Recently, the rapid advance of vehicular networks has led to the emergence of diverse delay-sensitive vehicular applications such as automatic driving, auto navigation. Note that existing ...resource-constrained vehicles cannot adequately meet these demands on low / ultra-low latency. By offloading parts of the vehicles' compute-intensive tasks to the edge servers in proximity, mobile edge computing is envisioned as a promising paradigm, giving rise to the vehicular edge computing networks (VECNs). However, most existing works on task offloading in VECNs did not take the load balancing of the computation resources at the edge servers into account. To address these issues and given the high dynamics of vehicular networks, we introduce fiber-wireless (FiWi) technology to enhance VECNs, due to its advantages on centralized network management and supporting multiple communication techniques. Aiming to minimize the processing delay of the vehicles' computation tasks, we propose a software-defined networking (SDN) based load-balancing task offloading scheme in FiWi enhanced VECNs, where SDN is introduced to provide supports for the centralized network and vehicle information management. Extensive analysis and numerical results corroborate that our proposed load-balancing scheme can achieve superior performance on processing delay reduction by utilizing the edge servers' computation resources more efficiently.
•Using nodule heterogeneity (texture/shape) features and representation learned by a deep model.•Constructing an ensemble classifier using back propagation neural network and AdaBoost.•Fusing the ...decisions made by 3 ensemble classifiers, which are trained on 3 features, respectively.•Outperforming three state-of-the-art nodule classification approaches on the LIDC-IDRI dataset.
The separation of malignant from benign lung nodules on chest computed tomography (CT) is important for the early detection of lung cancer, since early detection and management offer the best chance for cure. Although deep learning methods have recently produced a marked improvement in image classification there are still challenges as these methods contain myriad parameters and require large-scale training sets that are not usually available for most routine medical imaging studies. In this paper, we propose an algorithm for lung nodule classification that fuses the texture, shape and deep model-learned information (Fuse-TSD) at the decision level. This algorithm employs a gray level co-occurrence matrix (GLCM)-based texture descriptor, a Fourier shape descriptor to characterize the heterogeneity of nodules and a deep convolutional neural network (DCNN) to automatically learn the feature representation of nodules on a slice-by-slice basis. It trains an AdaBoosted back propagation neural network (BPNN) using each feature type and fuses the decisions made by three classifiers to differentiate nodules. We evaluated this algorithm against three approaches on the LIDC-IDRI dataset. When the nodules with a composite malignancy rate 3 were discarded, regarded as benign or regarded as malignant, our Fuse-TSD algorithm achieved an AUC of 96.65%, 94.45% and 81.24%, respectively, which was substantially higher than the AUC obtained by other approaches.
Display omitted
Traditional image quality assessment (IQA) methods do not perform robustly due to the shallow hand-designed features. It has been demonstrated that deep neural network can learn more effective ...features than ever. In this paper, we describe a new deep neural network to predict the image quality accurately without relying on the reference image. To learn more effective feature representations for non-reference IQA, we propose a two-stream convolution network that includes two subcomponents for image and gradient image. The motivation for this design is using a two-stream scheme to capture different-level information of inputs and easing the difficulty of extracting features from one steam. The gradient stream focuses on extracting structure features in details, and the image stream pays more attention to the information in intensity. In addition, to consider the locally non-uniform distribution of distortion in images, we add a region-based fully convolutional layer for using the information around the center of the input image patch. The final score of the overall image is calculated by averaging of the patch scores. The proposed network performs in an end-to-end manner in both the training and testing phases. The experimental results on a series of benchmark datasets, e.g., LIVE, CISQ, IVC, TID2013, and Waterloo Exploration Database, show that the proposed algorithm outperforms the state-of-the-art methods, which verifies the effectiveness of our network architecture.
Fusing a low-resolution hyperspectral image (HSI) with a high-resolution (HR) conventional image into an HR HSI has become a prevalent HSIs super-resolution scheme. However, in most previous works, ...little attention has been paid on exploiting the underlying manifold structure in the spatial domain of the latent HR HSI. In this paper, we advance a provable prior knowledge that the clustering manifold structure of the latent HSI can be well preserved in the spatial domain of the input conventional image. Inspired by this, we first conduct clustering in the spatial domain of the input conventional image and adopt the intra-cluster self-expressiveness model to implicitly depict the clustering manifold structure, which enables learning the complicated manifold structure via solving a constrained ridge regression model without knowing the exact form of the manifold. Then, we incorporate the learned structure into a variational super-resolution framework to regularize the latent HSI. The resulted framework can be effectively optimized by a standard alternating direction method of multipliers. Since the learned structure can well depict the underlying spatial manifold of the latent HSI, the proposed method shows the state-of-the-art super-resolution performance on two benchmark data sets.
•Search deep convolutional neural networks automatically for image classification.•Encode a deep convolutional neural network’s architecture into an integer string.•Evolve a population of DCNN ...architectures using genetic evolutionary operations.•Obtained DCNNs achieved satisfying results with less layers than pre-trained models.•Image classification using neither handcrafted features nor handcrafted networks.
Recent years have witnessed the breakthrough success of deep convolutional neural networks (DCNNs) in image classification and other vision applications. DCNNs have distinct advantages over traditional solutions in providing a uniform feature extraction-classification framework to free users from troublesome handcrafted feature extraction. However, DCNNs are far from autonomous, since their performance relies heavily on the handcrafted architectures, which also requires a lot expertise and experience to design, and cannot be continuously improved once the tuning of hyper-parameters converges. In this paper, we propose an autonomous and continuous learning (ACL) algorithm to generate automatically a DCNN architecture for each given vision task. We first partition a DCNN into multiple stacked meta convolutional blocks and fully connected blocks, each of which may contain the operations of convolution, pooling, fully connection, batch normalization, activation and drop out, and thus convert the architecture into an integer code. Then, we use genetic evolutionary operations, including selection, mutation and crossover to evolve a population of DCNN architectures. We have evaluated this algorithm on six image classification tasks, i.e., MNIST, Fashion-MNIST, EMNIST-Letters, EMNIST-Digits, CIFAR10 and CIFAR100. Our results indicate that the proposed ACL algorithm is able to evolve the DCNN architecture continuously if more time cost is allowed and can find a suboptimal DCNN architecture, whose performance is comparable to the state of the art.
As fuzzy c-means clustering (FCM) algorithm is sensitive to noise, local spatial information is often introduced to an objective function to improve the robustness of the FCM algorithm for image ...segmentation. However, the introduction of local spatial information often leads to a high computational complexity, arising out of an iterative calculation of the distance between pixels within local spatial neighbors and clustering centers. To address this issue, an improved FCM algorithm based on morphological reconstruction and membership filtering (FRFCM) that is significantly faster and more robust than FCM is proposed in this paper. First, the local spatial information of images is incorporated into FRFCM by introducing morphological reconstruction operation to guarantee noise-immunity and image detail-preservation. Second, the modification of membership partition, based on the distance between pixels within local spatial neighbors and clustering centers, is replaced by local membership filtering that depends only on the spatial neighbors of membership partition. Compared with state-of-the-art algorithms, the proposed FRFCM algorithm is simpler and significantly faster, since it is unnecessary to compute the distance between pixels within local spatial neighbors and clustering centers. In addition, it is efficient for noisy image segmentation because membership filtering are able to improve membership partition matrix efficiently. Experiments performed on synthetic and real-world images demonstrate that the proposed algorithm not only achieves better results, but also requires less time than the state-of-the-art algorithms for image segmentation.
As an alternative for depleting fossil fuel energy, hydrogen economy desires low-cost and efficient hydrogen production from water splitting. In order to explore a cheap, abundant, active, and ...durable catalyst for the electrocatalytic hydrogen evolution reaction (HER), two-dimensional (2D) ceria nanosheets are produced through a thermal decomposition exfoliation method from CeCO3OH with a layer-stacked structure. The additional cobalt dopant promotes formation of oxygen vacancies in ceria nanosheets and, in turn, optimizes hydrogen binding/water dissociation and increases the active sites. As a result, the 2D Co-doped CeO2 nanosheets exhibit an excellent catalytic performance in alkaline HER such that the overpotential is as low as 132 and 215 mV to deliver a high current density of 100 and 500 mA cm–2, respectively, outperforming Pt. Such 2D Co-doped CeO2 nanosheets are also durable HER electrocatalysts, as the activity loss during an extended period of operation is nearly negligible.
Unsupervised fusion-based hyperspectral imagery (HSI) super-resolution (SR) is an essential task of HSI processing, which aims to reconstruct a high-resolution (HR) HSI using only an observed ...low-resolution HSI and a conventional HR image. Although a large number of unsupervised HSI SR methods have been proposed, the heuristic handcrafted image priors adopted by the majority of these methods restrict their capacity to capture specific characteristics of the HSI, as well as their ability to generalize to noisy observation images. In this study, we investigate a fusion-based HSI SR framework with the deep image prior, in which the deep neural network (rather than a heuristic handcrafted image prior) is exploited to capture plenty of image statistics. Within this framework, we further propose an unsupervised recurrence-based HSI SR method using pixel-aware refinement, which utilizes the intermediate reconstruction results to self-supervise unsupervised learning. Due to containing the information of the image-specific characteristic, the proposed method achieves better performance, in terms of both accuracy and robustness to noise, compared with the existing methods. Extensive experiments on four HSI data sets demonstrate the effectiveness of the proposed method.
Vision-based mobile robot navigation is a vibrant area of research with numerous algorithms having been developed, the vast majority of which either belong to the scene-oriented simultaneous ...localization and mapping (SLAM) or fall into the category of robot-oriented lane-detection/trajectory tracking. These methods suffer from high computational cost and require stringent labelling and calibration efforts. To address these challenges, this paper proposes a lightweight robot navigation framework based purely on uncalibrated spherical images. To simplify the orientation estimation, path prediction and improve computational efficiency, the navigation problem is decomposed into a series of classification tasks. To mitigate the adverse effects of insufficient negative samples in the "navigation via classification" task, we introduce the spherical camera for scene capturing, which enables 360° fisheye panorama as training samples and generation of sufficient positive and negative heading directions. The classification is implemented as an end-to-end Convolutional Neural Network (CNN), trained on our proposed Spherical-Navi image dataset, whose category labels can be efficiently collected. This CNN is capable of predicting potential path directions with high confidence levels based on a single, uncalibrated spherical image. Experimental results demonstrate that the proposed framework outperforms competing ones in realistic applications.
Display omitted
•Direct additive manufacturing of ceramics using melt cast route.•Fabrication of compositionally gradient ceramic-metal structure in one additive manufacturing ...operation.•Characterization and defect analysis of AM processed parts.
Laser Engineered Net Shaping (LENS™), which is a laser based additive manufacturing method, was utilized to fabricate Ti-Al2O3 compositionally graded structures. The Ti-Al2O3 graded composites consisted of different sections −Ti6Al4V alloy, Ti6Al4V + Al2O3 composites, and pure Al2O3 ceramic. After LENS™ processing, microstructural characterization, phase analysis, elemental distribution, and microhardness measurements were performed on the cross sections of Ti-Al2O3 graded composites. Each section had their unique microstructures and phases. Moreover, hardness measurements demonstrated that the pure Al2O3 section had the highest hardness of 2365.5 ± 64.7 HV0.3. Conventional ceramic processing requires extensive post-processing including high temperature sintering, which makes it difficult for direct fabrication of metal-ceramic multi-layer structures. The results demonstrate that LENS™ can be utilized to process multi-material metal ceramic composites in a single step while maintaining the size, shape and compositional variations based on computer aided design files. Since this is a first-generation work, and limited research results are available in published literature related to LENS™ processing of both metals and ceramics in one operation, the demonstration of this work is expected to inspire future studies on manufacturing of multi-material composites using AM.