Search SciRate

Existing screening tools for early detection of autism are expensive, cumbersome, time-intensive, and sometimes fall short in predictive value. In this work, we apply Machine Learning (ML) to gold standard clinical data obtained across thousands of children at risk for autism spectrum disorders to create a low-cost, quick, and easy to apply autism screening tool that performs as well or better than most widely used standardized instruments. This new tool combines two screening methods into a single assessment, one based on short, structured parent-report questionnaires and the other on tagging key behaviors from short, semi-structured home videos of children. To overcome the scarcity, sparsity, and imbalance of training data, we apply creative feature selection, feature engineering, and novel feature encoding techniques. We allow for inconclusive determination where appropriate in order to boost screening accuracy when conclusive. We demonstrate a significant accuracy improvement over standard screening tools in a clinical study sample of 162 children.

Motivated by the desire to verify the correctness of algorithms for arrhythmia discrimination used in cardiac medical devices, we present a general wavelet-based characterization of peaks (local maxima and minima) that occur in cardiac electrograms, along with two peak-detection algorithms based on this characterization. Peak detection (PD) is a common signal-processing task, as peaks indicate events of interest, such as heartbeats (in the cardiac setting). The performance of PD thereby directly influences the correctness of the algorithms that depend on its output. We show that our wavelet-based PD algorithms (peakWPM and peakWPB) and a commercial PD algorithm from Medtronic Inc. (peakMDT) are easily expressible in Quantitative Regular Expressions (QREs), a formal language based on regular expressions for specifying complex numerical queries over data streams. We then study the accuracy and sensitivity of the resulting QRE-based PD algorithms on real patient data, and show that the wavelet-based peakWPM algorithm outperforms the other two PD algorithms, yielding results that are on par with those provided by a cardiologist.

Ventricular Fibrillation is a disorganized electrical excitation of the heart that results in inadequate blood flow to the body. It usually ends in death within seconds. The most common way to treat the symptoms of fibrillation is to implant a medical device, known as an Implantable Cardioverter Defibrillator (ICD), in the patient's body. Model-based verification can supply rigorous proofs of safety and efficacy. In this paper, we build a hybrid system model of the human heart+ICD closed loop, and show it to be a STORMED system, a class of o-minimal hybrid systems that admit finite bisimulations. In general, it may not be possible to compute the bisimulation. We show that approximate reachability can yield a finite simulation for STORMED systems, which improves on the existing verification procedure. In the process, we show that certain compositions respect the STORMED property. Thus it is possible to model check important formal properties of ICDs in a closed loop with the heart, such as delayed therapy, missed therapy, or inappropriately administered therapy. The results of this paper are theoretical and motivate the creation of concrete model checking procedures for STORMED systems.

The increased complexity and dynamism of present and future Multi-Agent Systems (MAS) enforce the need for considering both of their static (design-time) and the dynamic (run-time) aspects. A type of balance between the two aspects can definitely give better results related to system stability and adaptivity. MAS organization is the research area that is concerned with these issues and it is currently a very active and interesting research area. Designing a MAS with an initial organization and giving it the ability to dynamically reorganize to adapt the dynamic changes of its unpredictable and uncertain environment, is the feasible way to survive and to run effectively. Normally, MAS organization is tackled by what is called, MAS organizational models, which are concerned with the description (formally or informally) of the structural and dynamical aspects of agent organizations. This paper proposes a two-dimension space, called MOS-2, for positioning and assessing MAS organizational models based on two dimensions: their adopted engineering viewpoint (agent-centered or organization-centered) as the vertical dimension and the agents awareness/unawareness of the existence of the organizational level as the horizontal dimension. The MOS-2 space is applied for positioning a number of familiar organizational models. Its future trends and possible improvements are highlighted. They include the following, (1) adding Time as a dimension, (2) increasing the considered dimensions, (3) providing a quantitative approach for positioning MAS organizational models.

Motivated by the Model-Based Design process for Cyber-Physical Systems, we consider issues in conformance testing of systems. Conformance is a quantitative notion of similarity between the output trajectories of systems, which considers both temporal and spatial aspects of the outputs. Previous work developed algorithms for computing the conformance degree between two systems, and demonstrated how formal verification results for one system can be re-used for a system that is conformant to it. In this paper, we study the relation between conformance and a generalized approximate simulation relation for the class of Open Metric Transition Systems (OMTS). This allows us to prove a small-gain theorem for OMTS, which gives sufficient conditions under which the feedback interconnection of systems respects the conformance relation, thus allowing the building of more complex systems from conformant components.

Modern supervisory control and data acquisition (SCADA) systems comprise variety of industrial equipment such as physical control processes, logical control systems, communication networks, computers, and communication protocols. They are concerned with control and supervision of production control processes. Modern SCADA networks contain highly distributed information, control, and location. Moreover, they contain large number of heterogeneous components situated in highly changing and uncertain environments. As a result, engineering modern SCADA is a challenging issue and conventional engineering approaches are no longer suitable for them because of their increasing complexity and highly distribution. In this research, Multi-Agent Systems (MAS) are used to enable building adaptive agent-based SCADA system by modeling system components as agents in the micro level and as organizations or societies of agents in the macro level. A prototype has been implemented and evaluated within a simulation environment for demonstrating the adaptive behavior of the system-to-be, which results in continuous improvement of system performance.

SCADA (Supervisory Control and Data Acquisition) is concerned with gathering process information from industrial control processes found in utilities such as power grids, water networks, transportation, manufacturing, etc., to provide the human operators with the required real-time access to industrial processes to be monitored and controlled either locally (on-site)or remotely (i.e., through Internet). Conventional solutions such as custom SCADA packages, custom communication protocols, and centralized architectures are no longer appropriate for engineering this type of systems because of their highly distribution and their uncertain continuously changing working environments. Multi-agent systems (MAS) appeared as a new architectural style for engineering complex and highly dynamic applications such as SCADA systems. In this paper, we propose an approach for simply developing flexible and interoperable SCADA systems based on the integration of MAS and OPC process protocol. The proposed SCADA system has the following advantages: 1) simple (easier to be implemented); 2) flexible (able to adapt to its environment dynamic changes); and 3) interoperable (relative to the underlying control systems, which belongs to diverse of vendors). The applicability of the proposed approach is demonstrated by a real case study example carried out in a paper mill.

In complex, open, and heterogeneous environments, agents must be able to reorganize towards the most appropriate organizations to adapt unpredictable environment changes within Multi-Agent Systems (MAS). Types of reorganization can be seen from two different levels. The individual agents level (micro-level) in which an agent changes its behaviors and interactions with other agents to adapt its local environment. And the organizational level (macro-level) in which the whole system changes it structure by adding or removing agents. This chapter is dedicated to overview different aspects of what is called MAS Organization including its motivations, paradigms, models, and techniques adopted for statically or dynamically organizing agents in MAS.

Multi-Agent Systems (MAS) are adopted and tested with many complex and critical industrial applications, which are required to be adaptive, scalable, context-aware, and include real-time constraints. Industrial Control Networks (ICN) are examples of these applications. An ICN is considered a system that contains a variety of interconnected industrial equipments, such as physical control processes, control systems, computers, and communication networks. It is built to supervise and control industrial processes. This paper presents a development case study on building a multi-layered agent-based ICN in which agents cooperate to provide an effective supervision and control of a set of control processes, basically controlled by a set of legacy control systems with limited computing capabilities. The proposed ICN is designed to add an intelligent layer on top of legacy control systems to compensate their limited capabilities using a cost-effective agent-based approach, and also to provide global synchronization and safety plans. It is tested and evaluated within a simulation environment. The main conclusion of this research is that agents and MAS can provide an effective, flexible, and cost-effective solution to handle the emerged limitations of legacy control systems if they are properly integrated with these systems.

One of the most familiar SCADA (supervisory control and data acquisition) application protocols now is OPC protocol. This interface is supported by almost all SCADA, visualization, and process control systems. There are many research efforts tried to design and implement an approach to access an OPC DA server through the Internet. To achieve this goal they used diverse of modern IT technologies like XML, Web services, Java and AJAX. In this paper, we present a complete classification of the different approaches introduced in the literature. A comparative study is also introduced. Finally we study the feasibility of the realization of these approaches based on the real time constraints imposed by the nature of the problem.

Computer-based supervisory control and data acquisition (SCADA) systems have evolved over the past four decades, from standalone, compartmentalized operations into networked architectures that communicate across large distances. There is an emerging trend comprising SCADA and conventional IT units toward consolidating some overlapping activities. This trend is motivated by cost savings achieved by consolidating disparate platforms, networks, software, and maintenance tools. For reasons of efficiency, maintenance, economics, data acquisition, control platforms have migrated from isolated in-plant networks using proprietary hardware and software to PC-based systems using standard software, network protocols, and the Internet. In this thesis, we present an approach for web-based SCADA systems that adapt to the behavior of the target application. In addition, we take into account the real time constraints that imposed by the nature of the problem. We show that our approach is more efficient than other approaches in terms of consuming as little as possible of the available resources (computational power and network bandwidth).

In Model-Based Design of Cyber-Physical Systems (CPS), it is often desirable to develop several models of varying fidelity. Models of different fidelity levels can enable mathematical analysis of the model, control synthesis, faster simulation etc. Furthermore, when (automatically or manually) transitioning from a model to its implementation on an actual computational platform, then again two different versions of the same system are being developed. In all previous cases, it is necessary to define a rigorous notion of conformance between different models and between models and their implementations. This paper argues that conformance should be a measure of distance between systems. Albeit a range of theoretical distance notions exists, a way to compute such distances for industrial size systems and models has not been proposed yet. This paper addresses exactly this problem. A universal notion of conformance as closeness between systems is rigorously defined, and evidence is presented that this implies a number of other application-dependent conformance notions. An algorithm for detecting that two systems are not conformant is then proposed, which uses existing proven tools. A method is also proposed to measure the degree of conformance between two systems. The results are demonstrated on a range of models.

In this paper, we address the problem of local search for the falsification of hybrid automata with affine dynamics. Namely, if we are given a sequence of locations and a maximum simulation time, we return the trajectory that comes the closest to the unsafe set. In order to solve this problem, we formulate it as a differentiable optimization problem which we solve using Sequential Quadratic Programming. The purpose of developing such a local search method is to combine it with high level stochastic optimization algorithms in order to falsify hybrid systems with complex discrete dynamics and high dimensional continuous spaces. Experimental results indicate that indeed the local search procedure improves upon the results of pure stochastic optimization algorithms.