MyMedR

Displaying all 14 publications

Abstract:

Sort:

Fulltext Cantilever Beam with a Single Fiber Bragg Grating to Measure Temperature and Transversal Force Simultaneously

Abushagur AAG, Arsad N, Bakar AAA

Sensors (Basel), 2021 Mar 12;21(6).
PMID: 33809028 DOI: 10.3390/s21062002

This work investigates a new interrogation method of a fiber Bragg grating (FBG) sensor based on longer and shorter wavelengths to distinguish between transversal forces and temperature variations. Calibration experiments were carried out to examine the sensor's repeatability in response to the transversal forces and temperature changes. An automated calibration system was developed for the sensor's characterization, calibration, and repeatability testing. Experimental results showed that the FBG sensor can provide sensor repeatability of 13.21 pm and 17.015 pm for longer and shorter wavelengths, respectively. The obtained calibration coefficients expressed in the linear model using the matrix enabled the sensor to provide accurate predictions for both measurements. Analysis of the calibration and experiment results implied improvements for future work. Overall, the new interrogation method demonstrated the potential to employ the FBG sensing technique where discrimination between two/three measurands is needed.
Fulltext Anaesthetists' nightmare: masseter spasm after induction in an undiagnosed case of myotonia congenita

Looi I, Bakar AAA, Lim CH, Khoo TH, Samuel PE

Med J Malaysia, 2008 Dec;63(5):423-5.
PMID: 19803309

We report an undiagnosed case of myotonia congenita in a 24-year-old previously healthy primigravida, who developed life threatening masseter spasm following a standard dose of intravenous suxamethonium for induction of anaesthesia. Neither the patient nor the anaesthetist was aware of the diagnosis before this potentially lethal complication occurred.
Fulltext Binding Affinity of a Highly Sensitive Au/Ag/Au/Chitosan-Graphene Oxide Sensor Based on Direct Detection of Pb2+and Hg2+Ions

Kamaruddin NH, Bakar AAA, Mobarak NN, Zan MSD, Arsad N

Sensors (Basel), 2017 Oct 06;17(10).
PMID: 28984826 DOI: 10.3390/s17102277

The study of binding affinity is essential in surface plasmon resonance (SPR) sensing because it allows researchers to quantify the affinity between the analyte and immobilised ligands of an SPR sensor. In this study, we demonstrate the derivation of the binding affinity constant, K, for Pb2+and Hg2+ions according to their SPR response using a gold/silver/gold/chitosan-graphene oxide (Au/Ag/Au/CS-GO) sensor for the concentration range of 0.1-5 ppm. The higher affinity of Pb2+to binding with the CS-GO sensor explains the outstanding sensitivity of 2.05 °ppm-1against 1.66 °ppm-1of Hg2+. The maximum signal-to-noise ratio (SNR) upon detection of Pb2+is 1.53, and exceeds the suggested logical criterion of an SNR. The Au/Ag/Au/CS-GO SPR sensor also exhibits excellent repeatability in Pb2+due to the strong bond between its functional groups and this cation. The adsorption data of Pb2+and Hg2+on the CS-GO sensor fits well with the Langmuir isotherm model where the affinity constant, K, of Pb2+and Hg2+ions is computed. The affinity of Pb2+ions to the Au/Ag/Au/CS-GO sensor is significantly higher than that of Hg2+based on the value of K, 7 × 10⁵ M-1and 4 × 10⁵ M-1, respectively. The higher shift in SPR angles due to Pb2+and Hg2+compared to Cr3+, Cu2+and Zn2+ions also reveals the greater affinity of the CS-GO SPR sensor to them, thus supporting the rationale for obtaining K for these two heavy metals. This study provides a better understanding on the sensing performance of such sensors in detecting heavy metal ions.
Fulltext Sensitivity Enhancement of Pb(II) Ion Detection in Rivers Using SPR-Based Ag Metallic Layer Coated with Chitosan-Graphene Oxide Nanocomposite

Lokman NF, Azeman NH, Suja F, Arsad N, Bakar AAA

Sensors (Basel), 2019 Nov 25;19(23).
PMID: 31775327 DOI: 10.3390/s19235159

The detection of Pb(II) ions in a river using the surface plasmon resonance (SPR)-based silver (Ag) thin film technique was successfully developed. Chitosan-graphene oxide (CS-GO) was coated on top of the Ag thin film surface and acted as the active sensing layer for Pb(II) ion detection. CS-GO was synthesized and characterized, and the physicochemical properties of this material were studied prior to integration with the SPR. In X-ray photoelectron spectroscopy (XPS), the appearance of the C=O, C-O, and O-H functional groups at 531.2 eV and 532.5 eV, respectively, confirms the success of CS-GO nanocomposite synthesis. A higher surface roughness of 31.04 nm was observed under atomic force microscopy (AFM) analysis for Ag/CS-GO thin film. The enhancement in thin film roughness indicates that more adsorption sites are available for Pb(II) ion binding. The SPR performance shows a good sensor sensitivity for Ag/CS-GO with 1.38° ppm-1 ranging from 0.01 to 5.00 ppm of standard Pb(II) solutions. At lower concentrations, a better detection accuracy was shown by SPR using Ag/CS-GO thin film compared to Ag/CS thin film. The SPR performance using Ag/CS-GO thin film was further evaluated with real water samples collected from rivers. The results are in agreement with those of standard Pb(II) ion solution, which were obtained at incidence angles of 80.00° and 81.11° for local and foreign rivers, respectively.
Hybrid ensemble-based machine learning model for predicting phosphorus concentrations in hydroponic solution

Sulaiman R, Azeman NH, Mokhtar MHH, Mobarak NN, Abu Bakar MH, Bakar AAA

Spectrochim Acta A Mol Biomol Spectrosc, 2024 Jan 05;304:123327.
PMID: 37708761 DOI: 10.1016/j.saa.2023.123327

Accurate, label-free, and rapid methods for measuring phosphorus concentrations are essential in a hydroponic system, as excessive or insufficient phosphorus levels can adversely affect plant growth, human health, and environmental sustainability. In this study, we demonstrate the advantages of hybrid machine learning models compared to single machine learning models in predicting phosphorus concentration based on the absorbance dataset. Three machine learning classifiers- Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)- were employed as bases for single and hybrid machine learning models. Three ensemble techniques (voting, bagging, and stacking) were used to hybridize the classifiers. Among the single models, KNN demonstrated the fastest computational time of 18.07 s, while SVM achieved the highest accuracy of 99.6%. The hybrid SVM/KNN model using a voting classifier showed a significant increase in accuracy for KNN with only a slight increase in computational time. Bagging techniques increased the accuracy but at a longer computational time. The stacking technique, which combined SVM, KNN, and RF, achieved the highest accuracy of 99.73% with a short computational time of 36.18 s compared to the bagging and voting technique. This study demonstrates that the machine learning method can effectively distinguish phosphorus concentrations. In contrast, hybrid machine learning techniques can improve accuracy for predicting phosphorus without using labels, despite requiring longer computational time.
Fulltext Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification

Haque F, Bin Ibne Reaz M, Chowdhury MEH, Srivastava G, Hamid Md Ali S, Bakar AAA, et al.

Diagnostics (Basel), 2021 Apr 28;11(5).
PMID: 33925190 DOI: 10.3390/diagnostics11050801

BACKGROUND: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature.
METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms.
RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs.
CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.
Fulltext Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review

Thangarajoo RG, Reaz MBI, Srivastava G, Haque F, Ali SHM, Bakar AAA, et al.

Sensors (Basel), 2021 Dec 20;21(24).
PMID: 34960577 DOI: 10.3390/s21248485

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of '3N' biosignals-nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result.
Fulltext Density estimation of SARS-CoV2 spike proteins using super pixels segmentation technique

Taha BA, Al-Jubouri Q, Al Mashhadany Y, Hafiz Mokhtar MH, Bin Zan MSD, Bakar AAA, et al.

Appl Soft Comput, 2023 May;138:110210.
PMID: 36960080 DOI: 10.1016/j.asoc.2023.110210

The worldwide outbreak of COVID-19 disease was caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV 2). The existence of spike proteins, which allow these viruses to infect host cells, is one of the distinctive biological traits of various prior viruses. As a result, the process by which these viruses infect people is largely dependent on spike proteins. The density of SARS-CoV-2 spike proteins must be estimated to better understand and develop diagnostics and vaccines against the COVID-19 pandemic. CT scans and X-rays have three issues: frosted glass, consolidation, and strange roadway layouts. Each of these issues can be graded separately or together. Although CT scan is sensitive to COVID-19, it is not very specific. Therefore, patients who obtain these results should have more comprehensive clinical and laboratory tests to rule out other probable reasons. This work collected 586 SARS-CoV 2 transmission electron microscopy (TEM) images from open source for density estimation of virus spike proteins through a segmentation approach based on the superpixel technique. As a result, the spike density means of SARS-CoV2 and SARS-CoV were 21,97 nm and 22,45 nm, respectively. Furthermore, in the future, we aim to include this model in an intelligent system to enhance the accuracy of viral detection and classification. Moreover, we can remotely connect hospitals and public sites to conduct environmental hazard assessments and data collection.
Fulltext Machine Learning-Based Diabetic Neuropathy and Previous Foot Ulceration Patients Detection Using Electromyography and Ground Reaction Forces during Gait

Haque F, Reaz MBI, Chowdhury MEH, Ezeddin M, Kiranyaz S, Alhatou M, et al.

Sensors (Basel), 2022 May 05;22(9).
PMID: 35591196 DOI: 10.3390/s22093507

Diabetic neuropathy (DN) is one of the prevalent forms of neuropathy that involves alterations in biomechanical changes in the human gait. Diabetic foot ulceration (DFU) is one of the pervasive types of complications that arise due to DN. In the literature, for the last 50 years, researchers have been trying to observe the biomechanical changes due to DN and DFU by studying muscle electromyography (EMG) and ground reaction forces (GRF). However, the literature is contradictory. In such a scenario, we propose using Machine learning techniques to identify DN and DFU patients by using EMG and GRF data. We collected a dataset from the literature which involves three patient groups: Control (n = 6), DN (n = 6), and previous history of DFU (n = 9) and collected three lower limb muscles EMG (tibialis anterior (TA), vastus lateralis (VL), gastrocnemius lateralis (GL)), and three GRF components (GRFx, GRFy, and GRFz). Raw EMG and GRF signals were preprocessed, and different feature extraction techniques were applied to extract the best features from the signals. The extracted feature list was ranked using four different feature ranking techniques, and highly correlated features were removed. In this study, we considered different combinations of muscles and GRF components to find the best performing feature list for the identification of DN and DFU. We trained eight different conventional ML models: Discriminant analysis classifier (DAC), Ensemble classification model (ECM), Kernel classification model (KCM), k-nearest neighbor model (KNN), Linear classification model (LCM), Naive Bayes classifier (NBC), Support vector machine classifier (SVM), and Binary decision classification tree (BDC), to find the best-performing algorithm and optimized that model. We trained the optimized the ML algorithm for different combinations of muscles and GRF component features, and the performance matrix was evaluated. Our study found the KNN algorithm performed well in identifying DN and DFU, and we optimized it before training. We found the best accuracy of 96.18% for EMG analysis using the top 22 features from the chi-square feature ranking technique for features from GL and VL muscles combined. In the GRF analysis, the model showed 98.68% accuracy using the top 7 features from the Feature selection using neighborhood component analysis for the feature combinations from the GRFx-GRFz signal. In conclusion, our study has shown a potential solution for ML application in DN and DFU patient identification using EMG and GRF parameters. With careful signal preprocessing with strategic feature extraction from the biomechanical parameters, optimization of the ML model can provide a potential solution in the diagnosis and stratification of DN and DFU patients from the EMG and GRF signals.
Fulltext High stability resistive switching mechanism of a screen-printed electrode based on BOBZBT2 organic pentamer for creatinine detection

Khushaini MAA, Azeman NH, Ismail AG, Teh CH, Salleh MM, Bakar AAA, et al.

Sci Rep, 2021 Dec 07;11(1):23519.
PMID: 34876656 DOI: 10.1038/s41598-021-03046-9

The resistive switching (RS) mechanism is resulted from the formation and dissolution of a conductive filament due to the electrochemical redox-reactions and can be identified with a pinched hysteresis loop on the I-V characteristic curve. In this work, the RS behaviour was demonstrated using a screen-printed electrode (SPE) and was utilized for creatinine sensing application. The working electrode (WE) of the SPE has been modified with a novel small organic molecule, 1,4-bis[2-(5-thiophene-2-yl)-1-benzothiopene]-2,5-dioctyloxybenzene (BOBzBT2). Its stability at room temperature and the presence of thiophene monomers were exploited to facilitate the cation transport and thus, affecting the high resistive state (HRS) and low resistive state (LRS) of the electrochemical cell. The sensor works based on the interference imposed by the interaction between the creatinine molecule and the radical cation of BOBzBT2 to the conductive filament during the Cyclic Voltammetry (CV) measurement. Different concentrations of BOBzBT2 dilution were evaluated using various concentrations of non-clinical creatinine samples to identify the optimised setup of the sensor. Enhanced sensitivity of the sensor was observed at a high concentration of BOBzBT2 over creatinine concentration between 0.4 and 1.6 mg dL-1-corresponding to the normal range of a healthy individual.
Fulltext A machine learning model for early detection of diabetic foot using thermogram images

Khandakar A, Chowdhury MEH, Ibne Reaz MB, Md Ali SH, Hasan MA, Kiranyaz S, et al.

Comput Biol Med, 2021 10;137:104838.
PMID: 34534794 DOI: 10.1016/j.compbiomed.2021.104838

Diabetes foot ulceration (DFU) and amputation are a cause of significant morbidity. The prevention of DFU may be achieved by the identification of patients at risk of DFU and the institution of preventative measures through education and offloading. Several studies have reported that thermogram images may help to detect an increase in plantar temperature prior to DFU. However, the distribution of plantar temperature may be heterogeneous, making it difficult to quantify and utilize to predict outcomes. We have compared a machine learning-based scoring technique with feature selection and optimization techniques and learning classifiers to several state-of-the-art Convolutional Neural Networks (CNNs) on foot thermogram images and propose a robust solution to identify the diabetic foot. A comparatively shallow CNN model, MobilenetV2 achieved an F1 score of ∼95% for a two-feet thermogram image-based classification and the AdaBoost Classifier used 10 features and achieved an F1 score of 97%. A comparison of the inference time for the best-performing networks confirmed that the proposed algorithm can be deployed as a smartphone application to allow the user to monitor the progression of the DFU in a home setting.
Fulltext Localized Surface Plasmon Resonance Decorated with Carbon Quantum Dots and Triangular Ag Nanoparticles for Chlorophyll Detection

Nazri NAA, Azeman NH, Bakar MHA, Mobarak NN, Luo Y, Arsad N, et al.

Nanomaterials (Basel), 2021 Dec 23;12(1).
PMID: 35009983 DOI: 10.3390/nano12010035

This paper demonstrates carbon quantum dots (CQDs) with triangular silver nanoparticles (AgNPs) as the sensing materials of localized surface plasmon resonance (LSPR) sensors for chlorophyll detection. The CQDs and AgNPs were prepared by a one-step hydrothermal process and a direct chemical reduction process, respectively. FTIR analysis shows that a CQD consists of NH2, OH, and COOH functional groups. The appearance of C=O and NH2 at 399.5 eV and 529.6 eV in XPS analysis indicates that functional groups are available for adsorption sites for chlorophyll interaction. A AgNP-CQD composite was coated on the glass slide surface using (3-aminopropyl) triethoxysilane (APTES) as a coupling agent and acted as the active sensing layer for chlorophyll detection. In LSPR sensing, the linear response detection for AgNP-CQD demonstrates R2 = 0.9581 and a sensitivity of 0.80 nm ppm-1, with a detection limit of 4.71 ppm ranging from 0.2 to 10.0 ppm. Meanwhile, a AgNP shows a linear response of R2 = 0.1541 and a sensitivity of 0.25 nm ppm-1, with the detection limit of 52.76 ppm upon exposure to chlorophyll. Based on these results, the AgNP-CQD composite shows a better linearity response and a higher sensitivity than bare AgNPs when exposed to chlorophyll, highlighting the potential of AgNP-CQD as a sensing material in this study.
Fulltext A Machine Learning-Based Severity Prediction Tool for the Michigan Neuropathy Screening Instrument

Haque F, Reaz MBI, Chowdhury MEH, Shapiai MIB, Malik RA, Alhatou M, et al.

Diagnostics (Basel), 2023 Jan 11;13(2).
PMID: 36673074 DOI: 10.3390/diagnostics13020264

Diabetic sensorimotor polyneuropathy (DSPN) is a serious long-term complication of diabetes, which may lead to foot ulceration and amputation. Among the screening tools for DSPN, the Michigan neuropathy screening instrument (MNSI) is frequently deployed, but it lacks a straightforward rating of severity. A DSPN severity grading system has been built and simulated for the MNSI, utilizing longitudinal data captured over 19 years from the Epidemiology of Diabetes Interventions and Complications (EDIC) trial. Machine learning algorithms were used to establish the MNSI factors and patient outcomes to characterise the features with the best ability to detect DSPN severity. A nomogram based on multivariable logistic regression was designed, developed and validated. The extra tree model was applied to identify the top seven ranked MNSI features that identified DSPN, namely vibration perception (R), 10-gm filament, previous diabetic neuropathy, vibration perception (L), presence of callus, deformities and fissure. The nomogram's area under the curve (AUC) was 0.9421 and 0.946 for the internal and external datasets, respectively. The probability of DSPN was predicted from the nomogram and a DSPN severity grading system for MNSI was created using the probability score. An independent dataset was used to validate the model's performance. The patients were divided into four different severity levels, i.e., absent, mild, moderate, and severe, with cut-off values of 10.50, 12.70 and 15.00 for a DSPN probability of less than 50, 75 and 100%, respectively. We provide an easy-to-use, straightforward and reproducible approach to determine prognosis in patients with DSPN.
Fulltext Succinyl-κ-carrageenan Silver Nanotriangles Composite for Ammonium Localized Surface Plasmon Resonance Sensor

Abu Bakar MH, Azeman NH, Mobarak NN, Ahmad Nazri NA, Tengku Abdul Aziz TH, Md Zain AR, et al.

Polymers (Basel), 2022 Jan 14;14(2).
PMID: 35054734 DOI: 10.3390/polym14020329

This research investigates the physicochemical properties of biopolymer succinyl-κ-carrageenan as a potential sensing material for NH4+ Localized Surface Plasmon Resonance (LSPR) sensor. Succinyl-κ-carrageenan was synthesised by reacting κ-carrageenan with succinic anhydride. FESEM analysis shows succinyl-κ-carrageenan has an even and featureless topology compared to its pristine form. Succinyl-κ-carrageenan was composited with silver nanoparticles (AgNP) as LSPR sensing material. AFM analysis shows that AgNP-Succinyl-κ-carrageenan was rougher than AgNP-Succinyl-κ-carrageenan, indicating an increase in density of electronegative atom from oxygen compared to pristine κ-carrageenan. The sensitivity of AgNP-Succinyl-κ-carrageenan LSPR is higher than AgNP-κ-carrageenan LSPR. The reported LOD and LOQ of AgNP-Succinyl-κ-carrageenan LSPR are 0.5964 and 2.7192 ppm, respectively. Thus, AgNP-Succinyl-κ-carrageenan LSPR has a higher performance than AgNP-κ-carrageenan LSPR, broader detection range than the conventional method and high selectivity toward NH4+. Interaction mechanism studies show the adsorption of NH4+ on κ-carrageenan and succinyl-κ-carrageenan were through multilayer and chemisorption process that follows Freundlich and pseudo-second-order kinetic model.

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links