arXiv subjects

Yunlong Wang

Publications and source records attributed to Yunlong Wang.

At least 109 records · Page 6Linked to original sources

arXiv2019

Alignment Free and Distortion Robust Iris Recognition

Iris recognition is a reliable personal identification method but there is still much room to improve its accuracy especially in less-constrained situations. For example, free movement of head pose may cause large rotation difference between iris images. And illumination variations may cause irregular distortion of iris texture. To match intra-class iris images with head rotation robustly, the existing solutions usually need a precise alignment operation by exhaustive search within a determined range in iris image preprosessing or brute force searching the minimum Hamming distance in iris feature matching. In the wild, iris rotation is of much greater uncertainty than that in constrained situations and exhaustive search within a determined range is impracticable. This paper presents a unified feature-level solution to both alignment free and distortion robust iris recognition in the wild. A new deep learning based method named Alignment Free Iris Network (AFINet) is proposed, which uses a trainable VLAD (Vector of Locally Aggregated Descriptors) encoder called NetVLAD to decouple the correlations between local representations and their spatial positions. And deformable convolution is used to overcome iris texture distortion by dense adaptive sampling. The results of extensive experiments on three public iris image databases and the simulated degradation databases show that AFINet significantly outperforms state-of-art iris recognition methods.

cs.CV↗

arXiv2019

Representation Learning of EHR Data via Graph-Based Medical Entity Embedding

Automatic representation learning of key entities in electronic health record (EHR) data is a critical step for healthcare informatics that turns heterogeneous medical records into structured and actionable information. Here we propose ME2Vec, an algorithmic framework for learning low-dimensional vectors of the most common entities in EHR: medical services, doctors, and patients. ME2Vec leverages diverse graph embedding techniques to cater for the unique characteristic of each medical entity. Using real-world clinical data, we demonstrate the efficacy of ME2Vec over competitive baselines on disease diagnosis prediction.

cs.LG↗

arXiv2019

Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning

Models have been proposed to extract temporal patterns from longitudinal electronic health records (EHR) for clinical predictive models. However, the common relations among patients (e.g., receiving the same medical treatments) were rarely considered. In this paper, we propose to learn patient similarity features as phenotypes from the aggregated patient-medical service matrix using non-negative matrix factorization. On real-world medical claim data, we show that the learned phenotypes are coherent within each group, and also explanatory and indicative of targeted diseases. We conducted experiments to predict the diagnoses for Chronic Lymphocytic Leukemia (CLL) patients. Results show that the phenotype-based similarity features can improve prediction over multiple baselines, including logistic regression, random forest, convolutional neural network, and more.

stat.AP↗

arXiv2019

Rare Disease Detection by Sequence Modeling with Generative Adversarial Networks

Rare diseases affecting 350 million individuals are commonly associated with delay in diagnosis or misdiagnosis. To improve those patients' outcome, rare disease detection is an important task for identifying patients with rare conditions based on longitudinal medical claims. In this paper, we present a deep learning method for detecting patients with exocrine pancreatic insufficiency (EPI) (a rare disease). The contribution includes 1) a large longitudinal study using 7 years medical claims from 1.8 million patients including 29,149 EPI patients, 2) a new deep learning model using generative adversarial networks (GANs) to boost rare disease class, and also leveraging recurrent neural networks to model patient sequence data, 3) an accurate prediction with 0.56 PR-AUC which outperformed benchmark models in terms of precision and recall.

cs.LG↗

arXiv2019

Predicting Treatment Initiation from Clinical Time Series Data via Graph-Augmented Time-Sensitive Model

Many computational models were proposed to extract temporal patterns from clinical time series for each patient and among patient group for predictive healthcare. However, the common relations among patients (e.g., share the same doctor) were rarely considered. In this paper, we represent patients and clinicians relations by bipartite graphs addressing for example from whom a patient get a diagnosis. We then solve for the top eigenvectors of the graph Laplacian, and include the eigenvectors as latent representations of the similarity between patient-clinician pairs into a time-sensitive prediction model. We conducted experiments using real-world data to predict the initiation of first-line treatment for Chronic Lymphocytic Leukemia (CLL) patients. Results show that relational similarity can improve prediction over multiple baselines, for example a 5% incremental over long-short term memory baseline in terms of area under precision-recall curve.

cs.LG↗

arXiv2019

The Impact of Augmented-Reality Head-Mounted Displays on Users' Movement Behavior: An Exploratory Study

The augmented-reality head-mounted display (e.g., Microsoft HoloLens) is one of the most innovative technologies in multimedia and human-computer interaction in recent years. Despite the emerging research of its applications on engineering, education, medicines, to name a few, its impact on users' movement behavior is still underexplored. The movement behavior, especially for office workers with sedentary lifestyles, is related to many chronic conditions. Unlike the traditional screens, the augmented-reality head-mounted display (AR-HMD) could enable mobile virtual screens, which might impact on users' movement behavior. In this paper, we present our initial study to explore the impact of AR-HMDs on users' movement behavior. We compared the differences of macro-movements (e.g., sit-stand transitions) and micro-movements (e.g., moving the head) between two experimental modes (i.e., spatial-mapping and tag-along) with a dedicated trivial quiz task using HoloLens. The study reveals interesting findings: strong evidence supports that participants had more head-movements in the tag-along mode where higher simplicity and freedom of moving the virtual screen were given; body position/direction changes show the same effect with moderate evidence, while sit-stand transitions show no difference between the two modes with weak evidence. Our results imply several design considerations and research opportunities for future work on the ergonomics of AR-HMDs in the perspective of health.

cs.HC↗

arXiv2019

CoachAI: A Conversational Agent Assisted Health Coaching Platform

Poor lifestyle represents a health risk factor and is the leading cause of morbidity and chronic conditions. The impact of poor lifestyle can be significantly altered by individual behavior change. Although the current shift in healthcare towards a long lasting modifiable behavior, however, with increasing caregiver workload and individuals' continuous needs of care, there is a need to ease caregiver's work while ensuring continuous interaction with users. This paper describes the design and validation of CoachAI, a conversational agent assisted health coaching system to support health intervention delivery to individuals and groups. CoachAI instantiates a text based healthcare chatbot system that bridges the remote human coach and the users. This research provides three main contributions to the preventive healthcare and healthy lifestyle promotion: (1) it presents the conversational agent to aid the caregiver; (2) it aims to decrease caregiver's workload and enhance care given to users, by handling (automating) repetitive caregiver tasks; and (3) it presents a domain independent mobile health conversational agent for health intervention delivery. We will discuss our approach and analyze the results of a one month validation study on physical activity, healthy diet and stress management.

cs.AI↗

arXiv2019

Health Behaviour Change Techniques in Diabetes Management Applications: A Systematic Review

The rapid growth in mobile healthcare technology could significantly help control chronic diseases, such as diabetes. This paper presents a systematic review to characterise type 1 & type 2 diabetes management applications available in Apple's iTunes store. We investigated "Health & Fitness" and "Medical" apps following a two-step filtering process (Selection and Analysis phases). We firstly investigated the apps compliance to the persuasive system design (PSD) model. We then characterised the behaviour change techniques (BCTs) of top-ranked apps for diabetes management. Finally, we checked the apps regarding the stages of disease continuum. The findings revealed apps incorporation some PSD principles based on their configuration and behaviour change techniques. Most apps miss the element of BCT and focus on measuring exercise and caloric intake. Few apps consider managing specific diabetes type, which raises doubts about the effectiveness of those apps in providing sustainable diabetes management. Moreover, people may need multiple apps to initiate and maintain a healthy behaviour.

cs.CY↗

arXiv2019

Health Behavior Change in HCI: Trends, Patterns, and Opportunities

Unhealthy lifestyles could cause many chronic diseases, which bring patients and their families much burden. Research has shown the potential of digital technologies for supporting health behavior change to help us prevent these chronic diseases. The HCI community has contributed to the research on health behavior change for more than a decade. In this paper, we aim to explore the research trends and patterns of health behavior change in HCI. Our systematic review showed that physical activity drew much more attention than other behaviors. Most of the participants in the reviewed studies were adults, while children and the elderly were much less addressed. Also, we found there is a lack of standardized approaches to evaluating the user experience of interventions for health behavior change in HCI. Based on the reviewed studies, we provide suggestions and research opportunities on six topics, e.g., game integration, social support, and relevant AI application.

cs.HC↗

arXiv2018

Semi-supervised Rare Disease Detection Using Generative Adversarial Network

Rare diseases affect a relatively small number of people, which limits investment in research for treatments and cures. Developing an efficient method for rare disease detection is a crucial first step towards subsequent clinical research. In this paper, we present a semi-supervised learning framework for rare disease detection using generative adversarial networks. Our method takes advantage of the large amount of unlabeled data for disease detection and achieves the best results in terms of precision-recall score compared to baseline techniques.

cs.LG↗

arXiv2018

Modeling Treatment Delays for Patients using Feature Label Pairs in a Time Series

Pharmaceutical targeting is one of key inputs for making sales and marketing strategy planning. Targeting list is built on predicting physician's sales potential of certain type of patient. In this paper, we present a time-sensitive targeting framework leveraging time series model to predict patient's disease and treatment progression. We create time features by extracting service history within a certain period, and record whether the event happens in a look-forward period. Such feature-label pairs are examined across all time periods and all patients to train a model. It keeps the inherent order of services and evaluates features associated to the imminent future, which contribute to improved accuracy.

cs.LG↗

arXiv2018

Integrating Taxonomies into Theory-Based Digital Health Interventions for Behavior Change: A Holistic Framework

Digital health interventions have been emerging in the last decade. Due to their interdisciplinary nature, digital health interventions are guided and influenced by theories (e.g., behavioral theories, behavior change technologies, persuasive technology) from different research communities. However, digital health interventions are always coded using various taxonomies and reported in insufficient perspectives. The inconsistency and incomprehensiveness will bring difficulty for conducting systematic reviews and sharing contributions among communities. Based on existing related work, therefore, we propose a holistic framework that embeds behavioral theories, behavior change technique (BCT) taxonomy, and persuasive system design (PSD) principles. Including four development steps, two toolboxes, and one workflow, our framework aims to guide digital health intervention developers to design, evaluate, and report their work in a formative and comprehensive way.

cs.HC↗

arXiv2018

Persuasive Technology in Reducing Prolonged Sedentary Behavior at Work: A Systematic Review

Prolonged sedentary behavior is prevalent among office workers and has been found to be detrimental to health. Preventing and reducing prolonged sedentary behavior require interventions, and persuasive technology is expected to make a contribution in this domain. In this paper, we use the framework of persuasive system design (PSD) principles to investigate the utilization and effectiveness of persuasive technology in intervention studies at reducing sedentary behavior at work. This systematic review reveals that reminders are the most frequently used PSD principle. The analysis on reminders shows that hourly PC reminders alone have no significant effect on reducing sedentary behavior at work, while coupling with education or other informative session seems to be promising. Details of deployed persuasive technology with behavioral theories and user experience evaluation are expected to be reported explicitly in the future intervention studies.

cs.CY↗

arXiv2018

Realization of a scalable Laguerre-Gaussian mode sorter based on a robust radial mode sorter

The transverse structure of light is recognized as a resource that can be used to encode information onto photons and has been shown to be useful to enhance communication capacity as well as resolve point sources in superresolution imaging. The Laguerre-Gaussian (LG) modes form a complete and orthonormal basis set and are described by a radial index p and an orbital angular momentum (OAM) index l. Earlier works have shown how to build a sorter for the radial index p or/and the OAM index l of LG modes, but a scalable and dedicated LG mode sorter which simultaneous determinate p and l is immature. Here we propose and experimentally demonstrate a scheme to accomplish complete LG mode sorting, which consists of a novel, robust radial mode sorter that can be used to couple radial modes to polarizations, an l-dependent phase shifter and an OAM mode sorter. Our scheme is in principle efficient, scalable, and crosstalk-free, and therefore has potential for applications in optical communications, quantum information technology, superresolution imaging, and fiber optics.

physics.optics↗

arXiv2018

Clustering with Temporal Constraints on Spatio-Temporal Data of Human Mobility

Extracting significant places or places of interest (POIs) using individuals' spatio-temporal data is of fundamental importance for human mobility analysis. Classical clustering methods have been used in prior work for detecting POIs, but without considering temporal constraints. Usually, the involved parameters for clustering are difficult to determine, e.g., the optimal cluster number in hierarchical clustering. Currently, researchers either choose heuristic values or use spatial distance-based optimization to determine an appropriate parameter set. We argue that existing research does not optimally address temporal information and thus leaves much room for improvement. Considering temporal constraints in human mobility, we introduce an effective clustering approach - namely POI clustering with temporal constraints (PC-TC) - to extract POIs from spatio-temporal data of human mobility. Following human mobility nature in modern society, our approach aims to extract both global POIs (e.g., workplace or university) and local POIs (e.g., library, lab, and canteen). Based on two publicly available datasets including 193 individuals, our evaluation results show that PC-TC has much potential for next place prediction in terms of granularity (i.e., the number of extracted POIs) and predictability.

cs.LG↗

arXiv2018

Enhancement of spatial resolution of ghost imaging via localizing and thresholding

In ghost imaging scheme, an illuminated light is split into test and reference beams which pass through two different optical systems respectively and an image is constructed by the second-order correlation between the two light beams. Since both the two light beams are all diffracted when passing through the optical systems, spatial resolution of ghost imaging is in general lower than that of a corresponding conventional imaging system. When Gaussian-shaped light spots are used to illuminate an object, randomly scanning across the object plane, in ghost imaging scheme, we show that by localizing central positions of the spots of the reference light beam, the resolution can be enhanced by a factor of $\sqrt{2}$ same as that of the corresponding conventional imaging system. We also find that the resolution can be further enhanced by setting an appropriate threshold to the bucket measurement of ghost imaging.

physics.optics↗

arXiv2017

Towards a Holistic Approach to Designing Theory-based Mobile Health Interventions

Increasing evidence has shown that theory-based health behavior change interventions are more effective than non-theory-based ones. However, only a few segments of relevant studies were theory-based, especially the studies conducted by non-psychology researchers. On the other hand, many mobile health interventions, even those based on the behavioral theories, may still fail in the absence of a user-centered design process. The gap between behavioral theories and user-centered design increases the difficulty of designing and implementing mobile health interventions. To bridge this gap, we propose a holistic approach to designing theory-based mobile health interventions built on the existing theories and frameworks of three categories: (1) behavioral theories (e.g., the Social Cognitive Theory, the Theory of Planned Behavior, and the Health Action Process Approach), (2) the technological models and frameworks (e.g., the Behavior Change Techniques, the Persuasive System Design and Behavior Change Support System, and the Just-in-Time Adaptive Interventions), and (3) the user-centered systematic approaches (e.g., the CeHRes Roadmap, the Wendel's Approach, and the IDEAS Model). This holistic approach provides researchers a lens to see the whole picture for developing mobile health interventions.

cs.HC↗

arXiv2017

Rare Disease Physician Targeting: A Factor Graph Approach

In rare disease physician targeting, a major challenge is how to identify physicians who are treating diagnosed or underdiagnosed rare diseases patients. Rare diseases have extremely low incidence rate. For a specified rare disease, only a small number of patients are affected and a fractional of physicians are involved. The existing targeting methodologies, such as segmentation and profiling, are developed under mass market assumption. They are not suitable for rare disease market where the target classes are extremely imbalanced. The authors propose a graphical model approach to predict targets by jointly modeling physician and patient features from different data spaces and utilizing the extra relational information. Through an empirical example with medical claim and prescription data, the proposed approach demonstrates better accuracy in finding target physicians. The graph representation also provides visual interpretability of relationship among physicians and patients. The model can be extended to incorporate more complex dependency structures. This article contributes to the literature of exploring the benefit of utilizing relational dependencies among entities in healthcare industry.

stat.ML↗