Search

Accurate prediction of solar panel temperature can help keep on-orbit satellites in good condition. Traditional physical models have the ability to describe and predict temperature; however, the effect is not entirely satisfactory. To produce a better forecast, the panel current of the solar panel, which is strongly correlated with temperature signals, is chosen as the input, and a novel system identification model between the two signals is established. The model we propose is based on a Hammerstein-Wiener model and integrates wavelet neural networks that adopt self-constructed wavelet bases. In addition, a complete process of training and parameter optimization is designed to be less time consuming than previous methods. The result from a test set of real telemetry data demonstrates the efficiency and accuracy of our method. Moreover, the proposed prediction model, which is based on historical data, can be used in on board self-learning and our subsequent autonomous health management.

Networks derived from various disciplinary of sociality and nature are dynamic and incomplete, and temporal link prediction has wide applications in recommendation system and data mining system, etc. The current algorithms first obtain features by exploiting the topological or latent structure of networks, and then predict temporal links based on the obtained features. These algorithms are criticized by the separation of feature extraction and link prediction, which fails to fully characterize the dynamics of networks, resulting in undesirable performance. To overcome this problem, we propose a novel algorithm by joint multi-label learning and feature extraction (called MLjFE), where temporal link prediction and feature extraction are integrated into an overall objective function. The main advantage of MLjFE is that the features and parameter matrix for temporal link prediction are simultaneously learned during optimization procedure, which is more precise to capture dynamics of networks, improving the performance of algorithms. The experimental results on a number of artificial and real-world temporal networks demonstrate that the proposed algorithm significantly outperforms state-of-the-art methods, showing joint learning with feature extraction and temporal link prediction is promising.

The achievement of convolutional neural networks (CNNs) in a variety of applications is accompanied by a dramatic increase in computational costs and memory requirements. In this paper, we propose a novel framework to measure the importance of individual hidden units by computing a measure of relevance to identify the most critical filters and prune them to compress and accelerate CNNs. Unlike existing methods, we introduce the use of the activation of feature maps to detect valuable information and the essential semantic parts to evaluate the importance of feature maps, inspired by novel neural network interpretability. A majority voting technique based on the degree of alignment between a semantic concept and individual hidden unit representations is proposed to quantitatively evaluate the importance of feature maps. We also propose a simple yet effective method to estimate new convolution kernels based on the remaining, crucial channels to accomplish effective CNN compression. Experimental results show the effectiveness of our filter selection criteria, which outperforms the state-of-the-art baselines. Furthermore, we evaluate our pruning method on CIFAR-10, CUB-200, and ImageNet (ILSVRC 2012) datasets. The experimental results show that the proposed method efficiently achieves a 50% FLOPs reduction on CIFAR-10, with only 0.86% accuracy drop on the VGG-16 model. Meanwhile, ResNet pruned on CIFAR-10 achieves a 30% reduction in FLOPs with only 0.12% and 0.02% drops in accuracy on ResNet-20 and ResNet-32 respectively. For ResNet-50 on ImageNet, our pruned model achieves a 50% reduction in FLOPs with only a top-5 accuracy drop of 0.27%, which significantly outperforms state-of-the-art methods.

3D human pose estimation is a very difficult task. In this paper we propose that this problem can be more easily solved by first finding the solutions to a set of easier sub-problems. These are to locally estimate pose conditioned on a fixed root node state, which defines the global position and orientation of the person. The global solution can then be found using information extracted during this procedure. This approach has two key benefits: The first is that each local solution can be found by modeling the articulated object as a kinematic chain, which has far less degrees of freedom than alternative models. The second is that by using this approach we can represent, or support, a much larger area of the posterior than is currently possible. This allows far more robust algorithms to be implemented since there is far less pressure to prune the search space to free up computational resources. We apply this approach to two problems: The first is single frame monocular 3D pose estimation, where we propose a method to directly extract 3D pose without first extracting any intermediate 2D representation or being dependent on strong spatial prior models. The second is multi-view 3D tracking where we show that using the above technique results in an approach that is far more robust than current approaches, without relying on strong temporal prior models. In both domains we demonstrate the strength and versatility of the proposed method. A new approach to searching global solution by first finding a set of local solutionsApplied to both monocular 3D pose detection and multiview 3D trackingAchieve good accuracy using weak likelihood model and no assumed motion modelSource code is publically available to ensure reproducible results.

Automatic deformable 3D modeling is computationally expensive, especially when considering complex position, orientation and scale variations. We present a volume segmentation framework to utilize local and global regularizations in a data-driven approach. We introduce automated correspondence search to avoid manually labeling landmarks and improve scalability. We propose a novel marginal space learning technique, utilizing multi-resolution pooling to obtain local and contextual features without training numerous detectors or excessively dense patches. Unlike conventional convolutional neural network operators, graph-based operators allow spatially related features to be learned on the irregular domain of the multi-resolution space, and a graph-based convolutional neural network is proposed to learn representations for position and orientation classification. The graph-CNN classifiers are used within a marginal space learning framework to provide efficient and accurate shape pose parameter hypothesis prediction. During segmentation, a global constraint is initially non-iteratively applied, with local and geometric constraints applied iteratively for refinement. Comparison is provided against both classical deformable models and state-of-the-art techniques in the complex problem domain of segmenting aortic root structure from computerized tomography scans. The proposed method shows improvement in both pose parameter estimation and segmentation performance.

We present a study in level set representation and evolution using radial basis functions (RBFs) for active contour and active surface models. It builds on recent works by others who introduced RBFs into level sets for structural topology optimisation. Here, we introduce the concept into deformable models and present a new level set formulation able to handle more complex topological changes, in particular perturbation away from the evolving front. In the conventional level set technique, the initial active contour/surface is implicitly represented by a signed distance function and periodically re-initialised to maintain numerical stability. We interpolate the initial distance function using RBFs on a much coarser grid, which provides great potential in modelling in high dimensional space. Its deformation is considered as an updating of the RBF interpolants, an ordinary differential equation (ODE) problem, instead of a partial differential equation (PDE) problem, and hence it becomes much easier to solve. Re-initialisation is found no longer necessary, in contrast to conventional finite difference method (FDM) based level set approaches. The proposed level set updating scheme is efficient and does not suffer from self-flattening while evolving, hence it avoids large numerical errors. Further, more complex topological changes are readily achievable and the initial contour or surface can be placed arbitrarily in the image. These properties are extensively demonstrated on both synthetic and real 2D and 3D data. We also present a novel active contour model, implemented with this level set scheme, based on multiscale learning and fusion of image primitives from vector-valued data, e.g. colour images, without channel separation or decomposition.

Background Early prediction of the outcomes of dementia is important and challenging. This study aimed to identify influential predictors from primary care electronic health records that can robustly predict whether patients with dementia will be admitted to hospital or remain under GP care. Methods Health records of patients with dementia were collected from general practice (GP) and hospital data in Wales between 1980 and 2015. These records were linked at individual patient level via the Secure Anonymised Information Linkage databank. The GP records of each patient were selected 1 year before diagnosis up to hospital admission. An artificial intelligence technique, neural network with entropy regularisation (a multilayer feedforward neural network whose weights between input layer and the first hidden layer were regularised by an entropy metric into the fitness function during training process) was used to automatically identify the most influential predictors from initial GP read codes, sex, and age. 10-fold cross validation was used to assess the predictive performance of the identified signals. Findings 52·5 million individual records of 59 298 patients (20 674 men, 38 624 women) with dementia were used. 30 178 were admitted to hospital and 29 120 remained with GP care. More men were admitted to hospital than stayed with GP care (11 233 vs 9441), whereas more women stayed with GP care than were admitted (19 679 vs 18 945). From the 54 649 initial event codes, the ten most important signals identified for admission for dementia were two diagnostic events (nightmares, essential hypertension), five medication events (betahistine dihydrochloride, ibuprofen gel, simvastatin, influenza vaccine, calcium carbonate and colecalciferol chewable tablets), and three procedural events (third party encounter, social group 3—skilled, blood glucose raised). They performed significantly above chance to predict admission to hospital with sensitivity of 0·758 (95% CI 0·731–0·785), specificity 0·759 (0·71–0·808), precision 0·766 (0·735–0·797), and negative predictive value 0·751 (0·741–0·761). Linear regression with all raw features yielded values of 0·286 (0·26–0·313), 0·804 (0·792–0·816), 0·487 (0·463–0·511), and 0·633 (0·615–0·651), respectively, and with ten identified features yielded values of 0·684 (0·679–0·691), 0·712 (0·705–0·718), 0·747 (0·738–0·754), and 0·644 (0·64–0·651). Interpretation Outperforming traditional methods, the artificial intelligence technique provides an effective means of identifying influential clinical signals to predict hospital admission of patients with dementia significantly above chance. Funding Health Data Research UK Wales and Northern Ireland Site, National Centre for Population Health and Wellbeing Research (CA02), Major Project of National Social Science Foundation of China (16ZDA0092), Guangxi University Digital ASEAN Cloud Big Data Security and Mining Technology Innovation Team.