Ayman Atia

A Comparative Study of User Dependent and Independent Accelerometer-Based Gesture Recognition Algorithms

In this paper, we introduce an evaluation of accelerometer-based gesture recognition algorithms in user dependent and independent cases. Gesture recognition has many algorithms and this evaluation includes Hidden Markov Models, Support Vector Machine, K-nearest neighbor, Artificial Neural Net-work and Dynamic Time Warping. Recognition results are based on acceleration data collected from 12 users. We evaluated the algorithms based on the recognition accuracy related to different number of gestures from two datasets. Evaluation results show that the best accuracy for 8 and 18 gestures is achieved with dynamic time warping and K-nearest neighbor algorithms.

Three-dimensional angiography using mobile C-arm with IMU sensor attached: Initial study

Three-dimensional (3D) computed tomography (CT) imaging is becoming an essential demand in several clinical procedures. Mobile C-arm is a useful imaging tool for image-guided interventional radiology. C-arm systems are provided with X-ray image intensifier (XRII) or flat-panel detectors. Essentially, C-arm CT systems requires scanners with flat-panel detectors for its ability to provide homogenous image quality and improve the resolution of low-contrast subjects compared to those equipped with XRII. However, C-arm systems with XRIIs are widely used in several interventional procedures. Such systems can provide a high quality two-dimensional (2D) fluoroscopic images that facilitates minimal invasive surgery. However, it is unable to provide depth information for 3D imaging due to several factors. First, the gantry of XRII-based C-arms is usually operated manually, where the rotation angle is determined using printed angle scale attached to the scanner gantry. Second, the gantry orbital rotation is normally limited to angular range less than theoretically required for exact 3D reconstruction. Third, considering the offset-scan geometry, which is common configuration in mobile C-arm with XRII, the number of rays passing through field-of-view (FOV) is limited. In this paper, we develop a 3D angiographic imaging system using commercial C-arm system equipped with XRII. First, an in-house made gantry rotation unit is developed to control the scanner orbital rotation. Second, the gantry rotation is traced using inertial measurement unit (IMU) sensor attached to the scanner gantry. Geometry information obtained from IMU sensor are used to define the gantry position in the 3D space and synchronized with detector measurements. The SCAN algorithm is used for the 3D reconstruction and achieved results are of high quality.

Recognizing Driving Behavior and Road Anomaly using Smartphone Sensors

Roadtrafficaccidentsarecaused1.25milliondeathsperyearworldwide.Toimproveroadsafety andreducingroadaccidents,arecognitionmethodfordrivingeventsisintroducedinthispaper.The proposedmethoddetectedandclassifiedbothdrivingbehaviorsandroadanomaliespatternsbasedon smartphonesensors(accelerometerandgyroscope).k-NearestNeighborandDynamicTimeWarping algorithmswereutilizedformethodevaluation.Experimentswereconductedtoevaluatek-nearest neighboranddynamictimewarpingalgorithmsaccuracyforroadanomaliesanddrivingbehaviors detection,moreover,drivingbehaviorsclassification.Evaluationresultsshowedthatk-nearestneighbor algorithmdetectedroadanomaliesanddrivingbehaviorswithtotalaccuracy98.67%.Dynamictime warpingalgorithmclassified(normalandabnormal)drivingbehaviorswithtotalaccuracy96.75%. KeywoRDS Anomaly Detection, Behavior Classification, Driving Behavior, Road Anomalies, Smartphone Sensors

An Experimental Comparison Between Seven Classification Algorithms for Activity Recognition

The daily activities recognition is one of the most important areas that attract the attention of researchers. Automatic classification of activities of daily living (ADL) can be used to promote healthier lifestyle, though it can be challenging when it comes to intellectual disability personals, the elderly, or children. Thus developing a technique to recognize activities with high quality is critical for such applications. In this work, seven algorithms are developed and evaluated for classification of everyday activities like climbing the stairs, drinking water, getting up from bed, pouring water, sitting down on a chair, standing up from a chair, and walking. Algorithms of concern are K-nearest Neighbor, Artificial Neural Network, and Naive Bayes, Dynamic Time Warping,

Single Trial Authentication with Mental Password Writing

1 recognizer, Support Vector Machine, and a novel classifier (D

Anti-Bump: A Bump/Pothole Monitoring and Broadcasting System for Driver Awareness

1). We explore different algorithm activities with regard to recognizing everyday activities. We also present a technique based on

RemoAct: Portable Projected Interface with Hand Gesture Interaction

1 and DTW to enhance the recognition accuracy of ADL. Our result show that we can achieve up to 83 % accuracy for seven different activities.

Authentication Systems: Principles and Threats

This paper presents an authentication system that uses brain waves as a biometric discriminant trait. It utilizes Electroencephalogram EEG signals generated from mental writing of the user-owned password. Independent Component Analysis ICA and baseline correction has been used for preprocessing and noise removal. The effect of two types of features, multivariate autoregressive MVAR model parameters and power spectral density PSD features, have been studied for this activity. Performance results based on single trial analysis have revealed that imagined password writing can reach average Half Total Error Rate HTER of 5i¾ź% for PSD features vs 3i¾ź% obtained with MVAR coefficients. The experiments have shown that mental password writing can be used for increasing the user acceptance for enrollment conditions while maintaining high performance results.

Interactive Gestures for Liver Angiography Operation

This paper presents a system for bump detection and alarming system for drivers. We have presented an architecture that adopts context awareness and Bump location broadcasting to detect and save bumps locations. This system uses motion sensor to get the readings of the bump then we classify it using Dynamic Time Wrapping, Hidden Markov Model and Neural Network. We keep records for the bump location through tracking its geographic position. We developed a system that alarms the driver within appropriate profiled distance for bump occurrence. We conducted two experiments for testing the system in a street modeled architect with different kinds of bumps and potholes. The other experiment was on real street bumps. The results show that the system can detect bumps and potholes with reasonably accepted accuracy.

Hexart: Smart Merged Touch Tables

RemoAct is a wearable depth sensing and projection system that enables interaction on many surfaces. It makes interaction with the environment more intuitive through sharing and sending data with surrounding devices by applying certain gestures. This system offers a mobile and intuitive solution for interacting using a projected surface on habitual flat surfaces. Every user has their public and private areas, where the user can create tiles on the fly and share it with others and these public tiles are shown to other users through augmented reality. Interaction is made through hand gestures, finger tracking and hand tracking. This gives the user more freedom in movement. Different experiments were conducted to calculate the accuracy and RemoAct ran against different conventional methods to compare its accuracy, time and user experience. RemoAct takes less time for two users to draw one chart. As the system enables the users to work simultaneously, it reduces the needed time, short compared to successive drawing. For gesture recognition, accuracy reached 90-95\%. Object recognition and face identification accuracy varied with the variation of light.