Standard: The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) is a set of guidelines designed to improve the transparency and quality of reporting in systematic reviews and meta-analyses. PRISMA aims to help authors ensure that their review is reported in a clear, complete, and transparent manner, facilitating the critical appraisal and replication of these studies.
Refrence of update in PRISMA: The PRISMA 2020 statement_ An updated guideline for reporting.pdf
817.8 kB
Purpose of PRISMA:
Transparency: To increase the transparency of the reporting process, making it easier for readers to assess the reliability and validity of the research. Standardization: To standardize the structure of systematic reviews and meta-analyses, making it easier to compare and synthesize different studies. Quality Improvement: To improve the quality of systematic reviews and meta-analyses, which are fundamental to evidence-based practice in healthcare and other disciplines.
Key Components of PRISMA:
This includes a 27-item checklist and a four-phase flow diagram. The checklist items focus on various sections of a systematic review report, including the title, abstract, methods, results, discussion, and funding. Each section has specific criteria that need to be met to ensure comprehensive reporting. The PRISMA flow diagram visually represents the flow of information through the different phases of a systematic review. It maps out the number of records identified, included and excluded, and the reasons for exclusions. This helps in understanding the selection process. PRISMA guidelines emphasize rigorous methodology, including pre-defined objectives and eligibility criteria, an explicit, reproducible methodology, a systematic search that attempts to identify all studies, an assessment of the validity of the findings of the included studies (often through the assessment of risk of bias), and systematic presentation, and synthesis of the characteristics and findings of the included studies.
+++ real-time and non real-time BRI and BCV and Used DL/ML which technology
Publisheres:
ScienceDirect (Elsiever) -
Keywords
First route - BCI, robot, EEG, prediction, intention | BCI, EEG, prediction, intention
(BCI robot EEG prediction intention) / () Second route - BCI, robot, EGG, prediction, intention, driving | BCI, EGG, prediction, intention, driving
First Route - A:
BCI, robot, EEG, prediction, intention
First Route - B:
BCI, EEG, prediction, intention
First Route - A:
BCI, robot, EGG, prediction, intention, driving
First Route - B:
BCI, EGG, prediction, intention, driving
Title: A Decade-Long Review of Intention Prediction via EEG in Robotics and Driving Applications: Analyzing AI/Deep Learning Successes, Limitations, and Research Gaps
Keywords:
First route - BCI, robot, EEG, prediction, intention | BCI, EEG, prediction, intention Second route - BCI, robot, EGG, prediction, intention, driving | BCI, EGG, prediction, intention, driving Abstract:
Introduction:
Rationale: Intention prediction through EEG data has significant potential in the field of robotics and driving, especially when combined with AI, deep learning, and machine learning models. This review aims to consolidate findings over the past decade to understand the effectiveness of these computational models in predicting human intentions through EEG signals. The rationale stems from the need to address safety and efficiency in autonomous systems, specifically focusing on how deep learning models can interpret EEG data for practical applications such as human-robot collaboration and driver intention recognition. Understanding past achievements, limitations, and gaps in research will pave the way for future development in the field. To assess the effectiveness and limitations of existing AI, deep learning, and machine learning models in predicting human intention from EEG data in the fields of robotics and driving. To identify key successes in the practical application of these models in enhancing robotic and vehicular functions. To explore research gaps and opportunities that future work should address for improved intention prediction through EEG. Questions answered by review: What have been the most effective machine learning, deep learning, and AI models used in EEG-based intention prediction in the last decade? How have these models been successfully applied to intention prediction in robotics and driving contexts? What are the current limitations of these predictive models in handling EEG data for intention prediction? What are the emerging research gaps and challenges in developing more accurate and reliable intention prediction models? How do current models compare in terms of computational efficiency, prediction accuracy, and robustness across different intention prediction tasks?
Yep. But it can be, you know, not a robot but brain computer interface for controlling different types of machines that don't necessarily need to be robots. They may be very simple devices. So it's potentially interesting to have a look there. Brain computer interfaces for control. You could just look for autonomous driving. I think you might also get the driver assistance as well. I think there'll be a lot of stuff where people are not targets. maybe not autonomous driving, maybe just driving the keyword of brain computer interfaces So it's good to build up a list? I think some of those, normally, I see something I send it to you, I think for autonomous driving in a systematic review, I think it's gonna be have a look, I think it's gonna be a very small number of papers. But have a look. I think we might need to widen a little bit to just bring computer interfaces or eg for driving tasks or for driver assistance or something like that. 
Systematic Review
