This paper describes the use of data analytics tools for predicting the fatigue strength of steels. Several physics-based as well as data-driven approaches have been used to arrive at correlations between various properties of alloys and their compositions and manufacturing process parameters. Data-driven approaches are of significant interest to materials engineers especially in arriving at extreme value properties such as cyclic fatigue, where the current state-of-the-art physics based models have severe limitations. Unfortunately, there is limited amount of documented success in these efforts. In this paper, we explore the application of different data science techniques, including feature selection and predictive modeling, to the fatigue properties of steels, utilizing the data from the National Institute for Material Science (NIMS) public domain database, and present a systematic end-to-end framework for exploring materials informatics. Results demonstrate that several advanced data analytics techniques such as neural networks, decision trees, and multivariate polynomial regression can achieve significant improvement in the prediction accuracy over previous efforts, withR2values over 0.97. The results have successfully demonstrated the utility of such data mining tools for ranking the composition and process parameters in the order of their potential for predicting fatigue strength of steels, and actually develop predictive models for the same.
Detection of true human emotions has attracted a lot of interest in the recent years. The applications range from e-retail to health-care for developing effective companion systems with reliable emotion recognition. This paper proposes heart rate variability (HRV) features extracted from photoplethysmogram (PPG) signal obtained from a cost-effective PPG device such as Pulse Oximeter for detecting and recognizing the emotions on the basis of the physiological signals. The HRV features obtained from both time and frequency domain are used as features for classification of emotions. These features are extracted from the entire PPG signal obtained during emotion elicitation and baseline neutral phase. For analyzing emotion recognition, using the proposed HRV features, standard video stimuli are used. We have considered three emotions namely, happy, sad and neutral or null emotions. Support vector machines are used for developing the models and features are explored to achieve average emotion recognition of 83.8% for the above model and listed features.
1 July 2017 in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Identification of pulmonary diseases comprises of accurate auscultation as well as elaborate and expensive pulmonary function tests. Prior arts have shown that pulmonary diseases lead to abnormal lung sounds such as wheezes and crackles. This paper introduces novel spectral and spectrogram features, which are further refined by Maximal Information Coefficient, leading to the classification of healthy and abnormal lung sounds. A balanced lung sound dataset, consisting of publicly available data and data collected with a low-cost in-house digital stethoscope are used. The performance of the classifier is validated over several randomly selected non-overlapping training and validation samples and tested on separate subjects for two separate test cases: (a) overlapping and (b) non-overlapping data sources in training and testing. The results reveal that the proposed method sustains an accuracy of 80% even for non-overlapping data sources in training and testing.
Mobile smartphones have revolutionized the concept of mobile phones as different apps are built to offer various interesting applications in healthcare, gaming, etc. rather than using the phone only for voice services. The application developers take advantage of onboard sensors, web connectivity and powerful processing units of the smartphones to develop such interesting apps. In this paper, we present an interesting approach where direct acoustic coupling technique is employed to quickly and conveniently convert the smartphones into high quality digital stethoscope by using an ultra-low cost attachment. The design consideration primarily focused on affordability, simplicity and use-friendly aspects into account. The motivation of this work is to enable the heart patients to send their heart sound to doctor's chamber/ hospitals from their home instead of travelling all the way to hospitals/clinics. This is particularly useful in poor or developing countries where there is scarcity of healthcare centers and patients have to travel a long distance to visit the clinic. The situation becomes more serious in case of patients who went through heart surgery and requires follow up visits or for elderly population requiring routine checkups. For both the cases, in many instances, doctors primarily listen to the heart sound to prescribe further actions. Our solution can greatly help such situations and in many cases it can completely eliminate the travel. In addition, since data can also be recorded and saved, this opens up possibility for statistical analysis to further aid the diagnosis / monitoring. Thus, our solution can serve as a viable tool in connected health use cases for heart patients for needy geography.
The alarming statistics of Diabetes Mellitus (DM) Type 2 as the most common and prevalent disease in India and world over [1] has fuelled research in the direction of non-invasive and continuous monitoring of this disease. This paper describes a demonstration of an inexpensive mobile-phone based android application which can collect Photoplethysmogram (PPG) from fingertip via built-in camera and flash and transfer it to a high-end cloud server for early detection of DM. Additionally, this application allows continuous monitoring of DM patients can aid in assisting the short and long-term complication risks. The proposed application is targeted to cater to the inherent demand to for a mobile-based, pervasive system for continuous, non-invasive monitoring and detection of DM. Our application has been successfully deployed on Nexus 5 and tested on controlled and diabetic group with 80% specificity and 84% sensitivity for a 100 patient dataset and presented in this paper.