Three-dimensional sand printing(3DSP)is widely applied in sand mold *** this study,the effects of printing parameters including the resolution of printehead holes,activator content,layer thickness,and recoating speed ...
详细信息
Three-dimensional sand printing(3DSP)is widely applied in sand mold *** this study,the effects of printing parameters including the resolution of printehead holes,activator content,layer thickness,and recoating speed on the tensile and bending strengths,gas evolution,and loss-on-ignition(LOI)of 3DSP samples were investigated by changing single parameter,and the dimension deviation was also *** the resolution increases,the tensile strength,bending strength,gas evolution,LOI,and deviations at X-and Y-axis directions decrease gradually while the deviation at Z-axis direction firstly increases and then *** gas evolution and LOI drops by 13.02%and 8.13%respectively,but the strength only reduces by 2.2% when the resolution increases from 0.08 mm to 0.09 *** strengths of samples rise at first and then decline while the gas evolution and LOI rise gradually with the increasing activator content or recoating *** activator content is found to have little effect on the gas evolution as the activator increases from 0.14%to 0.34%,the gas evolution is increased by 7.3%which is far less than the LOI increment of 24.1%.As the layer thickness increases,the tensile and bending strengths firstly rise and then drop while gas evolution and LOI *** the optimal printing parameters of 0.09 mm resolution,0.18%activator,0.28 mm layer thickness and 160 mm·s^(-1) recoating speed,the tensile strengths for X-sample and Y-sample are 1.48 MPa and 1.37 MPa,the bending strengths are 1.84 MPa and 1.75 MPa,the gas evolution and LOI are 9.62 mL·g^(-1) and 1.92%,respectively.
The remote sensing image contains a lot of dense small targets, which increases the difficulty of object detection. The loss of small target feature information in feature fusion is rarely taken into account by the ta...
详细信息
Multi-view clustering is an important task in multimedia and machine learning. In multi-view clustering, multi-view spectral clustering is one kind of the most popular and effective methods. However, existing multi-vi...
详细信息
This paper is based on the Internet of Things technology, combined with image recognition technology, the construction of intelligent three-dimensional virtual information management system. The system is visually con...
详细信息
Traditional methods of violence detection in public spaces often struggle with low accuracy, limited real-time capabilities, and an inability to handle complex spatiotemporal patterns. They lack the sophistication nee...
详细信息
Traditional methods of violence detection in public spaces often struggle with low accuracy, limited real-time capabilities, and an inability to handle complex spatiotemporal patterns. They lack the sophistication needed to accurately distinguish between violent and non-violent activities, and their reliance on rule-based systems hinders adaptability to diverse scenarios. Moreover, their communication channels for alerts might be slow and inefficient. Mitigating the pervasive issue of violence within public spaces demands a technologically advanced approach. Addressing this imperative, we present a novel solution encompassing a profound neural network architecture. Our method harmoniously integrates a pre-trained Darknet19 model with both Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models, collectively orchestrated to achieve unprecedented efficacy in violence detection and prevention. Our approach commences with the extraction of spatial intricacies, meticulously executed by leveraging the potent capabilities of the Darknet19 model. Subsequently, these extracted spatial features serve as the foundational dataset for training the CNN, which in turn captures and distills essential temporal attributes inherent to the video sequences. These temporal features are then seamlessly channeled into the LSTM component of our architecture, which adeptly discerns and categorizes video-based activities into two distinct classes: manifestations of violence and non-violent behaviors. Validation and verification of our proposed model transpire upon the Fight dataset, resulting in a suite of commendable experimental outcomes. The integration of multi-modal alert dissemination mechanisms further enhances our system's efficacy. Notably, pertinent alerts are expeditiously communicated to relevant law enforcement entities through the synergistic utilization of WhatsApp, Telegram, and e-mail applications. This technologically fortified paradigm promises a transfo
Wave refrigerating technology is a new type of refrigerating technology that performs more efficiently and is more environmentally friendly. Nowadays, the commonly used control method is the PID control method. Howeve...
详细信息
Traffic prediction of wireless networks attracted many researchersand practitioners during the past decades. However, wireless traffic frequentlyexhibits strong nonlinearities and complicated patterns, which makes it ...
详细信息
Traffic prediction of wireless networks attracted many researchersand practitioners during the past decades. However, wireless traffic frequentlyexhibits strong nonlinearities and complicated patterns, which makes it challengingto be predicted accurately. Many of the existing approaches forpredicting wireless network traffic are unable to produce accurate predictionsbecause they lack the ability to describe the dynamic spatial-temporalcorrelations of wireless network traffic data. In this paper, we proposed anovel meta-heuristic optimization approach based on fitness grey wolf anddipper throated optimization algorithms for boosting the prediction accuracyof traffic volume. The proposed algorithm is employed to optimize the hyperparametersof long short-term memory (LSTM) network as an efficient timeseries modeling approach which is widely used in sequence prediction *** prove the superiority of the proposed algorithm, four other optimizationalgorithms were employed to optimize LSTM, and the results were *** evaluation results confirmed the effectiveness of the proposed approachin predicting the traffic of wireless networks accurately. On the other hand,a statistical analysis is performed to emphasize the stability of the proposedapproach.
—Spatial optimization problems (SOPs) refer to a class of problems where the decision variables require spatial organization. Existing methods based on evolutionary algorithms (EAs) fit conventional evolutionary oper...
详细信息
The extreme learning machine is a fast neural network with outstanding performance. However, the selection of an appropriate number of hidden nodes is time-consuming, because training must be run for several values, a...
详细信息
With the development of computer vision technology, human pose estimation as an indispensable part of human-computer interaction. Although Light-Weight High-Resolution Network-30 has Lower number of parameters, the pr...
详细信息
暂无评论