Yazar "Dikmen, Ismail Can" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Control method simulation and application for autonomous vehicles
    (Ieee, 2018) Arikan, Abdullah; Kayaduman, Abdulsamed; Polat, Suat; Simsek, Yasin; Dikmen, Ismail Can; Bakir, Hincal Gokhan; Karadag, Teoman
    Autonomous vehicles can be operated without the need for human intervention by perceiving their physical environment, thanks to their automatic control systems. At present, extensive studies on autonomous land, sea, and air vehicles are ongoing all around the world. This project is focused on autonomous land vehicles. In the simplest examples, the speed and position of the vehicle can be controlled with the position sensor in the front wheel section and the speed sensors in the rear wheel section. Autonomy is achieved by generating signals for the control system by interpreting the data from various sensors on the vehicle with the aid of an algorithm. Different control methods can be applied for such vehicles. Within the scope of this project, the control of the vehicle will be provided by PID (Proportional-Integral-Derivative) control method, in order to constitute a basis for autonomous vehicle technology,
  • Küçük Resim Yok
    Öğe
    Design and implementation of ultrasonic sonar system for autonomous vehicles
    (Ieee, 2018) Seven, Sibel; Dikmen, Ismail Can; Karadag, Teoman; Bakir, H. Gokhan; Abbasov, Teymuraz
    Autonomous vehicles are vehicles that contain a variety of sensors that sense the environment and that can be actuated without driver intervention thanks to these sensors. Researches on autonomous vehicle technology continues at full speed. In this study, data from ultrasonic sensor and the temperature sensor are processed in the micro controller and displayed on the computer screen. For this, the microcontroller controls both the servo motor, calculates the sound velocity in the environment, and encodes the signal to be transmitted from the ultrasonic sensor. In this case, more accurate results are obtained than using fixed sound speed. In addition, the encoding of the signal sent from the ultrasonic transmitter is also prevented from being affected by noise or other sensors in the environment. This study was designed and conducted for the model vehicle to be used for autonomous vehicle studies in the laboratories of our university.
  • Küçük Resim Yok
    Öğe
    Development and application of sensor network for autonomous vehicles
    (Ieee, 2018) Kayaduman, Abdulsamed; Arikan, Abdullah; Dikmen, Ismail Can; Bakir, Hincal Gokhan; Karadag, Teoman; Abbasov, Teymuraz
    Autonomous vehicles are self-driving vehicles by interpreting data gathered from the environment through sensors. A set of sensors on the vehicle collects the raw data from the environment in which the vehicle is interacting. The software algorithms interpret the data from the sensors and generate commands for the vehicle to follow the path, change direction and maneuver. In this project, the data from the camera module and various sensors were processed and interpreted by means of software libraries on a network composed of micro controllers. Camera modules and image processing algorithms are used to detect strips along the roadside. The resulting images and the data from the other sensors generate the necessary commands for the vehicle's movement with a pivotal software formed on the embedded system. By this means the model autonomous vehicle gain self-motion capability by perceiving its surroundings.
  • Küçük Resim Yok
    Öğe
    Electrical Method for Battery Chemical Composition Determination
    (Ieee-Inst Electrical Electronics Engineers Inc, 2022) Dikmen, Ismail Can; Karadag, Teoman
    Storage of electrical energy is one of the most important technical problems in terms of today's technology. The increasing number of high-capacity high-power applications, especially electric vehicles and grid scale energy storage, points to the fact that we will be faced with a large number of batteries that will need to be recycled and separated in the near future. Additionally multi-chemistry battery management systems that enables the collective use of superior features of different batteries with different chemical composition. Here, battery chemical composition determination emerges as a technical problem. In this study, an alternative method to the currently used methods for categorizing batteries according to their chemistry is discussed. As the foundation, batteries with four different chemical composition including Lithium Nickel Cobalt Aluminium Oxide, Lithium Iron Phosphate, Nickel Metal Hydride, and Lithium Titanate Oxide aged with a battery testing hardware. Fifth, is Lithium Sulphur battery which is simulated. Brand new and aged batteries are used in experimental setup that is consist of a programmable electronic DC load and a software developed to run the algorithm on it. According to the algorithm, batteries are connected to two different loads one by one and voltage-current data are stored. Collected data are pre-processed by framing them and framed data are processed with a separation function. Eventually, the determination problem is converted to a classification problem. In order to solve this, artificial neural network and classification tree algorithms are applied. Because the artificial neural network algorithm is applied in previous studies and the high computational cost of it is presented; classification tree algorithm is concluded to be more applicable especially on low-power microcontroller applications. Consequently, 100% accuracy for battery chemical composition determination is achieved and results are presented comparatively.
  • Küçük Resim Yok
    Öğe
    State of Health Estimation of Lithium Titanate Oxide Batteries Through Data-Driven Techniques and Machine Learning
    (Institute of Electrical and Electronics Engineers Inc., 2024) Yildiran, Nisanur; Dikmen, Ismail Can; Karadag, Teoman
    In this study, State of Health (SoH) estimation of lithium-ion batteries, which are integral to our daily life, was carried out. Experimental data were taken from lithium titanate oxide (LTO) batteries with 18650 geometry, depending on the cycle aging process performed in constant current-constant voltage mode in the battery analyzer; 2000 cycles of charge and discharge data were recorded. The data obtained were extracted and pre-processed. The extracted data were subjected to differential voltage analysis, one of the data-driven methods used for SoH analysis. Differential Voltage Analysis (DVA) is a highly efficient method for accurate and detailed battery aging characteristics analysis. What sets this study apart is the use of machine learning algorithms, specifically Linear Regression (LR), Support Vector Machine (SVM), and Gaussian Process Regression (GPR), in conjunction with DVA. SoH prediction is considered a regression problem, and the innovative use of machine learning algorithms in this context is a key aspect of this research. As a result of the regression analysis performed in Matlab, the methods with the highest accuracy were determined. The SoH prediction with the highest accuracy was made by linear regression, and the error rate was 1.5005 RMSE. All findings obtained were evaluated comparatively. © 2024 IEEE.
  • Küçük Resim Yok
    Öğe
    The Digital Age in Last Two Decades Hidden Cost of Risen Mobile Connectivity from Minutes to Terabytes; Invisible Silent Rise Exposure to Electromagnetic Fields and Health Burden
    (Institute of Electrical and Electronics Engineers Inc., 2025) Karadaǧ, Teoman; Yildiran, Nisanur; Dikmen, Ismail Can; Abbasov, Teymuraz
    The last two decades have witnessed an unprecedented evolution in mobile communication, progressing from voice-centric 2 G systems to ultra-fast 5 G networks with latency in the millisecond range. This technological transformation - characterized by exponential growth in mobile data consumption, subscriber density, and network complexity - has significantly improved societal connectivity and digital accessibility. However, this rapid advancement has also led to a silent and largely overlooked consequence: the continuous and pervasive exposure to Radiofrequency Electromagnetic Fields (RF-EMF). This paper comprehensively analyzes the historical development of mobile communication technologies (0 G to 5 G), the corresponding increase in RF-EMF frequencies and intensities, and the emerging public health concerns linked to this exposure. Using long-term spectral measurements in commercial zones, residential areas, and radio link sites, the study reveals a persistent baseline of electromagnetic pollution that intensifies with human activity and data traffic. Particularly concerning is the accumulation of RF-EMF in living environments during peak communication hours. Current safety standards and exposure limits are discussed with an emphasis on temporal variability and spatial heterogeneity of RF-EMF distribution. The findings underscore the urgent need for continuous, real-time monitoring and epidemiological assessment of electromagnetic environments, particularly in densely populated urban areas and critical public infrastructure. The study advocates for policy-driven mitigations to balance technological benefits with long-term health and environmental sustainability. © 2025 IEEE.