Investigating zero-state and steady-state performance of MEWMA-CoDa control chart using variable sampling interval.

Traditional process monitoring control charts (CCs) focused on sampling methods using fixed sampling intervals (FSIs). The variable sampling intervals (VSIs) scheme is receiving increasing attention, in which the sampling interval (SI) length varies according to the process monitoring statistics. A shorter SI is considered when the process quality indicates the possibility of an out-of-control (OOC) situation; otherwise, a longer SI is preferred. The VSI multivariate exponentially moving average for compositional data (VSI-MEWMACoDa) CC based on a coordinate representation using isometric log-ratio (ilr) transformation is proposed in this study. A methodology is proposed to obtain the optimal parameters by considering the zero-state (ZS) average time to signal (ZATS) and the steady-state (SS) average time to signal (SATS). The statistical performance of the proposed CC is evaluated based on a continuous-time Markov chain (CTMC) method for both cases, the ZS and the SS using a fixed value of in-control (IC) ATS0. Simulation results demonstrate that the VSI-MEWMACoDa CC has significantly decreased the OOC average time to signal (ATS) than the FSIMEWMACoDa CC. Moreover, it is found that the number of variables (d) has a negative impact on the ATS of the VSI-MEWMACoDa CC, and the subgroup size (n) has a mildly positive impact on the ATS of the VSI-MEWMACoDa CC. At the same time, the SATS of the VSI-MEWMACoDa CC is less than the ZATS of the VSI-MEWMACoDa CC for all the values of n and d. The proposed VSI-MEWMACoDa CC under steady-State performs effectively compared to its competitors, such as the FSI-MEWMACoDa CC, the VSI-T2CoDa CC and the FSI-T2CoDa CC. An example of an industrial problem from a plant in Europe is also given to study the statistical significance of the VSI-MEWMACoDa CC.

Guided multi-scale refinement network for camouflaged object detection.

The purpose of camouflaged object detection (COD) is to identify the hidden camouflaged object in an input image. Compared with other binary segmentation tasks like salient object detection, COD needs to deal with more complex scenes, such as low contrast, similar foreground and background. In this work, we proposed a novel guided multi-scale refinement network for COD. Specifically, we first design a global perception module for coarse localization by stacking multi-scale residual block on the top of the backbone in a recurrent manner. Then, we propose the guided multi-scale refinement module to refine such initial prediction progressively, which is combined with multi-level side-output features in a prediction-to-feature fusion strategy. By plugging into side-output features for multi-scale guidance, the missing object parts and false detection can be well remedied. Experimental results show that our proposed network can more accurately locate the camouflaged object and salient object with sharpened details than existing state-of-the-art approaches. In addition, our model is also very efficient and compact, which enables potential real-world applications.

A one-sided exponentially weighted moving average control chart for time between events.

Exponentially weighted moving average (EWMA) control charts for time-between-events (TBE) are commonly suggested to monitor high-quality processes for the early detection of process deteriorations. In this study, an enhanced one-sided EWMA TBE scheme is developed for rapid detection of increases or decreases in the process mean. The use of the truncation method helps to improve the sensitivity of the proposed scheme in the process mean detection. Moreover, by taking the effects of parameter estimation into account, the proposed scheme with estimated parameters is also investigated. Both the average run length (ARL) and standard deviation of run length (SDRL) performances of the proposed scheme with known and estimated parameters are studied using the Markov chain method, respectively. Furthermore, an optimal design procedure is developed for the recommended one-sided EWMA TBE chart based on ARL. Numerical results show that the proposed optimal one-sided EWMA TBE chart is more sensitive than the existing optimal one-sided exponential EWMA chart in monitoring both upward and downward mean shifts. Meanwhile, it also performs better than the existing comparative scheme in resisting the effect of parameter estimation. Finally, two illustrative examples are considered to show the implementation of the proposed scheme for simulated and real datasets.

Investigation of Cement Prepared with Microencapsulated Microorganisms.

Cracks in underground rock masses cause gas leakage, seepage, and water inflow. To realize calcium carbonate deposition and mineralization filling in rock cracks, microencapsulated bacterial spores were prepared by an oil phase separation method. To optimize the microorganism growth conditions, the effects of microcapsules with various pHs, particle sizes, and amounts on microcrack self-healing were investigated through an orthogonal test, and the best conditions for repairing the cracks using microencapsulated Bacillus sphaericus were obtained. Infrared analysis and scanning electron microscopy were used to observe the morphological characteristics and coating performance of the microcapsules. The results showed that the microcapsules contained functional groups in the core and wall materials. The surfaces of the microcapsules prepared by the test were rough, which was beneficial for adhesion onto the fracture surface. X-ray diffraction analysis, X-ray photoelectron spectroscopy, and thermal analysis were conducted. The results showed that the microcapsules with pH = 8 and a particle size of 100 µm had the highest thermal decomposition temperature and the best thermal stability. The elements of the core and wall materials were detected in the microcapsules, and the coating had a beneficial effect. The compression and acoustic emission tests of the specimens embedding microbial capsules with different contents under different working conditions revealed that the two fractures of the specimen were due to the rupture of the microcapsule and the rupture of the rock specimen, indicating the best mechanical triggering properties and compressive properties of the microcapsule.

Assisting scalable diagnosis automatically via CT images in the combat against COVID-19.

The pandemic of Coronavirus Disease 2019 (COVID-19) is causing enormous loss of life globally. Prompt case identification is critical. The reference method is the real-time reverse transcription PCR (RT-PCR) assay, whose limitations may curb its prompt large-scale application. COVID-19 manifests with chest computed tomography (CT) abnormalities, some even before the onset of symptoms. We tested the hypothesis that the application of deep learning (DL) to 3D CT images could help identify COVID-19 infections. Using data from 920 COVID-19 and 1,073 non-COVID-19 pneumonia patients, we developed a modified DenseNet-264 model, COVIDNet, to classify CT images to either class. When tested on an independent set of 233 COVID-19 and 289 non-COVID-19 pneumonia patients, COVIDNet achieved an accuracy rate of 94.3% and an area under the curve of 0.98. As of March 23, 2020, the COVIDNet system had been used 11,966 times with a sensitivity of 91.12% and a specificity of 88.50% in six hospitals with PCR confirmation. Application of DL to CT images may improve both efficiency and capacity of case detection and long-term surveillance.

Sparse Representation-Based Discriminative Metric Learning for Brain MRI Image Retrieval.

Magnetic resonance imaging (MRI) can have a good diagnostic function for important organs and parts of the body. MRI technology has become a common and important disease detection technology. At the same time, medical imaging data is increasing at an explosive rate. Retrieving similar medical images from a huge database is of great significance to doctors' auxiliary diagnosis and treatment. In this paper, combining the advantages of sparse representation and metric learning, a sparse representation-based discriminative metric learning (SRDML) approach is proposed for medical image retrieval of brain MRI. The SRDML approach uses a sparse representation framework to learn robust feature representation of brain MRI, and uses metric learning to project new features into the metric space with matching discrimination. In such a metric space, the optimal similarity measure is obtained by using the local constraints of atoms and the pairwise constraints of coding coefficients, so that the distance between similar images is less than the given threshold, and the distance between dissimilar images is greater than another given threshold. The experiments are designed and tested on the brain MRI dataset created by Chang. Experimental results show that the SRDML approach can obtain satisfactory retrieval performance and achieve accurate brain MRI image retrieval.

On the conditional performance of the synthetic chart with unknown process parameters using the exceedance probability criterion.

Recent researches on the control charts with unknown process parameters have noticed the large variability in the conditional in-control average run length (ARL) performance of control charts, especially when a small number of Phase I samples is used to estimate the process parameters. Some research works have been conducted on the conditional ARL performance of different types of control charts. In this paper, by simulating the empirical distribution of the conditional ARL and especially using the exceedance probability criterion (EPC), we study the conditional ARL performance of the synthetic [Formula: see text] chart. Our results show that a large amount of Phase I samples is needed to obtain a specified EPC of the synthetic chart. For the available number of Phase I samples, the control limits of the synthetic chart are adjusted using the EPC method to improve its conditional in-control performance. It is shown that, for small mean shift sizes, a tradeoff should be made between the conditional in-control and out-of-control performances. For moderate to large shifts, the conditional performance of the synthetic chart using the adjusted control limits is generally satisfied. By comparing the results with the ones using the bootstrap approach, it can also be concluded that the conditional performances of both approaches are comparable. While the method proposed in this paper requires much less computation work than the bootstrap approach.

Reverse Attention Based Residual Network for Salient Object Detection.

Benefiting from the quick development of deep convolutional neural networks, especially fully convolutional neural networks (FCNs), remarkable progresses have been achieved on salient object detection recently. Nevertheless, these FCNs based methods are still challenging to generate high resolution saliency maps, and also not applicable for subsequent applications due to their heavy model weights. In this paper, we propose a compact and efficient deep network with high accuracy for salient object detection. Firstly, we propose two strategies for initial prediction, one is a new designed multi-scale context module, the other is incorporating hand-crafted saliency priors. Secondly, we employ residual learning to refine it progressively by only learning the residual in each side-output, which can be achieved with few convolutional parameters, therefore leads to high compactness and high efficiency. Finally, we further design a novel reverse attention block to guide side-output residual learning in a top-down manner. Specifically, the current predicted salient regions are erased from each side-output feature, thus the missing object parts and details can be efficiently learned from these unerased regions, which results in high resolution and accuracy. Extensive experimental results on seven benchmark datasets demonstrate that the proposed network performs favorably against the state-of-the-art methods, and with advantages in terms of simplicity, efficiency and model size.

Embedding Attention and Residual Network for Accurate Salient Object Detection.

Salient object detection is usually used as a preprocessing step to facilitate a variety of subsequent applications which should take little time cost. With the quick development of deep learning recently, profound progresses have been made to achieve a new state-of-the-art performance. However, the learned features of the existing deep learning-based methods are not accurate enough thus leading to unsatisfactory detection in complex scenes, such as low contrast or very similar between salient object and background region and multiple (small) salient objects with diverse characteristics. In addition, some post-processing techniques are usually needed for refinement, which is time consuming. To address these issues, this paper presents an efficient fully convolutional salient object detection network. Specifically, we first introduce a visual attention mechanism to guide feature learning in side output layers. In detail, attention weight is employed in a top-down manner which can bridge high level semantic information to help shallow layers better locate salient objects and also filter out noisy response in the background region. Second, we propose a residual refinement network to fuse the learned multilevel features gradually. Not to simply add or concatenate them step by step as previous works, we introduce a second-order term into element-wise addition to learn stage-wise residual features for refinement. Such a second-order term not only benefits efficient gradient propagation but also increases network nonlinearity. Extensive experiments on seven standard benchmarks demonstrate that the proposed approach achieves consistently superior performance and performs well on small salient object detection in comparison with the very recent state-of-the-arts, especially in the metric of structure-measure.

Efficient Total Synthesis of Lissodendrin B, 2-Aminoimidazole Marine Alkaloids Isolated from Lissodendoryx (Acanthodoryx) Fibrosa.

Lissodendrin B is a 2-aminoimidazole alkaloid bearing a (p-hydroxyphenyl) glyoxal moiety that was isolated from the Indonesian sponge Lissodendoryx (Acanthodoryx) fibrosa. We reported the first efficient total synthesis of Lissodendrin B. The precursor 4,5-disubstituted imidazole was obtained through Suzuki coupling and Sonogashira coupling reactions from 4-iodoimidazole. C2-azidation and reduction of the azide then provided the core structures of Lissodendrin B. Subsequent triple-bond oxidation, demethylation, and deacetylation gave the final product. The synthesis approach consists of ten steps with an overall yield of 1.1% under mild reaction conditions, and it can be applied for future analog synthesis and biological studies.