|
|
|
 |
Search published articles |
 |
|
Showing 4 results for Askari
Dr Elham Askari,
Volume 16, Issue 1 (3-2025)
Abstract
Emotion recognition in Persian texts using data mining is a significant area within text analysis. Emotions are typically defined as individuals’ emotional reactions to situations, events, and information. Emotion recognition in text involves identifying and analyzing emotional content across various types of textual data. This paper presents a model for detecting different emotions in Persian texts using an enhanced transfer model. The proposed model comprises an encoder and a decoder, each equipped with a self-attention mechanism and RNN modules. Initially, a dataset of sentences annotated with emotional states—anger, happiness, sadness, and fear—is created by multiple users. These sentences are then converted into image representations and fed into the improved transfer model for emotion recognition. Experimental results demonstrate that the model effectively identifies the emotions of sadness, anger, happiness, and surprise with precision, accuracy, recall, and F1-score values of 90.25%, 91.4%, 91.6%, and 90.80%, respectively.
Mrs Sareh Bagheri Matak, Dr Elham Askari, Dr Sara Motamed,
Volume 16, Issue 2 (8-2025)
Abstract
Leukemia is one of the most common and dangerous types of cancer in the world. In many cases, the disease is curable if detected in its early stages. One of the effective tools for early detection is the analysis of microarray data, which measures the expression of thousands of genes simultaneously. However, the large volume of features and the presence of noise make the analysis process complex and time-consuming. Therefore, the selection of effective genes plays a key role in increasing the accuracy and reducing the computational cost of learning models. In this paper, a two-step hybrid approach is presented for feature selection and classification of leukemia types. In the first step, the features are filtered using the mutual information criterion and the genes with the highest correlation with the disease label are selected. In the second step, the XGBoost model is used to rank and stably select the features to identify the genes that are most important in different iterations. In the final stage, classification will be performed using the temporal fusion transformer method, which allows for fast and efficient learning of complex patterns among selected genes. Experimental results on real microarray datasets show that the proposed method outperforms the baseline methods with an accuracy of 99.2% and has been able to identify key genes effective in differentiating leukemia types by effectively reducing the data dimensions.
Saba Gholami, Sara Motamed, Elham Askari,
Volume 17, Issue 1 (5-2026)
Abstract
Autism spectrum disorder (ASD) is consistently associated with abnormal functional connectivity; resting-state fMRI data were obtained from the ABIDE dataset. Dynamic functional connectivity (DFC) was obtained in an autism-specific subnetwork consisting of 17 regions identified from previous static connectivity analyses. Time-varying connectivity matrices were estimated using a sliding window approach, and recurrent connectivity states were identified using a hidden Markov model. Dynamic measures included state occupancy rate, mean dwell time, and edge-level connectivity variability. Compared with controls, individuals with ASD showed a significant decrease in the occupancy of highly integrated connectivity states (ASD: 28.6 ± 7.4% vs. control: 36.9 ± 8.1%, p < 0.001) and longer dwell times in poorly integrated connectivity states (ASD: 42.3 ± 10.2 vs. control: 31.7 ± 9.5 s, p = 0.002). In contrast, edge-level connectivity variability was significantly increased in ASD, particularly in default mode-limbic connections. Importantly, increased connectivity variability in the default mode network significantly predicted ADOS total scores (β = 0.41), (p = 0.001). These findings suggest a dissociation between reduced network state flexibility and increased moment-to-moment connectivity variability in autism spectrum disorder (ASD).
Dr Elham Askari,
Volume 17, Issue 1 (5-2026)
Abstract
Autism Spectrum Disorder is associated with atypical brain function and altered neural patterns. In this study, an unsupervised and interpretable model based on Growing Self-Organizing Maps is proposed for modeling brain patterns in individuals with ASD. Neuroimaging data from the ABIDE I T1-weighted structural MRI dataset are utilized, and discriminative features, including wavelet coefficients, entropy measures, intensity histograms, and edge-based descriptors, are extracted from brain images. The GSOM model dynamically adapts its topology to the underlying data distribution, enabling effective structural representation of brain patterns. While the learning process is fully unsupervised, class labels are introduced only in a post-hoc evaluation step to assess model performance. Experimental results demonstrate that the proposed framework achieves a classification accuracy of 94.2%, while providing clearer cluster separation and improved structural modeling compared to fixed-topology self-organizing networks. These findings indicate that GSOM is a promising tool for adaptive brain modeling and structural analysis of ASD beyond conventional classification-oriented approaches.
|
|
