A novel garment transfer method supervised by distilled knowledge of virtual try-on model.

Garment transfer can wear the garment of the model image onto the personal image. As garment transfer leverages wild and cheap garment input, it has attracted tremendous attention in the community and has a huge commercial potential. Since the ground truth of garment transfer is almost unavailable in reality, previous studies have treated garment transfer as either pose transfer or garment-pose disentanglement, and trained garment transfer in self-supervised learning, However, these implementation methods do not cover garment transfer intentions completely and face the robustness issue in the testing phase. Notably, virtual try-on technology has exhibited superior performance using self-supervised learning, we propose to supervise the garment transfer training via knowledge distillation from virtual try-on. Specifically, the overall pipeline is first to infer a garment transfer parsing, and to use it to guide downstream warping and inpainting tasks. The transfer parsing reasoning model learns the response and feature knowledge from the try-on parsing reasoning model and absorbs the hard knowledge from the ground truth. The progressive flow warping model learns the content knowledge from virtual try-on for a reasonable and precise garment warping. To enhance transfer realism, we propose an arm regrowth task to infer exposed skin. Experiments demonstrate that our method has state-of-the-art performance in transferring garments between persons compared with other virtual try-on and garment transfer methods.

Robustness optimization for rapid prototyping of functional artifacts based on visualized computing digital twins.

This study presents a robustness optimization method for rapid prototyping (RP) of functional artifacts based on visualized computing digital twins (VCDT). A generalized multiobjective robustness optimization model for RP of scheme design prototype was first built, where thermal, structural, and multidisciplinary knowledge could be integrated for visualization. To implement visualized computing, the membership function of fuzzy decision-making was optimized using a genetic algorithm. Transient thermodynamic, structural statics, and flow field analyses were conducted, especially for glass fiber composite materials, which have the characteristics of high strength, corrosion resistance, temperature resistance, dimensional stability, and electrical insulation. An electrothermal experiment was performed by measuring the temperature and changes in temperature during RP. Infrared thermographs were obtained using thermal field measurements to determine the temperature distribution. A numerical analysis of a lightweight ribbed ergonomic artifact is presented to illustrate the VCDT. Moreover, manufacturability was verified based on a thermal-solid coupled finite element analysis. The physical experiment and practice proved that the proposed VCDT provided a robust design paradigm for a layered RP between the steady balance of electrothermal regulation and manufacturing efficacy under hybrid uncertainties.

Design, fabrication and application of self-spiraling pattern-driven 4D-printed actuator.

Self-spiraling actuators are widely found in nature and have high research and actuator-application value in self-lock and self-assembly. Four-dimensional (4D) printing is a new generation additive manufacturing of smart materials and has shown great potential for the fabrication of multi-functional and customized structures. The microarchitecture design of a bilayer actuator could bring flexible and diversified self-spiraling behaviors and more possibilities for practical application by combing 4D printing. This work investigates the stimuli effects of fiber patterns and fabrication parameters on self-spiraling behaviors of the bilayer actuator via both experimental and theoretical methods. This work may potentially provide pattern design guidance for 4D-printed self-spiraling actuators to meet different application requirements.

Privacy-preserving for assembly deviation prediction in a machine learning model of hydraulic equipment under value chain collaboration.

Hydraulic equipment, as a typical mechanical product, has been wildly used in various fields. Accurate acquisition and secure transmission of assembly deviation data are the most critical issues for hydraulic equipment manufacturer in the PLM-oriented value chain collaboration. Existing deviation prediction methods are mainly used for assembly quality control, which concentrate in the product design and assembly stage. However, the actual assembly deviations generated in the service stage can be used to guide the equipment maintenance and tolerance design. In this paper, a high-fidelity prediction and privacy-preserving method is proposed based on the observable assembly deviations. A hierarchical graph attention network (HGAT) is established to predict the assembly feature deviations. The hierarchical generalized representation and differential privacy reconstruction techniques are also introduced to generate the graph attention network model for assembly deviation privacy-preserving. A derivation gradient matrix is established to calculate the defined modified necessary index of assembly parts. Two privacy-preserving strategies are designed to protect the assembly privacy of node representation and adjacent relationship. The effectiveness and superiority of the proposed method are demonstrated by a case study with a four-column hydraulic press.

A semantic analysis-driven customer requirements mining method for product conceptual design.

Precise customer requirements acquisition is the primary stage of product conceptual design, which plays a decisive role in product quality and innovation. However, existing customer requirements mining approaches pay attention to the offline or online customer comment feedback and there has been little quantitative analysis of customer requirements in the analogical reasoning environment. Latent and innovative customer requirements can be expressed by analogical inspiration distinctly. In response, this paper proposes a semantic analysis-driven customer requirements mining method for product conceptual design based on deep transfer learning and improved latent Dirichlet allocation (ILDA). Initially, an analogy-inspired verbal protocol analysis experiment is implemented to obtain detailed customer requirements descriptions of elevator. Then, full connection layers and a softmax layer are added to the output-end of Chinese bidirectional encoder representations from Transformers (BERT) pre-training language model. The above deep transfer model is utilized to realize the customer requirements classification among functional domain, behavioral domain and structural domain in the customer requirement descriptions of elevator by fine-tuning training. Moreover, the ILDA is adopted to mine the functional customer requirements that can represent customer intention maximally. Finally, an effective accuracy of customer requirements classification is acquired by using the BERT deep transfer model. Meanwhile, five kinds of customer requirements of elevator and corresponding keywords as well as their weight coefficients in the topic-word distribution are extracted. This work can provide a novel research perspective on customer requirements mining for product conceptual design through natural language processing.

Synthesis of CoNi-layered double hydroxide on graphene oxide as adsorbent and construction of detection method for taste and odor compounds in smelling water.

Taste and odor (T&O) compounds are important water pollutant, some of which are toxic. The relevant studies are all expand upon the well-known T&O compounds but for the unknown odors in smelling water. In this work, a method combining purge and trap with gas chromatograph-mass spectrometer (PT-GC/MS) and disperse solid-phase extraction with gas chromatograph (GC) was first proposed to detect T&O compounds in unknown odorous water accurately. Firstly, PT-GC/MS was used for a qualitative test on unknown odors in smelling water and determine the analytes. The hollow CoNi-layered double hydroxide (LDH) on graphene oxide (GO) was then used as a composite adsorbent to pretreat the water, in which the GO provided large specific surface, and the LDH worked as a confinement cavity to enhance capture and retention capacity for volatile organic compounds (VOCs). According to the properties of T&O compounds determined by PT-GC/MS in water, a corresponding GC method was established for accurately quantitative analysis. In this paper, five T&O compounds were detected simultaneously, including dimethyl sulfide, meistylene, N, N-dimethylbenzylamine, 2, 4-dimethylbenzaldehyde and 2, 4-di-tert-butylphenol. Extraction parameters were optimized, including ratio of desorption solvent, amount of adsorbent, pH value, etc. Under the optimal conditions, the detection limits for analysis were 1.14 µg/L to 3.07 mg/L. The satisfactory recoveries were 94-98%. Furthermore, two optimal determination outcomes of odor waters from different places support the practicability of the method, which is expected to be widely used in the detection of unknown odors in smelling water.

Support Diminution Design for Layered Manufacturing of Manifold Surface Based on Variable Orientation Tracking.

This article proposes a support diminution design method for layered manufacturing of manifold surface based on variable orientation tracking (VOT). We aim at reducing the external support or upholders to a minimum with maximum possibility theoretically to save material and diminish material stripping effect (MSE), thereby improving the bilateral surface precision either exterior or interior. The cosmic gravity effect criterion is first used to extract surface need support from manifold surface with various materials by considering the balance force involving material characteristics and inclination angle. In the light of this criterion theory, varying the substrate normal orientation (SNO), namely workbench, for each layer in printing coordinate system, may break the balance between gravity and its equilibrium force. Therefore, the optimal SNO can be rigorously calculated using mathematical harmonic analysis among the continuous domain. To serve for the multidegree of freedom (DOF) on account of SNO, a reconfigurable VOT robot with six-axis DOF is developed for 3D printing (3DP). The matched servo controller is successfully implemented to accurate tracking of both orientation and Cartesian coordinates, using forward kinematic chains as well as reverse kinematic tracking. What is more, the end-effector (extruder) is holding perpendicular to the substrate workbench. The physical experiment that takes human external ear auricle, for example, using a layer-based process is implemented via VOT. The MSE due to supporting material can be clearly observed and diminished using an optical microscope. The stripped material from external support via diminution design can be evaluated quantitatively by electronic weighting balance. All of which indicate the findings that external support in 3DP can be virtually reckoned and diminished using VOT rather than the so-called build orientation traversal method. The VOT method upon which we touched can be widely applied to various layered manufacturing of accurate structure, for instance, cantilever, sandwich, and scaffolds in the occasion needing precise curtailment of outer support multimaterial.

Biomechanical performance design of joint prosthesis for medical rehabilitation via generative structure optimization.

This paper proposes a biomechanical performance design method of joint prosthesis for medical rehabilitation via Generative Structure Optimization (GSO). Firstly, the 3D reconstruction of manifold structure involving hard bone and cartilage is sequentially and progressively implemented from heterogeneous medical images such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) via iteration. On the basis of reconstructed mesh structure, the finite element method (FEM) is hereby employed to verify the structure by evaluating the mechanical force distribution. The biomechanical performance design model for 3 D printing (3DP) is then built using multi-objective optimization (MOO) by considering adaptive layer thickness, infill patterns and infill trajectories, etc. The GSO outlets a generative data-driven system which covers various stages such as personalized CT, subsequent 3 D reconstruction, further finite element analysis (FEA) and even structural parameter optimization. The physical experiment of Additive manufacturing (AM) proves that, the relative density, surface topography and wear-resisting performance of joint prosthesis can be improved by GSO which helps to improve biomechanical performance, including kinematics and dynamics. The proposed method may arouse the huge attention in the prosthesis applications to promote patients' high-end customization well-being.

Myelin sheath structure and regeneration in peripheral nerve injury repair.

Observing the structure and regeneration of the myelin sheath in peripheral nerves following injury and during repair would help in understanding the pathogenesis and treatment of neurological diseases caused by an abnormal myelin sheath. In the present study, transmission electron microscopy, immunofluorescence staining, and transcriptome analyses were used to investigate the structure and regeneration of the myelin sheath after end-to-end anastomosis, autologous nerve transplantation, and nerve tube transplantation in a rat model of sciatic nerve injury, with normal optic nerve, oculomotor nerve, sciatic nerve, and Schwann cells used as controls. The results suggested that the double-bilayer was the structural unit that constituted the myelin sheath. The major feature during regeneration was the compaction of the myelin sheath, wherein the distance between the 2 layers of cell membrane in the double-bilayer became shorter and the adjacent double-bilayers tightly closed together and formed the major dense line. The expression level of myelin basic protein was positively correlated with the formation of the major dense line, and the compacted myelin sheath could not be formed without the anchoring of the lipophilin particles to the myelin sheath.

A Robust Predicted Performance Analysis Approach for Data-Driven Product Development in the Industrial Internet of Things.

Industrial Internet of Things (IoT) is a ubiquitous network integrating various sensing technologies and communication technologies to provide intelligent information processing and smart control abilities for the manufacturing enterprises. The aim of applying industrial IoT is to assist manufacturers manage and optimize the entire product manufacturing process to improve product quality and production efficiency. Data-driven product development is considered as one of the critical application scenarios of industrial IoT, which is used to acquire the satisfied and robust design solution according to customer demands. Performance analysis is an effective tool to identify whether the key performance have reached the requirements in data-driven product development. The existing performance analysis approaches mainly focus on the metamodel construction, however, the uncertainty and complexity in product development process are rarely considered. In response, this paper investigates a robust performance analysis approach in industrial IoT environment to help product developers forecast the performance parameters accurately. The service-oriented layered architecture of industrial IoT for product development is first described. Then a dimension reduction approach based on mutual information (MI) and outlier detection is proposed. A metamodel based on least squares support vector regression (LSSVR) is established to conduct performance prediction process. Furthermore, the predicted performance analysis method based on confidence interval estimation is developed to deal with the uncertainty to improve the robustness of the forecasting results. Finally, a case study is given to show the feasibility and effectiveness of the proposed approach.

Precise and robust binocular camera calibration based on multiple constraints.

Precise calibration of a binocular vision system is the foundation of binocular vision measurement. In this paper, we propose a highly precise and robust binocular camera calibration method, which is devoted to minimize the error between the geometric relation of 3D reconstructed feature points and the ground truth, such as adjacent distance error, collinear error, and right-angle error. In addition, the reprojection error and epipolar are introduced to satisfy the homography relation and epipolar geometry theory better. We optimize all intrinsic parameters, extrinsic parameters, and distortion parameters to minimize the objective function, which is the sum of a series of nonlinear least squares terms. Levenberg-Marquardt iterative algorithm is used to find the optimal solution of the camera parameters. To test the precision and robustness of the proposed method, both actual measurement experiments and Gauss noise-adding experiments are carried out. The experimental results show that compared with the other two calibration methods in the contrast experiment, the distance measurement error, collinear error, and right-angle error are reduced dramatically. It is noticeable that in Gauss noise-adding experiments, the calibration parameters estimated by the proposed method are more stable.

A Framework of Joint Energy Provisioning and Manufacturing Scheduling in Smart Industrial Wireless Rechargeable Sensor Networks.

Energy provisioning is always a crucial problem restricting the further development and application of smart industrial wireless sensor networks in smart factories. In this paper, we present that it is necessary to develop smart industrial wireless rechargeable sensor networks (SIWRSNs) in a smart factory environment. Based on the complexity and time-effectiveness of factory operations, we establish a joint optimization framework named J-EPMS to effectively coordinate the charging strategies of wireless sensors and the scheduling plans of machines running. Then, we propose a novel double chains quantum genetic algorithm with Taboo search (DCQGA-TS) for J-EPMS to obtain a suboptimal solution. The simulation results demonstrate that the DCQGA-TS algorithm can maximally ensure the continuous manufacturing and markedly shorten the total completion time of all production tasks.

Exploring 3D Human Action Recognition: from Offline to Online.

With the introduction of cost-effective depth sensors, a tremendous amount of research has been devoted to studying human action recognition using 3D motion data. However, most existing methods work in an offline fashion, i.e., they operate on a segmented sequence. There are a few methods specifically designed for online action recognition, which continually predicts action labels as a stream sequence proceeds. In view of this fact, we propose a question: can we draw inspirations and borrow techniques or descriptors from existing offline methods, and then apply these to online action recognition? Note that extending offline techniques or descriptors to online applications is not straightforward, since at least two problems-including real-time performance and sequence segmentation-are usually not considered in offline action recognition. In this paper, we give a positive answer to the question. To develop applicable online action recognition methods, we carefully explore feature extraction, sequence segmentation, computational costs, and classifier selection. The effectiveness of the developed methods is validated on the MSR 3D Online Action dataset and the MSR Daily Activity 3D dataset.

Salvianolic acid B regulates gene expression and promotes cell viability in chondrocytes.

Articular chondrocytes reside in lacunae distributed in cartilage responsible for the remodelling of the tissue with limited ability of damage repairing. The in vitro expanded chondrocytes enhanced by factors/agents to obtain large numbers of cells with strengthened phenotype are essential for successful repair of cartilage lesions by clinical cell implantation therapies. Because the salvianolic acid B (Sal B), a major hydrophilic therapeutic agent isolated from Salvia miltiorrhiza, has been widely used to treat diseases and able to stimulate activity of cells, this study examines the effects of Sal B on passaged chondrocytes. Chondrocytes were treated with various concentrations of Sal B in monolayer culture, their morphological properties and changes, and mitochondrial membrane potential were analysed using microscopic analyses, including cellular biochemical staining and confocal laser scanning microscopy. The proteins were quantified by BCA and Western blotting, and the transcription of genes was detected by qRT-PCR. The passaged chondrocytes treated with Sal B showed strengthened cellular synthesis and stabilized mitochondrial membrane potential with upregulated expression of the marker genes for chondrocyte phenotype, Col2-α1, Acan and Sox9, the key Wnt signalling molecule ß-catenin and paracrine cytokine Cytl-1. The treatments using CYTL-1 protein significantly increased expression of Col2-α1 and Acan with no effect on Sox9, indicating the paracrine cytokine acts on chondrocytes independent of SOX9. Sal B has ultimately promoted cell growth and enhanced chondrocyte phenotype. The chondrocytes treated with pharmaceutical agent and cytokine in the formulated medium for generating large number of differentiated chondrocytes would facilitate the cell-based therapies for cartilage repair.

[Changes in splenocyte proliferation, subsets and cytokine production in mice immunized with recombinant vaccine Bifidobacterium bifidum (pGEX-Sj32) of Schistosoma japonicum].

OBJECTIVE: To observe the dynamic changes of immune responses of splenocytes in mice immunized with recombinant vaccine Bifidobacterium bifidum (pGEX-Sj32) of Schistosoma japonicum and investigate the immunological mechanism of the vaccine. METHODS: Eighty-eight BALB/c mice were randomized for immunization with 106 CFU recombinant vaccine orally or with 105 CFU recombinant vaccine intranasally. Four mice were selected from each group every two weeks to test the responses of the splenocytes to stimulations with SjAWA or ConA. MTT assay and flow cytometry were used to assess splenocyte proliferation and the distribution of CD4⁺ and CD8⁺ T cells, respectively; the levels of interleukin-10 (IL-10), IL-12 and tumor necrosis factor-α (TNF-α) in the cell culture supernatant were detected by ELISA. RESULTS: Regardless of the stimulations, the splencytes showed significantly enhanced proliferation in weeks 2-16 in oral administration group and in weeks 2-18 in intranasal group (P<0.01). CD4⁺ subsets in both two groups increased obviously in weeks 2-12 (P<0.01) but CD8⁺ subsets remained stable. In oral administration group, the levels of TNF-α, IL-10 and IL-12 increased in weeks 2-14, 2-18 and 2-14, and peaked at week 8, 10 and 6, respectively; in intranasal group, the cytokines increased in weeks 2-14, 2-18 and 2-18, and peaked at week 8, 10 and 8, respectively. CONCLUSION: The recombinant vaccine rBb (pGEX-Sj32) can induce effective immune responses in mice.

New bone formation and microstructure assessed by combination of confocal laser scanning microscopy and differential interference contrast microscopy.

Bone is a mineralized connective tissue that is continuously and microstructurally remodeled. Altered bone formation and microstructure arise in pathological bone conditions such as osteoporosis, osteonecrosis, fracture repair, and Paget disease of bone. A proper and objective assessment of bone formation and microstructure will provide insight into the understanding of bone pathogenesis and remodeling. Here, new bone formation ex vitro and its microstructure were evaluated in in vivo multiple sequential polychrome-labeled samples using confocal laser scanning microscopy (CLSM), which generated clearer and more reliable images of thick bone sections than conventional fluorescence microscopy (CFM). Intriguingly, fine details of the bone microstructural features, including the mineralization fronts, quiescent versus active osteons, and Volkmann's channel, were elucidated using CLSM, which defines the relationship between morphological changes and function, when combined with differential interference contrast microscopy. Furthermore, CLSM provided objective evaluations of bone formation, such as the ratio of labeled areas of new bone formation in a rabbit model when compared with CFM. Altogether, new bone formation and its microstructure can be evaluated more adequately using a combination of CLSM and DIC microscopies.

MRI and histologic analysis of collagen type II sponge on repairing the cartilage defects of rabbit knee joints.

There are limited treatment options for cartilage defects in clinical practice because of the lack of suitable biomaterials. Here, we evaluated the effects of collagen type II sponge on the articular cartilage repairing process using a cartilage injury of a rabbit knee joint model. We showed that the home-made collagen type II sponges appeared to have a suitable pore size of 93.26 ± 38.4 µm for chondrocyte growth. MRI with H&E staining results demonstrated that the effusion absorption in the collagen type II sponge treated group was quicker than that of the control group. Moreover, sporadic cartilage signals first appeared at 6 weeks in the collagen type II sponge treated group. Safranin O staining and immunohistochemical analysis confirmed that the newly formed cartilage expresses glycosaminoglycan and type II collagen matrix. Using Sirius red polarized light staining, we showed that the newly formed cartilage-like areas from the collagen type II treated group are significantly greater than those of the control group. Taken together, our data demonstrated that the home-made collagen type II sponge is able to promote cartilage repair in the cartilage injury of a rabbit knee joint model.

[An experimental study of using chitinous membrane as the culture scaffold for epidermal stem cells].

OBJECTIVE: To investigate the feasibility of constructing a skin tissue engineering covering on chitinous membrane using rat epidermal stem cells (ESCs). METHODS: Rat ESCs were isolated and cultured by cold digestive method and collagen type IV adherent method. Cell colonies were observed with inverted microscope. Expressions of DNA and RNA of ESCs were detected with laser scanning confocal microscope. Growth curves of cells were determined with Alamar BlueTM colorimetric method. Expressions of surface markers of ESCs (CD29, CD71, CD49d, and CD34) were detected with flow cytometer. Positive expressions of CK15, CK19, and P63 of ESCs were determined by immunohistochemistry. Influence of original chitinous membrane leachate in different dilutions on ESCs was observed. Condition of growth of ESCs on the vehicle was observed. RESULTS: Isolated cultured cells were verified as ESCs, of which the doubling generation time was 48 hs. CD29 and CD49d were positive; CD71 and CD34 were negative; CK19, CK15, and P63 were positive. Compared with that of control group, ESCs cultured in chitinous membrane leachate showed slight cell proliferation when diluted to 1:8-1:512 dilutions, but there was no statistically significant difference (P > 0.05). The checkerboard-form cell colonies of ESCs could be visualized with naked eyes on the chitinous membrane in 2-4 weeks of culture. A multitude of ESCs were seen to grow on fibres under microscope. CONCLUSIONS: Chitinous membrane may be used as ESCs culture vehicle, and biological compatibility is good.