Haluk Eren

Estimating driving behavior by a smartphone

In this paper, we propose an approach to understand the driver behavior using smartphone sensors. The aim for analyzing the sensory data acquired using a smartphone is to design a car-independent system which does not need vehicle mounted sensors measuring turn rates, gas consumption or tire pressure. The sensory data utilized in this paper includes the accelerometer, gyroscope and the magnetometer. Using these sensors we obtain position, speed, acceleration, deceleration and deflection angle sensory information and estimate commuting safety by statistically analyzing driver behavior. In contrast to state of the art, this work uses no external sensors, resulting in a cost efficient, simplistic and user-friendly system.

Stereo Vision and Statistical Based Behaviour Prediction of Driver

The goal of this project is to develop a Webcam-based system for monitoring the activities of automobile drivers. As in any system deployed for monitoring driver activities, the primary goal is to distinguish between safe and unsafe driving actions. There is no fixed list of actions that qualifies the unsafe driving behaviors. In general, an activity or an action that reduces a drivers alertness of their surroundings should be classified as unsafe driving behavior. Some examples of unsafe driving behavior include fatigue, talking on a cellular telephone, eating, and adjusting the controls of the dashboard stereo while driving. In this study, we also investigated the relationship between 2D and 3D face and pose recognition.

Upper airway detection and visualization from cone beam image slices.

This paper describes a method developed to assist in the detection and reconstruction of a three dimensional (3D) model of the human upper airway using cone beam computed tomography (CBCT) image slices and a 3D Gaussian smoothing kernel. The segmented and reconstructed volumetric airway is characterized by the corresponding three principal axes that are selected for viewing direction orientation via rotation and translation. These axes are derived using the 3D Principal Component Analysis (PCA) result of the rendered volume. To finely adjust the view and access airway, the major and minor axes of each slice are also computed using the two dimensional (2D) PCA in the respective planes. The exterior volume view is visualized in two modes, namely, a solid surface (volume details transparent to user) view and a nontransparent (volume detail accessible) view. This functionality provides an application driven use of the 3D airway in CBCT based anatomy studies. The extracted information may be useful as an imaging biomarker in the diagnostic assessment of patients with upper airway respiratory conditions such as obstructive sleep apnea, allergic rhinitis, and other related diseases; as well as planning orthopedic/orthodontic therapies.

Approaching car detection via clustering of vertical-horizontal line scanning optical edge flow

Here, we describe a method that detects vehicle(s) approaching from behind to a commuting car in the lane in which both are travelling. This research contributes to the development of driver assistance systems by means of informing them about the approaching traffic from behind and warn the drivers in case they are drowsy or not alert and the driving conditions are hazardous. We use the image pairs extracted from a video clip obtained from a video camera mounted on the back side of the car. This allows detection of the moving objects from the video image pairs using optical flow. Objects which are determined as not cars or vehicles have been eliminated by edge extraction. In turn, this approach leads to lessen the operation processing cost. Then, Density Histogram of Cluster Rows (DHCR) and Density Histogram of Cluster Columns (DHCC) are generated for the purpose of classification of motion vectors (MVs). Consequently, approching vehicles and cars are detected by localizing the place of the motion vector clusters using Vertical Horizontal Line Scanning (VHLS) as experimental results demonstrate.

An effective variable selection algorithm for Aggressive/Calm Driving detection via CAN bus

In this research, the aim is to come up with an algorithm determining most appropriate variables of CAN (Controller Area Network) bus data for Aggressive/Calm Driving detection problem. This study assists drivers to take attention their Aggressive/Calm Driving habits on steering wheel. System complexity increases as involving all the variables in the problem. Therefore we can get cost efficiency by eliminating variables. With this aim, the proposed algorithm is applied to find optimal variables before identifying driving mood. As an initial phase, we have realized several test-drives having employed drivers with different driving styles being aggressive and calm in order for collecting data needed. Afterwards the novel algorithm developed is applied to eliminate trivial variables. Proposed method is based on exploiting similar correlation characteristics related to variables appearing in both Aggressive and Calm driving. As applying the selection algorithm, similar relation clusters are obtained with the aim of searching for redundant variables that will be eliminated. In this manner we reach a favorable set belonging to optimal variables. This novel algorithm can be easily applied for the systems including binary data set.

Interactive risky behavior model for 3-car overtaking scenario using joint Bayesian network

In this paper, we propose a new model for 3-car interactive risky behavior of vehicles travelling in front and behind of a driver (overtaken) car. Following distance of vehicles moving in front and at rear end of the car in question plays an important role for overtaking scenario. Moreover, the distance between the car in front and the vehicle following it should be sufficiently long for preventing collision if overtaking is inevitable for the motorist behind the middle subject vehicle. Here, we consider the roles of the vehicles involved in such a scenario. We observe the behaviors of moving vehicles in front and the rear end of the subject car. To this end, front and rear car images are acquired by two cameras and subjected to vertical and horizontal optical flow edge map creation. In classification stage of the optical flow edge map clusters, a motion vector histogram thresholding method is utilized in conjunction with a decision assessment strategy based on the joint Bayesian belief network statistical model. In turn, not only the trajectories of the cars are captured but also joint behavior of three cars over-taken scenario is estimated using the proposed interactive risk model.

Cancer detection in mammograms estimating feature weights via Kullback-Leibler measure

In this study the aim is to determine cancerous possibility of suspicious lesions in mammograms. With this aim, probabilistic values of suspicious lesions in the image are found via exponential curve fitting and texture features in order to find weight values in the objective function. Afterwards, images are classified as normal, malign, and benign by utilizing Kullback Leibler method. Here, 3×10 mammography images set selected from Digital Database for Screening Mammography (DDSM) are used, and severity of disease is probabilistically estimated. Results are indicated on a scale to eliminate the suspicious lesions. Thus, it is considered that workload of clinicians shall be reduced by easily eliminating suspicious images out of many mammography images.

Prediction of driver head movement via Bayesian Learning and ARMA modeling

This paper introduces a drowsiness scale which illustrates instantaneous overall predictions about observed anomalous driver behavior. Driver can be informed about her/his own driving conditions by the camera mounted inside of the vehicle. Data obtained from driver behavior by observation is not sufficient to make a correct decision about overall vehicle and driver state unless road and vehicle conditions are also considered. Various driver related observations are involved in the design of an observatory system in collaboration with external road sensory inputs. In our system, we propose a Bayesian learning method about driver awareness state in learning phase. An auto-regressive moving average (ARMA) model is devised to be the driver drowsiness predictor. A mean-square tracking error is measured in different head positions to determine the predictors reliability and robustness under different illumination and conditions. An empirical set of plots is derived for the head positions corresponding to normal and drowsy driving conditions.

Smart driving in smart city

Smart cities have been drawing attention of researchers as seen in recent intensive studies. In associated with this fact, this situation is expected to continue in future works. In other side, smart vehicles are an indispensable part of smart cities. Scientists have been researching vehicles and transportation in order to reach safe and comfortable mobility. Among these vehicles, cars are the first ones that affect human life. In this study, smart cars and their drivers are elaborated in behavioral aspect. Existing works have been discussed to figure out futuristic driving behavior in smart city environment. In order to understand human thought system, additional studies have been given and recommendations have been provided. As seen in the researches conducted in recent years, researchers have been tried to interpret behavior of drivers by examining data taken by smart phones and vehicle OBD output. Evaluations are conducted by result of the specified methods. In recent decade, it has been observed that these behaviors are not only estimations; but also systems mounted on vehicles learn overall driving behavior. Hence, developed systems should work online while drivers on steering wheel. Consequently, this study will enlighten existing trends for different types of learning schemes. Future studies are expected to combine car, drivers biologic, psychological, and environmental data. Thus, in the near future, systems that understand the human thought will be developed.

Designing in-wheel switched reluctance motor for electric vehicles

Estimation of dimension parameters for an electrical machine has great importance before manufacturing. For this reason, analytical design should be performed in an optimum form. While motor analysis is accomplished by package programs, initial size parameters are intutivily provided and then various trials are examined to get optimum results. In this study, we are trying to find dimensional and electrical parameters generating mathematical equations in analytic approaches for In-Wheel Switched Reluctance Motor (IW-SRM), which will be employed by Electric Vehicle (EV). Therefore, optimum motor parameters for required speed and torque have been estimated by solving generated equations for in-wheel SRM with 18/12 poles via MATLAB. Using the parameters, analysis of in-wheel SRM has been carried out 3D Finite Element Method (FEM) by Ansoft Maxwell 15.0 Package Software. Consequently, the accuracy of the estimated parameters has been validated by the results of Maxwell 3D FEM.