MyMedR

Displaying publications 21 - 40 of 155 in total

Abstract:

Sort:

Fulltext Optimal feature selection using novel flamingo search algorithm for classification of COVID-19 patients from clinical text

Mahdi AY, Yuhaniz SS

Math Biosci Eng, 2023 Jan 11;20(3):5268-5297.
PMID: 36896545 DOI: 10.3934/mbe.2023244

Though several AI-based models have been established for COVID-19 diagnosis, the machine-based diagnostic gap is still ongoing, making further efforts to combat this epidemic imperative. So, we tried to create a new feature selection (FS) method because of the persistent need for a reliable system to choose features and to develop a model to predict the COVID-19 virus from clinical texts. This study employs a newly developed methodology inspired by the flamingo's behavior to find a near-ideal feature subset for accurate diagnosis of COVID-19 patients. The best features are selected using a two-stage. In the first stage, we implemented a term weighting technique, which that is RTF-C-IEF, to quantify the significance of the features extracted. The second stage involves using a newly developed feature selection approach called the improved binary flamingo search algorithm (IBFSA), which chooses the most important and relevant features for COVID-19 patients. The proposed multi-strategy improvement process is at the heart of this study to improve the search algorithm. The primary objective is to broaden the algorithm's capabilities by increasing diversity and support exploring the algorithm search space. Additionally, a binary mechanism was used to improve the performance of traditional FSA to make it appropriate for binary FS issues. Two datasets, totaling 3053 and 1446 cases, were used to evaluate the suggested model based on the Support Vector Machine (SVM) and other classifiers. The results showed that IBFSA has the best performance compared to numerous previous swarm algorithms. It was noted, that the number of feature subsets that were chosen was also drastically reduced by 88% and obtained the best global optimal features.

Matched MeSH terms: Support Vector Machine
Fulltext Improved accuracy and less fault prediction errors via modified sequential minimal optimization algorithm

Asim Shahid M, Alam MM, Mohd Su'ud M

PLoS One, 2023;18(4):e0284209.
PMID: 37053173 DOI: 10.1371/journal.pone.0284209

The benefits and opportunities offered by cloud computing are among the fastest-growing technologies in the computer industry. Additionally, it addresses the difficulties and issues that make more users more likely to accept and use the technology. The proposed research comprised of machine learning (ML) algorithms is Naïve Bayes (NB), Library Support Vector Machine (LibSVM), Multinomial Logistic Regression (MLR), Sequential Minimal Optimization (SMO), K Nearest Neighbor (KNN), and Random Forest (RF) to compare the classifier gives better results in accuracy and less fault prediction. In this research, the secondary data results (CPU-Mem Mono) give the highest percentage of accuracy and less fault prediction on the NB classifier in terms of 80/20 (77.01%), 70/30 (76.05%), and 5 folds cross-validation (74.88%), and (CPU-Mem Multi) in terms of 80/20 (89.72%), 70/30 (90.28%), and 5 folds cross-validation (92.83%). Furthermore, on (HDD Mono) the SMO classifier gives the highest percentage of accuracy and less fault prediction fault in terms of 80/20 (87.72%), 70/30 (89.41%), and 5 folds cross-validation (88.38%), and (HDD-Multi) in terms of 80/20 (93.64%), 70/30 (90.91%), and 5 folds cross-validation (88.20%). Whereas, primary data results found RF classifier gives the highest percentage of accuracy and less fault prediction in terms of 80/20 (97.14%), 70/30 (96.19%), and 5 folds cross-validation (95.85%) in the primary data results, but the algorithm complexity (0.17 seconds) is not good. In terms of 80/20 (95.71%), 70/30 (95.71%), and 5 folds cross-validation (95.71%), SMO has the second highest accuracy and less fault prediction, but the algorithm complexity is good (0.3 seconds). The difference in accuracy and less fault prediction between RF and SMO is only (.13%), and the difference in time complexity is (14 seconds). We have decided that we will modify SMO. Finally, the Modified Sequential Minimal Optimization (MSMO) Algorithm method has been proposed to get the highest accuracy & less fault prediction errors in terms of 80/20 (96.42%), 70/30 (96.42%), & 5 fold cross validation (96.50%).

Matched MeSH terms: Support Vector Machine
Fulltext Predicting dengue transmission rates by comparing different machine learning models with vector indices and meteorological data

Ong SQ, Isawasan P, Ngesom AMM, Shahar H, Lasim AM, Nair G

Sci Rep, 2023 Nov 05;13(1):19129.
PMID: 37926755 DOI: 10.1038/s41598-023-46342-2

Machine learning algorithms (ML) are receiving a lot of attention in the development of predictive models for monitoring dengue transmission rates. Previous work has focused only on specific weather variables and algorithms, and there is still a need for a model that uses more variables and algorithms that have higher performance. In this study, we use vector indices and meteorological data as predictors to develop the ML models. We trained and validated seven ML algorithms, including an ensemble ML method, and compared their performance using the receiver operating characteristic (ROC) with the area under the curve (AUC), accuracy and F1 score. Our results show that an ensemble ML such as XG Boost, AdaBoost and Random Forest perform better than the logistics regression, Naïve Bayens, decision tree, and support vector machine (SVM), with XGBoost having the highest AUC, accuracy and F1 score. Analysis of the importance of the variables showed that the container index was the least important. By removing this variable, the ML models improved their performance by at least 6% in AUC and F1 score. Our result provides a framework for future studies on the use of predictive models in the development of an early warning system.

Matched MeSH terms: Support Vector Machine
Fulltext Detection of Iris Presentation Attacks Using Feature Fusion of Thepade's Sorted Block Truncation Coding with Gray-Level Co-Occurrence Matrix Features

Khade S, Gite S, Thepade SD, Pradhan B, Alamri A

Sensors (Basel), 2021 Nov 08;21(21).
PMID: 34770715 DOI: 10.3390/s21217408

Iris biometric detection provides contactless authentication, preventing the spread of COVID-19-like contagious diseases. However, these systems are prone to spoofing attacks attempted with the help of contact lenses, replayed video, and print attacks, making them vulnerable and unsafe. This paper proposes the iris liveness detection (ILD) method to mitigate spoofing attacks, taking global-level features of Thepade's sorted block truncation coding (TSBTC) and local-level features of the gray-level co-occurrence matrix (GLCM) of the iris image. Thepade's SBTC extracts global color texture content as features, and GLCM extracts local fine-texture details. The fusion of global and local content presentation may help distinguish between live and non-live iris samples. The fusion of Thepade's SBTC with GLCM features is considered in experimental validations of the proposed method. The features are used to train nine assorted machine learning classifiers, including naïve Bayes (NB), decision tree (J48), support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), and ensembles (SVM + RF + NB, SVM + RF + RT, RF + SVM + MLP, J48 + RF + MLP) for ILD. Accuracy, precision, recall, and F-measure are used to evaluate the performance of the projected ILD variants. The experimentation was carried out on four standard benchmark datasets, and our proposed model showed improved results with the feature fusion approach. The proposed fusion approach gave 99.68% accuracy using the RF + J48 + MLP ensemble of classifiers, immediately followed by the RF algorithm, which gave 95.57%. The better capability of iris liveness detection will improve human-computer interaction and security in the cyber-physical space by improving person validation.

Matched MeSH terms: Support Vector Machine
Fulltext Integrated support vector regression and an improved particle swarm optimization-based model for solar radiation prediction

Ghazvinian H, Mousavi SF, Karami H, Farzin S, Ehteram M, Hossain MS, et al.

PLoS One, 2019;14(5):e0217634.
PMID: 31150467 DOI: 10.1371/journal.pone.0217634

Solar energy is a major type of renewable energy, and its estimation is important for decision-makers. This study introduces a new prediction model for solar radiation based on support vector regression (SVR) and the improved particle swarm optimization (IPSO) algorithm. The new version of algorithm attempts to enhance the global search ability for the PSO. In practice, the SVR method has a few parameters that should be determined through a trial-and-error procedure while developing the prediction model. This procedure usually leads to non-optimal choices for these parameters and, hence, poor prediction accuracy. Therefore, there is a need to integrate the SVR model with an optimization algorithm to achieve optimal choices for these parameters. Thus, the IPSO algorithm, as an optimizer is integrated with SVR to obtain optimal values for the SVR parameters. To examine the proposed model, two solar radiation stations, Adana, Antakya and Konya, in Turkey, are considered for this study. In addition, different models have been tested for this prediction, namely, the M5 tree model (M5T), genetic programming (GP), SVR integrated with four different optimization algorithms SVR-PSO, SVR-IPSO, Genetic Algorithm (SVR-GA), FireFly Algorithm (SVR-FFA) and the multivariate adaptive regression (MARS) model. The sensitivity analysis is performed to achieve the highest accuracy level of the prediction by choosing different input parameters. Several performance measuring indices have been considered to examine the efficiency of all the prediction methods. The results show that SVR-IPSO outperformed M5T and MARS.

Matched MeSH terms: Support Vector Machine*
Automated detection of sleep apnea using sparse residual entropy features with various dictionaries extracted from heart rate and EDR signals

Viswabhargav CSS, Tripathy RK, Acharya UR

Comput Biol Med, 2019 05;108:20-30.
PMID: 31003176 DOI: 10.1016/j.compbiomed.2019.03.016

Sleep is a prominent physiological activity in our daily life. Sleep apnea is the category of sleep disorder during which the breathing of the person diminishes causing the alternation in the upper airway resistance. The electrocardiogram derived respiration (EDR) and heart rate (RR-time-series) signals are normally used for the detection of sleep apnea as these two signals capture cardio-pulmonary activity information. Hence, the analysis of these two signals provides vital information about sleep apnea. In this paper, we propose the novel sparse residual entropy (SRE) features for the automated detection of sleep apnea using EDR and heart rate signals. The features required for the automated detection of sleep apnea are extracted in three steps: (i) atomic decomposition based residual estimation from both EDR and heart rate signals using orthogonal matching pursuit (OMP) with different dictionaries, (ii) estimation of probabilities from each sparse residual, and (iii) calculation of the entropy features. The proposed SRE features are fed to the combination of fuzzy K-means clustering and support vector machine (SVM) to pick the best performing classifier. The experimental results demonstrate that the proposed SRE features with radial basis function (RBF) kernel-based SVM classifier yielded higher performance with accuracy, sensitivity and specificity values of 78.07%, 78.01%, and 78.13%, respectively with Fourier dictionary and 10-fold cross-validation. For subject-specific or leave-one-out validation case, the SVM classifier has sensitivity and specificity of 85.43% and 92.60%, respectively using SRE features with Fourier dictionary (FD).

Matched MeSH terms: Support Vector Machine*
Predicting of the refractive index of haemoglobin using the Hybrid GA-SVR approach

Oyehan TA, Alade IO, Bagudu A, Sulaiman KO, Olatunji SO, Saleh TA

Comput Biol Med, 2018 07 01;98:85-92.
PMID: 29777986 DOI: 10.1016/j.compbiomed.2018.04.024

The optical properties of blood play crucial roles in medical diagnostics and treatment, and in the design of new medical devices. Haemoglobin is a vital constituent of the blood whose optical properties affect all of the optical properties of human blood. The refractive index of haemoglobin has been reported to strongly depend on its concentration which is a function of the physiology of biological cells. This makes the refractive index of haemoglobin an essential non-invasive bio-marker of diseases. Unfortunately, the complexity of blood tissue makes it challenging to experimentally measure the refractive index of haemoglobin. While a few studies have reported on the refractive index of haemoglobin, there is no solid consensus with the data obtained due to different measuring instruments and the conditions of the experiments. Moreover, obtaining the refractive index via an experimental approach is quite laborious. In this work, an accurate, fast and relatively convenient strategy to estimate the refractive index of haemoglobin is reported. Thus, the GA-SVR model is presented for the prediction of the refractive index of haemoglobin using wavelength, temperature, and the concentration of haemoglobin as descriptors. The model developed is characterised by an excellent accuracy and very low error estimates. The correlation coefficients obtained in these studies are 99.94% and 99.91% for the training and testing results, respectively. In addition, the result shows an almost perfect match with the experimental data and also demonstrates significant improvement over a recent mathematical model available in the literature. The GA-SVR model predictions also give insights into the influence of concentration, wavelength, and temperature on the RI measurement values. The model outcome can be used not only to accurately estimate the refractive index of haemoglobin but also could provide a reliable common ground to benchmark the experimental refractive index results.

Matched MeSH terms: Support Vector Machine*
Estimating the refractive index of oxygenated and deoxygenated hemoglobin using genetic algorithm - support vector regression model

Alade IO, Bagudu A, Oyehan TA, Rahman MAA, Saleh TA, Olatunji SO

Comput Methods Programs Biomed, 2018 Sep;163:135-142.
PMID: 30119848 DOI: 10.1016/j.cmpb.2018.05.029

BACKGROUND AND OBJECTIVES: The refractive index of hemoglobin plays important role in hematology due to its strong correlation with the pathophysiology of different diseases. Measurement of the real part of the refractive index remains a challenge due to strong absorption of the hemoglobin especially at relevant high physiological concentrations. So far, only a few studies on direct measurement of refractive index have been reported and there are no firm agreements on the reported values of refractive index of hemoglobin due to measurement artifacts. In addition, it is time consuming, laborious and expensive to perform several experiments to obtain the refractive index of hemoglobin. In this work, we proposed a very rapid and accurate computational intelligent approach using Genetic Algorithm/Support Vector Regression models to estimate the real part of the refractive index for oxygenated and deoxygenated hemoglobin samples.
METHODS: These models utilized experimental data of wavelengths and hemoglobin concentrations in building highly accurate Genetic Algorithm/Support Vector Regression model (GA-SVR).
RESULTS: The developed methodology showed high accuracy as indicated by the low root mean square error values of 4.65 × 10-4 and 4.62 × 10-4 for oxygenated and deoxygenated hemoglobin, respectively. In addition, the models exhibited 99.85 and 99.84% correlation coefficients (r) for the oxygenated and deoxygenated hemoglobin, thus, validating the strong agreement between the predicted and the experimental results CONCLUSIONS: Due to the accuracy and relative simplicity of the proposed models, we envisage that these models would serve as important references for future studies on optical properties of blood.

Matched MeSH terms: Support Vector Machine*
Prediction of water quality index in constructed wetlands using support vector machine

Mohammadpour R, Shaharuddin S, Chang CK, Zakaria NA, Ab Ghani A, Chan NW

Environ Sci Pollut Res Int, 2015 Apr;22(8):6208-19.
PMID: 25408070 DOI: 10.1007/s11356-014-3806-7

Poor water quality is a serious problem in the world which threatens human health, ecosystems, and plant/animal life. Prediction of surface water quality is a main concern in water resource and environmental systems. In this research, the support vector machine and two methods of artificial neural networks (ANNs), namely feed forward back propagation (FFBP) and radial basis function (RBF), were used to predict the water quality index (WQI) in a free constructed wetland. Seventeen points of the wetland were monitored twice a month over a period of 14 months, and an extensive dataset was collected for 11 water quality variables. A detailed comparison of the overall performance showed that prediction of the support vector machine (SVM) model with coefficient of correlation (R(2)) = 0.9984 and mean absolute error (MAE) = 0.0052 was either better or comparable with neural networks. This research highlights that the SVM and FFBP can be successfully employed for the prediction of water quality in a free surface constructed wetland environment. These methods simplify the calculation of the WQI and reduce substantial efforts and time by optimizing the computations.

Matched MeSH terms: Support Vector Machine*
Fulltext Shallow Landslide Susceptibility Mapping: A Comparison between Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine Algorithms

Nhu VH, Shirzadi A, Shahabi H, Singh SK, Al-Ansari N, Clague JJ, et al.

Int J Environ Res Public Health, 2020 04 16;17(8).
PMID: 32316191 DOI: 10.3390/ijerph17082749

Shallow landslides damage buildings and other infrastructure, disrupt agriculture practices, and can cause social upheaval and loss of life. As a result, many scientists study the phenomenon, and some of them have focused on producing landslide susceptibility maps that can be used by land-use managers to reduce injury and damage. This paper contributes to this effort by comparing the power and effectiveness of five machine learning, benchmark algorithms-Logistic Model Tree, Logistic Regression, Naïve Bayes Tree, Artificial Neural Network, and Support Vector Machine-in creating a reliable shallow landslide susceptibility map for Bijar City in Kurdistan province, Iran. Twenty conditioning factors were applied to 111 shallow landslides and tested using the One-R attribute evaluation (ORAE) technique for modeling and validation processes. The performance of the models was assessed by statistical-based indexes including sensitivity, specificity, accuracy, mean absolute error (MAE), root mean square error (RMSE), and area under the receiver operatic characteristic curve (AUC). Results indicate that all the five machine learning models performed well for shallow landslide susceptibility assessment, but the Logistic Model Tree model (AUC = 0.932) had the highest goodness-of-fit and prediction accuracy, followed by the Logistic Regression (AUC = 0.932), Naïve Bayes Tree (AUC = 0.864), ANN (AUC = 0.860), and Support Vector Machine (AUC = 0.834) models. Therefore, we recommend the use of the Logistic Model Tree model in shallow landslide mapping programs in semi-arid regions to help decision makers, planners, land-use managers, and government agencies mitigate the hazard and risk.

Matched MeSH terms: Support Vector Machine*
Automated glaucoma diagnosis using bit-plane slicing and local binary pattern techniques

Maheshwari S, Kanhangad V, Pachori RB, Bhandary SV, Acharya UR

Comput Biol Med, 2019 Feb;105:72-80.
PMID: 30590290 DOI: 10.1016/j.compbiomed.2018.11.028

BACKGROUND AND OBJECTIVE: Glaucoma is a ocular disorder which causes irreversible damage to the retinal nerve fibers. The diagnosis of glaucoma is important as it may help to slow down the progression. The available clinical methods and imaging techniques are manual and require skilled supervision. For the purpose of mass screening, an automated system is needed for glaucoma diagnosis which is fast, accurate, and helps in reducing the burden on experts.
METHODS: In this work, we present a bit-plane slicing (BPS) and local binary pattern (LBP) based novel approach for glaucoma diagnosis. Firstly, our approach separates the red (R), green (G), and blue (B) channels from the input color fundus image and splits the channels into bit planes. Secondly, we extract LBP based statistical features from each of the bit planes of the individual channels. Thirdly, these features from the individual channels are fed separately to three different support vector machines (SVMs) for classification. Finally, the decisions from the individual SVMs are fused at the decision level to classify the input fundus image into normal or glaucoma class.
RESULTS: Our experimental results suggest that the proposed approach is effective in discriminating normal and glaucoma cases with an accuracy of 99.30% using 10-fold cross validation.
CONCLUSIONS: The developed system is ready to be tested on large and diverse databases and can assist the ophthalmologists in their daily screening to confirm their diagnosis, thereby increasing accuracy of diagnosis.

Matched MeSH terms: Support Vector Machine
Fulltext Paddy leaf disease recognition system using image processing techniques and support vector machine

Hayatun Syamila Mamat, Nur Azwani Zaini, Suhaila Abd Halim

ESTEEM Academic Journal, 2020;16(2):41-50.
MyJurnal

Paddy is a crucial agroculture sector since rice is the staple food for the majority of the world's population. However, the production of paddy is slower and less productive since many factors have affected the growth of the paddy. The existence of disease in paddy component affects the quality of rice produced. Hence, the recognition of the disease at the beginning stage is crucial as the initial approach for prevention purposes. In this study, a system is developed to detect the paddy leaf disease such as bacterial leaf blight, brown spot and leaf smut. All the processes involved are implemented and compiled using MATLAB R2020a. A set of 105 image data with disease is converted to binary image using thresholding. 6 features from all the data are extracted and divided to testing and training set before the classification process. A cubic support vector machine is used for the classification process. Lastly, accuracy, precision, and misclassification for each disease are calculated for performance evaluation. Results show that the average performance of the diseases on accuracy, precision, and misclassification are 88.57%, 82.97%, and 11.43% respectively. The use of the processes act as assistance to the paddy farmer to identify the existence of the paddy leaf disease. This could improve the quality of the paddy produced by reducing the process of manual disease checking.

Matched MeSH terms: Support Vector Machine
Support vector machines for oil classification link with polyaromatic hydrocarbon contamination in the environment

Ismail A, Juahir H, Mohamed SB, Toriman ME, Kassim AM, Zain SM, et al.

Water Sci Technol, 2021 Mar;83(5):1039-1054.
PMID: 33724935 DOI: 10.2166/wst.2021.038

The main focus of this study is exploring the spatial distribution of polyaromatics hydrocarbon links between oil spills in the environment via Support Vector Machines based on Kernel-Radial Basis Function (RBF) approach for high precision classification of oil spill type from its sample fingerprinting in Peninsular Malaysia. The results show the highest concentrations of Σ Alkylated PAHs and Σ EPA PAHs in ΣTAH concentration in diesel from the oil samples PP3_liquid and GP6_Jetty achieving 100% classification output, corresponding to coherent decision boundary and projective subspace estimation. The high dimensional nature of this approach has led to the existence of a perfect separability of the oil type classification from four clustered oil type components; i.e diesel, bunker C, Mixture Oil (MO), lube oil and Waste Oil (WO) with the slack variables of ξ ≠ 0. Of the four clusters, only the SVs of two are correctly predicted, namely diesel and MO. The kernel-RBF approach provides efficient and reliable oil sample classification, enabling the oil classification to be optimally performed within a relatively short period of execution and a faster dataset classification where the slack variables ξ are non-zero.

Matched MeSH terms: Support Vector Machine
Hybrid Harmony Search-Artificial Intelligence Models in Credit Scoring

Goh RY, Lee LS, Seow HV, Gopal K

Entropy (Basel), 2020 Sep 04;22(9).
PMID: 33286758 DOI: 10.3390/e22090989

Credit scoring is an important tool used by financial institutions to correctly identify defaulters and non-defaulters. Support Vector Machines (SVM) and Random Forest (RF) are the Artificial Intelligence techniques that have been attracting interest due to their flexibility to account for various data patterns. Both are black-box models which are sensitive to hyperparameter settings. Feature selection can be performed on SVM to enable explanation with the reduced features, whereas feature importance computed by RF can be used for model explanation. The benefits of accuracy and interpretation allow for significant improvement in the area of credit risk and credit scoring. This paper proposes the use of Harmony Search (HS), to form a hybrid HS-SVM to perform feature selection and hyperparameter tuning simultaneously, and a hybrid HS-RF to tune the hyperparameters. A Modified HS (MHS) is also proposed with the main objective to achieve comparable results as the standard HS with a shorter computational time. MHS consists of four main modifications in the standard HS: (i) Elitism selection during memory consideration instead of random selection, (ii) dynamic exploration and exploitation operators in place of the original static operators, (iii) a self-adjusted bandwidth operator, and (iv) inclusion of additional termination criteria to reach faster convergence. Along with parallel computing, MHS effectively reduces the computational time of the proposed hybrid models. The proposed hybrid models are compared with standard statistical models across three different datasets commonly used in credit scoring studies. The computational results show that MHS-RF is most robust in terms of model performance, model explainability and computational time.

Matched MeSH terms: Support Vector Machine
Automatic classification of regular and irregular capnogram segments using time- and frequency-domain features: A machine learning-based approach

El-Badawy IM, Singh OP, Omar Z

Technol Health Care, 2021;29(1):59-72.
PMID: 32716337 DOI: 10.3233/THC-202198

BACKGROUND: The quantitative features of a capnogram signal are important clinical metrics in assessing pulmonary function. However, these features should be quantified from the regular (artefact-free) segments of the capnogram waveform.
OBJECTIVE: This paper presents a machine learning-based approach for the automatic classification of regular and irregular capnogram segments.
METHODS: Herein, we proposed four time- and two frequency-domain features experimented with the support vector machine classifier through ten-fold cross-validation. MATLAB simulation was conducted on 100 regular and 100 irregular 15 s capnogram segments. Analysis of variance was performed to investigate the significance of the proposed features. Pearson's correlation was utilized to select the relatively most substantial ones, namely variance and the area under normalized magnitude spectrum. Classification performance, using these features, was evaluated against two feature sets in which either time- or frequency-domain features only were employed.
RESULTS: Results showed a classification accuracy of 86.5%, which outperformed the other cases by an average of 5.5%. The achieved specificity, sensitivity, and precision were 84%, 89% and 86.51%, respectively. The average execution time for feature extraction and classification per segment is only 36 ms.
CONCLUSION: The proposed approach can be integrated with capnography devices for real-time capnogram-based respiratory assessment. However, further research is recommended to enhance the classification performance.

Matched MeSH terms: Support Vector Machine
Fulltext Fruit Battery Method for Oil Palm Fruit Ripeness Sensor and Comparison with Computer Vision Method

Aliteh NA, Minakata K, Tashiro K, Wakiwaka H, Kobayashi K, Nagata H, et al.

Sensors (Basel), 2020 Jan 23;20(3).
PMID: 31979252 DOI: 10.3390/s20030637

Oil palm ripeness' main evaluation procedure is traditionally accomplished by human vision. However, the dependency on human evaluators to grade the ripeness of oil palm fresh fruit bunches (FFBs) by traditional means could lead to inaccuracy that can cause a reduction in oil palm fruit oil extraction rate (OER). This paper emphasizes the fruit battery method to distinguish oil palm fruit FFB ripeness stages by determining the value of load resistance voltage and its moisture content resolution. In addition, computer vision using a color feature is tested on the same samples to compare the accuracy score using support vector machine (SVM). The accuracy score results of the fruit battery, computer vision, and a combination of both methods' accuracy scores are evaluated and compared. When the ripe and unripe samples were tested for load resistance voltage ranging from 10 Ω to 10 kΩ, three resistance values were shortlisted and tested for moisture content resolution evaluation. A 1 kΩ load resistance showed the best moisture content resolution, and the results were used for accuracy score evaluation comparison with computer vision. From the results obtained, the accuracy scores for the combination method are the highest, followed by the fruit battery and computer vision methods.

Matched MeSH terms: Support Vector Machine
Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods

Rahmati O, Choubin B, Fathabadi A, Coulon F, Soltani E, Shahabi H, et al.

Sci Total Environ, 2019 Oct 20;688:855-866.
PMID: 31255823 DOI: 10.1016/j.scitotenv.2019.06.320

Although estimating the uncertainty of models used for modelling nitrate contamination of groundwater is essential in groundwater management, it has been generally ignored. This issue motivates this research to explore the predictive uncertainty of machine-learning (ML) models in this field of study using two different residuals uncertainty methods: quantile regression (QR) and uncertainty estimation based on local errors and clustering (UNEEC). Prediction-interval coverage probability (PICP), the most important of the statistical measures of uncertainty, was used to evaluate uncertainty. Additionally, three state-of-the-art ML models including support vector machine (SVM), random forest (RF), and k-nearest neighbor (kNN) were selected to spatially model groundwater nitrate concentrations. The models were calibrated with nitrate concentrations from 80 wells (70% of the data) and then validated with nitrate concentrations from 34 wells (30% of the data). Both uncertainty and predictive performance criteria should be considered when comparing and selecting the best model. Results highlight that the kNN model is the best model because not only did it have the lowest uncertainty based on the PICP statistic in both the QR (0.94) and the UNEEC (in all clusters, 0.85-0.91) methods, but it also had predictive performance statistics (RMSE = 10.63, R2 = 0.71) that were relatively similar to RF (RMSE = 10.41, R2 = 0.72) and higher than SVM (RMSE = 13.28, R2 = 0.58). Determining the uncertainty of ML models used for spatially modelling groundwater-nitrate pollution enables managers to achieve better risk-based decision making and consequently increases the reliability and credibility of groundwater-nitrate predictions.

Matched MeSH terms: Support Vector Machine
Fulltext A Hybrid Approach to Detect Driver Drowsiness Utilizing Physiological Signals to Improve System Performance and Wearability

Awais M, Badruddin N, Drieberg M

Sensors (Basel), 2017 Aug 31;17(9).
PMID: 28858220 DOI: 10.3390/s17091991

Driver drowsiness is a major cause of fatal accidents, injury, and property damage, and has become an area of substantial research attention in recent years. The present study proposes a method to detect drowsiness in drivers which integrates features of electrocardiography (ECG) and electroencephalography (EEG) to improve detection performance. The study measures differences between the alert and drowsy states from physiological data collected from 22 healthy subjects in a driving simulator-based study. A monotonous driving environment is used to induce drowsiness in the participants. Various time and frequency domain feature were extracted from EEG including time domain statistical descriptors, complexity measures and power spectral measures. Features extracted from the ECG signal included heart rate (HR) and heart rate variability (HRV), including low frequency (LF), high frequency (HF) and LF/HF ratio. Furthermore, subjective sleepiness scale is also assessed to study its relationship with drowsiness. We used paired t-tests to select only statistically significant features (p < 0.05), that can differentiate between the alert and drowsy states effectively. Significant features of both modalities (EEG and ECG) are then combined to investigate the improvement in performance using support vector machine (SVM) classifier. The other main contribution of this paper is the study on channel reduction and its impact to the performance of detection. The proposed method demonstrated that combining EEG and ECG has improved the system's performance in discriminating between alert and drowsy states, instead of using them alone. Our channel reduction analysis revealed that an acceptable level of accuracy (80%) could be achieved by combining just two electrodes (one EEG and one ECG), indicating the feasibility of a system with improved wearability compared with existing systems involving many electrodes. Overall, our results demonstrate that the proposed method can be a viable solution for a practical driver drowsiness system that is both accurate and comfortable to wear.

Matched MeSH terms: Support Vector Machine
Paroxysmal atrial fibrillation prediction based on HRV analysis and non-dominated sorting genetic algorithm III

Boon KH, Khalil-Hani M, Malarvili MB

Comput Methods Programs Biomed, 2018 Jan;153:171-184.
PMID: 29157449 DOI: 10.1016/j.cmpb.2017.10.012

This paper presents a method that able to predict the paroxysmal atrial fibrillation (PAF). The method uses shorter heart rate variability (HRV) signals when compared to existing methods, and achieves good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to electrically stabilize and prevent the onset of atrial arrhythmias with different pacing techniques. We propose a multi-objective optimization algorithm based on the non-dominated sorting genetic algorithm III for optimizing the baseline PAF prediction system, that consists of the stages of pre-processing, HRV feature extraction, and support vector machine (SVM) model. The pre-processing stage comprises of heart rate correction, interpolation, and signal detrending. After that, time-domain, frequency-domain, non-linear HRV features are extracted from the pre-processed data in feature extraction stage. Then, these features are used as input to the SVM for predicting the PAF event. The proposed optimization algorithm is used to optimize the parameters and settings of various HRV feature extraction algorithms, select the best feature subsets, and tune the SVM parameters simultaneously for maximum prediction performance. The proposed method achieves an accuracy rate of 87.7%, which significantly outperforms most of the previous works. This accuracy rate is achieved even with the HRV signal length being reduced from the typical 30 min to just 5 min (a reduction of 83%). Furthermore, another significant result is the sensitivity rate, which is considered more important that other performance metrics in this paper, can be improved with the trade-off of lower specificity.

Matched MeSH terms: Support Vector Machine
Nitrate Classification Based on Optical Absorbance Data Using Machine Learning Algorithms for a Hydroponics System

Sulaiman R, Azeman NH, Abu Bakar MH, Ahmad Nazri NA, Masran AS, Ashrif A Bakar A

Appl Spectrosc, 2023 Feb;77(2):210-219.
PMID: 36348500 DOI: 10.1177/00037028221140924

Nutrient solution plays an essential role in providing macronutrients to hydroponic plants. Determining nitrogen in the form of nitrate is crucial, as either a deficient or excessive supply of nitrate ions may reduce the plant yield or lead to environmental pollution. This work aims to evaluate the performance of feature reduction techniques and conventional machine learning (ML) algorithms in determining nitrate concentration levels. Two features reduction techniques, linear discriminant analysis (LDA) and principal component analysis (PCA), and seven ML algorithms, for example, k-nearest neighbors (KNN), support vector machine, decision trees, naïve bayes, random forest (RF), gradient boosting, and extreme gradient boosting, were evaluated using a high-dimensional spectroscopic dataset containing measured nitrate-nitrite mixed solution absorbance data. Despite the limited and uneven number of samples per class, this study demonstrated that PCA outperformed LDA on the high-dimensional spectroscopic dataset. The classification accuracy of ML algorithms combined with PCA ranged from 92.7% to 99.8%, whereas the classification accuracy of ML algorithms combined with LDA ranged from 80.7% to 87.6%. The PCA with the RF algorithm exhibited the best performance with 99.8% accuracy.

Matched MeSH terms: Support Vector Machine

Filters

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

External Links