Machine learning(ML) has been widely applied to the upper layers of wireless communication systems for various purposes, such as deployment of cognitive radio and communication network. However, its application to the...Machine learning(ML) has been widely applied to the upper layers of wireless communication systems for various purposes, such as deployment of cognitive radio and communication network. However, its application to the physical layer is hampered by sophisticated channel environments and limited learning ability of conventional ML algorithms. Deep learning(DL) has been recently applied for many fields, such as computer vision and natural language processing, given its expressive capacity and convenient optimization capability. The potential application of DL to the physical layer has also been increasingly recognized because of the new features for future communications, such as complex scenarios with unknown channel models, high speed and accurate processing requirements; these features challenge conventional communication theories. This paper presents a comprehensive overview of the emerging studies on DL-based physical layer processing, including leveraging DL to redesign a module of the conventional communication system(for modulation recognition, channel decoding, and detection) and replace the communication system with a radically new architecture based on an autoencoder. These DL-based methods show promising performance improvements but have certain limitations, such as lack of solid analytical tools and use of architectures that are specifically designed for communication and implementation research, thereby motivating future research in this field.展开更多
The effects of Cr, Ni and Cu on the corrosion behavior of low carbon microalloying steel in a CI- containing environment were investigated. The results revealed that the corrosion process could be divided into the ini...The effects of Cr, Ni and Cu on the corrosion behavior of low carbon microalloying steel in a CI- containing environment were investigated. The results revealed that the corrosion process could be divided into the initial stage in which the corrosion rate increased with accumulation of corrosion products and the later stage in which homogeneous and compact inner rust layers started to protect steel substrate out of corrosion mediums. The results of X-ray diffraction (XRD) indicated that the rust layers of the three-group steels (Cr, Cr-Ni and Cr-Ni-Cu steels) were composed of α-FeOOH, β-FeOOH, γ-FeOOH, Fe3O4 and large amounts of amorphous compounds. The content of amorphous compounds of Cr-Ni-Cu steel was about 2%-3% more than that of Cr-Ni steel. The results of electron probe microanalysis (EPMA) showed that Cr concentrated mainly in the inner region of the rust of Cr-Ni-Cu steel, inner/outer interface especially, whereas Ni was uniformly distributed all over the rust and Cu was noticed rarely after 73 wet/dry cycles. The addition of Cr and Ni was beneficial to the formation of dense and compact inner rust layer, which was the most important reason for the improvement of corrosion resistance of experimental steel.展开更多
The interaction between permafrost and atmosphere is accomplished through transfer of heat and moisture in the overlay active layer. Thus, the research on the thermal and hydrodynamics of active layer during the thawi...The interaction between permafrost and atmosphere is accomplished through transfer of heat and moisture in the overlay active layer. Thus, the research on the thermal and hydrodynamics of active layer during the thawing and freezing processes was considered a key to revealing the heat and moisture exchanges between permafrost and atmosphere. The monitoring and research on active layer were conducted because permafrost occupies about two thirds of the total area of the Tibetan Plateau. Based on the analysis of the ground temperature data and soil moisture data of monitoring near the Wudaoliang region of the Tibetan Plateau, the thawing and freezing processes of active layer were divided into four stages, i.e. summer thawing stage (ST), autumn freezing stage (AF), winter cooling stage (WC) and spring warming stage (SW). Coupled heat and water flow is much more complicated in ST and AF, and more amount of water is migrating in these two stages. Heat is transferred mainly via conductive heat flow in the展开更多
文摘Machine learning(ML) has been widely applied to the upper layers of wireless communication systems for various purposes, such as deployment of cognitive radio and communication network. However, its application to the physical layer is hampered by sophisticated channel environments and limited learning ability of conventional ML algorithms. Deep learning(DL) has been recently applied for many fields, such as computer vision and natural language processing, given its expressive capacity and convenient optimization capability. The potential application of DL to the physical layer has also been increasingly recognized because of the new features for future communications, such as complex scenarios with unknown channel models, high speed and accurate processing requirements; these features challenge conventional communication theories. This paper presents a comprehensive overview of the emerging studies on DL-based physical layer processing, including leveraging DL to redesign a module of the conventional communication system(for modulation recognition, channel decoding, and detection) and replace the communication system with a radically new architecture based on an autoencoder. These DL-based methods show promising performance improvements but have certain limitations, such as lack of solid analytical tools and use of architectures that are specifically designed for communication and implementation research, thereby motivating future research in this field.
基金supported by the High Technology Research and Development Program of China (No. 2007AA03Z504)the Fundamental Research Funds for the Central Universities (No. N100507002)
文摘The effects of Cr, Ni and Cu on the corrosion behavior of low carbon microalloying steel in a CI- containing environment were investigated. The results revealed that the corrosion process could be divided into the initial stage in which the corrosion rate increased with accumulation of corrosion products and the later stage in which homogeneous and compact inner rust layers started to protect steel substrate out of corrosion mediums. The results of X-ray diffraction (XRD) indicated that the rust layers of the three-group steels (Cr, Cr-Ni and Cr-Ni-Cu steels) were composed of α-FeOOH, β-FeOOH, γ-FeOOH, Fe3O4 and large amounts of amorphous compounds. The content of amorphous compounds of Cr-Ni-Cu steel was about 2%-3% more than that of Cr-Ni steel. The results of electron probe microanalysis (EPMA) showed that Cr concentrated mainly in the inner region of the rust of Cr-Ni-Cu steel, inner/outer interface especially, whereas Ni was uniformly distributed all over the rust and Cu was noticed rarely after 73 wet/dry cycles. The addition of Cr and Ni was beneficial to the formation of dense and compact inner rust layer, which was the most important reason for the improvement of corrosion resistance of experimental steel.
文摘The interaction between permafrost and atmosphere is accomplished through transfer of heat and moisture in the overlay active layer. Thus, the research on the thermal and hydrodynamics of active layer during the thawing and freezing processes was considered a key to revealing the heat and moisture exchanges between permafrost and atmosphere. The monitoring and research on active layer were conducted because permafrost occupies about two thirds of the total area of the Tibetan Plateau. Based on the analysis of the ground temperature data and soil moisture data of monitoring near the Wudaoliang region of the Tibetan Plateau, the thawing and freezing processes of active layer were divided into four stages, i.e. summer thawing stage (ST), autumn freezing stage (AF), winter cooling stage (WC) and spring warming stage (SW). Coupled heat and water flow is much more complicated in ST and AF, and more amount of water is migrating in these two stages. Heat is transferred mainly via conductive heat flow in the