ASAli Ghanbari Sorkhi

Ali Ghanbari Sorkhi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ali Ghanbari Sorkhi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Adaptive Hybrid Recommender System for Requirements Reuse

    by Mohammad Mehdi Pourhashem Kallehbasti, Sajjad Kazemi, Jamshid Pirgazi, Ali Ghanbari Sorkhi

    Introduction: Requirements engineering plays a crucial role in the software development lifecycle, encompassing the elicitation, analysis, specification, and validation of requirements. Inefficiencies in any of these processes can lead to delays, budget overruns, and even project failure. This paper explores the integration of requirements reuse and recommender systems to enhance the elicitation process by leveraging historical project data and stakeholder interaction patterns. Methods: The proposed methodology incorporates a hybrid approach that combines collaborative filtering and content‐based filtering to recommend relevant requirements to stakeholders. A dynamic weighting framework adjusts the contributions of these two approaches based on the availability of data. In situations with insufficient qualified data, the approach relies more heavily on content‐based filtering to address challenges such as data sparsity and the cold‐start problem. To enhance the semantic similarity between requirements, the method aggregates GloVe word vectors with domain‐specific TF‐IDF scores to identify software engineering‐specific vocabulary. Results: Experimental evaluation using a benchmark dataset demonstrates that the proposed hybrid approach significantly improves the prediction accuracy of relevant requirements recommendations, compared to traditional methods. Conclusion: The integration of requirements reuse with a recommender system that combines collaborative and content‐based filtering offers an effective solution to streamline the elicitation process, mitigate risks of overlooking critical requirements, and save time during the evaluation and selection of requirements. The proposed method improves the efficiency and accuracy of requirements engineering, especially in contexts with limited data availability.

  • Open Access

    MoGraphDRP: Multi-omics and graph fusion with bilinear attention for predicting drug sensitivity

    by Zahra Ahmadi, Jamshid Pirgazi, Ali Ghanbari Sorkhi

    Accurate prediction of drug response in cancer cells is a fundamental step toward achieving precision medicine and designing personalized therapies. In this study, a multi-branch deep learning framework is proposed that integrates multi-omics cellular data including gene expression, mutation, methylation, and biological pathways with structural features of drugs (molecular graphs and various chemical fingerprints) to enable drug response prediction. The graph structure of the drug is modeled using a three-layer Graph Convolutional Network (GCN), and chemical fingerprints are compressed using MLP networks. These multiple representations of drugs are integrated and then combined with cellular features in a Multi-head Bilinear Attention module to model the complex interactions between cells and drugs. In the final stage, an ensemble model based on XGBoost is used to refine the outputs. The MoGraphDRP model demonstrates significantly higher accuracy in drug response prediction compared to existing state-of-the-art methods. Experimental results show that the MoGraphDRP model outperforms advanced methods such as BANDRP, DeepCDR, and DeepTTA, achieving PCC = 0.9689, RMSE = 0.6622, and R² = 0.9388. This model not only accurately reconstructs missing IC50 values but also effectively distinguishes between sensitive and resistant drugs in unknown combinations. The MoGraphDRP framework can serve as a powerful, interpretable, and reliable tool for analyzing drug response and designing preclinical treatments.

  • Open Access

    Improving Drug-Target Interaction Prediction Using SVM-SMOTE: A Solution for Imbalanced Dataset

    by Sara Naghib Zadeh, Zümrüt Ecevit Satı, Ali Ghanbari Sorkhi

    Drug–target interaction (DTI) prediction is a critical step in the drug discovery process, as experimental methods are often time-consuming and expensive. Machine learning techniques have emerged as effective alternatives for this task. However, DTI datasets commonly suffer from severe class imbalance, where the number of true interactions is significantly lower than negative ones—posing a serious challenge for model training. This study proposes an effective framework for DTI prediction. The model utilizes amino acid composition (AAC) and dipeptide composition (DPC) methods to extract protein features, while FP2 molecular fingerprints are used to represent drug features. To address the class imbalance problem, the SVM-SMOTE technique—an SVM-based synthetic minority oversampling method—is employed. For model training, a Linear Support Vector Machine (LSVM) algorithm is used. The proposed model was evaluated against several state-of-the-art methods using benchmark datasets, including Enzyme, GPCR, Ion Channel, and Nuclear Receptor. The results demonstrate that the proposed framework achieves superior performance. Extensive experiments were conducted at various stages of model design, using evaluation metrics such as AUC, accuracy, F1-score, and recall, all of which confirm the effectiveness of the proposed approach.

  • Open Access

    A Hybrid TLBO–XGBoost Model With Novel Labeling for Bitcoin Price Prediction

    by Elnaz Radmand, Jamshid Pirgazi, Ali Ghanbari Sorkhi

    In the digital currency market, including Bitcoin, price prediction using artificial intelligence (AI) and machine learning (ML) is critical but challenging. Conventional methods such as technical analysis (based on historical market data) and fundamental analysis (based on economic variables) suffer from data noise, processing delays, and insufficient data. To make predictions more accurate, faster, and able to handle more data, the suggested method combines several steps: extracting important information, labeling it, choosing the best features, merging different models, and fine‐tuning the model settings. Based on the price data, this approach initially generates 5 labels with a new labeling method based on the percentage of average price changes in several days and generates signals (hold, buy, sell, strong sell, and strong buy). Thereafter, it extracts 768 features from technical studies using the TA‐Lib library and from an authoritative site. The TLBOA algorithm, which does not get stuck in the local optimum with two updates, was used to select and reduce features to 15 to avoid overfitting. A variety of ML models, including support vector machine and Naive Bayes, use these selected features for training. By using the evolutionary DE algorithm to optimize the XGBoost meta‐parameters, we increased the accuracy by 1%–4%. The proposed strategy has performed better than other models, such as XGBoost with 85.66% and gradient boosting with 84.15%, and has achieved an accuracy of 91%–92%.


  • Open Access

    An efficient hybrid filter-wrapper method based on improved Harris Hawks optimization for feature selection

    by Jamshid Pirgazi, Mohammad Mehdi Pourhashem Kallehbasti, Ali Ghanbari Sorkhi, Ali Kermani

    Introduction: High-dimensional datasets often contain an abundance of features, many of which are irrelevant to the subject of interest. This issue is compounded by the frequently low number of samples and imbalanced class samples. These factors can negatively impact the performance of classification algorithms, necessitating feature selection before classification. The primary objective of feature selection algorithms is to identify a minimal subset of features that enables accurate classification. Methods: In this paper, we propose a two-stage hybrid method for the optimal selection of relevant features. In the first stage, a filter method is employed to assign weights to the features, facilitating the removal of redundant and irrelevant features and reducing the computational cost of classification algorithms. A subset of high-weight features is retained for further processing in the second stage. In this stage, an enhanced Harris Hawks Optimization algorithm and GRASP, augmented with crossover and mutation operators from genetic algorithms, are utilized based on the weights calculated in the first stage to identify the optimal feature set. Results: Experimental results demonstrate that the proposed algorithm successfully identifies the optimal subset of features. Conclusion: The two-stage hybrid method effectively selects the optimal subset of features, improving the performance of classification algorithms on high-dimensional datasets. This approach addresses the challenges posed by the abundance of features, low number of samples, and imbalanced class samples, demonstrating its potential for application in various fields.


  • An efficient weighted partial MaxSAT encoding for scheduling in overloaded real-time systems

    by Mohammad Mehdi Pourhashem Kallehbasti, Jamshid Pirgazi, Ali Ghanbari Sorkhi, Ali Kermani

  • Open Access

    An Accurate Heart Disease Prognosis Using Machine Intelligence and IoMT

    by Jamshid Pirgazi, Ali Ghanbari Sorkhi, Majid Iranpour Mobarkeh

    In recent years, Internet of Medical Things (IoMT) and machine learning (ML) have played a major role in the healthcare industry and prediction of in time diagnosis of diseases. Heart disease has long been considered one of the most common and lethal causes of death. Accordingly, in this paper, a multiple-step method using IoMT and ML has been proposed for diagnosis of heart disease based on image and numerical resources. In the first step, transfer learning based on convolutional neural network (CNN) is used for feature extraction. In the second step, three methods of distributed stochastic neighbor embedding (t-SNE), F-score, and correlation-based feature selection (CFS) are utilized to select the best features. In the end, a combination of outputs of three classifiers including Gaussian Bayes (GB), support vector machine (SVM), and random forest (RF) according to the majority voting is employed for diagnosis of the conditions of heart disease patients. The results were evaluated on the two UCI datasets. The results indicate the improvement of performance compared to other methods.


  • Open Access

    An End-to-End Deep Learning Approach for Plate Recognition in Intelligent Transportation Systems

    by Jamshid Pirgazi, Mohammad Mehdi Pourhashem Kallehbasti, Ali Ghanbari Sorkhi

    Accurate and fast recognition of license plates is one of the most important challenges in the field of license plate recognition systems. Due to the high frame rate of surveillance cameras, old license plate recognition systems cannot be used in real-time applications. On the other hand, the presence of natural and artificial noise and different light and weather conditions make the detection and recognition process of these systems challenging. In this paper, an end-to-end method for efficiently detecting and recognizing plates is presented. In the proposed method, vehicles are first detected using a single-shot detector- (SSD-) based deep learning model in the video frames and the input images. This will increase the speed and accuracy in identifying the location of the plate in the given images. Then, the location of the plate is identified using the proposed architecture based on convolutional networks. Finally, using a deep convolutional network and long short-term memory (LSTM), the characters related to the plate are recognized. An advantage of our method is that the proposed deep network is trained using different images with different qualities that leads to high performance in detecting and recognizing plates. Also, considering that in the proposed method the vehicles are first detected and then the plate is detected in the vehicle image, there is no limit in the number of identified plates. Moreover, plate detection in the vehicle rectangle, instead of the whole frame, speeds up our method. The proposed method is evaluated using several databases. The first part of the evaluation focuses on robustness and recognition speed. The proposed method has the accuracy of 100% for vehicle detection, 100% for plate detection, and 99.37% for character recognition. In the second part of evaluation, the proposed method is evaluated in terms of overall speed. The experimental results witness that the proposed method is capable of processing 30 frames per second without losing any data and also outperforms several methods proposed in recent years, in terms of time and accuracy.