Acoustical investigation of infant cries has been a clinical and research focus in the recent years. Findings of several studies reveal the importance of cry as a useful window for early detection of several diseases and communication difficulties such as hearing impairment, intellectual disabilities, cerebral palsy etc. This motivates us to use a minimal interface system that can automatically classify infant cries into normal and pathological with the help of state-of-the-art machine learning strategies. In this paper, we propose a software program for screening infants based on their cries. The proposed system is able to detect & classify infant cries into normal and pathological based on the acoustic input. To build and train the system, infant cries of normal and Low Birth Weight (LBW) newborn within 7 days of birth were considered. A pain induced cry elicited using the routine intramuscular immunization was recorded using a standard Olympus LS-100 recorder which was held about 10 centimetres away from the infant’s mouth. The acoustic correlates of these cries were used to build the software tool. Artificial Neural Network was employed to improve its functionality. Therefore, we propose a screening tool for further accessibility and large-scale implementation.
Texts are composed for multiple audiences and for numerous purposes. Each form of text follows a set of guidelines and structure to serve the purpose of writing. A common way of grouping texts is into text types. Describing these text types in terms of their linguistic characteristics is called ‘linguistic profiling of texts’. In this paper, we highlight the linguistic features that characterize a text type. The findings of the present study highlight the importance of parts of speech distribution and tenses as the most important microscopic linguistic characteristics of the text. Additionally, we demonstrate the importance of other linguistic characteristics of texts and their relative importance (top 25th, 50th and 75th percentile) in linguistic profiling. The results are discussed with the use case of genre and subgenre classifications with classification accuracies of 89 and 73 percentile, respectively.
Text classification is a prevalent and essential machine-learning task. Machine learning classifiers have developed immensely since their inception. The naïve Bayes classifier is one of the most prominent supervised machine learning classifiers. In this experiment, we highlight the performance of Naïve Bayes for classifying of authors/artists on the German lyrics corpus (“Songkorpus”) and compare the classification results with other classifier algorithms. The corpus of investigation consists of six artists with 970 songs in total. Bayes model evaluation measures revealed a precision of 0.91, recall of 0.94, and F1-measure of 0.9. Furthermore, the classification performance with other classifier algorithms did not reveal any statistically significant difference in performance. The results of the study add to the high volume of reports on the classification accuracy of Naive Bayes for the task of lyrical classification.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.