Rami J. Oweis

Seizure classification in EEG signals utilizing Hilbert-Huang transform

BackgroundClassification method capable of recognizing abnormal activities of the brain functionality are either brain imaging or brain signal analysis. The abnormal activity of interest in this study is characterized by a disturbance caused by changes in neuronal electrochemical activity that results in abnormal synchronous discharges. The method aims at helping physicians discriminate between healthy and seizure electroencephalographic (EEG) signals.MethodDiscrimination in this work is achieved by analyzing EEG signals obtained from freely accessible databases. MATLAB has been used to implement and test the proposed classification algorithm. The analysis in question presents a classification of normal and ictal activities using a feature relied on Hilbert-Huang Transform. Through this method, information related to the intrinsic functions contained in the EEG signal has been extracted to track the local amplitude and the frequency of the signal. Based on this local information, weighted frequencies are calculated and a comparison between ictal and seizure-free determinant intrinsic functions is then performed. Methods of comparison used are the t-test and the Euclidean clustering.ResultsThe t-test results in a P-value < 0.02 and the clustering leads to accurate (94%) and specific (96%) results. The proposed method is also contrasted against the Multivariate Empirical Mode Decomposition that reaches 80% accuracy. Comparison results strengthen the contribution of this paper not only from the accuracy point of view but also with respect to its fast response and ease to use.ConclusionAn original tool for EEG signal processing giving physicians the possibility to diagnose brain functionality abnormalities is presented in this paper. The proposed system bears the potential of providing several credible benefits such as fast diagnosis, high accuracy, good sensitivity and specificity, time saving and user friendly. Furthermore, the classification of mode mixing can be achieved using the extracted instantaneous information of every IMF, but it would be most likely a hard task if only the average value is used. Extra benefits of this proposed system include low cost, and ease of interface. All of that indicate the usefulness of the tool and its use as an efficient diagnostic tool.

An Intelligent Healthcare Management System: A New Approach in Work-order Prioritization for Medical Equipment Maintenance Requests

The effective maintenance management of medical technology influences the quality of care delivered and the profitability of healthcare facilities. Medical equipment maintenance in Jordan lacks an objective prioritization system; consequently, the system is not sensitive to the impact of equipment downtime on patient morbidity and mortality. The current work presents a novel software system (EQUIMEDCOMP) that is designed to achieve valuable improvements in the maintenance management of medical technology. This work-order prioritization model sorts medical maintenance requests by calculating a priority index for each request. Model performance was assessed by utilizing maintenance requests from several Jordanian hospitals. The system proved highly efficient in minimizing equipment downtime based on healthcare delivery capacity, and, consequently, patient outcome. Additionally, a preventive maintenance optimization module and an equipment quality control system are incorporated. The system is, therefore, expected to improve the reliability of medical equipment and significantly improve safety and cost-efficiency.

Hybrid Zinc Oxide Nanorods/Carbon Nanotubes Composite for Nitrogen Dioxide Gas Sensing

This study reports on the synthesis and fabrication of hybrid nanocomposite based on single-walled carbon nanotubes–ZnO nanorods (SWCNT-ZnONR) as resistive gas sensors for NO2 detection. The sensor was prepared using the standard simple and cost-effective hydrothermal process. The sensor was characterized by x-ray diffraction (XRD) and scanning electron microscopy. The findings revealed enhanced porous SWCNT-ZnONR nanocomposites due to the high porosity of the SWCNT. It was also found that the sensor exhibited average response and recovery times of about 70 s and 100 s, respectively. The XRD peak at 26° indicated that the SWCNT pattern was not disturbed, while sensitivity increased with temperature up to 150°C, at which the sensitivity was maximum. Similarly, the sensor sensitivity increased with NO2 concentration at all levels examined. Moreover, the results indicate that the sensor shows significant promise for NO2 gas sensing applications.

A computer-aided ECG diagnostic tool

Jordan lacks companies that provide local medical facilities with products that are of help in daily performed medical procedures. Because of this, the country imports most of these expensive products. Consequently, a local interest in producing such products has emerged and resulted in serious research efforts in this area. The main goal of this paper is to provide local (the north of Jordan) clinics with a computer-aided electrocardiogram (ECG) diagnostic tool in an attempt to reduce time and work demands for busy physicians especially in areas where only one general medicine doctor is employed and a bulk of cases are to be diagnosed. The tool was designed to help in detecting heart defects such as arrhythmias and heart blocks using ECG signal analysis depending on the time-domain representation, the frequency-domain spectrum, and the relationship between them. The application studied here represents a state of the art ECG diagnostic tool that was designed, implemented, and tested in Jordan to serve wide spectrum of population who are from poor families. The results of applying the tool on randomly selected representative sample showed about 99% matching with those results obtained at specialized medical facilities. Costs, ease of interface, and accuracy indicated the usefulness of the tool and its use as an assisting diagnostic tool.

An alternative respiratory sounds classification system utilizing artificial neural networks

Background: Computerized lung sound analysis involves recording lung sound via an electronic device, followed by computer analysis and classification based on specific signal characteristics as non-linearity and nonstationarity caused by air turbulence. An automatic analysis is necessary to avoid dependence on expert skills. Methods: This work revolves around exploiting autocorrelation in the feature extraction stage. All process stages were implemented in MATLAB. The classification process was performed comparatively using both artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) toolboxes. The methods have been applied to 10 different respiratory sounds for classification. Results: The ANN was superior to the ANFIS system and returned superior performance parameters. Its accuracy, specificity, and sensitivity were 98.6%, 100%, and 97.8%, respectively. The obtained parameters showed superiority to many recent approaches. Conclusions: The promising proposed method is an efficient fast tool for the intended purpose as manifested in the performance parameters, specifically, accuracy, specificity, and sensitivity. Furthermore, it may be added that utilizing the autocorrelation function in the feature extraction in such applications results in enhanced performance and avoids undesired computation complexities compared to other techniques.

A prototype Ultraviolet Light Sensor based on ZnO Nanoparticles/Graphene Oxide Nanocomposite Using Low Temperature Hydrothermal Method

A new prototype UV nanosensor using ZnO nanoparticles (NPs)/graphene oxide (GO) nanocomposite (ZnO-NP/GO) on silicon substrate is reported in this paper. The hybrid nanocomposite structure has been developed by an optimized hydrothermal process at low growth temperature (~50 °C). In this hybrid nanosensor, the ZnO nanoparticles act as UV- absorbing and charge carrier generating material, while graphene with its superior electrical conductivity has been used as a charge transporting material. Various nanostructure characterization techniques were intensively utilized including SEM, EDX, XRD, FTIR and UV-VIS. Also, the I-V measurement was employed to evaluate the prototype sensor. The morphological SEM analysis showed that the ZnO-NPs (average diameter of 20 nm) were dispersed evenly on the GO sheets. As well, the EDX spectra confirmed the exact chemical composition of the intended structure. The room temperature UV-VIS measurement revealed an enhanced optical absorption of UV-light at an absorption band centered on 375 nm. The improved optical and electrical properties were observed at an optimum relative concentration of 1:10. Under UV light illumination, the measured I-V characteristic of the prototype detector exhibited a considerable photocurrent increase of the ZnO-NP/GO nanocomposite compared to pristine ZnO nanostructure. These results can be promising for future enhanced UV- sensing applications.

ANN-based EMG classification for myoelectric control

This work presents a new neural network model related to EMG signal classification for myoelectric control. The aim of this work is to develop a more accurate method for pattern recognition and intention interpretation of five human forearm hand gestures: grasping, extension/flexion, and ulna/radial deviation. A sum of 750 signals that incorporated all the selected hand movements were acquired from five volunteers, preprocessed, and then time and time-series domain features were extracted. Classification model in MATLAB platform is then utilised for classification purposes. The neural network classifier achieved an average accuracy up to 96.7%. The system overall average validation parameters calculated for the five movements were: sensitivity of 96.9%, specificity of 99.0%, PPV of 96.9%, and NPV = 99.1%.

A Comparison Study on Machine Learning Algorithms Utilized in P300-based BCI

This study addresses Brain-Computer Interface (BCI) systems meant to permit communication for those who are severely locked-in. The current study attempts to evaluate and compare the efficiency of different translating algorithms. The setup used in this study detects the elicited P300 evoked potential in response to six different stimuli. Performance is evaluated in terms of error rates, bit-rates and runtimes for four different translating algorithms; Bayesian Linear Disciminant Analysis (BLDA), Linear Discriminant Analysis (LDA), Perceptron Batch (PB), and nonlinear Support Vector Machines (SVMs) were used to train the classifier whilst an N-fold cross validation procedure was used to test each algorithm. A communication channel based on Electroencephalography (EEG) is made possible using various machine learning algorithms and advanced pattern recognition techniques. All algorithms converged to 100% accuracy for seven of the eight subjects. While all methods obtained fairly good results, BLDA and PB were superior in terms of runtimes, where the average runtimes for BLDA and PB were 13 ± 2 and 15.6 ± 6 seconds, respectively. In terms of bit-rates, BLDA obtained the highest average value (22 ± 12 bits/minute), where the average bit-rate for all subjects, all sessions, and all algorithms was 18.76 ± 10 bits/minute.

Direct electrochemical bacterial sensor using ZnO nanorods disposable electrode

Purpose This paper aims to report a prototype of a reliable method for rapid, sensitive bacterial detection by using a low-cost zinc oxide nanorods (ZnONRs)-based electrochemical sensor. Design/methodology/approach The ZnONRs have been grown on the surface of a disposable, miniaturized working electrode (WE) using the low-temperature hydrothermal technique. Scanning electron microscopy and energy dispersion spectroscopy have been performed to characterize the distribution as well as the chemical composition of the ZnONRs on the surface, respectively. Moreover, the cyclic voltammetry test has been implemented to assess the effect of the ZnONRs on the signal conductivity between −1 V and 1 V with a scan rate of 0.01 V/s. Likewise, the effect of using different bacterial concentrations in phosphate-buffered saline has been investigated. Findings The morphological characterization has shown a highly distributed ZnONR on the WE with uneven alignment. Also, the achieved response time was about 12 minutes and the lower limit of detection was approximately 103 CFU abbreviation for Colony Forming Unit/mL. Originality/value This paper illustrates an outcome of an experimental work on a ZnONRs-based electrochemical biosensor for direct detection of bacteria.

Synthesis and characterization of photocatalytic polyurethane and poly(methyl methacrylate) microcapsules for the controlled release of methotrexate

Abstract The aim of this work is to prepare ultraviolet (UV) triggered controlled release of compounds from microcapsule systems (MCs). Polyurethane (PU) and poly(methyl methacrylate) (PMMA) microcapsules were studied with/without chemical functionalization using photocatalytic TiO2 nanoparticles (NPs) on their surface. Once TiO2 nanoparticles are illuminated with UV light (λ = 370 nm), they initiate the rupture of the polymeric bonds of the microcapsule and subsequently initiate the encapsulated compound release, methotrexate (MTX) or rhodamine (Rh), in the present work. The size, polydispersity, charge, and yield of all MCs were measured, being the methotrexate drug release for all systems determined and compared with and without functionalization with TiO2 NPs, under dark, visible light and UV illumination in vitro. Finally, the Rh release was characterized using fluorescence microscopy. The TiO2 NPs size is around 10 nm, as determined by X-ray diffraction experiments. The PU MCs average size is around 60 µm, its electric charge +3.11 mV and yield around 85%. As for the PMMA MCs, the average size is around 280 µm, its electric charge −7.2 mV and yield around 25% and 30% for both MTX and Rh, respectively. In general, adding TiO2 NPs or the encapsulated products to the MCs does not affect the size but functionalization with TiO2 NPs lowers the electric charge. Microcapsules functionalized with TiO2 nanoparticles and irradiated with UV light presented the highest release of MTX and Rh. All other samples showed lower drug release levels when studied under the same conditions.