Search

This article presents a comprehensive, multidisciplinary overview of the development of powertrain technologies for energy-efficient heavy-duty earthmoving machines. The heavy-duty earthmoving equipment industry has been among the biggest contributors to emissions globally. However, due to high power demand and multidisciplinary powertrain structures, improving the energy efficiency of heavy-duty mobile machines has been a pressing and challenging task in the industry. To cope with this challenge, hydraulics and power electronics (PE) have been the key driving forces. As such, the relative developments in both fields are covered in this article. For hydraulics, developments of efficient hydraulic circuits will be overviewed in detail along with the introduction of hydraulic energy recovery technologies. In addition, developments of PE architectures in hybrid and electrified machines will be introduced. Furthermore, potential medium-voltage dc mining site power distribution and the valves of wide bandgap devices will also be discussed with the hope to open up new research opportunities in PE. Moreover, emerging hybrid electrohydraulic drive technology is introduced. Based on the overview in this article, it is anticipated that electrohydraulic hybridization will be the future trend in the earthmoving machine industry. Deeper collaboration between the two areas is desirable.

Environmental and maternal exercise experienced even during the very earliest stages of life has the potential to cause developmental changes. The growing evidence demonstrated that diverse environmental stressors affect offspring in various aspects in early stage of life and can be transmitted directly or indirectly by both parental lines. The development of normobaric hypoxic environment facilities began in recent years after athletes born and trained at high altitude continued to update their records in sports competition, especially marathons and other endurance sports. Although a large number of studies have proved the effect of hypoxic training in the field of sports science and competition, the effectiveness of this training model on exercise performance/capacity and physiological variables is still controversial. Therefore, this study makes a brief review of the papers related to this scope and attempted to understand the potential mechanism of maternal exercise in hypoxic environment on exercise performance and reduction of metabolic risk factors.

Unsteady motion of the atmosphere incurs nonlinear and spatiotemporally coupled uncertainties in the wind power prediction (WPP) of multiple wind farms. This brings both opportunities and challenges to wind power probabilistic forecasting (WPPF) of a wind farm cluster or region, particularly when wind power is highly penetrated within the power system. This paper proposes an Improved Deep Mixture Density Network (IDMDN) for short-term WPPF of multiple wind farms and the entire region. In this respect, a deep multi-to-multi (m2m) mapping Neural Network model, which adopts the beta kernel as the mixture component to avoid the density leakage problem, is established to produce probabilistic forecasts in an end-to-end manner. A novel modified activation function and several general training procedures are then introduced to overcome the unstable behavior and NaN (Not a Number) loss issues of the beta kernel function. Verification of IDMDN is based on an open-source dataset collected from seven wind farms, and comparison results show that the proposed model improves the WPPF performance at both wind farm and regional levels. Furthermore, a laconic and accurate probabilistic expression of predicted power at each time step is produced by the proposed model.

The increasing scale of Structure-from-Motion is fundamentally limited by the conventional optimization framework for the all-in-one global bundle adjustment. In this paper, we propose a distributed approach to coping with this global bundle adjustment for very large scale Structure-from-Motion computation. First, we derive the distributed formulation from the classical optimization algorithm ADMM, Alternating Direction Method of Multipliers, based on the global camera consensus. Then, we analyze the conditions under which the convergence of this distributed optimization would be guaranteed. In particular, we adopt over-relaxation and self-adaption schemes to improve the convergence rate. After that, we propose to split the large scale camera-point visibility graph in order to reduce the communication overheads of the distributed computing. The experiments on both public large scale SfM data-sets and our very large scale aerial photo sets demonstrate that the proposed distributed method clearly outperforms the state-of-the-art method in efficiency and accuracy.

Hydraulic excavators are essential excavation machines, with more than 3.8 million sets in use in the mining, and engineering and architectural engineering construction fields. However, during the working process, a large amount of gravitational potential energy is wasted, causing low energy efficiency and poor emissions. Taking a large-scale excavator as an example, during a certain 90° excavation process, the gravitational potential energy wastage of the working device is approximately 975.1 kJ, which amounts to at least 20% of the energy consumption of the entire machine, causing significant energy waste and serious pollution. And, during the boom lowering process, the changing rate of potential energy is about 406.4 kW. In order to improve the energy efficiency of hydraulic excavators, the recovery of this huge energy that changes rapidly with low cost and high efficiency is a big problem that must be solved. This paper proposes a gravitational potential energy recovery scheme with an energy conversion cylinder and a hydraulic accumulator. Using this scheme, the gravitational potential energy of the working device can be stored and reused directly, without increasing the cost and install power of the machine largely. In the study, first, the system parameters are designed, following which the multidisciplinary dynamic model of the hydraulic excavator is established. The influence of the accumulator parameters on the energy recovery ratio is studied based on the model. The results demonstrate that with the newly designed system more than 75.9% of the gravitational potential energy can be stored in the accumulator during the lowering process. Moreover, during a certain lifting process, the input energy to the pump can be reduced by 52%. On this basis, a 76 t hydraulic excavator test system is constructed using the above principle. The experimental results match strongly with the co-simulation results. The energy consumption can be reduced to approximately 238 kJ during a certain 90° excavation cycle, and the system can reduce the carbon dioxide emissions by 28088.4 kg per year. The energy-saving and emission-reduction effects are remarkable; furthermore, this principle can directly be applied to other lifting machines.

The operating temperature of hydraulic oils should be controlled within a reasonable range to keep hydraulic systems in good working condition. However, due to the huge energy losses of hydraulic systems, the oil temperature will increase rapidly. In addition, some hydraulic equipment often operate in cold weather conditions. The conventional cooling with radiators and preheating with electric heaters will consume extra energy for hydraulic systems. Therefore, an organic Rankine cycle with heat pump system is proposed to achieve regenerative cooling and energy-efficient preheating. The system can operate in two modes: an organic Rankine cycle mode to produce electricity instead of consuming energy while cooling the hot oil, and a heat pump mode to preheat the oil with less energy before the hydraulic system starts up in a cold environment. The system is applied to a 260-ton hydraulic excavator to investigate the technical feasibility. On average, the calorific power of the excavator is 177 kW at 245 kW of consumed power in a typical cycle. Considering the cost of heat source, the earning of equilibrium temperature is proposed to evaluate the benefit of the organic Rankine cycle. The optimal working fluid is selected by comparing the system performance. Afterward, the peak points of earning of equilibrium temperature at different ambient temperatures are observed. Corresponding to the maximum earning of equilibrium temperature, the output power of the organic Rankine cycle ranges from 7.63 kW to 2.89 kW. These results show significant energy savings by applying the proposed system in the hydraulic system.

The conventional design methods for tracked walking systems of large hydraulic excavators based on empirical formulas, does not take into account the dynamic load of the track. As such, a safety margin factor has to be adopted to ensure adequate working strength. However, the machine weight will be increased, and the hydraulic system will be overmatched. To address this design issue, an electromechanical–hydraulic design approach based on co-simulation is proposed in this study. The proposed design approach consists of four parts, namely, 1) a terramechanics model of the track that considers the pressure–sinkage relationship and soil shear stress of the individual tracked plate, 2) a tracked multibody dynamics (MBD) model that considers the intermittent transmission between the sprocket and the tracks, 3) the hydraulic systems model, and 4) the data communication interface. To demonstrate the proposed approach, it was used to design a large hydraulic excavator with a bucket capacity of 15 m3. Experimental results from the prototype showed that the proposed design principle can accurately reflect the impact load and periodic torque fluctuations on the track. The maximum error between the simulated and experimental results is 5.4% in forward walking and 12.7% in backward walking, thus demonstrating the effectiveness and accuracy of the proposed design approach.

Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address this challenge by proposing a stereo matching network that considers pixel-wise matchability. Specifically, the network jointly regresses disparity and matchability maps from 3D probability volume through expectation and entropy operations. Next, a learned attenuation is applied as the robust loss function to alleviate the influence of weakly matchable pixels in the training. Finally, a matchability-aware disparity refinement is introduced to improve the depth inference in weakly matchable regions. The proposed deep stereo matchability (DSM) framework can improve the matching result or accelerate the computation while still guaranteeing the quality. Moreover, the DSM framework is portable to many recent stereo networks. Extensive experiments are conducted on Scene Flow and KITTI stereo datasets to demonstrate the effectiveness of the proposed framework over the state-of-the-art learning-based stereo methods., Accepted to ICPR 2020

The aim of this study was to analyze the clinical data, discharge rate, and fatality rate of COVID‐19 patients for clinical help. The clinical data of COVID‐19 patients from December 2019 to February 2020 were retrieved from four databases. We statistically analyzed the clinical symptoms and laboratory results of COVID‐19 patients and explained the discharge rate and fatality rate with a single‐arm meta‐analysis. The available data of 1994 patients in 10 literatures were included in our study. The main clinical symptoms of COVID‐19 patients were fever (88.5%), cough (68.6%), myalgia or fatigue (35.8%), expectoration (28.2%), and dyspnea (21.9%). Minor symptoms include headache or dizziness (12.1%), diarrhea (4.8%), nausea and vomiting (3.9%). The results of the laboratory showed that the lymphocytopenia (64.5%), increase of C‐reactive protein (44.3%), increase of lactic dehydrogenase (28.3%), and leukocytopenia (29.4%) were more common. The results of single‐arm meta‐analysis showed that the male took a larger percentage in the gender distribution of COVID‐19 patients 60% (95% CI [0.54, 0.65]), the discharge rate of COVID‐19 patients was 52% (95% CI [0.34,0.70]), and the fatality rate was 5% (95% CI [0.01,0.11])., Research Highlights Our study explored the clinical and epidemiological characteristics of COVID‐19 patients, and proposed the need to focus on other systemic symptoms such as the gastrointestinal tract firstly, which could be of use for clinical work.

A successful point cloud registration often lies on robust establishment of sparse matches through discriminative 3D local features. Despite the fast evolution of learning-based 3D feature descriptors, little attention has been drawn to the learning of 3D feature detectors, even less for a joint learning of the two tasks. In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point. In particular, we propose a keypoint selection strategy that overcomes the inherent density variations of 3D point clouds, and further propose a self-supervised detector loss guided by the on-the-fly feature matching results during training. Finally, our method achieves state-of-the-art results in both indoor and outdoor scenarios, evaluated on 3DMatch and KITTI datasets, and shows its strong generalization ability on the ETH dataset. Towards practical use, we show that by adopting a reliable feature detector, sampling a smaller number of features is sufficient to achieve accurate and fast point cloud alignment.[code release](https://github.com/XuyangBai/D3Feat), Accepted to CVPR 2020, supplementary materials included

In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection. The critical component in the framework is the iterative pyramid context module (PCM), which couples two tasks and stores the shared latent semantics to interact between the two tasks. For semantic boundary detection, we propose the novel spatial gradient fusion to suppress non-semantic edges. As semantic boundary detection is the dual task of semantic segmentation, we introduce a loss function with boundary consistency constraint to improve the boundary pixel accuracy for semantic segmentation. Our extensive experiments demonstrate superior performance over state-of-the-art works, not only in semantic segmentation but also in semantic boundary detection. In particular, a mean IoU score of 81.8% on Cityscapes test set is achieved without using coarse data or any external data for semantic segmentation. For semantic boundary detection, we improve over previous state-of-the-art works by 9.9% in terms of AP and 6.8% in terms of MF(ODS).

This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors. First, the ability to estimate the local shape (scale, orientation, etc.) of feature points is often neglected during dense feature extraction, while the shape-awareness is crucial to acquire stronger geometric invariance. Second, the localization accuracy of detected keypoints is not sufficient to reliably recover camera geometry, which has become the bottleneck in tasks such as 3D reconstruction. In this paper, we present ASLFeat, with three light-weight yet effective modifications to mitigate above issues. First, we resort to deformable convolutional networks to densely estimate and apply local transformation. Second, we take advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization. Finally, we use a peakiness measurement to relate feature responses and derive more indicative detection scores. The effect of each modification is thoroughly studied, and the evaluation is extensively conducted across a variety of practical scenarios. State-of-the-art results are reported that demonstrate the superiority of our methods., Comment: Accepted to CVPR 2020, supplementary materials included, code available

Temporal camera relocalization estimates the pose with respect to each video frame in sequence, as opposed to one-shot relocalization which focuses on a still image. Even though the time dependency has been taken into account, current temporal relocalization methods still generally underperform the state-of-the-art one-shot approaches in terms of accuracy. In this work, we improve the temporal relocalization method by using a network architecture that incorporates Kalman filtering (KFNet) for online camera relocalization. In particular, KFNet extends the scene coordinate regression problem to the time domain in order to recursively establish 2D and 3D correspondences for the pose determination. The network architecture design and the loss formulation are based on Kalman filtering in the context of Bayesian learning. Extensive experiments on multiple relocalization benchmarks demonstrate the high accuracy of KFNet at the top of both one-shot and temporal relocalization approaches. Our codes are released at https://github.com/zlthinker/KFNet., Comment: An oral paper of CVPR 2020

In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task. To capture the inherent correlation among video frames, we learn discriminative features (D-features) from the input images that reveal feature distribution from a global perspective. The D-features are then used to establish correspondence with all features of test image under conditional random field (CRF) formulation, which is leveraged to enforce consistency between pixels. The experiments verify that DFNet outperforms state-of-the-art methods by a large margin with a mean IoU score of 83.4% and ranks first on the DAVIS-2016 leaderboard while using much fewer parameters and achieving much more efficient performance in the inference phase. We further evaluate DFNet on the FBMS dataset and the video saliency dataset ViSal, reaching a new state-of-the-art. To further demonstrate the generalizability of our framework, DFNet is also applied to the image object co-segmentation task. We perform experiments on a challenging dataset PASCAL-VOC and observe the superiority of DFNet. The thorough experiments verify that DFNet is able to capture and mine the underlying relations of images and discover the common foreground objects.

Hydraulic excavator driven by an internal-combustion engine is widely used in the construction field. However, some problems, such as high pollutant emissions, noise and low efficiency, exist universally. To address these problems, an electric hydraulic excavator configuration combining with an independent metering in and metering out system is proposed to improve the overall energy efficiency. In this paper, a displacement variable pump driven by a speed variable electric motor is used as power source, and a matching method based on the segmented speed and continuous displacement control of the pump is proposed to meet the requirements of high dynamic, high energy efficiency and zero emission of hydraulic excavator under different working conditions. Then, an independent metering in and metering out system is employed to reduce throttling loss. A test rig with a 6-ton hydraulic excavator was built up and used to validate the proposed scheme. The energy consumption characteristics of the electro-hydraulic power source under different rotational speeds and different loads are further investigated to provide analytical and experimental references for control strategy designing. Furthermore, the working performance and energy distributions of the excavator with the pure displacement variable concept, and speed and displacement variable concept are studied comparatively. Results show that, compared with pure displacement variable concept, the electric power consumption during the idle period can be reduced from 2.05 kW to 0.7 kW, the energy saving ratio under partial load condition can be up to 33%, while it is 28.5% under digging condition.

While deep learning has recently achieved great success on multi-view stereo (MVS), limited training data makes the trained model hard to be generalized to unseen scenarios. Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures. In this paper, we introduce BlendedMVS, a novel large-scale dataset, to provide sufficient training ground truth for learning-based MVS. To create the dataset, we apply a 3D reconstruction pipeline to recover high-quality textured meshes from images of well-selected scenes. Then, we render these mesh models to color images and depth maps. To introduce the ambient lighting information during training, the rendered color images are further blended with the input images to generate the training input. Our dataset contains over 17k high-resolution images covering a variety of scenes, including cities, architectures, sculptures and small objects. Extensive experiments demonstrate that BlendedMVS endows the trained model with significantly better generalization ability compared with other MVS datasets. The dataset and pretrained models are available at \url{https://github.com/YoYo000/BlendedMVS}., Accepted to CVPR2020

Based on the previously developed fixed-displacement asymmetric axial piston pump, a variable displacement asymmetric axial piston pump (VDAAPP) with three independent suction/delivery ports is proposed. A basic linear model of VDAAPP is established to get open-loop bode diagram. Based on open-loop Bode diagram features and design requirements, P-controller is determined for VDAAPP. Then VDAAPP's performance is investigated by advanced modeling environment for performing simulations of engineering systems (AMESim) and automatic dynamic analysis of mechanical systems (ADAMS) joint simulation, and some key design parameters are obtained. Next, a VDAAPP prototype with a maximum displacement of 40 cc/rev is designed and manufactured, ratio of flow rates at ports A, B and T is 1:0.6:0.4. Due to hard limitations of the test bench, the performance only under the conditions of the opposite passive loads is tested. Preliminary test results indicate that VDAAPP prototype works normally and meets the design requirements for flow ratio, and the maximum rise time of the test pressure is about 0.32 s. However, due to special design of VDAAPP valve plate, the swash plate torque severely limits system dynamic response. Therefore, an improved swashplate control system based on asymmetric-valve-controlled asymmetric-piston scheme is presented as well, it is found to be an effective way to suppress the negative impact of swash plate torque on system dynamic performance. This provides a direction for the optimization of the swashplate control system for asymmetric axial piston pumps in the future.

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data. In this paper, we address the issue when previous assumptions of the self-supervised approaches are violated due to the dynamic nature of real-world scenes. Different from handling the noise as uncertainty, our key idea is to incorporate more robust geometric quantities and enforce internal consistency in the temporal image sequence. As demonstrated on commonly used benchmark datasets, the proposed method substantially improves the state-of-the-art methods on both depth and relative pose estimation for monocular image sequences, without adding inference overhead., International Conference on Computer Vision (ICCV) Workshop 2019

We present a convolutional network architecture for direct feature learning on mesh surfaces through their atlases of texture maps. The texture map encodes the parameterization from 3D to 2D domain, rendering not only RGB values but also rasterized geometric features if necessary. Since the parameterization of texture map is not pre-determined, and depends on the surface topologies, we therefore introduce a novel cross-atlas convolution to recover the original mesh geodesic neighborhood, so as to achieve the invariance property to arbitrary parameterization. The proposed module is integrated into classification and segmentation architectures, which takes the input texture map of a mesh, and infers the output predictions. Our method not only shows competitive performances on classification and segmentation public benchmarks, but also paves the way for the broad mesh surfaces learning.

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM). Recently, the self-supervised learning framework that jointly optimizes the relative pose and target image depth has attracted the attention of the community. Previous works rely on the photometric error generated from depths and poses between adjacent frames, which contains large systematic error under realistic scenes due to reflective surfaces and occlusions. In this paper, we bridge the gap between geometric loss and photometric loss by introducing the matching loss constrained by epipolar geometry in a self-supervised framework. Evaluated on the KITTI dataset, our method outperforms the state-of-the-art unsupervised ego-motion estimation methods by a large margin. The code and data are available at https://github.com/hlzz/DeepMatchVO., Accepted by ICRA 2019

Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations. In this paper, we go beyond the local detail representation by introducing context awareness to augment off-the-shelf local feature descriptors. Specifically, we propose a unified learning framework that leverages and aggregates the cross-modality contextual information, including (i) visual context from high-level image representation, and (ii) geometric context from 2D keypoint distribution. Moreover, we propose an effective N-pair loss that eschews the empirical hyper-parameter search and improves the convergence. The proposed augmentation scheme is lightweight compared with the raw local feature description, meanwhile improves remarkably on several large-scale benchmarks with diversified scenes, which demonstrates both strong practicality and generalization ability in geometric matching applications., Accepted to CVPR 2019 (oral), supplementary materials included. (https://github.com/lzx551402/contextdesc)

Semantic segmentation is pixel-wise classification which retains critical spatial information. The “feature map reuse” has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later spatial reconstruction. Along this direction, we go a step further by proposing a fully dense neural network with an encoderdecoder structure that we abbreviate as FDNet. For each stage in the decoder module, feature maps of all the previous blocks are adaptively aggregated to feedforward as input. On the one hand, it reconstructs the spatial boundaries accurately. On the other hand, it learns more efficiently with the more efficient gradient backpropagation. In addition, we propose the boundary-aware loss function to focus more attention on the pixels near the boundary, which boosts the “hard examples” labeling. We have demonstrated the best performance of the FDNet on the two benchmark datasets: PASCAL VOC 2012, NYUDv2 over previous works when not considering training on other datasets.

Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In this paper, we narrow down this gap by presenting an efficient CNN-based method to retrieve images with overlaps, which we refer to as the matchable image retrieval problem. Different from previous methods that generates training data based on sparse reconstruction, we create a large-scale image database with rich 3D geometrics and exploit information from surface reconstruction to obtain fine-grained training data. We propose a batched triplet-based loss function combined with mesh re-projection to effectively learn the CNN representation. The proposed method significantly accelerates the image retrieval process in 3D reconstruction and outperforms the state-of-the-art CNN-based and BoW methods for matchable image retrieval. The code and data are available at https://github.com/hlzz/mirror.

Applying the independent metering circuit on the excavator is an effective way to reduce energy consumption and improve the performance of the actuators, e.g. the boom in the negative load circuit. This paper aims to improve the energy efficiency and the stationarity of the boom system based on the independent metering circuit using the strategy of flow and pressure accordance, pump and valve coordinate in dynamic and static. After studying the mechanic structure of the boom, principles of the system and elements characteristics, the four control strategies are designed to settle the problems in the traditional throttling system using mechanically connected orifices valves such as the load-sensing system and new coordinate challenges brought with the multivariable. Finally, experiments based on load sensing and independent metering circuit are implemented on a physical prototype. The experimental results show that the energy consumption of the boom system falls by 15% compared to the load-sensing system; the pressure pulsations of the pump when the boom starts to move reduce from 6.9 MPa to 1.7 MPa. Therefore, the independent metering circuit and the control strategy are good configuration for the boom actuator.

Reconstructed building models using stereo-based methods inevitably suffer from noise, leading to the lack of regularity which is characterized by straightness of structural linear features and smoothness of homogeneous regions. We leverage the structural linear features embedded in the mesh to construct a novel surface scaffold structure for model regularization. The regularization comprises two iterative stages: (1) the linear features are semi-automatically proposed from images by exploiting photometric and geometric clues jointly; (2) the scaffold topology represented by spatial relations among the linear features is optimized according to data fidelity and topological rules, then the mesh is refined by adjusting itself to the consolidated scaffold. Our method has two advantages. First, the proposed scaffold representation is able to concisely describe semantic building structures. Second, the scaffold structure is embedded in the mesh, which can preserve the mesh connectivity and avoid stitching or intersecting surfaces in challenging cases. We demonstrate that our method can enhance structural characteristics and suppress irregularities in the building models robustly in some challenging datasets. Moreover, the regularization can significantly improve the results of general applications such as simplification and non-photorealistic rendering.

Rheumatoid arthritis (RA) affects millions world-wide. While anti-TNF treatment is widely used to reduce disease progression, treatment fails in ∼one-third of patients. No biomarker currently exists that identifies non-responders before treatment. A rigorous community-based assessment of the utility of SNP data for predicting anti-TNF treatment efficacy in RA patients was performed in the context of a DREAM Challenge (http://www.synapse.org/RA_Challenge). An open challenge framework enabled the comparative evaluation of predictions developed by 73 research groups using the most comprehensive available data and covering a wide range of state-of-the-art modelling methodologies. Despite a significant genetic heritability estimate of treatment non-response trait (h2=0.18, P value=0.02), no significant genetic contribution to prediction accuracy is observed. Results formally confirm the expectations of the rheumatology community that SNP information does not significantly improve predictive performance relative to standard clinical traits, thereby justifying a refocusing of future efforts on collection of other data., Rheumatoid arthritis patients respond differently to anti-TNF treatment. Using community-based challenge, the authors show that currently available data does not reveal meaningful genetic predictors of response to anti-TNF therapy, thus confirming clinical observations.

Naive Bayes Nearest Neighbor classifier, despite its simplicity, has recently gained remarkable success in image classification. Inspired from such results, we originally introduce to model the discriminativity of features using the density estimation approach presented in NBNN. Features are then grouped into positive and negative ones according to their log-discriminativity. More importantly, we speculate that updating the detector using merely positive features works much more confidently than the one using both negative and positive features, and further validate it on the PASCAL VOC 2007 dataset and LabelMe dataset. Therefore, we propose to localize the object of interest using positive features. However, unlike traditional detectors in this field, scores of the proposed one always increase as the test region becomes larger. To address this issue, we utilize context features to estimate scales of the objects and their probabilities, and then combine these estimations with the proposed detector to localize the target objects. We finally demonstrate the effectiveness of the proposed approach on PASCAL VOC 2007 in detail, due to its standard configurations on the training and test sets.

We have read Char's comment1. Thanks for readers’ attention and valuable feedback on our article. Following was our response to Char's question about data overlap.Firstly, the meta‐analysis reprocessed the existing data about COVID‐19 patients in published articles, and involved no other information outside of the article.This article is protected by copyright. All rights reserved.

Background Chrysanthemum zawadskii (CZ) belongs to the genus Chrysanthemum, also known as 'Gu-Jeol-Cho' in Korea. CZ has been used as herbal remedy to manage cough, hypertensive disorders, pharyngitis, bronchitis, gastroenteritis, pneumonia, bladder diseases and common cold. However, its effect on hair growth has not been documented. Objective The aim of present study was to elucidate the beneficial effects of CZ on hair growth. Methods Proliferation of follicular dermal papilla (DP) cells from human scalp skin was evaluated by MTT assay. The expression of various molecules in DP cells was checked by western blot assay. Effect of CZ extract on the hair growth was evaluated by hair organ culture and C57BL/6 mice model. Results Cultivation of DP cells with CZ extract increased cellular proliferation, increased expression of phosphorylated protein kinase B (p-Akt), p-ERK, B-cell lymphoma 2, and decreased expression of Bax. Treatment of human hair follicles with CZ extract significantly enhanced hair growth. Additionally, CZ markedly shortened telogen period, increased anagen transformation and stimulated hair growth in the animal study. Conclusion These results suggest that CZ extract has an effect of promoting hair growth and may therefore be a useful a therapeutic remedy for preventing hair loss.

Objective This study was to examine the effect of different exercise intensity and diet on the expression of the metabolism related factors in T2DM rat skeletal muscles. Methods Diet induced T2DM rat by a combination of low dose streptozotocin (STZ: 40mg/kg) and feeding of a high fat diet used as experimental animals. The rats trained on the treadmill for 8 weeks with low (40% max）and high (80% max) intensities of exercise on the treadmill for 8 weeks. The soleus (SOL) and extensor digitorum longus (EDL) muscles were excised. The western blotting was performed for the expression of AMPK, p-AMPK, PGC-1α，and GLUT-4 proteins. Results The expression of AMPK, p-AMPK, PGC-1α，and GLUT-4 proteins in SOL and EDL muscles were higher in both training groups compared to the non-training groups. The AMPK was differently expressed to the recruitment pattern of muscle group during exercise; expressed higher in SOL during low intensity of exercise and also highly expressed in EDL during high intensity of exercise, whereas the PGC-1a was expressed a contrast phenomenon to AMPK expression in both muscle groups. The expression of p-AMPK in both muscle groups was higher in low intensity of exercise and normal diet groups than in high intensity of exercise and high fat groups. The AMPK, p-AMPK, PGC-1α，and GLUT-4 protein expression demonstrated significantly higher in normal diet with endurance training group than in high fat diet with endurance training group. Conclusions In summary, the expression of AMPK, p-AMPK, PGC-1α，and GLUT-4 proteins was differed with exercise intensities, diet and the type of muscles. These results indicated that the endurance training improved the insulin sensitivity according to the exercise intensity and diet in T2DM rats.

Global Structure-from-Motion (SfM) techniques have demonstrated superior efficiency and accuracy than the conventional incremental approach in many recent studies. This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images. Specifically, we first divide all images into multiple partitions that preserve strong data association for well-posed and parallel local motion averaging. Then, we solve a global motion averaging that determines cameras at partition boundaries and a similarity transformation per partition to register all cameras in a single coordinate frame. Finally, local and global motion averaging are iterated until convergence. Since local camera poses are fixed during the global motion average, we can avoid caching the whole reconstruction in memory at once. This distributed framework significantly enhances the efficiency and robustness of large-scale motion averaging.

The manifold surface reconstruction in multi-view stereo often fails in retaining thin structures due to incomplete and noisy reconstructed point clouds. In this paper, we address this problem by leveraging spatial curves. The curve representation in nature is advantageous in modeling thin and elongated structures, implying topology and connectivity information of the underlying geometry, which exactly compensates the weakness of scattered point clouds. We present a novel surface reconstruction method using both curves and point clouds. First, we propose a 3D curve reconstruction algorithm based on the initialize-optimize-extend strategy. Then, tetrahedra are constructed from points and curves, where the volumes of thin structures are robustly preserved by the Curve-conformed Delaunay Refinement. Finally, the mesh surface is extracted from tetrahedra by a graph optimization. The method has been intensively evaluated on both synthetic and real-world datasets, showing significant improvements over state-of-the-art methods.

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space. The correspondence problem is generally addressed by the design of discriminative 3D local descriptors on the one hand, and the development of robust matching strategies on the other hand. In this work, we first propose a multi-view local descriptor, which is learned from the images of multiple views, for the description of 3D keypoints. Then, we develop a robust matching approach, aiming at rejecting outlier matches based on the efficient inference via belief propagation on the defined graphical model. We have demonstrated the boost of our approaches to registration on the public scanning and multi-view stereo datasets. The superior performance has been verified by the intensive comparisons against a variety of descriptors and matching methods.

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction. In this paper, we mitigate this limitation by proposing a novel local descriptor learning approach that integrates geometry constraints from multi-view reconstructions, which benefits the learning process in terms of data generation, data sampling and loss computation. We refer to the proposed descriptor as GeoDesc, and demonstrate its superior performance on various large-scale benchmarks, and in particular show its great success on challenging reconstruction tasks. Moreover, we provide guidelines towards practical integration of learned descriptors in Structure-from-Motion (SfM) pipelines, showing the good trade-off that GeoDesc delivers to 3D reconstruction tasks between accuracy and efficiency.

We present an end-to-end deep learning architecture for depth map inference from multi-view images. In the network, we first extract deep visual image features, and then build the 3D cost volume upon the reference camera frustum via the differentiable homography warping. Next, we apply 3D convolutions to regularize and regress the initial depth map, which is then refined with the reference image to generate the final output. Our framework flexibly adapts arbitrary N-view inputs using a variance-based cost metric that maps multiple features into one cost feature. The proposed MVSNet is demonstrated on the large-scale indoor DTU dataset. With simple post-processing, our method not only significantly outperforms previous state-of-the-arts, but also is several times faster in runtime. We also evaluate MVSNet on the complex outdoor Tanks and Temples dataset, where our method ranks first before April 18, 2018 without any fine-tuning, showing the strong generalization ability of MVSNet.

This paper investigates on the high performance torque control of electro-hydraulic load simulator (EHLS). In order to suppress actuator's motion disturbance, a nonlinear robust dual-loop control scheme is developed, which consists of a open-loop nonlinear velocity feed-forward compensator and a closed-loop nonlinear deterministic robust torque controller. The main function of the open-loop compensator is to decouple actuator's active motion disturbance, whereas the torque loop controller aims at guaranteeing the dynamics performance of tracking torque reference. Besides actuator's motion disturbance, both the nonlinearity characteristics and friction problem of the EHLS system are taken into consideration in this paper. The effectiveness of the developed method are verified through comparative co-simulations and experiments.

Complexity of large structure of hydraulic shovel system drives the guideline development for designing a swing unit of the shovel. Some of the issues are how to achieve smooth swing motion, save energy, and easily adjust its swing velocity. In this paper, we proposed a dual-closed-hydraulic-circuit (DCHC) accordingly to meet the design requirement. In the DCHC system, instead of manual adjustment, the displacement of hydraulic axial piston pump is controlled by programmed software algorithm through electronic control device, which significantly simplifies the current circuit design. The DCHC system also enables controllable recuperation of kinetic energy of swing motion for use by other actuators. Accordingly, the new system will achieve smoother motion compared with existing system and more efficient operation. We demonstrate the advantages of our DCHC design through simulation and verify through developing a hydraulic shovel prototype with bucket capacity of 15 cubic meters and operational weight of 270 tons. Both simulation and experimental results indicate that the DCHC system is feasible and works as intended.

In recent years, a trend toward the combination of variable displacement and speed-variable pump drive is becoming apparent. Combination of variable displacement and speed-variable pump drive has been revealed to be more efficient than speed-variable pump drive or variable displacement pump drive. However, few research works have dealt with the pumping performance of combination of variable displacement and speed-variable pump. This study aims to investigate the characteristics of pressure pulsations of combination of variable displacement and speed-variable pump. A simulation model is developed by means of software package ITI-SimulationX®. The model is used to predict the pressure pulsations under different operating conditions. Experiments are also carried out to verify theoretical results. From these results, it can be drawn that the pumping dynamics of combination of variable displacement and speed-variable pump is not the best in the view of pressure pulsation, and it is slightly inferior to that of variable displacement pump drive. For required delivery volumetric flow and load pressure, delivery pressure pulsations’ amplitude of combination of variable displacement and speed-variable pump slightly increases with an increase in swash plate angle and adapted rotational speed. However, test results also show that lower rotational speed and adapted swash plate angle working condition can effectively reduce total noise level of the system. Consequently, lower rotational speed and higher swash plate angle working condition are suggested for the design of combination of variable displacement and speed-variable pump drive controller.

This paper investigates suppression of actuator's motion disturbance problem in hardware-in-the-loop (HIL) experiment. A compound control scheme consists of a synchronization controller and a torque PI controller is developed. The structure of the synchronization controller is developed to match with the dynamics of actuator system. To cope with the parameter uncertainties problem, the parameters of the synchronization controller are obtained through adaptive update law. The tracking performance and global stability are proven using Lyapunov theorem. Co-simulations are performed to make the comparison between the traditional scheme and the improved method. Finally, the developed method is implemented on test rig, and compared with actuator velocity feed-forward compensation method.

Multi-view stereo (MVS) depends on the pre-determined camera geometry, often from structure from motion (SfM) or simultaneous localization and mapping (SLAM). However, cameras may not be locally optimal for dense stereo matching, especially when it comes from the large scale SfM or the SLAM with multiple sensor fusion. In this paper, we propose a local camera refinement approach for accurate dense reconstruction. Firstly, we refines the relative geometry of independent camera pair using a tailored bundle adjustment. The refinement is also extended to a multi-view version for general MVS reconstructions. Then, the non-rigid dense alignment is formulated as an inverse-distortion problem to transfer point clouds from each local coordinate system to a global coordinate system. The proposed framework has been intensively validated in both SfM and SLAM based dense reconstructions. Results on different datasets show that our method can significantly improve the dense reconstruction quality.

The power of modern image matching approaches is still fundamentally limited by the abrupt scale changes in images. In this paper, we propose a scale-invariant image matching approach to tackling the very large scale variation of views. Drawing inspiration from the scale space theory, we start with encoding the image’s scale space into a compact multi-scale representation. Then, rather than trying to find the exact feature matches all in one step, we propose a progressive two-stage approach. First, we determine the related scale levels in scale space, enclosing the inlier feature correspondences, based on an optimal and exhaustive matching in a limited scale space. Second, we produce both the image similarity measurement and feature correspondences simultaneously after restricting matching between the related scale levels in a robust way. The matching performance has been intensively evaluated on vision tasks including image retrieval, feature matching and Structurefrom- Motion (SfM). The successful integration of the challenging fusion of high aerial and low ground-level views with significant scale differences manifests the superiority of the proposed approach.

To obtain the ultimate high-level description of urban scenes, we propose a three-stage approach to recognizing the 3D reconstructed scene with efficient representations. First, we develop a joint semantic labeling method to obtain a semantic labeling of the triangular mesh-based representation by exploiting both image features and geometric features. The labeling is formulated over a conditional random field (CRF) that incorporates local spacial smoothness and multi-view consistency. Then, based on the labeled reconstructed meshes, we refine the man-made object segmentation in the recomposed global orthographic map with a graph partition algorithm, and propagate the coherent segmentation to the entire 3D meshes. Finally, we propose to generate a compact, abstracted geometric representation for each man-made object which is more visually appealing than the original cluttered models. This abstraction algorithm also leverages CRF formation to partition building footprints into minimal sets of structural linear features which are then used to construct profiles for large-scale scenes. The proposed recognition approach is able to robustly handle reconstructions with poor geometry and connectivity, thanks to the higher order CRF formulations which impose the ubiquitous regularity priors in urban scenes. Each stage performs an individual and uncoupling task. The intensive experiments have demonstrated the superior performance of our approach in robustness, accuracy and applicability.

A new method for feature subset selection in machine learning, FSS-MGSA (Feature Subset Selection by Modified Gravitational Search Algorithm), is presented. FSS-MGSA is an evolutionary, stochastic search algorithm based on the law of gravity and mass interactions, and it can be executed when domain knowledge is not available. A wrapper approach, over Naive-Bayes, ID3, K-Nearest Neighbor and Support Vector Machine learning algorithms, is used to evaluate the goodness of each visited solution. The key to the success of the MGSA is to utilize the piecewise linear chaotic map for increasing its diversity of species, and to use sequential quadratic programming for accelerating local exploitation. Promising results are achieved in a variety of tasks where domain knowledge is not available. The experimental results show that the proposed method has the ability of selecting the discriminating input features correctly and can achieve high accuracy of classification, which is comparable to or better than well-known similar classifier systems. Furthermore, the MGSA is tested on ten functions provided by CEC 2005 special session and compared with various modified Gravitational Search Algorithm, Particle Swarm Optimization, and Genetic Algorithm. The obtained results confirm the high performance of the MGSA in solving various problems in optimization.

In this paper, we develop a data-driven technique to model trees from a single laser scan. A multi-layer representation of the tree structure is proposed to guide the modeling process. In this process, a marching cylinder algorithm is first developed to construct visible branches from the laser scan data. Three levels of crown feature points are then extracted from the scan data to synthesize three layers of non-visible branches. Based on the hierarchical particle flow technique, the branch synthesis method has the advantage of producing visually convincing tree models that are consistent with scan data. User intervention is extremely limited. The robustness of this technique has been validated on both conifer and broadleaf trees.

Hydraulic cylinder is an indispensable linear actuator in high power applications like construction machinery. In order to reduce the energy consumption, the noise and the waste oil disposal pollution of the hydraulic cylinder control system, the most direct method is adopting the direct pump control technology which eliminates the throttle losses in the main power line. In such system, by changing the speed or the displacement of the pump, the pressure and volume flow will be matched with the need of loads. To date, research works in this field have been reported in many articles, but they are scattered and written in different languages. An overview which can summarize the latest development of this technology appears to be necessary. This paper provides a comprehensive review on this technology, aiming at clarifying recent advances and outlining potential challenges in the research and application of this technology. The review mainly covers three parts: system structure, control, and derived energy recovery system. Also the evolvement of the electro-hydraulic cylinder control system is introduced. The review indicates that attentions should be paid to the control and energy recovery plan of the direct pump controlled cylinder system, and to the newly proposed asymmetric pump controlled differential cylinder technology. It is envisaged that the information gathered in this paper will be a valuable one-stop source of information for researchers, as well as providing a direction for future research in this area.

In this study, we have a research on wave action on the submarine launched missile water trajectory and gesture angles during the process between launch and exit from water. Infinite water depth plane wave was used as the wave model, mathematics models of missile exceeding water under different wave conditions were established based on ideal potential flow theory. The flow field velocity potential was obtained by solving the Laplace equation, thus can obtain missile surface pressure. Considering free surface effects, simple Green's function was introduced to solve boundary value problems. Three-dimensional Fortran program and finite software ABAQUS were combined to complete the fluid-structure interaction simulation. The rules that wave level and phases effects on submarine- launched missile were finally obtained, which shows wave affect cannot be neglected. Simulation methods and results of this study have a certain reference value for the submarine-launched missile launching.