scholarly journals Ontology-Driven Toolset for Audio-Visual Stimuli Representation in EEG-Based BCI Research

2021 ◽  
Author(s):  
Konstantin Ryabinin ◽  
Svetlana Chuprina ◽  
Ivan Labutin
Keyword(s):  
Visual Analytics ◽  
Visual Stimuli ◽  
Third Party ◽  
Human Machine Interaction ◽  
Computer Interfaces ◽  
Eeg Data ◽  
Software And Hardware ◽  
High Level ◽  
Hardware Platforms ◽  
Computation Load

In the last decade, the recent advances in software and hardware facilitate the increase of interest in conducting experiments in the field of neurosciences, especially related to human-machine interaction. There are many mature and popular platforms leveraging experiments in this area including systems for representing the stimuli. However, these solutions often lack high-level adaptability to specific conditions, specific experiment setups, and third-party software and hardware, which may be involved in the experimental pipelines. This paper presents an adaptable solution based on ontology engineering that allows creating and tuning the EEG-based brain-computer interfaces. This solution relies on the ontology-driven SciVi visual analytics platform developed earlier. In the present work, we introduce new capabilities of SciVi, which enable organizing the pipeline for neuroscience-related experiments, including the representation of audio-visual stimuli, as well as retrieving, processing, and analyzing the EEG data. The distinctive feature of our approach is utilizing the ontological description of both the neural interface and processing tools used. This increases the semantic power of experiments, simplifies the reuse of pipeline parts between different experiments, and allows automatic distribution of data acquisition, storage, processing, and visualization on different computing nodes in the network to balance the computation load and to allow utilizing various hardware platforms, EEG devices, and stimuli controllers.

scholarly journals Algorithms for Controlling the Hardware and Software Platform for Moving in Virtual Reality

2021 ◽  
Vol 2096 (1) ◽  
pp. 012029
Author(s):  
D Dedov ◽  
V Vostrikova ◽  
E Surkova
Keyword(s):  
Virtual Reality ◽  
Human Movement ◽  
Initial Position ◽  
Machine Building ◽  
Control Algorithms ◽  
Quality Of Movement ◽  
Software And Hardware ◽  
High Level ◽  
Hardware Platforms

Abstract Comprehensive training of specialists in machine-building, chemical and mining industries requires the use of modern means of education. The use of software and hardware platforms based on virtual reality technologies and controlled treadmills allows for a high level of immersion in the learning process and the development of the necessary practical skills. However, the existing control algorithms for treadmills have a number of disadvantages: the effect of lag, low adaptability to human actions. The paper discusses several approaches to organizing the management of a software and hardware platform to improve the quality of movement in virtual reality. Linear and nonlinear algorithms have been developed and have been tested, and the quality of human movement in virtual reality has been made. The nonlinear modified algorithm has allowed to obtain the best results and to reduce the amplitude of oscillations relative to the initial position.

Development of hardware and software system for access control and management

Ergodesign ◽  
2020 ◽  
Vol 2020 (1) ◽  
pp. 19-24
Author(s):  
Igor Pestov ◽  
Polina Shinkareva ◽  
Sofia Kosheleva ◽  
Maxim Burmistrov
Keyword(s):  
Access Control ◽  
High Mobility ◽  
Raspberry Pi ◽  
Software System ◽  
Hardware System ◽  
Software And Hardware ◽  
Arduino Uno ◽  
Control And Management ◽  
Hardware Platforms ◽  
Hardware And Software System

This article aims to develop a hardware-software system for access control and management based on the hardware platforms Arduino Uno and Raspberry Pi. The developed software and hardware system is designed to collect data and store them in the database. The presented complex can be carried and used anywhere, which explains its high mobility.

scholarly journals Virtualizing AI at the Distributed Edge Towards Intelligent IoT Applications

2021 ◽  
Vol 10 (1) ◽  
pp. 13
Author(s):  
Claudia Campolo ◽  
Giacomo Genovese ◽  
Antonio Iera ◽  
Antonella Molinaro
Keyword(s):  
Resource Constraints ◽  
Smart Cities ◽  
Traditional Approach ◽  
Low Cost ◽  
Iot Applications ◽  
Software And Hardware ◽  
Iot Devices ◽  
Consumer Devices ◽  
Hardware Platforms ◽  
Smart Factories

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

scholarly journals A Novel Approach to EEG Speech Activity Detection with Visual Stimuli and Mobile BCI

2021 ◽  
Vol 11 (2) ◽  
pp. 674
Author(s):  
Marianna Koctúrová ◽  
Jozef Juhár
Keyword(s):  
Visual Stimuli ◽  
Computer Interface ◽  
Single Subject ◽  
Detection Accuracy ◽  
The Novel ◽  
Activity Detection ◽  
Speech Activity ◽  
Novel Approach ◽  
Eeg Data ◽  
Speech Activity Detection

With the ever-progressing development in the field of computational and analytical science the last decade has seen a big improvement in the accuracy of electroencephalography (EEG) technology. Studies try to examine possibilities to use high dimensional EEG data as a source for Brain to Computer Interface. Applications of EEG Brain to computer interface vary from emotion recognition, simple computer/device control, speech recognition up to Intelligent Prosthesis. Our research presented in this paper was focused on the study of the problematic speech activity detection using EEG data. The novel approach used in this research involved the use visual stimuli, such as reading and colour naming, and signals of speech activity detectable by EEG technology. Our proposed solution is based on a shallow Feed-Forward Artificial Neural Network with only 100 hidden neurons. Standard features such as signal energy, standard deviation, RMS, skewness, kurtosis were calculated from the original signal from 16 EEG electrodes. The novel approach in the field of Brain to computer interface applications was utilised to calculated additional set of features from the minimum phase signal. Our experimental results demonstrated F1 score of 86.80% and 83.69% speech detection accuracy based on the analysis of EEG signal from single subject and cross-subject models respectively. The importance of these results lies in the novel utilisation of the mobile device to record the nerve signals which can serve as the stepping stone for the transfer of Brain to computer interface technology from technology from a controlled environment to the real-life conditions.

scholarly journals A Review of Algorithms and Hardware Implementations for Spiking Neural Networks

2021 ◽  
Vol 11 (2) ◽  
pp. 23
Author(s):  
Duy-Anh Nguyen ◽  
Xuan-Tu Tran ◽  
Francesca Iacopi
Keyword(s):  
Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Training Algorithms ◽  
Current State ◽  
Hardware Implementations ◽  
Neuromorphic Hardware ◽  
High Level ◽  
Event Based ◽  
Hardware Platforms

Deep Learning (DL) has contributed to the success of many applications in recent years. The applications range from simple ones such as recognizing tiny images or simple speech patterns to ones with a high level of complexity such as playing the game of Go. However, this superior performance comes at a high computational cost, which made porting DL applications to conventional hardware platforms a challenging task. Many approaches have been investigated, and Spiking Neural Network (SNN) is one of the promising candidates. SNN is the third generation of Artificial Neural Networks (ANNs), where each neuron in the network uses discrete spikes to communicate in an event-based manner. SNNs have the potential advantage of achieving better energy efficiency than their ANN counterparts. While generally there will be a loss of accuracy on SNN models, new algorithms have helped to close the accuracy gap. For hardware implementations, SNNs have attracted much attention in the neuromorphic hardware research community. In this work, we review the basic background of SNNs, the current state and challenges of the training algorithms for SNNs and the current implementations of SNNs on various hardware platforms.

scholarly journals Allogeneic chimerism with low-dose irradiation, antigen presensitization, and costimulator blockade in H-2 mismatched mice

Blood ◽  
2001 ◽  
Vol 97 (2) ◽  
pp. 557-564 ◽  
Author(s):  
Peter J. Quesenberry ◽  
Suju Zhong ◽  
Han Wang ◽  
Marc Stewart
Keyword(s):  
Low Dose ◽  
Great Majority ◽  
Cd40 Ligand ◽  
Third Party ◽  
Whole Body ◽  
Spleen Cells ◽  
Graft Versus Host ◽  
Dose Irradiation ◽  
Unique Model ◽  
High Level

Abstract We have previously shown that the keys to high-level nontoxic chimerism in syngeneic models are stem cell toxic, nonmyelotoxic host treatment as provided by 100-cGy whole-body irradiation and relatively high levels of marrow stem cells. This approach was unsuccessful in H-2 mismatched B6.SJL to BALB/c marrow transplants, but with tolerization, stable multilineage chimerism was obtained. Ten million B6.SJL spleen cells were infused intravenously into BALB/c hosts on day −10 and (MR-1) anti-CD40 ligand monoclonal antibody (mAb) injected intraperitoneally at varying levels on days −10, −7, −3, 0, and +3 and the BALB/c mice irradiated (100 cGy) and infused with 40 million B6.SJL/H-2 mismatched marrow cells on day 0. Stable multilineage chimerism at levels between 30% to 40% was achieved in the great majority of mice at 1.6 mg anti-CD40 ligand mAb per injection out to 64 weeks after transplantation, without graft-versus-host disease. The transplanted mice were also tolerant of donor B6.SJL, but not third-party CBA/J skin grafts at 8 to 9 and 39 to 43 weeks after marrow transplantation. These data provide a unique model for obtaining stable partial chimerism in H-2 mismatched mice, which can be applied to various clinical diseases of man such as sickle cell anemia, thalassemia, and autoimmune disorders.

Virtual reality in Education. Broken promises or new hope?

2021 ◽  
Author(s):  
B. L. McGee ◽  
Lisa Jacka
Keyword(s):  
Virtual Reality ◽  
Learning Environments ◽  
Evidence Based ◽  
Research Needs ◽  
Business Environments ◽  
Global Pandemic ◽  
Technology Changes ◽  
Software And Hardware ◽  
High Level ◽  
K 12

Virtual reality in one form or another has been around for over 50 years, most notably in entertainment and business environments. Technology-focused teachers have been leading the way with attempts at utilising and integrating virtual reality into K-12 and Higher Education. However, as quickly as technology changes so does the enthusiasm for the use in educational contexts. Much of this is due to the high-level cost (time and money) with no evidence-based educational return. In 2020 the global pandemic forced the education sector to innovate to provide authentic learning environments for students. The time is right for virtual reality to take centre stage. Over 171 million people worldwide currently use virtual reality, and the market in education is expected to grow by 42% over the next five years. This paper focuses on a range of virtual reality literature encompassing work across the spectrum of software and hardware, identifying where more educational implementation and research needs to be done and providing a perspective on future possibilities focusing on current affordances.

scholarly journals SCREENING OF ENVIRONMENTAL IMPACT OF POLLUTION WITH THE QGIS PLUGIN ENVIFATE

2017 ◽  
Vol XLII-4/W2 ◽  
pp. 79-83 ◽  
Author(s):  
F. Geri ◽  
O. Cainelli ◽  
G. Salogni ◽  
P. Zatelli ◽  
M. Ciolli
Keyword(s):  
Environmental Pollution ◽  
Atmospheric Dispersion ◽  
Third Party ◽  
Environmental Research ◽  
Future Research ◽  
Toxic Substances ◽  
Command Line ◽  
Screening Analysis ◽  
High Level ◽  
The University

Public and academic interest in environmental pollution caused by toxic substances and other sources, like noise, is constantly raising. To protect public health and ecosystems it is necessary to maintain the concentrations of pollutants below a safety threshold. In this context the development of models able to assess environmental pollution impact has been identified as a priority for future research. Scientific community has therefore produced many predictive models in the field. The vast majority of them needs to be run by specialists with a deep technical knowledge of the modeled phenomena in order to process the data and understand the results and it is not feasible to use this models for simple prescreening activities. Planners, evaluators and technical operators need reliable, usable and simple tools in order to carry out screening analysis of impact assessment. <br><br> The ENVIFATE software is currently under development by the Department of Civil, environmental and mechanical engineering of the University of Trento, Italy, in the frame of a project funded by the Italian Veneto Region with the aim to make available to nonspecialists screening analysis to assess the risks of a set of possible environmental pollution sources in protected areas. <br><br> The development of ENVIFATE follows these basic requirements: i) Open-Source ii) multiplatform iii) user friendly iv) GIS oriented. In order to respect these principles we have chosen to develop a plugin of QGIS, using python as a development language and creating a module for each environmental compartment analyzed: rivers, lakes, atmospheric dispersion, dispersion in groundwater and noise. <br><br> The plugin architecture is composed of a series of core functions characterized by command line interfaces that can be called from third-party applications (such as Grass GIS), connectable in custom data flows and with a high level of modularity and scalability. The base of the different models are highly tested and reliable algorithms adopted by the Italian Institute for Protection and Environmental Research (Istituto Superiore per la Protezione e la Ricerca Ambientale – ISPRA). Due to their simplicity, and for safety reasons, the structure of these models is constrained to provide conservative results, so to overestimate actual risk. This approach allows to provide statistically validated instruments to be used in different environmental contexts. All modules of the plugin provide numerical and cartographical results: in particular the command-line interface provides "static" results, or linked to a particular spatial and temporal state, while the Qgis plugins iterate the single analysis along space and time in order to provide georeferenced maps and time distributed results.

Sign in / Sign up

Export Citation Format

Share Document