Applied Article
H.3. Artificial Intelligence
Farid Ariai; Maryam Tayefeh Mahmoudi; Ali Moeini
Abstract
In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining, including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming ...
Read More
In the era of pervasive internet use and the dominance of social networks, researchers face significant challenges in Persian text mining, including the scarcity of adequate datasets in Persian and the inefficiency of existing language models. This paper specifically tackles these challenges, aiming to amplify the efficiency of language models tailored to the Persian language. Focusing on enhancing the effectiveness of sentiment analysis, our approach employs an aspect-based methodology utilizing the ParsBERT model, augmented with a relevant lexicon. The study centers on sentiment analysis of user opinions extracted from the Persian website 'Digikala.' The experimental results not only highlight the proposed method's superior semantic capabilities but also showcase its efficiency gains with an accuracy of 88.2% and an F1 score of 61.7. The importance of enhancing language models in this context lies in their pivotal role in extracting nuanced sentiments from user-generated content, ultimately advancing the field of sentiment analysis in Persian text mining by increasing efficiency and accuracy.
Original/Review Paper
F.2.11. Applications
Ali Sedehi; Alireza Alfi; Mohammadreza Mirjafari
Abstract
This paper addresses a key challenge in designing a suitable controller for DC-DC converters to regulate the output voltage effectively within a limited time frame. In addition to non-minimum phase behavior of such type of converter, a significant issue, namely parametric uncertainty, can further complicate ...
Read More
This paper addresses a key challenge in designing a suitable controller for DC-DC converters to regulate the output voltage effectively within a limited time frame. In addition to non-minimum phase behavior of such type of converter, a significant issue, namely parametric uncertainty, can further complicate this task. Robust control theory is an efficient approach to deal with this problem. However, its implementation often requires high-order controllers, which may not be practical due to hardware and computational constraints. Here, we propose a low-order robust controller satisfying the robust stability and performance criteria of conventional high-order controllers. To tackle this issue, a constraint optimization problem is formulated, and the evolutionary algorithms are adopted to achieve the optimal parameter values of the controller. Both simulation and experimental outcomes have been documented, and a comparative analysis with an optimal Proportional-Integral (PI) controller has been conducted to substantiate efficiency to the proposed methodology.
Original/Review Paper
H.5. Image Processing and Computer Vision
Farima Fakouri; Mohsen Nikpour; Abbas Soleymani Amiri
Abstract
Due to the increased mortality caused by brain tumors, accurate and fast diagnosis of brain tumors is necessary to implement the treatment of this disease. In this research, brain tumor classification performed using a network based on ResNet architecture in MRI images. MRI images that available in the ...
Read More
Due to the increased mortality caused by brain tumors, accurate and fast diagnosis of brain tumors is necessary to implement the treatment of this disease. In this research, brain tumor classification performed using a network based on ResNet architecture in MRI images. MRI images that available in the cancer image archive database included 159 patients. First, two filters called median and Gaussian filters were used to improve the quality of the images. An edge detection operator is also used to identify the edges of the image. Second, the proposed network was first trained with the original images of the database, then with Gaussian filtered and Median filtered images. Finally, accuracy, specificity and sensitivity criteria have been used to evaluate the results. Proposed method in this study was lead to 87.21%, 90.35% and 93.86% accuracy for original, Gaussian filtered and Median filtered images. Also, the sensitivity and specificity was calculated 82.3% and 84.3% for the original images, respectively. Sensitivity for Gaussian and Median filtered images was calculated 90.8% and 91.57%, respectively and specificity was calculated 93.01% and 93.36%, respectively. As a conclusion, image processing approaches in preprocessing stage should be investigated to improve the performance of deep learning networks.
Technical Paper
B.3. Communication/Networking and Information Technology
Roya Morshedi; S. Mojtaba Matinkhah; Mohammad Taghi Sadeghi
Abstract
IoT devices has witnessed a substantial increase due to the growing demand for smart devices. Intrusion Detection Systems (IDS) are critical components for safeguarding IoT networks against cyber threats. This study presents an advanced approach to IoT network intrusion detection, leveraging deep learning ...
Read More
IoT devices has witnessed a substantial increase due to the growing demand for smart devices. Intrusion Detection Systems (IDS) are critical components for safeguarding IoT networks against cyber threats. This study presents an advanced approach to IoT network intrusion detection, leveraging deep learning techniques and pristine data. We utilize the publicly available CICIDS2017 dataset, which enables comprehensive training and testing of intrusion detection models across various attack scenarios, such as Distributed Denial of Service (DDoS) attacks, port scans, botnet activity, and more. Our goal is to provide a more effective method than the previous methods. Our proposed deep learning model incorporates dense transition layers and LSTM architecture, designed to capture both spatial and temporal dependencies within the data. We employed rigorous evaluation metrics, including sparse categorical cross-entropy loss and accuracy, to assess model performance. The results of our approach show outstanding accuracy, reaching a peak of 0.997 on the test data. Our model demonstrates stability in loss and accuracy metrics, ensuring reliable intrusion detection capabilities. Comparative analysis with other machine learning models confirms the effectiveness of our approach. Moreover, our study assesses the model's resilience to Gaussian noise, revealing its capacity to maintain accuracy in challenging conditions. We provide detailed performance metrics for various attack types, offering insights into the model's effectiveness across diverse threat scenarios.
Applied Article
H.3. Artificial Intelligence
Sajjad Alizadeh Fard; Hossein Rahmani
Abstract
Fraud in financial data is a significant concern for both businesses and individuals. Credit card transactions involve numerous features, some of which may lack relevance for classifiers and could lead to overfitting. A pivotal step in the fraud detection process is feature selection, which profoundly ...
Read More
Fraud in financial data is a significant concern for both businesses and individuals. Credit card transactions involve numerous features, some of which may lack relevance for classifiers and could lead to overfitting. A pivotal step in the fraud detection process is feature selection, which profoundly impacts model accuracy and execution time. In this paper, we introduce an ensemble-based, explainable feature selection framework founded on SHAP and LIME algorithms, called "X-SHAoLIM". We applied our framework to diverse combinations of the best models from previous studies, conducting both quantitative and qualitative comparisons with other feature selection methods. The quantitative evaluation of the "X-SHAoLIM" framework across various model combinations revealed consistent accuracy improvements on average, including increases in Precision (+5.6), Recall (+1.5), F1-Score (+3.5), and AUC-PR (+6.75). Beyond enhanced accuracy, our proposed framework, leveraging explainable algorithms like SHAP and LIME, provides a deeper understanding of features' importance in model predictions, delivering effective explanations to system users.
Original/Review Paper
H.3. Artificial Intelligence
Damianus Kofi Owusu; Christiana Cynthia Nyarko; Joseph Acquah; Joel Yarney
Abstract
Head and neck cancer (HNC) recurrence is ever increasing among Ghanaian men and women. Because not all machine learning classifiers are equally created, even if multiple of them suite very well for a given task, it may be very difficult to find one which performs optimally given different distributions. ...
Read More
Head and neck cancer (HNC) recurrence is ever increasing among Ghanaian men and women. Because not all machine learning classifiers are equally created, even if multiple of them suite very well for a given task, it may be very difficult to find one which performs optimally given different distributions. The stacking learns how to best combine weak classifier models to form a strong model. As a prognostic model for classifying HNSCC recurrence patterns, this study tried to identify the best stacked ensemble classifier model when the same ML classifiers for feature selection and stacked ensemble learning are used. Four stacked ensemble models; in which first one used two base classifiers: gradient boosting machine (GBM) and distributed random forest (DRF); second one used three base classifiers: GBM, DRF, and deep neural network (DNN); third one used four base classifiers: GBM, DRF, DNN, and generalized linear model (GLM); and fourth one used five base classifiers: GBM, DRF, DNN, GLM, and Naïve bayes (NB) were developed, using GBM meta-classifier in each case. The results showed that implementing stacked ensemble technique consisting of five base classifiers on gradient boosted features achieved better performance than achieved on other feature subsets, and implementing this stacked ensemble technique on gradient boosted features achieved better performance compared to other stacked ensemble techniques implemented on gradient boosted features and other feature subsets used. Learning stacked ensemble technique having five base classifiers on GBM features is clinically appropriate as a prognostic model for classifying and predicting HNSCC patients’ recurrence data.
Original/Review Paper
H.3.2.2. Computer vision
Masoumeh Esmaeiili; Kourosh Kiani
Abstract
The classification of emotions using electroencephalography (EEG) signals is inherently challenging due to the intricate nature of brain activity. Overcoming inconsistencies in EEG signals and establishing a universally applicable sentiment analysis model are essential objectives. This study introduces ...
Read More
The classification of emotions using electroencephalography (EEG) signals is inherently challenging due to the intricate nature of brain activity. Overcoming inconsistencies in EEG signals and establishing a universally applicable sentiment analysis model are essential objectives. This study introduces an innovative approach to cross-subject emotion recognition, employing a genetic algorithm (GA) to eliminate non-informative frames. Then, the optimal frames identified by the GA undergo spatial feature extraction using common spatial patterns (CSP) and the logarithm of variance. Subsequently, these features are input into a Transformer network to capture spatial-temporal features, and the emotion classification is executed using a fully connected (FC) layer with a Softmax activation function. Therefore, the innovations of this paper include using a limited number of channels for emotion classification without sacrificing accuracy, selecting optimal signal segments using the GA, and employing the Transformer network for high-accuracy and high-speed classification. The proposed method undergoes evaluation on two publicly accessible datasets, SEED and SEED-V, across two distinct scenarios. Notably, it attains mean accuracy rates of 99.96% and 99.51% in the cross-subject scenario, and 99.93% and 99.43% in the multi-subject scenario for the SEED and SEED-V datasets, respectively. Noteworthy is the outperformance of the proposed method over the state-of-the-art (SOTA) in both scenarios for both datasets, thus underscoring its superior efficacy. Additionally, comparing the accuracy of individual subjects with previous works in cross subject scenario further confirms the superiority of the proposed method for both datasets.
Original/Review Paper
H.3.15.3. Evolutionary computing and genetic algorithms
Mahdieh Maazalahi; Soodeh Hosseini
Abstract
Detecting and preventing malware infections in systems is become a critical necessity. This paper presents a hybrid method for malware detection, utilizing data mining algorithms such as simulated annealing (SA), support vector machine (SVM), genetic algorithm (GA), and K-means. The proposed method combines ...
Read More
Detecting and preventing malware infections in systems is become a critical necessity. This paper presents a hybrid method for malware detection, utilizing data mining algorithms such as simulated annealing (SA), support vector machine (SVM), genetic algorithm (GA), and K-means. The proposed method combines these algorithms to achieve effective malware detection. Initially, the SA-SVM method is employed for feature selection, where the SVM algorithm identifies the best features, and the SA algorithm calculates the SVM parameters. Subsequently, the GA-K-means method is utilized to identify attacks. The GA algorithm selects the best chromosome for cluster centers, and the K-means algorithm has applied to identify malware. To evaluate the performance of the proposed method, two datasets, Andro-Autopsy and CICMalDroid 2020, have been utilized. The evaluation results demonstrate that the proposed method achieves high true positive rates (0.964, 0.985), true negative rates (0.985, 0.989), low false negative rates (0.036, 0.015), and false positive rates (0.022, 0.043). This indicates that the method effectively detects malware while reasonably minimizing false identifications.
Technical Paper
H.5. Image Processing and Computer Vision
Sekine Asadi Amiri; Mahda Nasrolahzadeh; Zeynab Mohammadpoory; AbdolAli Movahedinia; Amirhossein Zare
Abstract
Improving the quality of food industries and the safety and health of the people’s nutrition system is one of the important goals of governments. Fish is an excellent source of protein. Freshness is one of the most important quality criteria for fish that should be selected for consumption. It ...
Read More
Improving the quality of food industries and the safety and health of the people’s nutrition system is one of the important goals of governments. Fish is an excellent source of protein. Freshness is one of the most important quality criteria for fish that should be selected for consumption. It has been shown that due to improper storage conditions of fish, bacteria, and toxins may cause diseases for human health. The conventional methods of detecting spoilage and disease in fish, i.e. analyzing fish samples in the laboratory, are laborious and time-consuming. In this paper, an automatic method for identifying spoiled fish from fresh fish is proposed. In the proposed method, images of fish eyes are used. Fresh fish are identified by shiny eyes, and poor and stale fish are identified by gray color changes in the eye. In the proposed method, Inception-ResNet-v2 convolutional neural network is used to extract features. To increase the accuracy of the model and prevent overfitting, only some useful features are selected using the mRMR feature selection method. The mRMR reduces the dimensionality of the data and improves the classification accuracy. Then, since the number of samples is low, the k-fold cross-validation method is used. Finally, for classifying the samples, Naïve bayes and Random forest classifiers are used. The proposed method has reached an accuracy of 97% on the fish eye dataset, which is better than previous references.
Original/Review Paper
H.3.7. Learning
Mohammad Rezaei; Mohsen Rezvani; Morteza Zahedi
Abstract
With the increasing interconnectedness of communications and social networks, graph-based learning techniques offer valuable information extraction from data. Traditional centralized learning methods faced challenges, including data privacy violations and costly maintenance in a centralized environment. ...
Read More
With the increasing interconnectedness of communications and social networks, graph-based learning techniques offer valuable information extraction from data. Traditional centralized learning methods faced challenges, including data privacy violations and costly maintenance in a centralized environment. To address these, decentralized learning approaches like Federated Learning have emerged. This study explores the significant attention Federated Learning has gained in graph classification and investigates how Model Agnostic Meta-Learning (MAML) can improve its performance, especially concerning non-IID (Non-Independent Identically Distributed) data distributions.In real-world scenarios, deploying Federated Learning poses challenges, particularly in tuning client parameters and structures due to data isolation and diversity. To address this issue, this study proposes an innovative approach using Genetic Algorithms (GA) for automatic tuning of structures and parameters. By integrating GA with MAML-based clients in Federated Learning, various aspects, such as graph classification structure, learning rate, and optimization function type, can be automatically adjusted. This novel approach yields improved accuracy in decentralized learning at both the client and server levels.
Original/Review Paper
H.5. Image Processing and Computer Vision
Pouria Maleki; Abbas Ramazani; Hassan Khotanlou; Sina Ojaghi
Abstract
Providing a dataset with a suitable volume and high accuracy for training deep neural networks is considered to be one of the basic requirements in that a suitable dataset in terms of the number and quality of images and labeling accuracy can have a great impact on the output accuracy of the trained ...
Read More
Providing a dataset with a suitable volume and high accuracy for training deep neural networks is considered to be one of the basic requirements in that a suitable dataset in terms of the number and quality of images and labeling accuracy can have a great impact on the output accuracy of the trained network. The dataset presented in this article contains 3000 images downloaded from online Iranian car sales companies, including Divar and Bama sites, which are manually labeled in three classes: car, truck, and bus. The labels are in the form of 5765 bounding boxes, which characterize the vehicles in the image with high accuracy, ultimately resulting in a unique dataset that is made available for public use.The YOLOv8s algorithm, trained on this dataset, achieves an impressive final precision of 91.7% for validation images. The Mean Average Precision (mAP) at a 50% threshold is recorded at 92.6%. This precision is considered suitable for city vehicle detection networks. Notably, when comparing the YOLOv8s algorithm trained with this dataset to YOLOv8s trained with the COCO dataset, there is a remarkable 10% increase in mAP at 50% and an approximately 22% improvement in the mAP range of 50% to 95%.
Original/Review Paper
H.3. Artificial Intelligence
Afrooz Moradbeiky; Farzin Yaghmaee
Abstract
Knowledge graphs are widely used tools in the field of reasoning, where reasoning is facilitated through link prediction within the knowledge graph. However, traditional methods have limitations, such as high complexity or an inability to effectively capture the structural features of the graph. The ...
Read More
Knowledge graphs are widely used tools in the field of reasoning, where reasoning is facilitated through link prediction within the knowledge graph. However, traditional methods have limitations, such as high complexity or an inability to effectively capture the structural features of the graph. The main challenge lies in simultaneously handling both the structural and similarity features of the graph. In this study, we employ a constraint satisfaction approach, where each proposed link must satisfy both structural and similarity constraints. For this purpose, each constraint is considered from a specific perspective, referred to as a view. Each view computes a probability score using a GRU-RNN, which satisfies its own predefined constraint. In the first constraint, the proposed node must have a probability of over 0.5 with frontier nodes. The second constraint computes the Bayesian graph, and the proposed node must have a link in the Bayesian graph. The last constraint requires that a proposed node must fall within an acceptable fault. This allows for N-N relationships to be accurately determined, while also addressing the limitations of embedding. The results of the experiments showed that the proposed method improved performance on two standard datasets.
