Sleep specialists often conduct manual sleep stage scoring by visually inspecting the patient’s neurophysiological signals collected at sleep labs. This is, generally, a very difficult, tedious and time-consuming task. The limitations of manual sleep stage scoring have escalated the demand for developing Automatic Sleep Stage Classification (ASSC) systems. Sleep stage classification refers to identifying the various stages of sleep and is a critical step in an effort to assist physicians in the diagnosis and treatment of related sleep disorders. The aim of this paper is to survey the progress and challenges in various existing Electroencephalogram (EEG) signal-based methods used for sleep stage identification at each phase; including pre-processing, feature extraction and classification; in an attempt to find the research gaps and possibly introduce a reasonable solution. Many of the prior and current related studies use multiple EEG channels, and are based on 30 s or 20 s epoch lengths which affect the feasibility and speed of ASSC for real-time applications. Thus, in this paper, we also present a novel and efficient technique that can be implemented in an embedded hardware device to identify sleep stages using new statistical features applied to 10 s epochs of single-channel EEG signals. In this study, the PhysioNet Sleep European Data Format (EDF) Database was used. The proposed methodology achieves an average classification sensitivity, specificity and accuracy of 89.06%, 98.61% and 93.13%, respectively, when the decision tree classifier is applied. Finally, our new method is compared with those in recently published studies, which reiterates the high classification accuracy performance.
Epilepsy is a crucial neurological disorder in which patients experience epileptic seizure caused by abnormal electrical discharges from the brain. It is highly common in children and adults at the age of 65-70. Around 1 % of the world's population is affected by this disease. The mechanism of epilepsy is still incomprehensible to researchers; however, 80% of the seizure activity can be treated effectively if proper diagnosis is performed. This disease mostly leads to uncontrollable movements, convulsions and loss of conscious and contends the patient to increased possibility of accidental injury and even death. As a result, monitoring the person with epilepsy from being exposed to the danger is among the basic death to life transformation solutions. In this paper, we propose the most important methodologies that could be implemented in hardware for monitoring an epileptic patient. Many studies show that, Electroencephalogram (EEG) is the most important signal used by physicians in assessing the brain activities and diagnosing different brain disorders. This study is based on different EEG datasets that were obtained and described by researchers for analysis and diagnosis of epilepsy. Butterworth bandpass filters are implemented and used to preprocess and decompose the EEG signal into five different EEG frequency bands (delta, theta, alpha, beta, and gamma). In addition, different features such as energy, standard deviation and entropy are then computed and extracted from each Δ, Θ, α, β and γ sub-band. Furthermore, the extracted features are then fed to a supervised learning classifier; support vector machine (SVM); in order to detect the epileptic events and identify if the acquired signal is corresponding to seizure or not according to the objective of this research. If seizure is experienced, appropriate monitoring should be taken in action. Experimental results on a number of subjects confirm 95% classification accuracy of the proposed work.
In recent years, the estimation of human sleep disorders from Electroencephalogram (EEG) signals have played an important role in developing automatic detection of sleep stages. A few methods exist in the market presently towards this aim. However, sleep physicians may not have full assurance and consideration in such methods due to concerns associated with systems accuracy, sensitivity and specificity. This paper presents a novel and efficient technique that can be implemented in a microcontroller device to identify sleep stages in an effort to assist physicians in the diagnosis and treatment of related sleep disorders by enhancing the accuracy of the developed algorithm using a single channel of EEG signals. First, the dataset of EEG signal is filtered and decomposed into delta, theta, alpha, beta and gamma subbands using Butterworth band-pass filters. Second, a set of sample statistical discriminating features are derived from each frequency band. Finally, sleep stages consisting of Wakefulness, Rapid Eye Movement (REM) and Non-Rapid Eye Movement (NREM) are classified using several supervised machine learning classifiers including multi-class Support Vector Machines (SVM), Decision Trees (DT), Neural Networks (NN), K-Nearest Neighbors (KNN) and Naive Bayes (NB). This paper combines REM with Stage 1 NREM due to data similarities. Performance is then compared based on single channel EEG signals that were obtained from 20 healthy subjects. The results show that the proposed technique using DT classifier efficiently achieves high accuracy of 97.30% in differentiating sleeps stages. Also, a comparison of our method with some recent available works in the literature reiterates the high classification accuracy performance.
Sleep disorders are considered as one of the major human life issues in the recent years. Therefore, efficient and automated systems that can differentiate sleep stages and assist physicians/neurologists in the diagnosis and treatment of sleep-related disorders, are highly on demand. The present paper is devoted to developing an easy-to-implement sleep stage classification algorithm that works fast (near real-time) in a proficient way. The proposed algorithm is based on two statistical features applied to single-channel EEG signals. We examined the effectiveness of our technique by building a near real-time detection system using the Neurosky's Mindwave Mobile device, an affordable wireless EEG headset, to obtain EEG signals. The system is one-way without feedback loops. The results of analyzing our algorithm show that the run-time performance of this detection technique is quasi-linearly proportional to the size of the input samples and the execution time is fast, regardless of the time recording the data.
In this work, an efficient digital system is designed using hardware to filter the Electrocardiogram (ECG) signal and to detect the QRS complex (beats). The system implementation has been done by using a Field Programmable Gate Array (FPGA). In the first phase of the hardware system implementation, Finite Impulse Response (FIR) filters are designed for preprocessing and denoising the ECG signal. The filtered signal is then used as the input of the second phase of the hardware implementation to detect and classify the ECG beats. The entire system has been implemented on ALTERA DE II FPGA by designing synthesizable finite state machines. Quartus II tool has been used to simulate and test the system. The designed system has been tested on ECG waves from the MIT-BIH Arrhythmia database by windowing the signal and applying adaptive signal and noise thresholds in each window of processing. The hardware system has achieved an overall accuracy of 98% in the beat detection phase, while providing the detected beats and the classification of irregular heart beat rates in real time.
Currently, sleep disorders are considered as one of the major human life issues. There are several stable physiological stages that the human brain goes through during sleep. Nowadays, many biomedical signals such as EEG, ECG, EMG, and EOG offer useful details for clinical setups that are used in identifying sleep disorders. In this work, we propose an efficient technique that could be implemented in hardware to differentiate sleep stages which will assist physicians in the diagnosis and treatment of related sleep disorders. This study depends on different EEG datasets from PhysioNet using the Sleep-EDF [Expanded] Database that were acquired and described by scientists for the analysis and diagnosis of sleep stages. Generally, the EEG signal is decomposed into five bands: delta, theta, alpha, beta, and gamma to define the change in brain state. In this work, Butterworth band-pass filters are designed to filter and decompose EEG into the above frequency sub-bands. In addition, various discriminating features including energy, standard deviation and entropy are computed and extracted from each δ, □, α, β and γ sub-band. Furthermore, the extracted features are then fed to a supervised learning classifier; support vector machine (SVM) to be able to recognize the sleep stages state and identify if the acquired signal is corresponding to wake or stage 1 of sleep, according to the purpose of this research. The key novelty of this work is to identify the sleep stages from a publicly available EEG signal dataset by using a feasible set of features, easily implementable filters in any microcontroller device, and an efficient classification method. Therefore, physicians can track these sleep stages to identify certain patterns such as detecting fatigue, drowsiness, and/or various sleep disorders such as sleep apnea. The experimental results on a variety of subjects verify 92.5% of classification accuracy of the proposed work.
This work represents the design and verification of three different finite impulse response (FIR) filter implementations for removing the noise of electrocardiogram (ECG) signals. Generally, ECG signals may be contaminated with different noise sources such as body movement and respiration, electromyography (EMG) interference, power line interference and the baseline wander noise. The FIR filter coefficients are calculated to attenuate the 60 Hz frequencies. The advanced filter design tool available with MATLAB is used to first determine the FIR filter coefficients. These coefficients are then used in three different FIR filter implementations: regular implementation, pipelined implementation and pipelined multiply-accumulate (MAC) implementation. The three implementations are designed using VHDL and the Quartus II design toolset. A test bench is also designed to verify the operation of each filter implementation, and the Modelsim simulator available with Quartus is used to run the tests. The synthesized reports for the three different implementations show the resource utilization and the maximum operating frequency. As a result, the regular (direct) design produces the simplest design but consumes more resources and operates at lower frequencies. The pipelined architecture consumes more resources but it enhances the operating frequency. The pipelined MAC implementation requires the least resources and operates at extremely higher performance, however, the main drawback is its complexity. The hardware implementations can be further viewed as an industrial ECG monitoring framework where system dynamics modeling can be applied to minimize the risks associated with the framework using any of the three implementations.
Nowadays, analyzing EEG signals has made it easy to diagnose many sleep-related breathing disorders such as Obstructive Sleep Apnea (OSA), which is a potentially serious sleep disorder that affects the quality of human life. This paper introduces an efficient methodology that could be implemented in hardware to differentiate OSA patients from normal controls, based on the Electroencephalogram (EEG) signals. For this purpose, first, the EEG recorded datasets that were obtained from the Phsyionet website are filtered and decomposed into delta, theta alpha, beta and gamma sub-bands using Infinite Impulse Response (IIR) Butterworth band-pass filters. Second, descriptive features such as energy and variance are extracted from each frequency band that are used as input parameters for classification. Finally, several machine learning algorithms including Support Vector Machines (SVM), Artificial Neural Networks (ANN), Linear Discriminant Analysis (LDA) and Naive Bayes (NB) are employed in order to identify if the OSA exists or not, according to the objective of this study. The results that are obtained from these classifiers are then compared in terms of accuracy, sensitivity and specificity. The experimental results show that the SVM attained the best classification accuracy of 97.14% as compared to the others.
Currently, sleep disorders are considered as one of the major human life issues. Human sleep is a regular state of rest for the body in which the eyes are not only usually closed, but also have several nervous centers being inactive; hence, rendering the person either partially or completely unconscious and making the brain a less complicated network. This paper introduces an efficient technique towards differentiating sleep stages to assist physicians in the diagnosis and treatment of related sleep disorders. The idea is based on easily implementable filters in any hardware device and feasible discriminating features of the Electroencephalogram EEG signal by employing the one-against-all method of the multiclass Support Vector machine (SVM) to recognize the sleep stages and identify if the acquired signal is corresponding to wake, stage1, stage2, stage3 or stage4. The experimental results on several subjects achieve 92% of classification accuracy of the proposed work. A comparison of our proposed technique with some recent available work in the literature also presents the high classification accuracy performance.
 scale(2.18978)'%3e%3cpath d='M246.026 120.178c-.558-.295-1.186-.768-1.395-1.054-.314-.438-.132-.456 1.163-.104 2.318.629 3.814.383 5.298-.873l1.308-1.103 1.54.784c.848.428 1.748.725 2.008.656.667-.176 2.05-1.95 2.005-2.564-.054-.759.587-.568.896.264.615 1.631-.281 3.502-1.865 3.918-.773.201-1.488.127-2.659-.281-1.438-.502-1.684-.494-2.405.058-1.618 1.239-3.869 1.355-5.894.299zm5.734-5.242c-.563-.717-1.239-3.424-1.021-4.088.192-.576.391-.691.914-.527.918.287 1.13.92.993 3.064-.107 1.747-.366 2.206-.886 1.551zm-67.516-1.946c-.185 1.311 2.325 4.568 3.458 5.158-.77.345-1.728.188-2.434.576-3.948 3.948-18.367 18.006-21 21.366 7.799.154 16.448-.106 23.761-.44-.007-5.299 5.018-5.572 8.381-7.502 1.73 2.725 6.075 2.516 6.618 6.617 0 4.91.009 12.307.009 17.646h-66.625c-1.172 5.176-5.844 9.125-12.354 7.5 2.014-2.104 5.405-2.827 6.619-5.734 1.024-6.365-2.046-10.296-4.031-13.906 3.284-1.195 3.782-1.494 7.121-3.737-2.344 7.12 6.091 6.338 12.353 6.175.211-2.417.089-5.271-1.766-5.624 2.396-.87 2.794-1.168 6.619-4.412v9.593c14.886 0 30.942-.111 46.139-.111 0-3.002.795-7.824-1.581-7.824-2.269 0-.107 6.173-1.87 6.173h-35.63c0-1.328-.034-4.104-.034-6.104 1.51-1.51 1.331-1.379 11.648-11.697 1.028-1.031 8.266-7.568 14.599-13.713zm89.06-.254c2.487 1.339 4.457 3.191 7.502 3.972-.354 1.261-1.476 1.759-1.77 3.087v26.91c3.402.75 4.118-1.178 5.737-2.205.442 4.307 3.186 8.529 3.088 11.91h-14.559c.002-14.555.002-29.114.002-43.674zm-19.412 14.412s5.296-4.471 5.296-4.643v23.484l3.814-.006c0-8.947-.118-18.022-.118-26.338 1.548-1.549 4.58-3.791 5.338-5.358v42.06c-10.746 0-30.793.012-33.443.012-.493-8.729-.577-17.771 9.6-15.826v-3.563c-.311-.609-.868.147-.998-.645 1.615-1.617 2.163-2.029 6.538-5.852 0 4.612.08 15.5.08 15.5 1.07 0 3.153.004 3.857.004.001.002.036-18.227.036-18.829zm-12.553 18.603c.716 1.075 3.154 1.056 3.04-.755-.411-1.493-3.616-.924-3.04.755z'/%3e%3ccircle cx='144.527' cy='161.369' r='2.042'/%3e%3cpath d='M207.549 112.779c2.488 1.339 4.457 3.191 7.502 3.971-.353 1.26-1.476 1.76-1.768 3.087v26.911c3.401.749 4.117-1.18 5.736-2.206.441 4.308 3.185 8.528 3.088 11.91h-14.56c.002-14.556.002-29.114.002-43.673z'/%3e%3c/g%3e%3c/svg%3e)