Volume 67, Issue 3

Epilepsy is a neurological disorder requiring specialists to scrutinize medical data at diagnosis. Diagnosis stage is both time consuming and challenging, requiring expertise in detection of epileptic seizures from multi-channel noisy EEG data. It is crucial that EEG signals be automatically classified in order to help experts detect epileptic seizures correctly. In this study, a novel hybrid deep learning and SVM technique is employed on a restructured EEG data. EEG signals were transformed into a two-dimensional image sequence. Clough–Tocher technique is employed for interpolation of the values obtained from the electrodes placed on the skull during EEG measurements in order to estimate the signal strength in the missing places over the picture. After the parameters in the deep learning architecture were optimized on the validation data, it is observed that the proposed technique’s performance for classifying epilepsy moments over EEG signals demonstrated unmatched performance. This study fills a gap in the literature in terms of demonstrating a superior performance in automatic detection of epileptic episodes on a benchmark EEG data set and takes a substantial leap towards fully automated detection of epileptic disorders.

Many researchers have measured the differences in electroencephalography (EEG) while viewing 2D and 3D movies to uncover the neuromechanism underlying distinct viewing experiences. Using whole-brain network analyses of scalp EEG, our previous study reported that beta and gamma bands presented higher global efficiencies while viewing 3D movies. However, scalp EEG is influenced by volume conduction, not allowing inference from a neuroanatomy perspective; thus, source reconstruction techniques are recommended. This paper is the first to measure the differences in the frontal-occipital networks in EEG source space during 2D and 3D movie viewing. EEG recordings from 40 subjects were performed during 2D and 3D movie viewing. We constructed frontal-occipital networks of alpha, beta, and gamma bands in EEG source space and analyzed network efficiencies. We found that the beta band exhibited higher global efficiency in 3D movie viewing than in 2D movie viewing; however, the alpha global efficiency was not statistically significant. In addition, a support vector machine (SVM) classifier, taking functional connectivities as classification features, was built to identify whether the frontal-occipital networks contain patterns that could distinguish 2D and 3D movie viewing. Using the 6 most important functional connectivity features of the beta band, we obtained the best accuracy of 0.933. Our findings shed light on uncovering the neuromechanism underlying distinct experiences while viewing 2D and 3D movies.

Functional near-infrared spectroscopy (fNIRS) is a type of functional brain imaging. Brain-computer interfaces (BCIs) based on fNIRS have recently been implemented. Most existing fNIRS-BCI studies have involved off-line analyses, but few studies used online performance testing. Furthermore, existing online fNIRS-BCI experimental paradigms have not yet carried out studies using different imagined movements of the same side of a single limb. In the present study, a real-time fNIRS-BCI system was constructed to identify two imagined movements of the same side of a single limb (right forearm and right hand). Ten healthy subjects were recruited and fNIRS signal was collected and real-time analyzed with two imagined movements (leftward movement involving the right forearm and right-hand clenching). In addition to the mean and slope features of fNIRS signals, the correlation coefficient between fNIRS signals induced by different imagined actions was extracted. A support vector machine (SVM) was used to classify the imagined actions. The average accuracy of real-time classification of the two imagined movements was 72.25 ± 0.004%. The findings suggest that different imagined movements on the same side of a single limb can be recognized real-time based on fNIRS, which may help to further guide the practical application of online fNIRS-BCIs.

Extracting data from {Zhu, 2019 #5} daily life activities is important in biomechanical applications to define exact boundary conditions for the intended use-based applications. Although optoelectronic camera-marker based systems are used as gold standard tools for medical applications, due to line-of-sight problem, there is a need for wearable, affordable motion capture (MOCAP) systems. We investigate the potential use of a wearable inertial measurement unit (IMU) based-wearable MOCAP system for biomechanical applications. The in vitro proof of concept is provided for the full lower body consisting of hip, knee, and ankle joints via controlled single-plane anatomical range of motion (ROM) simulations using an electrical motor, while collecting data simultaneously via opto-electronic markers and IMU sensors. On 15 healthy volunteers the flexion-extension, abduction-adduction, internal-external rotation (ROM) values of hip and, the flexion – extension ROM values of the knee and ankle joints are calculated for both systems. The Bland-Altman graphs showed promising agreement both for in vitro and in vivo experiments. The maximum Root Mean Square Errors (RMSE) between the systems in vitro was 3.4° for hip and 5.9° for knee flexion motion in vivo , respectively. The gait data of the volunteers were assessed between the heel strike and toe off events to investigate the limits of agreement, calculating the population averages and standard deviation for both systems over the gait cycle. The maximum difference was for the ankle joint <6°. The results show that proposed system could be an option as an affordable-democratic solution.

Chronic obstructive pulmonary disease (COPD) and pneumonia are lethal pulmonary illnesses with equivocal nature of abnormal pulmonic acoustics. Using lung sound signals, the classification of pulmonary abnormalities is a difficult task. A standalone system was conceived for screening COPD and Pneumonia patients through signal processing and machine learning methodologies. The proposed system will assist practitioners and pulmonologists in the accurate classification of disease. In this research work, ICBHI’s and self-collected lung sound (LS) databases are used to investigate COPD and pneumonia patient. In this scheme, empirical mode decomposition (EMD), discrete wavelet transform (DWT), and analysis of variance (ANOVA) techniques are employed for segmentation, noise elimination, and feature selection, respectively. To overcome the inherent limitation of ICBHI’s LS database, the adaptive synthetic (ADASYN) sampling technique is used to eradicate class imbalance. Lung sound features are used to train fine Gaussian support vector machine (FG-SVM) for classification of COPD, pneumonia, and heathy healthy subjects. This machine learning scheme is implemented on low cost and portable Raspberry pi 3 model B+ (Cortex-A53 (ARMv8) 64-bit SoC @ 1.4 GHz through hardware-supported language. Resultant hardware is capable of screening COPD and pneumonia patients accurately and assist health professionals.

The functionality of smart glasses includes the possibility of wireless communication. For this purpose, WiFi or Bluetooth modules are integrated into the glasses. They emit electromagnetic radiation in the vicinity of the user’s head. This simulation study investigates the impact of varying positions, frequencies, and antenna types of the embedded WiFi or Bluetooth modules on different tissue types in the human head. The absorption of electromagnetic energy causes the main impact on the tissue in the head. This physical process is best described by the specific absorption rate SAR. To investigate the effects of position, frequency, and antenna type on the simulated SAR values multiple simulations have been carried out considering real-world applications of smart glasses. The results show that the type of antenna has little effect on the SAR values of the different tissues. The maximum regulated output powers explain the frequencies’ impact on the exposure. According to our findings, the greatest influence on the SAR values can be attributed to the placement of the antenna. Finally, our study reveals that positioning the antenna at the front side of the head is optimal for most tissues because of its maximal distance to the head tissues.

Bone marrow cell morphology has always been an important tool for the diagnosis of blood diseases. Still, it requires years of experience from a suitable person. Furthermore, the outcomes of their recognition are subjective and there is no objective quantitative standard. As a result, developing a deep learning automatic classification system for bone marrow cells is extremely important. However, typical classification machine learning systems only produce classification answers, and will not refuse to generate predictions when the prediction reliability is low. It will pose a big problem in some high-risk systems such as bone marrow cell recognition. This paper proposes a bone marrow cell classification method with rejected option (CMWRO) to classify 11 bone marrow cells. CMWRO is based on convolutional neural networks, ICP and SoftMax (CNN-ICP-SoftMax), containing a classifier with rejected option. When the rejected rate (RR) of tested samples is 0.3143, it can ensure that the precision, sensitivity, accuracy of the accepted samples reach 0.9921, 0.9917 and 0.9944 respectively. And the rejected samples will be handled by other ways, such as identified by doctors. Besides, the method has a good filtering effect on cell types that the classifier is not trained, such as abnormal cells and cells with less sample distribution. It can reach more than 82% in filtering efficiency. CMWRO improves the doctors’ trust in the results of accepted samples to a certain extent. They only need to carefully identify the samples that CMWRO refuses to recognize, and finally combines the two results. It can greatly improve the efficiency and accuracy of bone marrow cell recognition.