Multivariate Dynamic Processes Research Articles

A theory-informed emotion regulation variability index: Bray-Curtis dissimilarity.

Emotion regulation (ER) variability refers to how individuals vary their use of ER strategies across time. It helps individuals to meet contextual needs, underscoring its importance in well-being. The theoretical foundation of ER variability recognizes two constituent processes: strategy switching (e.g., moving from distraction to social sharing) and endorsement change (e.g., decreasing the intensity of both distraction and social sharing). ER variability is commonly operationalized as the SD between strategies per observation (between-strategy SD) or within a strategy across time (within-strategy SD). In this article, we show that these SD-based approaches cannot sufficiently capture strategy switching and endorsement change, leading to ER variability indices with poor validity. We propose Bray-Curtis dissimilarity, a measure used in ecology to quantify biodiversity variability, as a theory-informed ER variability index. First, we demonstrate how Bray-Curtis dissimilarity is more sensitive than SD-based approaches in detecting ER variability through two simulation studies. Second, assuming that higher ER variability is adaptive in daily life, we test the relation between ER variability and negative affect in three experience sampling method data sets (total N = [70, 95, 200], number of moment-level observations = [5,040, 6,329, 14,098]). At both the moment level and person level, higher Bray-Curtis dissimilarity predicted lower negative affect more consistently than SD-based indices. We conclude that Bray-Curtis dissimilarity may better capture moment-level within-person ER variability and could have implications for studying variability in other multivariate dynamic processes. The article is accompanied by an R tutorial and practical recommendations for using Bray-Curtis dissimilarity with experience sampling method data. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Testing for Granger Causality in the Frequency Domain: A Phase Resampling Method

abstractThis article introduces phase resampling, an existing but rarely used surrogate data method for making statistical inferences of Granger causality in frequency domain time series analysis. Granger causality testing is essential for establishing causal relations among variables in multivariate dynamic processes. However, testing for Granger causality in the frequency domain is challenging due to the nonlinear relation between frequency domain measures (e.g., partial directed coherence, generalized partial directed coherence) and time domain data. Through a simulation study, we demonstrate that phase resampling is a general and robust method for making statistical inferences even with short time series. With Gaussian data, phase resampling yields satisfactory type I and type II error rates in all but one condition we examine: when a small effect size is combined with an insufficient number of data points. Violations of normality lead to slightly higher error rates but are mostly within acceptable ranges. We illustrate the utility of phase resampling with two empirical examples involving multivariate electroencephalography (EEG) and skin conductance data.

Algorithms for the inference of causality in dynamic processes: Application to cardiovascular and cerebrovascular variability.

This study faces the problem of causal inference in multivariate dynamic processes, with specific regard to the detection of instantaneous and time-lagged directed interactions. We point out the limitations of the traditional Granger causality analysis, showing that it leads to false detection of causality when instantaneous and time-lagged effects coexist in the process structure. Then, we propose an improved algorithm for causal inference that combines the Granger framework with the approach proposed by Pearl for the study of causality among multiple random variables. This new approach is compared with the traditional one in theoretical and simulated examples of interacting processes, showing its ability to retrieve the correct structure of instantaneous and time-lagged interactions. These approaches for causal inference are then tested on the physiological variability series of heart period, arterial pressure and cerebral blood flow variability obtained in subjects with postural-related syncope during a tilt-test protocol.

A New Subspace Identification Approach Based on Principal Component Analysis and Noise Estimation

In this paper, a new subspace identification approach based on principal component analysis (PCA) and noise estimation is developed for multivariable dynamic process modeling. In contrast to typical subspace identification methods based on standard PCA with instrumental variables, the noise term is first estimated and naturally eliminated in the proposed approach, and then a PCA procedure is used to determine system observability subspace and extract system matrices A, B, C, and D from the estimated observability subspace. For comparison with other typical subspace identification methods based on PCA, numerical simulation and activated sludge process benchmark modeling are included to demonstrate the superiority of the proposed approach and reveal the probable reason for unsatisfied B and D estimations derived by some subspace identification methods based on PCA.

An Overview of Roll Stabilizers and Systems for Their Control

Ship roll motion in waves can be characterized as a strongly non-linear and multivariable dynamic process which is more affected by disturbances, in general, than by the maximal controlling parameter. The article presents methods of roll motion compensation, the majority of which have been used on ships for many years. Although they are not capable of reducing permanently the error to zero, their potential has still not been used to the full. The operational efficiency of roll motion compensators can be improved using control systems. Research activities are in progress to check the applicability of advanced control methods making use of modern computer techniques. Some of them are mentioned in this paper.

Анализ динамических характеристик состояния рынка ценных бумаг

The article is devoted to automatic analyzing system of information as the first stage of DM (Data Mining) algorithms which are the basis of new type of automatic control of multivariate dynamic processes. It is unavailable to use these algorithms without statistic and dynamic analyses forming the information flows structure.

Data Mining algorithms in the dynamic processes control tasks

The article is devoted to DM (Data Mining) algorithms which are the basis of new type of automatic control of multivariate dynamic processes. DM methods combine immediate control decisions with deep numerical analysis of retrospective data. New conceptual principles of analytic control allow DM to be separate part of information technology.

Quality Relevant Data-Driven Modeling and Monitoring of Multivariate Dynamic Processes: The Dynamic T-PLS Approach

In data-based monitoring field, the nonlinear iterative partial least squares procedure has been a useful tool for process data modeling, which is also the foundation of projection to latent structures (PLS) models. To describe the dynamic processes properly, a dynamic PLS algorithm is proposed in this paper for dynamic process modeling, which captures the dynamic correlation between the measurement block and quality data block. For the purpose of process monitoring, a dynamic total PLS (T-PLS) model is presented to decompose the measurement block into four subspaces. The new model is the dynamic extension of the T-PLS model, which is efficient for detecting quality-related abnormal situation. Several examples are given to show the effectiveness of dynamic T-PLS models and the corresponding fault detection methods.

Detectability study for statistical monitoring of multivariate dynamic processes

Fault detection and diagnosis for dynamic processes is an intensively investigated area. However, the problem of determining whether or not system faults can be successfully detected based on the output measurements for a given dynamic process remains an open research topic. An intrinsic definition of fault detectability in multivariate dynamic processes is proposed in this paper. It defines the detectability in an intrinsic manner as a system property, without any reference to any specific fault detection algorithm. Furthermore, the relationship between system structure and the detectability for mean change faults and variability change faults are investigated. Analytical criteria for checking the system detectability are established. The results presented in this paper can provide guidelines on system design improvement for process monitoring and control. A case study is presented that illustrates the effectiveness of the proposed methods.

The Latent Factor VAR Model: Testing for a Common Component in the Intraday Trading Process

In this paper, we propose a framework for the modelling of multivariate dynamic processes which are driven by an unobservable common autoregressive component. Economically motivated by the mixture-of-distribution hypothesis, we model the multivariate intraday trading process of return volatility, volume and trading intensity by a VAR model that is augmented by a joint latent factor serving as a proxy for the unobserved information flow. The model is estimated by simulated maximum likelihood using efficient importance sampling techniques. Analyzing intraday data from the NYSE, we find strong empirical evidence for the existence of an underlying persistent component as an important driving force of the trading process. It is shown that the inclusion of the latent factor clearly improves the goodness-of-fit of the model as well as its dynamical and distributional properties.

Vector-Based Approach Towards Isolation of Sensor Faults in Dynamic Systems

This paper proposes a novel vector-based approach towards isolation of faulty sensors in multivariate dynamic processes. The main contributions are: (1) a set of structured residual vectors is employed for fault isolation; (2) a unified scheme for isolation of single and multiple faulty sensors is proposed; and (3) the optimality of fault detection and isolation is proven.

Monitoring of multivariable dynamic processes and sensor auditing

Industrial continuous processes are usually operated under closed-loop control, yielding process measurements that are autocorrelated, cross correlated, and collinear. A statistical process monitoring (SPM) method based on state variables is introduced to monitor such processes. The statistical model that describes the in-control variability is based on a canonical variate (CV) state space model. The CV state variables are linear combinations of the past process measurements which explain the variability of the future measurements the most, and they are regarded as the principal dynamic dimensions. A T2 statistic based on the CV state variables is utilized for developing the SPM procedure. The CV state variables are also used for monitoring sensor reliability. An experimental application to a high temperature short time (HTST) pasteurization process illustrates the proposed methodology.

Intelligent Sensor Auditing by Interfacing Knowledge-Based Systems and Multivariate Spm Tools

An intelligent sensor monitoring and auditing environment has been developed by interfacing multivariate statistical process monitoring (MSPM) techniques and knowledge-based systems (KBS) for monitoring sensor status in multivariable processes. The real-time KBS development environment G2 is integrated with an MSPM method that can monitor multivariable dynamic processes with autocorrelated data. The MSPM Inethod is based on a canonical variate state space (CVSS) process model of a dynamic process and it is used for auditing sensor status for bias, drift and excessive noise affecting the sensors of multivariable continuous processes. Changes in the magnitudes of means and variances of residuaLs between measured and predicted process variables are used to detect and discriminate sensor abnormalities. The statistical model that describes the in-control variability of sensor readings is based on a CVSS model. The CV state variables obtained from the state space model are linear combinations of the past process measurements which explain the variability of the future measurements the most, and they are regarded as the principal dynamic dimensions. The method can detect and discriminate between bias change, drift, and variations in noise levels of process sensors based on the analysis of data batches. The MSPM modules are developed in Matlab, cOnverted to C, and linked with G2. The presentation will focus on the structure and performance of the integrated system and illustration of the methodology by simulation studies.

State Variable Based Statistical Methods for Auditing Sensors of Multivariable Dynamic Processes

Abstract A statistical process monitoring method based on a state space model of a dynamic process is introduced for auditing sensor status for bias, drift and excessive noise affecting the sensors of multivariable continuous processes. Changes in the magnitudes of means and variances of residuals between measured and predicted process variables are used to detect and discriminate sensor abnormalities. The statistical model that describes the in-control variability is based on a canonical variate state space (CVSS) model. The CV state variables obtained from the state space model are linear combinations of the past process measurements which explain the variability of the future measurements the most, and they are regarded as the principal dynamic dimensions. The method can detect and discriminate between bias change, drift, and variations in noise levels of process sensors based on the analysis of data batches. An experimental application to a high-temperature short-time (HTST) milk pasteurization process illustrates the proposed methodology.

Statistical monitoring of multivariable dynamic processes with state‐space models

AbstractIndustrial continuous processes may have a large number of process variables and are usually operated for extended periods at fixed operating points under closed‐loop control, yielding process measurements that are autocorrelated, cross‐correlated, and collinear. A statistical process monitoring (SPM) method based on multivariate statistics and system theory is introduced to monitor the variability of such processes. The statistical model that describes the in‐control variability is based on a canonical‐variate (CV) state‐space model that is an equivalent representation of a vector autoregressive moving‐average time‐series model. The CV state variables obtained from the state‐space model are linear combinations of the past process measurements that explain the variability of the future measurements the most. Because of this distinctive feature, the CV state variables are regarded as the principal dynamic directions A T2 statistic based on the CV state variables is used for developing an SPM procedure. Simple examples based on simulated data and an experimental application based on a high‐temperature short‐time milk pasteurization process illustrate advantages of the proposed SPM method.

Monitoring of Multivariable Dynamic Processes and Sensor Auditing

Abstract Industrial continuous processes are usually operated under closed-loop control, yielding process measurements that are autocorrelated, cross correlated, and collinear. A statistical process monitoring (SPM) method based on state variables is introduced to monitor such processes. The statistical model that describes the in-control variability is based on a canonical variate (CV) state space model. The CV state variables are linear combinations of the past process measurements which explain the variability of the future measurements the most, and they are regarded as the principal dynamic dimensions. ATstatistic based on the CVstate variablesis utilized for developing the SPM procedure. The CV state variables are also used for monitoring sensor reliability. An experimental application to a high temperature short time (HTST) pasteurization process illustrates the proposed methodology.

Nonlinear time series models for multivariable dynamic processes

Several paradigms are available for developing nonlinear dynamic input-output models of processes. Polynomial models, threshold models, models based on spline functions, and polynomial models with exponential and trigonometric functions can describe various types of nonlinearities and pathological behavior observed in many physical processes. A unified nonlinear model development framework is not available, and the search of the appropriate nonlinear structure is part of the model development effort. Various artificial neural network structures and nonlinear time series model structures are presented and illustrated by developing a model from data sets generated by a series of example systems. The use of a nonlinear model development paradigm which is not compatible with the types of nonlinearities that exist in the data can have a significant effect on model development effort and model accuracy.

Opening the Classroom Closet: Sexual Orientation and Self-Disclosure

In this article, I address two topics that are relevant to family pedagogy: sexual orientation and self-disclosure. I use my teaching experience to demonstrate how content and strategy--in this case, sexual orientation and self-disclosure--can be combined to teach students something important about themselves and about families. By including lesbian, gay, and bisexual perspectives in the classroom in general, and my own experience in particular, I advance my pedagogical aim of teaching more accurate knowledge about families. I illustrate my observations about disclosing sexual orientation with my experience as a teacher and a lesbian, discuss heterosexism and heterosexual privilege in family studies, share an entry from my teaching diary, and propose recommendations for instructors to use in making their teaching about families more inclusive of sexual orientation. In short, I examine how sexual orientation and self-disclosure are valuable components of impassioned teaching. I undertake this objective to incorporate more accurate knowledge about families with an awareness of potential controversy and risk. As an out lesbian, I relinquish the safety that the assumption of heterosexuality confers on people who do not disclose their sexual orientation (Freedman, 1990). People who are heterosexual are not presumed to have a sexual orientation. Although being a lesbian in the classroom when most students and colleagues are heterosexual makes me other in relation to them, being out also gives me some control over defining what sexual orientation means to me. Coming out enriches the subject matter of family studies, provides students with a positive frame of reference for authenticity, and exemplifies that one can have an academic career as an out gay person (Rothblum, 1993). By disclosing important aspects of my identity, I invite and model ways for students to understand their own experiences with social locations such as gender, race, class, and sexual orientation. Many students have said that our classroom is the first time they realized that they, too, had a sexual orientation. Students also learn to examine the privileges, opportunities, and oppressions that accompany their race, class, gender, age, sexual orientation, and physical ability, and gain understanding and respect for others with diverse experiences. SEXUAL ORIENTATION AS PART OF A TEACHER'S IDENTITY In my classes on family theories, methods, and diversity, a major instructional aim is to help students unsettle essentialist categories of social location, and to assist them in understanding the ways in which these identities and structures are social products. As an action-oriented teacher, I want to empower students to not just learn facts but to transform their ways of thinking about and acting upon differences (Allen & Baber, 1992b; Fonow & Cook, 1991). I do so primarily through conversations about personal experiences. I bring my full self into the classroom. When appropriate, I augment the textual material I ask students to read with examples from my own life, inviting students' intellectual and emotional involvement in the course. I share my passionate engagement with family studies to encourage students to learn about subjects that have been marginalized and misrepresented. One of the many topics I share is that I identify myself as a lesbian. I have been heterosexual, and there are lesbians, gay men, heterosexual women, heterosexual men, and bisexual people in my classes. There are also students with identities that I do not have a language inclusive enough to describe. Although some believe that sexual orientation is a fixed identity, I view sexual orientation, like gender, race, class, and age, as fluid and socially constructed (Golden, 1987; Phelan, 1993; Rust, 1993). Sexual orientation, like personality or the self, is not a fixed, unchanging quality, but a multivariable dynamic process that includes sexual behavior, fantasies, and attraction, as well as emotional and social preference, lifestyle choice, and self-identification (Klein, 1990). …

Sexual orientation: a multi-variable dynamic process.

Theory and research concerning sexual orientation has been restricted in its scope and influence by the lack of clear and widely accepted definitions of terms like heterosexual, bisexual, and homosexual. In an attempt to better demarcate and understand the complexities of human sexual attitudes, emotions, and behavior, the Klein Sexual Orientation Grid (KSOG) was developed and administered. The KSOG is composed of seven variables that are dimensions of sexual orientation, each of which is rated by the subject as applying to the present, past, or ideal. Analysis of the data from subjects who filled out the KSOG in Forum Magazine indicated that the instrument was a reliable and valid research tool which took into consideration the multi-variable and dynamic aspects of sexual orientation.