Zhikun Deng

Lifelogging Data Validation Model for Internet of Things Enabled Personalized Healthcare

Internet of Things (IoT) technology offers opportunities to monitor lifelogging data by a variety of assets, like wearable sensors, mobile apps, etc. But due to heterogeneity of connected devices and diverse human life patterns in an IoT environment, lifelogging personal data contains huge uncertainty and are hardly used for healthcare studies. Effective validation of lifelogging personal data for longitudinal health assessment is demanded. In this paper, lifelogging physical activity (LPA) is taken as a target to explore how to improve the validity of lifelogging data in an IoT enabled healthcare system. A rule-based adaptive LPA validation (LPAV) model, LPAV-IoT, is proposed for eliminating irregular uncertainties (IUs) and estimating data reliability in IoT healthcare environments. A methodology specifying four layers and three modules in LPAV-IoT is presented for analyzing key factors impacting validity of LPA. A series of validation rules are designed with uncertainty threshold parameters and reliability indicators and evaluated through experimental investigations. Following LPAV-IoT, a case study on a personalized healthcare platform myhealthavatar connecting three state-of-the-art wearable devices and mobile apps are carried out. The results reflect that the rules provided by LPAV-IoT enable efficiently filtering at least 75% of IU and adaptively indicating the reliability of LPA data on certain condition of IoT environments.

A Survey of Physical Activity Monitoring and Assessment Using Internet of Things Technology

As a key health indictor, daily physical activity (PA) data has great significance on diagnosis and treatment of many chronic diseases. Numerous studies have been carried out for accurately monitoring and assessing physical activity. Most attentions of these studies focus on designing standalone highly accurate wearable sensors or investigating advance machine learning algorithms to train these PA data in a controlled environment. But the wide use of cost-effective wearable devices and mobile apps makes it possible to monitor and access PA into a more open and connective Internet of Things (IoT) environment. Yet, it still lacks of a systemic survey on how to effectively transfer classic PA monitoring and assessment (PAMA) technologies into a heterogeneous device connected IoT environment. In an effect to understand the development of IoT technologies in PAMA, this paper reviews current research of PAMA technologies from an IoT layer-based perspective, and also identifies research challenges and future trends. A main contribution of this review paper is that it is first attempt to categorize classic PAMA technologies into an IoT architecture systematically.

Ellipse fitting model for improving the effectiveness of life-logging physical activity measures in an Internet of Things environment

The popular use of wearable devices and mobile phones makes the effective capture of life-logging physical activity (PA) data in an Internet of Things (IoT) environment possible. The effective collection of measures of PA in the long term is beneficial to interdisciplinary healthcare research and collaboration from clinicians, researchers and patients. However, due to heterogeneity of connected devices and rapid change of diverse life patterns in an IoT environment, life-logging PA information captured by mobile devices usually contains much uncertainty. In this study, the authors project the distribution of irregular uncertainty by defining a walking speed related score named as daily activity in physical space and present an ellipse-fitting model-based validity improvement method for reducing uncertainties of life-logging PA measures in an IoT environment. The experimental results reflect that the proposed method remarkably improves the validity of PA measures in a healthcare platform.

Improving the Validity of Lifelogging Physical Activity Measures in an Internet of Things Environment

Recently, the popular use of wearable devices and mobile apps makes the effectively capture of lifelogging physical activity data in an Internet of Things (IoT) environment possible. The effective collection of measures of physical activity in the long term is beneficial to interdisciplinary healthcare research and collaboration from clinicians, researchers to patients. However, due to heterogeneity of connected devices and rapid change of diverse life patterns in an IoT environment, lifelogging physical activity information captured by mobile devices usually contains much uncertainty. In this paper, we provide a comprehensive review of existing life-logging physical activity measurement devices, and identify regular and irregular uncertainties of these activity measures in an IoT environment. We then project the distribution of irregular uncertainty by defining a walking speed related score named as Daily Activity in Physical Space (DAPS). Finally, we present an ellipse fitting model based validity improvement method for reducing uncertainties of life-logging physical activity measures in an IoT environment. The experimental results reflect that the proposed method effectively improves the validity of physical activity measures in a healthcare platform.

Life-Logging Data Aggregation Solution for Interdisciplinary Healthcare Research and Collaboration

The wide-spread use of wearable devices and mobile apps in the Internet of Things (IoT) environments makes effectively capture of life-logging personal health data come true. A long-term collection of these health data will benefit to interdisciplinary healthcare research and collaboration. But most wearable devices and mobile apps in the market focus on personal fitness plan and lack of compatibility and extensibility to each other. Existing IoT based platforms rarely achieve a successful heterogeneous life-logging data aggregation. Also, the demand on high security increases difficulties of designing reliable platform for integrating and managing multi-resource life-logging health data. This paper investigates the possibility of collecting and aggregating life-logging data with the use of wearable devices, mobile apps and social media. It compares existing personal health data collection solutions and identifies essential needs of designing a life-logging data aggregator in the IoT environments. An integrated data collection solution with high secure standard is proposed and deployed on a state-of-the-art interdisciplinary healthcare platform: MHA [15] by integrating five life-logging resources: Fitbit, Moves, Facbook, Twitter, etc. The preliminary experiment demonstrates that it successfully record, store and reuse the unified and structured personal health information in a long term, including activities, location, exercise, sleep, food, heat rate and mood.

GSWO: A programming model for GPU-enabled parallelization of sliding window operations in image processing

Sliding Window Operations (SWOs) are widely used in image processing applications. They often have to be performed repeatedly across the target image, which can demand significant computing resources when processing large images with large windows. In applications in which real-time performance is essential, running these filters on a CPU often fails to deliver results within an acceptable timeframe. The emergence of sophisticated graphic processing units (GPUs) presents an opportunity to address this challenge. However, GPU programming requires a steep learning curve and is error-prone for novices, so the availability of a tool that can produce a GPU implementation automatically from the original CPU source code can provide an attractive means by which the GPU power can be harnessed effectively. This paper presents a GPU-enabled programming model, called GSWO, which can assist GPU novices by converting their SWO-based image processing applications from the original C/C++ source code to CUDA code in a highly automated manner. This model includes a new set of simple SWO pragmas to generate GPU kernels and to support effective GPU memory management. We have implemented this programming model based on a CPU-to-GPU translator (C2GPU). Evaluations have been performed on a number of typical SWO image filters and applications. The experimental results show that the GSWO model is capable of efficiently accelerating these applications, with improved applicability and a speed-up of performance compared to several leading CPU-to-GPU source-to-source translators.

Management of Scientific Documents and Visualization of Citation Relationships using Weighted Key Scientific Terms

Effective management and visualization of scientific and research documents can greatly assist researchers by improving understanding of relationships (e.g. citations) between the documents. This paper presents work on the management and visualization of large corpuses of scientific papers in order to help researchers explore their citation relationships. Term selection and weighting are used for mining citation relationships by identifying the most relevant. To this end, we present a variation of the TF-IDF scheme, which uses external domain resources as references to calculate the term weighting in a particular domain; document weighting is taken into account in the calculation of term weighting from a group of citations. A simple hierarchical word weighting method is also presented. The work is supported by an underlying architecture for document management using NoSQL databases and employs a simple visualization interface.

Ontology Driven Personal Health Knowledge Discovery

With fast development of smart sensor devices and mobile applications, all different kinds of information related to humans can be founded on the Internet that can be seen as a universal data repository or called Web of Data. Health or healthcare related data are not exceptional in the Web of Data age. The most important and valuable data comes from IoT such as sensors and mobile activity tracking applications to support developing self-health risk detection and management applications. This paper presents a comprehensive ontology driven knowledge discovery framework in personal health domain, which aims to reason and discover health knowledge from various data sources of IoT. The framework contains a sensor oriented Personal Wellness Knowledge Ontology and data integration architecture to complete a whole lifecycle of health knowledge detecting and reasoning path. In addition, a cloud computing based parallel semantic lifting algorithm is described for illustrating the semantic data generation process in detail.

Data Mining, Management and Visualization in Large Scientific Corpuses

Organizing scientific papers helps efficiently derive meaningful insights of the published scientific resources, enables researchers grasp rapid technological change and hence assists new scientific discovery. In this paper, we experiment text mining and data management of scientific publications for collecting and presenting useful information to support research. For efficient data management and fast information retrieval, four data storages are employed: a semantic repository, an index and search repository, a document repository and a graph repository, taking full advantage of their features and strength. The results show that the combination of these four repositories can effectively store and index the publication data with reliability and efficiency and hence supply meaningful information to support scientific research.

Examining sensor-based physical activity recognition and monitoring for healthcare using Internet of Things: A systematic review

Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) have been considered as a key paradigm for smart healthcare. Traditional methods for PARM focus on controlled environments with the aim of increasing the types of identifiable activity subjects complete and improving recognition accuracy and system robustness by means of novel body-worn sensors or advanced learning algorithms. The emergence of the Internet of Things (IoT) enabling technology is transferring PARM studies to open and connected uncontrolled environments by connecting heterogeneous cost-effective wearable devices and mobile apps. Little is currently known about whether traditional PARM technologies can tackle the new challenges of IoT environments and how to effectively harness and improve these technologies. In an effort to understand the use of IoT technologies in PARM studies, this paper will give a systematic review, critically examining PARM studies from a typical IoT layer-based perspective. It will firstly summarize the state-of-the-art in traditional PARM methodologies as used in the healthcare domain, including sensory, feature extraction and recognition techniques. The paper goes on to identify some new research trends and challenges of PARM studies in the IoT environments, and discusses some key enabling techniques for tackling them. Finally, this paper consider some of the successful case studies in the area and look at the possible future industrial applications of PARM in smart healthcare.