SRResNet Performance Enhancement Using Patch Inputs and Partial Convolution-Based Padding

Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem effectively.One of deep neural networks successful in the Super-Resolution(SR)problem is ResNet which can render the capability of deeper networks with the help of skip connections.However,zero padding(ZP)scheme in the network restricts benefits of skip connections in SRResNet and its performance as the ratio of the number of pure input data to that of zero padded data increases.In this paper.we consider the ResNet with Partial Convolution based Padding(PCP)instead of ZP to solve SR problem.Since training of deep neural networks using patch images is advantageous in many aspects such as the number of training image data and network complexities,patch image based SR performance is compared with single full image based one.The experimental results show that patch based SRResNet SR results are better than single full image based ones and the performance of deep SRResNet with PCP is better than the one with ZP.

Different known guard intervals for single/multi-carrier transceiver

To enhance the bandwidth efficiency of the guard interval （GI） assisted wireless communication system, an attractive scheme is proposed, which combines the functions of pilots and the GI together, so that the pilot resource used for estimating channel state is saved. Based on the proposed different known guard intervals （DKGI）, the time-domain channel estimation can be simply applied on the receiver side. After channel estimation, the receiver can employ the cyclic convolution restoring （CCR） function to reconstruct the cyclical convolution relationship between the signal and the channel, by which the receiver can also achieve good performance through the conventional 1-tap frequency domain equalization （FDE）.

Weak GPS signal acquisition method based on DBZP

Double block zero padding(DBZP) is a widely used but costly method for weak global positioning system(GPS) signal acquisition in software receivers. To improve the computational efficiency, this paper proposes an algorithm based on the differential DBZP algorithm and the discrete cosine transform(DCT) domain filtering method. The proposed method involves using a differential correlator after the DBZP operation. Subsequently, DCT domain low pass filtering(LPF) and inverse DCT(IDCT) reconstruction are carried out to improve the signal to noise ratio(SNR). The theoretical analysis and simulation results show that the detection algorithm can effectively improve the SNR of the acquired signal and increase the probability of detection under the same false alarm probability.

A Lightweight Model of VGG-U-Net for Remote Sensing Image Classification

Remote sensing image analysis is a basic and practical research hotspot in remote sensing science.Remote sensing images contain abundant ground object information and it can be used in urban planning,agricultural monitoring,ecological services,geological exploration and other aspects.In this paper,we propose a lightweight model combining vgg-16 and u-net network.By combining two convolutional neural networks,we classify scenes of remote sensing images.While ensuring the accuracy of the model,try to reduce the memory of themodel.According to the experimental results of this paper,we have improved the accuracy of the model to 98%.The memory size of the model is 3.4 MB.At the same time,The classification and convergence speed of the model are greatly improved.We simultaneously take the remote sensing scene image of 64×64 as input into the designed model.As the accuracy of the model is 97%,it is proved that the model designed in this paper is also suitable for remote sensing images with few target feature points and low accuracy.Therefore,the model has a good application prospect in the classification of remote sensing images with few target feature points and low pixels.

Asynchronous cooperative transmission scheme using linear dispersion code

The cooperative diversity schemes can effectively create a virtual antenna array for path fading combating multiin wireless channels. However, a lot of cooperative diversity schemes require perfect synchronization which is, in practice, difficult and even impossible to be realized. In this paper, we propose an asynchronous cooperative diversity scheme based on the linear dispersion code （LDC）. By adding the zero padding （ZP） between linear dispersion codewords, our scheme mitigates the effect of asynchronism effectively. The length of ZP is decided by relative timing errors between different relays. Besides, an easy decoding method of our scheme is given in this paper by restructuring the stacked channel matrix.