The concept of Cyber Security (CS) has been started to be used with the development of Internet technology. Nowadays, CS has vital importance and Cyber Terror and Extremism (CTE) is one of the CS problems. Terror must be detected before terrorism comes true. In other words, people who commit the crime must be detected automatically before they move on. At this stage, what people say about some issues is very valuable because sayings can be turned into actions. The aim of this study is to use Antisocial Behavior dataset to try to detect CTE in the text contents. To detect CTE, text documents should be converted to numerical vectors which consist of numerical weights of the terms present in the text documents. Vectors are computed by using four different weighting methods in our study. These methods are the well-known binary weighting, term frequency based weighting, term frequency and inverse document frequency based weighting, and our proposed fuzzy set based weighting methods. Naive Bayes Multinomial (NBM) and Support Vector Machines (SVM) are used as classifiers to compare the performances of the weighting methods for CTE detection. Our experimental analysis shows that fuzzy set based weighting method with SVM classifier gives the best classification accuracy which reaches up to 99%.

Success is very important for all of us. Most people wants prosperity, reputation, and richness that can only be achieved with the success. A society that wants to be successful should pay attention to their new generation because they are the future of the world. If we want to invest to our future, we must contribute to success of our new generations. Therefore, in this study, the academic performance of the students that belong to different levels of education like primary, secondary, and high school levels is tried to be determined by applying various classification methods such as Multilayer Perceptron (MLP), Random Forest (RF), Naïve Bayes (NB), Decision Tree (J48), and Voting classifiers. It is also observed which characteristics are more related to the improvement of academic performance of the students. Features like absence of student, parent's school satisfaction, raising hands on class, and parent who is responsible for the student can affect the success of the student. A comparison is made with other study that previously worked on the same data set. As a result, better classification accuracy is achieved. We observe the best classification accuracy as 80.6% by Voting classifier, while the previous study has the highest accuracy as 79.1 % by applying Artificial Neural Network (ANN) classifier. Also, in our study, Apriori algorithm is applied to detect relationships between features.

Air pollution in cities is a serious environmental issue. In Turkey, the air quality index values of the measurement stations are calculated according to European Union standards. There are many kinds of measurement parameters (features) and 6 different kinds of air quality classes according to measurement stations in Turkey. Non-valuable features can be eliminated effectively with feature selection methods without any performance loss in classification. This study aims to investigate, analyze and implement a feature selection method using the FireFly Optimization Algorithm (FOA) approach. In the study, data from measurement stations for the Zonguldak region, which is known as the most polluted region in Turkey, are obtained and analyzed. Along with the acquired data, new features have been added such as day type day slots and the Covid19 feature since it is thought that curfew restrictions have an impact on air quality. The results were compared with a filter-based feature selection algorithm namely ReliefF. Experimental results show that FOA based feature selection method outperforms the ReliefF method at classification using the Random Forest classifier for air pollution even if with a fewer number of features. The Macro averaged F-score of the data set is increased from 0.685 to 0.988 using the FOA-based feature selection method.

Predicting driver injury severity is critical for enhancing road safety, but it is complicated because fatal accidents inherently create class imbalance within datasets. This study conducts a comparative analysis of machine-learning (ML) and deep-learning (DL) models for multi-class driver injury severity prediction using a comprehensive dataset of 107,195 traffic accidents from the Adana, Mersin, and Antalya provinces in Turkey (2018–2023). To address the significant imbalance between fatal, injury, and non-injury classes, the hybrid SMOTE-ENN algorithm was employed for data balancing. Subsequently, feature selection techniques, including Relief-F, Extra Trees, and Recursive Feature Elimination (RFE), were utilized to identify the most influential predictors. Various ML models (K-Nearest Neighbors (KNN), XGBoost, Random Forest) and DL architectures (Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN)) were developed and rigorously evaluated. The findings demonstrate that traditional ML models, particularly KNN (0.95 accuracy, 0.95 F1-macro) and XGBoost (0.92 accuracy, 0.92 F1-macro), significantly outperformed DL models. The SMOTE-ENN technique proved effective in managing class imbalance, and RFE identified a critical 25-feature subset including driver fault, speed limit, and road conditions. This research highlights the efficacy of well-preprocessed ML approaches for tabular crash data, offering valuable insights for developing robust predictive tools to improve traffic safety outcomes.

In previous studies, the focus has predominantly been on anomaly detection, with minimal attention given to anomaly prevention. However, anomaly prevention holds greater significance than anomaly detection. Preventing anomalous behavior before it occurs and identifying potential anomalies in advance to enable timely intervention is both challenging and crucial. In this study, a Suspicious Nodes Anomaly Prevention framework for anomaly prevention has been developed. First, a novel K-medoid based Salp Swarm Anomaly Detection method is proposed within the framework. This method reveals unclustered data by applying clustering and determines the boundaries of clusters using a nature-inspired algorithm that optimizes the threshold. Since threshold determination is an optimization problem, it aligns well with nature-inspired algorithms. Additionally, the Enron email dataset was selected as it is a real-world dataset with accessible content information. Initially, content and node features were extracted from the Enron email dataset. The proposed anomaly detection method was then applied separately to each of these features. Nodes identified as anomalous by one feature but normal by others were of particular interest. These nodes were labeled as “suspicious nodes,” and their connections were analyzed to detect potentially harmful email content. This framework fills a significant gap in the anomaly detection literature by contributing an unprecedented approach to anomaly prevention, offering early intervention capabilities in various sectors by identifying risks in advance. In this study, the proposed framework demonstrates high efficacy in detecting anomalies, achieving a True Positive Rate of 94% in node-based anomaly detection and 78% in content-based anomaly detection, indicating a robust capability for early intervention and risk identification.