Large-scale is a trend in person re-identification (re-id). It is important that real-time search be performed in a large gallery. While previous methods mostly focus on discriminative learning, this ...paper makes the attempt in integrating deep learning and hashing into one framework to evaluate the efficiency and accuracy for large-scale person re-id. We integrate spatial information for discriminative visual representation by partitioning the pedestrian image into horizontal parts. Specifically, Part-based Deep Hashing (PDH) is proposed, in which batches of triplet samples are employed as the input of the deep hashing architecture. Each triplet sample contains two pedestrian images (or parts) with the same identity and one pedestrian image (or part) of the different identity. A triplet loss function is employed with a constraint that the Hamming distance of pedestrian images (or parts) with the same identity is smaller than ones with the different identity. In the experiment, we show that the proposed PDH method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.
Human adoption of artificial intelligence (AI) technique is largely hampered because of the increasing complexity and opacity of AI development. Explainable AI (XAI) techniques with various methods ...and tools have been developed to bridge this gap between high-performance black-box AI models and human understanding. However, the current adoption of XAI technique still lacks “human-centered” guidance for designing proper solutions to meet different stakeholders’ needs in XAI practice. We first summarize a human-centered demand framework to categorize different stakeholders into five key roles with specific demands by reviewing existing research and then extract six commonly used human-centered XAI evaluation measures which are helpful for validating the effect of XAI. In addition, a taxonomy of XAI methods is developed for visual computing with analysis of method properties. Holding clearer human demands and XAI methods in mind, we take a medical image diagnosis scenario as an example to present an overview of how extant XAI approaches for visual computing fulfil stakeholders’ human-centered demands in practice. And we check the availability of open-source XAI tools for stakeholders’ use. This survey provides further guidance for matching diverse human demands with appropriate XAI methods or tools in specific applications with a summary of main challenges and future work toward human-centered XAI in practice.
Recommender systems are the systems that take advantages of users’ historical behavior data to model the users’ behavior preferences to recommend things to users. However, recommender systems often ...suffer from data sparsity issues, due to a lack of adequate preference data, which degrades the overall recommendation performance. Cross-domain recommender systems were later developed to transfer knowledge from the auxiliary domain with rich user behavior data to help improve the recommendation performance of the target domain. Most of the existing cross-domain recommendation methods assume that overlapping entities are shared between domains, and then use them as a bridge for knowledge transfer across domains. However, this assumption does not universally hold. In this scenario, the existing cross-domain recommendation methods rarely consider the distribution inconsistency between domains, but directly transfer the cluster-level knowledge learned from the auxiliary domain to the target domain, which cannot ensure the consistency of knowledge transfer. Therefore, when overlapping entities are not shared between domains, how to effectively transfer knowledge is a key challenge for cross-domain recommender systems. Here, we propose a Cross-Domain Collaborative Recommendation without Overlapping Entities Based on Domain Adaptation, called CCR-DA. We find that CCR-DA can simultaneously achieve the consistency of knowledge transfer and avoid negative transfer in a unified framework. Specifically, we first seamlessly integrate the Maximum Mean Discrepancy (MMD) regularization constraints into the weighted collective matrix tri-factorization to reduce the distribution discrepancy between domains, so as to ensure the consistency of knowledge transfer. Then we further incorporate the graph regularization of user and item graphs from the two domains into the above framework to maintain the inherent geometric structure of each domain, thereby avoiding negative transfer. Experimental results on three categories of cross-domain recommendation tasks constructed from six real-world data sets show that our CCR-DA method outperforms.
The exceptional characteristics of magnesium alloys make them appropriate materials in various applications, although their low corrosion resistance critically limits their use. Sol–gel coating is ...among the most efficient ways to avoid corrosion, and silanes/siloxane polymers play a very essential role in the formation of sol–gel coating materials. These materials form very stable chemical bonds on surfaces of metals because of their siloxane (−Si–O−) network along with their thermal and chemical stability. In this work, the current progress of silane-based coatings on magnesium alloys is reviewed. First, we have focused on hybrid organic–inorganic sol–gel coatings using silanes and then a critical examination of protection effects of these coatings on a magnesium alloy. Modification methods of these coatings to achieve improved barrier properties have also been emphasized along with the role of silanes in the making of superhydrophobic surfaces. The recent development of silanes as outstanding precursors was also highlighted.
This paper considers the problem of intelligent jamming attack on a MIMO wireless communication link with a transmitter, a receiver, and an adversarial jammer, each equipped with multiple antennas. ...We present an optimal jamming signal design, which can maximally disrupt the MIMO transmission when the transceiver adopts an anti-jamming mechanism. In particular, signal-to-jamming-plus-noise ratio (SJNR) at the receiver is used as the anti-jamming reliability metric of the legitimate MIMO transmission. The jamming signal design is developed under the most crucial scenario for the jammer where the legitimate transceiver adopt jointly designed maximum-SJNR transmit beamforming and receive filter to suppress/mitigate the disturbance from the jammer. Under this best anti-jamming scheme, we aim to optimize the jamming signal to minimize the receiver's maximum-SJNR under a given jamming power budget. The optimal jamming signal designs are developed in different cases with accordance to the availability of channel state information (CSI) at the jammer. The analytical approximations of the jamming performance in terms of average maximum-SJNR are also provided. Extensive simulation studies confirm our analytical predictions and illustrate the efficiency of the designed optimal jamming signal on disrupting MIMO communications.
•The pre-stress loading method is proposed to obtain the acoustoelastic constant.•The longitudinal and transverse welding residual stresses are measured, respectively.•The finite element analysis ...model for laser ultrasonic measurement of welding residual stress is established.
Laser ultrasonic is a most promising method for non-destructive evaluation of residual stress. The residual stress of thin steel plate is measured by laser ultrasonic technique. The pre-stress loading device is designed which can easily realize the condition of the specimen being laser ultrasonic tested at the same time in the known stress state. By the method of pre-stress loading, the acoustoelastic constants are obtained and the effect of different test directions on the results of surface wave velocity measurement is discussed. On the basis of known acoustoelastic constants, the longitudinal and transverse welding residual stresses are measured by the laser ultrasonic technique. The finite element method is used to simulate the process of surface wave detection of welding residual stress. The pulsed laser is equivalent to the surface load and the relationship between the physical parameters of the laser and the load is established by the correction coefficient. The welding residual stress of the specimen is realized by the ABAQUS function module of predefined field. The results of finite element analysis are in good agreement with the experimental method. The simple and effective numerical and experimental methods for laser ultrasonic measurement of residual stress are demonstrated.
The preheating of the substrate in laser additive superalloys can reduce residual stress and minimize cracking. However, this preheating process can lead to changes in the heat transfer conditions, ...ultimately affecting the resulting microstructure and mechanical properties. In order to explore the influence of substrate preheating on the formation of laser cladding, this research focuses on investigating the characteristics of Inconel 718, a nickel-based superalloy, as the subject of study. To simulate the temperature and flow field of laser cladding, a 3D computational fluid dynamics (CFD) model is employed. By varying the initial preheating conditions, an investigation is conducted into the distribution of the temperature field under different parameters. This leads to the acquisition of varying temperature gradients, G, and solidification speeds, R. Subsequently, an analysis is carried out on both the flow field and solidification microstructure in the melt pool. The results demonstrate that the preheating of the substrate results in a slower cooling rate, ultimately leading to the formation of a coarser microstructure.
•A new HS-SPME-GC×GC-TOFMS method for the analysis of vinegar volatiles was described.•Ordered separation of furans and pyrazines were achieved and studied.•360 Compounds were tentatively identified ...in Zhenjiang aromatic vinegar.•15 Odor-active compounds were suspected the most potent.
In this work, a method to characterize the aroma compounds of Zhenjiang aromatic vinegar (ZAV) was developed using comprehensive two dimensional gas chromatography (GC×GC) coupled with time-of-flight mass spectrometry (TOFMS) and gas chromatography olfactometry (GC-O). The column combination was optimized and good separation was achieved. Structured chromatograms of furans and pyrazines were obtained and discussed. A total of 360 compounds were tentatively identified based on mass spectrum match factors, structured chromatogram and linear retention indices comparison. The most abundant class in number was ketones. A large number of esters, furans and derivatives, aldehydes and alcohols were also detected. The odor-active components were identified by comparison of the reported odor of the identified compounds with the odor of corresponding GC-O region. The odorants of methanethiol, 2-methyl-propanal, 2-methyl-butanal/3-methyl-butanal, octanal, 1-octen-3-one, dimethyl trisulfide, trimethyl-pyrazine, acetic acid, 3-(methylthio)-propanal, furfural, benzeneacetaldehyde, 3-methyl-butanoic acid/2-methyl-butanoic acid and phenethyl acetate were suspected to be the most potent. About half of them were identified as significant aroma constituents in ZAV for the first time. Their contribution to specific sensory attribute of ZAJ was also studied. The results indicated that the presented method is suitable for characterization of ZAV aroma constituents. This study also enriches our knowledge on the components and aroma of ZAV.
In view of the fact that the mature eddy current sensors on the market have a small measuring range and a certain requirement for the measured conductor area, which cannot meet the requirement of TBM ...disc cutter Wear monitoring, Ansoft Maxwell simulation was used to optimize the coil geometry parameters and circuit structure of eddy current sensor in this study. A special sensor for measuring disc cutter wear was designed, and the feasibility of the design was verified by measuring a 17-inch disc cutter. The results indicate that the linear range of the eddy current sensor is 35 mm under the condition that the measured blade width is 19 mm, which can meet the requirement of disc cutter wear measurement and provide monitoring data for real-time disc cutter wear monitoring system.
In this work, the effect of Y2O3 addition on the grain growth and densification of W matrix was explored from a kinetic perspective by comparing the low temperature sintering behavior of W-Y2O3 ...composite nanopowder system with that of pure W nanopowder system. By combining nonisothermal sintering experiment with the power law of grain growth, it was found that grain boundary diffusion is responsible for the mass transport mechanism in both systems. The inhibition of W grain growth after Y2O3 addition is closely related to the lower surface diffusivity of W skeleton. The densification rate of W skeleton in these two systems were modelled using a periodic 3D arrangement of identical particles and a much smaller grain boundary diffusivity of W skeleton was obtained for W-Y2O3 sample. Firstly, it is the decrease in dihedral angle of W matrix after Y2O3 addition that causes a decrease in thermodynamic driving force for densification. Secondly, from the view of atomic mobility, the inhibited W grain growth caused by limited surface diffusivity is one of the reasons impeding densification. Besides, Y2O3 grains distributed at W grain boundary coarsen through wetting W grain boundary, which also has an inhibition effect on the W skeleton densification.
After Y2O3 being added into W matrix, mass transport mechanism of grain boundary diffusion remain unchanged. Besides, W skeleton densification is suppressed by Y2O3, which is caused by the lower surface diffusion, smaller dihedral angle and wetting of W grain boundary by Y2O3. Display omitted
•Grain boundary diffusion is the mass transport mechanism in pure W and W-Y2O3 systems during the low temperature sintering.•During the intermediate stage of low temperature sintering, W skeleton densification is suppressed by Y2O3 addition.•The lower surface diffusion, smaller dihedral angle and wetting of W grain boundary cause the densification inhibition.