Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep con...Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep convolu- tional neural network with seven convolutional layers and three fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW us- ing one single network. An open-source C＋＋ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.展开更多
The stability control of surrounding rock for large or super-large section chamber is a difficult technical problem in deep mining condition.Based on the in-site geological conditions of Longgu coal mine,this paper us...The stability control of surrounding rock for large or super-large section chamber is a difficult technical problem in deep mining condition.Based on the in-site geological conditions of Longgu coal mine,this paper used the dynamic module of FLAC3D to study the response characteristics of deep super-large section chamber under dynamic and static combined loading condition.Results showed that under the static loading condition,the maximum vertical stress,deformation and failure range are large,where the stress concentration coefficient is 1.64.The maximum roof-to-floor and two-sides deformations are 54.6 mm and 53.1 mm,respectively.Then,under the dynamic and static combined loading condition:(1)The influence of dynamic load frequency on the two-sides is more obvious;(2)The dynamic load amplitude has the greatest influence on the stress concentration degree,and the plastic failure tends to develop to the deeper;(3)With the dynamic load source distance increase,the response of surrounding rock is gradually attenuated.On this basis,empirical equations for each dynamic load conditions were obtained by using regression analysis method,and all correlation coefficients are greater than 0.99.This research provided reference for the supporting design of deep super-large section chamber under same or similar conditions.展开更多
Service recommendation provides an effective solution to extract valuable information from the huge and ever-increasing volume of big data generated by the large cardinality of user devices.However,the distributed and...Service recommendation provides an effective solution to extract valuable information from the huge and ever-increasing volume of big data generated by the large cardinality of user devices.However,the distributed and rich multi-source big data resources raise challenges to the centralized cloud-based data storage and value mining approaches in terms of economic cost and effective service recommendation methods.In view of these challenges,we propose a deep neural collaborative filtering based service recommendation method with multi-source data(i.e.,NCF-MS)in this paper,which adopts the cloud-edge collaboration computing paradigm to build recommendation model.More specifically,the Stacked Denoising Auto Encoder(SDAE)module is adopted to extract user/service features from auxiliary user profiles and service attributes.The Multiple Layer Perceptron(MLP)module is adopted to integrate the auxiliary user/service features to train the recommendation model.Finally,we evaluate the effectiveness of the NCF-MS method on three public datasets.The experimental results show that our proposed method achieves better performance than existing methods.展开更多
基金This work was partially supported by the National Basic Research Program of China （973 Program） （2015CB351802）, and the National Natural Science Foundation of China （Grant Nos. 61402443, 61390511, 61379083, 61222211）.
文摘Robust face representation is imperative to highly accurate face recognition. In this work, we propose an open source face recognition method with deep representation named as VIPLFaceNet, which is a lO-layer deep convolu- tional neural network with seven convolutional layers and three fully-connected layers. Compared with the well-known AlexNet, our VIPLFaceNet takes only 20% training time and 60% testing time, but achieves 40% drop in error rate on the real-world face recognition benchmark LFW. Our VIPLFaceNet achieves 98.60% mean accuracy on LFW us- ing one single network. An open-source C＋＋ SDK based on VIPLFaceNet is released under BSD license. The SDK takes about 150ms to process one face image in a single thread on an i7 desktop CPU. VIPLFaceNet provides a state-of-the-art start point for both academic and industrial face recognition applications.
基金Project(2018YFC0604703)supported by the National Key R&D Program of ChinaProjects(51804181,51874190)supported by the National Natural Science Foundation of China+3 种基金Project(ZR2018QEE002)supported by the Shandong Province Natural Science Fund,ChinaProject(ZR2018ZA0603)supported by the Major Program of Shandong Province Natural Science Foundation,ChinaProject(2019GSF116003)supported by the Key R&D Project of Shandong Province,ChinaProject(SDKDYC190234)supported by the Shandong University of Science and Technology,Graduate Student Technology Innovation Project,China。
文摘The stability control of surrounding rock for large or super-large section chamber is a difficult technical problem in deep mining condition.Based on the in-site geological conditions of Longgu coal mine,this paper used the dynamic module of FLAC3D to study the response characteristics of deep super-large section chamber under dynamic and static combined loading condition.Results showed that under the static loading condition,the maximum vertical stress,deformation and failure range are large,where the stress concentration coefficient is 1.64.The maximum roof-to-floor and two-sides deformations are 54.6 mm and 53.1 mm,respectively.Then,under the dynamic and static combined loading condition:(1)The influence of dynamic load frequency on the two-sides is more obvious;(2)The dynamic load amplitude has the greatest influence on the stress concentration degree,and the plastic failure tends to develop to the deeper;(3)With the dynamic load source distance increase,the response of surrounding rock is gradually attenuated.On this basis,empirical equations for each dynamic load conditions were obtained by using regression analysis method,and all correlation coefficients are greater than 0.99.This research provided reference for the supporting design of deep super-large section chamber under same or similar conditions.
基金supported by the Natural Science Foundation of Zhejiang Province(Nos.LQ21F020021 and LZ21F020008)Zhejiang Provincial Natural Science Foundation of China(No.LZ22F020002)the Research Start-up Project funded by Hangzhou Normal University(No.2020QD2035).
文摘Service recommendation provides an effective solution to extract valuable information from the huge and ever-increasing volume of big data generated by the large cardinality of user devices.However,the distributed and rich multi-source big data resources raise challenges to the centralized cloud-based data storage and value mining approaches in terms of economic cost and effective service recommendation methods.In view of these challenges,we propose a deep neural collaborative filtering based service recommendation method with multi-source data(i.e.,NCF-MS)in this paper,which adopts the cloud-edge collaboration computing paradigm to build recommendation model.More specifically,the Stacked Denoising Auto Encoder(SDAE)module is adopted to extract user/service features from auxiliary user profiles and service attributes.The Multiple Layer Perceptron(MLP)module is adopted to integrate the auxiliary user/service features to train the recommendation model.Finally,we evaluate the effectiveness of the NCF-MS method on three public datasets.The experimental results show that our proposed method achieves better performance than existing methods.
