Semi-supervised learning techniques utilize both labeled and unlabeled images to enhance classification performance in scenarios where labeled images are limited. However, challenges such as integrating unlabeled imag...
详细信息
Semi-supervised learning techniques utilize both labeled and unlabeled images to enhance classification performance in scenarios where labeled images are limited. However, challenges such as integrating unlabeled images with incorrect pseudo-labels, determining appropriate thresholds for the pseudo-labels, and label prediction fluctuations on low-confidence unlabeled images, hinder the effectiveness of existing methods. This research introduces a novel framework named Interpolation Consistency for Bad Generative Adversarial Networks (IC-BGAN) that utilizes a new loss function. The proposed model combines bad adversarial training, fusion techniques, and regularization to address the limitations of semi-supervised learning. IC-BGAN creates three types of image augmentations and label consistency regularization in interpolation of bad fake images, real and bad fake images, and unlabeled images. It demonstrates linear interpolation behavior, reducing fluctuations in predictions, improving stability, and facilitating the identification of decision boundaries in low-density areas. The regularization techniques boost the discriminative capability of the classifier and discriminator, and send a better signal to the bad generator. This improves the generalization and the generation of diverse inter-class fake images as support vectors with information near the true decision boundary, which helps to correct the pseudo-labeling of unlabeled images. The proposed approach achieves notable improvements in error rate from 2.87 to 1.47 on the Modified National Institute of Standards and Technology (MNIST) dataset, 3.59 to 3.13 on the Street View House Numbers (SVHN) dataset, and 12.13 to 9.59 on the Canadian Institute for Advanced Research, 10 classes (CIFAR-10) dataset using 1000 labeled training images. Additionally, it reduces the error rate from 22.11 to 18.40 on the CINIC-10 dataset when using 700 labeled images per class. The experiments demonstrate the IC-BGAN framework outp
This paper presents a novel method for accurately estimating the cumulative capacity credit(CCC)of renewable energy(RE)*** data from the main interconnected system(MIS)of Oman for 2028,where a substantial increase in ...
详细信息
This paper presents a novel method for accurately estimating the cumulative capacity credit(CCC)of renewable energy(RE)*** data from the main interconnected system(MIS)of Oman for 2028,where a substantial increase in RE generation is anticipated,the method is introduced alongside the traditional effective load carrying capability(ELCC)*** ensure its robustness,we compare CCC results with ELCC calculations using two distinct standards of reliability criteria:loss of load hours(LOLH)at 24 hour/year and 2.4 hour/*** method consistently gives accurate results,emphasizing its exceptional accuracy,efficiency,and simplicity.A notable feature of the method is its independence from loss of load probability(LOLP)calculations and the iterative procedures associated with analytic-based reliability ***,it relies solely on readily available data such as annual hourly load profiles and hourly generation data from integrated RE *** innovation is of particular significance to prospective independent power producers(IPPs)in the RE sector,offering them a valuable tool for estimating capacity credits without the need for sensitive generating unit forced outage rate data,often restricted by privacy concerns.
In optical applications where avalanche photodiodes (APDs) provide the benefit of high sensitivity, Sb-based materials systems such as AlInAsSb and AlGaAsSb have shown extremely low excess noise factors. The Monte Car...
详细信息
In this paper, we consider the problem of finding a meta-learning online control algorithm that can learn across the tasks when faced with a sequence of N (similar) control tasks. Each task involves controlling a line...
详细信息
Nowadays, unmanned aerial vehicles (UAVs) play a significant role in transmission line inspection. This article focuses on the inertial measurement unit (IMU) as a critical component to study the impacts of electromag...
详细信息
Wireless power transfer (WPT) within the human body can enable long-lasting medical devices but poses notable challenges, including absorption by biological tissues and weak coupling between the transmitter (Tx) and r...
详细信息
High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation lear...
详细信息
High-dimensional and incomplete(HDI) matrices are primarily generated in all kinds of big-data-related practical applications. A latent factor analysis(LFA) model is capable of conducting efficient representation learning to an HDI matrix,whose hyper-parameter adaptation can be implemented through a particle swarm optimizer(PSO) to meet scalable ***, conventional PSO is limited by its premature issues,which leads to the accuracy loss of a resultant LFA model. To address this thorny issue, this study merges the information of each particle's state migration into its evolution process following the principle of a generalized momentum method for improving its search ability, thereby building a state-migration particle swarm optimizer(SPSO), whose theoretical convergence is rigorously proved in this study. It is then incorporated into an LFA model for implementing efficient hyper-parameter adaptation without accuracy loss. Experiments on six HDI matrices indicate that an SPSO-incorporated LFA model outperforms state-of-the-art LFA models in terms of prediction accuracy for missing data of an HDI matrix with competitive computational ***, SPSO's use ensures efficient and reliable hyper-parameter adaptation in an LFA model, thus ensuring practicality and accurate representation learning for HDI matrices.
In emergency response operations, the role of unmanned aerial vehicles (UAVs) has become vital for performing tasks such as human detection. However, these tasks are computationally intensive, and UAVs have limited re...
详细信息
This study aims to verify the reliability of Vehicle-to-Everything (V2X) communication systems for improving safety in advanced driving scenarios. Current autonomous driving systems that rely on sensors such as GPS or...
详细信息
This paper investigates integration of distributed energy resources(DERs)in microgrids(MGs)through two-stage power conversion structures consisting of DC-DC boost converter and DC-AC voltage source converter(VSC)*** c...
详细信息
This paper investigates integration of distributed energy resources(DERs)in microgrids(MGs)through two-stage power conversion structures consisting of DC-DC boost converter and DC-AC voltage source converter(VSC)*** contrast to existing investigations that treated DC-link voltage as an ideal constant voltage,this paper considers the non-ideal dynamic coupling between both subsystems for completeness and higher accuracy,which introduces additional DC-side dynamics to the *** analysis shows parameters of the boost converter’s power model that impact stability through the *** selecting these parameters can mitigate this effect on stability and improve dynamic performance across the ***,an optimization framework is developed to facilitate in selecting adequate boost converter parameters in designing a stable voltage source converter-based microgrid(VSC-MG).The developed optimization framework,based on particle swarm optimization,considers dynamic coupling between both subsystems and is also effective in avoiding inadequate boost converter parameters capable of propagating instability through the DC-link to the *** are performed with MATLAB/Simulink to validate theoretical analyses.
暂无评论