Multiclass Non-Randomized Spectral–Spatial Active Learning for Hyperspectral Image Classification

An extended DeLone and McLean's model to determine the success factors of e-learning platform

Due to the COVID-19 pandemic, all Saudi universities have adopted e-learning systems to ensure that educational activities continue. Shaqra University adopted a platform called the Shaqra University e-learning platform. This study aimed to identify the factors contributing to the success of that platform in Shaqra University, based on students' responses. This research has proposed an extension of well-known DeLone and McLean's Information Systems Success (D&M ISS) model to check and validate the success factors of the Shaqra University platform. The questionnaire was adopted in this study to collect data from students currently enrolled at Shaqra University. One thousand online links to the questionnaire were randomly distributed among current students enrolled in Shaqra University. The results revealed that the instrument adopted in this study was valid and reliable. Also, the results showed that the model was a good fit for the Saudi context. The proposed factors of instructor's quality, learner quality, and perceived usefulness positively impacted the e-learning platform. On the other hand, the factors information quality, system quality and service quality had no positive impact on the use of the e-learning platform.

Spatiotemporal Analysis of Web News Archives for Crime Prediction

In today’s world, security is the most prominent aspect which has been given higher priority. Despite the rapid growth and usage of digital devices, lucrative measurement of crimes in under-developing countries is still challenging. In this work, unstructural crime data (900 records) from the news archives of the previous eight years were extracted to predict the behavior of criminals’ networks and transform it into useful information using natural language processing (NLP). To estimate the next move of criminals in Pakistan, we performed hotspot-based spatial analysis. Later, this information is fed to two different classifiers for possible identification and prediction. We achieved the maximum accuracy of 92% using K-Nearest Neighbor (KNN) and 62% using the Random Forest algorithm. In terms of crimes, the results showed that the most prevalent crime events are robberies. Thus, the usage of digital information archives, spatial analysis, and machine learning techniques can open new ways of handling a peaceful and sustainable society in eradicating crimes for countries having paucity of financial resources.

Hyperspectral Imaging for Minced Meat Classification Using Nonlinear Deep Features

Minced meat substitution is one of the most common forms of food fraud in the meat industry. Recently, Hyperspectral Imaging (HSI) has been used for the classification and identification of minced meat types. However, conventional methods are based only on spectral information and ignore the spatial variability of the data. Moreover, these methods first tend to reduce the size of the data, which to some extent ignores the abstract level information and does not preserve the spatial information. Therefore, this work proposes a novel Isos-bestic wavelength reduction method for the different minced meat types, by retaining only Myoglobin pigments (Mb) in the meat spectra. A total of 60 HSI cubes are acquired using Fx 10 Hyperspectral sensor. For each HSI cube, a set of preprocessing schemes is applied to extract the Region of Interest (ROI) and spectral preprocessing, i.e., Golay filtering. Later, these preprocessed HSI cubes are fed into a 3D-Convolutional Neural Network (3D-CNN) model for nonlinear feature extraction and classification. The proposed pipeline outperformed several state-of-the-art methods, with an overall accuracy of 94.0%.

Myoglobin-Based Classification of Minced Meat Using Hyperspectral Imaging

Minced meat substitution is one of the most common frauds which not only affects consumer health but impacts their lifestyles and religious customs as well. A number of methods have been proposed to overcome these frauds; however, these mostly rely on laboratory measures and are often subject to human error. Therefore, this study proposes novel hyperspectral imaging (400–1000 nm) based non-destructive isos-bestic myoglobin (Mb) spectral features for minced meat classification. A total of 60 minced meat spectral cubes were pre-processed using true-color image formulation to extract regions of interest, which were further normalized using the Savitzky–Golay filtering technique. The proposed pipeline outperformed several state-of-the-art methods by achieving an average accuracy of 88.88%.

Hyperspectral Imaging for Color Adulteration Detection in Red Chili

The quality of red chili is characterized based on its color and pungency. Several factors like humidity, temperature, light, and storage conditions affect the characteristic qualities of red chili, thus preservation required several measures. Instead of ensuring these measures, traders are using oil and Sudan dye in red chili to increase the value of an inferior product. Thus, this work presents the feasibility of utilizing a hyperspectral camera for the detection of oil and Sudan dye in red chili. This study describes the important wavelengths (500–700 nm) where different adulteration affects the response of the reflected spectrum. These wavelengths are then utilized for training an Support Vector Machine (SVM) algorithm to detect pure, oil-adulterated, and Sudan dye-adulterated red chili. The classification performance achieves 97% with the reduced dimensionality and 100% with complete validation data. The trained algorithm is further tested on separate data with different adulteration levels in comparison to the training data. Results show that the algorithm successfully classifies pure, oil-adulterated, and Sudan-adulterated red chili with an accuracy of 100%.