Background/Objectives: In this study, a vision transformer (ViT) based ensemble architecture was developed for the classification of normal, benign, and malignant diseases from breast ultrasound images. The breast ultrasound images (BUSI) dataset was used for the implementation of the proposed method. This dataset includes 133 normal, 437 benign, and 210 malignant ultrasound images. Methods: ROI segmentation and image preprocessing were applied to the dataset to select only the tumor region and use it in the model. Thus, a better performance was achieved using only the lesion regions. Image augmentation was performed using the Albumentations library to increase the number of images. Feature extraction was performed on the obtained images using three ViT-based models (ViT-Base, DeiT, ViT-Small). The purpose of using three different models is to achieve high accuracy. The extracted features were classified using a multilayer perceptron (MLP). Training was performed using 10-fold stratified cross-validation. Results: The purpose of stratified cross-validation is to include a certain number of images from all three classes in each cross-validation proposed model provided 96.2% precision and 86.3% recall for the benign class and 92.9% recall and 76.4% precision for the malignant class. The normal class achieved 100% success. The area under the curve (AUC) values were 0.97, 0.96, and 1.00 for benign and malignant tumors, respectively, and 1.00 for normal tumors. Conclusions: The ROI-based ViT + MLP + Ensemble architecture provided higher accuracy and explainability compared to traditional convolutional neural network (CNN) based methods in medical image classification. It demonstrated a stable success, especially in minority classes, and presented a potential, reliable, and flexible solution in clinical decision support systems.

Location detection plays a crucial role in various applications. In this study, a machine learning (ML) method using inertial measurement unit (IMU) data was developed to determine direction with the Global Positioning System (GPS). In this study, an electronic board was designed using an Arduino Mega, Altimu-10 IMU sensor, GPS module, and SD card module. This electronic board was placed on a car to create a new dataset. This dataset consists of 1952x11 data. The dataset was obtained using accelerometer (x, y, z), gyroscope (x, y, z), compass (x, y, z), and GPS sensor data. The Decision Tree Algorithm was proposed for direction determination in this study. The angles between each position and the previous position were calculated using the latitude and longitude values obtained from the collected data. Then, the data were divided into 4 classes: North, East, South, and West, based on specific angle ranges. Finally, a direction detection model was developed using IMU data in the proposed method, achieving an accuracy of approximately 82.11%.

Machining processes often face challenges such as elevated temperatures and wear, which traditional cutting fluids are insufficient to address. As a result, solutions involving nanoparticle additives are being explored to enhance cooling and lubrication performance. This study investigates the effect of thermal conductivity, an important property influenced by the densities of mono and hybrid nanofluids. To this end, various nanofluids were prepared by incorporating hexagonal boron nitride (hBN), zinc oxide (ZnO), multi-walled carbon nanotubes (MWCNTs), titanium dioxide (TiO₂), and aluminum oxide (Al₂O₃) nanoparticles into sunflower oil as the base fluid. Hybrid nanofluids were created by combining two nanoparticles, including ZnO + MWCNT, hBN + MWCNT, hBN + ZnO, hBN + TiO₂, hBN + Al₂O₃, and TiO₂ + Al₂O₃. A dataset consisting of 180 data points was generated by measuring the thermal conductivity and density of the prepared nanofluids at various temperatures (30–70 °C) in a laboratory setting. Conducting thermal conductivity measurements across different temperature ranges presents significant challenges, requiring considerable time and resources, and often resulting in high costs and potential inaccuracies. To address these issues, a feedforward artificial neural network (FFANN) method was proposed to predict thermal conductivity. Our multilayer FFANN model takes as input the temperature of the experimental environment where the measurement is made, the measured thermal conductivity of the relevant nanoparticle, and the relative density of the nanoparticle. The FFANN model predicts the thermal conductivity value linearly as output. The model demonstrated high predictive accuracy, with a reliability of R = 0.99628 and a coefficient of determination (R²) of 0.9999. The average mean absolute error (MAE) for all hybrid nanofluids was 0.001, and the mean squared error (MSE) was 1.76 × 10⁻⁶. The proposed FFANN model provides a State-of-the-Art approach for predicting thermal conductivity, offering valuable insights into selecting optimal hybrid nanofluids based on thermal conductivity values and nanoparticle density.

Odor, one of our senses, is an important sense of life. In some cases, smell can be vitally important. A smell can also help in the correct recognition of a substance. Odor is composed of gas molecules. In this study, 8 simple semiconductor gas sensors were used to detect the odor of various substances. A gas sensor fusion setup was created with gas sensors and a candidate data set was created by collecting sensor data with the help of Arduino Mega embedded system. With the help of this data set, the odor of 7 different cleaning agents and similar substances was detected with the help of Decision Trees (DT). The results obtained from the decision tree (DT) classifier using the data set obtained from the fusion setup (95.44%) are close to the state-of-the-art results. As a result of the study, the feasibility of an embedded odor detection device has been demonstrated.