Efficient Human Epithelial-2 cell image classification can facilitate the diagnosis of many autoimmune diseases. This paper proposes an automatic framework for this classification task, by utilizing ...the deep convolutional neural networks (CNNs) which have recently attracted intensive attention in visual recognition. In addition to describing the proposed classification framework, this paper elaborates several interesting observations and findings obtained by our investigation. They include the important factors that impact network design and training, the role of rotation-based data augmentation for cell images, the effectiveness of cell image masks for classification, and the adaptability of the CNN-based classification system across different datasets. Extensive experimental study is conducted to verify the above findings and compares the proposed framework with the well-established image classification models in the literature. The results on benchmark datasets demonstrate that 1) the proposed framework can effectively outperform existing models by properly applying data augmentation, 2) our CNN-based framework has excellent adaptability across different datasets, which is highly desirable for cell image classification under varying laboratory settings. Our system is ranked high in the cell image classification competition hosted by ICPR 2014.
•Synthesis of SA–CMC–Ca–Fe gel beads through cross-linking beading of SA and CMC in CaCl2 and FeCl3 solutions.•SA–CMC gel bead shows larger specific surface area and porosity due to the internal ...network structure.•The lead ions’ removal rate by SA–CMC is significantly better than the conventional adsorbents.•The high Pb2+ adsorption capacity of SA–CMC was discussed by different adsorption isotherms.•Based on different kinetic study, chemical adsorption is the main adsorption process of Pb2+ adsorption of SA–CMC gel beads.
Alginate–carboxymethyl cellulose (CMC) gel beads were prepared in this study using sodium alginate (SA) and sodium CMC through blending and cross-linking. The specific surface area and aperture of the prepared SA–CMC gel beads were tested. The SA–CMC structure was characterized and analyzed via infrared spectroscopy, scanning electron microscopy, and energy-dispersive X-ray spectroscopy. Static adsorption experiment demonstrated that Pb(II) adsorption of SA–CMC exceeded 99% under the optimized conditions. In addition, experiments conducted under the same experimental conditions showed that the lead ion removal efficiency of SA–CMC was significantly higher than that of conventional adsorbents. The Pb(II) adsorption process of SA–CMC followed the Langmuir adsorption isotherm, and the dynamic adsorption model could be described through a pseudo-second-order rate equation. Pb(II) removal mechanisms of SA–CMC, including physical, chemical, and electrostatic adsorptions, were discussed based on microstructure analysis and adsorption kinetics. Chemical adsorption was the main adsorption method among these mechanisms.
This paper proposes a new method, i.e., weighted hierarchical depth motion maps (WHDMM) + three-channel deep convolutional neural networks (3ConvNets), for human action recognition from depth maps on ...small training datasets. Three strategies are developed to leverage the capability of ConvNets in mining discriminative features for recognition. First, different viewpoints are mimicked by rotating the 3-D points of the captured depth maps. This not only synthesizes more data, but also makes the trained ConvNets view-tolerant. Second, WHDMMs at several temporal scales are constructed to encode the spatiotemporal motion patterns of actions into 2-D spatial structures. The 2-D spatial structures are further enhanced for recognition by converting the WHDMMs into pseudocolor images. Finally, the three ConvNets are initialized with the models obtained from ImageNet and fine-tuned independently on the color-coded WHDMMs constructed in three orthogonal planes. The proposed algorithm was evaluated on the MSRAction3D, MSRAction3DExt, UTKinect-Action, and MSRDailyActivity3D datasets using cross-subject protocols. In addition, the method was evaluated on the large dataset constructed from the above datasets. The proposed method achieved 2-9% better results on most of the individual datasets. Furthermore, the proposed method maintained its performance on the large dataset, whereas the performance of existing methods decreased with the increased number of actions.
To make the interface design of computer application system better, meet the psychological and emotional needs of users, and be more humanized, the emotional factor is increasingly valued by ...interface designers. In the design of human-computer interaction graphical interfaces, the designer attaches great importance to the emotional design of the interface, and enhances the humanized design of the interface, which cannot only improve the comfort of the interface, but also improve the fun of the interface, to ensure the psychological and emotional needs of users can be better satisfied. It may acquire information that is favorable to innovative design by utilizing cluster analysis algorithm to tackle the problem of complicated cultural information, and then utilize cellular genetic algorithm to carry out creative design of cultural items. It increases the availability of cultural and creative goods. The classic cluster analysis technique offers the maximum data clustering effect of 53.3%, according to the findings of this paper’s experiments. While the improved cluster analysis algorithm has the highest data clustering effect of 90%. It can be seen that the improved cluster analysis algorithm can effectively perform cluster analysis on a large amount of data in cultural and creative products. It thus finds out the most suitable designer’s creative information, which helps designers create better products.
Moso bamboo (Phyllostachys edulis) is an economically and ecologically important nontimber forestry species. Further development of this species as a sustainable bamboo resource has been hindered by ...a lack of population genome information. Here, we report a moso bamboo genomic variation atlas of 5.45 million single-nucleotide polymorphisms (SNPs) from whole-genome resequencing of 427 individuals covering 15 representative geographic areas. We uncover low genetic diversity, high genotype heterozygosity, and genes under balancing selection underlying moso bamboo population adaptation. We infer its demographic history with one bottleneck and its recently small population without a rebound. We define five phylogenetic groups and infer that one group probably originated by a single-origin event from East China. Finally, we conduct genome-wide association analysis of nine important property-related traits to identify candidate genes, many of which are involved in cell wall, carbohydrate metabolism, and environmental adaptation. These results provide a foundation and resources for understanding moso bamboo evolution and the genetic mechanisms of agriculturally important traits.
Existing unsupervised visual odometry (VO) methods either match pairwise images or integrate the temporal information using recurrent neural networks over a long sequence of images. They are either ...not accurate, time-consuming in training or error accumulative. In this paper, we propose a method consisting of two camera pose estimators that deal with the information from pairwise images and a short sequence of images, respectively. For image sequences, a transformer-like structure is adopted to build a geometry model over a local temporal window, referred to as transformer-based auxiliary pose estimator (TAPE). Meanwhile, a flow-to-flow pose estimator (F2FPE) is proposed to exploit the relationship between pairwise images. The two estimators are constrained through a simple yet effective consistency loss in training. Empirical evaluation has shown that the proposed method outperforms the state-of-the-art unsupervised learning-based methods by a large margin and performs comparably to supervised and traditional ones on the KITTI and Malaga dataset.
The product design major was formally established in 2011 and has been an important part of Chinese art education since then. At the same time, it has laid a solid foundation for the development of ...China’s higher education. Therefore, the product design major occupies an important position in China’s higher education and plays an irreplaceable role in cultivating industrial design talents for the country. With the continuous development and progress of national education, the teaching of product design is also constantly innovating, in order to better improve the teaching effect of product design and cultivate more product design professionals for the country. The purpose of this paper is to study the teaching of product design major based on intelligent network teaching, establish an intelligent network teaching system, and carry out intelligent network teaching experiment of product design major based on this system. The experiment concluded that the overall satisfaction of the students majoring in product design on the intelligent network teaching reached 82%, and the intelligent network teaching mode also increased the outstanding performance rate of the students majoring in product design by 30%.
With deep convolutional features, cross-region matching (CRM) has recently shown superior performance on image retrieval. It evaluates image similarity by comparing image regions at different ...locations and scales, and is, therefore, more robust to geometric variance of objects. This paper first scrutinizes CRM-based image retrieval to provide a rigorous probabilistic interpretation by following the probability ranking principle. In addition to manifesting the assumptions implicitly taken by CRM, our interpretation highlights a fundamental issue hindering the performance of CRM-when comparing two image regions, CRM ignores modeling the distribution of the visual concept class associated with an image region, making the similarity comparison less precise. Taking advantage of the unprecedented representation capability of deep convolutional features, this paper proposes one approach to tackle that issue. It treats locally clustered image regions as a pseudo-labeled class sharing the same visual concept and utilizes them to model the distribution of the visual concept class associated with an image region. Both non-parametric and parametric methods are developed for this purpose, with careful probabilistic justification. Extensive experimental study on multiple benchmark data sets demonstrates the superior performance of the proposed pseudo-label approach to CRM and other comparable methods, with the maximum improvement of more than 10 percentage points over CRM.
Scene flow describes the motion of 3D objects in real world and potentially could be the basis of a good feature for 3D action recognition. However, its use for action recognition, especially in the ...context of convolutional neural networks (ConvNets), has not been previously studied. In this paper, we propose the extraction and use of scene flow for action recognition from RGB-D data. Previous works have considered the depth and RGB modalities as separate channels and extract features for later fusion. We take a different approach and consider the modalities as one entity, thus allowing feature extraction for action recognition at the beginning. Two key questions about the use of scene flow for action recognition are addressed: how to organize the scene flow vectors and how to represent the long term dynamics of videos based on scene flow. In order to calculate the scene flow correctly on the available datasets, we propose an effective self-calibration method to align the RGB and depth data spatially without knowledge of the camera parameters. Based on the scene flow vectors, we propose a new representation, namely, Scene Flow to Action Map (SFAM), that describes several long term spatio-temporal dynamics for action recognition. We adopt a channel transform kernel to transform the scene flow vectors to an optimal color space analogous to RGB. This transformation takes better advantage of the trained ConvNets models over ImageNet. Experimental results indicate that this new representation can surpass the performance of state-of-the-art methods on two large public datasets.
Modern supply chain is a complex system and plays an important role for different sectors under the globalization economic integration background. Supply chain management system is proposed to handle ...the increasing complexity and improve the efficiency of flows of goods. It is also useful to prevent potential frauds and guarantee trade compliance. Currently, most companies maintain their own IT systems for supply chain management. However, it is hard for these isolated systems to work together and provide a global view of the status of the highly distributed supply chain system. Using emerging decentralized ledger/blockchain technology, which is a special type of distributed system in essence, to build supply chain management system is a promising direction to go. Decentralized ledger usually suffers from low performance and lack of capability to protect information stored on the ledger. To overcome these challenges, we propose CoC (supply chain on blockchain), a novel supply chain management system based on a hybrid decentralized ledger with a novel two-step block construction mechanism. We also design an efficient storage scheme and information protection method that satisfy requirements of supply chain management. These techniques can also be applied to other decentralized ledger based applications with requirements similar to supply chain management.
PDF
