Object Selection Using LSTM Networks for Spontaneous Gaze-Based Interaction

Two years on with Covid-19, touchless technology has evolved from a device that symbolizes luxury to something that is necessary. Eye tracker is one type of touchless technologies that uses user's gaze to interact with computer without touching the screen. Development of spontaneous gazebased interaction is progressing very rapidly. Researchers have developed various object selection methods without prior gazeto-screen calibration. Recently, the conventional approach of setting threshold was developed as a gaze-based object selection method. However, the use of threshold values is considered non-adaptive and requires additional data pre-processing to handle noises. To overcome this problem, deep learning is used as an object selection method for spontaneous gaze-based interaction. Deep learning does not require any data preprocessing method to achieve accurate object selection results. Out of five deep learning algorithms that were evaluated, LSTM (Long Short-Term Memory) and BiLSTM (Bidirectional Long Short-Term Memory) networks achieved comparable accuracy of 95.17 pm 0.95% and 95.15 pm 1.17%, respectively. In future, our research is promising for development of real-time object selection technique for touchless public display. © 2022 IEEE.

Spontaneous gaze interaction based on smooth pursuit eye movement using difference gaze pattern method

Human gaze is a promising input modality for being able to be used as natural user interface in touchless technology during Covid-19 pandemic. Spontaneous gaze interaction is required to allow participants to directly interact with an application without any prior eye tracking calibration. Smooth pursuit eye movement is commonly used in this kind of spontaneous gaze-based interaction. Many studies have been focused on various object selection techniques in smooth pursuit-based gaze interaction;however, challenges in spatial accuracy and implementation complexity have not been resolved yet. To address these problems, we then proposed an approach using difference patterns between gaze and dynamic objects' trajectories for object selection named Difference Gaze Pattern method (DGP). Based on the experimental results, our proposed method yielded the best object selection accuracy of 80.86±9.57% and success time of 5,885±1,097 ms. The experimental results also showed the robustness of object selection using difference patterns to spatial accuracy and it was relatively simpler to be implemented. The results also suggested that our proposed method can contribute to spontaneous gaze interaction. © 2022 KIPMI.

Spontaneous Gaze-Based Application Using 2D Correlation and Velocity Threshold Identification

Demand for touchless technology has grown with the surge of Covid-19 pandemic. Spontaneous gaze-based application is one of several promising technologies for touchless interaction. Despite of this potential, little attention has been paid to the performance of traditional eye movements classification methods on improving accuracy of gaze-based object selection. To handle this research gap, we proposed a novel workflow of spontaneous gaze-based object selection using 2D Correlation as similarity measure and Velocity Threshold Identification (I-VT) as a method for eye movements classification. We compared our method with Pearson Product-Moment Correlation (PPMC) as similarity measure and Dispersion Threshold Identification (I-DT) for eye movements classification. Our experimental results showed that the proposed method yielded object selection accuracy up to 95:62%+/-3:48%. In future, our proposed method can be implemented in the development of touchless interactive technologies that adhere to the World Health Organization guidelines, especially during the Covid-19 pandemic.

The Study of Multivariable Autoregression Methods to Forecast Infectious Diseases

Infectious diseases can have an enormous impact on the public because they negatively affect not only mortality but also unemployment and other social impacts. It is crucial to anticipate additional resources to counter infectious diseases mathematical and statistical tools that can be used to generate forecasts of reported cases. In this paper, the multivariable autoregression methods were compared for forecasting infectious diseases. We discuss the methods and use them to forecast infectious diseases. In this case, we used several COVID-19 cases as the object of forecasting. We used three prediction methods as Vector Autoregression (VAR), Vector Autoregression Moving Average (VARMA), and Autoregression Moving Average with exogenous variable (VARMA-X). The results show that the models have different results, among three methods, VAR give the best result of forecasting daily covid case for both stationary and non-stationary data. While VARMA-X shows the lowest performance for forecasting the dataset. We suggest by combining the AR model with the ANN model can provide a better result for forecasting. © 2021 IEEE.

Gaze-Controlled Digital Signage for Public Health Education during Covid-19 Pandemic

For more than a decade, digital signages have been used in health facilities and public environment to provide fun and interactive approach of education. Unfortunately, interacting with conventional digital signage during Covid-19 pandemic raises a concern on its hygiene. Thus, touchless interaction is preferable to avoid direct contact on the touch screen. Here we present a novel study on effectiveness of gaze-based interaction in a digital signage for public health education. Instead of touching the screen, the users engage with the content by gazing at a dynamic button that moves in horizontal or vertical direction. Experimental results show that gazing at faster dynamic buttons (angular speed of 60.28°/s) than its slower counterpart (angular speed of 30.14°/s) requires shorter time to complete a three-steps task (T = 84, Z =-1.977, p < 0.05). Our study provides a scientific proof of concept for further development of touchless digital signage that complies with health protocols of the World Health Organization during Covid-19 pandemic. © 2021 IEEE.