Zahra MARDANI Korani

Ms. Zahra MARDANI Korani


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
28 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
ZKZahra MARDANI Korani
Zahra MARDANI Korani
AMArmin Moin
Armin Moin
ASAlberto Rodrigues da Silva
Alberto Rodrigues da Silva
joao ferreirajoao ferreira
joao ferreira
This paper reviews the literature on model-driven engineering (MDE) tools and languages for the internet of things (IoT). Due to the abundance of big data in the IoT, data analytics and machine learning (DAML) techniques play a key role in providing smart IoT applications. In particular, since a significant portion of the IoT data is sequential time series data, such as sensor data, time series analysis techniques are required. Therefore, IoT modeling languages and tools are expected to support DAML methods, including time series analysis techniques, out of the box. In this paper, we study and classify prior work in the literature through the mentioned lens and following the scoping review approach. Hence, the key underlying research questions are what MDE approaches, tools, and languages have been proposed and which ones have supported DAML techniques at the modeling level and in the scope of smart IoT services.

28 March 2025 in Sensors
Verified
Journal Article
Open access
PDF file
GJGonçalo Jesus
Gonçalo Jesus
ZKZahra MARDANI Korani
Zahra MARDANI Korani
Elsa AlvesElsa Alves
Elsa Alves
AOAnabela Oliveira
Anabela Oliveira
This paper presents an innovative service for river flow forecasting and its demonstration in two dam-controlled rivers in Portugal, Tejo, and Mondego rivers, based on using Multilayer Perceptron (MLP) models to predict and forecast river flow. The main goal is to create and improve AI models that operate as remote services, providing precise and timely river flow predictions for the next 3 days. This paper examines the use of MLP architectures to predict river discharge using comprehensive hydrological data from Portugal’s National Water Resources Information System (Sistema Nacional de Informação de Recursos Hídricos, SNIRH), demonstrated for the Tejo and Mondego river basins. The methodology is described in detail, including data preparation, model training, and forecasting processes, and provides a comparative study of the MLP model’s performance in both case studies. The analysis shows that MLP models attain acceptable accuracy in short-term river flow forecasts for the selected scenarios and datasets, adeptly reflecting discharge patterns and peak occurrences. These models seek to enhance water resources management and decision-making by amalgamating modern data-driven methodologies with established hydrological and meteorological data sources, facilitating better flood mitigation and sustainable water resource planning as well as accurate boundary conditions for downstream forecast systems.

20 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
GJGonçalo Jesus
Gonçalo Jesus
ZKZahra MARDANI Korani
Zahra MARDANI Korani
Elsa AlvesElsa Alves
Elsa Alves
AOAnabela Oliveira
Anabela Oliveira
This paper presents an innovative service for river flow forecasting and its demonstration in two dam-controlled rivers in Portugal, Tejo and Mondego rivers, based on using Multilayer Perceptron (MLP) models to predict and forecast river flow. The main goal is to create and improve AI models that operate as remote services, providing precise and timely river flow predictions for the next 3 days. This paper examines the use of MLP architectures to predict river discharge using comprehensive hydrological data from Portugal’s National Water Resources Information System (Sistema Nacional de Informação de Recursos Hídricos, SNIRH), demonstrated for the Tejo and Mondego river basins. The methodology is described in detail, including data preparation, model training, and forecasting processes, and provides a comparative study of the MLP model’s performance in both case studies. The analysis shows that MLP models attain reasonable accuracy in short-term river flow forecasts for the selected scenarios and datasets, adeptly reflecting discharge patterns and peak occurrences. These models seek to enhance water resource management and decision-making by amalgamating modern data-driven methodologies with established hydrological and meteorological data sources, facilitating better flood mitigation and sustainable water resource planning as well as accurate boundary conditions for downstream forecast systems.

4 October 2026
Verified
Conference Paper
Open access
ZKZahra MARDANI Korani
Zahra MARDANI Korani
TSThimoty Smet
Thimoty Smet
Moharram ChallengerMoharram Challenger
Moharram Challenger
AMArmin Moin
Armin Moin
joao ferreirajoao ferreira
joao ferreira
GJGonçalo Jesus
Gonçalo Jesus


15 August 2023 in arXiv
Verified
Preprint
Open access
PDF file
ANAnahita Nekoozadeh
Anahita Nekoozadeh
MAMohammad Reza Ahmadzadeh
Mohammad Reza Ahmadzadeh
ZKZahra MARDANI Korani
Zahra MARDANI Korani
Transformers have achieved widespread success in computer vision. At their heart, there is a Self-Attention (SA) mechanism, an inductive bias that associates each token in the input with every other token through a weighted basis. The standard SA mechanism has quadratic complexity with the sequence length, which impedes its utility to long sequences appearing in high resolution vision. Recently, inspired by operator learning for PDEs, Adaptive Fourier Neural Operators (AFNO) were introduced for high resolution attention based on global convolution that is efficiently implemented via FFT. However, the AFNO global filtering cannot well represent small and moderate scale structures that commonly appear in natural images. To leverage the coarse-to-fine scale structures we introduce a Multiscale Wavelet Attention (MWA) by leveraging wavelet neural operators which incurs linear complexity in the sequence size. We replace the attention in ViT with MWA and our experiments with CIFAR and Tiny-ImageNet classification demonstrate significant improvement over alternative Fourier-based attentions such as AFNO and Global Filter Network (GFN).