List of Articles
-
Open Access Article
1 - A New Hybrid Method Based on Intelligent Algorithms for Intrusion Detection in SDN-IoT
Zakaria Raeisi Fazlloah Adibnia Mahdi YazdianIn recent years, the use of Internet of Things in societies has grown widely. On the other hand, a new technology called Software Defined Networks has been proposed to solve the challenges of the Internet of Things. The security problems in these Software Defined Networ MoreIn recent years, the use of Internet of Things in societies has grown widely. On the other hand, a new technology called Software Defined Networks has been proposed to solve the challenges of the Internet of Things. The security problems in these Software Defined Networks and the Internet of Things have made SDN-IoT security one of the most important concerns. On the other hand, the use of intelligent algorithms has been an opportunity that these algorithms have been able to make significant progress in various cases such as image processing and disease diagnosis. Of course, intrusion detection systems for SDN-IoT environment still face the problem of high false alarm rate and low accuracy. In this article, a new hybrid method based on intelligent algorithms is proposed. The proposed method integrates the monitoring algorithms of frequent return gate and unsupervised k-means classifier in order to obtain suitable results in the field of intrusion detection. The simulation results show that the proposed method, by using the advantages of each of the integrated algorithms and covering each other's disadvantages, has more accuracy and a lower false alarm rate than other methods such as the Hamza method. Also, the proposed method has been able to reduce the false alarm rate to 1.1% and maintain the accuracy at around 99%. Manuscript profile -
Open Access Article
2 - Providing a Face Recognition System with an Optimal Selection of Features Based on the Cuckoo Optimization Algorithm
Farnaz Hoseini Hamed SepehrzadehFace recognition is a pattern recognition process that is specifically performed on faces. Face recognition has many applications in identifying credit cards, security systems, and other cases. Creating a face recognition system with high accuracy is a big challenge tha MoreFace recognition is a pattern recognition process that is specifically performed on faces. Face recognition has many applications in identifying credit cards, security systems, and other cases. Creating a face recognition system with high accuracy is a big challenge that has been the focus of various researchers in recent years. The feature extraction process and classification are two important issues in diagnosis systems that can play a significant role in increasing the accuracy of diagnosis. Considering this issue, in this study, taking into account the combined features and optimizing the cuckoo algorithm, a method to improve the accuracy of face recognition is proposed. In the presented method, seven features are extracted from the images in the database, and then by obtaining the feature vector, the steps related to feature selection are performed using the cuckoo algorithm. The proposed method has been implemented with MATLAB software and compared with other methods. The evaluation results show that the proposed method was able to perform the detection on the images of ORL and FDBB databases with 93.00% and 95.12% accuracy, respectively. The result obtained for this evaluation criterion has a higher value than other compared methods. Manuscript profile -
Open Access Article
3 - Ranking Improvement Using BERT
shekoofe bostan Ali-Mohammad Zare-Bidoki Mohammad-Reza PajoohanIn today's information age, efficient document ranking plays a crucial role in information retrieval systems. This article proposes a new approach to document ranking using embedding models, with a focus on the BERT language model to improve ranking results. The propose MoreIn today's information age, efficient document ranking plays a crucial role in information retrieval systems. This article proposes a new approach to document ranking using embedding models, with a focus on the BERT language model to improve ranking results. The proposed approach uses vocabulary embedding methods to represent the semantic representations of user queries and document content. By converting textual data into semantic vectors, the relationships and similarities between queries and documents are evaluated under the proposed ranking relationships with lower cost. The proposed ranking relationships consider various factors to improve accuracy, including vocabulary embedding vectors, keyword location, and the impact of valuable words on ranking based on semantic vectors. Comparative experiments and analyses were conducted to evaluate the effectiveness of the proposed relationships. The empirical results demonstrate the effectiveness of the proposed approach in achieving higher accuracy compared to common ranking methods. These results indicate that the use of embedding models and their combination in proposed ranking relationships significantly improves ranking accuracy up to 0.87 in the best case. This study helps improve document ranking and demonstrates the potential of the BERT embedding model in improving ranking performance. Manuscript profile -
Open Access Article
4 - On the Behavior of Pre-trained Word Embedding Variants in Deep Headline Generation from Persian Texts
Mohammad Ebrahim Shenassa Behrooz Minaei-BidgoliInspired by sequence-to-sequence models for machine translation, deep-learning based summarization methods were presented. The summaries generated this way, are structurally more readable and usually convey the complete meaning to the reader. In these methods, embeddi MoreInspired by sequence-to-sequence models for machine translation, deep-learning based summarization methods were presented. The summaries generated this way, are structurally more readable and usually convey the complete meaning to the reader. In these methods, embedding vectors are used for semantic representation, in which the weight of each word vector is learned according to its neighboring words from a large corpus. In static word embedding, the weight of the vectors is obtained by choosing a proximity window for each word. But in contextual ones like BERT, multilayer transformers are applied to calculate the weight of these vectors, which pay attention to all the words in the text. So far, several papers have shown that contextual word embedding are more successful than the other ones due to the ability of fine-tuning the weights to perform a specific natural language processing task. However, the performance of the initial weights of these vectors is not investigated for headline generation from Persian texts. In this paper, we will investigate the behavior of pre-trained word embedding variants without fine-tuning in deep headline generation from Persian texts. To train the headline generation model, "Elam Net" is used, which is a Persian corpus containing about 350 thousand pairs of abstracts and titles of scientific papers. The results show that the use of BERT model, even without fine-tuning its weights, is effective in improving the quality of generated Persian headlines, bringing the ROUGE-1 metric to 42%, which is better than the other pre-trained ones. Manuscript profile -
Open Access Article
5 - Emotion Recognition Based on EEG Signals Using Deep Learning Based on Bi-Directional Long Short-Term Memory and Attention Mechanism
Seyyed Abed Hosseini M. HoushmandThis research deals with the recognition of emotions from EEG signals using deep learning based on bi-directional long short-term memory (LSTM) and attention mechanism. In this study, two SEED and DEAP databases are utilized for the emotion recognition. The SEED databas MoreThis research deals with the recognition of emotions from EEG signals using deep learning based on bi-directional long short-term memory (LSTM) and attention mechanism. In this study, two SEED and DEAP databases are utilized for the emotion recognition. The SEED database includes EEG signals in 62 channels from 15 participants in three categories of positive, neutral, and negative emotions. The DEAP dataset includes EEG signals in 32 channels from 32 participants in two categories of valence and arousal. LSTM has shown its efficiency in extracting temporal information from long physiological signals. The innovations of this research include the use of a new loss function and Bayesian optimizer to find the initial learning rate. The accuracy of the proposed method for the classification of emotions in the SEED database is 96.72%. The accuracy of the proposed method for classifying emotions into two categories of valence and arousal is 94.9% and 97.1%, respectively. Finally, comparing the obtained results with recent research studies. Manuscript profile -
Open Access Article
6 - Comparison of Faster RCNN and RetinaNet for Car Recognition in Adverse Weather
Yaser Jamshidi Raziyeh Sadat OkhovatVehicle detection and tracking plays an important role in self-driving cars and smart transportation systems. Adverse weather conditions, such as the heavy snow, fog, rain, dust, create dangerous limitations by reducing camera visibility and affect the performance of de MoreVehicle detection and tracking plays an important role in self-driving cars and smart transportation systems. Adverse weather conditions, such as the heavy snow, fog, rain, dust, create dangerous limitations by reducing camera visibility and affect the performance of detection algorithms used in traffic management systems and autonomous cars. In this article, Faster RCNN deep object recognition network with ResNet50 core and RetinaNet network is used and the accuracy of these two networks for vehicle recognition in adverse weather is investigated. The used dataset is the DAWN file, which contains real-world images collected with different types of adverse weather conditions. The obtained results show that the presented method has increased the detection accuracy from 0.2% to 75% in the best case, and the highest increase in accuracy is related to rainy conditions. Manuscript profile -
Open Access Article
7 - Adaptive Acoustic Beamforming with Improved Differential Method
Negar Sarshar Mehdi BekraniDifferential beamformers exhibit effective performance in broadband applications, such as acoustic applications, but they have limited white noise gain. To address this limitation, this paper introduces an adaptive weighting-based algorithm designed to enhance the white MoreDifferential beamformers exhibit effective performance in broadband applications, such as acoustic applications, but they have limited white noise gain. To address this limitation, this paper introduces an adaptive weighting-based algorithm designed to enhance the white noise gain of the differential beamformer by leveraging the minimum variance distortionless response (MVDR) beamforming technique. For this purpose, differential beamforming is implemented in two stages: in the first stage, the spatial difference of observations is obtained, and in the second stage, the beamformer is optimized. Subsequently, by calculating the coefficients and combining the differential and MVDR beamformers, the proposed adaptive beamformer is derived. In this beamformer, to construct the output signal, the contribution of the differential and MVDR methods is dynamically adjusted using an adaptive combination coefficient, which is a function of frequency, microphone inter-distance, target angle, and the number of microphones. The proposed beamformer, considering four microphones spaced 2 cm apart reveals a remarkable enhancement in white noise gain by 35 dB and SNR gain by 18 dB at a frequency of 1 kHz. Additionally, the proposed adaptive algorithm demonstrates a 3.5 dB improvement in directivity factor over its differential counterpart. Manuscript profile