Advanced techniques for collecting statistical data

“Advanced Techniques for Collecting Statistical Data” is an edited book consisting of 17 contemporaneous articles focused on data collection methods, from qualitative research techniques to automated data collection systems. The first chapters include a practical guide to designing, sampling, and collecting qualitative research data. The second part of the book is devoted to data mining of information collected from clinical and social studies surveys, as well as from social media. The final chapters reflect on current efforts to optimize and automate data collection procedures. This book also includes new methodologies based on automatic data collection and analysis systems based on smartphone technology and Artificial Intelligence (AI), as well as their application in clinical research, sociology, stock market prediction and other fields. This book is intended to reach an academic audience ranging from undergraduate students to junior researchers. Smartphone technologies combined with the improvement of cloud-based research architecture offers great opportunities in social sciences. The most common methodology in the social sciences is still the use of surveys and other approaches that require the active participation of research subjects. However, there are some areas that are best researched not through surveys, but rather by observing individuals’ behaviour in a continuous social experiment. Mobile technologies make it possible to observe behaviour on a new level by using raw data of various kinds collected by our most common everyday companion: our smartphone. Moreover, since smartphones shape our daily lives thanks to various actions available through countless apps, it is logical to consider them as a platform for actual research. There have been numerous research projects that have relied on collecting participants’ mobile sensor and app usage data, but the biggest concern has been the willingness to share this data. Privacy and trust concerns both contribute to people’s unwillingness to provide access to their personal data, and uncovering these attitudes is a critical step for any successful experimental design. In this paper, we present the results of our pre-experimental survey to uncover prospective participants’ attitudes toward sharing their mobile sensor and app usage data. This experiment is part of a larger research and software development project aimed at creating a modular active and passive data collection tool for smartphones that could be used in social and health research. Passive data collection, on the other hand, means that sensor data from the smartphone is collected and sent periodically without the participant knowing that data was collected at any given time. There are various sensors that can be used in a smartphone: multiple location-based sensors (GPS, gyroscopes), accelerometers, audio sensors, Bluetooth radios, Wi-Fi antennas, and with the advancement of technology, many other sensors–such as pulse or blood pressure sensors. In the field of healthcare, such passive data collection is becoming the main solution for health monitoring in the elderly or in other special scenarios. The application of Big Data not only brings us great convenience, but also brings social problems such as Big Data “familiar”, information leakage and so on, which seriously affects customers’ willingness to participate and their satisfaction with the enterprise. How to collect customer information in order to improve customers’ willingness to participate is an urgent topic to be discussed. This paper proposes an analytical framework, which considers that the decision-making of Big Data objects participating in the Big Data collection process is a process of comprehensive value balance, including four types of CO creation, inducement, dedication and fishing, involving two dimensions of activity value and data value, and the necessity of procedure, activity value, information sensitivity, process complexity, data security and procedure From the six aspects of value judgment, this paper may provide useful enlightenment and reference for Big Data subjects to choose the target data collection method of Big Data application and improve the participation willingness of Big Data objects. The current study aims to propose artificial intelligence-based body sensor network framework (AIBSNF), a framework for strategic use of body sensor networks (BSN), which combines with real-time location system (RTLS) and wearable biosensors to collect multivariate, low noise, and high-fidelity data. This facilitates gathering of time-synchronized location and physiological vitals data, which allows artificial intelligence and machine learning (AI/ML)-based time series analysis. The study gives a brief overview of wearable sensor technology, RTLS, and provides use cases of AI/ML algorithms in the field of sensor fusion. The study also elaborates sample scenarios using a specific sensor network consisting of pressure sensors (insoles), accelerometers, gyroscopes, ECG, EMG, and RTLS position detectors for particular applications in the field of health care and sports. The AIBSNF may provide a solid blueprint for conducting research and development, forming a smooth end-to-end pipeline from data collection using BSN, RTLS and final stage analytics based on AI/ML algorithms.