With the rapid development of service-oriented computing (SOC)/service-oriented architecture (SOA), cloud computing and web services, cloud-based design and manufacture (CBDM) is emerging as ...state-of-the-art technologies and methodologies to enable collaborative product development (CPD). CBDM-enabled CPD can provide cost-effective, flexible and scalable solutions to collaborative partners by sharing the resources in the applications of design and manufacturing. Feature-based data exchange (FBDE) has been one of the key issues in history of CPD and should be adapted in lasted CBDM-enabled CPD. Firstly this paper presents a service-oriented architecture for data exchange in CBDM. Within this architecture, FBDE was registered as service and FBDE users in the CBDM environment can acquire a set of FBDE services to replace the traditional FBDE functions among heterogeneous CAD systems. Secondly, in orderto put the philosophy of FBDE-as-a-Service into practice for CBDM, this paper proposes a peerto peer (P2P) approach for service-oriented FBDE, which revolutionizes the traditional centralized and neutral-file based approach. Thirdly, technique issues of FBDE-as-a-Service in P2P architecture are discussed in details, including constituting of the P2P FBDE service, procedure of service-oriented P2P FBDE, pre-P2P FBDE service, topological entity matching between pre/post-P2P service and post-P2P FBDE service. Finally, a case study of data exchange is tested to demonstrate the proposed idea of service-oriented FBDE for CBDM.
•This paper discovers the spatial locality feature of point sets and proposes a novel search algorithm called local start search (LSS) to compute the exact Hausdorff Distance. The LSS algorithm can ...greatly reduce the running time when dealing with large scale of point set, in which the spatial continuity and distance continuity are very common.•LSS maintains high performance in both overlap and non-overlap situations of a pair of regular point sets, while EARLYBREAK experiences degraded performance in overlap situations.•Furthermore, for general point sets in overlap situations, the preprocess of excluding the intersection in EARLYBREAK will fail. However, LSS can still process the general point sets with different point sizes after ordering the sets.•Our algorithm outperforms the state-of-the-art algorithm. Experiments demonstrate the efficiency and accuracy of the proposed method.
The Hausdorff Distance (HD) is a very important similarity measurement in Pattern Recognition, Shape Matching and Artificial Intelligence. Because of its inherent computational complexity, computing the HD using the NAIVEHD (brute force) algorithm is difficult, especially for comparing the similarity between large scale point sets in the time of big data. To overcome this problem, we propose a novel, efficient and general algorithm for computing the exact HD for arbitrary point sets, which takes advantage of the spatial locality of point sets, namely, Local Start Search (LSS). Different from the state-of-the-art algorithm EARLYBREAK in PAMI 2015, our idea comes from the observation and fact that the neighbor points of a break position in the current loop have higher probability to break the next loop than other points. Therefore, in our algorithm, we add a new mechanism to record the current break position as a start position, which is initialized as search center of the next loop. Then, LSS executes the next loop by scanning the neighbor points around the center. In this way, LSS maintains high performance in both overlap and non-overlap situations. Furthermore, the LSS algorithm can process arbitrary data by adopting the Morton Curve to establish the order of scattered point sets, while the EARLYBREAK is mainly applied to regular data which require the same grid size, such as medical images or voxel data. In the non-overlapping situation when comparing pairs of arbitrary point sets, LSS achieves performance as good as EARLYBREAK algorithm. While in the overlapping situation when comparing pairs of arbitrary point sets, LSS is faster than EARLYBREAK by three orders of magnitude. Thus, as a whole, LSS outperforms EARLYBREAK. In addition, LSS compared against the increment hausdorff distance calculation algorithm (INC) and significantly outperforms it by an order of magnitude faster. Experiments demonstrate the efficiency and accuracy of the proposed method.
The complexity and diversity of buildings make it challenging to extract low-level and high-level features with strong feature representation by using deep neural networks in building extraction ...tasks. Meanwhile, deep neural network-based methods have many network parameters, which take up a lot of memory and time in training and testing. We propose a novel fully convolutional neural network called the Context Feature Enhancement Network (CFENet) to address these issues. CFENet comprises three modules: the spatial fusion module, the focus enhancement module, and the feature decoder module. First, the spatial fusion module aggregates the spatial information of low-level features to obtain buildings’ outline and edge information. Secondly, the focus enhancement module fully aggregates the semantic information of high-level features to filter the information of building-related attribute categories. Finally, the feature decoder module decodes the output of the above two modules to segment the buildings more accurately. In a series of experiments on the WHU Building Dataset and the Massachusetts Building Dataset, our CFENet balances efficiency and accuracy compared to the other four methods we compared, and achieves optimality on all five evaluation metrics: PA, PC, F1, IoU, and FWIoU. This indicates that CFENet can effectively enhance and fuse buildings’ low-level and high-level features, improving building extraction accuracy.
Since the discovery of metal nanoparticles (NPs) in the 1960s, unknown toxicity, cost and the ethical hurdles of research in humans have hindered the translation of these NPs to clinical use. In this ...work, we demonstrate that Pt NPs with protein coronas are generated in vivo in human blood when a patient is treated with cisplatin. These self-assembled Pt NPs form rapidly, accumulate in tumors, and remain in the body for an extended period of time. Additionally, the Pt NPs are safe for use in humans and can act as anti-cancer agents to inhibit chemotherapy-resistant tumor growth by consuming intracellular glutathione and activating apoptosis. The tumor inhibitory activity is greatly amplified when the Pt NPs are loaded in vitro with the chemotherapeutic drug, daunorubicin, and the formulation is effective even in daunorubicin-resistant models. These in vivo-generated metal NPs represent a biocompatible drug delivery platform for chemotherapy resistant tumor treatment.
Self-attention networks have revolutionized the field of natural language processing and have also made impressive progress in image analysis tasks. Corrnet3D proposes the idea of first obtaining the ...point cloud correspondence in point cloud registration. Inspired by these successes, we propose an unsupervised network for non-rigid point cloud registration, namely NrtNet, which is the first network using a transformer for unsupervised large deformation non-rigid point cloud registration. Specifically, NrtNet consists of a feature extraction module, a correspondence matrix generation module, and a reconstruction module. Feeding a pair of point clouds, our model first learns the point-by-point features and feeds them to the transformer-based correspondence matrix generation module, which utilizes the transformer to learn the correspondence probability between pairs of point sets, and then the correspondence probability matrix conducts normalization to obtain the correct point set corresponding matrix. We then permute the point clouds and learn the relative drift of the point pairs to reconstruct the point clouds for registration. Extensive experiments on synthetic and real datasets of non-rigid 3D shapes show that NrtNet outperforms state-of-the-art methods, including methods that use grids as input and methods that directly compute point drift.
Estimating accurate 3D human poses from 2D images remains a challenge due to the lack of explicit depth information in 2D data. This paper proposes an improved mixture density network for 3D human ...pose estimation called the Locally Connected Mixture Density Network (LCMDN). Instead of conducting direct coordinate regression or providing unimodal estimates per joint, our approach predicts multiple possible hypotheses by the Mixture Density Network (MDN). Our network can be divided into two steps: the 2D joint points are estimated from the input images first; then, the information of human joints correlation is extracted by a feature extractor. After the human pose feature is extracted, multiple pose hypotheses are generated via the hypotheses generator. In addition, to make better use of the relationship between human joints, we introduce the Locally Connected Network (LCN) as a generic formulation to replace the traditional Fully Connected Network (FCN), which is applied to a feature extraction module. Finally, to select the most appropriate 3D pose result, a 3D pose selector based on the ordinal ranking of joints is adopted to score the predicted pose. The LCMDN improves the representation capability and robustness of the original MDN method notably. Experiments are conducted on the Human3.6M and MPII dataset. The average Mean Per Joint Position Error (MPJPE) of our proposed LCMDN reaches 50 mm on the Human3.6M dataset, which is on par or better than the state-of-the-art works. The qualitative results on the MPII dataset show that our network has a strong generalization ability.
Point clouds captured by 3D scans are typically sparse, irregular, and noisy, resulting in 3D wireframes reconstructed by existing approaches often containing redundant edges or lacking proper edges. ...To tackle these issues, this paper proposes a coarse-to-fine pipeline for 3D wireframe reconstruction from point clouds. First, a learning-based module is dedicated to predicting the corner and edge points from the input point cloud, and each pair of corner points is linked together to generate an initial 3D wireframe. Second, a coarse pruning module is utilized to generate a coarse 3D wireframe, which is achieved by pruning observable redundant edges from the initial 3D wireframe based on the asymmetric Chamfer distance. Third, a refined pruning module is used to generate a refined 3D wireframe with correct topological structures, which can help prune redundant edges that are difficult to observe from the coarse 3D wireframe. Finally, a heuristic algorithm is exploited to fine-tune the refined 3D wireframe to ensure the final 3D wireframe preserves the characteristics of both vertical and parallel. The experimental results reveal that the proposed method significantly improves the performance of 3D wireframes reconstruction from point clouds on the large-scale ABC dataset and a challenging furniture dataset.
Display omitted
•A coarse-to-fine 3D wireframe reconstruction approach for 3D point clouds.•Two different pruning modules are used successively to prune redundant edges.•Edge points are used as self-supervised labels for 3D wireframe reconstruction.•Preserve the characteristics of both vertical and parallel in 3D wireframes.•Achieve superior results to existing methods on 3D wireframe reconstruction.
In this study, we aimed to classify 7 cow behavior patterns automatically with an inertial measurement unit (IMU) using a fully convolutional network (FCN) algorithm. Behavioral data of 12 cows were ...collected by attaching an IMU in a waterproof box on the neck behind the head of each cow. Seven behavior patterns were considered: rub scratching (leg), ruminating-lying, lying, feeding, self-licking, rub scratching (neck), and social licking. To simplify the data and compare classification performance with or without magnetometer data, the 9-axis IMU data were reduced using the square root of the sum of squares to develop 2 datasets. Comparing the classification accuracy of the 3 models using a window size of 64 with 6-axis data and a window size of 128 with both 6-axis and 9-axis data, the best overall accuracy (83.75%) was achieved using the FCN model with a window size of 128 (12.8 s) using all IMU data. This model achieved classification accuracies of 83.2, 96.5, 92.8, 98.1, 82.9, 87.2, and 45.2% for ruminating-lying, lying, feeding, rub scratching (leg), self-licking, rub scratching (neck), and social licking, respectively. As a sequence of varied and intensive movement, the classification accuracy of behavior patterns related to skin disease was lower; better classification of these behavior patterns could be achieved with full IMU data and a larger window size. In the future, additional data will take into account different data types, such as audio and video data, to further enhance performance. In addition, an adaptive sliding window size will be used to improve model performance.
Display omitted
Sepsis is a clinical syndrome caused by uncontrollable immune dysregulation triggered by pathogen infection, characterized by high incidence, mortality rates, and disease burden. Current treatments ...primarily focus on symptomatic relief, lacking specific therapeutic interventions. The core mechanism of sepsis is believed to be an imbalance in the host’s immune response, characterized by early excessive inflammation followed by late immune suppression, triggered by pathogen invasion. This suggests that we can develop immunotherapeutic treatment strategies by targeting and modulating the components and immunological functions of the host’s innate and adaptive immune systems. Therefore, this paper reviews the mechanisms of immune dysregulation in sepsis and, based on this foundation, discusses the current state of immunotherapy applications in sepsis animal models and clinical trials.
Periodontitis is a prevalent disease and one of the leading causes of tooth loss. Biofilms are initiating factor of periodontitis, which can destroy periodontal tissue by producing virulence factors. ...The overactivated host immune response is the primary cause of periodontitis. The clinical examination of periodontal tissues and the patient's medical history are the mainstays of periodontitis diagnosis. However, there is a lack of molecular biomarkers that can be used to identify and predict periodontitis activity precisely. Non-surgical and surgical treatments are currently available for periodontitis, although both have drawbacks. In clinical practice, achieving the ideal therapeutic effect remains a challenge. Studies have revealed that bacteria produce extracellular vesicles (EVs) to export virulence proteins to host cells. Meanwhile, periodontal tissue cells and immune cells produce EVs that have pro- or anti-inflammatory effects. Accordingly, EVs play a critical role in the pathogenesis of periodontitis. Recent studies have also presented that the content and composition of EVs in saliva and gingival crevicular fluid (GCF) can serve as possible periodontitis diagnostic indicators. In addition, studies have indicated that stem cell EVs may encourage periodontal regeneration. In this article, we mainly review the role of EVs in the pathogenesis of periodontitis and discuss their diagnostic and therapeutic potential.