A deep learning approach for electric motor fault diagnosis based on modified InceptionV3.

Electric motors are essential equipment widely employed in various sectors. However, factors such as prolonged operation, environmental conditions, and inadequate maintenance make electric motors prone to various failures. In this study, we propose a thermography-based motor fault detection method based on InceptionV3 model. To enhance the detection accuracy, we apply Contrast Limited Adaptive Histogram Equalization (CLAHE) to the input images. Furthermore, we improved the performance of the InceptionV3 by integrating a Squeeze-and-Excitation (SE) channel attention mechanism. The proposed model was tested using a dataset containing 369 thermal images of an electric motor with 11 types of faults. Image augmentation was employed to increase the data size and the evaluation was conducted using fivefold cross validation. Experimental results indicate that the proposed model can achieve accuracy, precision, recall, and F1 score of 98.82%, 98.93%, 98.82%, and 98.87%, respectively. Additionally, by freezing the fully connected layers of the InceptionV3 model for feature extraction and training a Support Vector Machines (SVM) to perform classification, it is able to achieve 100% detection rate across all four evaluation metrics. This research contributes to the field of industrial motor fault diagnosis. By incorporating deep learning techniques based on InceptionV3 and SE channel attention mechanism with a traditional classifier, the proposed method can accurately classify different motor faults.

Physical, mechanical, and microstructural characterisation of tungsten carbide-based polymeric composites for radiation shielding application.

Polymeric based composites have gained considerable attention as potential candidates for advanced radiation shielding applications due to their unique combination of high-density, radiation attenuation properties and improved mechanical strength. This study focuses on the comprehensive characterisation of polymeric based composites for radiation shielding applications. The objective of this study was to evaluate the physical, mechanical and microstructural properties of tungsten carbide-based epoxy resin and tungsten carbide cobalt-based epoxy resin for its efficiency in shielding against gamma-rays ranging from 0.6 up to 1.33 MeV. Polymeric composites with different weight percentages of epoxy resin (40 wt%, 35 wt%, 30 wt%, 25 wt%, 20 wt%, 15 wt% and 10 wt%) were fabricated, investigated and compared to conventional lead shield. The attenuation of the composites was performed using NaI (Tl) gamma-ray spectrometer to investigate the linear and mass attenuation coefficients, half value layer, and mean free path. High filler loadings into epoxy resin matrix (90% filler/10% epoxy) exhibited excellent gamma shielding properties. Mechanical properties, such as hardness were examined to assess the structural integrity and durability of the composites under various conditions. The fabricated composites showed a good resistance, the maximum hardness was attributed to composites with small thickness. The high loading of fillers in the epoxy matrix improved the microhardness of the composites. The distribution of the filler powder within the epoxy matrix was investigated using FESEM/EDX. The results revealed the successful incorporation of tungsten carbide and cobalt particles into the polymer matrix, leading to increased composite density and enhanced radiation attenuation. The unique combination of high-density, radiation attenuation, and improved mechanical properties positions polymeric based composites as promising candidates for radiation protection field.

Convolutional neural network optimized by differential evolution for electrocardiogram classification.

The Coronavirus disease 2019, or COVID-19, has shifted the medical paradigm from face-to-face to telehealth. Telehealth has become a vital resource to contain the virus spread and ensure the continued care of patients. In terms of preventing cardiovascular diseases, automating electrocardiogram (ECG) classification is a promising telehealth intervention. The healthcare service ensures that patient care is appropriate, comfortable, and accessible. Convolutional neural networks (CNNs) have demonstrated promising results in ECG categorization, which require high accuracy and short training time to ensure healthcare quality. This study proposes a one-dimensional-CNN (1D-CNN) arrhythmia classification based on the differential evolution (DE) algorithm to optimize the accuracy of ECG classification and training time. The performance of 1D-CNNs of different activation functions are optimized based on the standard DE algorithm. Finally, based on MIT-BIH and SCDH arrhythmia databases, the performances of optimized and unoptimized 1D-CNN are compared and analysed. Results show that the 1D-CNN optimized by the DE has higher accuracy in heartbeats classification. The optimized 1D-CNN improves from 97.6% to 99.5% on MIT-BIH and from 80.2% to 88.5% on SCDH. Therefore, the optimized 1D-CNN shows improvements of 1.9% and 8.3% in the two datasets, respectively. In addition, compared with the unoptimized 1D-CNN based on the same parameter settings, the optimized 1D-CNN has less training time. Under the conditions of ReLU function and 10 epochs, the training takes 9.22 s on MIT-BIH and 10.35 s on SCDH, reducing training time by 67.2% and 64.2%, respectively.

Disruption of white matter integrity and its relationship with cognitive function in non-severe traumatic brain injury.

Background: Impairment in cognitive function is a recognized outcome of traumatic brain injury (TBI). However, the degree of impairment has variable relationship with TBI severity and time post injury. The underlying pathology is often due to diffuse axonal injury that has been found even in mild TBI. In this study, we examine the state of white matter putative connectivity in patients with non-severe TBI in the subacute phase, i.e., within 10 weeks of injury and determine its relationship with neuropsychological scores. Methods: We conducted a case-control prospective study involving 11 male adult patients with non-severe TBI and an age-matched control group of 11 adult male volunteers. Diffusion MRI scanning and neuropsychological tests were administered within 10 weeks post injury. The difference in fractional anisotropy (FA) values between the patient and control groups was examined using tract-based spatial statistics. The FA values that were significantly different between patients and controls were then correlated with neuropsychological tests in the patient group. Results: Several clusters with peak voxels of significant FA reductions (p < 0.05) in the white matter skeleton were seen in patients compared to the control group. These clusters were located in the superior fronto-occipital fasciculus, superior longitudinal fasciculus, uncinate fasciculus, and cingulum, as well as white matter fibers in the area of genu of corpus callosum, anterior corona radiata, superior corona radiata, anterior thalamic radiation and part of inferior frontal gyrus. Mean global FA magnitude correlated significantly with MAVLT immediate recall scores while matrix reasoning scores correlated positively with FA values in the area of right superior fronto-occipital fasciculus and left anterior corona radiata. Conclusion: The non-severe TBI patients had abnormally reduced FA values in multiple regions compared to controls that correlated with several measures of executive function during the sub-acute phase of TBI.

Alteration in the Functional Organization of the Default Mode Network Following Closed Non-severe Traumatic Brain Injury.

The debilitating effect of traumatic brain injury (TBI) extends years after the initial injury and hampers the recovery process and quality of life. In this study, we explore the functional reorganization of the default mode network (DMN) of those affected with non-severe TBI. Traumatic brain injury (TBI) is a wide-spectrum disease that has heterogeneous effects on its victims and impacts everyday functioning. The functional disruption of the default mode network (DMN) after TBI has been established, but its link to causal effective connectivity remains to be explored. This study investigated the differences in the DMN between healthy participants and mild and moderate TBI, in terms of functional and effective connectivity using resting-state functional magnetic resonance imaging (fMRI). Nineteen non-severe TBI (mean age 30.84 ± 14.56) and twenty-two healthy (HC; mean age 27.23 ± 6.32) participants were recruited for this study. Resting-state fMRI data were obtained at the subacute phase (mean days 40.63 ± 10.14) and analyzed for functional activation and connectivity, independent component analysis, and effective connectivity within and between the DMN. Neuropsychological tests were also performed to assess the cognitive and memory domains. Compared to the HC, the TBI group exhibited lower activation in the thalamus, as well as significant functional hypoconnectivity between DMN and LN. Within the DMN nodes, decreased activations were detected in the left inferior parietal lobule, precuneus, and right superior frontal gyrus. Altered effective connectivities were also observed in the TBI group and were linked to the diminished activation in the left parietal region and precuneus. With regard to intra-DMN connectivity within the TBI group, positive correlations were found in verbal and visual memory with the language network, while a negative correlation was found in the cognitive domain with the visual network. Our results suggested that aberrant activities and functional connectivities within the DMN and with other RSNs were accompanied by the altered effective connectivities in the TBI group. These alterations were associated with impaired cognitive and memory domains in the TBI group, in particular within the language domain. These findings may provide insight for future TBI observational and interventional research.

Neural alterations in working memory of mild-moderate TBI: An fMRI study in Malaysia.

Working memory (WM) encompasses crucial cognitive processes or abilities to retain and manipulate temporary information for immediate execution of complex cognitive tasks in daily functioning such as reasoning and decision-making. The WM of individuals sustaining traumatic brain injury (TBI) was commonly compromised, especially in the domain of WM. The current study investigated the brain responses of WM in a group of participants with mild-moderate TBI compared to their healthy counterparts employing functional magnetic resonance imaging. All consented participants (healthy: n = 26 and TBI: n = 15) performed two variations of the n-back WM task with four load conditions (0-, 1-, 2-, and 3-back). The respective within-group effects showed a right hemisphere-dominance activation and slower reaction in performance for the TBI group. Random-effects analysis revealed activation difference between the two groups in the right occipital lobe in the guided n-back with cues, and in the bilateral occipital lobe, superior parietal region, and cingulate cortices in the n-back without cues. The left middle frontal gyrus was implicated in the load-dependent processing of WM in both groups. Further group analysis identified that the notable activation changes in the frontal gyri and anterior cingulate cortex are according to low and high loads. Though relatively smaller in scale, this study was eminent as it clarified the neural alterations in WM in the mild-moderate TBI group compared to healthy controls. It confirmed the robustness of the phenomenon in TBI with the reproducibility of the results in a heterogeneous non-Western sample.

Interactive Blood Vessel Segmentation from Retinal Fundus Image Based on Canny Edge Detector.

Optometrists, ophthalmologists, orthoptists, and other trained medical professionals use fundus photography to monitor the progression of certain eye conditions or diseases. Segmentation of the vessel tree is an essential process of retinal analysis. In this paper, an interactive blood vessel segmentation from retinal fundus image based on Canny edge detection is proposed. Semi-automated segmentation of specific vessels can be done by simply moving the cursor across a particular vessel. The pre-processing stage includes the green color channel extraction, applying Contrast Limited Adaptive Histogram Equalization (CLAHE), and retinal outline removal. After that, the edge detection techniques, which are based on the Canny algorithm, will be applied. The vessels will be selected interactively on the developed graphical user interface (GUI). The program will draw out the vessel edges. After that, those vessel edges will be segmented to bring focus on its details or detect the abnormal vessel. This proposed approach is useful because different edge detection parameter settings can be applied to the same image to highlight particular vessels for analysis or presentation.

Neovascularization Detection and Localization in Fundus Images Using Deep Learning.

Proliferative Diabetic Retinopathy (PDR) is a severe retinal disease that threatens diabetic patients. It is characterized by neovascularization in the retina and the optic disk. PDR clinical features contain highly intense retinal neovascularization and fibrous spreads, leading to visual distortion if not controlled. Different image processing techniques have been proposed to detect and diagnose neovascularization from fundus images. Recently, deep learning methods are getting popular in neovascularization detection due to artificial intelligence advancement in biomedical image processing. This paper presents a semantic segmentation convolutional neural network architecture for neovascularization detection. First, image pre-processing steps were applied to enhance the fundus images. Then, the images were divided into small patches, forming a training set, a validation set, and a testing set. A semantic segmentation convolutional neural network was designed and trained to detect the neovascularization regions on the images. Finally, the network was tested using the testing set for performance evaluation. The proposed model is entirely automated in detecting and localizing neovascularization lesions, which is not possible with previously published methods. Evaluation results showed that the model could achieve accuracy, sensitivity, specificity, precision, Jaccard similarity, and Dice similarity of 0.9948, 0.8772, 0.9976, 0.8696, 0.7643, and 0.8466, respectively. We demonstrated that this model could outperform other convolutional neural network models in neovascularization detection.

Classification of Non-Severe Traumatic Brain Injury from Resting-State EEG Signal Using LSTM Network with ECOC-SVM.

Traumatic brain injury (TBI) is one of the common injuries when the human head receives an impact due to an accident or fall and is one of the most frequently submitted insurance claims. However, it is often always misused when individuals attempt an insurance fraud claim by providing false medical conditions. Therefore, there is a need for an instant brain condition classification system. This study presents a novel classification architecture that can classify non-severe TBI patients and healthy subjects employing resting-state electroencephalogram (EEG) as the input, solving the immobility issue of the computed tomography (CT) scan and magnetic resonance imaging (MRI). The proposed architecture makes use of long short term memory (LSTM) and error-correcting output coding support vector machine (ECOC-SVM) to perform multiclass classification. The pre-processed EEG time series are supplied to the network by each time step, where important information from the previous time step will be remembered by the LSTM cell. Activations from the LSTM cell is used to train an ECOC-SVM. The temporal advantages of the EEG were amplified and able to achieve a classification accuracy of 100%. The proposed method was compared to existing works in the literature, and it is shown that the proposed method is superior in terms of classification accuracy, sensitivity, specificity, and precision.

Detection of Moderate Traumatic Brain Injury from Resting-State Eye-Closed Electroencephalography.

Traumatic brain injury (TBI) is one of the injuries that can bring serious consequences if medical attention has been delayed. Commonly, analysis of computed tomography (CT) or magnetic resonance imaging (MRI) is required to determine the severity of a moderate TBI patient. However, due to the rising number of TBI patients these days, employing the CT scan or MRI scan to every potential patient is not only expensive, but also time consuming. Therefore, in this paper, we investigate the possibility of using electroencephalography (EEG) with computational intelligence as an alternative approach to detect the severity of moderate TBI patients. EEG procedure is much cheaper than CT or MRI. Although EEG does not have high spatial resolutions as compared with CT and MRI, it has high temporal resolutions. The analysis and prediction of moderate TBI from EEG using conventional computational intelligence approaches are tedious as they normally involve complex preprocessing, feature extraction, or feature selection of the signal. Thus, we propose an approach that uses convolutional neural network (CNN) to automatically classify healthy subjects and moderate TBI patients. The input to this computational intelligence system is the resting-state eye-closed EEG, without undergoing preprocessing and feature selection. The EEG dataset used includes 15 healthy volunteers and 15 moderate TBI patients, which is acquired at the Hospital Universiti Sains Malaysia, Kelantan, Malaysia. The performance of the proposed method has been compared with four other existing methods. With the average classification accuracy of 72.46%, the proposed method outperforms the other four methods. This result indicates that the proposed method has the potential to be used as a preliminary screening for moderate TBI, for selection of the patients for further diagnosis and treatment planning.

Arrangements of Resting State Electroencephalography as the Input to Convolutional Neural Network for Biometric Identification.

Biometric is an important field that enables identification of an individual to access their sensitive information and asset. In recent years, electroencephalography- (EEG-) based biometrics have been popularly explored by researchers because EEG is able to distinct between two individuals. The literature reviews have shown that convolutional neural network (CNN) is one of the classification approaches that can avoid the complex stages of preprocessing, feature extraction, and feature selection. Therefore, CNN is suggested to be one of the efficient classifiers for biometric identification. Conventionally, input to CNN can be in image or matrix form. The objective of this paper is to explore the arrangement of EEG for CNN input to investigate the most suitable input arrangement of EEG towards the performance of EEG-based identification. EEG datasets that are used in this paper are resting state eyes open (REO) and resting state eyes close (REC) EEG. Six types of data arrangement are compared in this paper. They are matrix of amplitude versus time, matrix of energy versus time, matrix of amplitude versus time for rearranged channels, image of amplitude versus time, image of energy versus time, and image of amplitude versus time for rearranged channels. It was found that the matrix of amplitude versus time for each rearranged channels using the combination of REC and REO performed the best for biometric identification, achieving validation accuracy and test accuracy of 83.21% and 79.08%, respectively.

Intelligent color vision system for ripeness classification of oil palm fresh fruit bunch.

Ripeness classification of oil palm fresh fruit bunches (FFBs) during harvesting is important to ensure that they are harvested during optimum stage for maximum oil production. This paper presents the application of color vision for automated ripeness classification of oil palm FFB. Images of oil palm FFBs of type DxP Yangambi were collected and analyzed using digital image processing techniques. Then the color features were extracted from those images and used as the inputs for Artificial Neural Network (ANN) learning. The performance of the ANN for ripeness classification of oil palm FFB was investigated using two methods: training ANN with full features and training ANN with reduced features based on the Principal Component Analysis (PCA) data reduction technique. Results showed that compared with using full features in ANN, using the ANN trained with reduced features can improve the classification accuracy by 1.66% and is more effective in developing an automated ripeness classifier for oil palm FFB. The developed ripeness classifier can act as a sensor in determining the correct oil palm FFB ripeness category.

Medical image fusion scheme using complex contourlet transform based on PCA.

We present an efficient method for the fusion of medical captured images using different modalities that enhances the original images and combines the complementary information of the various modalities. The contourlet transform has mainly been employed as a fusion technique for images obtained from equal or different modalities. The limitation of directional information of dual-tree complex wavelet (DT-CWT) is rectified in dual-tree complex contourlet transform (DT-CCT) by incorporating directional filter banks (DFB) into the DT-CWT. The DT-CCT produces images with improved contours and textures, while the property of shift invariance is retained. To improve the fused image quality, we propose a new method for fusion rules based on principle component analysis (PCA) which depend on frequency component of DT-CCT coefficients (contourlet domain). For low frequency components, PCA method is adopted and for high frequency components, the salient features are picked up based on local energy. The final fusion image is obtained by directly applying inverse dual tree complex contourlet transform (IDT-CCT) to the fused low and high frequency components. The experimental results showed that the proposed method produces fixed image with extensive features on multimodality.