Authors:Bağış Altınöz; Hüsamettin Eken, Anıl Cönger, Sultan Can Abstract: This paper demonstrates a study that focuses on the modeling, design, and realization of an Inertial Measurement Unit (IMU) component for the use of Unmanned Aerial Vehicles (UAV). The experimental data is obtained by multiple flights conducted by the realized UAV (Teknofest–SEMRUK team UAV). The structure is remodeled for increasing the accuracy, and performance of the UAV after the conducted flights. Noise parameters are estimated throughout the Allan variance analysis. MEMS technology-based capacitive-type accelerometers and gyroscopes are preferred. This paper also discusses the error types and compares the real data with the modeled simulation data. Systematic errors of the inertial sensors are simulated according to their datasheet parameters. Sensor filters and noise are modeled and they are also implemented in the simulation. Simulation results and UAV measurements are compared to observe the efficiency of modeling. A complementary filter is presented and combined with a magnetometer, accelerometer, and gyroscope to obtain the ultimate design. The comparison showed a satisfactory agreement among the complementary filter measurements and UAV measurements in the stable position and the results presented. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Murat Şimşek; Mehmet Kemal Tekbaş Abstract: Due to the limitations of the hardware system, analysis of retail stores has caused problems such as excessive workload, incomplete analysis, slow analysis speed, difficult data collection, non-real-time data collection, passenger flow statistics, and density analysis. However, heatmaps are a viable solution to these problems and provide adaptable and effective analysis. In this paper, we propose to use the deep sequence tracking algorithm together with the YOLO object recognition algorithm to create heatmap visualizations. We will present key innovations of our customized YOLO-Deep SORT system to solve some fundamental problems in in-store customer behavior analysis. These innovations include our use of footpad targeting to make bounding boxes more precise and less noisy. Finally, we made a comprehensive evaluation and comparison to determine the success rate of our system and found that the success rate was higher than the systems we compared in the literature. The results show that our heatmap visualization enables accurate, timely, and detailed analysis. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Abdullah Asım Yılmaz Abstract: The detection of fraudulent activities in credit cards transactions presents a significant challenge due to the constantly changing and unpredictable tactics used by fraudsters, who take advantage of technological advancements to evade security measures and cause substantial financial harm. In this paper, we suggested a machine learning based methodology to detect fraud in credit cards. The suggested method contains four key phases, including data normalization, data preprocessing, feature selection, classification. For classification artificial neural network, decision tree, logistic regression, naive bayes, random forest while for feature selection particle swarm optimization is employed. With the use of a dataset created from European cardholders, the suggested method was tested. The experimental results show that the suggested method beats the other machine learning techniques and can successfully classify frauds with a high detection rate. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Yahya Doğan Abstract: Pooling is a non-linear operation that aggregates the results of a given region to a single value. This method effectively removes extraneous details in feature maps while keeping the overall information. As a result, the size of feature maps is reduced, which decreases computing costs and prevents overfitting by eliminating irrelevant data. In CNN models, the max pooling and average pooling methods are commonly utilized. The max pooling selects the highest value within the pooling area and aids in preserving essential features of the image. However, it ignores the other values inside the pooling region, resulting in a significant loss of information. The average pooling computes the average values within the pooling area, which reduces data loss. However, by failing to emphasize critical pixels in the image, it may result in the loss of significant features. To examine the performance of pooling methods, this study comprised the experimental analysis of multiple models, i.e. shallow and deep, datasets, i.e. Cifar10, Cifar100, and SVHN, and pool sizes, e.g. $2x2$, $3x3$, $10x10$. Furthermore, the study investigated the effectiveness of combining two approaches, namely Concat (Max, Avg), to minimize information loss. The findings of this work provide an important guideline for selecting pooling methods in the design of CNNs. The experimental results demonstrate that pooling methods have a considerable impact on model performance. Moreover, there are variances based on the model and pool size. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Oguzkan Akbel; Aykut Kalaycıoğlu Abstract: The weapon-target assignment problem has been considered as an essential issue for military applications to provide a protection for defended assets. The goal of a typical weapon-target assignment problem is to maximize the expected survivability of the valuable assets. In this study, defense of naval vessels that encounter aerial targets is considered. The vessels are assumed to have different types of weapons having various firepower and cost as well as the incoming targets may have different attack capabilities. In a typical scenario, in addition to protecting assets, it is also desirable to minimize the cost of weapons. Therefore, an asset-based static weapon-target assignment problem is considered in order to both maximize the expected survivability of the assets and minimize the weapon budget. Thus, a co-operative game theory based solution is proposed which relates the utilities of the individuals to the global utility and reach the Nash equilibrium. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Mustafa Veysel Özsarı; Şifa Özsarı, Ayhan Aydın, Mehmet Serdar Güzel Abstract: Technology and online opportunities brought by technology are increasing day by day. Many transactions, from banking to shopping, can be done online. However, the abuse of technology is also increasing at the same rate. Therefore, it is very important to ensure the security of the network for data protection. The application of artificial intelligence-based approaches has also become popular in the field of information security. When the data collected for intrusion detection is examined, it is seen that there are many features. In this study, the features in the USB-IDS-1 dataset were reduced by genetic algorithm and its success was examined with various classifiers. Among the selected methods, there are decision trees, random forest, k-NN, Naive Bayes and artificial neural networks. Accuracy, sensitivity, precision and F1-score were used as metrics. According to the results obtained, it was seen that the genetic algorithm was quite successful in the Hulk and Slowloris data set, it was partially effective in the Slowhttptest data, but was not successful in the TCP set. However, the performance of the algorithms was poor as a result of using all features in Slowhttptest and TCP data. PubDate: Fri, 14 Jun 2024 00:00:00 +030
Authors:Tolga Kayın; Çağatay Berke Erdaş Abstract: In the world where urbanization and population density are increasing, transportation methods are also diversifying and the use of unmanned vehicles is becoming widespread. In order for unmanned vehicles to perform their tasks autonomously, they need to be able to perceive their own position, the environment and predict the possible movements/routes of environmental factors, similar to living things. In autonomous vehicles, it is extremely important for the safety of the vehicle and the surrounding factors to be able to predict the future position of the objects around it with high performance so that the vehicle can plan correctly. Due to the stated reasons, the behavioral prediction module is a very important component for autonomous vehicles, especially in moving environments. In this study, fast and successful robotic behavioral prediction module has been developed to enable the autonomous vehicle to plan more safely and successfully. PubDate: Fri, 14 Jun 2024 00:00:00 +030