Search

The incipient fault is difficult to detect because of its small amplitude and insignificant impact, however, ignoring such fault may cause irreversible damage to the system. In this paper, a hierarchical latent variable extraction and multisegment probability density analysis method is proposed to detect the incipient fault. Firstly, three data subspaces are constructed, which are named dominant, intermediate and residual spaces, and key latent variables which contain more offline variance or online variation information will be retained. Afterwards, the expanded data distribution interval and multiple data segments are constructed for the probability density estimation. Based on the improved symmetric divergence index, the distribution distance between the online data and offline modeling data can be evaluated, which has achieved 95.3% and 86.8% average detection rates for the faults in numerical case and Tennessee Eastman process. Finally, a real multiphase flow facility is used to demonstrate the effectiveness of the proposed method.

In real‐world applications, large amounts of data from multiple sources come in the form of streams. This makes multi‐view feature learning cost much time when new instances rise incrementally. Dealing with these growing multi‐view data becomes a challenging problem. Some single‐view methods focus on processing the data dynamically, but they are not suitable for multi‐view data. Some online multi‐view methods are proposed to tackle it, but they ignore the influence of uncorrelated items in each view. Therefore, in this study, the authors propose a new algorithm, called Incremental Multi‐view Correlated Feature Learning (IMCFL) based on non‐negative matrix factorisation, to learn the common feature across views. By separating uncorrelated items of new instances and constructing incremental joint learning of correlated and uncorrelated features, the proposed IMCFL can eliminate the influence of uncorrelated information in the individual view and improve the effectiveness of incremental multi‐view common feature learning. Extensive experiments on real‐world datasets confirm its superiority by comparing it with other state‐of‐the‐art incremental and non‐incremental methods.

Gaussian sampling over the integers is one of the fundamental building blocks of lattice-based cryptography. Among the extensively used trapdoor sampling algorithms, it is ineluctable until now. Under the influence of numerous side-channel attacks, it is still challenging to construct a Gaussian sampler that is generic, efficient, and resistant to timing attacks. In this paper, our contribution is three-fold. First, we propose a secure, efficient exponential Bernoulli sampling algorithm. It can be applied to Gaussian samplers based on rejection samplings. We apply it to FALCON, a candidate of round 3 of the NIST post-quantum cryptography standardization project, and reduce its signature generation time by 13–14%. Second, we develop an isochronous Gaussian sampler based on rejection sampling. Our Algorithm can securely sample from Gaussian distributions with different standard deviations and arbitrary centers. We apply it to PALISADE (S&P 2018), an open-source lattice-based cryptography library. During the online phase of trapdoor sampling, the running time of the G-lattice sampling algorithm is reduced by 44.12% while resisting timing attacks. Third, we improve the efficiency of the COSAC sampler (PQC 2020). The new COSAC sampler is 1.46x–1.63x faster than the original and has the lowest expected number of trials among all Gaussian samplers based on rejection samplings. But it needs a more efficient algorithm sampling from the normal distribution to improve its performance.

The technique of recognising text in natural scene pictures is widely used in social production. For the existing identification methods, it is difficult to accurately identify in complex environments. The accuracy of the detection determines the efficiency of the identification. A text detection method based on Multiscale Connectionist Text Proposal Network is proposed. The Multiscale-Region Proposal Network regresses and classifies the extracted region to obtain the final candidate region. Taking a large number of commodity image samples as a dataset, the multi-scale joint text proposal network is used to detect and locate the text content area in the image. The experimental results show that the proposed algorithm improves the detection accuracy in complex environments.

Adaptive optics—optical coherence tomography (AO-OCT) is a non-invasive technique for imaging retinal vascular and structural features at cellular-level resolution. Whereas retinal blood vessel density is an important biomarker for ocular diseases, particularly glaucoma, automated blood vessel segmentation tools in AO-OCT have not yet been explored. One reason for this is that AO-OCT allows for variable input axial dimensions, which are not well accommodated by 2D-2D or 3D-3D segmentation tools. We propose a novel bidirectional long short-term memory (LSTM)-based network for 3D-2D segmentation of blood vessels within AO-OCT volumes. This technique incorporates inter-slice connectivity and allows for variable input slice numbers. We compare this proposed model to a standard 2D UNet segmentation network considering only volume projections. Furthermore, we expanded the proposed LSTM-based network with an additional UNet to evaluate how it refines network performance. We trained, validated, and tested these architectures in 177 AO-OCT volumes collected from 18 control and glaucoma subjects. The LSTM-UNet has statistically significant improvement (p &lt, 0.05) in AUC (0.88) and recall (0.80) compared to UNet alone (0.83 and 0.70, respectively). LSTM-based approaches had longer evaluation times than the UNet alone. This study shows that a bidirectional convolutional LSTM module improves standard automated vessel segmentation in AO-OCT volumes, although with higher time cost.

SLAM is a key technology in the field of mobile robot. However, it is difficult to meet the requirements of positioning accuracy by using single sensor to locate and navigate for a mobile robot. Multi-sensor information fusion technology has become an important method to solve the problem of mobile robot positioning and navigation. By establishing information fusion model, building sensor experimental platform such as laser radar, ultrasonic ranging module and monocular camera, based on the laser RBPF-SLAM algorithm, a SLAM algorithm based on multi-sensor information fusion is proposed. The mobile robot can locate and construct road sign map at the same time. The laser RBPF-SLAM positioning and monocular visual positioning are advanced by using the information fusion model Information fusion under the maximum posterior probability criterion. Through experiments, the accuracy, effectiveness and practicability of the proposed method are verified.

In this paper, we introduce the first simulation framework that provides cost-effective means to evaluate indoor navigation systems for different user groups (e.g., users with visual impairment), various positioning techniques, and navigation instructions algorithms. The simulation engine uses the Unity game engine, which tracks the virtual user interaction and motion in a virtual environment that represents the physical environment in which the user navigates. The framework includes the following modules that will be defined by the indoor navigation system developers: 1) Positioning module which simulates indoor localization techniques and their observed accuracy; 2) Indoor navigation algorithm module that generates the navigation instructions using natural language phrases, and 3) Virtual user model (VUM) that includes human perception and information processing that can understand navigation instructions, perceive the surrounding environment, and act based on this information. The framework also includes a performance analysis module that evaluates the indoor navigation system performance in terms of navigation success rate and route similarity.

In this paper, a novel method named distributed independent component–principal component regression (distributed ICPCR) is proposed to monitor the large-scale non-Gaussian process. First, multiple...

Tomato spotted wilt virus is a wide-spread plant disease in the world. It can threaten thousands of plants with a persistent and propagative manner. Early disease detection is expected to be able to control the disease spread, to facilitate management practice, and further to guarantee accompanying economic benefits. Hyperspectral imaging, a powerful remote sensing tool, has been widely applied in different science fields, especially in plant science domain. Rich spectral information makes disease detection possible before visible disease symptoms showing up. In the paper, a new hyperspectral analysis proximal sensing method based on generative adversarial nets (GAN) is proposed, named as outlier removal auxiliary classifier generative adversarial nets (OR-AC-GAN). It is an all-in-one method, which integrates the tasks of plant segmentation, spectrum classification and image classification. The model focuses on image pixels, which can effectively visualize potential plant disease positions, and keep experts’ attention on these diseased pixels. Meanwhile, this new model can improve the performances of classic spectrum band selection methods, including the maximum variance principle component analysis (MVPCA), fast density-peak-based clustering, and similarity-based unsupervised band selection. Selecting spectrum wavebands reasonably is an important preprocessing step in spectroscopy/hyperspectral analysis applications, which can reduce the computation time for potential in-field applications, affect the prediction results and make the hyperspectral analysis results explainable. In the experiment, the hyperspectral reflectance imaging system covers the spectral range from 395 nm to 1005 nm. The proprosed model makes use of 83 bands to do the analysis. The plant level classification accuracy gets 96.25% before visible symptoms shows up. The pixel prediction false positive rate in healthy plants gets as low as 1.47%. Combining the OR-AC-GAN with three existing band selection algorithms, the performance of these band selection models can be significantly improved. Among them, MVPCA can leverage only 8 spectrum bands to get the same plant level classification accuracy as OR-AC-GAN, and the pixel prediction false positive rate in healthy plants is 1.57%, which is also comparable to OR-AC-GAN. This new model can be potentially transferred to other plant diseases detection applications. Its property to boost the performance of existing band selection methods can also accelerate the in-field applications of hyperspectral imaging technology.

Maize inspection is an important and time-consuming task in the domain of food engineering. The human-based inspection strategy needs to be brought up to date with the rapid developments in the maize industry. In this paper, an automatic maize-inspection machine is proposed. Our proposed machine integrates several new designs in terms of both hardware and software components. First, a gravity-based dual-side camera design expands the machine's field-of-view to evaluate maize kernels more thoroughly. Second, touching kernels are pre-processed using a new k-means clustering guided-curvature method, which can improve the robustness of our machine. Next, a deep convolutional neural network, which has shown promise for application in image processing, is embedded into the system to evaluate maize kernels. In this work, the ResNet, which is a deep convolutional neural network architecture, was trained by fine-tuning with 1632 images. It achieved a 98.2% prediction accuracy for 408 test images, which outperforms existing approaches.

With the continuous expansion of the scale of the power grid and the gradual maturity of the application of drones, drones with the advantages of flexibility and convenience can overcome terrain constraints while reducing manpower and safety risks and can be well qualified for the power inspection work under the large-scale development of the power grid and improve the inspection efficiency. However, the massive amount of data collected by UAV power line inspection relies on the human judgment through the naked eyes of staff, and the recognition efficiency is very low and the accuracy rate is subjectively influenced. In recent years, the gradual introduction of traditional machine learning and deep learning has led to significant improvements in inspection efficiency and accuracy. The autonomous obstacle avoidance technology based on the inherent electromagnetic field characteristics of power lines makes it possible for UAVs to cruise autonomously. Based on a systematic summary of the achieved results, this paper briefly reviews the overall development of both power component detection and autonomous cruise in UAV power line inspection. At the same time, the current problems and future research trends are described, expecting to provide references for further research in this field.

Background Hereditary hearing loss (HHL) is the most common sensory deficit, which highly afflicts humans. With gene sequencing technology development, more variants will be identified and support genetic diagnoses, which is difficult for human experts to diagnose. This study aims to develop a machine learning-based genetic diagnosis model of HHL-related variants of GJB2, SLC26A4 and MT-RNR1. Methods This case-control study included 1898 subjects, among which 1354 were HHL patients and 544 were carriers. Risk assessment models were established based on variants at 144 sites in three genes related to HHL by building six machine learning (ML) models. We compared the ML models with the genetic risk score (GRS) and expert interpretation (EI) to verify the clinical performance. Findings Among the six ML models, the support vector machine (SVM) showed the best performance. For the prediction of HHL-related gene sites in subjects with variants, the area under the receiver operating characteristic (AUC) of the SVM model was 0.803 (0.680–0.814) in the 10-fold stratified cross-validation and 0.751 (0.635–0.779) in external validation. The predicted results were better than both EI and GRS. Furthermore, 11 sites were identified as the smallest feature set that can be accurately predicted. Interpretation The developed SVM model has great potential to be an efficient and effective tool for HHL prediction when high throughput sequencing data are available. Funding This study was supported by the National Key Research and Development Program (2017YFC1001800).

Partial least squares (PLS) and linear regression methods are widely utilized for quality-related fault detection in industrial processes. Standard PLS decomposes the process variables into principal and residual parts. However, as the principal part still contains many components unrelated to quality, if these components were not removed it could cause many false alarms. Besides, although these components do not affect product quality, they have a great impact on process safety and information about other faults. Removing and discarding these components will lead to a reduction in the detection rate of faults, unrelated to quality. To overcome the drawbacks of Standard PLS, a novel method, MI-PLS (mutual information PLS), is proposed in this paper. The proposed MI-PLS algorithm utilizes mutual information to divide the process variables into selected and residual components, and then uses singular value decomposition (SVD) to further decompose the selected part into quality-related and quality-unrelated components, subsequently constructing quality-related monitoring statistics. To ensure that there is no information loss and that the proposed MI-PLS can be used in quality-related and quality-unrelated fault detection, a principal component analysis (PCA) model is performed on the residual component to obtain its score matrix, which is combined with the quality-unrelated part to obtain the total quality-unrelated monitoring statistics. Finally, the proposed method is applied on a numerical example and Tennessee Eastman process. The proposed MI-PLS has a lower computational load and more robust performance compared with T-PLS and PCR.

Commercialized RGB-D and LiDAR cameras have been widely applied in food and agricultural engineering fields. However, the general-use 3D cameras cannot ensure high resolution 3D imaging because of their imaging principles. The accuracy of their generated height map ranges from 1cm – 10cm in the actual measurements, which cannot meet the requirement of accurate object height estimation in the food processing lines, especially for visualizing sub-centimeter food product shape variations. This research customized an active 3D scanning system, which utilized the line scanning method to ensure the scanning speed compared to the dot scanning and to minimize the cross talk in the frame scanning. Different from some industrial level 3D line scanning cameras, the system avoided synchronizing the imaging acquisition and processing line conveyor movement. Instead, to implement the 3D imaging for a static object, a programmable rotational mirror was integrated in the system to reflect the line laser for covering the scanning of the entire field of view. In our experimental setup, for a 5-cm calibration phantom, the standard derivation of height estimation from the system is 0.15mm in a 1m photographic distance, which is superior to commercialized RGB-D cameras including Intel RealSense and Kinect. The customized system can also automatically generate well-registered color and depth image pairs and its idea can easily fit into different food and agricultural applications.

Eddy current testing (ECT) is an effective technique for evaluating depth of metal surface defects. However, in practice, evaluation primarily relies on the experience of an operator and is often carried out by manual inspection. In this article, we address the challenges of automatic depth evaluation of metal surface defects by virtual of state-of-the-art deep learning (DL) techniques. The main contributions are threefold. First, a highly integrated portable ECT device is developed, taking the advantage of an advanced field-programmable gate array (Zynq-7020 system on chip) and provides fast data acquisition and in-phase/quadrature demodulation. Second, a dataset, termed metal defects of different depths by ECT (MDDECT), is constructed using the ECT device by human operators and made openly available. It contains 48000 scans from 18 defects of different depths and liftoffs. Third, the depth evaluation problem is formulated as a time series classification problem, and various state-of-the-art 1-D residual convolutional neural networks are trained and evaluated on the MDDECT dataset. A 38-layer 1-D ResNeXt achieves an accuracy of 93.58% in discriminating the surface defects in a stainless steel sheet with depths from 0.3 to 2.0 mm in the resolution of 0.1 mm. In addition, the results show that the trained ResNeXt1D-38 model is immune to liftoff signals.

Data-based process monitoring methods have received tremendous attention in recent years, and modern industrial process data often exhibit dynamic and nonlinear characteristics. Traditional autoencoders, such as stacked denoising autoencoders (SDAEs), have excellent nonlinear feature extraction capabilities, but they ignore the dynamic correlation between sample data. Feature extraction based on manifold learning using spatial or temporal neighbors has been widely used in dynamic process monitoring in recent years, but most of them use linear features and do not take into account the complex nonlinearities of industrial processes. Therefore, a fault detection scheme based on temporal-spatial neighborhood enhanced sparse autoencoder is proposed in this paper. Firstly, it selects the temporal neighborhood and spatial neighborhood of the sample at the current time within the time window with a certain length, the spatial similarity and time serial correlation are used for weighted reconstruction, and the reconstruction combines the current sample as the input of the sparse stack autoencoder (SSAE) to extract the correlation features between the current sample and the neighborhood information. Two statistics are constructed for fault detection. Considering that both types of neighborhood information contain spatial-temporal structural features, Bayesian fusion strategy is used to integrate the two parts of the detection results. Finally, the superiority of the method in this paper is illustrated by a numerical example and the Tennessee Eastman process.

Multi-view data can represent objects from different perspectives and thus provide complementary information for data analysis. A topic of great importance in multi-view learning is to locate a low-dimensional latent subspace, where common semantic features are shared by multiple data sets. However, most existing methods ignore uncorrelated items (i.e., view-specific features) and may cause semantic bias during the process of common feature learning. In this article, we propose a non-negative correlated and uncorrelated feature co-learning (CoUFC) method to address this concern. More specifically, view-specific (uncorrelated) features are identified for each view when learning the common (correlated) feature across views in the latent semantic subspace. By eliminating the effects of uncorrelated information, useful inter-view feature correlations can be captured. We design a new objective function in CoUFC and derive an optimization approach to solve the objective with the analysis on its convergence. Experiments on real-world sensor, image, and text data sets demonstrate that the proposed method outperforms the state-of-the-art multiview learning methods.

Networked telerobots are operated by humans through remote interactions and have found applications in hazardous and/or unstructured environments, such as outer space, underwater, telesurgery, manufacturing, and production. In precision agricultural robotics, target monitoring, recognition, and detection is a complex task, requiring expertise. Hence, they can be more efficiently performed by collaborative human-robot systems. A HUB is an online portal, a platform to create and share scientific and advanced computing tools. Multiple HUBs have been developed recently for scientific research objectives. HUB-CI is a tool developed by PRISM Center at Purdue University to enable cyber-augmented collaborative interactions over cyber-supported complex systems. The research reported here, sponsored in part by BARD, implements the HUB-CI model to improve the Collaborative Intelligence (CI) of an agricultural telerobotic system for early detection of anomalies in pepper plants grown in greenhouses. Specific CI tools developed for this purpose include: (1) spectral image segmentation for detecting and mapping to anomalies in growing pepper plants; (2) workflow/task administration protocols for managing/coordinating interactions between software, hardware, and human agents, engaged in the monitoring and detection, which would reliably lead to precise, responsive mitigation. These CI tools aim to minimize interactions’ conflicts and errors that may impede detection effectiveness, thus reducing crops’ quality. On-going lab and field experiments indicate that planned and optimized collaborative interactions with HUB-CI (as opposed to ad-hoc or fixed-structured interactions) yield significantly fewer errors and better detection. Hence, it improves system productivity of precise monitoring for healthy growth of pepper plants in greenhouses.

In this article, a Collaborative Control Protocol for Robotic and Cyber-Physical System (CCP-CPS) is presented. CCP-CPS, which enables an application of robotics in a CPS system for smart and precision agriculture (PA), aims to monitor and identify stresses in greenhouse crops by a hyperspectral analysis method. Roles of CCP-CPS are to assign tasks to agents, identify and resolve conflicts and errors in the system, and enable a more effective collaboration and interaction among agents in CPS, compared to traditional non-collaborative and non-CPS approach. Collaborative Control Theory (CCT) is utilized for two system levels; protocol and agent level (CCP level), and CPS and environment level (CPS level). We use two case studies to test and validate our method with alternative approaches. The results from computer simulation show that 1) CCP-CPS can identify the highest number of greenhouse locations containing stresses, 2) CCP-CPS can utilize available resources (time) effectively, and 3) CCP-CPS can respond to an emergency stress situation faster and have more tolerance capability with system conflicts and errors, by having human integration and cyber-augmented greenhouse system, than other monitoring systems.

An automated high-speed strawberry calyx removal machine was designed, built, tested, and evaluated. The three main components of the machine consisted of 1) a strawberry loading and orientation conveyor, 2) a color-based machine vision section for strawberry feature identification, and 3) a synchronized multi-waterjet knife calyx removal system. An overview of the machine as well as a description of the working principles of each component is included. A full-scale model of this machine was evaluated through a 12-week pilot study, during which the machine processed over 70 metric tons of strawberries. Results indicated that the machine could produce an average calyx-free strawberry weight yield of 49.6 percent at a rate of 2270 kg/hr. Furthermore, it was seen that strawberry size had a significant effect on machine efficacy.

Face recognition technology, as a biometric recognition technology, is very mature and has many applications. It achieves in-depth applications in smart campus systems, such as classroom attendance, classroom behavior analysis, and smart restaurants. Using human faces as the face data foundation, computer vision and image processing technologies are applied to research and implement face recognition. Based on the principal component analysis (PCA) theory, this paper analyzed the characteristics of face data, studied the face recognition algorithm. Considering the LBP and SVM algorithm, an improved PCA face recognition algorithm was proposed. Through comparative experiments, the results show that the proposed algorithm can improve the accuracy of face recognition.

In eddy current testing (ECT), feature extraction methods play an important role in the detection and classification of defects. Convolutional sparse coding (CSC) has gained attentions in recent years as this can provide a versatile framework in the description of signal and rich options for effective discrimination and classification algorithms. In this paper, we propose a feature extraction method which for the first time applies the CSC model for ECT. The local dictionary in the model is trained using signal segments corresponding to scans of defects. The proposed algorithm has achieved 98% accuracy in terms of the recovery of the location of defect signal segments. The recovered coefficients are adopted as unique features which eventually correspond to the profiles of the defect.

One challenge in decoding EEG-based motor imagery for brain computer interface (BCI) is the inter-session non-stationarities due to factors like subject fatigue or electrode placements. This non stationarity leads to lower decoding accuracy, especially if data from the training and testing sessions are collected on separate days. An existing technique termed data space adaptation (DSA) transforms EEG data such that the distribution of test and training data are aligned. Decoding accuracy has been shown to improve when transformed data was used for classification instead of the original data. In this study, space transformed data from six subjects were fed into a Convolutional Neural Network (CNN) and a Filter Bank Common Spatial Pattern (FBCSP) model. The results show that when no adaptation was applied, there was on average a 2.8% improvement in decoding accuracy when CNN was used compared to FBCSP. When DSA was used in conjunction with FBCSP, the majority of the subjects had improved decoding accuracy. However, DSA together with CNN on average yielded a lower decoding accuracy compared to CNN alone. Hence the results suggest that when decoding non-stationary EEG data for motor imagery, DSA should be used only in conjunction with FBCSP, but not when CNN is used as a decoding model.

With the availability of multi-object spectrometers and the designing \& running of some large scale sky surveys, we are obtaining massive spectra. Therefore, it becomes more and more important to deal with the massive spectral data efficiently and accurately. This work investigated the classification problem of stellar spectra under the assumption that there is no perfect absolute flux calibration, for example, the spectra from Guoshoujing Telescope (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, LAMOST). The proposed scheme consists of the following two procedures: Firstly, a spectrum is normalized based on a 17th polynomial fitting; Secondly, a random forest (RF) is utilized to classifying the stellar spectra. The experiments on four stellar spectral libraries show that RF has a good classification performance. This work also studied the spectral feature evaluation problem based on RF. The evaluation is helpful in understanding the results of the proposed stellar classification scheme and exploring its potential improvements in future., 10 pages, 8 figures,2 tables

Traditional monitoring methods are trained with normal data and map the process variables into latent variables directly. However, for these methods, the process variables would become intertwined in the latent variables, which results in that the fluctuations of process variables would be submerged in noise or neutralized in latent variables space. In order to address the submergence and neutralization problems, a novel algorithm load weighted denoising autoencoder (LWDAE) is proposed. According to the direction and magnitude of online data, the loading matrix of LWDAE is weighted to highlight the useful information of both training data and online data in latent variables space. In addition, to reduce the effect of noise on weighting matrix, LWDAE modifies the loss function by adding two new regularizations and revises the calculation logic of weighting matrix to consider the successive samples. Case studies of continuous stirred tank reactor demonstrate the effectiveness of LWDAE.

Using multi-source sensing data based on the Internet of Things (IoT) with artificial intelligence and big data processing technology to achieve predictive maintenance of mechanical equipment can remarkably improve the service life of the machine and reduce labor costs when diagnosing mechanical faults, and it has become a highly relevant research topic. In this paper, the multi-source sensing data fusion models and fusion algorithms are studied and discussed. First, the Joint Directors of Laboratories (JDL) fusion model and the Hierarchical fusion model are compared and analyzed. Then, various types of fusion algorithms based on Neural Networks and Deep Learning, including Dempster-Shafer (D-S) evidence theory and their applications in mechanical fault diagnosis and fault prediction, are studied and compared. The findings reveal that exploring and designing a more intelligent fusion model incorporating the beneficial characteristics of different fusion algorithms are challenging and have a certain value for promoting the development of mechanical fault diagnosis and prediction.