A5059557438- Neural Networks and Applications
- Energy Load and Power Forecasting
- Fuzzy Logic and Control Systems
- Fault Detection and Control Systems
- EEG and Brain-Computer Interfaces
- Anomaly Detection Techniques and Applications
- COVID-19 diagnosis using AI
- Electric Power System Optimization
- AI in cancer detection
- Stock Market Forecasting Methods
- Traffic Prediction and Management Techniques
- Machine Learning and ELM
- Metaheuristic Optimization Algorithms Research
- Blind Source Separation Techniques
- Traffic control and management
- Advanced Control Systems Optimization
- Artificial Intelligence in Healthcare
- Evolutionary Algorithms and Applications
- Adversarial Robustness in Machine Learning
- Solar Radiation and Photovoltaics
- Teleoperation and Haptic Systems
- Face and Expression Recognition
- Fuzzy Systems and Optimization
- Machine Fault Diagnosis Techniques
- Forecasting Techniques and Applications
Deakin University
2016-2025
Amirkabir University of Technology
2005-2024
Concordia University
2023
High Institute for Education and Research in Transfusion Medicine
2023
Intelligent Systems Research (United States)
2017-2022
Bionics Institute
2021
Iranian Legal Medicine Organization
2021
Aalborg University
2017
Universiti Teknologi Petronas
2016
Kohat University of Science and Technology
2016
Prediction intervals (PIs) have been proposed in the literature to provide more information by quantifying level of uncertainty associated point forecasts. Traditional methods for construction neural network (NN) based PIs suffer from restrictive assumptions about data distribution and massive computational loads. In this paper, we propose a new, fast, yet reliable method NN predictions. The lower upper bound estimation (LUBE) constructs an with two outputs estimating prediction interval...
Electrical power systems are evolving from today's centralized bulk to more decentralized systems. Penetrations of renewable energies, such as wind and solar power, significantly increase the level uncertainty in Accurate load forecasting becomes complex, yet important for management Traditional methods generating point forecasts demands cannot properly handle uncertainties system operations. To quantify potential associated with forecasts, this paper implements a neural network (NN)-based...
Quantification of uncertainties associated with wind power generation forecasts is essential for optimal management farms and their successful integration into systems. This paper investigates two neural network-based methods direct rapid construction prediction intervals (PIs) short-term forecasting in farms. The lower upper bound estimation bootstrap are used to quantify forecasts. effectiveness efficiency these general uncertainty quantification examined using twenty four month data from...
This paper makes use of the idea prediction intervals (PIs) to capture uncertainty associated with wind power generation in systems. Since forecasting errors cannot be appropriately modeled using distribution probability functions, here we employ a powerful nonparametric approach called lower upper bound estimation (LUBE) method construct PIs. The proposed LUBE uses new framework based on combination PIs overcome performance instability neural networks (NNs) used method. Also, fuzzy-based...
Uncertainty quantification plays a critical role in the process of decision making and optimization many fields science engineering. The field has gained an overwhelming attention among researchers recent years resulting arsenal different methods. Probabilistic forecasting particular prediction intervals (PIs) are one techniques most widely used literature for uncertainty quantification. Researchers have reported studies applications such as medical diagnostics, bioinformatics, renewable...
The early and reliable detection of COVID-19 infected patients is essential to prevent limit its outbreak. PCR tests for are not available in many countries also there genuine concerns about their reliability performance. Motivated by these shortcomings, this paper proposes a deep uncertainty-aware transfer learning framework using medical images. Four popular convolutional neural networks (CNNs) including VGG16, ResNet50, DenseNet121, InceptionResNetV2 first applied extract features from...
Preventing communicable diseases requires understanding the spread, epidemiology, clinical features, progression, and prognosis of disease. Early identification risk factors outcomes might help in identifying critically ill patients, providing appropriate treatment, preventing mortality. We conducted a prospective study patients with flu-like symptoms referred to imaging department tertiary hospital Iran between March 3, 2020, April 8, 2020. Patients COVID-19 were followed up after two...
Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, vehicles, must have reliable vision their workspace to robustly accomplish driving functions. Speaking machine vision, deep learning techniques, specifically convolutional neural networks, been proven be the state art technology in field. As these networks typically involve millions parameters elements, designing optimal architecture for structures difficult...
Accurate prediction of solar energy is an important issue for photovoltaic power plants to enable early participation in auction industries and cost-effective resource planning. This article introduces a new deep learning-based multistep ahead approach improve the forecasting performance global horizontal irradiance (GHI). A convolutional long short-term memory used extract optimal features accurate GHI. The such neural networks directly depends on their architectures. To deal with this...
The first known case of Coronavirus disease 2019 (COVID-19) was identified in December 2019. It has spread worldwide, leading to an ongoing pandemic, imposed restrictions and costs many countries. Predicting the number new cases deaths during this period can be a useful step predicting facilities required future. purpose study is predict rate one, three seven-day ahead next 100 days. motivation for every n days (instead just day) investigation possibility computational cost reduction still...
Deep neural networks (DNNs) have achieved the state-of-the-art (SOTA) performance in numerous fields. However, DNNs need high computation times, and people always expect better a lower computation. Therefore, we study human somatosensory system design network (SpinalNet) to achieve higher accuracy with fewer computations. Hidden layers (HLs) traditional NNs receive inputs previous layer, apply activation function, then transfer outcomes next layer. In proposed SpinalNet, each layer is split...