Figure 1 - available via license: CC BY-NC-ND
Content may be subject to copyright.
Three typical EEG patterns of A, B and E.
Source publication
Wide-scale information embedding is prerequisite to enhance the performance as well as the reliability of decision making algorithms
for viable implementation. Feature fusion technology significantly helps incorporating such information to provide promising algorithm
performance. In this article, a fusion based model with the aid of Discriminant co...
Context in source publication
Context 1
... Data set: A well-known publically available data set is used in this analysis [37]. The dataset consists of five sets-A to E. Each set contains 100 single channel recordings segmented from multi- channel recordings. Duration of each recording is 23.6 s. The data sets were recorded at the University Hospital Bonn, Germany with inbuilt amplifier and 12-ADC at a sampling rate of 173.61Hz. The signals were filtered with a band of 0-60 Hz. The number of samples in each recording was 4097 (=sampling rate × time). During data collection, the healthy volunteers were relaxed in an awake state with eyes open (A) and eyes closed (B). Sets C, D and E are originated from our EEG archive of pre-surgical diagnosis. Sets C and D were measured during the seizure free interval while set E contained seizure activity. In this study, we consider two data sets A and B of eye open state and eye close state, and E that have seizure activities as shown in Fig.1. Both C and D fall in the same pre-diagnose groups and therefore not considered in this study. Our study dataset includes 150 recordings (50 A, 50 B and 50 ...
Similar publications
The neurological pathology which occurs due to the
disturbance of the nerve cell activity and causing recurrent seizures
is called epilepsy. In medical practice, the localization of the epileptogenic
area or region in the brain is the primary task for the
effectiveness of the epilepsy surgery. The epileptogenic region is
identified based on the pre...
Features extracted from the wavelet transform coefficient matrix are widely used in the design of machine learning models to classify event-related potential (ERP) and electroencephalography (EEG) signals in a wide range of brain activity research and clinical studies. This novel study is aimed at dramatically improving the performance of such wave...
With the rapid development of emotion recognition technology, how to realize the naturalization and intellectualization of human–computer interaction, so that the human emotional state can be effectively recognized by the machine, and then get natural and harmonious emotional feedback results, has become the focus of research in the field of emotio...
Electroencephalography (EEG) is a bio-signal used in various approaches such as clinical diagnosis. The analysis aims to investigate the validity of EEG signal detection after mTBI which refers to mild traumatic brain injury. Although EEG does not directly present features that could be found within mTBI, by utilizing the processing method of CWT (...
Citations
... Information fusion has been also very demanding in medical pattern recognition applications [110]. According to [111] information fusion in pattern recognition are categorized into feature fusion [98], [112]- [118], model fusion [83], [100] and decision fusion. Feature fusion is seen to be the most effective way to improve the performance of decision models. ...
Fusion technologies have rapidly evolved. These technologies are normally customized according to the needs of domains. Despite a large number of publications on intelligence fusion applications for various domains, they are scattered. The aim of this review is to present the state of the art for intelligence fusion applications within a specific domain. We identified three major domains for the purpose, namely robotics, military, and healthcare, during the initial process of the systematic review. These three domains are always in need of superior intelligence. Articles were searched mainly in IEEE Xplore. We limit the range of publications to the year 2014 to 2019, to focus on the most recent publications. We adopt the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol to screen, filter and evaluate qualities of each retrieved article. As a result, we retrieved 675 articles at the initial stage of the search, we conducted screening and filtering process and reviewed 153 articles potential articles, and finally, we excluded 36 articles as they do not comply with our quality assessment criteria. Only 117 articles are included. The results of this study are a list of classified applications within the domains and a number of relevant techniques or approaches used in each classified application. The finding of this review showed that the most published works for the use of intelligence fusion are mainly applications in the robotics domain, where mostly used techniques are Kalman Filter and its variants. Outcomes of this study can be a guideline or an insight for researchers to further develop and implement in this field.
... The overall accuracy of ME is one to two percentage points higher than that of MPLNN. Using wavelet to extract the characteristics of the signal can not only make full use of the characteristics of wavelet fractal, capture features on different scales, but also use the characteristics of wavelet time domain or spatial domain displacement to preserve the spatio-temporal information of the feature [8]. Based on the original research, Subasi changed the classification method and introduced SVM. ...
... Zero number of turns, S is the step size of convolution or pooling. Therefore, the length, width, and depth dimensions of the data output [2,48,8], and the one-dimensional vector is expanded into 768 neurons, and the number of hidden neurons in the layer is set to 256. And use the Dropout method to reduce overfitting. ...
The brain-computer interface technology interprets the EEG signals displayed by the human brain’s neurological thinking activities through computers and instruments, and directly uses the interpreted information to manipulate the outside world, thereby abandoning the human peripheral nerves and muscle systems. The emergence of brain-computer interface technology has brought practical value to many fields. Based on the mechanism and characteristics of motion imaging EEG signals, this paper designs the acquisition experiment of EEG signals. After removing the anomalous samples, the wavelet-reconstruction method is used to extract the specific frequency band of the motion imaging EEG signal. According to the characteristics of motor imagery EEG signals, the feature recognition algorithm of convolutional neural networks is discussed. After an in-depth analysis of the reasons for choosing this algorithm, a variety of different network structures were designed and trained. The optimal network structure is selected by analyzing the experimental results, and the reasons why the structure effect is superior to other structures are analyzed. The results show that the method has a high accuracy rate for the recognition of motor imagery EEG, and it has good robustness.
Use of an appropriate stimulus is essential to acquire proper nerve conduction signal. This paper presents a voltage controlled stimulator that generates proper voltage to be applied over the skin for nerve conduction study (NCS). Unlike conventional stimulator, the designed stimulator is based on battery which is suitable for portable nerve study machines. The recording and signal processing involve signal conditioning circuit that consisting of filter and amplifier circuits. The conditioning circuit amplifies and filters low-level biomedical signal, usually, falls in mV. Experimental setup has been tested and demonstrated using real-time data collected in laboratory. The system is adaptable to the subjects with safety.
Medical images are taken by using different modalities like Magnetic resonance imaging (MRI), positron emission tomography (PET) image, computed tomography (CT), X-ray and Ultrasound. Each and every modalities has its own pros and cons. In now a days there are many modality images are fused and getting very good resultant image. This resultant image will give very good analysis about the disease. We can easily find out the disease portion with its exact circumference. Magnetic resonance imaging (MRI) and positron emission tomography (PET) image fusion is a late half breed methodology utilized in a few oncology applications. The MRI image demonstrates the brain tissue life structures and does not contain any useful data, while the PET image the mind work and has a low spatial goals. An ideal MRI–PET combination technique safeguards the practical data of the PET image and includes spatial attributes of the MRI image with the less conceivable spatial twisting. In this paper we discussed about different types of modalities fusing and which will get good result to analyse the disease perfectly and accurately.
