Computational modeling for the quantitative assessment of cardiac autonomic response to orthostatic stress.

The autonomic nervous system (ANS) plays a critical role in regulating not only cardiac functions but also various other physiological processes, such as respiratory rate, digestion, and metabolic activities. The ANS is divided into the sympathetic and parasympathetic nervous systems, each of which has distinct but complementary roles in maintaining homeostasis across multiple organ systems in response to internal and external stimuli. Early detection of ANS dysfunctions, such as imbalances between the sympathetic and parasympathetic branches or impairments in the autonomic regulation of bodily functions, is crucial for preventing or slowing the progression of cardiovascular diseases.

Quantitative Assessment of Autonomic Regulation of the Cardiac System.

Autonomic neural system (ANS) regulates the circulation to provide optimal perfusion of every organ in accordance with its metabolic needs, and the quantitative assessment of autonomic regulation is crucial for personalized medicine in cardiovascular diseases. In this paper, we propose the Dystatis to quantitatively evaluate autonomic regulation of the human cardiac system, based on homeostatis and probabilistic graphic model, where homeostatis explains ANS regulation while the probability graphic model systematically defines the regulation process for quantitative assessment. The indices and measurement methods for three well-designed scenarios are also illustrated to evaluate the proposed Dystatis: (1) heart rate variability (HRV), blood pressure variability (BPV), and respiration synchronization (Synch) in resting situation; (2) chronotropic competence indices (CCI) in graded exercise testing; and (3) baroreflex sensitivity (BRS), sympathetic nerve activity (SNA), and parasympathetic nerve activity (PNA) in orthostatic testing.

A personalized-model-based central aortic pressure estimation method.

Central Aortic Pressure (CAP) can be used to predict cardiovascular structural damage and cardiovascular events, and the development of simple, well-validated and non-invasive methods for CAP waveforms estimation is critical to facilitate the routine clinical applications of CAP. Existing widely applied methods, such as generalized transfer function (GTF-CAP) method and N-Point Moving Average (NPMA-CAP) method, are based on clinical practices, and lack a mathematical foundation. Those methods also have inherent drawback that there is no personalisation, and missing individual aortic characteristics.

Self-contained pedestrian tracking during normal walking using an inertial/magnetic sensor module.

This paper proposes a novel self-contained pedestrian tracking method using a foot-mounted inertial and magnetic sensor module, which not only uses the traditional zero velocity updates, but also applies the stride information to further correct the acceleration double integration drifts and thus improves the tracking accuracy. In our method, a velocity control variable is designed in the process model, which is set to the average velocity derived from stride information in the swing (nonzero velocity) phases or zero in the stance (zero-velocity) phases. Stride-based position information is also derived as the pseudomeasurements to further improve the accuracy of the position estimates.

Hierarchical information fusion for global displacement estimation in microsensor motion capture.

This paper presents a novel hierarchical information fusion algorithm to obtain human global displacement for different gait patterns, including walking, running, and hopping based on seven body-worn inertial and magnetic measurement units. In the first-level sensor fusion, the orientation for each segment is achieved by a complementary Kalman filter (CKF) which compensates for the orientation error of the inertial navigation system solution through its error state vector. For each foot segment, the displacement is also estimated by the CKF, and zero velocity update is included for the drift reduction in foot displacement estimation.

Ubiquitous human upper-limb motion estimation using wearable sensors.

Human motion capture technologies have been widely used in a wide spectrum of applications, including interactive game and learning, animation, film special effects, health care, navigation, and so on. The existing human motion capture techniques, which use structured multiple high-resolution cameras in a dedicated studio, are complicated and expensive. With the rapid development of microsensors-on-chip, human motion capture using wearable microsensors has become an active research topic.

A dynamic conditional random field model for foreground and shadow segmentation.

This paper proposes a dynamic conditional random field (DCRF) model for foreground object and moving shadow segmentation in indoor video scenes. Given an image sequence, temporal dependencies of consecutive segmentation fields and spatial dependencies within each segmentation field are unified by a dynamic probabilistic framework based on the conditional random field (CRF). An efficient approximate filtering algorithm is derived for the DCRF model to recursively estimate the segmentation field from the history of observed images.

Spatiotemporal video segmentation based on graphical models.

This paper proposes a probabilistic framework for spatiotemporal segmentation of video sequences. Motion information, boundary information from intensity segmentation, and spatial connectivity of segmentation are unified in the video segmentation process by means of graphical models. A Bayesian network is presented to model interactions among the motion vector field, the intensity segmentation field, and the video segmentation field.