Monitoring Disease Severity of Mild Cognitive Impairment from Single-Channel EEG Data Using Regression Analysis.

A deviation in the soundness of cognitive health is known as mild cognitive impairment (MCI), and it is important to monitor it early to prevent complicated diseases such as dementia, Alzheimer's disease (AD), and Parkinson's disease (PD). Traditionally, MCI severity is monitored with manual scoring using the Montreal Cognitive Assessment (MoCA). In this study, we propose a new MCI severity monitoring algorithm with regression analysis of extracted features of single-channel electro-encephalography (EEG) data by automatically generating severity scores equivalent to MoCA scores. We evaluated both multi-trial and single-trail analysis for the algorithm development. For multi-trial analysis, 590 features were extracted from the prominent event-related potential (ERP) points and corresponding time domain characteristics, and we utilized the lasso regression technique to select the best feature set. The 13 best features were used in the classical regression techniques: multivariate regression (MR), ensemble regression (ER), support vector regression (SVR), and ridge regression (RR). The best results were observed for ER with an RMSE of 1.6 and residual analysis. In single-trial analysis, we extracted a time-frequency plot image from each trial and fed it as an input to the constructed convolutional deep neural network (CNN). This deep CNN model resulted an RMSE of 2.76. To our knowledge, this is the first attempt to generate automated scores for MCI severity equivalent to MoCA from single-channel EEG data with multi-trial and single data.

Misalignment-Tolerant Planar Spiral Coil Pair Design for 13.56 MHz Inductive Coupling of Wireless Resistive Analog Passive Sensors.

Long-term daily-life body signal monitoring offers numerous advantages, such as timely response to health alerts, diseases monitoring, and reducing time and expenses related to clinical trials. Access to physiological data can be achieved with low-cost and comfortable wireless wearable sensors. In our previous publication, we reported a low-cost, easy to implement, and unobtrusive wireless resistive analog passive (WRAP) sensor to provide a feasible bio-signal monitoring technique by using a pair of printed spiral coils (PSC) in a near field connection. Sensitivity, defined as the response to the transducer, is a critical feature in the establishment of a reliable system. In the previous publication, we presented the utilization of a Genetic Algorithm to design a pair of coils and related components to maximize sensitivity. Although the coils' misalignment can significantly affect the optimized sensitivity, it was not incorporated into the optimization process. This paper focuses on optimizing the coils and components in order to maximize both their sensitivity and their resilience against movements of the PSC pair. In a square-shaped pair comprising a primary coil of 60 mm and a secondary coil of 20 mm dimensions, we found that the sensitivity is maximized at 1.3 mƱ for a 16 mm axial distance. Additionally, it remains above 0.65 mƱ within ±11.25 mm lateral and +14 mm axial displacements.

Inductive Coupling of Bipolar Signals with a Conjugate Coil Pair for an Analog Passive ECG Sensor Using a PPy-Coated pvCNT Dry Electrodes.

The wireless capture of analog differential signals from fully passive (battery-less) sensors is technically challenging but it can allow for the seamless capture of differential biosignals such as an electrocardiogram (ECG). This paper presents a novel design for the wireless capture of analog differential signals using a novel conjugate coil pair for a wireless resistive analog passive (WRAP) ECG sensor. Furthermore, we integrate this sensor with a new type of dry electrode, namely conductive polymer polypyrrole (PPy)-coated patterned vertical carbon nanotube (pvCNT) electrodes. The proposed circuit uses dual-gate depletion-mode MOSFETs to convert the differential biopotential signals to correlated drain-source resistance changes and the conjugate coil wirelessly transmits the differences of the two input signals. The circuit rejects (17.24 dB) common mode signals and passing only differential signals. We have integrated this novel design with our previously reported PPy-coated pvCNT dry ECG electrodes, fabricated on a stainless steel substrate with a diameter of 10 mm, which provided a zero-power (battery-less) ECG capture system for long duration monitoring. The scanner transmits an RF carrier signal at 8.37 MHz. The proposed ECG WRAP sensor uses only two complementary biopotential amplifier circuits, each of which has a single-depletion MOSFET. The amplitude-modulated RF signal is envelope-detected, filtered, amplified, and transmitted to a computer for signal processing. ECG signals are collected using this WRAP sensor and compared with a commercial counterpart. Due to the battery-less nature of the ECG WRAP sensor, it has the potential to be a body-worn electronic circuit patch with dry pvCNT electrodes that stably operate for a long period of time.

A Field Study to Capture Events of Interest (EoI) from Living Labs Using Wearables for Spatiotemporal Monitoring Towards a Framework of Smart Health (sHealth).

Everyday wearables such as smartwatches or smart bands can play a pivotal role in the field of fitness and wellness and hold the prospect to be used for early disease detection and monitoring towards Smart Health (sHealth). One of the challenges is the extraction of reliable biomarkers from data collected using these devices in the real world (Living Labs). In this yearlong field study, we collected the nocturnal instantaneous heart rate from 9 participants using wrist-worn commercial smart bands and extracted heart rate variability features (HRV). In addition, we measured core body temperature using our custom-designed flexible Inkjet-Printed (IJP) temperature sensor and SpO2 with a finger pulse oximeter. The core body temperature along with user-reported symptoms have been used for automated spatiotemporal monitoring of flu symptoms severity in real-time. The extracted HRV feature values are within the 95% confidence interval of normative values and shows an anticipated trend for gender and age. The resulting dataset from this study is a novel addition and may be used for future investigations.Clinical Relevance- The findings of this study shows usability of wearables in detection and monitoring of diseases such as obstructive sleep apnea reducing the prevalence of undiagnosed cases. This framework also has potentials to monitor outbreaks of flu and other diseases with spatiotemporal distribution.

Estimating Reliability of Signal Quality of Physiological Data from Data Statistics Itself for Real-time Wearables.

Artificial intelligence (AI) algorithms including machine and deep learning relies on proper data for classification and subsequent action. However, real-time unsupervised streaming data might not be reliable, which can lead to reduced accuracy or high error rates. Estimating reliability of signals, such as from wearable sensors for disease monitoring, is thus important but challenging since signals can be noisy and vulnerable to artifacts. In this paper, we propose a novel "Data Reliability Metric (DReM)" and demonstrate the proof-of-concept with two bio signals: electrocardiogram (ECG) and photoplethysmogram (PPG). We explored various statistical features and developed Artificial Neural Network (ANN), Random Forest (RF) and Support Vector Machine (SVM) models to autonomously classify good quality signals from the bad quality signals. Our results demonstrate the performance of the classification with a cross-validation accuracy of 99.7%, sensitivity of 100%, precision of 97% and F-score of 96%. This work demonstrates the potential of DReM to objectively and automatically estimate signal quality in unsupervised real-time settings with low computational requirement suitable for low-power digital signal processing techniques on wearables.

Immunomagnetic Capture and Multiplexed Surface Marker Detection of Circulating Tumor Cells with Magnetic Multicolor Surface-Enhanced Raman Scattering Nanotags.

Circulating tumor cells (CTCs) have substantial clinical implications in cancer diagnosis and monitoring. Although significant progress has been made in developing technologies for CTC detection and counting, the ability to quantitatively detect multiple surface protein markers on individual tumor cells remains very limited. In this work, we report a multiplexed method that uses magnetic multicolor surface-enhanced Raman scattering (SERS) nanotags in conjunction with a chip-based immunomagnetic separation to quantitatively and simultaneously detect four surface protein markers on individual tumor cells in whole blood. Four-color SERS nanotags were prepared using magnetic-optical iron oxide-gold core-shell nanoparticles with different Raman reporters to recognize four different cancer markers with respective antibodies. A microfluidic device was fabricated to magnetically capture the nanoparticle-bound tumor cells and to perform online negative staining and single-cell optical detection. The level of each targeted protein was obtained by signal deconvolution of the mixed SERS signals from individual tumor cells using the classic least squares regression method. The method was tested with spiked tumor cells in human whole blood with three different breast cancer cell lines and compared with the results of purified cancer cells suspended in a phosphate buffer solution. The method, with either spiked cancer cells in blood or purified cancer cells, showed a strong correlation with purified cancer cells by enzyme-linked immunosorbent assay, suggesting the potential of our method for the reliable detection of multiple surface markers on CTCs. Combining immunomagnetic enrichment with high specificity, multiplexed targeting for the capture of CTC subpopulations, multicolor SERS detection with high sensitivity and specificity, microfluidics for handling rare cells and magnetic-plasmonic nanoparticles for dual enrichment and detection, our method provides an integrated, yet a simple and an efficient platform that has the potential to more sensitively detect and monitor cancer metastasis.

Electric Stimulus-Responsive Chitosan/MNP Composite Microbeads for a Drug Delivery System.

In the last several years, conventional drug delivery systems (DDS) have evolved into DDS that are responsive to exogenous or endogenous stimuli. The objective of this paper is to present a DDS that is responsive to an electric stimulus in the form of bipolar electric pulses. The DDS structure is based on chitosan embedded with magnetic nanoparticles, and crosslinked with polyethylene glycol dimethacrylate to form microbeads. This DDS is loaded with vancomycin as the therapeutic agent of interest. Silver inter-digitated electrodes (IDE) were printed on polyimide substrates with a MEMS-based inkjet material deposition printer, and used to provide 100 Hz pulses of electric current to the DDS for 3 min. The results showed that the stimulated groups released ∼800% more vancomycin than the non-stimulated groups in the excitation duration, but followed a first-order elution profile otherwise. Another significance of our approach is that it does not need complicated or expensive fabrication processes, and can be customized according to the targeted implant site. The IDE system has also been modeled using COMSOL to study the distributed electric fields and ion migration during the stimulus. This paper demonstrates a novel and promising technique of providing stimulus to drug substrates for controllable drug delivery.

A Single-Channel EEG-Based Approach to Detect Mild Cognitive Impairment via Speech-Evoked Brain Responses.

Mild cognitive impairment (MCI) is the preliminary stage of dementia, which may lead to Alzheimer's disease (AD) in the elderly people. Therefore, early detection of MCI has the potential to minimize the risk of AD by ensuring the proper mental health care before it is too late. In this paper, we demonstrate a single-channel EEG-based MCI detection method, which is cost-effective and portable, and thus suitable for regular home-based patient monitoring. We collected the scalp EEG data from 23 subjects, while they were stimulated with five auditory speech signals. The cognitive state of the subjects was evaluated by the Montreal cognitive assessment test (MoCA). We extracted 590 features from the event-related potential (ERP) of the collected EEG signals, which included time and spectral domain characteristics of the response. The top 25 features, ranked by the random forest method, were used for classification models to identify subjects with MCI. Robustness of our model was tested using leave-one-out cross-validation while training the classifiers. Best results (leave-one-out cross-validation accuracy 87.9%, sensitivity 84.8%, specificity 95%, and F score 85%) were obtained using support vector machine (SVM) method with radial basis kernel (RBF) (sigma = 10/cost = 102 ). Similar performances were also observed with logistic regression (LR), further validating the results. Our results suggest that single-channel EEG could provide a robust biomarker for early detection of MCI.

Telemetry-controlled simultaneous stimulation-and-recording device (SRD) to study interhemispheric cortical circuits in rat primary somatosensory (SI) cortex.

BACKGROUND: A growing need exists for neuroscience platforms that can perform simultaneous chronic recording and stimulation of neural tissue in animal models in a telemetry-controlled fashion with signal processing for analysis of the chronic recording data and external triggering capability. We describe the system design, testing, evaluation, and implementation of a wireless simultaneous stimulation-and-recording device (SRD) for modulating cortical circuits in physiologically identified sites in primary somatosensory (SI) cortex in awake-behaving and freely-moving rats. The SRD was developed using low-cost electronic components and open-source software. The function of the SRD was assessed by bench and in-vivo testing. RESULTS: The SRD recorded spontaneous spiking and bursting neuronal activity, evoked responses to programmed intracortical microstimulation (ICMS) delivered internally by the SRD, and evoked responses to external peripheral forelimb stimulation. CONCLUSIONS: The SRD is capable of wireless stimulation and recording on a predetermined schedule or can be wirelessly synchronized with external input as would be required in behavioral testing prior to, during, and following ICMS.

Severity Classification of Chronic Obstructive Pulmonary Disease and Asthma with Heart Rate and SpO2 Sensors.

Asthma and Chronic Obstructive Pulmonary Disease are chronic and long-term lung diseases. Disease monitoring with minimal sensors with high efficacy can make the disease control simple and practical for patients. We propose a model for the severity assessment of the diseases through wearables and compatible with mobile health applications, using only heart rate and SpO2 (from pulse oximeter sensor). Patient data were obtained from the MIMIC- III Waveform Database Matched Subset. The dataset consists of 158 subjects. Both heart rate and SpO2 signal of patients are analyzed via the proposed algorithm to classify the severity of the diseases. Strategically, a rule-based threshold approach in real time evaluation is considered for the categorization scheme. Furthermore, a method is proposed to assess severity as an Event of Interest (EOI) from the computed metrics in retrospective. This type of autonomous system for real-time evaluation of patient's condition has the potential to improve individual health through continual monitoring and self- management, as well as improve the health status of the overall Smart and Connected Community (SCC).

Sensitivity optimization of Printed Spiral Coil for Wireless Resistive Analog Passive (WRAP) Sensors using Genetic Algorithm.

Body-worn battery-less Wireless Resistive Analog Passive (WRAP) sensor can be unobtrusive while collecting physiological data continuously. Inductive connection between a pair of Printed Spiral Coils (PSC) eliminates the intrusive wires. Inductive connection of primary and secondary PSC enabled us to probe the body signals using the inductive link. The primary side voltage is modulated by the sensed body signal at the secondary PSC. The coil physical characteristics influence the sensitivity which is defined as observed voltage changes over the sensor variation. We have previously reported an iterative method to optimize the coil specifications for maximum sensitivity with constrained coil prof ile size by maximizing the power transfer efficiency from primary to secondary. In this study sensitivity is maximized by first, driving an analytical multivariable equation of circuit components and physical characteristics, and then using Genetic Algorithm (GA) to maximize it with considering the size and fabrication constraints. The results are compared to the other methods that shows a higher result in the range of 102 comparing to the best alternate methods (sqp). It helps us to detect smaller physiological signals in the noisy environment.

BRAINsens: Body-Worn Reconfigurable Architecture of Integrated Network Sensors.

Body sensor network (BSN) is a promising human-centric technology to monitor neurophysiological data. We propose a fully-reconfigurable architecture that addresses the major challenges of a heterogenous BSN, such as scalabiliy, modularity and flexibility in deployment. Existing BSNs especially with Electroencephalogarm (EEG) have these limitations mainly due to the use of driven-right-leg (DRL) circuit. We address these limitations by custom-designing DRL-less EEG smart sensing nodes (SSN) for modular and spatially distributed systems. Each single-channel EEG SSN with a input-referred noise of 0.82 µVrms and CMRR of 70 dB (at 60 Hz), samples brain signals at 512 sps. SSNs in the network can be configured at the time of deployment and can process information locally to significantly reduce data payload of the network. A Control Command Node (CCN) initializes, synchronizes, periodically scans for the available SSNs in the network, aggregates their data and sends it wirelessly to a paired device at a baud rate of 115.2 kbps. At the given settings of the I2C bus speed of 100 kbps, CCN can configure up to 39 EEG SSNs in a lego-like platform. The temporal and frequency-domain performance of the designed "DRL-less" EEG SSNs is evaluated against a research-grade Neuroscan and consumer-grade Emotiv EPOC EEG. The results show that the proposed network system with wearable EEG can be deployed in situ for continuous brain signal recording in real-life scenarios. The proposed system can also seamlessly incorporate other physiological SSNs for ECG, HRV, temperature etc. along with EEG within the same topology.

Magnetic stimulus responsive vancomycin drug delivery system based on chitosan microbeads embedded with magnetic nanoparticles.

Local antibiotic delivery can overcome some of the shortcomings of systemic therapy, such as low local concentrations and delivery to avascular sites. A localized drug delivery system (DDS), ideally, could also use external stimuli to modulate the normal drug release profile from the DDS to provide efficacious drug administration and flexibility to healthcare providers. To achieve this objective, chitosan microbeads embedded with magnetic nanoparticles were loaded with the antibiotic vancomycin and stimulated by a high frequency alternating magnetic field. Three such stimulation sessions separated by 1.5 h were applied to each test sample. The chromatographic analysis of the supernatant from these stimulated samples showed more than approximately 200% higher release of vancomycin from the DDS after the stimulation periods compared to nonstimulated samples. A 16-day long term elution study was also conducted where the DDS was allowed to elute drug through normal diffusion over a period of 11 days and stimulated on day 12 and day 15, when vancomycin level had dropped below therapeutic levels. Magnetic stimulation boosted elution of test groups above minimum inhibitory concentration (MIC), as compared to control groups (with no stimulation) which remained below MIC. The drug release from test groups in the intervals where no stimulation was given showed similar elution behavior to control groups. These results indicate promising possibilities of controlled drug release using magnetic excitation from a biopolymer-based DDS. © 2017 Wiley Periodicals, Inc. J Biomed Mater Res Part B: Appl Biomater, 106B: 2169-2176, 2018.

ElectronixTutor: an intelligent tutoring system with multiple learning resources for electronics.

BACKGROUND: The Office of Naval Research (ONR) organized a STEM Challenge initiative to explore how intelligent tutoring systems (ITSs) can be developed in a reasonable amount of time to help students learn STEM topics. This competitive initiative sponsored four teams that separately developed systems that covered topics in mathematics, electronics, and dynamical systems. After the teams shared their progress at the conclusion of an 18-month period, the ONR decided to fund a joint applied project in the Navy that integrated those systems on the subject matter of electronic circuits. The University of Memphis took the lead in integrating these systems in an intelligent tutoring system called ElectronixTutor. This article describes the architecture of ElectronixTutor, the learning resources that feed into it, and the empirical findings that support the effectiveness of its constituent ITS learning resources. RESULTS: A fully integrated ElectronixTutor was developed that included several intelligent learning resources (AutoTutor, Dragoon, LearnForm, ASSISTments, BEETLE-II) as well as texts and videos. The architecture includes a student model that has (a) a common set of knowledge components on electronic circuits to which individual learning resources contribute and (b) a record of student performance on the knowledge components as well as a set of cognitive and non-cognitive attributes. There is a recommender system that uses the student model to guide the student on a small set of sensible next steps in their training. The individual components of ElectronixTutor have shown learning gains in previous decades of research. CONCLUSIONS: The ElectronixTutor system successfully combines multiple empirically based components into one system to teach a STEM topic (electronics) to students. A prototype of this intelligent tutoring system has been developed and is currently being tested. ElectronixTutor is unique in its assembling a group of well-tested intelligent tutoring systems into a single integrated learning environment.

Magnetic stimuli-responsive chitosan-based drug delivery biocomposite for multiple triggered release.

Stimuli-responsive biomaterials offer a unique advantage over traditional local drug delivery systems in that the drug elution rate can be controllably increased to combat developing symptomology or maintain high local elution levels for disease treatment. In this study, superparamagnetic Fe3O4 nanoparticles and the antibiotic vancomycin were loaded into chitosan microbeads cross-linked with varying lengths of polyethylene glycol dimethacrylate. Beads were characterized using degradation, biocompatibility, and elution studies with successive magnetic stimulations at multiple field strengths and frequencies. Thirty-minute magnetic stimulation induced a temporary increase in daily elution rate of up to 45% that was dependent on field strength, field frequency and cross-linker length. Beads degraded by up to 70% after 3 days in accelerated lysozyme degradation tests, but continued to elute antibiotic for up to 8 days. No cytotoxic effects were observed in vitro compared to controls. These promising preliminary results indicate clinical potential for use in stimuli-controlled drug delivery.

Comparative Study of Wavelet-Based Unsupervised Ocular Artifact Removal Techniques for Single-Channel EEG Data.

Electroencephalogram (EEG) is a technique for recording the asynchronous activation of neuronal firing inside the brain with non-invasive scalp electrodes. Artifacts, such as eye blink activities, can corrupt these neuronal signals. While ocular artifact (OA) removal is well investigated for multiple channel EEG systems, in alignment with the recent momentum toward minimalistic EEG systems for use in natural environments, we investigate unsupervised and effective removal of OA from single-channel streaming raw EEG data. In this paper, the unsupervised wavelet transform (WT) decomposition technique was systematically evaluated for the effectiveness of OA removal for a single-channel EEG system. A set of seven raw EEG data set was analyzed. Two commonly used WT methods, Discrete Wavelet Transform (DWT) and Stationary Wavelet Transform (SWT), were applied. Four WT basis functions, namely, haar, coif3, sym3, and bior4.4, were considered for OA removal with universal threshold and statistical threshold (ST). To quantify OA removal efficacy from single-channel EEG, five performance metrics were utilized: correlation coefficients, mutual information, signal-to-artifact ratio, normalized mean square error, and time-frequency analysis. The temporal and spectral analysis shows that the optimal combination could be DWT with ST with coif3 or bior4.4 to remove OA among 16 combinations. This paper demonstrates that the WT can be an effective tool for unsupervised OA removal from single-channel EEG data for real-time applications.

Design and validation of a wearable "DRL-less" EEG using a novel fully-reconfigurable architecture.

The conventional EEG system consists of a driven-right-leg (DRL) circuit, which prohibits modularization of the system. We propose a Lego-like connectable fully reconfigurable architecture of wearable EEG that can be easily customized and deployed at naturalistic settings for collecting neurological data. We have designed a novel Analog Front End (AFE) that eliminates the need for DRL while maintaining a comparable signal quality of EEG. We have prototyped this AFE for a single channel EEG, referred to as Smart Sensing Node (SSN), that senses brain signals and sends it to a Command Control Node (CCN) via an I2C bus. The AFE of each SSN (referential-montage) consists of an off-the-shelf instrumentation amplifier (gain=26), an active notch filter fc = 60Hz), 2nd-order active Butterworth low-pass filter followed by a passive low pass filter (fc = 47.5 Hz, gain = 1.61) and a passive high pass filter fc = 0.16 Hz, gain = 0.83). The filtered signals are digitized using a low-power microcontroller (MSP430F5528) with a 12-bit ADC at 512 sps, and transmitted to the CCN every 1 s at a bus rate of 100 kbps. The CCN can further transmit this data wirelessly using Bluetooth to the paired computer at a baud rate of 115.2 kbps. We have compared temporal and frequency-domain EEG signals of our system with a research-grade EEG. Results show that the proposed reconfigurable EEG captures comparable signals, and is thus promising for practical routine neurological monitoring in non-clinical settings where a flexible number of EEG channels are needed.

Medical device market in China.

With China's growing old-age population and economic presence on the international stage, it has become important to evaluate its domestic and foreign market contribution to medical devices. Medical devices are instruments or apparatuses used in the prevention, rehabilitation, treatment, or knowledge generation with respect to disease or other abnormal conditions. This article provides information drawn from recent publications to describe the current state of the Chinese domestic market for medical devices and to define opportunities for foreign investment potential therein. Recent healthcare reforms implemented to meet rising demand due to an aging and migrating population are having a positive effect on market growth-a global market with a projected growth of 15% per year over the next decade.

Stealth Engineering for In Vivo Drug Delivery Systems.

In generic terms, a drug delivery substrate (DDS) can be described as a vehicle to transport drug to the point of interest. A DDS that would ideally have the capability to control drug dosage and achieve target specificity, localization, and higher therapeutic efficacy has been pursued as a holy grail in pharmaceutical research. Over the years, diverse classes, structures, and modifications of DDS have been proposed to achieve this aim. One of its major deterrents, however, is rapid elimination of drug by the immune system before intended functionality. Stealth engineering is broadly defined as a method of designing a drug carrier to minimize or delay opsonization until the encapsulated drug is delivered to the intended target. Stealth-engineered DDS has been successful in extending drug circulation lifetime from a few minutes to several days. Currently, this field of research has made much progress since its initiation in 1960s with liposomes to DNA boxes. Activity has also benefited several areas of medicine, where it has been applied in cancer, gene therapy, bone regrowth, and infection treatment. This review covers the progress of some types of DDS that have been published and indexed in major databases (including ScienceDirect, PubMed, and Google Scholar) in the scientific literature.

Unsupervised eye blink artifact denoising of EEG data with modified multiscale sample entropy, Kurtosis, and wavelet-ICA.

Brain activities commonly recorded using the electroencephalogram (EEG) are contaminated with ocular artifacts. These activities can be suppressed using a robust independent component analysis (ICA) tool, but its efficiency relies on manual intervention to accurately identify the independent artifactual components. In this paper, we present a new unsupervised, robust, and computationally fast statistical algorithm that uses modified multiscale sample entropy (mMSE) and Kurtosis to automatically identify the independent eye blink artifactual components, and subsequently denoise these components using biorthogonal wavelet decomposition. A 95% two-sided confidence interval of the mean is used to determine the threshold for Kurtosis and mMSE to identify the blink related components in the ICA decomposed data. The algorithm preserves the persistent neural activity in the independent components and removes only the artifactual activity. Results have shown improved performance in the reconstructed EEG signals using the proposed unsupervised algorithm in terms of mutual information, correlation coefficient, and spectral coherence in comparison with conventional zeroing-ICA and wavelet enhanced ICA artifact removal techniques. The algorithm achieves an average sensitivity of 90% and an average specificity of 98%, with average execution time for the datasets ( N = 7) of 0.06 s ( SD = 0.021) compared to the conventional wICA requiring 0.1078 s ( SD = 0.004). The proposed algorithm neither requires manual identification for artifactual components nor additional electrooculographic channel. The algorithm was tested for 12 channels, but might be useful for dense EEG systems.