Stamatis Mastromichalakis

Mr. Stamatis Mastromichalakis

tmnetworks
orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in Journal of Information and Optimization Sciences
Verified
Journal Article
Closed access
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
SCSpiros Chountasis
Spiros Chountasis
MSMichalis A. Savelonas
Michalis A. Savelonas
This work introduces a signal watermarking scheme employing the fractional Fourier transform in the time-frequency domain. The proposed scheme employs an image representation of a signal, the so-called time-frequency representation, in order to embed the watermark, whereas the detector is applied on the fractional time-frequency distribution. Thus, it benefits from the two additional degrees of freedom, associated with the two angles of the 2D fractional Fourier transform, which allow hiding more watermarks than the ones allowed in 1D time or frequency domains. The proposed scheme is experimentally tested on mono-component and multi-component frequency modulated signals. It is shown that watermarking by means of 2D fractional Fourier transform achieves almost perfect detectability for noiseless signals and results in smaller distortions of the original 1D signal, than the ones induced by watermarking based on 1D fractional Fourier. In addition, the proposed watermarking scheme outperforms watermarking on 1D fractional Fourier domain in terms of robustness against noise.

26 May 2020 in Journal of Information and Optimization Sciences
Verified
Journal Article
Closed access
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
SCSpiros Chountasis
Spiros Chountasis
The classification of tomography images into non-healthy or healthy is a key pre-clinical state for patients. The training and feature extraction comprise the most time and memory consuming processes in a classifier. The aim of this paper is to provide a moment based scheme to improve the operation of classifying a given brain image as normal or abnormal. The moment features are used as input vectors to the SVM algorithm. The image is analyzed in orthogonal Fourier basis, prior to the feature extraction method. Image representation by a subset of coefficients facilitates image component selectivity, leading to extra robustness and accuracy. The proposed method has been applied on both training and classification procedures. To demonstrate the potential of the technique presented in this paper in comparison with other state-of-the-art methods, numerical simulations were performed.

29 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
Despite the unresolved 'dying ReLU problem', the classical ReLU activation function (AF) has been extensively applied in Deep Neural Networks (DNN), in particular Convolutional Neural Networks (CNN), for image classification. The common gradient issues of ReLU pose challenges in applications on academy and industry sectors. Recent approaches for improvements are in a similar direction by just proposing variations of the AF, such as Leaky ReLU (LReLU), while maintaining the solution within the same unresolved gradient problems. In this paper, the Absolute Leaky ReLU (ALReLU) AF, a variation of LReLU, is proposed, as an alternative method to resolve the common 'dying ReLU problem' on NN-based algorithms for supervised learning. The experimental results demonstrate that by using the absolute values of LReLU's small negative gradient, has a significant improvement in comparison with LReLU and ReLU, on image classification of diseases such as COVID-19, text and tabular data classification tasks on five different datasets.

1 July 2021 in Automatic Control and Computer Sciences
Verified
Journal Article
Closed access
PDF file
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
SCSpiros Chountasis
Spiros Chountasis
The classification of tomography images into unhealthy or healthy is a key preclinical process within medical image processing. The training and feature ex

9 June 2021 in Preprints.org
Verified
Preprint
Open access
PDF file
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
Two of the most common activation functions (AF) in deep neural networks (DNN) training are Sigmoid and ReLU. Sigmoid was tend to be more popular the previous decades, but it was suffering with the common vanishing gradient problems. ReLU has resolved these problems by using zero gradient and not tiny values for negative weights and the value “1” for all positives. Although it significant resolves the vanishing of the gradients, it poses new issues with dying neurons of the zero values. Recent approaches for improvements are in a similar direction by just proposing variations of the AF, such as Leaky ReLU (LReLU), while maintaining the solution within the same unresolved gradient problems. In this paper, the combining of the Sigmoid and ReLU in one single function is proposed, as a way to take the advantages of the two. The experimental results demonstrate that by using the ReLU’s gradient solution on positive weights, and Sigmoid’s gradient solution on negatives, has a significant improvement on performance of training Neural Networks on image classification of diseases such as COVID-19, text and tabular data classification tasks on five different datasets.

11 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
SMStamatis Mastromichalakis
Stamatis Mastromichalakis
Activation functions (AFs) are crucial components of deep neural networks (DNNs), having a significant impact on their performance. An activation function in a DNN is typically a smooth, nonlinear function that transforms an input signal into an output signal for the subsequent layer. In this paper, we propose the Parametric Leaky Tanh (PLTanh), a novel hybrid activation function designed to combine the strengths of both the Tanh and Leaky ReLU (LReLU) activation functions. PLTanh is differentiable at all points and addresses the 'dying ReLU' problem by ensuring a non-zero gradient for negative inputs, consistent with the behavior of LReLU. By integrating the unique advantages of these two diverse activation functions, PLTanh facilitates the learning of more intricate nonlinear relationships within the network. This paper presents an empirical evaluation of PLTanh against established activation functions, namely ReLU, LReLU, and ALReLU utilizing five diverse datasets.