Test scheduling is a process that manages tests within a System-on-Chip (SoC) to minimize test time by allocating test resources and adjusting priorities. Efficient test scheduling offers cost saving opportunities by ...
详细信息
This paper presents DeepTSF, a comprehensive machine learning operations (MLOps) framework aiming to innovate time series forecasting through workflow automation and codeless modeling. DeepTSF automates key aspects of...
详细信息
This study introduces a modeling approach for the transient response of batteries against fast-front impulse currents. An experimental methodology is presented to allow time-domain simulation of the surge performance ...
详细信息
This study introduces a modeling approach for the transient response of batteries against fast-front impulse currents. An experimental methodology is presented to allow time-domain simulation of the surge performance of the battery using a straightforward process that involves mathematical analysis of the experimental records. A lithium iron phosphate battery was used as a case study;the voltage across the battery terminals and the current flowing through them is recorded for a range of 0.1 to 5 kA generated through a combination wave generator (12 kV 1.2/50 μs, 6 kA 8/20 μs). The developed non-linear equivalent circuit model yields results in very good agreement with experimental data of standard and non-standard impulse currents with a wavefront duration longer than 3 μs and time-to-half up to 60 μs. This work provides an advanced framework for surge protection of battery systems contributing to reliability and resilience of modern power grids against lightning events and electromagnetic pulses. Authors
Machine learning, a vital part of artificial intelli-gence, improves our ability to make predictions from complex data. The success of these predictions relies heavily on the model's fit with its data and the data...
详细信息
This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitiv...
详细信息
This study addresses the limitations of Transformer models in image feature extraction,particularly their lack of inductive bias for visual *** to Convolutional Neural Networks(CNNs),the Transformers are more sensitive to different hyperparameters of optimizers,which leads to a lack of stability and slow *** tackle these challenges,we propose the Convolution-based Efficient Transformer Image Feature Extraction Network(CEFormer)as an enhancement of the Transformer *** model incorporates E-Attention,depthwise separable convolution,and dilated convolution to introduce crucial inductive biases,such as translation invariance,locality,and scale invariance,into the Transformer ***,we implement a lightweight convolution module to process the input images,resulting in faster convergence and improved *** results in an efficient convolution combined Transformer image feature extraction *** results on the ImageNet1k Top-1 dataset demonstrate that the proposed network achieves better accuracy while maintaining high computational *** achieves up to 85.0%accuracy across various model sizes on image classification,outperforming various baseline *** integrated into the Mask Region-ConvolutionalNeuralNetwork(R-CNN)framework as a backbone network,CEFormer outperforms other models and achieves the highest mean Average Precision(mAP)*** research presents a significant advancement in Transformer-based image feature extraction,balancing performance and computational efficiency.
We consider word-of-mouth social learning involving $m$ Kalman filter agents that operate sequentially. The first Kalman filter receives the raw observations, while each subsequent Kalman filter receives a noisy mea...
详细信息
ISBN:
(数字)9798331541033
ISBN:
(纸本)9798331541040
We consider word-of-mouth social learning involving
$m$
Kalman filter agents that operate sequentially. The first Kalman filter receives the raw observations, while each subsequent Kalman filter receives a noisy measurement of the conditional mean of the previous Kalman filter. The prior is updated by the m-th Kalman filter. When
$m=2$
, and the observations are noisy measurements of a Gaussian random variable, the covariance goes to zero as
$k^{-1/3}$
for
$k$
observations, instead of
$O(k^{-1})$
in the standard Kalman filter. In this paper we prove that for
$m$
agents, the covariance decreases to zero as
$k^{-(2^{m}-1)}$
, i.e, the learning slows down exponentially with the number of agents. We also show that by artificially weighing the prior at each time, the learning rate can be made optimal as
$k^{-1}$
. The implication is that in word-of-mouth social learning, artificially re-weighing the prior can yield the optimal learning rate.
This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with a pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures w...
详细信息
Complete targets coverage is required by many Internet of Things (IoT) applications. In this respect, an important goal is to maximize the number of time slots with complete targets coverage. Achieving such coverage i...
详细信息
This paper presents a comprehensive framework for activity recognition and anomaly detection in smart home environments, targeting applications in convenience, efficiency, responsiveness, and healthcare. The proposed ...
详细信息
暂无评论