Zhang Jie

Learn More
majors in high-resolution remote sensing image classification and its application. Abstract: This paper proposes a generative model based semi-supervised learning method of remote sensing image classification , which makes use of both the labeled and unlabeled samples to handle the insufficient labeled training samples problems. We first train an original(More)
The goal of this study is to investigate the immunoregulative effects of Panax japonicus polysaccharide (PJPS) on mice of low immunity. An orthogonal experiment was designed to determine the best extraction process for PJPS. By the tests of macrophages swallow chicken red blood cells, Delayed-type hypersensitivity (DTH), and serum hemolysin value, we(More)
Speech enhancement is an essential technique to process degraded audio in various applications. Beamforming to eliminate interferences based on sensor arrays is the most well-known method for this issue. However, traditional beamformers often face magnitude incoherence towards received signals due to directional weighting. Therefore, a novel dual-channel(More)
Nowadays, personalized services are quite pervasive and become more and more important. Many companies provide personalized services such as an item recommendation, a personal advertisement, etc. However, current personalized services have overlooked an important point that a user's focused interest is changing based on the contexts. For example, a person(More)
A simple and cost-effective design of centralized light source wavelength division multiplexing passive optical network (WDM-PON) is proposed, which supports simultaneous transmission of point-to-point data and broadcast services. 10 Gbit/s differential quadrature phase shift keying (DQPSK) downstream data and superimposed 2.5 Gbit/s inverse return-to-zero(More)
Based on multi-sensor data fusion technique, monitoring system for pipeline security is designed. Many sensors and processing modules are used to acquire early warning signals when pipes are threatened. The non-stationary signal analysis method based on empirical mode decomposition is used to process the signals. The normalized kurtosis extracted from the(More)
  • 1