In the past few decades E-learning in higher education is increased and played a vital role in pandemics like COVID-19. Particularly, online examinations are conducted on e-learning platforms which leads to many security and cheating issues. For this reason, numerous research is available proposed methodologies and techniques for seamless execution of online examination. However, it is hard to find any study that provides the latest systematic literature review of anti-cheat or cheating prediction techniques and the approaches in the literature. We have analyzed 2223 studies. However, after applying inclusion and exclusion criteria 23 studies relevant studies are finalized. The review revealed that there are three types of proctoring, fully live online, recorded & reviewed and fully automated. This study provides a comparative analysis of online examination techniques & tools performed on 23 studies from the last five years 2017 to 2021. Furthermore, in this time duration five leading cheating prevention features are identified.14 important techniques which are mostly used in this time duration are found in which best frequent approach used in literature is NLP and 10 data sets including both public and private are identified. Proceeding toward the proposed solution, a total of 20 tools for the anti-cheat examinations are found. Almost 23 leading existing tools were found in the literature. To narrow down the criteria for adoption factor is analyzed and studies of the online anti-cheat examination solution adoption in different countries are also investigated. Finally, the overall cost of the e-learning infrastructure, specifically the conduction of examinations is determined by comparing the key factors of the global adoption with major online exam features.
Roman Urdu is an informal form of writing the Urdu language which is written in Latin script. It is the language most widely used on the internet, social media, and text messaging by native Urdu speakers. The problem that arises with Roman Urdu is an inconsistent way of writing by different people. No standard rules are defined for writing Roman Urdu which makes it very difficult to perform Natural Language Processing. To overcome this issue, the text needs to be normalized to perform effective analysis. Therefore, this work provides a Roman Urdu dictionary that works as the foundation for processing Roman Urdu. It also proposes a model for the lexical normalization of Roman Urdu text.
To make the internet a more productive environment, it is vital to promote constructiveness in online discussion forums. Customers are regularly offered the chance to share their thoughts and experiences with a product on online marketplaces. Generally, online products have fewer constructive reviews, and some of them are unrelated to the product. Existing approaches focus on textual features to classify a product's constructiveness and ignore semantic and contextual information about the reviews. The directed graph model has been utilized in this study to represent information about the product. Also, the node and graph level features like average in-degree, out-degree, and clustering coefficients are used to model constructiveness in product evaluation to encourage the most informative reviews. Graph embedding techniques are used to depict each node as a vector into low-dimensional space and preserve the structure and properties of the graph as well. The topic modeling approach has been used to contextualize the reviews with the appropriate product. Additionally, we employed logistic regression, random forest, Gaussian naive Bayes, support vector machine (SVM), and Gradient Boosting Machine models trained on Amazon product reviews and constructive news corpus for constructiveness. These ML models outperform the baseline approach, achieving a 90% F1-Score.
Industrial sectors are constantly under pressure to produce higher-quality goods while maximizing yield. Machine maintenance is a critical component of manufacturing, accounting for a significant portion of total production costs. Corrective, preventive, and conditional maintenance strategies only make a negligible contribution to cost and downtime reduction. With the fifth industrial revolution, industrialists can now use sensors and cyber-physical systems to perform predictive maintenance on manufacturing operations. This strategy eliminates unnecessary maintenance and minimizes downtime by continuously collecting and analyzing data to predict time to failure. Numerous approaches to fault prediction have been proposed for predictive maintenance, but most of them are prohibitively expensive due to the massive number of features in manufacturing machines. The purpose of this work is to develop a technique for reliably predicting machine problems with the fewest possible features. To select features, we used SVR-based Recursive Feature Elimination (SVR-RFE) and Random Forest Regressor (RFR), while to predict, we used Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN). Our experiments on the 2018 PHM Challenge Dataset demonstrate that the proposed strategy outperforms prior approaches and reduces the mean absolute percentage error (SMAPE).
The variability in the shape and appearance of the same plant organs and similarity between organs of different plants results in fewer inter-class and high intra-class variations making organ-based plant classification a challenging problem. Classification of plants using a single organ may not be able to deal with these challenges. Thus the use of multiple organs can be more effective in improving the classification performance by learning different aspects of the same class. Existing approaches mainly focus on generic features of plants while ignoring features related to multiple organs. In the proposed approach, Convolutional Neural Network (CNN) is used to exploit the information of multiple organs instead of a single organ for the classification of plants. Moreover, the representation of minority classes is increased through DC GAN. The comparison of the proposed approach with the existing approaches on the publicly available PlantCLEF dataset shows its better performance in the accurate classification of plants.
