計通學院研究生學術交流報告會（第六場）
發布時間: 2020-10-28 09:40:18 瀏覽量:
時間：2020年10月30日 晚上 7：00
地點：理科樓B311
標題：《Research of improving semantic image segmentation based on a feature fusion model》
匯報人：陶家俊
摘要：
The context information of images had been lost due to the low resolution of features, and due to repeated combinations of max-pooling layer and down-sampling layer. When the feature extraction process had been performed using a convolutional network, the result of semantic image segmentation loses sensitivity to the location of the object. The semantic image segmentation based on a feature fusion model with context features layer-by-layer had been proposed. Firstly, the original images had been pre-processed by the Gaussian Kernel Function to generate a series of images with different resolutions to form an image pyramid. Secondly, inputting an image pyramid into the network structure in which the plurality of fully convolutional network was been combined in parallel to obtain a set of initial features with different granularities by expanding receptive fields using Atrous Convolutions, and the initialization of feature fusion with different layer-by-layer granularities in a top-down method. Finally, the score map of feature fusion model had been calculated and sent to the conditional random field, modeling the class correlations between image pixels of the original image by the fully connected conditional random field, and the spatial position information and color vector information of image pixels were jointed to optimize and obtain results. The experiments on the PASCAL VOC 2012 and PASCAL Context datasets had achieved better mean Intersection Over Union than the state-of-the-art works. The proposed method has about 6.3% improved to the conventional methods.
錄取期刊：Journal of Ambient Intelligence and Humanized Computing
標題：《A Radar Signal Recognition Approach via IIF-Net Deep Learning Models》
匯報人：張會強
摘要：
In the increasingly complex electromagnetic environment of modern battlefields, how to quickly and accurately identify radar signals is a hotspot in the field of electronic countermeasures. In this paper, USRP N210, USRP-LW N210, and other general software radio peripherals are used to simulate the transmitting and receiving process of radar signals, and a total of 8 radar signals, namely, Barker, Frank, chaotic, P1, P2, P3, P4, and OFDM, are produced. The signal obtains time-frequency images (TFIs) through the Choi–Williams distribution function (CWD). According to the characteristics of the radar signal TFI, a global feature balance extraction module (GFBE) is designed. Then, a new IIF-Net convolutional neural network with fewer network parameters and less computation cost has been proposed. The signal-to-noise ratio (SNR) range is ?10 to 6?dB in the experiments. The experiments show that when the SNR is higher than ?2?dB, the signal recognition rate of IIF-Net is as high as 99.74%, and the signal recognition accuracy is still 92.36% when the SNR is ?10?dB. Compared with other methods, IIF-Net has higher recognition rate and better robustness under low SNR.
錄取期刊：Hindawi Computational Intelligence and Neuroscience
標題：《Novel Linguistic Steganography Based on Character-Level Text Generation》
匯報人：楊雙輝
摘要：Abstract: With the development of natural language processing, linguistic steganography has become a research hotspot in the field of information security. However, most existing linguistic steganographic methods may suffer from the low embedding capacity problem. Therefore, this paper proposes a character-level linguistic steganographic method (CLLS) to embed the secret information into characters instead of words by employing a long short-term memory (LSTM) based language model. First, the proposed method utilizes the LSTM model and large-scale corpus to construct and train a character-level text generation model. Through training, the best evaluated model is obtained as the prediction model of generating stego text. Then, we use the secret information as the control information to select the right character from predictions of the trained character-level text generation model. Thus, the secret information is hidden in the generated text as the predicted characters having different prediction probability values can be encoded into different secret bit values. For the same secret information, the generated stego texts vary with the starting strings of the text generation model, so we design a selection strategy to find the highest quality stego text from a number of candidate stego texts as the final stego text by changing the starting strings. The experimental results demonstrate that compared with other similar methods, the proposed method has the fastest running speed and highest embedding capacity. Moreover, extensive experiments are conducted to verify the effect of the number of candidate stego texts on the quality of the final stego text. The experimental results show that the quality of the final stego text increases with the number of candidate stego texts increasing, but the growth rate of the quality will slow down.
錄取期刊：MATHEMATICS