In this paper, the development of an eye-tracking-based human–computer interface for real-time applications is presented. To identify the most appropriate pupil detection algorithm for the proposed interface, we analyzed the performance of eight algorithms, six of which we developed based on the most representative pupil center detection techniques. The accuracy of each algorithm was evaluated for different eye images from four representative databases and for video eye images using a new testing protocol for a scene image. For all video recordings, we determined the detection rate within a circular target 50-pixel area placed in different positions in the scene image, cursor controllability and stability on the user screen, and running time. The experimental results for a set of 30 subjects show a detection rate over 84% at 50 pixels for all proposed algorithms, and the best result (91.39%) was obtained with the circular Hough transform approach. Finally, this algorithm was implemented in the proposed interface to develop an eye typing application based on a virtual keyboard. The mean typing speed of the subjects who tested the system was higher than 20 characters per minute.

In this paper, a new drivers’ warning application through personalized Direct-Sequence Spread Spectrum Code-Division Multiple Access (DSSS-CDMA) transmissions, performed using the FM radio broadcasting infrastructure is presented. The proposed application is designed to simultaneously transmit a maximum of 15 low-resolution image notifications together with standard FM radio broadcasting in different geographical areas. The application is intended to warn drivers of significant driving events in major traffic areas of a country. The proposed solution is low-cost and rapid to put into practice because the modifications, both on the transmission infrastructure and on the receiver’s side, are relatively easy to implement. The transmission of image notifications is performed in subsidiary bands of commercial FM radio systems. The receiver is implemented using the Software-Defined Radio (SDR) paradigm and is able to extract the audio signal (corresponding to the usual FM transmission) and the data component, depending on the geographical area in which the vehicle is located. The receiver is based on a novel implementation of a modified Costas loop using two new nonlinear limiters. Appropriate image notification is selected using a specific decoding key, generated according to the geographical position of the vehicle. The performance of the data transmission system is analyzed by plotting the Bit Error Rate (BER) versus the signal-to-noise ratio for different numbers of image notifications simultaneously transmitted. The proposed radio communication system was validated through an experimental setup based on Universal Software Radio Peripheral (USRP) devices driven by MATLAB/Simulink software.

In this paper, we present a new complex electronic system for facilitating communication with severely disabled patients and telemonitoring their physiological parameters. The proposed assistive system includes three subsystems (Patient, Server, and Caretaker) connected to each other via the Internet. The two-way communication function is based on keywords technology using a WEB application implemented at the server level, and the application is accessed remotely from the patient’s laptop/tablet PC. The patient’s needs can be detected by using different switch-type sensors that are adapted to the patient’s physical condition or by using eye-tracking interfaces. The telemonitoring function is based on a wearable wireless sensor network, organized around the Internet of Things concept, and the sensors acquire different physiological parameters of the patients according to their needs. The mobile Caretaker device is represented by a Smartphone, which uses an Android application for communicating with patients and performing real-time monitoring of their physiological parameters. The prototype of the proposed assistive system was tested in “Dr. C.I. Parhon” Clinical Hospital of Iaşi, Romania, on hospitalized patients from the Clinic of Geriatrics and Gerontology. The system contributes to an increase in the level of care and treatment for disabled patients, and this ultimately lowers costs in the healthcare system.

In this paper, the implementation of a new pupil detection system based on artificial intelligence techniques suitable for real-time and real-word applications is presented. The proposed AI-based pupil detection system uses a classifier implemented with slim-type neural networks, with its classes being defined according to the possible positions of the pupil within the eye image. In order to reduce the complexity of the neural network, a new parallel architecture is used in which two independent classifiers deliver the pupil center coordinates. The training, testing, and validation of the proposed system were performed using almost 40,000 eye images with a resolution of 320 × 240 pixels and coming from 20 different databases, with a high degree of generality. The experimental results show a detection rate of 96.29% at five pixels with a standard deviation of 3.38 pixels for all eye images from all databases and a processing speed of 100 frames/s. These results indicate both high accuracy and high processing speed, and they allow us to use the proposed solution for different real-time applications in variable and non-uniform lighting conditions, in fields such as assistive technology to communicate with neuromotor-disabled patients by using eye typing, in computer gaming, and in the automotive industry for increasing traffic safety by monitoring the driver’s cognitive state.

In this paper a new application for transmitting image notifications on the FM radio broadcasting infrastructure, dedicated to warn drivers about significant road events and to increase the traffic safety is presented. The paper analyses different technical solutions suitable for transmitting and receiving real-time image notifications in different scenarios by using the software-defined radio concept. In the first scenario, the image notifications are QPSK modulated and transmitted with 8 kb/s bit-rate by using the mono FM radio channel. In order to increase the speed of data transmission, the second scenario uses the FM subcarrier channels dedicated for broadcasting alternate services. In this case, the speed of data transmission was 40 kb/s, 60 kb/s and 80 kb/s for QPSK, 8-PSK and 16-PSK modulations, respectively. A new software solution to perform the real-time carrier synchronization for 8-PSK/16-PSK modulation based on a decision-directed PLL and non-linear decision block is also presented. The functionality of the proposed application was demonstrated by simulations for both transmission scenarios. Moreover, the first scenario was tested experimentally by using a professional FM transmitter and a simple RTL-SDR dongle at the reception. The customized baseband modulating signal including audio, data (image notification) and RDS signals was generated by using a device built by the authors. The receiver provides the digital signal through a USB interface to a software program, running on a processing unit, for demodulation. An experimental method for plotting BER vs. Eb/N0 ratio, based on signal-to-noise ratio measured with a software spectrum analyzer has been proposed also. This method allows the characterization of the experimental setup and give hints about the QPSK signal power level compared to the other ones (audio and RDS signals).

This paper presents a new software-defined vehicular radio communication system based on DS-CDMA technology using orthogonal Walsh-Hadamard codes. The proposed radio communication system can simultaneously receive an audio stereo signal and a data signal with DS-CDMA modulation within a standard FM radio broadcasting (87.5 – 108 MHz). This study also investigates the transmission/reception of the same data signal with frequency modulation in different ISM radio bands. The data transmission rate is significantly increased to 32 kbit/s using DS-CDMA technology, in which the input data signal is divided into 16 parallel sequences that are spread with orthogonal Walsh-Hadamard sequences, which reduces multi-access interference, jamming and their contribution to the system self-noise. To perform symbol synchronization at reception, the Walsh-Hadamard codes of length 16 were reshaped by adding synchronization pulses at the transmitter and, respectively, corresponding to padding zeros at the receiver. The paper presents a new software-defined radio receiver capable to receive at the same time the data signal with DS-CDMA modulation, as well as the audio stereo signal. The proposed radio receiver includes a carrier synchronization loop operating at the baseband and a novel symbol timing synchronization loop based on synchronization pulses. The proposed radio communication system was implemented in MATLAB/Simulink and simulated under the conditions of channel impairments, considering the carrier frequency offset and timing offset on an AWGN, Rayleigh and Rician communication channel. To validate the simulation results, the bit error rate depending on the signal-to-noise ratio of the received signal was plotted for the different communication channel models. The experimental results were obtained under laboratory conditions using USRP-type devices.