Fusing Deep Learning with Support Vector Machines to Detect COVID-19 in X-Ray Images

Deep neural networks are powerful learning machines that have laid foundations for most of the recent advancements in data analysis. Their most important advantage lies in learning how to extract the features from raw data, and these deep features are later classified with fully-connected layers. Although there exist more effective classifiers, including support vector machines, their high computational complexity is a serious obstacle in using them for classifying highly-dimensional and often huge datasets of deep features. We introduce a new framework which allows us to classify the deep features with evolutionarily-optimized support vector machines and we apply it to a real-life problem of detecting COVID-19 from X-ray images. We demonstrate that the proposed approach is highly effective and it outperforms well-established transfer learning strategies, thus improving the potential of existing pre-trained deep models. It can be particularly beneficial in cases when the amount and quality of labeled data is insufficient for performing full training of a network, but still too large for training a regular support vector machine. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Mobile e-Learning Platform for Audio-Tactile Graphics Presentation

The use of multimedia in education means that more and more information is presented graphically. However, it limits the education of blind people, especially in science, where graphical content is the most often way of presenting the information. One of the commonly used alternative forms of graphic presentation is tactile graphics with descriptions in braille. Nonetheless, in the case of complex pictures, this form of presentation is insufficient for a blind student, and reading the tactile pictures often requires an assistant’s help. In the paper, we present a developed e-learning platform for audio-tactile graphics presentation for the blinds dedicated to standard Android tablets, whose advantage is the automatic adaptation of interactive audio descriptions to the student’s level of knowledge. The platform also enables the automatic assessment of the student's knowledge and exercise selection assigned to the appropriate knowledge level. The paper also presents the research results regarding the effectiveness of self-learning using our platform on two age groups of blind students while solving math exercises. The obtained research results show that the developed platform and the proposed method of verifying students’ knowledge and selecting exercises positively influence the improvement of learning effectiveness. The platform can be used during the traditional lesson at school and also for self-learning which makes it especially desirable during the Coronavirus pandemic. © 2022, Springer Nature Switzerland AG.