Recent advances in convolutional neuralnetworks (CNNs) have positioned them as leading models for linearizing power amplifiers (PAs) in digital predistortion (DPD) applications. However, current approaches often rely...
详细信息
ISBN:
(纸本)9798350359329;9798350359312
Recent advances in convolutional neuralnetworks (CNNs) have positioned them as leading models for linearizing power amplifiers (PAs) in digital predistortion (DPD) applications. However, current approaches often rely on a manually crafted architecture, leading to issues such as limited generalization ability and increased computational complexity. To address these issues, this study develops a method of growing neural architecture search (GNAS) for complex-valued CNN, or GNAS-CVCNN for short. A complex-valued convolution layer alongside a respective activation layer deals with the memory effects and nonlinear distortion of the PA and leverages on the properties of complex-valued signals prevalent in intermediate frequency (IF) domains. The GNAS-CVCNN optimally evolves the network structure and its associated parameters in tandem. This ensures the delivery of high performance with computational efficiency. We apply the GNAS-CVCNN to the linearization of two distinct real-world PAs whose operating bandwidth are 100MHz and 180MHz, respectively. Results comparison with the latest neuralnetworks available reveals the superior linearization ability of the GNAS-CVCNN. Additionally, it achieves this higher performance with a reduced network size and enhanced processing speed, underscoring its practical efficacy in DPD applications.
This research aims to develop a multi-threading method for rapid tool wear detection by integrating image classification and object detection techniques to address the challenge of tool wear detection. The research pr...
详细信息
Deep neuralnetworks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from diffe...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Deep neuralnetworks often severely forget previously learned knowledge when learning new knowledge. Various continual learning (CL) methods have been proposed to handle such a catastrophic forgetting issue from different perspectives and achieved substantial improvements. In this paper, a novel two-branch continual learning framework is proposed to further enhance most existing CL methods. Specifically, the main branch can be any existing CL model and the newly introduced side branch is a lightweight convolutional network. The output of each main branch block is modulated by the output of the corresponding side branch block. Such a simple two-branch model can then be easily implemented and learned with the vanilla optimization setting without whistles and bells. Extensive experiments with various settings on multiple image datasets show that the proposed framework yields consistent improvements over state-of-the-art methods.
The wavelet transform has emerged as a powerful tool in deciphering structural information within images. And now, the latest research suggests that combining the prowess of wavelet transform with neuralnetworks can ...
详细信息
ISBN:
(纸本)1577358872
The wavelet transform has emerged as a powerful tool in deciphering structural information within images. And now, the latest research suggests that combining the prowess of wavelet transform with neuralnetworks can lead to unparalleled image deraining results. By harnessing the strengths of both the spatial domain and frequency space, this innovative approach is poised to revolutionize the field of imageprocessing. The fascinating challenge of developing a comprehensive framework that takes into account the intrinsic frequency property and the correlation between rain residue and background is yet to be fully explored. In this work, we propose to investigate the potential relationships among rainfree and residue components at the frequency domain, forming a frequency mutual revision network (FMRNet) for image deraining. Specifically, we explore the mutual representation of rain residue and background components at frequency domain, so as to better separate the rain layer from clean background while preserving structural textures of the degraded images. Meanwhile, the rain distribution prediction from the low-frequency coefficient, which can be seen as the degradation prior is used to refine the separation of rain residue and background components. Inversely, the updated rain residue is used to benefit the low-frequency rain distribution prediction, forming the multi-layer mutual learning. Extensive experiments demonstrate that our proposed FMRNet delivers significant performance gains for seven datasets on image deraining task, surpassing the state-of-the-art method ELFormer by 1.14 dB in PSNR on the Rain100L dataset, while with similar computation cost. Code and retrained models are available at https://***/kuijiang94/FMRNet.
This paper focuses on the urban road pothole detection problem and develops a computer vision-based pothole detection model using deep learning methods. First, a pre-trained EfficientNetBO convolutional neural network...
详细信息
In recent years, remarkable progress has been made in generative models, particularly in the fields of computer vision and natural language processing. The ability of generative models to generate new and diverse samp...
详细信息
ISBN:
(纸本)9783031543265;9783031543272
In recent years, remarkable progress has been made in generative models, particularly in the fields of computer vision and natural language processing. The ability of generative models to generate new and diverse samples has resulted in a wide range of applications, such as image and video synthesis, text generation, and music composition. This study investigates generative modeling advances made using Variational Autoencoders (VAEs), Generative Adversarial networks (GANs), and diffusion models. Although VAEs and GANs have been widely used for generative modeling tasks in the past, diffusion models have recently emerged as state-of-the-art models. This study provides a detailed analysis of each model, including its strengths and limitations, as well as its applications in image synthesis and video generation. Furthermore, this paper discusses recent developments in diffusion models such as denoising. Finally, this paper implements these proposed models to generate water crystal images.
In this study, a rectangular microstrip patch antenna design using an artificialneural network (ANN) is presented for radio frequency (RF) energy harvesting applications. Epoxy FR4 material with a dielectric constant...
详细信息
ISBN:
(纸本)9798350388978;9798350388961
In this study, a rectangular microstrip patch antenna design using an artificialneural network (ANN) is presented for radio frequency (RF) energy harvesting applications. Epoxy FR4 material with a dielectric constant of 4.3 and a thickness of 1.6 mm was used as the dielectric substrate. The designed antenna has a dimension of ([60x38.7x1.6]) mm3. The designed antenna is intended to operate in the 2.4 GHz band. The ANN used in this study consists of an input layer, three hidden layers, and an output layer. First, a simulation is performed and the results obtained in terms of return losses and frequencies are fed to the ANN model. The model of the ANN algorithm that predicts S11 values in the relevant frequency range using the input parameters to obtain the return losses of the antenna in the relevant frequency range was developed in MATLAB. After the ANN was created, S11 values were predicted using new data through MATLAB, and the results were compared with the simulation results and measurement results of the antenna.
The proceedings contain 138 papers. The topics discussed include: efficient parking lot management system for parking attendants based on real-time impulsive sound detection and voice command recognition;impact of PON...
ISBN:
(纸本)9798350309249
The proceedings contain 138 papers. The topics discussed include: efficient parking lot management system for parking attendants based on real-time impulsive sound detection and voice command recognition;impact of PON network range and laser power on GPON and XGSPON coexistence system;enhancing breast cancer classification using ensemble techniques and feature selection algorithms;diabetic retinopathy detection using modified U-Net architecture and artificial metaplasticity algorithm;brain tumor classification using DenseNet and U-net convolutional neuralnetworks;a comparative analysis of branch-cut and quality-guided algorithms for inSAR interferogram;classification of multi-view mammogram images using a parallel pre-trained models system;and deep learning approaches for plant diseases identification and classification: a comprehensive review.
Deep neuralnetworks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-cla...
详细信息
ISBN:
(纸本)1577358872
Deep neuralnetworks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target class chosen by the attacker when a test instance (from a non-target class) is embedded with a specific trigger, while maintaining high accuracy on attack-free instances. Although there are extensive studies on backdoor attacks against image data, the susceptibility of video-based systems under backdoor attacks remains largely unexplored. Current studies are direct extensions of approaches proposed for image data, e.g., the triggers are independently embedded within the frames, which tend to be detectable by existing defenses. In this paper, we introduce a simple yet effective backdoor attack against video data. Our proposed attack, adding perturbations in a transformed domain, plants an imperceptible, temporally distributed trigger across the video frames, and is shown to be resilient to existing defensive strategies. The effectiveness of the proposed attack is demonstrated by extensive experiments with various well-known models on two video recognition benchmarks, UCF101 and HMDB51, and a sign language recognition benchmark, Greek Sign Language (GSL) dataset. We delve into the impact of several influential factors on our proposed attack and identify an intriguing effect termed "collateral damage" through extensive studies.
作者：
Navaprakash, N.Reddy, S. VikramDakshinesh, S.SIMATS
Saveetha School of Engineering Department of Electronics and Communication Engineering Chennai India SIMATS
Saveetha School of Engineering Department of Embedded System Chennai India
Text extraction is a critical task in data processing and analysis, requiring high accuracy for effective applications. This research employed a publicly accessible Kaggle dataset to assess the performance of two neur...
详细信息
暂无评论