System-level design, and dependability prediction of safety-critical systems demand integration of architectural and analysis artifacts in a single development environment. Hybrid systems, with mutual dependencies and extensive interactions between the control portion and its physical environment, further intensify this need. Architecture Analysis and Design Language (AADL) is a model-based engineering language for the architectural design and analysis of embedded control systems. Core AADL has been extended with sub-languages for modeling and analysis of discrete behavior of the control portion, but not for continuous behavior of the physical environment. In a previous work, we have introduced Hybrid Annex for continuous behavior modeling as part of initial findings of an ongoing research effort on fulfilling the need for integrated modeling of the computing system along with its physical environment. In this article, we first detail complete structure of the Hybrid Annex along with appropriate examples for each section. Then, we present formal semantics of the synchronous subset of AADL models annotated with Hybrid Annex specifications using Hybrid Communicating Sequential Processes (HCSP). Formal semantics are used to verify correctness of AADL models (with Hybrid Annex specifications) using Hybrid Hoare Logic (HHL). A case study on a realistically-scaled automatic cruise control system is provided to demonstrate modeling and verification of hybrid systems using AADL with the proposed extension.

We give an introduction to the MARS toolchain for formal modeling and verification of hybrid systems. It consists of translators from Simulink/Stateflow models to Hybrid Communicating Sequential Processes (HCSP), and tools for simulation, code generation, and deductive verification of an HCSP model. We apply the toolchain to model the descent guidance control phase of the recently launched Tianwen I mars lander, and verify that it correctly controls the velocity of the lander.

Abstract Identification of dynamical and hybrid systems using trajectory data is an important way to construct models for complex systems where derivation from first principles is too difficult. In this paper, we study the identification problem for switched dynamical systems with polynomial ODEs. This is a difficult problem as it combines estimating coefficients for nonlinear dynamics and determining boundaries between modes. We propose two different algorithms for this problem, depending on whether to perform prior segmentation of trajectories. For methods with prior segmentation, we present a heuristic segmentation algorithm and a way to classify themodes using clustering. Formethods without prior segmentation, we extend identification techniques for piecewise affine models to our problem. To estimate derivatives along the given trajectories, we use Linear MultistepMethods. Finally, we propose a way to evaluate an identified model by computing a relative difference between the predicted and actual derivatives. Based on this evaluation method, we perform experiments on five switched dynamical systems with different parameters, for a total of twenty cases. We also compare with three baseline methods: clustering with DBSCAN, standard optimization methods in SciPy and identification of ARX models in Matlab, as well as with state-of-the-art identification method for piecewise affine models. The experiments show that our two methods perform better across a wide range of situations.

Practical constrains of user interfaces make the user's judgment (during the feedback loop) deviate from real thoughts (when the full document is read).This is often overlooked in evaluation of relevance feedback.This paper quantitatively analyze the impact of judging inconsistency on the performance of relevance feedback.

User adaptation is a critical problem in the design of human-computer interaction systems. Many pattern recognition problems, such as handwriting/sketching recognition and speech recognition, are user dependent, since different users' handwritings, drawing styles, and accents are different. Therefore, the classifiers for these problems should provide the functionality of user adaptation so as to let each particular user experience better recognition accuracy according to his input habit/style. However, the user adaptation functionality requires the classifiers to have the incremental learning ability, by which the classifiers can adapt to the user quickly without too much computation cost. In this paper, an SVM-based incremental learning algorithm is presented to solve this problem for sketch recognition. Our algorithm utilizes only the support vectors instead of all the historical samples, and selects some important samples from all newly added samples as training data. The importance of a sample is measured according to its distance to the hyper-plane of the SVM classifier. Theoretical analysis, experimentation, and evaluation of our algorithm in our online graphics recognition system SmartSketchpad, are presented to show the effectiveness of this algorithm. According to our experiments, this algorithm can reduce both the training time and the required storage space for the training dataset to a large extent with very little loss of precision.

A novel and fast shape classification and regularization algorithm for on-line sketchy graphics recognition is proposed. We divided the on-line graphics recognition process into four stages: preprocessing, shape classification, shape fitting, and regularization. The attraction force model is proposed to combine progressively the vertices on the input sketchy stroke and reduce the total number of vertices before the type of shape can be determined After that, the shape is fitted and gradually rectified to a regular one, thus the regularized shape fits the user-intended one precisely. Experimental results show that this algorithm can rapidly yield good recognition precision (averagely above 90%) and a fine regularization effect. Consequently, it is especially suitable for weak computation environments such as PDAs, which solely depend on a pen-based user interface.

An online graphics recognition system is presented, which provides users a natural, convenient, and efficient way to input rigid and regular shapes or graphic objects (e.g., triangles, rectangles, ellipses, straight line, arrowheads, etc.) by quickly drawing their sketchy shapes in single or multiple strokes. An input sketchy (hand-drawn) shape is immediately converted into the user-intended rigid shape based on the shape similarity and the time constraint of the sketchy line. Three different (rule-based, SVM-based, and ANN-based) approaches have been applied and compared in the system. Experiments and evaluation are also presented, which show good performance of the system.