Local recurrence based performance prediction and prognostics in the nonlinear and nonstationary systems

Yang, Hui; Bukkapatnam, Satish T. S.; Barajas, Leandro G.

doi:10.1016/j.patcog.2011.01.010

Cited by 33 publications

(14 citation statements)

References 29 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dynamic VCG Implementation DetailsMost previous investigations utilized the lag-reconstructed ECG representation to quantify nonlinear dynamical patterns, e.g., recurrence statistics and study their correlations with cardiac disorders. The mathematical formulation of recurrence quantifiers is detailed in our previous investigation [25,26] and other references [20,27]. The recurrence plot is defined as:

T_{i, j} : = Θ (ϵ - ||\vec{x} (i) - \vec{x} (j)||)

, where ϵ is a cutoff distance and Θ is the Heaviside function.…”

Section: Resultsmentioning

confidence: 99%

Spatiotemporal representation of cardiac vectorcardiogram (VCG) signals

Yang

Bukkapatnam

Komanduri

2012

BioMedical Engineering OnLine

Self Cite

View full text Add to dashboard Cite

BackgroundVectorcardiogram (VCG) signals monitor both spatial and temporal cardiac electrical activities along three orthogonal planes of the body. However, the absence of spatiotemporal resolution in conventional VCG representations is a major impediment for medical interpretation and clinical usage of VCG. This is especially so because time-domain features of 12-lead ECG, instead of both spatial and temporal characteristics of VCG, are widely used for the automatic assessment of cardiac pathological patterns.Materials and methodsWe present a novel representation approach that captures critical spatiotemporal heart dynamics by displaying the real time motion of VCG cardiac vectors in a 3D space. Such a dynamic display can also be realized with only one lead ECG signal (e.g., ambulatory ECG) through an alternative lag-reconstructed ECG representation from nonlinear dynamics principles. Furthermore, the trajectories are color coded with additional dynamical properties of space-time VCG signals, e.g., the curvature, speed, octant and phase angles to enhance the information visibility.ResultsIn this investigation, spatiotemporal VCG signal representation is used to characterize various spatiotemporal pathological patterns for healthy control (HC), myocardial infarction (MI), atrial fibrillation (AF) and bundle branch block (BBB). The proposed color coding scheme revealed that the spatial locations of the peak of T waves are in the Octant 6 for the majority (i.e., 74 out of 80) of healthy recordings in the PhysioNet PTB database. In contrast, the peak of T waves from 31.79% (117/368) of MI subjects are found to remain in Octant 6 and the rest (68.21%) spread over all other octants. The spatiotemporal VCG signal representation is shown to capture the same important heart characteristics as the 12-lead ECG plots and more.ConclusionsSpatiotemporal VCG signal representation is shown to facilitate the characterization of space-time cardiac pathological patterns and enhance the automatic assessment of cardiovascular diseases.

show abstract

T_{i, j} : = Θ (ϵ - ||\vec{x} (i) - \vec{x} (j)||)

, where ϵ is a cutoff distance and Θ is the Heaviside function.…”

Section: Resultsmentioning

confidence: 99%

Spatiotemporal representation of cardiac vectorcardiogram (VCG) signals

Yang

Bukkapatnam

Komanduri

2012

BioMedical Engineering OnLine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, we developed a novel approach of heterogeneous recurrence analysis [5,12] that utilizes a new fractal representation to delineate heterogeneous recurrence states, including the recurrences of both single states and multi-state sequences. Third, we collaborated with General Motors and developed a local recurrence model [13] for the prognosis of nonlinear and nonstationary evolution of manufacturing operational conditions.…”

Section: Complex Engineering and Biologicalmentioning

confidence: 99%

“…For instance, the rate of change in the buffer stock ⁄ can be described as the differences between the throughput rates of upstream and downstream machines, i.e., ⁄ . Because the quantity of buffer stock often has lower and upper bounds, linearity is lost when these bounds are reached [13][14][15][16]. Furthermore, internal and external disruptions that require control actions occur throughout the manufacturing process, from material procurement to the transportation of finished goods.…”

Section: System Dynamics Modeling and Simulationmentioning

confidence: 99%

“…Examples of state variables include the machine throughput, downtime, buffer levels and their coupled temporal dynamics. Harnessing multi-sensor signals, in the form of tractable models to predict dynamic behaviors, is essential to support day-to-day manufacturing planning and control decisions [13,14]. This provides an unprecedented opportunity to develop nonlinear system dynamics simulation models (NSDS) of multistage manufacturing systems that use a series of buffer stocks and product flows, in which the state changes are continuous.…”

Section: System Dynamics Modeling and Simulationmentioning

confidence: 99%

“…Yang and his research team developed a sensor-driven NSDS modeling approach [13][14][15][16] to simulate operational dynamics of a multistage assembly line. The movement of entities is treated as a fluid flow, buffer stocks are water tanks, the conveyor belt is water pipe and manufacturing stations are the valves which control the rates of flow.…”

Section: System Dynamics Modeling and Simulationmentioning

confidence: 99%

See 2 more Smart Citations

Theoretical Foundations

Blending Technologies in Second Language Classrooms

View full text Add to dashboard Cite

Research OverviewDr. Yang and his research team at USF aim to create a rigorous knowledge body for sensorbased complex systems monitoring, modeling and analysis. The research will ultimately contribute to a new paradigm where a complex system is autonomized and optimized at all scales. As shown in Figure 1, industry in the 21 st century is investing in a variety of sensor networks and dedicated data centers to increase information visibility in both engineering and healthcare domains. Real-time sensing brings the proliferation of big data (i.e., dynamic, nonlinear, nonstationary, high dimensional) that contains a wealth of information on the condition and status of a product, process or a system. Big Data presents a 'gold mine' of this era (21 st century). Innovations in industrial and systems engineering in this century will be highly dominated by "new methods and tools" to mine the big data and harness its power for new product development, problem solving and system optimization. Nonlinear Dynamics and ChaosEngineering and physiological systems (e.g., nanoscale machining and human heart) involve greater levels of complexity and technical challenge. Much of the complexity emerges from nonlinear dynamics of the underlying process. In order to cope with system complexity and dynamic environments, modern industries are investing in a variety of sensors and data acquisition systems. However, most of existing approaches adopt linear methods and tools for sensor information processing. Traditional linear approaches interpret the regular structure, e.g., Complex Engineering and Biological

show abstract