Chelsea Dobbins

Prediction of preterm deliveries from EHG signals using machine learning.

There has been some improvement in the treatment of preterm infants, which has helped to increase their chance of survival. However, the rate of premature births is still globally increasing. As a result, this group of infants are most at risk of developing severe medical conditions that can affect the respiratory, gastrointestinal, immune, central nervous, auditory and visual systems. In extreme cases, this can also lead to long-term conditions, such as cerebral palsy, mental retardation, learning difficulties, including poor health and growth. In the US alone, the societal and economic cost of preterm births, in 2005, was estimated to be

Scalable Daily Human Behavioral Pattern Mining from Multivariate Temporal Data

26.2 billion, per annum. In the UK, this value was close to £2.95 billion, in 2009. Many believe that a better understanding of why preterm births occur, and a strategic focus on prevention, will help to improve the health of children and reduce healthcare costs. At present, most methods of preterm birth prediction are subjective. However, a strong body of evidence suggests the analysis of uterine electrical signals (Electrohysterography), could provide a viable way of diagnosing true labour and predict preterm deliveries. Most Electrohysterography studies focus on true labour detection during the final seven days, before labour. The challenge is to utilise Electrohysterography techniques to predict preterm delivery earlier in the pregnancy. This paper explores this idea further and presents a supervised machine learning approach that classifies term and preterm records, using an open source dataset containing 300 records (38 preterm and 262 term). The synthetic minority oversampling technique is used to oversample the minority preterm class, and cross validation techniques, are used to evaluate the dataset against other similar studies. Our approach shows an improvement on existing studies with 96% sensitivity, 90% specificity, and a 95% area under the curve value with 8% global error using the polynomial classifier.

Advanced Artificial Neural Network Classification for Detecting Preterm Births Using EHG Records

This work introduces a set of scalable algorithms to identify patterns of human daily behaviors. These patterns are extracted from multivariate temporal data that have been collected from smartphones. We have exploited sensors that are available on these devices, and have identified frequent behavioral patterns with a temporal granularity, which has been inspired by the way individuals segment time into events. These patterns are helpful to both end-users and third parties who provide services based on this information. We have demonstrated our approach on two real-world datasets and showed that our pattern identification algorithms are scalable. This scalability makes analysis on resource constrained and small devices such as smartwatches feasible. Traditional data analysis systems are usually operated in a remote system outside the device. This is largely due to the lack of scalability originating from software and hardware restrictions of mobile/wearable devices. By analyzing the data on the device, the user has the control over the data, i.e., privacy, and the network costs will also be removed.

The utilization of data analysis techniques in predicting student performance in massive open online courses (MOOCs)

Abstract Globally, the rate of preterm births are increasing, thus resulting in significant health, development and economic problems. Current methods for the early detection of such births are inadequate. Nevertheless, there has been some evidence that the analysis of uterine electrical signals, collected from the abdominal surface, could provide an independent and easier way to diagnose true labour and detect the onset of preterm delivery. Using advanced machine learning algorithms, in conjunction with Electrohysterography signal processing, numerous studies have focused on detecting true labour several days prior to the event. However, in this paper, the Electrohysterography signals have been used to detect preterm births. This has been achieved using an open dataset, which contains 262 records for women who delivered at term and 38 who delivered prematurely. Several new features from Electromyography studies have been utilised, as well as feature-ranking techniques to determine their discriminative capabilities in detecting term and preterm records. Seven different artificial neural networks were then used to identify these records. The results illustrate that the combination of the Levenberg–Marquardt trained Feed-Forward Neural Network, Radial Basis Function Neural Network and the Random Neural Network classifiers performed the best, with 91% for sensitivity, 84% for specificity, 94% for the area under the curve and 12% for the mean error rate.

Lesson Learned from Collecting Quantified Self Information via Mobile and Wearable Devices

The growth of the Internet has enabled the popularity of open online learning platforms to increase over the years. This has led to the inception of Massive Open Online Courses (MOOCs) that globally enrol millions of people. Such courses operate under the concept of open learning, where content does not have to be delivered via standard mechanisms that institutions employ, such as physically attending lectures. Instead learning occurs online via recorded lecture material and online tasks. This shift has allowed more people to gain access to education, regardless of their learning background. However, despite these advancements, completion rates for MOOCs are low. The paper presents our approach to learner predication in MOOCs by exploring the impact that technology has on open learning and identifies how data about student performance can be captured to predict trend so that at risk students can be identified before they drop-out. The study we have undertaken uses the eRegister system, which has been developed to capture and analyze data. The results indicate that high/active engagement, interaction and attendance is reflective of higher marks. Additonally, our approach is able to normalize the data into consistent a series so that the end result can be transformed into a dashboard of statistics that can be used by organizers of the MOOC. Based on this, we conclude that there is a fundamental need for predictive systems within learning communities.

Monitoring and measuring sedentary behaviour with the aid of human digital memories

The ubiquity and affordability of mobile and wearable devices has enabled us to continually and digitally record our daily life activities. Consequently, we are seeing the growth of data collection experiments in several scientific disciplines. Although these have yielded promising results, mobile and wearable data collection experiments are often restricted to a specific configuration that has been designed for a unique study goal. These approaches do not address all the real-world challenges of “continuous data collection” systems. As a result, there have been few discussions or reports about such issues that are faced when “implementing these platforms” in a practical situation. To address this, we have summarized our technical and user-centric findings from three lifelogging and Quantified Self data collection studies, which we have conducted in real-world settings, for both smartphones and smartwatches. In addition to (i) privacy and (ii) battery related issues; based on our findings we recommend further works to consider (iii) implementing multivariate reflection of the data; (iv) resolving the uncertainty and data loss; and (v) consider to minimize the manual intervention required by users. These findings have provided insights that can be used as a guideline for further Quantified Self or lifelogging studies.

Creating human digital memories for a richer recall of life experiences

There is growing global concern over the growing levels of obesity and the fact that people in general are not as active as they once were. Many believe that this is directly related to poor diet and our increasing reliance on technology, such as television, social networking, computer games, and voice activated home control systems. These kinds of activities increase sedentary behaviour across all age groups and is considered one of the main contributors to obesity and poor health. For this reason decreasing sedentary behaviour is considered a crucial theme within many research programs in health. Ironically, there is general agreement that the use of technology is likely to help researchers understand this type of behaviour. One interesting approach is based upon the use of human digital memories to provide visual lifelogs of a users activity and to identify the behaviour patterns of individuals. In this way visual lifelogs provide a way for users to evaluate their lifestyle choices. This paper discusses some of the key technologies used to achieve this and considers some of the challenges that still need to be addressed.

Capturing and sharing human digital memories with the aid of ubiquitous Peer-to-Peer mobile services

Human digital memories focus on documenting our lifetime. This outlet allows us to capture and bring together information that is related to almost any aspect of our lives. Creating these memories allows us to recall experiences, seamlessly; and to re-live specific events, using detailed information about those experiences. The evolution of smart devices enables any object to provide us with information. With all of this data at our disposal, new opportunities are arising to incorporate this data into our digital memories. Consequently, the challenge is to develop a platform, capable of linking captured information together, to form feature rich digital memories of human experiences. This paper presents DigMem, a platform for creating human digital memories, using pervasive devices and linked data. Information is semantically structured to create temporal “memory boxes”. A working prototype has been successfully developed, which demonstrates the approach.

Creating Human Digital Memories with the Aid of Pervasive Mobile Devices

The explosion of mobile computing and the sharing of content ubiquitously has enabled users to create and share memories instantly. Access to different data sources, such as location, movement, and physiology, has helped to create a data rich society where new and enhanced memories will form part of everyday life. Peer-to-Peer (P2P) systems have also increased in popularity over the years, due to their ad hoc and decentralized nature. Mobile devices are “smarter” and are increasingly becoming part of P2P systems; opening up a whole new dimension for capturing, sharing and interacting with enhanced human digital memories. This will require original and novel platforms that automatically compose data sources from ubiquitous ad-hoc services that are prevalent within the environments we occupy. This is important for a number of reasons. Firstly, it will allow digital memories to be created that include richer information, such as how you felt when the memory was created and how you made others feel. Secondly, it provides a set of core services that can more easily manage and incorporate new sources as and when you are available. In this way memories created in the same location, and time are not necessarily similar - it depends on the data sources that are accessible. This paper presents DigMem, the initial prototype that is being developed to utilize distributed mobile services. DigMem captures and shares human digital memories, in a ubiquitous P2P environment. We present a case study to validate the implementation and evaluate the applicability of the approach.

Detecting physical activity within lifelogs towards preventing obesity and aiding ambient assisted living

The abundance of mobile and sensing devices, within our environment, has led to a society in which any object, embedded with sensors, is capable of providing us with information. A human digital memory, created with the data from these pervasive devices, produces a more dynamic and data rich memory. Information such as how you felt, where you were and the context of the environment can be established. This paper presents the DigMem system, which utilizes distributed mobile services, linked data and machine learning to create such memories. Along with the design of the system, a prototype has also been developed, and two case studies have been undertaken, which successfully create memories. As well as demonstrating how memories are created, a key concern in human digital memory research relates to the amount of data that is generated and stored. In particular, searching this set of big data is a key challenge. In response to this, the paper evaluates the use of machine learning algorithms, as an alternative to SPARQL, and treats searching as a classification problem. In particular, supervised machine learning algorithms are used to find information in semantic annotations, based on probabilistic reasoning. Our approach produces good results with 100% sensitivity, 93% specificity, 93% positive predicted value, 100% negative predicted value, and an overall accuracy of 97%.