An adaptive dispersion estimation(ADE)is proposed to compensate dispersion and estimate the transfer function of the fiber channel with GerchbergSaxton(G-S)algorithm,using the stochastic gradient descent(SGD)method in...
详细信息
An adaptive dispersion estimation(ADE)is proposed to compensate dispersion and estimate the transfer function of the fiber channel with GerchbergSaxton(G-S)algorithm,using the stochastic gradient descent(SGD)method in the intensity-modulation and direct-detection(IM-DD)system,improving the tolerance of the algorithm to chromatic dispersion(CD).In order to address the divergence arising from the perturbation in the amplitude of the received signal caused by the filtering effect of the non-ideal channels,a channel-compensation equalizer(CCE)derived from the back-to-back(BTB)scenario is employed at the transmitter to make the amplitude of the received signal depicting the CD effect more *** simulation results demonstrate the essentiality of CCE for the convergence and performance improvement of the G-S *** show that it supports 112Gb/s four-level pulse amplitude modulation(PAM4)over 100 km standard single-mode fiber(SSMF)transmission under the 7%forward error correction(FEC)threshold of ***,ADE improves the tolerance to wavelength drift from about 4 nm to 42 nm,and there is a better tolerance for fiber distance perturbation,indicating the G-S algorithm and its derived algorithms with the ADE scheme exhibit superior robustness to the perturbation in the system.
Weather forecasting joins among the most critical undertakings in agriculture, disaster management, transportation, and many other sectors. Though traditional forecasting techniques are commonly employed, they tend no...
详细信息
We experimentally analyze the effect of the optical power on the time delay signature identification and the random bit generation in chaotic semiconductor laser with optical *** to the inevitable noise during the pho...
详细信息
We experimentally analyze the effect of the optical power on the time delay signature identification and the random bit generation in chaotic semiconductor laser with optical *** to the inevitable noise during the photoelectric detection and analog-digital conversion,the varying of output optical power would change the signal to noise ratio,then impact time delay signature identification and the random bit *** results show that,when the optical power is less than-14 dBm,with the decreasing of the optical power,the actual identified time delay signature degrades and the entropy of the chaotic signal ***,the extracted random bit sequence with lower optical power is more easily pass through the randomness testing.
Traditional unimodal biometric recognition technologies, wh-ile widely applied across various fields, still face limitations such as environmental interference, spoofing attacks, and individual differences, leading to...
详细信息
Advancements in medical imaging have been substantially driven by deep learning technologies, particularly Convolutional Neural Networks (CNNs). A critical hurdle in this domain is the imbalance of datasets, where cer...
详细信息
ISBN:
(纸本)9798350383652
Advancements in medical imaging have been substantially driven by deep learning technologies, particularly Convolutional Neural Networks (CNNs). A critical hurdle in this domain is the imbalance of datasets, where certain medical conditions are underrepresented, leading to potential biases in diagnostic models. This research addresses the imbalance in medical imaging datasets, specifically in chest radiography, by leveraging Generative Adversarial Networks (GANs) for data augmentation. The study utilizes the ChestXray2017 dataset, which is skewed towards pneumonia cases, resulting in a dearth of normal chest X-ray images. To counter this, Deep Convolution Generative Adversarial Networks (DCGAN) were employed to generate synthetic images of normal chest X-rays, thus aiming to balance the dataset. In this study, we conducted a comparative analysis of a Convolutional Neural Network's (CNN) performance on a chest radiography dataset, before and after augmenting it with Deep Convolution Generative Adversarial Network (DCGAN)-generated images. Initially, the CNN trained on the un-augmented dataset achieved 93% training accuracy and 87% validation accuracy. After integrating 400 synthetic normal chest X-ray images, the training accuracy slightly increased to 95%, while the validation accuracy notably improved to 89%. This enhancement in validation accuracy demonstrates the model's improved generalization capabilities due to a more balanced training dataset. Our results indicate that GAN-based data augmentation effectively addresses class imbalances in medical imaging datasets, potentially leading to more accurate and reliable diagnostic models. However, the study also underscores the need for further research into the quality and ethical implications of using synthetic images in medical diagnostics. Overall, the integration of GAN-generated images into CNN training presents a promising method for improving classification performance in medical imaging, offering a practical
Due to the current development of networked systems and the emergence of global cyber threats, efficient and fast NIDS are required. The suggested article aims to analyse new and improved AI and Machine Learning (ML) ...
详细信息
The Vehicle-to-Grid (V2G) network is a smart grid technology generated under the background of the rapid development of new energy technology, which allows mobile energy storage vehicles (MESVs) to realize bidirection...
详细信息
With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery ...
详细信息
With the popularity of online learning in educational settings, knowledge tracing(KT) plays an increasingly significant role. The task of KT is to help students learn more effectively by predicting their next mastery of knowledge based on their historical exercise sequences. Nowadays, many related works have emerged in this field, such as Bayesian knowledge tracing and deep knowledge tracing methods. Despite the progress that has been made in KT, existing techniques still have the following limitations: 1) Previous studies address KT by only exploring the observational sparsity data distribution, and the counterfactual data distribution has been largely ignored. 2) Current works designed for KT only consider either the entity relationships between questions and concepts, or the relations between two concepts, and none of them investigates the relations among students, questions, and concepts, simultaneously, leading to inaccurate student modeling. To address the above limitations,we propose a graph counterfactual augmentation method for knowledge tracing. Concretely, to consider the multiple relationships among different entities, we first uniform students, questions, and concepts in graphs, and then leverage a heterogeneous graph convolutional network to conduct representation *** model the counterfactual world, we conduct counterfactual transformations on students’ learning graphs by changing the corresponding treatments and then exploit the counterfactual outcomes in a contrastive learning framework. We conduct extensive experiments on three real-world datasets, and the experimental results demonstrate the superiority of our proposed Graph CA method compared with several state-of-the-art baselines.
High-Level Synthesis (HLS) enables rapid prototyping of complex hardware designs by translating C or C++ code to low-level RTL code. However, the testing and evaluation of HLS designs still typically rely on slow RTL-...
详细信息
The field of machine learning (ML) is growing at a break-neck pace. As ML models increasingly demand real-time performance, energy efficiency, and high throughput, researchers look to customized computing architecture...
详细信息
暂无评论