Search

The reliable and cost-effective condition monitoring of the bearings installed in water pumps is a real challenge in the industry. This paper presents a novel strong feature selection and extraction algorithm (SFSEA) to extract fault-related features from the instantaneous power spectrum (IPS). The three features extracted from the IPS using the SFSEA are fed to an extreme gradient boosting (XBG) classifier to reliably detect and classify the minor bearing faults. The experiments performed on a lab-scale test setup demonstrated classification accuracy up to 100%, which is better than the previously reported fault classification accuracies and indicates the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

For early fault detection of a bearing, the localized defect generally brings a complex vibration signal, so it is difficult to detect the periodic transient characteristics from the signal spectrum using conventional bearing fault diagnosis methods. Therefore, many matrix analysis technologies, such as singular value decomposition (SVD) and reweighted SVD (RSVD), were proposed recently to solve this problem. However, such technologies also face failure in bearing fault detection due to the poor interpretability of the obtained eigenvector. Non-negative Matrix Factorization (NMF), as a part-based representation algorithm, can extract low-rank basis spaces with natural sparsity from the time–frequency representation. It performs excellent interpretability of the factor matrices due to its non-negative constraints. By this virtue, NMF can extract the fault feature by separating the frequency bands of resonance regions from the amplitude spectrogram automatically. In this paper, a new feature extraction method based on sparse kernel NMF (KNMF) was proposed to extract the fault features from the amplitude spectrogram in greater depth. By decomposing the amplitude spectrogram using the kernel-based NMF model with L1 regularization, sparser spectral bases can be obtained. Using KNMF with the linear kernel function, the time–frequency distribution of the vibration signal can be decomposed into a subspace with different frequency bands. Thus, we can extract the fault features, a series of periodic impulses, from the decomposed subspace according to the sparse frequency bands in the spectral bases. As a result, the proposed method shows a very high performance in extracting fault features, which is verified by experimental investigations and benchmarked by the Fast Kurtogram, SVD and NMF-based methods. [ABSTRACT FROM AUTHOR]

To solve the problems of low accuracy, low real-time performance, poor robustness and others caused by the complex environment, this paper proposes a face mask recognition and standard wear detection algorithm based on the improved YOLO-v4. Firstly, an improved CSPDarkNet53 is introduced into the trunk feature extraction network, which reduces the computing cost of the network and improves the learning ability of the model. Secondly, the adaptive image scaling algorithm can reduce computation and redundancy effectively. Thirdly, the improved PANet structure is introduced so that the network has more semantic information in the feature layer. At last, a face mask detection data set is made according to the standard wearing of masks. Based on the object detection algorithm of deep learning, a variety of evaluation indexes are compared to evaluate the effectiveness of the model. The results of the comparations show that the mAP of face mask recognition can reach 98.3% and the frame rate is high at 54.57 FPS, which are more accurate compared with the exiting algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we present a WiFi-based intrusion detection system called Wi-Alarm. Motivated by our observations and analysis that raw channel state information (CSI) of WiFi is sensitive enough to monitor human motion, Wi-Alarm omits data preprocessing. The mean and variance of the amplitudes of raw CSI data are used for feature extraction. Then, a support vector machine (SVM) algorithm is applied to determine detection results. We prototype Wi-Alarm on commercial WiFi devices and evaluate it in a typical indoor scenario. Results show that Wi-Alarm reduces much computational expense without losing accuracy and robustness. Moreover, different influence factors are also discussed in this paper. [ABSTRACT FROM AUTHOR]

For some measurement and detection applications based on video (sequence images), if the exposure time of camera is not suitable with the motion speed of the photographed target, fuzzy edges will be produced in the image, and some poor lighting condition will aggravate this edge blur phenomena. Especially, the existence of noise in industrial field environment makes the extraction of fuzzy edges become a more difficult problem when analyzing the posture of a high-speed moving target. Because noise and edge are always both the kind of high-frequency information, it is difficult to make trade-offs only by frequency bands. In this paper, a noise-tolerant edge detection method based on the correlation relationship between layers of wavelet transform coefficients is proposed. The goal of the paper is not to recover a clean image from a noisy observation, but to make a trade-off judgment for noise and edge signal directly according to the characteristics of wavelet transform coefficients, to realize the extraction of edge information from a noisy image directly. According to the wavelet coefficients tree and the Lipschitz exponent property of noise, the idea of neural network activation function is adopted to design the activation judgment method of wavelet coefficients. Then the significant wavelet coefficients can be retained. At the same time, the non-significant coefficients were removed according to the method of judgment of isolated coefficients. On the other hand, based on the design of Daubechies orthogonal compactly-supported wavelet filter, rational coefficients wavelet filters can be designed by increasing free variables. By reducing the vanishing moments of wavelet filters, more high-frequency information can be retained in the wavelet transform fields, which is benefit to the application of edge detection. For a noisy image of high-speed moving targets with fuzzy edges, by using the length 8-4 rational coefficients biorthogonal wavelet filters and the algorithm proposed in this paper, edge information could be detected clearly. Results of multiple groups of comparative experiments have shown that the edge detection effect of the proposed algorithm in this paper has the obvious superiority. [ABSTRACT FROM AUTHOR]

A sensor registry system (SRS) registers sensor metadata and provides them for a seamless semantic process. Recently, network coverage information-based SRS (NC-SRS) was developed to provide sensor information filtering by combining path prediction and network coverage checks. However, the NC-SRS has problems caused by issues such as termination of OpenSignal service and pre-building road segments. Therefore, this paper proposes a sensor registry system-based predictive information service (SRS-PIS) using a grid. SRS-PIS predicts a path based on the grid, checks the network coverage, and filters the sensor. This paper presents a grid-based real-time path prediction algorithm and an algorithm for grouping network service-disabled areas. To obtain network coverage information, we constructed and implemented a grid-based coverage map through experiment to measure the signal strength. As an evaluation, we compared features among SRS-based systems and SRS-PIS, and compared advantages and disadvantages between segment-based and grid-based methods. [ABSTRACT FROM AUTHOR]

In this paper, a Deep Learning approach is proposed to classify impact data based on the type of impact (Hard or Soft Impacts), via obtaining voltage signals from Piezo-Electric sensors, mounted on a composite panel. The data is processed further to be classified based on their energy, location and material. Minimalistic and Automated feature extraction and selection is achieved via a deep learning algorithm. Convolutional Neural Networks (CNN) are employed to extract and select important features from the voltage data. Once features are selected the impacts, are classified based on either, Hard Impacts (simulated from steel impactors in a lab setting), Soft Impacts (simulated from silicon impactors in a lab setting) and their corresponding location and energy levels. Furthermore, in order to use the right data for training they are obtained from the signals as anomalies via Isolation Forests (IF) to speed up the process. Using this approach Hard and Soft Impacts, their corresponding locations and respective energies are identified with high accuracy. [ABSTRACT FROM AUTHOR]

With the enormous amount of multi-source data produced by various sensors and feature extraction approaches, multi-view clustering (MVC) has attracted developing research attention and is widely exploited in data analysis. Most of the existing multi-view clustering methods hold on the assumption that all of the views are complete. However, in many real scenarios, multi-view data are often incomplete for many reasons, e.g., hardware failure or incomplete data collection. In this paper, we propose an adaptive weighted graph fusion incomplete multi-view subspace clustering (AWGF-IMSC) method to solve the incomplete multi-view clustering problem. Firstly, to eliminate the noise existing in the original space, we transform complete original data into latent representations which contribute to better graph construction for each view. Then, we incorporate feature extraction and incomplete graph fusion into a unified framework, whereas two processes can negotiate with each other, serving for graph learning tasks. A sparse regularization is imposed on the complete graph to make it more robust to the view-inconsistency. Besides, the importance of different views is automatically learned, further guiding the construction of the complete graph. An effective iterative algorithm is proposed to solve the resulting optimization problem with convergence. Compared with the existing state-of-the-art methods, the experiment results on several real-world datasets demonstrate the effectiveness and advancement of our proposed method. [ABSTRACT FROM AUTHOR]

In recent years, increasing image data comes from various sensors, and object detection plays a vital role in image understanding. For object detection in complex scenes, more detailed information in the image should be obtained to improve the accuracy of detection task. In this paper, we propose an object detection algorithm by jointing semantic segmentation (SSOD) for images. First, we construct a feature extraction network that integrates the hourglass structure network with the attention mechanism layer to extract and fuse multi-scale features to generate high-level features with rich semantic information. Second, the semantic segmentation task is used as an auxiliary task to allow the algorithm to perform multi-task learning. Finally, multi-scale features are used to predict the location and category of the object. The experimental results show that our algorithm substantially enhances object detection performance and consistently outperforms other three comparison algorithms, and the detection speed can reach real-time, which can be used for real-time detection. [ABSTRACT FROM AUTHOR]

People with sleep apnea (SA) are at increased risk of having stroke and cardiovascular diseases. Polysomnography (PSG) is used to detect SA. This paper conducts feature selection from PSG signals and uses a support vector machine (SVM) to detect SA. To analyze SA, the Physionet Apnea Database was used to obtain various features. Electrocardiography (ECG), oxygen saturation (SaO2), airflow, abdominal, and thoracic signals were used to provide various frequency-, time-domain and non-linear features (n = 87). To analyse the significance of these features, firstly, two evaluation measures, the rank-sum method and the analysis of variance (ANOVA) were used to evaluate the significance of the features. These features were then classified according to their significance. Finally, different class feature sets were presented as inputs for an SVM classifier to detect the onset of SA. The hill-climbing feature selection algorithm and the k-fold cross-validation method were applied to evaluate each classification performance. Through the experiments, we discovered that the best feature set (including the top-five significant features) obtained the best classification performance. Furthermore, we plotted receiver operating characteristic (ROC) curves to examine the performance of the SVM, and the results showed the SVM with Linear kernel (regularization parameter = 1) outperformed other classifiers (area under curve = 95.23%, sensitivity = 94.29%, specificity = 96.17%). The results confirm that feature subsets based on multiple bio-signals have the potential to identify patients with SA. The use of a smaller subset avoids dimensionality problems and reduces the computational load. [ABSTRACT FROM AUTHOR]

The required precision for attitude determination in spacecraft is increasing, providing a need for more accurate attitude determination sensors. The star sensor or star tracker provides unmatched arc-second precision and with the rise of micro satellites these sensors are becoming smaller, faster and more efficient. The most critical component in the star sensor system is the lost-in-space star identification algorithm which identifies stars in a scene without a priori attitude information. In this paper, we present an efficient lost-in-space star identification algorithm using a neural network and a robust and novel feature extraction method. Since a neural network implicitly stores the patterns associated with a guide star, a database lookup is eliminated from the matching process. The search time is therefore not influenced by the number of patterns stored in the network, making it constant (O(1)). This search time is unrivalled by other star identification algorithms. The presented algorithm provides excellent performance in a simple and lightweight design, making neural networks the preferred choice for star identification algorithms. [ABSTRACT FROM AUTHOR]

The vibration signal of an early rolling bearing is nonstationary and nonlinear, and the fault signal is weak and difficult to extract. To address this problem, this paper proposes a genetic mutation particle swarm optimization variational mode decomposition (GMPSO-VMD) algorithm and applies it to rolling bearing vibration signal fault feature extraction. Firstly, the minimum envelope entropy is used as the objective function of the GMPSO to find the optimal parameter combination of the VMD algorithm. Then, the optimized VMD algorithm is used to decompose the vibration signal of the rolling bearing and several intrinsic mode functions (IMFs) are obtained. The envelope spectrum analysis of GMPSO-VMD decomposed rolling bearing fault signal IMF1 was carried out. Moreover, the feature frequency of the four fault states of the rolling bearing are extracted accurately. Finally, the GMPSO-VMD algorithm is utilized to analyze the simulation signal and rolling bearing fault vibration signal. The effectiveness of the GMPSO-VMD algorithm is verified by comparing it with the fixed parameter VMD (FP-VMD) algorithm, complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm and empirical mode decomposition (EMD) algorithm. [ABSTRACT FROM AUTHOR]

Bearing spall detection and predicting its size are great challenges. Model-based simulation is a well-known traditional approach to physically model the influence of the spall on the bearing. Building a physical model is challenging due to the bearing complexity and the expert knowledge required to build such a model. Obviously, building a partial physical model for some of the spall sizes is easier. In this paper, we propose a machine-learning algorithm, called Probability-Based Forest, that uses a partial physical model. First, the behavior of some of the spall sizes is physically modeled and a simulator based on this model generates scenarios for these spall sizes in different conditions. Then, the machine-learning algorithm trains these scenarios to generate a prediction model of spall sizes even for those that have not been modeled by the physical model. Feature extraction is a key factor in the success of this approach. We extract features using two traditional approaches: statistical and physical, and an additional new approach: Time Series FeatuRe Extraction based on Scalable Hypothesis tests (TSFRESH). Experimental evaluation with well-known physical model shows that our approach achieves high accuracy, even in cases that have not been modeled by the physical model. Also, we show that the TSFRESH feature-extraction approach achieves the highest accuracy. [ABSTRACT FROM AUTHOR]

Traffic sign detection systems provide important road control information for unmanned driving systems or auxiliary driving. In this paper, the Faster region with a convolutional neural network (R-CNN) for traffic sign detection in real traffic situations has been systematically improved. First, a first step region proposal algorithm based on simplified Gabor wavelets (SGWs) and maximally stable extremal regions (MSERs) is proposed. In this way, the region proposal a priori information is obtained and will be used for improving the Faster R-CNN. This part of our method is named as the highly possible regions proposal network (HP-RPN). Second, in order to solve the problem that the Faster R-CNN cannot effectively detect small targets, a method that combines the features of the third, fourth, and fifth layers of VGG16 to enrich the features of small targets is proposed. Third, the secondary region of interest method to enhance the feature of detection objects and improve the classification capability of the Faster R-CNN is proposed. Finally, a method of merging the German traffic sign detection benchmark (GTSDB) and Chinese traffic sign dataset (CTSD) databases into one larger database to increase the number of database samples is proposed. Experimental results show that our method improves the detection performance, especially for small targets. [ABSTRACT FROM AUTHOR]

To achieve the full analytical potential of the streaming data from the internet of things, the interconnection of various data sources is needed. By definition, those sources are heterogeneous and their integration is not a trivial task. A common approach to exploit streaming sensor data potential is to use machine learning techniques for predictive analytics in a way that is agnostic to the domain knowledge. Such an approach can be easily integrated in various use cases. In this paper, we propose a novel framework for data fusion of a set of heterogeneous data streams. The proposed framework enriches streaming sensor data with the contextual and historical information relevant for describing the underlying processes. The final result of the framework is a feature vector, ready to be used in a machine learning algorithm. The framework has been applied to a cloud and to an edge device. In the latter case, incremental learning capabilities have been demonstrated. The reported results illustrate a significant improvement of data-driven models, applied to sensor streams. Beside higher accuracy of the models the platform offers easy setup and thus fast prototyping capabilities in real-world applications. [ABSTRACT FROM AUTHOR]

The research field of visual-inertial odometry has entered a mature stage in recent years. However, unneglectable problems still exist. Tradeoffs have to be made between high accuracy and low computation for users. In addition, notation confusion exists in quaternion descriptions of rotation; although not fatal, this may results in unnecessary difficulties in understanding for researchers. In this paper, we develop a visual-inertial odometry which gives consideration to both precision and computation. The proposed algorithm is a filter-based solution that utilizes the framework of the noted multi-state constraint Kalman filter. To dispel notation confusion, we deduced the error state transition equation from scratch, using the more cognitive Hamilton notation of quaternion. We further come up with a fully linear closed-form formulation that is readily implemented. As the filter-based back-end is vulnerable to feature matching outliers, a descriptor-assisted optical flow tracking front-end was developed to cope with the issue. This modification only requires negligible additional computation. In addition, an initialization procedure is implemented, which automatically selects static data to initialize the filter state. Evaluations of proposed methods were done on a public, real-world dataset, and comparisons were made with state-of-the-art solutions. The experimental results show that the proposed solution is comparable in precision and demonstrates higher computation efficiency compared to the state-of-the-art. [ABSTRACT FROM AUTHOR]

A binocular vision system is a common perception component of an intelligent vehicle. Benefiting from the biomimetic structure, the system is simple and effective. Which are extremely snesitive on external factors, especially missing vision signals. In this paper, a virtual view-generation algorithm based on generative adversarial networks (GAN) is proposed to enhance the robustness of binocular vision systems. The proposed model consists of two parts: generative network and discriminator network. To improve the quality of a virtual view, a generative network structure based on 3D convolutional neural networks (3D-CNN) and attentive mechanisms is introduced to extract the time-series features from image sequences. To avoid gradient vanish during training, the dense block structure is utilized to improve the discriminator network. Meanwhile, three kinds of image features, including image edge, depth map and optical flow are extracted to constrain the supervised training of model. The final results on KITTI and Cityscapes datasets demonstrate that our algorithm outperforms conventional methods, and the missing vision signal can be replaced by a generated virtual view. [ABSTRACT FROM AUTHOR]

Visual Simultaneous Localization and Mapping (SLAM) approaches have achieved a major breakthrough in recent years. This paper presents a new monocular visual odometry algorithm able to localize in 3D a robot or a camera inside an unknown environment in real time, even on slow processors such as those used in unmanned aerial vehicles (UAVs) or cell phones. The so-called semi-direct visual localization (SDVL) approach is focused on localization accuracy and uses semi-direct methods to increase feature-matching efficiency. It uses inverse-depth 3D point parameterization. The tracking thread includes a motion model, direct image alignment, and optimized feature matching. Additionally, an outlier rejection mechanism (ORM) has been implemented to rule out misplaced features, improving accuracy especially in partially dynamic environments. A relocalization module is also included but keeping the real-time operation. The mapping thread performs an automatic map initialization with homography, a sampled integration of new points and a selective map optimization. The proposed algorithm was experimentally tested with international datasets and compared to state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

This paper presents a modeling approach to feature classification and environment mapping for indoor mobile robotics via a rotary ultrasonic array and fuzzy modeling. To compensate for the distance error detected by the ultrasonic sensor, a novel feature extraction approach termed "minimum distance of point" (MDP) is proposed to determine the accurate distance and location of target objects. A fuzzy model is established to recognize and classify the features of objects such as flat surfaces, corner, and cylinder. An environmental map is constructed for automated robot navigation based on this fuzzy classification, combined with a cluster algorithm and least-squares fitting. Firstly, the platform of the rotary ultrasonic array is established by using four low-cost ultrasonic sensors and a motor. Fundamental measurements, such as the distance of objects at different rotary angles and with different object materials, are carried out. Secondly, the MDP feature extraction algorithm is proposed to extract precise object locations. Compared with the conventional range of constant distance (RCD) method, the MDP method can compensate for errors in feature location and feature matching. With the data clustering algorithm, a range of ultrasonic distances is attained and used as the input dataset. The fuzzy classification model—including rules regarding data fuzzification, reasoning, and defuzzification—is established to effectively recognize and classify the object feature types. Finally, accurate environment mapping of a service robot, based on MDP and fuzzy modeling of the measurements from the ultrasonic array, is demonstrated. Experimentally, our present approach can realize environment mapping for mobile robotics with the advantages of acceptable accuracy and low cost. [ABSTRACT FROM AUTHOR]

It is crucial for robots to autonomously steer in complex environments safely without colliding with any obstacles. Compared to conventional methods, deep reinforcement learning-based methods are able to learn from past experiences automatically and enhance the generalization capability to cope with unseen circumstances. Therefore, we propose an end-to-end deep reinforcement learning algorithm in this paper to improve the performance of autonomous steering in complex environments. By embedding a branching noisy dueling architecture, the proposed model is capable of deriving steering commands directly from raw depth images with high efficiency. Specifically, our learning-based approach extracts the feature representation from depth inputs through convolutional neural networks and maps it to both linear and angular velocity commands simultaneously through different streams of the network. Moreover, the training framework is also meticulously designed to improve the learning efficiency and effectiveness. It is worth noting that the developed system is readily transferable from virtual training scenarios to real-world deployment without any fine-tuning by utilizing depth images. The proposed method is evaluated and compared with a series of baseline methods in various virtual environments. Experimental results demonstrate the superiority of the proposed model in terms of average reward, learning efficiency, success rate as well as computational time. Moreover, a variety of real-world experiments are also conducted which reveal the high adaptability of our model to both static and dynamic obstacle-cluttered environments. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification is a hot issue in the field of remote sensing. It is possible to achieve high accuracy and strong generalization through a good classification method that is used to process image data. In this paper, an efficient hyperspectral image classification method based on improved Rotation Forest (ROF) is proposed. It is named ROF-KELM. Firstly, Non-negative matrix factorization(NMF) is used to do feature segmentation in order to get more effective data. Secondly, kernel extreme learning machine (KELM) is chosen as base classifier to improve the classification efficiency. The proposed method inherits the advantages of KELM and has an analytic solution to directly implement the multiclass classification. Then, Q-statistic is used to select base classifiers. Finally, the results are obtained by using the voting method. Three simulation examples, classification of AVIRIS image, ROSIS image and the UCI public data sets respectively, are conducted to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]