As the development of wireless networks advances towards the deployment of 6G technology, ensuring robust security measures becomes crucial. In this paper, we propose 6G-SECUREIDS, a novel intrusion detection system d...
As the development of wireless networks advances towards the deployment of 6G technology, ensuring robust security measures becomes crucial. In this paper, we propose 6G-SECUREIDS, a novel intrusion detection system designed specifically for 6G wireless networks. The system leverages machine learning techniques and blockchain technology to detect and mitigate security threats, safeguard data privacy, and ensure efficient and optimized training. Our experimental results demonstrate the effectiveness and reliability of the system, with the clients achieving high accuracy scores across different model architectures. The promising results highlight the potential of 6G-SECUREIDS as a valuable security solution for future 6G networks, contributing to the overall protection and integrity of the wireless communication ecosystem.
Diffraction of pulsed electromagnetic (EM) waves in a slot excited Fabry Perót type resonator antenna is studied analytically in the modiÀed Kirchhoff approximation. Closed-form space-time expressions for th...
详细信息
Determining if a given arbitrary, wide function can be implemented by a programmable logic block, is unfortunately, in general, a very difficult problem, called the Boolean matching problem. We introduce a novel imple...
详细信息
Determining if a given arbitrary, wide function can be implemented by a programmable logic block, is unfortunately, in general, a very difficult problem, called the Boolean matching problem. We introduce a novel implemented algorithm able to map for performance combinational networks using k -LUT based FPGAs. We consider in this paper delay optimum and area optimal k-LUT FPGA mapping algorithms and compare them against a newly developed and recently improved algorithm.
The recent development of the Enriched Analytical Solution Method (EASM) for evaluating the spatio-temporal distribution of the temperature fields generated during the Laser Powder Bed Fusion (LPBF) Additive Manufactu...
详细信息
In this work we address the multispectral image classification problem from a Bayesian perspective. We develop an algorithm which utilizes the logistic regression function as the observation model in a probabilistic f...
详细信息
ISBN:
(纸本)9781467399623
In this work we address the multispectral image classification problem from a Bayesian perspective. We develop an algorithm which utilizes the logistic regression function as the observation model in a probabilistic framework, Super-Gaussian (SG) priors which promote sparsity on the adaptive coefficients, and Variational inference to obtain estimates of all the model unknowns. The proposed algorithm is validated on both synthetic and real experiments and compared with other state-of-the-art methods, such as Support Vector Machine and Gaussian Processes, demonstrating its improved performance.
Thermal properties of refractory nanocomposites with embedded single-walled carbon nanotubes were investigated using proposed automated approach. In this approach, differences in nanocomposites with varying parameters...
详细信息
ISBN:
(数字)9798331520564
ISBN:
(纸本)9798331520571
Thermal properties of refractory nanocomposites with embedded single-walled carbon nanotubes were investigated using proposed automated approach. In this approach, differences in nanocomposites with varying parameters, observed under temperature differentials and thermal loads, are highlighted. These findings are crucial for their integration into sensor systems and for applications requiring enhanced fire resistance. The results indicate that nanocomposites with a nanotube dispersion time of 2 hours exhibit a peak temperature difference of 55 “C, while those with a 1-hour dispersion time show a maximum difference of 50 °C. A comparative analysis of heat transfer dynamics suggests that extending the dispersion time by 1 hour increases fire resistance by 15%.
Companies typically select those projects that maximize their profit as the primary criterion, within the limited budget at their disposal. This criterion may lead to some company departments getting an exceedingly la...
详细信息
Companies typically select those projects that maximize their profit as the primary criterion, within the limited budget at their disposal. This criterion may lead to some company departments getting an exceedingly large share of the overall budget and induce a negative perception of unfairness among the less favourite ones. We investigate how profit optimization can be sought after while achieving the desired level of fairness at the same time. Adopting a maximin approach to fairness and using an Integer Linear Programming solver, we show that a linear trade-off is possible, since fairness and profit exhibit a nearly perfect linear anticorrelation. Fairness can be improved by even a relatively small reduction of profit, especially in large companies (i.e., managing a large number of projects).
In this paper we address the crowdsourcing problem, where a classifier must be trained without knowing the real labels. For each sample, labels (which may not be the same) are provided by different annotators (usually...
详细信息
ISBN:
(纸本)9781509007479
In this paper we address the crowdsourcing problem, where a classifier must be trained without knowing the real labels. For each sample, labels (which may not be the same) are provided by different annotators (usually with different degrees of expertise). The problem is formulated using Bayesian modeling, and considers scenarios where each annotator may label a subset of the training set samples only. Although Bayesian approaches have been previously proposed in the literature, we introduce Variational Bayes inference to develop an iterative algorithm where all latent variables are automatically estimated. In the experimental section the proposed model is evaluated and compared with other state-of-the-art methods on two real datasets.
Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is...
详细信息
ISBN:
(纸本)9781479957521
Many real classification tasks are oriented to sequence (neighbor) labeling, that is, assigning a label to every sample of a signal while taking into account the sequentiality (or neighborhood) of the samples. This is normally approached by first filtering the data and then performing classification. In consequence, both processes are optimized separately, with no guarantee of global optimality. In this work we utilize Bayesian modeling and inference to jointly learn a classifier and estimate an optimal filterbank. Variational Bayesian inference is used to approximate the posterior distributions of all unknowns, resulting in an iterative procedure to estimate the classifier parameters and the filterbank coefficients. In the experimental section we show, using synthetic and real data, that the proposed method compares favorably with other classification/filtering approaches, without the need of parameter tuning.
暂无评论