Searcharxiv⌕ Search

arXiv subjects

Mehdi Asadi

Publications and source records attributed to Mehdi Asadi.

13 recordsLinked to original sources
arXiv2026

MariData: One-Step Unpaired Image Translation for Maritime Environments

The development on robust perception systems for Maritime Autonomous Surface Ships (MASS) is heavily constrained by the scarcity of diverse training data, particularly for adverse weather and low-light conditions. Because collecting paired images in dynamic maritime environments is physically impossible, synthetic data generation via unpaired image-to-image translation offers a critical solution. However, existing generative models suffer from failing to preserve the fine structural details of small navigational objects due to latent compression bottlenecks. In this paper, we introduce a framework for generating synthetic maritime data using CycleGAN-turbo, a one-step unpaired translation architecture. By incorporating zero-convolution skip connections to bypass the Variational Autoencoder (VAE) bottleneck, our approach explicitly preserves small object details (e.g., distant vessels and sea marks) during translation. We compiled a dataset of 7,000 maritime images to train and evaluate models for Day-to-Foggy, Day-to-Sunset, and Day-to-Night domain translations. Qualitative evaluations and variable-strength inference studies demonstrate that our method effectively synthesizes realistic atmospheric conditions while maintaining the underlying semantic structure of the scene. The Day-to-Foggy and Day-to-Sunset models exhibit great structural retention, whereas the Day-to-Night model highlights the challenge of semantic hallucination, such as generating artificial coastal lights, induced by unbalanced training distributions. Ultimately, this work establishes an efficient, structure-aware data synthesis pipeline that directly addresses the data scarcity bottleneck in autonomous maritime navigation.

cs.CV↗
arXiv2024

A Review on Generative AI Models for Synthetic Medical Text, Time Series, and Longitudinal Data

This paper presents the results of a novel scoping review on the practical models for generating three different types of synthetic health records (SHRs): medical text, time series, and longitudinal data. The innovative aspects of the review, which incorporate study objectives, data modality, and research methodology of the reviewed studies, uncover the importance and the scope of the topic for the digital medicine context. In total, 52 publications met the eligibility criteria for generating medical time series (22), longitudinal data (17), and medical text (13). Privacy preservation was found to be the main research objective of the studied papers, along with class imbalance, data scarcity, and data imputation as the other objectives. The adversarial network-based, probabilistic, and large language models exhibited superiority for generating synthetic longitudinal data, time series, and medical texts, respectively. Finding a reliable performance measure to quantify SHR re-identification risk is the major research gap of the topic.

cs.LG↗
arXiv2024

Long-range self-hybridized exciton polaritons in two-dimensional Ruddlesden-Popper perovskites

Lead halide perovskites have emerged as platforms for exciton-polaritonic studies at room temperature thanks to their excellent photoluminescence efficiency and synthetic versatility. In this work we find proof of strong exciton-photon coupling in cavities formed by the layered crystals themselves, a phenomenon known as self-hybridization effect. We use multi-layers of high quality Ruddlesden-Popper perovskites in their 2D crystalline form, benefitting from their quantum-well excitonic resonances and the strong Fabry-Perot cavity modes resulting from the total-internal-reflection at their smooth surfaces. Optical spectroscopy reveals bending of the cavity modes typical for exciton-polariton formation, and photoluminescence spectroscopy shows thickness dependent splitting of the excitonic resonance. Strikingly, local optical excitation with energy below the excitonic resonance of the flakes in photoluminescence measurements unveils coupling of light to in-plane polaritonic modes with directed propagation. These exciton-polaritons exhibit high coupling efficiencies and extremely low loss propagation mechanisms which is confirmed by finite difference time domain simulations. We therefore prove that mesoscopic 2D Ruddlesden-Popper perovskites flakes represent an effective but simple system to study the rich physics of exciton-polaritons at room temperature.

cond-mat.mtrl-sci↗
arXiv2023

Learning Activation Functions for Sparse Neural Networks

Sparse Neural Networks (SNNs) can potentially demonstrate similar performance to their dense counterparts while saving significant energy and memory at inference. However, the accuracy drop incurred by SNNs, especially at high pruning ratios, can be an issue in critical deployment conditions. While recent works mitigate this issue through sophisticated pruning techniques, we shift our focus to an overlooked factor: hyperparameters and activation functions. Our analyses have shown that the accuracy drop can additionally be attributed to (i) Using ReLU as the default choice for activation functions unanimously, and (ii) Fine-tuning SNNs with the same hyperparameters as dense counterparts. Thus, we focus on learning a novel way to tune activation functions for sparse networks and combining these with a separate hyperparameter optimization (HPO) regime for sparse networks. By conducting experiments on popular DNN models (LeNet-5, VGG-16, ResNet-18, and EfficientNet-B0) trained on MNIST, CIFAR-10, and ImageNet-16 datasets, we show that the novel combination of these two approaches, dubbed Sparse Activation Function Search, short: SAFS, results in up to 15.53%, 8.88%, and 6.33% absolute improvement in the accuracy for LeNet-5, VGG-16, and ResNet-18 over the default training protocols, especially at high pruning ratios. Our code can be found at https://github.com/automl/SAFS

cs.LG↗
arXiv2023

Accurate Detection of Paroxysmal Atrial Fibrillation with Certified-GAN and Neural Architecture Search

This paper presents a novel machine learning framework for detecting Paroxysmal Atrial Fibrillation (PxAF), a pathological characteristic of Electrocardiogram (ECG) that can lead to fatal conditions such as heart attack. To enhance the learning process, the framework involves a Generative Adversarial Network (GAN) along with a Neural Architecture Search (NAS) in the data preparation and classifier optimization phases. The GAN is innovatively invoked to overcome the class imbalance of the training data by producing the synthetic ECG for PxAF class in a certified manner. The effect of the certified GAN is statistically validated. Instead of using a general-purpose classifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of the proposed framework exhibits a high value of 99% which not only enhances state-of-the-art by up to 5.1%, but also improves the classification performance of the two widely-accepted baseline methods, ResNet-18, and Auto-Sklearn, by 2.2% and 6.1%.

cs.LG↗
arXiv2012

Metrizability of Cone Metric Spaces Via Renorming the Banach Spaces

In this paper we show that by renorming an ordered Banach space, every cone P can be converted to a normal cone with constant K = 1 and consequently due to this approach every cone metric space is really a metric one and every theorem in metric space valid for cone metric space automatically.

math.FA↗
arXiv2012

Fixed Point Theorems of Generalized Contractions in Partially Ordered Cone Metric Spaces

The aim of this paper is to present some fixed point theorems for generalized contractions by altering distance functions in a complete cone metric spaces endowed with a partial order. We also generalize fixed point theorems of J. Harjani, K. Sadarangani [J. Harjani, K. Sadarangani, Generalized contractions in partially ordered metric spaces and applications to ordinary differential equations, Nonlinear Analysis 72 (2010) 1188-1197] from metric spaces to cone metric spaces.

math.FA↗
arXiv2012

Examples in Cone Metric Spaces: A Survey

In this survey, at first we review to many examples which have been made on cone metric spaces to verify some properties of cones on real Banach spaces and cone metrics and second, in continue like as examples that sandwich theorem doesn't hold and we shall present an other example that comparison test doesn't hold with an example for normal cones.

math.FA↗
arXiv2012

Some Notes on the paper "The Equivalence of Cone Metric Spaces and Metric Spaces"

In this paper we shall show that the metrics are equivalent which obtained by Feng and Mao in [[1], Y. Feng and W. Mao, Equivalence of Cone Metric spaces and Metric Spaces, Fixed Point Theory, 11(2)(2010), 259-264.] and Du in [[2], Wei-Shih Du, A Note on Cone Metric Fixed Point Theory and its equivalence, Nonlinear Analysis, 72 2259-2261 (2010)]. Also in the sequel we calculate some examples by one of the metrics.

math.FA↗
arXiv2011

Metrizability of Cone Metric spaces

In 2007 H. Long-Guang and Z. Xian, [H. Long-Guang and Z. Xian, Cone Metric Spaces and Fixed Point Theorems of Contractive Mapping, J. Math. Anal. Appl., 322(2007), 1468-1476], generalized the concept of a metric space, by introducing cone metric spaces, and obtained some fixed point theorems for mappings satisfying certain contractive conditions. The main question was "Are cone metric spaces a real generalization of metric spaces?" Throughout this paper we answer the question in the negative, proving that every cone metric space is metrizable and the equivalent metric satisfies the same contractive conditions as the cone metric. So most of the fixed point theorems which have been proved are straightforward results from the metric case.

math.FA↗