Search

Emotion assessment in stroke patients gives meaningful information to physiotherapists to identify the appropriate method for treatment. This study was aimed to classify the emotions of stroke patients by applying bispectrum features in electroencephalogram (EEG) signals. EEG signals from three groups of subjects, namely stroke patients with left brain damage (LBD), right brain damage (RBD), and normal control (NC), were analyzed for six different emotional states. The estimated bispectrum mapped in the contour plots show the different appearance of nonlinearity in the EEG signals for different emotional states. Bispectrum features were extracted from the alpha (8&ndash, 13) Hz, beta (13&ndash, 30) Hz and gamma (30&ndash, 49) Hz bands, respectively. The k-nearest neighbor (KNN) and probabilistic neural network (PNN) classifiers were used to classify the six emotions in LBD, RBD and NC. The bispectrum features showed statistical significance for all three groups. The beta frequency band was the best performing EEG frequency-sub band for emotion classification. The combination of alpha to gamma bands provides the highest classification accuracy in both KNN and PNN classifiers. Sadness emotion records the highest classification, which was 65.37% in LBD, 71.48% in RBD and 75.56% in NC groups.

The stroke patients perceive emotions differently with normal people due to emotional disturbances, the emotional impairment of the stroke patients can be effectively analyzed using the EEG signal. The EEG signal has been known as non-linear and the neuronal oscillation under different mental states can be observed by non-linear method. The non-linear analysis of different emotional states in the EEG signal was performed by using hurst exponent (HURST). In this study, the long-range temporal correlation (LRTC) was examined in the emotional EEG signal of stroke patients and normal control subjects. The estimation of the HURST was more statistically significant in normal group than the stroke groups. In this study, the statistical test on the HURST has shown a more significant different among the emotional states of normal subject compared to the stroke patients. Particularly, it was also found that the gamma frequency band in the emotional EEG has shown more statistically significant among the different emotional states.

Bone is made up of multiple components that are arranged hierarchically to give unique toughness to the bone. However, bone is still susceptible to the fracture. Various events might initiate the crack in the bone structure, such as falling from high place and vehicle accidence. Previous studies reported that the stress distribution in the bone was affected by the microstructure that presence in the bone such as interstitial matrix, cement line and osteon. The presence of osteon in the bone was reported to affect the microcrack propagation in the bone microstructure. However, there is still a missing link between the bone microstructure and bone fracture. This study was aimed to identify the ultimate stress region in the single osteon with different lamellae thickness and presence lacunae. Numerical models of single osteon were developed using Finite Element Method. Based on the stress distribution in the models, the ultimate stress region is predicted as a location of microcrack initiation. Finite element analysis of the single osteon model under compressive loading has been carried out. Based on the results, highest ultimate stress was found in the osteon model with lamellae thickness = 55.0 µm with no lacunae. These findings suggest that thickness of the lamellae did affect the stress distribution in the single osteon model. The results will be useful as the preliminary results for the future studies for bone damage and failure.

Screws in bone implant are widely used in medical technology which focus on stabilizing and supporting the broken bone in means of healing. Improvement in bone implant are required in order to ensure better healing process because some failures may happen due to the crack of the screw implant. Previous studies showed there are lack of investigation on screw crack detection in bone screw implant. Early detection of screw implant loosening is crucial for faster repairing and a healthy ready-to-operate. The purpose of this study is to investigate the received signal strength of electromagnetic field induction on implant screw by employing a single channel magnetic induction spectroscopy using flat spiral coil sensor. This study also to evaluate the screw implant under the action of electromagnetic field induction. The electromagnetic method is choose to be implement using the COMSOL Multiphysics’s simulation software. The magnetic induction spectroscopy technique was used in this study to evaluate the received signal strength data for the different screw crack and non-crack. In this study, a high-cycle fatigue test using the flat coil sensor was performed in order to monitor cracks in Titanium Ti-6Al-4V screw.. The results suggested the feasibility of the proposed electromagnetic induction spectroscopy.

Sudden cardiac death (SCD) is one of the cardiovascular diseases that lead to millions of deaths worldwide every year. The aim of the present work is to propose a method for reducing the mortality rate of the SCD patients by an early prediction for SCD from the ECG signal. Normal and SCD MIT databases were used in this research work. One minute segments of ECG signals were segmented from MIT databases where these segments are ten minutes before sudden cardiac arrest (SCA) onset. The collected raw ECG signals were subjected to filter to remove the noise and then normalized. A frequency-domain feature and time-domain features were extracted from the Q-T segment, Q-T interval, R-R interval and QRS interval. The features were normalized to improve the performance of the classifier. Artificial intelligence classifiers; namely, K-nearest neighbor (KNN) and linear discriminant analysis (LDA) were used separately on SCD and normal ECG signals. The highest classification accuracy obtained for KNN and LDA are 97% and 95.5% respectively.

Heart monitoring kits are only available for bedridden patients and the traditional heart monitoring kits have many wires that are obstacle patients’ mobility. Most of the existing heart monitoring kits can not detect heart diseases. Thus, the current study proposed a wireless heart monitoring kit to monitor patients with a heart abnormality. The proposed kit can detect and classify four arrhythmia types as well as normal ECG with high accuracy. The design and development of the wireless heart abnormality monitoring kit (WHAMK) in this research were divided into three stages. These stages are the development of an arrhythmias detection and classification method using artificial intelligence approach, design and implementation of the kit hardware, and design and coding of the kit software. Arrhythmias classification approach is divided into four stages, namely obtaining the electrocardiograph (ECG) signals, preprocessing, features extraction and classification. The features extraction method are based on statistical features. The library support vector machine (LIBSVM) was used to classify the ECG signals. The hardware of the kit is divided into two parts, namely ECG body sensor (EBS), and processing and displaying unit (PDU). EBS working on acquiring the ECG signal from patient's body. PDU working on processing the collected ECG signal, plotting it and detecting the arrhythmias. Arrhythmias classification approach was developed by using statistical features and LIBSVM. They were implemented in the software of the kit to enable it to detect the arrhythmias in the real-time and fully automatically. The kit can detect and classify four arrhythmia types as well as normal sinus rhythm (NSR). These types of arrhythmia are premature atrial contraction (PAC), premature ventricles contraction (PVC), Bradycardia and Tachycardia. The proposed kit gave a good accuracy for detecting and classifying Arrhythmia with the overall accuracy of 96.2%.

The stroke patients often suffered from emotional disturbances, and this leads to perceive emotions differently than normal control subjects; the emotional impairment of the stroke patients can be effectively analyzed using EEG signal. The EEG signal has been known to have non-Gaussian properties, and the non-Gaussianity characteristics of the EEG differ under different emotional states. The analysis of non-Gaussianity in EEG signal was performed by using higher-order statistics measures such as the skewness and kurtosis. In this study, the non-Gaussianity was examined in the emotional EEG signal of stroke patients and normal control subjects. The estimation of the emotional EEG distribution from the results was symmetrically non-Gaussian for both stroke and normal groups. Particularly, it was found that the normal subjects have more non-Gaussian EEG distribution than the stroke patients.

Emotion is regulated by the interconnection of the brain network. Each emotion is a different mental state, where the neuronal oscillations differ for different emotions. The EEG signal has been a useful method to analyze emotions. Furthermore, the neuronal oscillation can be observed by analyzing the scaling properties of EEG signal. In this study, the EEG signal was used as the source of emotions of stroke patients and normal subject. The Hurst Exponent (HURST) was estimated from the EEG signal to analyze the autocorrelation of the signal. The estimated HURST indicated that all emotions in this work were exhibit positive correlation in the time scale, also the neuronal oscillation for every emotions experimented were statistically different.

The machine learning algorithms can be applied in many classification problems including the clinical studies. In the stroke emotion analysis, the machine learning is used to analyze the emotion of stroke patients and normal people. The K-Nearest Neighbor (KNN) classifier relies on the distance metric to calculate the nearest class for classification. The aim of this study is to compare the performances of different distance metrics apply on the classification of emotional electroencephalogram (EEG) between stroke and normal people. The Detrended Fluctuation Analysis (DFA) feature was extracted from the EEG signal of both classes and KNN was applied with different distance metrics for comparison. The results showed that the City Block distance metric performs the best among all. Moreover, the lower values of nearest neighbor were required to provide high classification result. The results from this study showed that the performance of the KNN classification was affected by the distance metric used.

The gas chromatography mass spectrometry (GCMS) with combination of Solid Phase Micro-extraction (SPME) was used to study the volatile organic compounds (VOCs) which emitted by the in-vitro cultured human cells and compared with documented volatile biomarker of lung cancer. For this purpose, the lung cancer cell (A549) and non-cancerous lung cell (WI38VA13) were cultured in identical growth medium, concurrently. The VOCs in the headspace of the cell cultures and the blank growth media (reference sample) were collected directly from the culture flask using SPME for 15minutes. The results show that two different volatile metabolites were screened out between A549 cells and Wi38VA13 cells. A549 cell found to emit 2 noticeable VOC which are decane and heneicosane. While for WI38VA13, the VOCs released were 1-Heptanol and heptadecane. The acquired VOCs were compared with the previous studies. The findings in this work conclude that the specific VOC of cells can be act as their odour signature and can be used to provide non-invasively screening of lung cancer using gas array sensor devices.

Bone implant is a promising technique to heal the fracture site where it focusing to stabilize and support the bone. Improvement in bone implant are required in order to ensure better healing process because some failures may happen due to the loss of implant stability. Previous studies showed there are lack of investigation on bone implant. Early detection of screw implant loosening is crucial for faster repairing and a healthy ready-to-operate. The purpose of this study is to investigate the signal strength of electromagnetic field induction on human bone by employing a single channel magnetic induction spectroscopy using flat spiral coil sensor. This study also to evaluate the various type of coil sensitivity of the magnetic induction spectroscopy on femur bone. The electromagnetic field induction will be analyse using the COMSOL Multiphysics simulation software to collect the data of received signal strength. The promising experimental results suggested the feasibility of the proposed electromagnetic induction spectroscopy.

Array based gas sensor technology namely Electronic Nose (E-nose) now offers the potential of a rapid and robust analytical approach to odor measurement for medical use. Wounds become infected when a microorganism which is bacteria from the environment or patients body enters the open wound and multiply. The conventional method consumes more time to detect the bacteria growth. However, by using this E-Nose, the bacteria can be detected and classified according to their volatile organic compound (VOC) in shorter time. Readings were taken from headspace of samples by manually introducing the portable e-nose system into a special container that containing a volume of bacteria in suspension. The data will be processed by using statistical analysis which is Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA) methods. The most common bacteria in diabetic foot are Staphylococcus aureus, Escherchia coli, Pseudomonas aeruginosa, and many more.

In this experiment, three different cell cultures (A549, WI38VA13 and MCF7) and blank medium (without cells) as a control were used. The electronic nose (E-Nose) was used to sniff the headspace of cultured cells and the data were recorded. After data pre-processing, two different features were extracted by taking into consideration of both steady state and the transient information. The extracted data are then being processed by multivariate analysis, Linear Discriminant Analysis (LDA) to provide visualization of the clustering vector information in multi-sensor space. The Probabilistic Neural Network (PNN) classifier was used to test the performance of the E-Nose on determining the volatile organic compounds (VOCs) of lung cancer cell line. The LDA data projection was able to differentiate between the lung cancer cell samples and other samples (breast cancer, normal cell and blank medium) effectively. The features extracted from the steady state response reached 100% of classification rate while the tran...

This paper proposes a preliminary investigation on the volatile production patterns generated from three sets of in-vitro cancerous cell samples of headspace that contains volatile organic compounds using the electronic nose system. A commercialized electronic nose consisting of 32 conducting polymer sensors (Cyranose 320) is used to analyze the three classes of signals which are lung cancer cells grown in media, breast cancer cells grown in media and the blank media (without cells). Neural Network (PNN) based classification technique is applied to investigate the performance of an electronic nose (E-nose) system for cancerous lung cell classification.

Lack of effective tools to diagnose lung cancer at an early stage has caused high mortality in cancer patients especially in lung cancer patients. Electronic nose (E-Nose) technology is believed to offer non-invasive, rapid and reliable analytic approach by measuring the odour released from cancer to assist medical diagnosis. In this work, using a commercial E-nose (Cyranose-320), we aimed to detect the volatile organic compounds (VOCs) emitted by different types of cancerous cells. The lung cancer cell (A549) and breast cancer cell (MCF-7) were used for this study. Both cells were cultured using Dulbecco's Modified Eagle's Medium (DMEM) with 10% of Fetal Bovine Serum (FBS) and incubated for three days. The static headspace of cell cultures and blank medium were directly sniffed by Cyranose-320. The preliminary results from this study showed that, the E-nose is able to detect and distinguish the presence of VOCs in cancerous cells with accuracy of 100% using LDA. To this end, the VOCs emitted from cancerous cells can potentially used as biomarker.

The existing clinical diagnostics for lung cancer are mostly based on physics, biochemical and imaging techniques. The use of electronic nose (E-nose) system to detect volatile organic compounds (VOCs) in lung cancer cells or exhaled air breath of a patient is expected to be able to classify different volatile components leading to the diagnosis of lung cancer at an early stage. In this preliminary study, a commercialized E-nose consists of an array of 32 conducting polymer sensors (Cyranose 320) was used to detect and discriminate the VOCs emitted from cancer cells which is A549 (lung cancer cell line) between MCF7 (breast cancer cell line). Blank medium was used to obtain controlled value. The VOC profiles of each sample were characterized using a classification algorithm called k-Nearest Neighbors (KNN) to test and benchmark the performance of Enose in identifying VOCs of lung cancer from different cancer cell lines. The E-nose with KNN classifier was able to classify the VOCs of lung cancer cell with over 90% successful accuracy in 30 seconds. This study can conclude that e-nose is capable to rapidly discriminate volatile organic compounds of cancerous cells which generated during cell growth.

Foot infections may lead to serious complications if failed to detect at an early stage; especially for diabetic patients. It is necessary to develop an easy and reliable method to identify and classify the causative bacteria from the wound to assist health care practitioners. Therefore, this study proposed an alternative to the conventional technique by using an electronic nose with 32 matrices of non-specific conducting polymer sensors known as Cyranose320. A novel odour detection method is developed and targeted for microbial bacteria causing infection on diabetic foot using direct injection of static headspace. The bacteria are obtained from the clinical specimens by swabbing technique and isolated in a blood agar medium to verify the performance of the bacterial specialized medium. Various classification algorithm techniques proved that each bacteria produce certain characteristic of odour and can be used as a surrogate bio-marker. Thus, preliminary results from this study show that the electronic nose is able to identify and classify the presence of causative bacteria with high success rate of over 90% in diabetic foot infection.

Recent survey has pointed out that, by 2030, almost 23.6 million people will die from Cardiovascular Diseases (CVD), mainly from heart disease and stroke. These are projected to remain the single leading causes of death. One of CVD risk factors is atherosclerosis which can be predicted by myocardial ischemia detection; where this condition is caused by the lack of oxygen and nutrients to the contractile cells [3]. Ischemia changes of the ECG frequently affect the entire wave shape of ST-T complex, thus are inadequately described by isolated feature such as ST slope, ST-J amplitude and positive and negative amplitude of the T wave. In order to identify the abnormal CVDs due to the traditional risk factor such as tobacco smoking, there are several types of classifier have been used in the previous research works such as Artificial Neural Network (ANN)[21], Fuzzy Logic system[22], Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM). Most of the researchers used SVM and Fuzzy Logic system in their studies [11][23].

Background Effective management of patients with diabetic foot infection is a crucial concern. A delay in prescribing appropriate antimicrobial agent can lead to amputation or life threatening complications. Thus, this electronic nose (e-nose) technique will provide a diagnostic tool that will allow for rapid and accurate identification of a pathogen. Results This study investigates the performance of e-nose technique performing direct measurement of static headspace with algorithm and data interpretations which was validated by Headspace SPME-GC-MS, to determine the causative bacteria responsible for diabetic foot infection. The study was proposed to complement the wound swabbing method for bacterial culture and to serve as a rapid screening tool for bacteria species identification. The investigation focused on both single and poly microbial subjected to different agar media cultures. A multi-class technique was applied including statistical approaches such as Support Vector Machine (SVM), K Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA) as well as neural networks called Probability Neural Network (PNN). Most of classifiers successfully identified poly and single microbial species with up to 90% accuracy. Conclusions The results obtained from this study showed that the e-nose was able to identify and differentiate between poly and single microbial species comparable to the conventional clinical technique. It also indicates that even though poly and single bacterial species in different agar solution emit different headspace volatiles, they can still be discriminated and identified using multivariate techniques.