Search

Background: Atherosclerotic cardiovascular disease is the leading cause of death worldwide. Early detection of carotid atherosclerosis can prevent the progression of cardiovascular disease. Many (semi‐) automatic methods have been designed for the segmentation of carotid vessel wall and the diagnosis of carotid atherosclerosis (i.e., the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis) on black blood magnetic resonance imaging (BB‐MRI). However, most of these methods ignore the intrinsic correlation among different tasks on BB‐MRI, leading to limited performance. Purpose: Thus, we model the intrinsic correlation among the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis tasks on BB‐MRI by using the multi‐task learning technique and propose a gated multi‐task network (GMT‐Net) to perform three related tasks in a neural network (i.e., carotid artery lumen segmentation, outer wall segmentation, and carotid atherosclerosis diagnosis). Methods: In the proposed method, the GMT‐Net is composed of three modules, including the sharing module, the segmentation module, and the diagnosis module, which interact with each other to achieve better learning performance. At the same time, two new adaptive layers, namely, the gated exchange layer and the gated fusion layer, are presented to exchange and merge branch features. Results: The proposed method is applied to the CAREII dataset (i.e., 1057 scans) for the lumen segmentation, the outer wall segmentation, and the carotid atherosclerosis diagnosis. The proposed method can achieve promising segmentation performances (0.9677 Dice for the lumen and 0.9669 Dice for the outer wall) and better diagnosis accuracy of carotid atherosclerosis (0.9516 AUC and 0.9024 Accuracy) in the "CAREII test" dataset (i.e., 106 scans). The results show that the proposed method has statistically significant accuracy and efficiency. Conclusions: Even without the intervention of reviewers required for the previous works, the proposed method automatically segments the lumen and outer wall together and diagnoses carotid atherosclerosis with high performance. The proposed method can be used in clinical trials to help radiologists get rid of tedious reading tasks, such as screening review to separate normal carotid arteries from atherosclerotic arteries and to outline vessel wall contours. [ABSTRACT FROM AUTHOR]

Identification and detection of thin-cap fibroatheroma (TCFA) from intravascular optical coherence tomography (IVOCT) images is critical for treatment of coronary heart diseases. Recently, deep learning methods have shown promising successes in TCFA identification. However, most methods usually do not effectively utilize multi-view information or incorporate prior domain knowledge. In this paper, we propose a multi-view contour-constrained transformer network (MVCTN) for TCFA identification in IVOCT images. Inspired by the diagnosis process of cardiologists, we use contour constrained self-attention modules (CCSM) to emphasize features corresponding to salient regions (i.e., vessel walls) in an unsupervised manner and enhance the visual interpretability based on class activation mapping (CAM). Moreover, we exploit transformer modules (TM) to build global-range relations between two views (i.e., polar and Cartesian views) to effectively fuse features at multiple feature scales. Experimental results on a semi-public dataset and an in-house dataset demonstrate that the proposed MVCTN outperforms other single-view and multi-view methods. Lastly, the proposed MVCTN can also provide meaningful visualization for cardiologists via CAM. [ABSTRACT FROM AUTHOR]

Purpose: Early detection of carotid atherosclerosis on the vessel wall (VW) magnetic resonance imaging (MRI) (VW‐MRI) images can prevent the progression of cardiovascular disease. However, the manual inspection process of the VW‐MRI images is cumbersome and has low reproducibility. Therefore in this paper, by using the convolutional neural networks (CNNs), we develop a deep morphology aided diagnosis (DeepMAD) network for automated segmentation of the VW of carotid artery and for automated diagnosis of the carotid atherosclerosis with the black‐blood (BB) VW‐MRI (i.e., the T1‐weighted MRI) in a slice‐by‐slice manner. Methods: The proposed DeepMAD network consists of a segmentation subnetwork and a diagnosis subnetwork for performing the segmentation and diagnosis tasks on the BB‐VW‐MRI images, where the manual labeled lumen area, the manual labeled outer wall area and the manual labeled lesion Types based on the modified American Heart Association (AHA) criteria are used as the ground‐truth. Specifically, a deep U‐shape CNN with a weighted fusion layer is designed as the segmentation subnetwork, where the lumen area and the outer wall area can be simultaneously segmented under the supervision of the triple Dice loss to provide the vessel wall map as morphological information. Then, the image stream from the BB‐VWMRI image and the morphology stream from the obtained vessel wall map are extracted from two deep CNNs and combined to obtain the diagnosis results of atherosclerosis in the diagnosis subnetwork. In addition, the triple input set is formed by three carotid regions of interest (ROIs) from three consecutive slices of the MRI sequence and input to the DeepMAD network, where the first and last slices used as additional adjacent slices to provide 2.5D spatial information along the carotid artery centerline for the intermediate slice, which is the target slice for segmentation and diagnosis in the study. Results: Compared to other existing methods, the DeepMAD network can achieve promising segmentation performances (0.9594 Dice for the lumen and 0.9657 Dice for the outer wall) and better diagnosis Accuracy of the carotid atherosclerosis (0.9503 AUC and 0.8916 Accuracy) in the test dataset (including invisible subjects) from same source as the training dataset. In addition, the trained DeepMAD model can be successfully transferred to another test dataset for segmentation and diagnosis tasks with remarkable performance (0.9475 Dice for the lumen and 0.9542 Dice for the outer wall, 0. 9227 AUC and 0.8679 Accuracy for diagnosis). Conclusions: Even without the intervention of reviewers required for previous works, the proposed DeepMAD network automatically segments the lumen and the outer wall together and diagnoses the carotid atherosclerosis with high performances. The DeepMAD network can be used in clinical trials to help radiologists get rid of tedious reading tasks, such as screening review to separate the normal carotid from the atherosclerotic arteries and outlining the vessel wall contours. [ABSTRACT FROM AUTHOR]

We propose a new subspace-based localization of far-field (FF) and near-field (NF) narrowband signals (LOFNS) without eigendecomposition impinging on a symmetrical uniform linear array, where the oblique projection operator is utilized to isolate the NF signals from the FF ones, and the procedures of computationally burdensome eigendecomposition are not required in the estimation of the NF and FF location parameters and the computation of oblique projection operator. As a measure against the impact of finite array data, an alternating iterative scheme is presented to improve the estimation accuracy of the oblique projection operator and, hence, that of the NF location parameters, where the “saturation behavior” encountered in most of localization methods is overcome. Furthermore, the statistical analysis of the proposed LOFNS is studied, and the asymptotic mean-squared-error expressions of the estimation errors are derived for the FF and NF location parameters. Finally, the effectiveness and the theoretical analysis of the proposed LOFNS are substantiated through numerical examples, and the simulation results demonstrate that the LOFNS provides remarkable and satisfactory estimation performance for both the NF and FF signals compared with some existing localization methods even with eigendecomposition. [ABSTRACT FROM AUTHOR]

This paper deals with the problem of tracking the two-dimensional (2-D) direction-of-arrivals (DOAs) of multiple moving targets with crossover points on their trajectories, and we propose a new computationally efficient cross-correlation based 2-D DOA estimation with automatic pair-matching (CODEC) method for noncoherent narrowband signals impinging on the L-shaped sensor array structured by two uniform linear arrays (ULAs) with omnidirectional sensors. The effectiveness of the proposed method and the theoretical analysis are substantiated through numerical examples. [ABSTRACT FROM AUTHOR]

In order to mitigate the effect of additive noises and reduce the computational burden, we propose a new computationally efficient cross-correlation based two-dimensional (2-D) direction-of-arrivals (DOAs) estimation (CODE) method for noncoherent narrowband signals impinging on the L-shaped sensor array structured by two uniform linear arrays (ULAs). By estimating the azimuth and elevation angles independently with a one-dimensional (1-D) subspace-based estimation technique without eigendecomposition, where the null spaces are obtained through a linear operation of the matrices formed from the cross-correlation matrix between the received data of two ULAs, then the pair-matching of estimated azimuth and elevation angles is accomplished by searching the minimums of a cost function of the azimuth and elevation angles, where the computationally intensive and time-consuming eigendecomposition process is avoided. Further the asymptotic mean-square-error (MSE) expressions of the azimuth and elevation estimates are derived. The effectiveness of proposed method and the theoretical analysis are verified through numerical examples, and it is shown that the proposed CODE method performs well at low signal-to-noise ratio (SNR) and with a small number of snapshots. [ABSTRACT FROM AUTHOR]

In this paper, we propose a computationally simple and efficient subspace-based adaptive method for estimating directions-of-arrival (AMEND) for multiple coherent narrowband signals impinging on a uniform linear array (ULA), where the previously proposed QR-based method is modified for the number determination, a new recursive least-squares (RLS) algorithm is proposed for null space updating, and a dynamic model and the Luenberger state observer are employed to solve the estimate association of directions automatically. The statistical performance of the RLS algorithm in stationary environment is analyzed in the mean and mean-squares senses, and the mean-square-error (MSE) and mean-square derivation (MSD) learning curves are derived explicitly. Furthermore, an analytical study of the RLS algorithm is carried out to quantitatively compare the performance between the RLS and least-mean-square (LMS) algorithms in the steady-state. The theoretical analyses and effectiveness of the proposed RLS algorithm are substantiated through numerical examples. [ABSTRACT FROM PUBLISHER]

A computationally simple direction-of-arrival (DOA) estimation method with good statistical performance is attractive in many practical applications of array processing. In this paper, we propose a new computationally efficient subspace-based method without eigendecomposition (SUMWE) for the coherent narrowband signals impinging on a uniform linear array (ULA) by exploiting the array geometry and its shift invariance property. The coherency of incident signals is decorrelated through subarray averaging, and the null space is obtained through a linear operation of a matrix formed from the cross-correlations between some sensor data, where the effect of additive noise is eliminated. Consequently, the DOAs can be estimated without performing eigendecomposition, and there is no need to evaluate all correlations of the array data. Furthermore, the SUMWE is also suitable for the case of partly coherent or incoherent signals, and it can be extended to the spatially correlated noise by choosing appropriate subarrays. The statistical analysis of the SUMWE is studied, and the asymptotic mean-squared-error (MSE) expression of the estimation error is derived. The performance of the SUMWE is demonstrated, and the theoretical analysis is substantiated through numerical examples. It is shown that the SUMWE is superior in resolving closely spaced coherent signals with a small number of snapshots and at low signal-to-noise ratio (SNR) and offers good estimation performance for both uncorrelated and correlated incident signals. [ABSTRACT FROM AUTHOR]

Presents information on a study which addressed the problem of directions-of-arrival (DOA) estimation of coherent narrowband signals impinging on a uniform linear array when the number of signals is unknown using linear prediction model. Problem formulation; Optimal regularization approach for corrected least squares estimation; Data-based iterative algorithm for DOA estimation; Conclusions.

Detection of the directions of arrival (DOA) and the number of impinging signals is an essential function in many array antenna beamforming techniques. A new approach is presented here for estimating the DOA and the number of desired signals in array antennas. The new algorithm exploits the cyclostationarity of the modulated signals, which are disturbed by unknown interferences and noises, to suppress undesired signals. In this approach, the outputs of antenna sensors are applied to a linear prediction model and the cyclic correlation is calculated to utilize the cyclostationarity of the desired signals. Also the error of estimation of the cyclic correlation function in the linear prediction model is evaluated and the DOA of the desired signals is correctly estimated. Results are compared with the results of conventional approaches, such as cyclic MUSIC, in the presence of interference and at low signal-to-noise ratios. Numerical examples are presented to show the effectiveness of the proposed method. © 1999 Scripta Technica, Electron Comm Jpn Pt 1, 82(10): 29–39, 1999 [ABSTRACT FROM AUTHOR]

Background Purpose Methods Results Conclusions Liver lesions mainly occur inside the liver parenchyma, which are difficult to locate and have complicated relationships with essential vessels. Thus, preoperative planning is crucial for the resection of liver lesions. Accurate segmentation of the hepatic and portal veins (PVs) on computed tomography (CT) images is of great importance for preoperative planning. However, manually labeling the mask of vessels is laborious and time‐consuming, and the labeling results of different clinicians are prone to inconsistencies. Hence, developing an automatic segmentation algorithm for hepatic and PVs on CT images has attracted the attention of researchers. Unfortunately, existing deep learning based automatic segmentation methods are prone to misclassifying peripheral vessels into wrong categories.This study aims to provide a fully automatic and robust semantic segmentation algorithm for hepatic and PVs, guiding subsequent preoperative planning. In addition, to address the deficiency of the public dataset for hepatic and PV segmentation, we revise the annotations of the Medical Segmentation Decathlon (MSD) hepatic vessel segmentation dataset and add the masks of the hepatic veins (HVs) and PVs.We proposed a structure with a dual‐stream encoder combining convolution and Transformer block, named Dual‐stream Hepatic Portal Vein segmentation Network, to extract local features and long‐distance spatial information, thereby extracting anatomical information of hepatic and portal vein, avoiding misdivisions of adjacent peripheral vessels. Besides, a multi‐scale feature fusion block based on dilated convolution is proposed to extract multi‐scale features on expanded perception fields for local features, and a multi‐level fusing attention module is introduced for efficient context information extraction. Paired t‐test is conducted to evaluate the significant difference in dice between the proposed methods and the comparing methods.Two datasets are constructed from the original MSD dataset. For each dataset, 50 cases are randomly selected for model evaluation in the scheme of 5‐fold cross‐validation. The results show that our method outperforms the state‐of‐the‐art Convolutional Neural Network‐based and transformer‐based methods. Specifically, for the first dataset, our model reaches 0.815, 0.830, and 0.807 at overall dice, precision, and sensitivity. The dice of the hepatic and PVs are 0.835 and 0.796, which also exceed the numeric result of the comparing methods. Almost all the p‐values of paired t‐tests on the proposed approach and comparing approaches are smaller than 0.05. On the second dataset, the proposed algorithm achieves 0.749, 0.762, 0.726, 0.835, and 0.796 for overall dice, precision, sensitivity, dice for HV, and dice for PV, among which the first four numeric results exceed comparing methods.The proposed method is effective in solving the problem of misclassifying interlaced peripheral veins for the HV and PV segmentation task and outperforming the comparing methods on the relabeled dataset. [ABSTRACT FROM AUTHOR]

In-memory error correction code (ECC) is a promising technique to improve the yield and reliability of high density memory design. However, the use of in-memory ECC poses a new problem to memory repair analysis algorithm, which has not been explored before. This article first makes a quantitative evaluation and demonstrates that the straightforward algorithms for memory with redundancy and in-memory ECC have serious deficiency on either repair rate or repair analysis speed. Accordingly, an optimal repair analysis algorithm that leverages preprocessing/filter algorithms, hybrid search tree, and depth-first search strategy is proposed to achieve low computational complexity and optimal repair rate in the meantime. In addition, a heuristic repair analysis algorithm that uses a greedy strategy is proposed to efficiently find repair solutions. Experimental results demonstrate that the proposed optimal repair analysis algorithm can achieve optimal repair rate and increase the repair analysis speed by up to 105 × compared with the straightforward exhaustive search algorithm. The proposed heuristic repair analysis algorithm is approximately 28 percent faster than the proposed optimal algorithm, at the expense of 5.8 percent repair rate loss. [ABSTRACT FROM AUTHOR]

In the human visual system, visual saliency perception is a rapid pre-attention processing mechanism, which can benefit myriad visual tasks, such as segmentation, localization, and detection. While most research is devoted to saliency detection on 2D images and 3D meshes, little work has been performed for efficient saliency detection on 3D point clouds. In this paper, we present a novel point clouds saliency detection method by employing principal component analysis (PCA) in a sigma-set feature space. In this method, we first construct local shape descriptors based on covariance matrices for saliency detection, considering that covariance matrices can naturally model nonlinear correlations of different low-level compact and rotational-invariant features. Secondly, we transform these covariance matrices to vector descriptors in Euclidean vector space by applying the sigma-point technique, which keeps the inner statistics of regions of 3D point clouds. Based on our informative descriptors, PCA is employed in the descriptor space for identifying saliency patterns in a point cloud. Our method shows its advantages of being structure-sensitive, capturing geometry information and computationally efficient. Experimental results demonstrate that our method achieves good performance without using any topological information. [ABSTRACT FROM AUTHOR]

The mutant strains of COVID-19 caused a global explosion of infections, including many cities of China. In 2020, a hybrid AI model was proposed by Zheng et al., which accurately predicted the epidemic in Wuhan. As the main part of the hybrid AI model, ISI method makes two important assumptions to avoid over-fitting. However, the assumptions cannot be effectively applied to new mutant strains. In this paper, a more general method, named the multi-weight susceptible-infected model (MSI) is proposed to predict COVID-19 in Chinese Mainland. First, a Gaussian pre-processing method is proposed to solve the problem of data fluctuation based on the quantity consistency of cumulative infection number and the trend consistency of daily infection number. Then, we improve the model from two aspects: changing the grouped multi-parameter strategy to the multi-weight strategy, and removing the restriction of weight distribution of viral infectivity. Experiments on the outbreaks in many places in China from the end of 2021 to May 2022 show that, in China, an individual infected by Delta or Omicron strains of SARS-CoV-2 can infect others within 3–4 days after he/she got infected. Especially, the proposed method effectively predicts the trend of the epidemics in Xi'an, Tianjin, Henan, and Shanghai from December 2021 to May 2022. [ABSTRACT FROM AUTHOR]

Large-scale image classification is a challenging task and has recently attracted active research interests. In this paper, a new algorithm is developed to achieve more effective implementation of large-scale image classification by hierarchical learning of large-margin metrics (HLMMs). A hierarchical visual tree is seamlessly integrated with metric learning to learn a set of node-specific/category-specific large-margin metrics. First, a hierarchical visual tree is learned to characterize the inter-category visual correlations effectively and organize large numbers of image categories in a coarse-to-fine fashion. Second, a new algorithm is developed to support hierarchical learning of large-margin metrics by training nearest class mean (NCM) classifiers over our hierarchical visual tree. In addition, we also consider dimensionality reduction as a regularizer for high-dimensional data in our large-margin metric learning. Two top-down approaches are developed for supporting hierarchical learning of large-margin metrics. We focus on learning more discriminative metrics for NCM node classifiers to identify the visually similar sub-nodes (visually similar image categories) under the same parent node over our hierarchical visual tree. A mini-batch stochastic gradient descend method is used to optimize our HLMMs learning algorithm. The experimental results on ImageNet Large Scale Visual Recognition Challenge 2010 dataset (ILSVRC2010) have demonstrated that our HLMMs learning algorithm is very promising for supporting large-scale image classification. [ABSTRACT FROM AUTHOR]

Age estimation can aid in forensic medicine applications, diagnosis, and treatment planning for orthodontics and pediatrics. Existing dental age estimation methods rely heavily on specialized knowledge and are highly subjective, wasting time, and energy, which can be perfectly solved by machine learning techniques. As the key factor affecting the performance of machine learning models, there are usually two methods for feature extraction: human interference and autonomous extraction without human interference. However, previous studies have rarely applied these two methods for feature extraction in the same image analysis task. Herein, we present two types of convolutional neural networks (CNNs) for dental age estimation. One is an automated dental stage evaluation model (ADSE model) based on specified manually defined features, and the other is an automated end-to-end dental age estimation model (ADAE model), which autonomously extracts potential features for dental age estimation. Although the mean absolute error (MAE) of the ADSE model for stage classification is 0.17 stages, its accuracy in dental age estimation is unsatisfactory, with the MAE (1.63 years) being only 0.04 years lower than the manual dental age estimation method (MDAE model). However, the MAE of the ADAE model is 0.83 years, being reduced by half that of the MDAE model. The results show that fully automated feature extraction in a deep learning model without human interference performs better in dental age estimation, prominently increasing the accuracy and objectivity. This indicates that without human interference, machine learning may perform better in the application of medical imaging. [ABSTRACT FROM AUTHOR]

We introduce an innovative and mathematically rigorous definition for computing common information from multi-view data, drawing inspiration from Gács-Körner common information in information theory. Leveraging this definition, we develop a novel supervised multi-view learning framework to capture both common and unique information. By explicitly minimizing a total correlation term, the extracted common information and the unique information from each view are forced to be independent of each other, which, in turn, theoretically guarantees the effectiveness of our framework. To estimate information-theoretic quantities, our framework employs matrix-based Rényi's α -order entropy functional, which forgoes the need for variational approximation and distributional estimation in high-dimensional space. Theoretical proof is provided that our framework can faithfully discover both common and unique information from multi-view data. Experiments on synthetic and seven benchmark real-world datasets demonstrate the superior performance of our proposed framework over state-of-the-art approaches. • We formulate a mathematically definition of common information for multiview data. • We propose a multiview learning method that discerns common and unique information. • Our method is scalable to data more than two view, supported by theoretical proof. • Experimental results substantiate the efficacy of the proposed framework. [ABSTRACT FROM AUTHOR]

Object detection and semantic segmentation are two fundamental techniques for Intelligent Vehicles (IV) and Advanced Driving Assistance System (ADAS). Motivated by recent studies demonstrating that object detection and semantic segmentation are two highly-correlated tasks, this paper handles the problem of joint object detection and semantic segmentation in traffic scenes. Existing methods perform the joint object detection and semantic segmentation by sharing the same backbone network, but always ignore the interactive connection between the subdividing detection branch and segmentation branch, leading to the insufficient interaction between the two branches. Considering this situation, this paper proposes a joint object detection and semantic segmentation model with the cross-attention and inner-attention mechanisms. The cross-attention mechanism enables to build up the essential interaction between the subdividing detection branch and segmentation branch to fully make use of their correlation. In addition, the inner-attention contributes to strengthening the representations of feature maps in the model. Given an image, an encoder-decoder network is firstly used to extract initial feature maps. Then, the inner-attention mechanism is applied to strengthen the initial feature maps to obtain segmentation feature maps. Subsequently, the cross-attention mechanism utilizes the segmentation feature maps to guide the generation of object detection feature maps. Finally, the semantic segmentation is performed on the segmentation feature maps and object detection is performed on the detection feature maps. In the experiments, two well-known public traffic datasets are used to evaluate our model. Our model achieves the highest performance in comparison with several recently-proposed methods. In addition, some ablation studies are conducted to evaluate the proposed inner-attention and cross-attention mechanisms, and experiment results validate their effectiveness. [ABSTRACT FROM AUTHOR]

A criterion based on the minimum MSE (mean square error) is given to determine the number of signals mixed with white Gaussian noise in order to estimate their frequencies based on the modified minimum square error method using a higher-order linear prediction model (CLS). Being different from the usual autoregression (AR) model of linear prediction, the method has the advantage of iterative reduction of noise by subtraction of noise variances from diagonal elements of the correlation matrix of observed signal disturbed by noise at the instance of taking an inversion. But it needs precise estimation of both the rank of the correlation matrix and variances of noise by using only observed signals. In this paper, the following three points are made: (1) the analytic method to determine the order of eigenvalues which minimizes MSE criterion derived from eigenvalue analysis; (2) the formula which must be satisfied by noise variances; and (3) the iterative algorithm which gives simultaneous solution for rank order determination of the correlation matrix and estimation of noise variances. Finally, numerical examples are given to show the usefulness and correctness of the proposed MSE criterion, and some comparisons with other methods are made. © 1998 Scripta Technica. Electron Comm Jpn Pt 3, 81(1): 13–23, 1998 [ABSTRACT FROM AUTHOR]

In this paper, a robust echo state network with correntropy induced loss function (CLF) is presented. CLF is robust to outliers through the mechanism of correntropy which is widely applied in information theoretic learning. The proposed method can improve the anti-noise capacity of echo state network and overcome its problem of being sensitive outliers which are prevalent in real-world tasks. The echo state network with CLF inherits the basic architecture of echo state network, but replaces the commonly used mean square error (MSE) criterion with CLF. The stochastic gradient descent method is adopted to optimize the objective function. The proposed method is subsequently verified in nonlinear system identification and chaotic time-series prediction. Experimental results demonstrate that our method is robust to outliers and outperforms the echo state networks with Bayesian regression and Huber loss function. [ABSTRACT FROM AUTHOR]

Energy storage devices (ESD), such as UPS batteries, have been repurposed in datacenter as a promising tuning knob for peak power shaving and power cost reducing. However, batteries progressively aging due to irregular usage patterns, which result in less effective capacity and even pose serious threat to server availability. Nevertheless, prior proposals largely ignore the aging issues of battery which may lead to low energy availability for datacenter servers. To fill this critical void, we thoroughly investigate battery aging on a heavily instrumented prototype system over an observation period of ten months. We propose Battery Anti-Aging Treatment Plus (BAAT-P ), a novel power delivery architecture included aging management algorithms from the perspective of computing system to hide, reduce, mitigate and plan the battery aging effects for high energy availability in datacenter. Our techniques exploit diverse battery aging mechanisms and dynamic aging management algorithms to provide system-level availability guarantee for datacenter. We evaluate the BAAT-P design with a real prototype. Compared with a battery powered datacenter without aging management policies, the results show that BAAT-P can extend battery lifetime by 72 percent, reduce battery cost by 33 percent and effectively improve energy availability for datacenter servers while maintaining workload performance for the performance critical workloads. [ABSTRACT FROM AUTHOR]

Datacenters, the essential infrastructures for supercomputing and cloud computing, are facing increasing pressure of capping tremendous power consumption and carbon emission. Many studies have proposed to leverage energy storage devices to shave peak power or smooth intermittent power for datacenters, respectively. However, a joint energy management of peak shaving and renewable energy harvesting in datacenters is still lacking. In this paper, we propose a new power management scheme named RE-UPS, which explores the opportunity to shave datacenter peak power demand with renewable energy. RE-UPS is based on the emerging distributed energy storage architecture and existing UPS infrastructure of datacenter. It further leverages a dynamic heuristic algorithm to determine the appropriate energy storage allocation and server power sources. The proposed energy management policies can greatly optimize the design among maximizing renewable energy harvest, shaving peak power, and maintaining UPS energy availability. Compared to the baseline power management schemes, RE-UPS can averagely improve backup energy capacity by 28 %, extend battery lifetime by 42 %, increase green energy utilization by 78 %, and reduce workload performance degradation by 13 %. [ABSTRACT FROM AUTHOR]

Text detection in natural scene images is a hot and challenging problem in pattern recognition and computer vision. Considering the complex situations in natural scene images, we propose a robust two-steps method in this paper based on multi-layer segmentation and higher order conditional random field (CRF). Given an input image, the method separates text from its background by using multi-layer segmentation, which decomposes the input image into nine layers. Then, the connected components (CCs) in these different layers are obtained as candidate text. These candidate text CCs are verified by higher order CRF based analysis. Inspired from the multistage information integration mechanism of visual brains, features from three different levels, including separate CCs, CC pairs and CC strings, are integrated by a higher order CRF model to distinguish text from non-text. The remaining CCs are then grouped into words for easy evaluation. Experiments on the ICDAR datasets and street view dataset show that the proposed method achieves the state-of-art in natural scene text detection. [ABSTRACT FROM AUTHOR]

Introduction: Optical coherence tomography (OCT) is an intravascular imaging modality which is widely used clinically for coronary plaque characterization. It has the ability to measure the fibrous cap thickness and to detect lipid content. Therefore, it can be used to identify in vivo thin-cap fibroatheroma(TCFA) and to detect plaque vulnerability. However, it takes much time for a doctor to learn to understand OCT images. We proposed a novel method of detecting vulnerable coronary plaques in OCT images of coronary artery disease (CAD) patients with deep learning. Methods and Results: The procedure includes: 1) preprocessing of the original images including coordinates transformation, image denoising and data augmentation; 2) deep learning network training on a dataset of 2000 images including classification, object detection and segmentation; 3) postprocessing of the detected images including image filtering and expert knowledge based adjustment. The model was tested on a separate series of 300 coronary OCT images. The results indicate that applying the image detecting method provided by this paper, the accuracy rate was 85.0% while the sensitivity (recall rate) was 93%. Conclusions: Our artificial intelligence method can help improve clinical decision-making and reduce human medical errors of Cardiologists, thus help provide a more individualized treatment for each CAD patients. [ABSTRACT FROM AUTHOR]