Kewei Yang

A Bayesian approach for sleep and wake classification based on dynamic time warping method

Sleep plays a significant role in human’ smental and physical health. Recently, the associations between lack of sleep and weight gain, development of cancer and many other health problems have been recognized. Then monitoring the sleep and wake state all night is becoming a hotspot issue. Traditionally it classified by a PSG recording which is very costly and uncomfortable. Nowadays, with the advance of internet of things, many convenient wearable devices are being used for medical use, like measuring the heart rate (HR), blood pressure and other signals. With the sleep quality monitor problem, the key question is how to discriminate the sleep and weak stage from these signals. This paper proposed a Bayesian approach based on dynamic time warping (DTW) method for sleep and wake classification. It used HR and surplus pulse O2 (SPO2) signals to analyze the sleep states and the occurrence of some sleep-related problems. DTW is an algorithm that searches an optimal alignment between time series with scaling and shifting and Bayesian methods have been successfully used for object classification in many study. In this paper, a three-step process is used for sleep and wake classification. In the first step, the DTW is used to extract features of the original HR and SPO2 signals. Then a probabilistic model is introduced for using the Bayesian classification for uncertain data. And in the classification step, the DTW features are used as the training dataset in the Bayesian approach for sleep and wake classification. Finally, a case study form a real-word applications, collected from the website of the Sleep Heart Health Study, is presented to shown the feasibility and advantages of the DTW-based Bayesian approach.

A two-stage preference-based evolutionary multi-objective approach for capability planning problems

As a type of long-term planning problems, capability planning problems (CPPs) have received considerable attention in the defense and military area. In this paper, we model CPPs as a type of project scheduling problems, referred to as multi-mode resource investment project scheduling problems (MRIPSPs). The makespan and the cost are simultaneously considered. To deliver decision support, a two-stage approach is developed considering both operational and strategic perspectives. At both levels, knowledge of experts or preference of decision makers is utilized. By integrating domain knowledge at the operational level and preference information at the strategic level into the optimization algorithm, a two-stage preference-based multi-objective evolutionary algorithm is proposed. A hypothetical case with 16 tasks is studied. The experimental results show that by focusing computational efforts on the sub-regions where experts or decision makers are interested, we can obtain the solutions which are not only closer to the true Pareto front in objective space, but also hold good characteristics in decision space.

An Interactive Portfolio Decision Analysis Approach for System-of-Systems Architecting Using the Graph Model for Conflict Resolution

A novel approach based on the graph model for conflict resolution (GMCR) methodology is proposed to address the problem of multistakeholder system portfolio decision analysis encountered in architecting a system of systems (SoS) with desired capabilities. More specifically, a flexible four-process framework for capability-based SoS architecting containing interactive portfolio decision analysis to promote multistakeholder design negotiations on system portfolio selections is presented. By taking full advantage of the inherent realistic and flexible design of the GMCR paradigm, an interactive portfolio decision analysis approach is designed to facilitate the systematic modeling and analysis of system portfolio decisions at the SoS level in order to achieve potential compromises among all key stakeholders having disparate preferences and interacting according to different conflict behavior patterns. This approach permits the prediction of possible mutually agreeable system portfolios for SoS architecture development. Last, the feasibility of the proposed approach is demonstrated using an illustrative example.

A Novel Executable Modeling Approach for System-of-Systems Architecture

A novel executable modeling approach is proposed for system-of-systems architecture by taking full advantage of the Department of Defense Architecture Framework (DoDAF) Meta-model (DM2) and defining the common model transformation specification at the metamodel level. This methodology provides more flexibility and adaptability for the automated construction of executable models directly from the architectural data rather than from static models. More specifically, the architectural data metamodel is first established to guide architectural data modeling of core data elements and associations in DM2 as the common and consistent data dictionary for architecture modeling, while the executable formalism metamodel is designed to formally define executable models. Then, the mapping rules between both metamodels are presented as the common transformation specification regardless of which modeling language or methodology is employed in developing architectural descriptions. Finally, eXtensible Markup Language (XML) technology, like XML schema languages and eXtensible Stylesheet Language specifications, is discussed to facilitate the automated transformation of executable models from architectural instance data. The feasibility of the proposed approach is illustrated using a published example where colored Petri net (CPN) is used as the executable formalism.

The study of guided emergent behavior in system of systems requirement analysis

Emergent behavior is a core trait of SoSs. But the emergence cannot be predicted before its appearance. We propose a method which using Semi-autonomous Agent based simulation to detect the emergent behaviors of SoSs. Agent based Modeling and Simulation are available for the observation of emergent behaviors of SoSs. We propose the multi-agent based simulation methods to demonstrate the evolution of SoSs. Semi-autonomous Agents is applied to model the elements which are consists of SoSs. The framework of Parallel executive and feedback to real world is used to verify and validate the emergent properties which are useful to the SoSs or not. Through the comparation between real world executive results and simulation outcomes, we could regulate the parameters or adjust rules running in the SoSs and guide the emergent behavior of SoSs to the stakeholders desire direction.

Study on System of Systems capability modeling framework based on complex relationship analyzing

System of Systems (SoS) capability has two forms—Capability Requirement (CR) and Capability Property (CP). This paper emphasizes on the emergence process of CP. A double layer CP modeling framework is proposed based on the complexity analyzing of SoS relationships, and the key modeling technique has discussed. The double layer framework addressed a modeling process from micro mechanism modeling to macro behavior distinguishing. The micro mechanism modeling is creating network model of SoS relationship based on analyzing and formalizing SoS complex relationship, and the macro behavior distinguishing is recognizing SoS CP based on aggregating capability index system. The framework researches in SoS internal complex relationship from the prospective of capability, focuses on relationships which have major influence on the CP, and induces the consequence of relationships through nonlinear process modeling.

Structural robustness of combat networks of weapon system-of-systems based on the operation loop

ABSTRACT The structural robustness of the combat network of weapon system-of-systems (CNWSOS) has been widely used to characterise its operation ability and survivability in the integrated joint operations. In this paper, after introducing the concept of the operation loop, a directed CNWSOS network model is first put forward. Then, the directed natural connectivity, a new measure of the CNWSOS robustness that extends the concept of natural connectivity to the directed combat networks, is proposed to provide both a definite physical meaning and a simple mathematical formulation. Last, the feasibility and effectiveness of the proposed structural robustness measure are demonstrated using both numerical experiments and an empirical case study. The directed natural connectivity facilitates a more sensitive and precise quantitative analysis of the structural robustness, which in turn provides useful insights for designing a more robust CNWSOS, including improving the accuracy of intelligence acquisition, enhancing the communication capabilities of weapon systems, and strengthening the capability of precision strikes.

An Approach for Weapon System-of-Systems Scheme Generation Based on a Supernetwork Granular Analysis

A weapon system of systems (WSoS) is a collection of interdependent systems providing multiple interdependent capabilities to support multiple tasks. In this paper, we propose a WSoS scheme generation method based on a granular analysis of a WSoS supernetwork. More precisely, we establish a WSoS supernetwork model based on a “network-centered” combat mode. Next, based on the theory of quotient space, a granular analysis is presented to reduce the complexity of the WSoS scheme generation. Then, the WSoS supernetwork is converted into a directed weighted network with multiple granularities, and an algorithm for the WSoS scheme generation based on the directed weighted network is presented. Consequently, each WSoS scheme corresponds to a path in the directed weighted network, and the capability of supporting the realization of a task by a WSoS can be analyzed based on the schemes. Finally, the feasibility of the proposed approach is demonstrated using an illustrative example.

Executable System-of-Systems architecting based on DoDAF meta-model

Methods used to gain executable architecture are all based on transforming view models to executable models, which can not take the advantage of “data-centric” approach adopted by DoDAF2.0. A novel executable architecting approach transforming DoDAF Meta-model (DM2) to executable model directly is proposed, which can overcame the limitation of traditional approaches that information consistency and data completeness may be damaged. An example to analyze Command and Control (C2) capability in Air Defense System-of-Systems (ADSoS) is provided in detail to illustrate the process to transform DM2 to Coloured Petri Net (CPN). Besides, the input and output data is also given in detail along with the process illustration.

Automatic sleep and wake classifier with heart rate and pulse oximetry: Derived dynamic time warping features and logistic model

This paper presents a novel sleep/wake classification method based on heart rate and pulse oximetry, using logistic model with derived dynamic time warping and correlation features introduced, which were used to classify sleep stages. 100 sleep recordings obtained from the Sleep Heart Health Study dataset, which are available on websites, were used to validate the proposed method. Using the features extracted by our research, classification performance of a LD classifier and feedforward neural classifier were compared to the proposed logistic classifier. The classification accuracy and AUC of the logistic classifier was found to be better (83.8%, 0.924) than those of the two other classifiers (80.1%, 0.732 for LD and 64.0%, 0.801 for neural classifier). The result demonstrated that the proposed logistic classifier using the derived dynamic time warping and correlation features extracted from heart rate and pulse oximetry signals can classify sleep stages efficiently and effectively, which can provide a novel way to carry out automatic sleep stage classification with a wearable device.