Implementation of a Brain-Computer Interface for Robotic Arm Control

Abougarair, Ahmed J.; Gnan, Hanadi M.; Oun, Abdulhamid; Elwarshfani, Saadedin O.

doi:10.1109/mi-sta52233.2021.9464359

Cited by 20 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There has been almost three decades of research involving BCI systems and motor imagery [49,50] -and their implementation with consumer-grade EEG is growing. By training an algorithm to detect specific EEG patterns reflecting imagined motor functions, users can operate artificial limbs [33,[51][52][53][54][55] and wheelchairs [56][57][58][59][60][61]. Motor imagery with consumer-grade EEG has also been used to control electric vehicles [62] and aerial drones [8,63,64].…”

Section: Brain-computer Interfacesmentioning

confidence: 99%

A scoping review on the use of consumer-grade EEG devices for research

Sabio

Williams

McArthur

et al. 2022

Preprint

View full text Add to dashboard Cite

BACKGROUND: Commercial electroencephalography (EEG) devices have become increasingly available over the last decade. These devices have been used in a wide variety of fields ranging from engineering to cognitive neuroscience. PURPOSE: The aim of this study was to chart peer-review articles that used currently available consumer-grade EEG devices to collect neural data. We provide an overview of the research conducted with these relatively more affordable and user-friendly devices. We also inform future research by exploring the current and potential scope of consumer-grade EEG. METHODS: We followed a five-stage methodological framework for a scoping review that included a systematic search using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. We searched the following electronic databases: PsycINFO, MEDLINE, Embase, Web of Science, and IEEE Xplore. We charted study data according to application (BCI, experimental research, validation, signal processing, and clinical) and location of use as indexed by the first author's country. RESULTS: We identified 916 studies that used data recorded with consumer-grade EEG: 531 were reported in journal articles and 385 in conference papers. Emotiv devices were most used, followed by the NeuroSky MindWave, OpenBCI, interaXon Muse, and MyndPlay Mindband. The most common use was for brain-computer interfaces, followed by experimental research, signal processing, validation, and clinical purposes. CONCLUSIONS: Consumer-grade EEG has proven to be a useful tool for neuroscientific research and will likely continue to be used well into the future. Our study provides a comprehensive review of their application, as well as future directions for researchers who wish to use these devices.

show abstract

Section: Brain-computer Interfacesmentioning

confidence: 99%

A scoping review on the use of consumer-grade EEG devices for research

Sabio

Williams

McArthur

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Some of the classes feature a lot of images, while others don't. [16][17][18] Figure 2 Sample images from dataset. 19,20…”

Section: Data Overviewmentioning

confidence: 99%

“…One of the main hyper-parameters that impacts the model's accuracy is the learning rate. [13][14][15][16][17] A full pass of the dataset is defined as an epoch. Epochs can have a significant impact on accuracy.…”

Section: Parametr Tunningmentioning

confidence: 99%

Real time traffic sign detection and recognition for autonomous vehicle

Abougarair¹,

Elmaryul²,

Aburakhis³

2022

IRATJ

View full text Add to dashboard Cite

The advancement of technology has made it possible for modern cars to utilize an increasing number of processing systems. Many methods have been developed recently to detect traffic signs using image processing algorithms. This study deals with an experiment to build a CNN model which can classify traffic signs in real-time effectively using OpenCV. The experimentation method involves building a CNN model based on a modified LeNet architecture with four convolutional layers, two max-pooling layers and two dense layers. The model is trained and tested with the German Traffic Sign Recognition Benchmark (GTSRB) dataset. Parameter tuning with different combinations of learning rate and epochs is done to improve the model’s performance. Later, this model is used to classify the images introduced to the camera in real- time. The graphs depicting the accuracy and loss of the model before and after parameter tuning are presented. Also, an experiment was performed to classify the traffic sign image introduced to the camera by using the CNN model. A high probability score is achieved during the process.

show abstract

“…There are several non-AI alternatives available, but the Google "gtts" AI-based solution was the best choice because it does not require an account or a large library to be loaded on the machine. 15,16 Figure 5 & 6 shows the steps for converting text to speech using AI. Table 1 present the comparison between STT solutions.…”

Section: Preparation Proceduresmentioning

confidence: 99%

Design and implementation of smart voice assistant and recognizing academic words

Abougarair¹,

Aburakhis²,

Zaroug³

2022

IRATJ

View full text Add to dashboard Cite

This paper approaches the use of a Virtual Assistant using neural networks for recognition of commonly used words. The main purpose is to facilitate the users’ daily lives by sensing the voice and interpreting it into action. Alice, which is the name of the assistant, is implemented based on four main techniques: Hot word detection, Voice to Text conversion, Intent recognition, and Text to Voice conversion. Linux is the operating system of choice, for developing and running the assistant because it is in the public domain, also, Linux has been implemented on most Single-board computers. Python is chosen as a development language due to its capabilities and compatibility with various APIs and libraries, which are deemed necessary for the project. The virtual assistant will be required to communicate with IoT devices. In addition, a speech recognition system is created in order to recognize the significant technical words. An artificial neural network (ANN) with different structure networks and training algorithms is utilized in conjunction with the Mel Frequency Cepstral Coefficient (MFCC) feature extraction technique to increase the identification rate effectively and find the optimal performance. For training purposes, the Levenberg-Marquardt (LM) and BGFS Quasi-Newton Resilient Backpropagation are compared using 10 MFCC, utilizing from 10 to 50 neurons increasing in increments of 10 similarly for 13MFCC the training is done utilizing from between 10 to 50 neurons.

show abstract

Implementation of a Brain-Computer Interface for Robotic Arm Control

Cited by 20 publications

References 7 publications

A scoping review on the use of consumer-grade EEG devices for research

A scoping review on the use of consumer-grade EEG devices for research

Real time traffic sign detection and recognition for autonomous vehicle

Design and implementation of smart voice assistant and recognizing academic words

Contact Info

Product

Resources

About