This paper presents an algorithm for the detection of micro-crack defects in the multicrystalline solar cells. This detection goal is very challenging due to the presence of various types of image anomalies like dislocation clusters, grain boundaries, and other artifacts due to the spurious discontinuities in the gray levels. In this work, an algorithm featuring an improved anisotropic diffusion filter and advanced image segmentation technique is proposed. The methods and procedures are assessed using 600 electroluminescence images, comprising 313 intact and 287 defected samples. Results indicate that the methods and procedures can accurately detect micro-crack in solar cells with sensitivity, specificity, and accuracy averaging at 97%, 80%, and 88%, respectively.
This paper presents a review of the machine detection systems for micro-crack inspection of solar wafers and cells. To-date, there are various methods and procedures that have been developed at various laboratories around the world to inspect solar wafers and solar cells for manufacturing defects. This paper on micro-crack detection offers a comprehensive and an up-to-date review of different detection strategies, describing the main features of each technique together with its strengths as well as weaknesses. This paper will benefit researchers and practitioners, especially those who want to develop automatic inspection systems for inspecting solar wafers or solar cells for micro-cracks.
A wideband hybrid dielectric resonator antenna (DRA) consisting of a rectangular slot patch and a perforated stacked cylindrical dielectric resonator (DR) is proposed. A rectangular slot was etched on the grounding side of a microwave laminate (ϵs =3.38) to excite the hybrid resonator at a high frequency. The stacked DR used consists of three different layers of permittivity, in which air-cavity was introduced internally to form a perforated structure. With a proper stacking arrangement of the perforated DRs on top of the rectangular slot, their operating frequencies were merged together to produce a wideband hybrid DRA. It was found that the combination of the stacked DR with perforated structure in the hybrid element had yielded an impedance bandwidth of as wide as 75.8% (12.2 GHz - 27.1 GHz). Huge improvement in bandwidth was successfully achieved in this study in comparison to that without a perforated structure of only 48.9%. Simulation of the antenna was performed in time domain using Computer Simulation Technology (CST) and was subsequently verified with the measurement results. The average simulated and measured directivity of the antenna were recorded to be 6.05 dBi and 5.65 dBi, respectively, with a stable broadside radiation throughout the operating range of frequency. The radiation characteristics were seen to be broadside in both the E-plane and H-plane.
2 June 2019 in Computational Intelligence and Neuroscience
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.
A sudden blow or jolt to the human brain called traumatic brain injury (TBI) is one of the most common injuries recorded in the health insurance claim. Generally, computed tomography (CT) or magnetic resonance imaging (MRI) is required to identify the trauma's severity. Unfortunately, CT and MRI equipment are bulky, expensive, and not always available, limiting their use in TBI detection. Therefore, as an alternative, this study presents a novel classification architecture that can classify non-severe TBI patients from healthy subjects by using resting-state electroencephalogram (EEG) as the input. The proposed architecture employs a convolutional neural network (CNN), and error-correcting output codes support vector machine (ECOC-SVM) to perform automated feature extraction and multi-class classification. In this architecture, complex feature selection and extraction steps are avoided. The proposed architecture attained a high-performance classification accuracy of 99.76%, potentially being used as a classification approach to preventing healthcare insurance fraud. The proposed method is compared to existing studies in the literature. The outcome from the comparisons indicates that the proposed method has outperformed the benchmarked methods by presenting the highest classification accuracy and precision.