Search

COVID-19 which was announced as a pandemic on 11 March 2020, is still infecting millions to date as the vaccines that have been developed do not prevent the disease but rather reduce the severity of the symptoms. Until a vaccine is developed that can prevent COVID-19 infection, the testing of individuals will be a continuous process. Medical personnel monitor and treat all health conditions; hence, the time-consuming process to monitor and test all individuals for COVID-19 becomes an impossible task, especially as COVID-19 shares similar symptoms with the common cold and pneumonia. Some off-the-counter tests have been developed and sold, but they are unreliable and add an additional burden because false-positive cases have to visit hospitals and perform specialized diagnostic tests to confirm the diagnosis. Therefore, the need for systems that can automatically detect and diagnose COVID-19 automatically without human intervention is still an urgent priority and will remain so because the same technology can be used for future pandemics and other health conditions. In this paper, we propose a modified machine learning (ML) process that integrates deep learning (DL) algorithms for feature extraction and well-known classifiers that can accurately detect and diagnose COVID-19 from chest CT scans. Publicly available datasets were made available by the China Consortium for Chest CT Image Investigation (CC-CCII). The highest average accuracy obtained was 99.9% using the modified ML process when 2000 features were extracted using GoogleNet and ResNet18 and using the support vector machine (SVM) classifier. The results obtained using the modified ML process were higher when compared to similar methods reported in the extant literature using the same datasets or different datasets of similar size; thus, this study is considered of added value to the current body of knowledge. Further research in this field is required to develop methods that can be applied in hospitals and can better equip mankind to be prepared for any future pandemics.

Automating hate speech or inappropriate text detection in social media and other internet platforms is gaining a lot of interest and becoming a valuable research topic for both industry and academia in recent years. It is more important for applications to identify the disruptive contents, understand sentiment analysis, identify cyber bullying, detect flames, threats, hatred towards people or particular communities or groups etc. Text classification is a very challenging task due to the nature and complexities with languages, especially its context, micro words, emojis, typo error and sarcasm present in the text. In this paper, we have proposed a model with a novel approach for generating hybrid features for an effective feature representation to classify hate speech. We have combined features learned from deep learning methods with the semantic features like word n-grams and tweets specific syntactic features to form hybrid feature sets. We have also improvised preprocessing steps to reduce the number of missing embeddings to increase the vocabulary for efficient feature learning. We have experimented with the various neural networks for feature learning and machine learning models with hybrid features for classification. Our work delivers hybrid features and appropriate preprocessing techniques for an efficient classification of the standard dataset of 16k annotated hate speech tweets. The combination of Long Short Term Memory (LSTM) trained on Random Embeddings for deep learning features extraction and Logistic Regression (LR) as a classifier with the hybrid features is found to be the best model and it outperforms the state of the art reported in the literature.

In robotic applications, highly specific objects such as industrial parts, for example, often need to be recognized. In these cases methods can’t rely on the online availability of large labeled training data sets or pre-trained models. This is especially true for depth data, thus making it challenging for deep learning (DL) approaches. Therefore, this work analyzes the performance of various traditional (global or part-based) and DL features on a restricted depth data set, depending on the tasks complexity. While the sample size is small, we can conclude that pre-trained DL descriptors are the most descriptive, but not by a statistically significant margin and therefore part-based descriptors are still a viable option for small, but difficult 3D data sets.