple dynamic objects in an indoor environment. The main method is to use the laser range finder to estimate the radial velocities of objects in a certain environment, and match them with the object’s radial velocities estimated by the RFID phase. The method also uses a fixed time series as “sliding time window” to find the cluster with the highest similarity of each RFID tag in each window. Moreover, the Pearson correlation coefficient (PCC) is used in the update stage of the particle filter (PF) to estimate the moving path of each cluster in order to improve the accuracy in a complex environment with obstacles. The experiments were verified by a SCITOS G5 robot. The results show that this method can achieve an matching rate of 90.18% and a localization accuracy of 0.33m in an environment with the presence of obstacles. This method effectively improves the matching rate and localization accuracy of multiple objects in indoor scenes when compared to the Bray-Curtis (BC) similarity matching-based approach as well as the particle filter-based approach.

Background and Objective: The reliability of low-cost mobile systems for recording Electrocardiographic (ECG) data is mostly unknown, posing questions regarding the quality of the recorded data and the validity of the extracted physiological parameters. The present study compared the BITalino toolkit with an established medical-grade ECG system (BrainAmp-ExG). Methods: Participants underwent simultaneous ECG recordings with the two instruments while watching pleasant and unpleasant pictures of the “International Affective Picture System” (IAPS). Common ECG parameters were extracted and compared between the two systems. The Intraclass Correlation Coefficients (ICCs) and the Bland–Altman Limits of Agreement (LoA) method served as criteria for measurement agreement. Results: All but one parameter showed an excellent agreement (>80%) between both devices in the ICC analysis. No criteria for Bland–Altman LoA and bias were found in the literature regarding ECG parameters. Conclusion: The results of the ICC and Bland–Altman methods demonstrate that the BITalino system can be considered as an equivalent recording device for stationary ECG recordings in psychophysiological experiments.

This study aimed to investigate the accuracy and reliability of hip and ankle worn Actigraph GT3X+ (AG) accelerometers to measure steps as a function of gait speed. Additionally, the effect of the low frequency extension filter (LFEF) on the step accuracy was determined. Thirty healthy individuals walked straight and walked with continuous turns in different gait speeds. Number of steps were recorded with a hip and ankle worn AG, and with a Stepwatch (SW) activity monitor positioned around the right ankle, which was used as a reference for step count. The percentage agreement, interclass correlation coefficients and Bland–Altmann plots were determined between the AG and the reference SW across gait speeds for the two walking conditions. The ankle worn AG with the default filter was the most sensitive for step detection at >0.6 m/s, whilst accurate step detection for gait speeds < 0.6 m/s were only observed when applying the LFEF. The hip worn AG with the default filter showed poor accuracy (12–78%) at gait speeds < 1.0 m/s whereas the accuracy increased to >87% for gait speeds < 1.0 m/s when applying the LFEF. Ankle worn AG was the most sensitive to measure steps at a vast range of gait speeds. Our results suggest that sensor placement and filter settings need to be taken into account to provide accurate estimates of step counts.

The direction-of-arrival (DoA) estimation of an acoustic source can be estimated with a uniform linear array using classical techniques such as generalized cross-correlation, beamforming, subspace techniques, etc. However, these methods require a search in the angular space and also have a higher angular error at the end-fire. In this paper, we propose the use of regression techniques to improve the results of DoA estimation at all angles including the end-fire. The proposed methodology employs curve-fitting on the received multi-channel microphone signals, which when applied in tandem with support vector regression (SVR) provides a better estimation of DoA as compared to the conventional techniques and other polynomial regression techniques. A multilevel regression technique is also proposed, which further improves the estimation accuracy at the end-fire. This multilevel regression technique employs the use of linear regression over the results obtained from SVR. The techniques employed here yielded an overall 63% improvement over the classical generalized cross-correlation technique.

During the processing and planting of soybeans, it is greatly significant that a reliable, rapid, and accurate technique is used to detect soybean varieties. Traditional chemical analysis methods of soybean variety sampling (e.g., mass spectrometry and high-performance liquid chromatography) are destructive and time-consuming. In this paper, a robust and accurate method for nondestructive soybean classification is developed through hyperspectral imaging and ensemble machine learning algorithms. Image acquisition, preprocessing, and feature selection are used to obtain different types of soybean hyperspectral features. Based on these features, one of ensemble classifiers-random subspace linear discriminant (RSLD) algorithm is used to classify soybean seeds. Compared with the linear discrimination (LD) and linear support vector machine (LSVM) methods, the results show that the RSLD algorithm in this paper is more stable and reliable. In classifying soybeans in 10, 15, 20, and 25 categories, the RSLD method achieves the highest classification accuracy. When 155 features are used to classify 15 types of soybeans, the classification accuracy of the RSLD method reaches 99.2%, while the classification accuracies of the LD and LSVM methods are only 98.6% and 69.7%, respectively. Therefore, the ensemble classification algorithm RSLD can maintain high classification accuracy when different types and different classification features are used.

Since the chirp spread spectrum (CSS) system is considered as a communication technology for the Internet of things (IoT), long-range communication and a high data rate are required. In wireless communications, in order to increase spectral efficiency and to extend transmission coverage, a two-path successive relaying (TPSR) protocol has been proposed. Thus, in order to improve transmission performance of the CSS system, in this paper we apply the TPSR protocol to the CSS system. However, since the TPSR protocol is successively relaying data, the spectral efficiency may be limited due to inter-relay interference (IRI). Hence, we propose a multiple linear chirp-based IRI mitigation method for the CSS-based TPSR protocol. In the proposed scheme, the cross-correlation coefficient (CCC) has been derived mathematically according to a separating bandwidth in a given total bandwidth. Then, one separating bandwidth that guarantees the transmission performance is allocated to the primary relay by considering a single relay CCC (SR-CCC) and another separating bandwidth that guarantees the orthogonality from the primary relay is allocated to the secondary relay by considering the inter-relay CCC (IR-CCC). Since the IR-CCC means a degree of similarity between these two relays, it is possible to mitigate the IRI effect within the same bandwidth by allocating orthogonal separating bandwidths to each relay. Simulation results show that the proposed scheme can improve the transmission performance by mitigating the IRI effect even in high IRI environments. Consequently, we expect that the proposed scheme can extend the transmission coverage and increase the data rate of the CSS system.

Carbon fiber reinforced polymer materials are widely applied in structure strengthened engineering because of the many advantages of carbon fiber reinforced polymer. However, the debonding damage between the carbon fiber reinforced polymer and host structures occurs frequently, which might lead to the brittle failure of structure components, especially flexural ones. In this paper, an electromechanical impedance-based method, an important technique in structural health monitoring, was adopted to detect the debonding damage of carbon fiber reinforced polymer plate-strengthened steel beam by using lead zirconate titanate (PZT) transducers. A carbon fiber reinforced polymer plate-strengthened steel beam specimen was fabricated in the laboratory and two PZT sensors were attached at different locations on the carbon fiber reinforced polymer plate. The impedance signatures with variation of the different degrees of the debonding damage were measured by an impedance analyzer. The root-mean-square deviation method and the cross-correlation coefficient method were used to quantify the correlation between the electromechanical impedance and the debonding damage degree. The results reflect that an electromechanical impedance-based structural health monitoring technique can serve as a good method to detect the debonding damage of carbon fiber reinforced polymer plate-strengthened steel structures.

An accurate prediction of cage-cultured water quality is a hot topic in smart mariculture. Since the mariculturing environment is always open to its surroundings, the changes in water quality parameters are normally nonlinear, dynamic, changeable, and complex. However, traditional forecasting methods have lots of problems, such as low accuracy, poor generalization, and high time complexity. In order to solve these shortcomings, a novel water quality prediction method based on the deep LSTM (long short-term memory) learning network is proposed to predict pH and water temperature. Firstly, linear interpolation, smoothing, and moving average filtering techniques are used to repair, correct, and de-noise water quality data, respectively. Secondly, Pearson’s correlation coefficient is used to obtain the correlation priors between pH, water temperature, and other water quality parameters. Finally, a water quality prediction model based on LSTM is constructed using the preprocessed data and its correlation information. Experimental results show that, in the short-term prediction, the prediction accuracy of pH and water temperature can reach 98.56% and 98.97%, and the time cost of the predictions is 0.273 s and 0.257 s, respectively. In the long-term prediction, the prediction accuracy of pH and water temperature can reach 95.76% and 96.88%, respectively.

An unconstrained monitoring method for a driver’s heartbeat is investigated in this paper. Signal measurement was carried out by using pressure sensors array. Due to the inevitable changes of posture during driving, the monitoring place for heartbeat measurement needs to be adjusted accordingly. An experiment was conducted to attach a pressure sensors array to the backrest of a seat. On the basis of the extreme learning machine classification method, driving posture can be recognized by monitoring the distribution of pressure signals. Then, a band-pass filter in heart rate range is adapted to the pressure signals in the frequency domain. Furthermore, a peak point array of the processed pressure frequency spectrum is derived and has the same distribution as the pressure signals. Thus, the heartbeat signals can be extracted from pressure sensors. Then, the correlation coefficient analysis of heartbeat signals and electrocardio-signals is performed. The results show a high level of correlation. Finally, the effects of driving posture on heartbeat signal extraction are discussed to obtain a theoretical foundation for measuring point real-time adjustment.

Land cover change detection based on remote sensing has become increasingly important for protecting the ecological environment. Spatial features of images can be extracted by object-level methods. However, the computational complexity is high when using many features to detect land cover change. Meanwhile, single-constrained change detection (SCCD) methods produce non-objective and inaccurate results. Therefore, we proposed a land cover change detection method: the object-level double constrained change detection (ODCD) method. First, spectral and spatial features were calculated based on multi-scale segmentation results. Second, using the significant difference test (SDT), feature differences among all categories were calculated, and the features with more significant differences were considered as the optimal features. Third, the maximum Kappa coefficient was used as the criterion for determining the optimal change intensity and correlation coefficient. Finally, the ODCD was validated using GF-1 satellite images on March 2016 and February 2017 in north Beiqijia Town, Beijing. Using optimal feature selection, the dimension of features was reduced from 26 to 12. Compared with SCCD methods, the result of the ODCD was more reliable and accurate. Its overall accuracy was 10% higher, overall error was 27% lower, and the Kappa coefficient was 0.22 higher. In conclusion, the ODCD is effective for land cover change detection and can improve computational efficiency.

Wireless access in vehicular environments to support wireless communication between vehicles has been developed to provide road safety and infotainment services. In vehicular environments where the channel changes rapidly, channel estimation is very important in improving the reliability of wireless communication. Therefore, numerous channel estimation schemes have been proposed; however, none of the schemes proposed so far can perform well over the entire signal-to-noise ratio (SNR) region. In this paper, we propose a novel channel estimation scheme that selectively uses the better scheme between two channel estimation schemes on a symbol-by-symbol basis. The results show that the proposed scheme performs symbol-by-symbol selection of the better channel estimation scheme within a packet, and thus shows excellent performance over the entire SNR region in vehicular environments in terms of the bit error rate and packet error rate.