Explore the vast range of titles available.

Synthetic Aperture Radar (SAR) is renowned for its all-weather and all-time imaging capabilities, making it invaluable for ship target recognition. Despite the advancements in deep learning models, the efficiency of Convolutional Neural Networks (CNNs) in the frequency domain is often constrained by memory limitations and the stringent real-time requirements of embedded systems. To surmount these obstacles, we introduce the Split_(C)omposite method, an innovative convolution acceleration technique grounded in Fast Fourier Transform (FFT). This method employs input block decomposition and a composite zero-padding approach to streamline memory bandwidth and computational complexity via optimized frequency-domain convolution and image reconstruction. By capitalizing on FFT’s inherent periodicity to augment frequency resolution, Split_(C)omposite facilitates weight sharing, curtailing both memory access and computational demands. Our experiments, conducted using the OpenSARShip-4 dataset, confirm that the Split_(C)omposite method upholds high recognition precision while markedly enhancing inference velocity, especially in the realm of large-scale data processing, thereby exhibiting exceptional scalability and efficiency. When juxtaposed with state-of-the-art convolution optimization technologies such as Winograd and TensorRT, Split_(C)omposite has demonstrated a significant lead in inference speed without compromising the precision of recognition.

This paper presents a new modified Single Block Zero‐Padding (mSBZP) Partial Correlation Method (PCM) Parallel Code Search (PCS) algorithm for effective acquisition of weak GNSS tiered signal using coherent processing of its secondary code (SC) component. Two problems are discussed: acquisition of primary codes with a longer period using FFT blocks of limited length, and the utilization of PCS in the presence of SC bit transition. The PCM and SC bit transition forms parasitic fragments in the Cross‐Ambiguity‐Function (CAF) to devaluate signal detection performance. A novel analysis of this mechanism and its impact is presented. A novel mSBZP‐PCM‐PCS algorithm is proposed, which does not degrade the CAF. Then, the algorithm is combined with SC bit transition removal schema and sequential search to construct an estimator for weak tiered signal acquisition. The performance of the method is demonstrated by analysis and computer simulation using Galileo E1C and GPS L1C‐P signals.

Ultra-low-power is a key performance indicator in 6G-IoT ecosystems. Sensor nodes in this eco-system are also capable of running light-weight artificial intelligence (AI) models. In this work, we have achieved high performance in a gas sensor system using Convolutional Neural Network (CNN) with a smaller number of gas sensor elements. We have identified redundant gas sensor elements in a gas sensor array and removed them to reduce the power consumption without significant deviation in the node’s performance. The inevitable variation in the performance due to removing redundant sensor elements has been compensated using specialized data pre-processing (zero-padded virtual sensors and spatial augmentation) and CNN. The experiment is demonstrated to classify and quantify the four hazardous gases, viz., acetone, carbon tetrachloride, ethyl methyl ketone, and xylene. The performance of the unoptimized gas sensor array has been taken as a “baseline” to compare the performance of the optimized gas sensor array. Our proposed approach reduces the power consumption from 10 Watts to 5 Watts; classification performance sustained to 100 percent while quantification performance compensated up to a mean squared error (MSE) of 1.12 × 10−2. Thus, our power-efficient optimization paves the way to “computation on edge”, even in the resource-constrained 6G-IoT paradigm.

Synthetic Aperture Radar (SAR) is renowned for its all-weather and all-time imaging capabilities, making it invaluable for ship target recognition. Despite the advancements in deep learning models, the efficiency of Convolutional Neural Networks (CNNs) in the frequency domain is often constrained by memory limitations and the stringent real-time requirements of embedded systems. To surmount these obstacles, we introduce the Split_ Composite method, an innovative convolution acceleration technique grounded in Fast Fourier Transform (FFT). This method employs input block decomposition and a composite zero-padding approach to streamline memory bandwidth and computational complexity via optimized frequency-domain convolution and image reconstruction. By capitalizing on FFT’s inherent periodicity to augment frequency resolution, Split_ Composite facilitates weight sharing, curtailing both memory access and computational demands. Our experiments, conducted using the OpenSARShip-4 dataset, confirm that the Split_ Composite method upholds high recognition precision while markedly enhancing inference velocity, especially in the realm of large-scale data processing, thereby exhibiting exceptional scalability and efficiency. When juxtaposed with state-of-the-art convolution optimization technologies such as Winograd and TensorRT, Split_ Composite has demonstrated a significant lead in inference speed without compromising the precision of recognition.

Orthogonal frequency division multiplexing (OFDM) is an efficient multicarrier scheme that uses different types of guard intervals such as cyclic prefix (CP) and known symbol padding (KSP) (zero padding (ZP), unique word (UW), etc.) in block formation. Among these guard intervals, CP varies for each block, while other guard intervals remain fixed from block to block. These guard intervals efficiently perform channel estimation, synchronization and remove inter-block interference (IBI); nevertheless, none of the existing schemes develop any relationship between the guard interval (sequence) and the data symbols on different subcarriers of the OFDM block. We present a new idea of selecting the guard interval based on the data symbols of a subset of subcarriers in the block and exploit the high auto-correlation of the selected guard sequence to improve the bit error rate (BER) performance of the system. The results based on a fair comparison show that our enhanced orthogonal frequency division multiplexing (eOFDM) scheme inherits significant improvements in BER and the capacity of a multicarrier system as compared to the existing techniques.

Accurate electricity data is the foundation for time-of-use pricing. However, for various reasons, some data may be incorrect or lost. To address this issue, this paper proposes a recovery algorithm based on differential Fourier transform to restore missing metering data. First, the total electricity consumption data is differentiated and up-sampled as the interpolation sequence. Next, a Fourier transform is performed on the interpolated sequence to convert it from the time domain to the frequency domain. Zero-padding is applied in the high-frequency regions to enhance time-domain resolution. Then, the sequence is converted back to the time domain through an inverse Fourier transform, yielding the missing power consumption sequence. Finally, a proportional scaling method is applied to satisfy the non-decreasing characteristic. Numerical experiments demonstrate that the method proposed in this paper exhibits high reliability and accuracy in restoring missing electricity data.

The brain-computer interface (BCI) of steady-state visual evoked potential (SSVEP) is one of the fundamental ways of human-computer communication. The main challenge is that there may be a nonlinear relationship between different SSVEP in other states. For improving the performance of SSVEP BCI, a novel CNN algorithm model is proposed in this study. Based on the discrete Fourier transform to calculate the signal's power spectral density (PSD), we perform zero-padding in the signal's time domain to improve its performance on the PSD and make it more refined. In this way, the frequency point interval in the PSD of the SSVEP is consistent with the minimum gap between the stimulation frequency. Combining the nonlinear transformation capabilities of CNN in deep learning, a zero-padding frequency domain convolutional neural network (ZPFDCNN) model is proposed. Extensive experiments based on the SSVEP dataset validate the effectiveness of our method. The study verifies that the proposed ZPFDCNN method can improve the effectiveness of the SSVEP-based high-speed BCI ITR. It has massive potential in the application of BCI.

Fast and accurate estimation of sinusoidal signals plays an important role in many fields like communications, radar, sonar, etc. In underwater signal processing applications, sinusoidal signals usually take the form of CW pulses in most practical applications, therefore, zero-padding and duty-cycle show their great importance to the estimation of sinusoidal signals. In this paper, a high-precision estimation algorithm of sinusoidal signal is proposed, which combines amplitude ratio algorithm and fractional Fourier coefficient interpolation algorithm. The proposed algorithm uses the adjacent spectral line ratio algorithm instead of the Fourier coefficient maximum amplitude discrete spectral line search algorithm for coarse estimation, and modifies the traditional interpolation method. The proposed algorithm improves the Fourier coefficient interpolation algorithm by combining zero-padded signals to achieve the accurate frequency estimation for zero-padded sinusoidal signal. The performance of the algorithm is also in accordance with theoretical level for zero-padded signals, which is a great improvement over the frequency estimation algorithm for non-padded signals as well as the algorithm for zero-padding signals. The theoretical results are verified by extensive computer simulations which show that the proposed algorithm can both achieve better results for zero-padding cases and maintain comparable performance with competing algorithms for the non-padded signal. Therefore, the algorithm can be better applied to practical underwater detection or communication signals.

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.

This note provides a self-contained introduction to Rader's fast Fourier transform (FFT). We start by explaining the need for an additional type of FFT. The properties of the multiplicative group of the integers modulo a prime number are then developed and their relevance to the calculation of the discrete Fourier transform is explained. Rader's FFT is then derived, Rader's zero-padding technique is described, and the performance of the unpadded and the zero-padded approaches is examined.