In this paper,we propose a sub-6GHz channel assisted hybrid beamforming(HBF)for mmWave system under both line-of-sight(LOS)and non-line-of-sight(NLOS)scenarios without mmWave channel estimation.Meanwhile,we resort to ...In this paper,we propose a sub-6GHz channel assisted hybrid beamforming(HBF)for mmWave system under both line-of-sight(LOS)and non-line-of-sight(NLOS)scenarios without mmWave channel estimation.Meanwhile,we resort to the selfsupervised approach to eliminate the need for labels,thus avoiding the accompanied high cost of data collection and annotation.We first construct the dense connection network(DCnet)with three modules:the feature extraction module for extracting channel characteristic from a large amount of channel data,the feature fusion module for combining multidimensional features,and the prediction module for generating the HBF matrices.Next,we establish a lightweight network architecture,named as LDnet,to reduce the number of model parameters and computational complexity.The proposed sub-6GHz assisted approach eliminates mmWave pilot resources compared to the method using mmWave channel information directly.The simulation results indicate that the proposed DCnet and LDnet can achieve the spectral efficiency that is superior to the traditional orthogonal matching pursuit(OMP)algorithm by 13.66% and 10.44% under LOS scenarios and by 32.35% and 27.75% under NLOS scenarios,respectively.Moreover,the LDnet achieves 98.52% reduction in the number of model parameters and 22.93% reduction in computational complexity compared to DCnet.展开更多
Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inv...Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inversion.However,multi-parameter inversion may bring coupling effects on the parameters and destabilize the inversion.In addition,the lateral recognition accuracy of geological structures receives great attention.To address these challenges,a multi-task learning network considering the angle-gather difference is proposed in this work.The deep learning network is usually assumed as a black box and it is unclear what it can learn.However,the introduction of angle-gather difference can force the deep learning network to focus on the lateral differences,thus improving the lateral accuracy of the prediction profile.The proposed deep learning network includes input and output blocks.First,angle gathers and the angle-gather difference are fed into two separate input blocks with Res Net architecture and Unet architecture,respectively.Then,three elastic parameters,including P-and S-wave velocities and density,are simultaneously predicted based on the idea of multi-task learning by using three separate output blocks with the same convolutional network layers.Experimental and field data tests demonstrate the effectiveness of the proposed method in improving the prediction accuracy of seismic elastic parameters.展开更多
BACKGROUND: The inclusion of cardiopulmonary resuscitation(CPR) in formal education has been a useful approach to providing basic life support(BLS) services. However, because not all students have been able to learn d...BACKGROUND: The inclusion of cardiopulmonary resuscitation(CPR) in formal education has been a useful approach to providing basic life support(BLS) services. However, because not all students have been able to learn directly from certified instructors, we studied the educational efficacy of the use of peer-assisted learning(PAL) to train high-school students to perform BLS services.METHODS: This study consisted of 187 high-school students: 68 participants served as a control group and received a 1-hour BLS training from a school nurse, and 119 were included in a PAL group and received a 1-hour CPR training from a PAL leader. Participants' BLS training was preceded by the completion of questionnaires regarding their background. Three months after the training, the participants were asked to respond to questionnaires about their willingness to perform CPR on bystander CPR and their retention of knowledge of BLS.RESULTS: We found no statistically significant difference between the control and PAL groups in their willingness to perform CPR on bystanders(control: 55.2%, PAL: 64.7%, P=0.202). The PAL group was not significantly different from the control group(control: 60.78±39.77, PAL: 61.76±17.80, P=0.848) in retention of knowledge about BLS services.CONCLUSION: In educating high school students about BLS, there was no significant difference between PAL and traditional education in increasing the willingness to provide CPR to bystanders or the ability to retain knowledge about BLS.展开更多
With focus now placed on the learner, more attention is given to his learning style, multiple intelligence and developing learning strategies to enable him to make sense of and use of the target language appropriately...With focus now placed on the learner, more attention is given to his learning style, multiple intelligence and developing learning strategies to enable him to make sense of and use of the target language appropriately in varied contexts and with different uses of the language. To attain this, the teacher is tasked with designing, monitoring and processing language learning activities for students to carry out and in the process learn by doing and reflecting on the learning process they went through as they interacted socially with each other. This paper describes a task named"The Fishbowl Technique"and found to be effective in large ESL classes in the secondary level in the Philippines.展开更多
The global nuclear mass based on the macroscopic-microscopic model was studied by applying a newly designed multi-task learning artificial neural network(MTL-ANN). First, the reported nuclear binding energies of 2095 ...The global nuclear mass based on the macroscopic-microscopic model was studied by applying a newly designed multi-task learning artificial neural network(MTL-ANN). First, the reported nuclear binding energies of 2095 nuclei(Z ≥ 8, N ≥ 8) released in the latest Atomic Mass Evaluation AME2020 and the deviations between the fitting result of the liquid drop model(LDM)and data from AME2020 for each nucleus were obtained.To compensate for the deviations and investigate the possible ignored physics in the LDM, the MTL-ANN method was introduced in the model. Compared to the single-task learning(STL) method, this new network has a powerful ability to simultaneously learn multi-nuclear properties,such as the binding energies and single neutron and proton separation energies. Moreover, it is highly effective in reducing the risk of overfitting and achieving better predictions. Consequently, good predictions can be obtained using this nuclear mass model for both the training and validation datasets and for the testing dataset. In detail, the global root mean square(RMS) of the binding energy is effectively reduced from approximately 2.4 MeV of LDM to the current 0.2 MeV, and the RMS of Sn, Spcan also reach approximately 0.2 MeV. Moreover, compared to STL, for the training and validation sets, 3-9% improvement can be achieved with the binding energy, and 20-30% improvement for S_(n), S_(p);for the testing sets, the reduction in deviations can even reach 30-40%, which significantly illustrates the advantage of the current MTL.展开更多
"College English Curriculum Requirements", edited by Department of Higher Education(2007), put forward clearly one of the key points of the national College English teaching reform was to strengthen the appl..."College English Curriculum Requirements", edited by Department of Higher Education(2007), put forward clearly one of the key points of the national College English teaching reform was to strengthen the application of computer to college English teaching and apply computer-and-classroom-based English teaching mode, improving the previous mode dominated by a single teacher. Most colleges and universities in China have basically achieved the popularity of computer multimedia classrooms and campus networks. However, according to researches(Xia, 2002), most teachers still hold the main role of them in classes as"language interpreter"and"language instructor". Although advanced computer technology has been provided, most teachers feel confused or difficult in using it to assist their English teaching efficiently. As a consequence, computer technology fail to play its role in English classes. Driven by the great development of science and technology, computer has brought about incredible changes in every aspect of social life since 1980 s. In current times, almost every aspect of college students' life has been closely associated with computer. However, in most situations, computer is not taken as a typical language learning tool in their daily life. It is known that most students' English basis is relatively weak in vocational colleges; meanwhile, the way in which they learned English during the middle school period was basically translation- based teaching. Thus they have little or even no interest in English learning at all. In this way, discovering a new and interesting way with the aid of computer to learn English is of essential importance. Based on this, the paper discusses five major aspects under the circumstance of computer-assisted English learning. It is hoped that vocational college English teaching and learning can become more efficient by means of computer technology, finally students' English learning motivation and English competence can be enhanced to a great extent.展开更多
Spatio-temporal cellular network traffic prediction at wide-area level plays an important role in resource reconfiguration,traffic scheduling and intrusion detection,thus potentially supporting connected intelligence ...Spatio-temporal cellular network traffic prediction at wide-area level plays an important role in resource reconfiguration,traffic scheduling and intrusion detection,thus potentially supporting connected intelligence of the sixth generation of mobile communications technology(6G).However,the existing studies just focus on the spatio-temporal modeling of traffic data of single network service,such as short message,call,or Internet.It is not conducive to accurate prediction of traffic data,characterised by diverse network service,spatio-temporality and supersize volume.To address this issue,a novel multi-task deep learning framework is developed for citywide cellular network traffic prediction.Functionally,this framework mainly consists of a dual modular feature sharing layer and a multi-task learning layer(DMFS-MT).The former aims at mining long-term spatio-temporal dependencies and local spatio-temporal fluctuation trends in data,respectively,via a new combination of convolutional gated recurrent unit(ConvGRU)and 3-dimensional convolutional neural network(3D-CNN).For the latter,each task is performed for predicting service-specific traffic data based on a fully connected network.On the real-world Telecom Italia dataset,simulation results demonstrate the effectiveness of our proposal through prediction performance measure,spatial pattern comparison and statistical distribution verification.展开更多
Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one....Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks(CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-theart methods by 88.2% on PETA and 83.25% on RAP, respectively.展开更多
The unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)has been deemed a promising solution for energy-constrained devices to run smart applications with computationintensive and latency-sensitive require...The unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)has been deemed a promising solution for energy-constrained devices to run smart applications with computationintensive and latency-sensitive requirements,especially in some infrastructure-limited areas or some emergency scenarios.However,the multi-UAVassisted MEC network remains largely unexplored.In this paper,the dynamic trajectory optimization and computation offloading are studied in a multi-UAVassisted MEC system where multiple UAVs fly over a target area with different trajectories to serve ground users.By considering the dynamic channel condition and random task arrival and jointly optimizing UAVs'trajectories,user association,and subchannel assignment,the average long-term sum of the user energy consumption minimization problem is formulated.To address the problem involving both discrete and continuous variables,a hybrid decision deep reinforcement learning(DRL)-based intelligent energyefficient resource allocation and trajectory optimization algorithm is proposed,named HDRT algorithm,where deep Q network(DQN)and deep deterministic policy gradient(DDPG)are invoked to process discrete and continuous variables,respectively.Simulation results show that the proposed HDRT algorithm converges fast and outperforms other benchmarks in the aspect of user energy consumption and latency.展开更多
目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞...目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞学标本,采用华为云ModelArts平台开发的人工智能(artifical intelligence,AI)辅助诊断系统与初级、中级、高级医师进行诊断比对,计算灵敏度、特异度、精确率、符合率、曲线下面积(area under the curve,AUC)等指标,评估AI系统的诊断效能及其对不同年资医师的辅助诊断效果。采用McNemar检验比较AI系统与人工诊断的差异。结果在1044例宫颈脱落细胞学标本中,AI系统在非典型细胞检出的灵敏度和特异度分别为98.96%和89.15%,均高于初级医师(81.95%和91.81%)。AI系统的总体诊断精确率为93.68%,显著高于初级医师(87.26%,P<0.001)。AI辅助可显著提高初级医师的诊断性能,灵敏度从80.1%提升至96.5%,特异度从85.6%提升至92.3%。结论本研究构建的AI辅助宫颈细胞学诊断系统性能优越,尤其能显著提高初级医师的诊断水平,具有良好的临床应用前景。展开更多
基金supported in part by the National Natural Science Foundation of China under Grants 62325107,62341107,62261160650,and U23A20272in part by the Beijing Natural Science Foundation under Grant L222002.
文摘In this paper,we propose a sub-6GHz channel assisted hybrid beamforming(HBF)for mmWave system under both line-of-sight(LOS)and non-line-of-sight(NLOS)scenarios without mmWave channel estimation.Meanwhile,we resort to the selfsupervised approach to eliminate the need for labels,thus avoiding the accompanied high cost of data collection and annotation.We first construct the dense connection network(DCnet)with three modules:the feature extraction module for extracting channel characteristic from a large amount of channel data,the feature fusion module for combining multidimensional features,and the prediction module for generating the HBF matrices.Next,we establish a lightweight network architecture,named as LDnet,to reduce the number of model parameters and computational complexity.The proposed sub-6GHz assisted approach eliminates mmWave pilot resources compared to the method using mmWave channel information directly.The simulation results indicate that the proposed DCnet and LDnet can achieve the spectral efficiency that is superior to the traditional orthogonal matching pursuit(OMP)algorithm by 13.66% and 10.44% under LOS scenarios and by 32.35% and 27.75% under NLOS scenarios,respectively.Moreover,the LDnet achieves 98.52% reduction in the number of model parameters and 22.93% reduction in computational complexity compared to DCnet.
基金financially supported by the National Natural Science Foundation of China(Grant Nos.42130810,42204135,42174170,and 42074165)the Natural Science Foundation of Hunan Province(Grant No.2023JJ40716)。
文摘Pre-stack seismic inversion is an effective way to investigate the characteristics of hydrocarbon-bearing reservoirs.Multi-parameter application is the key to identifying reservoir lithology and fluid in pre-stack inversion.However,multi-parameter inversion may bring coupling effects on the parameters and destabilize the inversion.In addition,the lateral recognition accuracy of geological structures receives great attention.To address these challenges,a multi-task learning network considering the angle-gather difference is proposed in this work.The deep learning network is usually assumed as a black box and it is unclear what it can learn.However,the introduction of angle-gather difference can force the deep learning network to focus on the lateral differences,thus improving the lateral accuracy of the prediction profile.The proposed deep learning network includes input and output blocks.First,angle gathers and the angle-gather difference are fed into two separate input blocks with Res Net architecture and Unet architecture,respectively.Then,three elastic parameters,including P-and S-wave velocities and density,are simultaneously predicted based on the idea of multi-task learning by using three separate output blocks with the same convolutional network layers.Experimental and field data tests demonstrate the effectiveness of the proposed method in improving the prediction accuracy of seismic elastic parameters.
文摘BACKGROUND: The inclusion of cardiopulmonary resuscitation(CPR) in formal education has been a useful approach to providing basic life support(BLS) services. However, because not all students have been able to learn directly from certified instructors, we studied the educational efficacy of the use of peer-assisted learning(PAL) to train high-school students to perform BLS services.METHODS: This study consisted of 187 high-school students: 68 participants served as a control group and received a 1-hour BLS training from a school nurse, and 119 were included in a PAL group and received a 1-hour CPR training from a PAL leader. Participants' BLS training was preceded by the completion of questionnaires regarding their background. Three months after the training, the participants were asked to respond to questionnaires about their willingness to perform CPR on bystander CPR and their retention of knowledge of BLS.RESULTS: We found no statistically significant difference between the control and PAL groups in their willingness to perform CPR on bystanders(control: 55.2%, PAL: 64.7%, P=0.202). The PAL group was not significantly different from the control group(control: 60.78±39.77, PAL: 61.76±17.80, P=0.848) in retention of knowledge about BLS services.CONCLUSION: In educating high school students about BLS, there was no significant difference between PAL and traditional education in increasing the willingness to provide CPR to bystanders or the ability to retain knowledge about BLS.
文摘With focus now placed on the learner, more attention is given to his learning style, multiple intelligence and developing learning strategies to enable him to make sense of and use of the target language appropriately in varied contexts and with different uses of the language. To attain this, the teacher is tasked with designing, monitoring and processing language learning activities for students to carry out and in the process learn by doing and reflecting on the learning process they went through as they interacted socially with each other. This paper describes a task named"The Fishbowl Technique"and found to be effective in large ESL classes in the secondary level in the Philippines.
基金supported by the National Natural Science Foundation of China(Nos.1187050492,12005303,and 12175170).
文摘The global nuclear mass based on the macroscopic-microscopic model was studied by applying a newly designed multi-task learning artificial neural network(MTL-ANN). First, the reported nuclear binding energies of 2095 nuclei(Z ≥ 8, N ≥ 8) released in the latest Atomic Mass Evaluation AME2020 and the deviations between the fitting result of the liquid drop model(LDM)and data from AME2020 for each nucleus were obtained.To compensate for the deviations and investigate the possible ignored physics in the LDM, the MTL-ANN method was introduced in the model. Compared to the single-task learning(STL) method, this new network has a powerful ability to simultaneously learn multi-nuclear properties,such as the binding energies and single neutron and proton separation energies. Moreover, it is highly effective in reducing the risk of overfitting and achieving better predictions. Consequently, good predictions can be obtained using this nuclear mass model for both the training and validation datasets and for the testing dataset. In detail, the global root mean square(RMS) of the binding energy is effectively reduced from approximately 2.4 MeV of LDM to the current 0.2 MeV, and the RMS of Sn, Spcan also reach approximately 0.2 MeV. Moreover, compared to STL, for the training and validation sets, 3-9% improvement can be achieved with the binding energy, and 20-30% improvement for S_(n), S_(p);for the testing sets, the reduction in deviations can even reach 30-40%, which significantly illustrates the advantage of the current MTL.
文摘"College English Curriculum Requirements", edited by Department of Higher Education(2007), put forward clearly one of the key points of the national College English teaching reform was to strengthen the application of computer to college English teaching and apply computer-and-classroom-based English teaching mode, improving the previous mode dominated by a single teacher. Most colleges and universities in China have basically achieved the popularity of computer multimedia classrooms and campus networks. However, according to researches(Xia, 2002), most teachers still hold the main role of them in classes as"language interpreter"and"language instructor". Although advanced computer technology has been provided, most teachers feel confused or difficult in using it to assist their English teaching efficiently. As a consequence, computer technology fail to play its role in English classes. Driven by the great development of science and technology, computer has brought about incredible changes in every aspect of social life since 1980 s. In current times, almost every aspect of college students' life has been closely associated with computer. However, in most situations, computer is not taken as a typical language learning tool in their daily life. It is known that most students' English basis is relatively weak in vocational colleges; meanwhile, the way in which they learned English during the middle school period was basically translation- based teaching. Thus they have little or even no interest in English learning at all. In this way, discovering a new and interesting way with the aid of computer to learn English is of essential importance. Based on this, the paper discusses five major aspects under the circumstance of computer-assisted English learning. It is hoped that vocational college English teaching and learning can become more efficient by means of computer technology, finally students' English learning motivation and English competence can be enhanced to a great extent.
基金supported in part by the Science and Technology Project of Hebei Education Department(No.ZD2021088)in part by the S&T Major Project of the Science and Technology Ministry of China(No.2017YFE0135700)。
文摘Spatio-temporal cellular network traffic prediction at wide-area level plays an important role in resource reconfiguration,traffic scheduling and intrusion detection,thus potentially supporting connected intelligence of the sixth generation of mobile communications technology(6G).However,the existing studies just focus on the spatio-temporal modeling of traffic data of single network service,such as short message,call,or Internet.It is not conducive to accurate prediction of traffic data,characterised by diverse network service,spatio-temporality and supersize volume.To address this issue,a novel multi-task deep learning framework is developed for citywide cellular network traffic prediction.Functionally,this framework mainly consists of a dual modular feature sharing layer and a multi-task learning layer(DMFS-MT).The former aims at mining long-term spatio-temporal dependencies and local spatio-temporal fluctuation trends in data,respectively,via a new combination of convolutional gated recurrent unit(ConvGRU)and 3-dimensional convolutional neural network(3D-CNN).For the latter,each task is performed for predicting service-specific traffic data based on a fully connected network.On the real-world Telecom Italia dataset,simulation results demonstrate the effectiveness of our proposal through prediction performance measure,spatial pattern comparison and statistical distribution verification.
基金supported by National Key R&D Program of China(-NO.2017YFC0803700)National Nature Science Foundation of China(No.U1736206)+6 种基金National Nature Science Foundation of China(61671336)National Nature Science Foundation of China(61671332)Technology Research Program of Ministry of Public Security(No.2016JSYJA12)Hubei Province Technological Innovation Major Project(-No.2016AAA015)Hubei Province Technological Innovation Major Projec(2017AAA123)National Key Research and Development Program of China(No.2016YFB0100901)Nature Science Foundation of Jiangsu Province(No.BK20160386)
文摘Pedestrian attributes recognition is a very important problem in video surveillance and video forensics. Traditional methods assume the pedestrian attributes are independent and design handcraft features for each one. In this paper, we propose a joint hierarchical multi-task learning algorithm to learn the relationships among attributes for better recognizing the pedestrian attributes in still images using convolutional neural networks(CNN). We divide the attributes into local and global ones according to spatial and semantic relations, and then consider learning semantic attributes through a hierarchical multi-task CNN model where each CNN in the first layer will predict each group of such local attributes and CNN in the second layer will predict the global attributes. Our multi-task learning framework allows each CNN model to simultaneously share visual knowledge among different groups of attribute categories. Extensive experiments are conducted on two popular and challenging benchmarks in surveillance scenarios, namely, the PETA and RAP pedestrian attributes datasets. On both benchmarks, our framework achieves superior results over the state-of-theart methods by 88.2% on PETA and 83.25% on RAP, respectively.
基金supported by National Natural Science Foundation of China(No.62471254)National Natural Science Foundation of China(No.92367302)。
文摘The unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC)has been deemed a promising solution for energy-constrained devices to run smart applications with computationintensive and latency-sensitive requirements,especially in some infrastructure-limited areas or some emergency scenarios.However,the multi-UAVassisted MEC network remains largely unexplored.In this paper,the dynamic trajectory optimization and computation offloading are studied in a multi-UAVassisted MEC system where multiple UAVs fly over a target area with different trajectories to serve ground users.By considering the dynamic channel condition and random task arrival and jointly optimizing UAVs'trajectories,user association,and subchannel assignment,the average long-term sum of the user energy consumption minimization problem is formulated.To address the problem involving both discrete and continuous variables,a hybrid decision deep reinforcement learning(DRL)-based intelligent energyefficient resource allocation and trajectory optimization algorithm is proposed,named HDRT algorithm,where deep Q network(DQN)and deep deterministic policy gradient(DDPG)are invoked to process discrete and continuous variables,respectively.Simulation results show that the proposed HDRT algorithm converges fast and outperforms other benchmarks in the aspect of user energy consumption and latency.
文摘目的探索并验证基于华为云ModelArts平台构建的深度学习模型在宫颈液基细胞学(liquid-based cytology,LBC)非典型细胞诊断中的应用价值,并评估其对不同诊断经验医师的辅助效果。方法回顾性分析2020年东莞市人民医院1044例宫颈脱落细胞学标本,采用华为云ModelArts平台开发的人工智能(artifical intelligence,AI)辅助诊断系统与初级、中级、高级医师进行诊断比对,计算灵敏度、特异度、精确率、符合率、曲线下面积(area under the curve,AUC)等指标,评估AI系统的诊断效能及其对不同年资医师的辅助诊断效果。采用McNemar检验比较AI系统与人工诊断的差异。结果在1044例宫颈脱落细胞学标本中,AI系统在非典型细胞检出的灵敏度和特异度分别为98.96%和89.15%,均高于初级医师(81.95%和91.81%)。AI系统的总体诊断精确率为93.68%,显著高于初级医师(87.26%,P<0.001)。AI辅助可显著提高初级医师的诊断性能,灵敏度从80.1%提升至96.5%,特异度从85.6%提升至92.3%。结论本研究构建的AI辅助宫颈细胞学诊断系统性能优越,尤其能显著提高初级医师的诊断水平,具有良好的临床应用前景。
