MyMedR

Displaying publications 81 - 100 of 417 in total

Abstract:

Sort:

Fulltext A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal

Ullah A, Rehman SU, Tu S, Mehmood RM, Fawad, Ehatisham-Ul-Haq M

Sensors (Basel), 2021 Feb 01;21(3).
PMID: 33535397 DOI: 10.3390/s21030951

Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model's classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outperformed the corresponding state-of-the-art classification algorithms for the same data, which validates the proposed models' effectiveness.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext A modeling study by response surface methodology and artificial neural network on culture parameters optimization for thermostable lipase production from a newly isolated thermophilic Geobacillus sp. strain ARM

Ebrahimpour A, Abd Rahman RN, Ean Ch'ng DH, Basri M, Salleh AB

BMC Biotechnol, 2008;8:96.
PMID: 19105837 DOI: 10.1186/1472-6750-8-96

Thermostable bacterial lipases occupy a place of prominence among biocatalysts owing to their novel, multifold applications and resistance to high temperature and other operational conditions. The capability of lipases to catalyze a variety of novel reactions in both aqueous and nonaqueous media presents a fascinating field for research, creating interest to isolate novel lipase producers and optimize lipase production. The most important stages in a biological process are modeling and optimization to improve a system and increase the efficiency of the process without increasing the cost.

Matched MeSH terms: Neural Networks (Computer)*
Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification

Pang T, Wong JHD, Ng WL, Chan CS

Comput Methods Programs Biomed, 2021 May;203:106018.
PMID: 33714900 DOI: 10.1016/j.cmpb.2021.106018

BACKGROUND AND OBJECTIVE: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images.
METHODS: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method.
RESULTS: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods.
CONCLUSION: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Prediction of remaining useful life (RUL) of Komatsu excavator under reliability analysis in the Weibull-frailty model

Ghomghaleh A, Khaloukakaie R, Ataei M, Barabadi A, Nouri Qarahasanlou A, Rahmani O, et al.

PLoS One, 2020;15(7):e0236128.
PMID: 32667940 DOI: 10.1371/journal.pone.0236128

It is an essential task to estimate the remaining useful life (RUL) of machinery in the mining sector aimed at ensuring the production and the customer's satisfaction. In this study, a conceptual framework was used to determine the RUL under the reliability analysis in a frailty model. The proposed framework was implemented on a Komatsu PC-1250 excavator from the Sungun copper mine. Also, the Weibull-frailty model was selected to describe the failure behavior and compare it with the classical-exponential model. The frailty model was also used to evaluate the impact of unobserved environmental conditions on the RUL values. Both applied models were fitted to the obtained data from 80 operational hours of the Komatsu PC-1250 excavator. Plotting the results from the reliability analysis of two models demonstrated that the mine system with the frailty model performs better than the classical model before reaching the reliability of 80%. Besides, the frailty model shows a coherent with the operational time of the excavator, while the classical model demonstrates a sinusoid variation. The obtained results may be used for the development of maintenance, preventive repairs planning, and the spare parts replacement intervals.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Automatic Polyp Segmentation in Colonoscopy Images Using a Modified Deep Convolutional Encoder-Decoder Architecture

Eu CY, Tang TB, Lin CH, Lee LH, Lu CK

Sensors (Basel), 2021 Aug 20;21(16).
PMID: 34451072 DOI: 10.3390/s21165630

Colorectal cancer has become the third most commonly diagnosed form of cancer, and has the second highest fatality rate of cancers worldwide. Currently, optical colonoscopy is the preferred tool of choice for the diagnosis of polyps and to avert colorectal cancer. Colon screening is time-consuming and highly operator dependent. In view of this, a computer-aided diagnosis (CAD) method needs to be developed for the automatic segmentation of polyps in colonoscopy images. This paper proposes a modified SegNet Visual Geometry Group-19 (VGG-19), a form of convolutional neural network, as a CAD method for polyp segmentation. The modifications include skip connections, 5 × 5 convolutional filters, and the concatenation of four dilated convolutions applied in parallel form. The CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB databases were used to evaluate the model, and it was found that our proposed polyp segmentation model achieved an accuracy, sensitivity, specificity, precision, mean intersection over union, and dice coefficient of 96.06%, 94.55%, 97.56%, 97.48%, 92.3%, and 95.99%, respectively. These results indicate that our model performs as well as or better than previous schemes in the literature. We believe that this study will offer benefits in terms of the future development of CAD tools for polyp segmentation for colorectal cancer diagnosis and management. In the future, we intend to embed our proposed network into a medical capsule robot for practical usage and try it in a hospital setting with clinicians.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext A Novel RSSI Prediction Using Imperialist Competition Algorithm (ICA), Radial Basis Function (RBF) and Firefly Algorithm (FFA) in Wireless Networks

Goudarzi S, Haslina Hassan W, Abdalla Hashim AH, Soleymani SA, Anisi MH, Zakaria OM

PLoS One, 2016;11(7):e0151355.
PMID: 27438600 DOI: 10.1371/journal.pone.0151355

This study aims to design a vertical handover prediction method to minimize unnecessary handovers for a mobile node (MN) during the vertical handover process. This relies on a novel method for the prediction of a received signal strength indicator (RSSI) referred to as IRBF-FFA, which is designed by utilizing the imperialist competition algorithm (ICA) to train the radial basis function (RBF), and by hybridizing with the firefly algorithm (FFA) to predict the optimal solution. The prediction accuracy of the proposed IRBF-FFA model was validated by comparing it to support vector machines (SVMs) and multilayer perceptron (MLP) models. In order to assess the model's performance, we measured the coefficient of determination (R2), correlation coefficient (r), root mean square error (RMSE) and mean absolute percentage error (MAPE). The achieved results indicate that the IRBF-FFA model provides more precise predictions compared to different ANNs, namely, support vector machines (SVMs) and multilayer perceptron (MLP). The performance of the proposed model is analyzed through simulated and real-time RSSI measurements. The results also suggest that the IRBF-FFA model can be applied as an efficient technique for the accurate prediction of vertical handover.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Master-Leader-Slave Cuckoo Search with Parameter Control for ANN Optimization and Its Real-World Application to Water Quality Prediction

Jaddi NS, Abdullah S, Abdul Malek M

PLoS One, 2017;12(1):e0170372.
PMID: 28125609 DOI: 10.1371/journal.pone.0170372

Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent Lévy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.

Matched MeSH terms: Neural Networks (Computer)*
A new hyperbox selection rule and a pruning strategy for the enhanced fuzzy min-max neural network

Mohammed MF, Lim CP

Neural Netw, 2017 Feb;86:69-79.
PMID: 27890606 DOI: 10.1016/j.neunet.2016.10.012

In this paper, we extend our previous work on the Enhanced Fuzzy Min-Max (EFMM) neural network by introducing a new hyperbox selection rule and a pruning strategy to reduce network complexity and improve classification performance. Specifically, a new k-nearest hyperbox expansion rule (for selection of a new winning hyperbox) is first introduced to reduce the network complexity by avoiding the creation of too many small hyperboxes within the vicinity of the winning hyperbox. A pruning strategy is then deployed to further reduce the network complexity in the presence of noisy data. The effectiveness of the proposed network is evaluated using a number of benchmark data sets. The results compare favorably with those from other related models. The findings indicate that the newly introduced hyperbox winner selection rule coupled with the pruning strategy are useful for undertaking pattern classification problems.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Optimized artificial neural network to improve the accuracy of estimated fault impedances and distances for underground distribution system

Naidu K, Ali MS, Abu Bakar AH, Tan CK, Arof H, Mokhlis H

PLoS One, 2020;15(1):e0227494.
PMID: 31999711 DOI: 10.1371/journal.pone.0227494

This paper proposes an approach to accurately estimate the impedance value of a high impedance fault (HIF) and the distance from its fault location for a distribution system. Based on the three-phase voltage and current waveforms which are monitored through a single measurement in the network, several features are extracted using discrete wavelet transform (DWT). The extracted features are then fed into the optimized artificial neural network (ANN) to estimate the HIF impedance and its distance. The particle swarm optimization (PSO) technique is employed to optimize the parameters of the ANN to enhance the performance of fault impedance and distance estimations. Based on the simulation results, the proposed method records encouraging results compared to other methods of similar complexity for both HIF impedance values and estimated distances.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion

Zafar R, Dass SC, Malik AS

PLoS One, 2017;12(5):e0178410.
PMID: 28558002 DOI: 10.1371/journal.pone.0178410

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain-computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method.

Matched MeSH terms: Neural Networks (Computer)*
Kernel Bayesian ART and ARTMAP

Masuyama N, Loo CK, Dawood F

Neural Netw, 2018 Feb;98:76-86.
PMID: 29202265 DOI: 10.1016/j.neunet.2017.11.003

Adaptive Resonance Theory (ART) is one of the successful approaches to resolving "the plasticity-stability dilemma" in neural networks, and its supervised learning model called ARTMAP is a powerful tool for classification. Among several improvements, such as Fuzzy or Gaussian based models, the state of art model is Bayesian based one, while solving the drawbacks of others. However, it is known that the Bayesian approach for the high dimensional and a large number of data requires high computational cost, and the covariance matrix in likelihood becomes unstable. This paper introduces Kernel Bayesian ART (KBA) and ARTMAP (KBAM) by integrating Kernel Bayes' Rule (KBR) and Correntropy Induced Metric (CIM) to Bayesian ART (BA) and ARTMAP (BAM), respectively, while maintaining the properties of BA and BAM. The kernel frameworks in KBA and KBAM are able to avoid the curse of dimensionality. In addition, the covariance-free Bayesian computation by KBR provides the efficient and stable computational capability to KBA and KBAM. Furthermore, Correntropy-based similarity measurement allows improving the noise reduction ability even in the high dimensional space. The simulation experiments show that KBA performs an outstanding self-organizing capability than BA, and KBAM provides the superior classification ability than BAM, respectively.

Matched MeSH terms: Neural Networks (Computer)*
Automatic seizure detection by convolutional neural networks with computational complexity analysis

Cimr D, Fujita H, Tomaskova H, Cimler R, Selamat A

Comput Methods Programs Biomed, 2023 Feb;229:107277.
PMID: 36463672 DOI: 10.1016/j.cmpb.2022.107277

BACKGROUND AND OBJECTIVES: Nowadays, an automated computer-aided diagnosis (CAD) is an approach that plays an important role in the detection of health issues. The main advantages should be in early diagnosis, including high accuracy and low computational complexity without loss of the model performance. One of these systems type is concerned with Electroencephalogram (EEG) signals and seizure detection. We designed a CAD system approach for seizure detection that optimizes the complexity of the required solution while also being reusable on different problems.
METHODS: The methodology is built-in deep data analysis for normalization. In comparison to previous research, the system does not necessitate a feature extraction process that optimizes and reduces system complexity. The data classification is provided by a designed 8-layer deep convolutional neural network.
RESULTS: Depending on used data, we have achieved the accuracy, specificity, and sensitivity of 98%, 98%, and 98.5% on the short-term Bonn EEG dataset, and 96.99%, 96.89%, and 97.06% on the long-term CHB-MIT EEG dataset.
CONCLUSIONS: Through the approach to detection, the system offers an optimized solution for seizure diagnosis health problems. The proposed solution should be implemented in all clinical or home environments for decision support.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Parasitic egg recognition using convolution and attention network

AlDahoul N, Karim HA, Momo MA, Escobar FIF, Magallanes VA, Tan MJT

Sci Rep, 2023 Sep 02;13(1):14475.
PMID: 37660120 DOI: 10.1038/s41598-023-41711-3

Intestinal parasitic infections (IPIs) caused by protozoan and helminth parasites are among the most common infections in humans in low-and-middle-income countries. IPIs affect not only the health status of a country, but also the economic sector. Over the last decade, pattern recognition and image processing techniques have been developed to automatically identify parasitic eggs in microscopic images. Existing identification techniques are still suffering from diagnosis errors and low sensitivity. Therefore, more accurate and faster solution is still required to recognize parasitic eggs and classify them into several categories. A novel Chula-ParasiteEgg dataset including 11,000 microscopic images proposed in ICIP2022 was utilized to train various methods such as convolutional neural network (CNN) based models and convolution and attention (CoAtNet) based models. The experiments conducted show high recognition performance of the proposed CoAtNet that was tuned with microscopic images of parasitic eggs. The CoAtNet produced an average accuracy of 93%, and an average F1 score of 93%. The finding opens door to integrate the proposed solution in automated parasitological diagnosis.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext A generative adversarial network for synthetization of regions of interest based on digital mammograms

Oyelade ON, Ezugwu AE, Almutairi MS, Saha AK, Abualigah L, Chiroma H

Sci Rep, 2022 Apr 13;12(1):6166.
PMID: 35418566 DOI: 10.1038/s41598-022-09929-9

Deep learning (DL) models are becoming pervasive and applicable to computer vision, image processing, and synthesis problems. The performance of these models is often improved through architectural configuration, tweaks, the use of enormous training data, and skillful selection of hyperparameters. The application of deep learning models to medical image processing has yielded interesting performance, capable of correctly detecting abnormalities in medical digital images, making them surpass human physicians. However, advancing research in this domain largely relies on the availability of training datasets. These datasets are sometimes not publicly accessible, insufficient for training, and may also be characterized by a class imbalance among samples. As a result, inadequate training samples and difficulty in accessing new datasets for training deep learning models limit performance and research into new domains. Hence, generative adversarial networks (GANs) have been proposed to mediate this gap by synthesizing data similar to real sample images. However, we observed that benchmark datasets with regions of interest (ROIs) for characterizing abnormalities in breast cancer using digital mammography do not contain sufficient data with a fair distribution of all cases of abnormalities. For instance, the architectural distortion and breast asymmetry in digital mammograms are sparsely distributed across most publicly available datasets. This paper proposes a GAN model, named ROImammoGAN, which synthesizes ROI-based digital mammograms. Our approach involves the design of a GAN model consisting of both a generator and a discriminator to learn a hierarchy of representations for abnormalities in digital mammograms. Attention is given to architectural distortion, asymmetry, mass, and microcalcification abnormalities so that training distinctively learns the features of each abnormality and generates sufficient images for each category. The proposed GAN model was applied to MIAS datasets, and the performance evaluation yielded a competitive accuracy for the synthesized samples. In addition, the quality of the images generated was also evaluated using PSNR, SSIM, FSIM, BRISQUE, PQUE, NIQUE, FID, and geometry scores. The results showed that ROImammoGAN performed competitively with state-of-the-art GANs. The outcome of this study is a model for augmenting CNN models with ROI-centric image samples for the characterization of abnormalities in breast images.

Matched MeSH terms: Neural Networks (Computer)*
Optimization of operational parameters using RSM, ANN, and SVM in membrane integrated with rotating biological contactor

Waqas S, Harun NY, Arshad U, Laziz AM, Sow Mun SL, Bilad MR, et al.

Chemosphere, 2024 Feb;349:140830.
PMID: 38056711 DOI: 10.1016/j.chemosphere.2023.140830

Membrane fouling is a critical bottleneck to the widespread adoption of membrane separation processes. It diminishes the membrane permeability and results in high operational energy costs. The current study presents optimizing the operating parameters of a novel rotating biological contactor (RBC) integrated with an external membrane (RBC + ME) that combines membrane technology with an RBC. In the RBC + ME, the membrane panel is placed external to the bioreactor. Response surface methodology (RSM) is applied to optimize the membrane permeability through three operating parameters (hydraulic retention time (HRT), rotational disk speed, and sludge retention time (SRT)). The artificial neural networks (ANN) and support vector machine (SVM) are implemented to depict the statistical modelling approach using experimental data sets. The results showed that all three operating parameters contribute significantly to the performance of the bioreactor. RSM revealed an optimum value of 40.7 rpm disk rotational speed, 18 h HRT and 12.4 d SRT, respectively. An ANN model with ten hidden layers provides the highest R2 value, while the SVM model with the Bayesian optimizer provides the highest R2. RSM, ANN, and SVM models reveal the highest R-square values of 0.97, 0.99, and 0.99, respectively. Machine learning techniques help predict the model based on the experimental results and training data sets.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Forecasting stock prices changes using long-short term memory neural network with symbolic genetic programming

Li Q, Kamaruddin N, Yuhaniz SS, Al-Jaifi HAA

Sci Rep, 2024 Jan 03;14(1):422.
PMID: 38172568 DOI: 10.1038/s41598-023-50783-0

This study introduces an augmented Long-Short Term Memory (LSTM) neural network architecture, integrating Symbolic Genetic Programming (SGP), with the objective of forecasting cross-sectional price returns across a comprehensive dataset comprising 4500 listed stocks in the Chinese market over the period from 2014 to 2022. Using the S&P Alpha Pool Dataset for China as basic input, this architecture incorporates data augmentation and feature extraction techniques. The result of this study demonstrates significant improvements in Rank Information coefficient (Rank IC) and IC information ratio (ICIR) by 1128% and 5360% respectively when it is applied to fundamental indicators. For technical indicators, the hybrid model achieves a 206% increase in Rank IC and an impressive surge of 2752% in ICIR. Furthermore, the proposed hybrid SGP-LSTM model outperforms major Chinese stock indexes, generating average annualized excess returns of 31.00%, 24.48%, and 16.38% compared to the CSI 300 index, CSI 500 index, and the average portfolio, respectively. These findings highlight the effectiveness of SGP-LSTM model in improving the accuracy of cross-sectional stock return predictions and provide valuable insights for fund managers, traders, and financial analysts.

Matched MeSH terms: Neural Networks (Computer)*
A deep convolutional neural network for the automatic segmentation of glioblastoma brain tumor: Joint spatial pyramid module and attention mechanism network

Liu H, Huang J, Li Q, Guan X, Tseng M

Artif Intell Med, 2024 Feb;148:102776.
PMID: 38325925 DOI: 10.1016/j.artmed.2024.102776

This study proposes a deep convolutional neural network for the automatic segmentation of glioblastoma brain tumors, aiming sat replacing the manual segmentation method that is both time-consuming and labor-intensive. There are many challenges for automatic segmentation to finely segment sub-regions from multi-sequence magnetic resonance images because of the complexity and variability of glioblastomas, such as the loss of boundary information, misclassified regions, and subregion size. To overcome these challenges, this study introduces a spatial pyramid module and attention mechanism to the automatic segmentation algorithm, which focuses on multi-scale spatial details and context information. The proposed method has been tested in the public benchmarks BraTS 2018, BraTS 2019, BraTS 2020 and BraTS 2021 datasets. The Dice score on the enhanced tumor, whole tumor, and tumor core were respectively 79.90 %, 89.63 %, and 85.89 % on the BraTS 2018 dataset, respectively 77.14 %, 89.58 %, and 83.33 % on the BraTS 2019 dataset, and respectively 77.80 %, 90.04 %, and 83.18 % on the BraTS 2020 dataset, and respectively 83.48 %, 90.70 %, and 88.94 % on the BraTS 2021 dataset offering performance on par with that of state-of-the-art methods with only 1.90 M parameters. In addition, our approach significantly reduced the requirements for experimental equipment, and the average time taken to segment one case was only 1.48 s; these two benefits rendered the proposed network intensely competitive for clinical practice.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting

Waheeb W, Ghazali R, Herawan T

PLoS One, 2016;11(12):e0167248.
PMID: 27959927 DOI: 10.1371/journal.pone.0167248

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

Matched MeSH terms: Neural Networks (Computer)*
Fulltext Vision-Based Apple Classification for Smart Manufacturing

Ismail A, Idris MYI, Ayub MN, Por LY

Sensors (Basel), 2018 Dec 10;18(12).
PMID: 30544660 DOI: 10.3390/s18124353

Smart manufacturing enables an efficient manufacturing process by optimizing production and product transaction. The optimization is performed through data analytics that requires reliable and informative data as input. Therefore, in this paper, an accurate data capture approach based on a vision sensor is proposed. Three image recognition methods are studied to determine the best vision-based classification technique, namely Bag of Words (BOW), Spatial Pyramid Matching (SPM) and Convolutional Neural Network (CNN). The vision-based classifiers categorize the apple as defective and non-defective that can be used for automatic inspection, sorting and further analytics. A total of 550 apple images are collected to test the classifiers. The images consist of 275 non-defective and 275 defective apples. The defective category includes various types of defect and severity. The vision-based classifiers are trained and evaluated according to the K-fold cross-validation. The performances of the classifiers from 2-fold, 3-fold, 4-fold, 5-fold and 10-fold are compared. From the evaluation, SPM with SVM classifier attained 98.15% classification accuracy for 10-fold and outperformed the others. In terms of computational time, CNN with SVM classifier is the fastest. However, minimal time difference is observed between the computational time of CNN and SPM, which were separated by only 0.05 s.
Fulltext Automatic COVID-19 Detection Using Exemplar Hybrid Deep Features with X-ray Images

Barua PD, Muhammad Gowdh NF, Rahmat K, Ramli N, Ng WL, Chan WY, et al.

Int J Environ Res Public Health, 2021 07 29;18(15).
PMID: 34360343 DOI: 10.3390/ijerph18158052

COVID-19 and pneumonia detection using medical images is a topic of immense interest in medical and healthcare research. Various advanced medical imaging and machine learning techniques have been presented to detect these respiratory disorders accurately. In this work, we have proposed a novel COVID-19 detection system using an exemplar and hybrid fused deep feature generator with X-ray images. The proposed Exemplar COVID-19FclNet9 comprises three basic steps: exemplar deep feature generation, iterative feature selection and classification. The novelty of this work is the feature extraction using three pre-trained convolutional neural networks (CNNs) in the presented feature extraction phase. The common aspects of these pre-trained CNNs are that they have three fully connected layers, and these networks are AlexNet, VGG16 and VGG19. The fully connected layer of these networks is used to generate deep features using an exemplar structure, and a nine-feature generation method is obtained. The loss values of these feature extractors are computed, and the best three extractors are selected. The features of the top three fully connected features are merged. An iterative selector is used to select the most informative features. The chosen features are classified using a support vector machine (SVM) classifier. The proposed COVID-19FclNet9 applied nine deep feature extraction methods by using three deep networks together. The most appropriate deep feature generation model selection and iterative feature selection have been employed to utilise their advantages together. By using these techniques, the image classification ability of the used three deep networks has been improved. The presented model is developed using four X-ray image corpora (DB1, DB2, DB3 and DB4) with two, three and four classes. The proposed Exemplar COVID-19FclNet9 achieved a classification accuracy of 97.60%, 89.96%, 98.84% and 99.64% using the SVM classifier with 10-fold cross-validation for four datasets, respectively. Our developed Exemplar COVID-19FclNet9 model has achieved high classification accuracy for all four databases and may be deployed for clinical application.

Filters

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

External Links