Category: Journal of AI and Data Mining

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.

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.

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.

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.

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.

Efficient regular-frequent pattern mining from sensors-produced data has become a challenge. The large volume of data leads to prolonged runtime, thus delaying vital predictions and decision makings which need an immediate response. So, using big data platforms and parallel algorithms is an appropriate solution. Additionally, an incremental technique is more suitable to mine patterns from big data streams than static methods. This study presents an incremental parallel approach and compact tree structure for extracting regular-frequent patterns from the data of wireless sensor networks. Furthermore, fewer database scans have been performed in an effort to reduce the mining runtime. This study was performed on Intel 5-day and 10-day datasets with 6, 4, and 2 nodes clusters. The findings show the runtime was improved in all 3 cluster modes by 14, 18, and 34% for the 5-day dataset and by 22, 55, and 85% for the 10-day dataset, respectively.

The Internet of Things (IoT) has emerged as a rapidly growing technology that enables seamless connectivity between a wide variety of devices. However, with this increased connectivity comes an increased risk of cyber-attacks. In recent years, the development of intrusion detection systems (IDS) has become critical for ensuring the security and privacy of IoT networks. This article presents a study that evaluates the accuracy of an intrusion detection system (IDS) for detecting network attacks in the Internet of Things (IoT) network. The proposed IDS uses the Decision Tree Classifier and is tested on four benchmark datasets: NSL-KDD, BOT-IoT, CICIDS2017, and MQTT-IoT. The impact of noise on the training and test datasets on classification accuracy is analyzed. The results indicate that clean data has the highest accuracy, while noisy datasets significantly reduce accuracy. Furthermore, the study finds that when both training and test datasets are noisy, the accuracy of classification decreases further. The findings of this study demonstrate the importance of using clean data for training and testing an IDS in IoT networks to achieve accurate classification. This research provides valuable insights for the development of a robust and accurate IDS for IoT networks.

Hidden Markov Models (HMMs) are machine learning models that has been applied to a range of real-life applications including intrusion detection, pattern recognition, thermodynamics, statistical mechanics among others. A multi-layered HMMs for real-time fraud detection and prevention whilst reducing drastically the number of false positives and negatives is proposed and implemented in this study. The study also focused on reducing the parameter optimization and detection times of the proposed models using a hybrid algorithm comprising the Baum-Welch, Genetic and Particle-Swarm Optimization algorithms. Simulation results revealed that, in terms of Precision, Recall and F1-scores, our proposed model performed better when compared to other approaches proposed in literature.

The identification of emotions in short texts of low-resource languages poses a significant challenge, requiring specialized frameworks and computational intelligence techniques. This paper presents a comprehensive exploration of shallow and deep learning methods for emotion detection in short Persian texts. Shallow learning methods employ feature extraction and dimension reduction to enhance classification accuracy. On the other hand, deep learning methods utilize transfer learning and word embedding, particularly BERT, to achieve high classification accuracy. A Persian dataset called "ShortPersianEmo" is introduced to evaluate the proposed methods, comprising 5472 diverse short Persian texts labeled in five main emotion classes. The evaluation results demonstrate that transfer learning and BERT-based text embedding perform better in accurately classifying short Persian texts than alternative approaches. The dataset of this study ShortPersianEmo will be publicly available online at https://github.com/vkiani/ShortPersianEmo.

Machine learning (ML) is a popular tool in healthcare while it can help to analyze large amounts of patient data, such as medical records, predict diseases, and identify early signs of cancer. Gastric cancer starts in the cells lining the stomach and is known as the 5th most common cancer worldwide. Therefore, predicting the survival of patients, checking their health status, and detecting their risk of gastric cancer in the early stages can be very beneficial. Surprisingly, with the help of machine learning methods, this can be possible without the need for any invasive methods which can be useful for both patients and physicians in making informed decisions. Accordingly, a new hybrid machine learning-based method for detecting the risk of gastric cancer is proposed in this paper. The proposed model is compared with traditional methods and based on the empirical results, not only the proposed method outperform existing methods with an accuracy of 98% but also gastric cancer can be one of the most important consequences of H. pylori infection. Additionally, it can be concluded that lifestyle and dietary factors can heighten the risk of gastric cancer, especially among individuals who frequently consume fried foods and suffer from chronic atrophic gastritis and stomach ulcers. This risk is further exacerbated in individuals with limited fruit and vegetable intake and high salt consumption.