2011 international joint conference on neural networks (ijcnn)

https://doi.org/10.1016/j.chb.2022.107289

What is XR? Towards a Framework for Augmented and Virtual Reality

During the years common understanding of the possibilities and perspectives of Virtual Reality (VR) usage has been changed. It is thought that VR is mainly used in entertainment purposes, but it is being used already for many years in different industries, and now with easier access to the hardware it became a helpful and accessible tool that could be used and developed in any field of human activities. In manufacturing, immersive technologies are mainly used nowadays for the visualisation of processes and products combining those visuals into \nthe factory Digital Twin (DT) which is possible to view from the inside look. This feature is already being used in several manufacturing simulation tools, which enable to view onto industrial line / robotic cells via Virtual Reality glasses. However, the potential of using simulations with VR in manufacturing is not fully uncovered. The main aim of this, industrial robotics targeted research is to enable besides simulation also universal control algorithms through Virtual Reality experience, produced by game engine Unity3D, which can be easily modified for a wide range of industrial equipment. The primary outcome of this work is the development of the synchro-nisation model of real and virtual industrial robots and experimental testing the developed model in Virtual Reality and shop floor labs\n\n

/pdf/digital-twin-based-synchronised-control-and-simulation-of-msb4h2rztx.pdf

Digital Twin based synchronised control and simulation of the industrial robotic cell using Virtual Reality

Adaptive Signal Processing: Next Generation Solutions

THE ORIGINAL Amazon Echo speaker/personal assistant has been one of the more successful consumer electronics products of the past year. Having shipped three million according to analyst Consumer Intelligence Research Partners, Amazon is looking to extend the range in form factor, portability and price. Two variations have just launched in the US. The Amazon Tap, the subject of this teardown, is a smaller, battery-powered Echo. The Amazon Echo Dot is a hockey-puck-sized and mainspowered version. The Tap costs $150 (£103 pre-VAT) and the Dot is $90. Echo continues to retail at $180. The company says that it will roll out the new products in the UK and the rest of the world during 2016.

The teardown - Amazon tap portable speaker and assistant [Reviews Consumer Technology]

In this paper, we present our findings related to the problem of localization and visualization of a sound source placed in the same room as the listener. The particular effect that we aim to investigate is called synesthesia—the act of experiencing one sense modality as another, e.g., a person may vividly experience flashes of colors when listening to a series of sounds. Towards that end, we apply a series of recently developed methods for detecting sound source in a three-dimensional space around the listener.We also apply a Kalman filter to smooth out the perceived motion. Further, we transform the audio signal into a series of visual shapes, such that the size of each shape is determined by the loudness of the sound source, and its color is determined by the dominant spectral component of the sound. The developed prototype is verified in real time. The prototype configuration is described and some initial experimental results are reported and discussed. Some ideas for further development are also presented.

/pdf/towards-a-synesthesia-laboratory-real-time-localization-and-4u8h2ff97k.pdf

Towards a Synesthesia Laboratory: Real-time Localization and Visualization of a Sound Source for Virtual Reality Applications

This paper presents the process for a case study concerning fully immersive application of physical environment. The paper considers intelligent systems integration to VR and self-learning activities with sociological aspects by significant experimental platform. Authors aim to detail the process of systematical design including modelling, computing, intelligence and an initial evolution of virtual environment. Also practical usage and futuristic aspects are included for the concept. As the project based on physical environment, target of the work is concentrated to give high presence feeling for end-users. To increasing presence feeling, authors aim to maximize immersion level. Self-learning activities based on the perception of supervised and unsupervised learning. The activities are engaged to immersive and entertaining structure. Heterogeneous intercontinental participants provide unique feedback source. The environment is research and development center of Tallinn University of Technology. The virtual environment of the center has been evaluated based on realistic conditions.

Virtual Reality Meets Intelligence in Large Scale Architecture

A DFT investigation of hydrogen adsorption and storage properties of Mg decorated IRMOF-16 structure

This paper addresses the identification and implementation of the Ground Source Heat Pump (GSHP) Model. It presents a comparison of different models, including neural network (NN) based models. The system was installed and is located at Tallinn University of Technology. It includes borehole heat exchangers, a heat pump and heat distribution part, which are set up in the same plant. Although experimental data at different depth levels were measured and stored for a year, there was no application to determine the identification of the system. In general, the aim of this paper is to identify a system to predict the behaviour of ground source heat pump models. Several models were applied to identify the system. After applying those models, they were compared. The model with the best performance is the Hammerstein-Wiener model. The selection criteria were the best fit, parameter estimation, validation of the model and structure of dynamic models. Models based on neural networks based on models were applied to the ground source heat pump and compared with the Hammerstein-Wiener model. Overall, the main implementation is an identified model of GSHP short helical heat exchanger to analyze the ground temperature field and to help to better predict the amount of heat energy from the ground. The measured output and simulated output were compared, and an error calculated. The temperature record of each hour is one cell of data set and arrays of 5634 data set are used to implement the system. Also arrays of 4000 data cells are used from total data for model validation. The proposed identification and analysis may be useful in developing ground source heat pump systems.

System identification models and using neural networks for Ground Source Heat Pump with Ground Temperature Modeling

Virtual Reality (VR) is considered to be a powerful modern medium for immersive data visualization and exploration. However, few studies have proposed solutions to complement data visualization in immersive environment considering the user's behavior. This paper addresses dynamic modeling of user behavior approach in an interactive VR based application. In this application, real-time data communication is employed to track accurate location and orientation of head mounted display device worn by the user. In our experiment, we use example of collected data and provide a methodology to predict next movements of the user by using nonlinear autoregressive (NAR) and location in the application by the nonlinear autoregressive neural network with exogenous inputs (NARX). Results suggest both neural networks are suitable for performing prediction which can be used to achieve an improved feeling of presence while reducing required high computational power. Data analysis part of the research is also linked to human behaviors to improve studies which are usually performed by traditional survey techniques.

Ahmet Kose

Papers

Towards a Synesthesia Laboratory: Real-time Localization and Visualization of a Sound Source for Virtual Reality Applications

Virtual Reality Meets Intelligence in Large Scale Architecture

A DFT investigation of hydrogen adsorption and storage properties of Mg decorated IRMOF-16 structure

System identification models and using neural networks for Ground Source Heat Pump with Ground Temperature Modeling

Dynamic Predictive Modeling Approach of User Behavior in Virtual Reality based Application