If users focus on such visual stimuli for a significant period, they feel fatigued or suffer from sore eyes (Puanhvuan and Wongsawat, 2012; Chai et al., 2014). Therefore, such physiological control signals are neither suitable nor effective for wheelchair operation. Despite the advantages of using navigation systems that assist the control of the wheelchair with shared control, limited findings have been reported. However, it is worth noting that several cases, for instance, wheelchair operation in a corridor or a free area with unfamiliar impediments, need to be addressed.
An adaptive Stacked Denoising Auto Encoder (SDAE) was developed in Attia et al. (2018) to tackle cross-session MW classification from EEG, and it was reported that the proposed classifier achieved an accuracy of 95.5%. Although most of the artifact removal algorithms offer good performance, the methods listed in section EEG Data Pre-processing Strategies suffer from different limitations when utilized in a particular EEG-based application. Indeed, some methods are only focused on the detection and removal of particular artifacts. Some methods need reference channels to enhance the accuracy of artifact removal, which is not feasible for some specific applications. ICA-based algorithms can deal with all kinds of artifacts occurring in EEG recordings. Regression and adaptive filters are more feasible choices when the reference channels for specific artifacts are available.
Are you fascinated by the inner workings of the human brain and curious about how EEG machines operate? Many tech enthusiasts and DIY enthusiasts have pondered the idea of constructing their own Electroencephalogram (EEG) machine. The question that arises is, how feasible would it be to build my own EEG from scratch?
A low pass filter is good at doing this because, as far as signals go, your heartbeat is pretty slow. Our goal with the low-pass filter is to eliminate all signals that contain frequencies higher than your ECG. In our case, everything above this frequency we want to eliminate, and everything below this frequency we want to keep.
The Complexity of EEG Machines
Once the desired icon is reached, a peak is observed in the neural signals of the user. The system was tested using four participants, and the accuracy rate observed varied from 33 to 100% among different users. Kim et al. (2013) also suggested a non-invasive P300 stimulus-based BCI system to switch TV channels from a viewing distance of 3 meters and a 46-inch TV screen.
The pure CSP approach sometimes cannot achieve sufficient performance due to the subject-specific optimal frequency band. Hence, the choice of an optimized filter band may enhance performance, but the selection of the optimal sub-band through pure CSP takes a large amount of time. To overcome this issue, numerous changes have been applied to the CSP. The common spatio-spectral pattern approach (CSSP) combines an FIR filter with a CSP algorithm and was observed to improve performance relative to pure CSP (Reddy et al., 2019). Common sparse spatio-spectral patterns (CSSSP) (Dornhege et al., 2006) are a comparatively more advanced procedure where the common spectral patterns across channels are investigated.
EEG machines are highly complex devices that require precise calibration and intricate circuitry to accurately measure and record brain activity. These machines detect electrical signals generated by neurons in the brain through electrodes placed on the scalp. Replicating this level of accuracy and sensitivity in a DIY project can be quite challenging, especially for those without a background in neuroscience or engineering.
Crimp the ground wire around the cable jacket, then slide the plug cover over the plug and screw it tight. Skin irritation or redness may be present at the locations where the electrodes were placed, but this will wear off in a few hours. Ask your healthcare provider to tell you what you should do before your test.
Challenges of Building an EEG
One of the main challenges of building your own EEG is sourcing high-quality components that are capable of capturing and amplifying weak electrical signals produced by the brain. Additionally, ensuring proper electrode placement and signal processing is crucial for obtaining reliable data. Without access to specialized equipment and expertise, achieving the same level of precision as commercially available EEG machines may be difficult.
DIY EEG Projects
Despite the challenges, there are enthusiasts and researchers who have successfully created their own EEG machines using open-source hardware and software. These projects often involve using microcontrollers, amplifiers, and custom-built electrodes to capture brainwave data. While these projects may not match the accuracy and reliability of professional EEG machines, they offer valuable learning experiences and insights into the field of neurotechnology.
Conclusion
In conclusion, building your own EEG machine is a complex and challenging endeavor that requires specialized knowledge and resources. While it may be feasible for individuals with a background in engineering or neuroscience, most DIY enthusiasts may find it more practical to explore other avenues for studying brain activity. However, for those willing to take on the challenge, the process of building an EEG can be a rewarding and educational journey into the fascinating world of neurotechnology.
