Araştırma Çıktıları | WoS | Scopus | TR-Dizin | PubMed
Permanent URI for this communityhttps://hdl.handle.net/20.500.14719/1741
Browse
4 results
Search Results
Publication Metadata only Neural Network-Based Human Detection Using Raw UWB Radar Data(IEEE, 2024) Dogan, Emine Berjin; Yousefi, Mohammad; Soyak, Ece Gelal; Karamzadeh, Saeid; Kolosovs, D; Bahcesehir University; Bahcesehir University; Bahcesehir University; Bahcesehir UniversityUltra-Wideband (UWB) radar technology is a widely used technology for human detection and tracking through walls, because of its effectiveness in low-visibility situations. This study demonstrates a neural network-based identification of human presence using raw data obtained directly from the UWB radar. First, measurements have been collected with different human subjects at different positions relative to the UWB radar. A convolutional neural network (CNN) model has been trained on this dataset, to detect the presence of a human. Next, the algorithm effectiveness is deeply investigated using the Gradient-weighted Class Activation Mapping (Grad-CAM) method, and the observations on detected presence are discussed.Publication Metadata only Faster Wi-Fi Fingerprinting Using Feature Selection(IEEE, 2020) Aydin, Hurkan M.; Ali, Muhammad Ammar; Soyak, Ece Gelal; Bahcesehir University; Bahcesehir UniversityWi-Fi fingerprinting has been widely used for indoor positioning, as Wi-Fi technology is easily deployed and supported. In fingerprinting, a database is created using the received signal strength indicator (RSSI) values in the area of interest, position prediction is performed by finding the best match for a measured RSSI among the values in the database. As location positioning gains importance for continuous interactive (CI) applications in large indoor spaces such as malls and airports, the fingerprinting databases become larger, making it computationally more difficult to position targets in real-time. On the other hand, CI applications such as Augmented Reality (AR) require low-latency positioning for a good user experience. In this work, we propose to use feature selection methods along with the K-nearest neighbors (KNN) classification and regression algorithms in order to create a simple and swift location positioning system. Our evaluation of various feature selection methods shows that computation times for positioning can be reduced by 75% using feature selection.Publication Metadata only The Analysis of Feature Selection with Machine Learning for Indoor Positioning(IEEE, 2021) Aydin, Hurkan M.; Ali, Muhammad Ammar; Soyak, Ece Gelal; Bahcesehir University; Bahcesehir UniversityIndoor positioning is useful in various venues including warehouses, convention centers, malls, airports, nursing homes. In these scenarios, reducing the complexity of location estimation both improves responsiveness and helps to elongate battery life of the mobile device. In this work, we carry out a detailed analysis of the impact of Principal Component Analysis (PCA) on the computational complexity and accuracy with different machine learning algorithms on a large data set containing 520 APs. We compare the algorithms' training and testing times, as well as their accuracies in the presence and absence of PCA. Our results show that (i) PCA significantly reduces both the training and testing times for classification and regression using k-nearest neighbor (kNN) and support vector machine (SVM) algorithms while preserving if not improving accuracy, (ii) PCA slightly improves the training/testing times for regression using multi-layer perceptron (MLP), (iii) random forest (RF) does not perform well with PCA.Publication Metadata only Low-Powered Agriculture IoT Systems with LoRa(IEEE, 2020) Kokten, Esma; Caliskan, Bahadir Can; Karamzadeh, Saeid; Soyak, Ece Gelal; Aboltins, A; Litvinenko, A; Bahcesehir University; Bahcesehir UniversityMonitoring is key to increase the efficiency of food storage in the open field in terms of cost, logistics and quality of the crops. For the long range data transmission in such environments, mobile technologies are not suitable, as the end devices are generally battery-limited. In this work, a prototype has been developed for monitoring goods in storage. The battery life time of this prototype is analysed in terms of calculations as well as measurements, on LoRa technology. Our results show that (i) while sleeping current has the smallest percentage, it has the greatest impact in increasing battery life, (ii) monitoring node shall have low self discharge battery for long battery life, and (iii) sensors are the main power sink that deplete battery.