Applied Article
H.3.2.2. Computer vision
Homayoun Rastegar; Hassan Khotanlou
Abstract
One of the challenges in digital image processing that we face today is the presence of haze in images. This challenge is particularly prominent in imaging areas with humid and rainy weather compared to other locations. Examples of AI-based systems that can be impacted by this type of challenge include ...
Read More
One of the challenges in digital image processing that we face today is the presence of haze in images. This challenge is particularly prominent in imaging areas with humid and rainy weather compared to other locations. Examples of AI-based systems that can be impacted by this type of challenge include smart traffic control cameras, autonomous vehicles, and Video Assistant Referee (VAR) systems in football stadiums, security and surveillance cameras, and more. Therefore, this paper aims to propose a method that can mitigate this problem using Self-Supervised Learning (SSL) and deep learning. To this end, a Convolutional Autoencoder Network (CAN) with Convolutional Block Attention Module (CBAM) was proposed to reduce haze from images. The advantage of the proposed method is using fewer layers and filters compared to other models introduced by previous researchers in this field and using more important convolutional channels and important image regions using CBAM. Experiments in this paper reveal that overusing large or numerous convolutional filters to generate diverse features can reduce a model's ability to dehaze images effectively. Thus, the number of filters should be carefully limited. On the other hand, a combined loss function was used to train the proposed architecture. The proposed model was trained and tested using NH-haze dataset and the Realistic Single Image Dehazing (RESIDE) dataset. To evaluate our method, we used structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR). The test results of the proposed architecture showed that it has higher performance compared to the state-of-the-art in the field.
Original/Review Paper
H.6.5.11. Robotics
Seyedeh Mahsa Zakipour Behambari; Saeed Khankalantary
Abstract
This paper focuses on the design of advanced controllers and the implementation of magnetic tracking and velocity tracking at the position control and formation control levels for a group of quadcopters. Initially, PID controllers are developed based on the quadcopter structure, and then a constrained ...
Read More
This paper focuses on the design of advanced controllers and the implementation of magnetic tracking and velocity tracking at the position control and formation control levels for a group of quadcopters. Initially, PID controllers are developed based on the quadcopter structure, and then a constrained fuzzy-PID controller is introduced to steer the system to the desired position. The performance of this controller is compared with classical PID and fuzzy-PID controllers. This study examines the arrangement and formation coordination of six quadcopters under three different scenarios, evaluating their formation control and coordination. Each quadcopter has an internal controller responsible for maintaining formation accuracy and system stability. Due to the complexity of quadcopter dynamics, trajectory tracking is one of the most challenging research areas. In this regard, a fuzzy-PID controller is proposed to stabilize the quadcopter along predefined trajectories, utilizing speed information as input. Simulation results in the MATLAB/Simulink environment demonstrate that the fuzzy-PID controller outperforms the classical PID controller. Moreover, this controller exhibits greater resistance to external disturbances across all axes, higher accuracy in reducing tracking errors, and improved stability. This superiority is particularly evident in multi-agent systems, emphasizing the significance of advanced control techniques in enhancing the regulation of both single and multi-agent quadcopters. Ultimately, this improves tracking performance while ensuring dynamic efficiency in uncertain environments.
Methodologies
H.3.8. Natural Language Processing
Mohammad Hadi Goldani; Saeedeh Momtazi; Reza Safabakhsh
Abstract
The widespread use of web-based forums and social media has led to an increase in news consumption. To mitigate the impact of misinformation on users' health-related decisions, it is crucial to develop machine learning models that can automatically detect and combat fake news. In this paper, we propose ...
Read More
The widespread use of web-based forums and social media has led to an increase in news consumption. To mitigate the impact of misinformation on users' health-related decisions, it is crucial to develop machine learning models that can automatically detect and combat fake news. In this paper, we propose a novel multilingual model with dynamic transformer model called Hybrid CapsNet for Covid-19 fake news detection in English and Persian languages. Our model incorporates two dynamic pre-trained representation models that incrementally uptrain and update the word embeddings in the training phase., dynamic RoBERTa for English and dynamic ParsBERT for Persian, and two parallel classifiers with new loss function namely margin loss. By utilizing dynamic transformer and both Deep Convolutional Neural Networks (DCNN) and Capsule Neural Networks (CapsNet), we achieve better performance than state-of-the-art baselines. To evaluate the proposed model, we use two recent Covid-19 datasets in English and Persian. Our results, in terms of F1-score, demonstrate the effectiveness of the Hybrid CapsNet model. Our model outperforms existing baselines, suggesting that it can be an effective tool for detecting and combating fake news related to Covid-19 in multiple languages. Overall, our study highlights the importance of developing effective machine learning models for combating misinformation during critical events such as the Covid-19 pandemic. The proposed model has the potential to be applied to other languages and domains and can be a valuable tool for protecting public health and safety.
Original/Review Paper
A.5. I/O and Data Communications
Farzane Shirazi; Nazbanoo Farzaneh
Abstract
Efficient allocation of parking spaces in urban environments remains a significant challenge due to diverse user preferences such as cost, proximity, and convenience. This paper proposes a novel intelligent parking assignment framework based on the Cheetah Optimization Algorithm (COA), a bio-inspired ...
Read More
Efficient allocation of parking spaces in urban environments remains a significant challenge due to diverse user preferences such as cost, proximity, and convenience. This paper proposes a novel intelligent parking assignment framework based on the Cheetah Optimization Algorithm (COA), a bio-inspired metaheuristic mimicking the adaptive hunting behavior of cheetahs. The method integrates user-specific criteria in a multi-stage process, first collecting system and driver data, then applying COA to optimize parking space allocation. Compared to deep reinforcement learning and other metaheuristics like Genetic Algorithm and Whale Optimization Algorithm, COA demonstrates faster convergence, and improved solution quality. The results confirm that COA is an effective and robust approach for real-time, personalized smart parking management in dynamic urban settings.
Original/Review Paper
H.6.3.2. Feature evaluation and selection
Zeinab Abbasi
Abstract
Storing and processing large volume datasets is one of the most critical problems in large-scale processing. Therefore, it is need to reduce their size before further processing. This paper is proposed a framework for data reduction in large-scale datasets. The proposed framework is based on MapReduce ...
Read More
Storing and processing large volume datasets is one of the most critical problems in large-scale processing. Therefore, it is need to reduce their size before further processing. This paper is proposed a framework for data reduction in large-scale datasets. The proposed framework is based on MapReduce algorithm. It has three steps. Firstly, by reservoir sampling, some instances of a dataset are selected. In the second step, the features of these selected instances are weighted using ReliefF algorithm. Then, all weights are averaged for each feature and features with the highest weight values are selected. Finally, the selected features have been used in classification. Implementation results of the proposed framework show a good reduction of time. It also increases accuracy or maintains it when a large amount of data is removed by eliminating irrelevant features in classification algorithms.
Original/Review Paper
H.3. Artificial Intelligence
Elahe Moradi
Abstract
Liver disorders are among the most common diseases worldwide, and their timely diagnosis and prediction can significantly improve treatment outcomes. In recent years, the application of artificial intelligence, particularly machine learning and deep learning algorithms, in the medical field has gained ...
Read More
Liver disorders are among the most common diseases worldwide, and their timely diagnosis and prediction can significantly improve treatment outcomes. In recent years, the application of artificial intelligence, particularly machine learning and deep learning algorithms, in the medical field has gained tremendous importance and has led to reduced healthcare costs. In this study, the ILPD dataset from the UCI Machine Learning Repository, which comprises 583 liver patient records with 11 features, was utilized. In this research, a predictive framework based on Multilayer Perceptron (MLP) is employed for the prediction of liver disorders. To address the class imbalance in the binary classification dataset, the Synthetic Minority Oversampling Technique (SMOTE)–Tomek approach was implemented to improve data balance. Moreover, due to the presence of a substantial number of outlier values, a robust scaling method was applied for their management. Finally, the performance of the proposed method was compared with three well-known machine learning algorithms. To enhance evaluation robustness, a five-fold cross-validation was employed across all classifiers. All simulations were conducted using Python, and the results illustrate that the proposed method achieves superior performance, with an accuracy of 90.90% compared to state-of-the-art approaches.
Original/Review Paper
H.6.5.2. Computer vision
Havva Askari; Razieh Rastgoo; Kourosh Kiani
Abstract
Drowsiness remains a significant challenge for drivers, often resulting from extended working hours, inadequate sleep, and accumulated fatigue. This condition not only impairs reaction time and decision-making but also contributes to a substantial number of road accidents globally. Therefore, reliable ...
Read More
Drowsiness remains a significant challenge for drivers, often resulting from extended working hours, inadequate sleep, and accumulated fatigue. This condition not only impairs reaction time and decision-making but also contributes to a substantial number of road accidents globally. Therefore, reliable and timely detection of driver drowsiness is essential for enhancing transportation safety and reducing the risk of traffic-related fatalities. With the rapid progress in deep learning, numerous models have been developed to detect driver drowsiness with high accuracy. However, the real-world performance of these models can deteriorate under varying environmental conditions, such as changes in cabin illumination, facial occlusions, and dynamic shadows on the driver’s face. To address these limitations, this paper proposes a robust, real-time driver drowsiness detection model that leverages facial behavioral features and a Transformer-based neural network architecture. The Mediapipe framework is utilized to extract a comprehensive set of facial keypoints, capturing subtle facial movements and expressions indicative of drowsiness. These keypoints are then encoded to form feature vectors that serve as input to the Transformer network, enabling effective temporal modeling of facial dynamics. The proposed model is trained and evaluated on the National Tsing Hua University (NTHU) Driver Drowsiness Detection dataset, achieving a state-of-the-art accuracy of 99.71%, demonstrating its potential for deployment in real-world in-vehicle systems.
Technical Paper
H.5. Image Processing and Computer Vision
Sekine Asadi Amiri; Zahra Davoudi
Abstract
wildfires are among the most serious environmental and socio-economic threats worldwide, significantly impacting ecosystems and climate patterns. In recent years, deep learning-based methods, particularly Convolutional Neural Networks (CNNs), have played a crucial role in improving wildfire detection ...
Read More
wildfires are among the most serious environmental and socio-economic threats worldwide, significantly impacting ecosystems and climate patterns. In recent years, deep learning-based methods, particularly Convolutional Neural Networks (CNNs), have played a crucial role in improving wildfire detection accuracy. This study presents an enhanced approach for identifying wildfire-affected areas using deep learning models. Specifically, three models—ResNet50, ResNet101, and EfficientNetB0—have been examined. To improve accuracy and reduce model complexity, the Flatten layer in all three architectures has been replaced with a Global Average Pooling (GAP) layer. This modification reduces the number of features and enhances the extraction of meaningful patterns from images. Additionally, a Dense layer with 128 neurons has been added after the GAP layer to enhance the learning and integration of the extracted features. To prevent overfitting, a Dropout layer with a rate of 0.5 has been incorporated. Finally, a Dense layer with 2 neurons serves as the output layer, responsible for the final classification. These optimizations have led to improved model accuracy and enhanced performance in wildfire detection. The dataset used consists of 42,850 satellite images, categorized into wildfire and nowildfire areas. Experimental results indicate that the ResNet101 model achieved the highest accuracy of 99.60%, while ResNet50 and EfficientNetB0 achieved accuracies of 99.35% and 99.10%, respectively. These results highlight the high potential of deep learning-based methods in improving wildfire detection accuracy and their role in environmental crisis management.
Original/Review Paper
H.3.2.3. Decision support
Fatemeh Iranmanesh; Najme Mansouri; Behnam Mohammad Hasani Zade
Abstract
The diagnosis of Alzheimer's Disease (AD) remains a significant challenge in medical research. To address the limitations of static models in capturing dynamic brain changes, this paper proposes a novel GNN-xLSTM model that integrates Graph Neural Networks (GNN) with an extended Long Short-Term Memory ...
Read More
The diagnosis of Alzheimer's Disease (AD) remains a significant challenge in medical research. To address the limitations of static models in capturing dynamic brain changes, this paper proposes a novel GNN-xLSTM model that integrates Graph Neural Networks (GNN) with an extended Long Short-Term Memory (xLSTM) architecture. The key innovation lies in combining GNN’s ability to model spatial relationships in brain imaging data with xLSTM’s enhanced sequential learning via matrix-based memory representation and exponential gate stabilization. In the proposed approach, brain images are divided into regions, with each region represented as a graph node connected in a grid structure, and feature vectors are extracted for each node. The proposed architecture incorporates Graph Convolutional Network (GCN) layers, xLSTM cells, residual connections, batch normalization, and dropout to jointly capture global, local, and temporal dependencies. Evaluated on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, the GNN-xLSTM model outperforms baseline models in terms of accuracy, precision, recall, and F1-score. These results demonstrate the model’s effectiveness in identifying critical brain regions and improving AD classification performance.
Research Note
H.3. Artificial Intelligence
Soodeh Shadravan; Ali Karimi
Abstract
The Coati Optimization Algorithm (COA) is a newly developed metaheuristic algorithm, drawing inspiration from the clever tactics Coatis use when attacking Iguanas as well as their strategies for dealing with and evading predators. This algorithm has shown a commendable level of effectiveness when compared ...
Read More
The Coati Optimization Algorithm (COA) is a newly developed metaheuristic algorithm, drawing inspiration from the clever tactics Coatis use when attacking Iguanas as well as their strategies for dealing with and evading predators. This algorithm has shown a commendable level of effectiveness when compared to various other metaheuristic algorithms. Its performance metrics indicate that it outperforms many alternatives in terms of efficiency and results. To overcome challenges such as the imbalance between exploration and exploitation phases and become trapped in local optima for solving complex optimization problems, an innovative technique known as "Enhanced Opposition-Based Learning" (EOBL) has been integrated with the COA algorithm. This technique draws inspiration from Random Opposition-Based Learning methods and can effectively influence the balance between exploration and exploitation phases. The Enhanced of Coati Optimization Algorithm (EOBCOA) is a novel metaheuristic algorithm proposed to enhance the performance of the COA. This method has been applied on standard benchmark functions to improve the proposed optimization algorithm. To assess the effectiveness of the proposed EOBCOA method, it was tested on standard benchmark functions, including IEEE CEC2005, IEEE CEC2019, and seven engineering problems. The results show that the EOBCOA method outperforms other advanced algorithms in achieving global optimization.
