Ali Karimoddini

A finite element based method for identification of switched linear systems

Non-stationary time series analysis is important in the study of complex systems. Finding mathematical models for such complex systems with transitions between different phases is an ill-posed problem. This paper brings the problem of time series analysis into the context of hybrid modeling. Approximating the hybrid system by a switched linear system, the problem is reduced to identifying the switching times and model parameters. To address this problem, the non-stationary time series clustering technique based on Finite Elements is used for modeling of switched linear systems. The advantage of this method is that it is not necessary to add restrictive statistical assumptions on system variables. Illustrative examples have been provided to verify the proposed algorithm.

Switched linear system identification based on bounded-switching clustering

This paper aims at identifying switched linear systems, which are described by noisy input/output data. This problem is originally non-convex and ill-posed. The proposed approach utilizes bounded-switching clustering method to convert the problem into a binary integer optimization and least square. This method optimally divides a time series into several clusters whose parameters are piecewise constant in time. Optimal number and order of linear sub-systems as well as the number of switches are selected using Akaike Information Criterion. The performance of the algorithm is evaluated through simulations. Parameters and structures of switched systems are found accurately in the presence of noise.

Delayed and Hidden Variables Interactions in Gene Regulatory Networks

Reverse Engineering of Gene Regulatory Networks (GRN), i.e. Finding appropriate mathematical models to understand complex cellular systems, can be used in disease diagnosis, treatment, and drug design. There are fundamental gaps in the construction of GRN with regard to modeling of hidden/delayed interactions. Addressing these deficiencies is critical to understanding complex intracellular processes and enabling full use of the vast and ever-growing amount of available genomic data. Current modeling strategies either ignore or oversimplify time delays resulted from transcription and translation processes during gene expression. In addition, many research works do not account hidden variables such as transcription factors, repressors, small metabolites, DNA, microRNA species that regulate themselves and other genes but are not readily detectable on micro array experiments. To capture the effect of these parameters, in this paper, we utilize our developed Partially Connected Artificial Neural Networks with Evolvable Topology (PANNET) to find a more comprehensive model of GRN by considering the effects of unknown hidden variables and different time delays. This method is innovative, since the structure of the network has memory and internal states, which can model the unknown hidden variables and time delays. We furthermore use a new evolutionary optimization based on variable-length Genetic Algorithm (GA) to find a sparse structure of PANNET to predict the gene expression levels accurately. Finally we demonstrate the capability of PANNET in constructing GRN, including the effect of different delays and unknown hidden variables through modeling of E. Coli SOS inducible DNA repair system.

Fuzzy modeling of drivers' actions at intersections

Advanced Driver Assistance systems (ADAS) are systems that assist the driver during the driving task. This technology has great potentials in improving driver and traffic safety. It is very important for an ADAS to predict human drivers behaviors at urban environment to avoid crashes. Because of the complexity of human-vehicle interaction, it is difficult to obtain an explicit model for analyzing the drivers behaviors. Instead, models are developed for various driver decisions and driving scenarios (such as lane change decisions and intersection scenarios) which can then be integrated using switch models. Intersections are one of the major scenarios that require special attention in driver behavior modeling. This paper uses Takagi-Sugeno as a data driven technique to model and predict drivers behaviors at intersections. In the proposed technique, a Takagi-Sugeno model is trained for each maneuver using a Gath-Geva fuzzy clustering algorithm. The proposed models are then evaluated with naturalistic real-world driving data collected in urban traffic, and the estimation results are presented. The results suggest that the proposed technique can correctly estimate the drivers actions at intersections with high accuracy. This technique uses fewer numbers of maneuver models for training that leads to less computational complexity.

Identification of anomalies in lane change behavior using one-class SVM

Advanced driver assistance systems are required to detect latent hazards posed by surrounding vehicles and generate an appropriate response to enhance safety. Lane changes constitute potentially risky maneuvers, as drivers involved encounter latent hazards due to surrounding vehicles. A careful study of lane change behavior is therefore essential in identifying potential abnormalities that may lead to various hazards, during the process of a lane change. In this study, an anomaly detection technique is used to compare snapshots of normal and dangerous lane change maneuvers, to identify the abnormal instances. A one-class support vector machine is used and tested for novelty identification of naturalistic driving study data. The results show that the technique is able to detect dangerous lane changes with high accuracy. In addition, results suggest that dangerous behavior could occur before, after or during a lane change maneuver.

Achieving fault-tolerance and safety of discrete-event systems through learning

A system is said to be fault-tolerant if it remains functional even after a fault occurs. By describing faults as unpredicted events, we study the active fault-tolerance of discrete-event systems (DES) while ensuring safety requirements. Starting from a finite automaton model of the uncontrolled plant, our proposed control framework consists of nominal supervision, fault diagnosis and active post-fault control reconfiguration. First a nominal supervisor is designed with respect to the nominal mode to ensure the control specification prior to the occurrence of faults. Second, a learning-based algorithm is proposed to compute a diagnoser that can detect the occurrence of a fault. Necessary and sufficient conditions under which a post-fault safety-enforcing control reconfiguration is feasible are explored, and a second learning-based design algorithm for the post-fault supervisor is presented by using the limited lookahead policies. Effectiveness the proposed framework is examined through an example.

Stable Gene Regulatory Network Modeling From Steady-State Data

Gene regulatory networks represent an abstract mapping of gene regulations in living cells. They aim to capture dependencies among molecular entities such as transcription factors, proteins and metabolites. In most applications, the regulatory network structure is unknown, and has to be reverse engineered from experimental data consisting of expression levels of the genes usually measured as messenger RNA concentrations in microarray experiments. Steady-state gene expression data are obtained from measurements of the variations in expression activity following the application of small perturbations to equilibrium states in genetic perturbation experiments. In this paper, the least absolute shrinkage and selection operator-vector autoregressive (LASSO-VAR) originally proposed for the analysis of economic time series data is adapted to include a stability constraint for the recovery of a sparse and stable regulatory network that describes data obtained from noisy perturbation experiments. The approach is applied to real experimental data obtained for the SOS pathway in Escherichia coli and the cell cycle pathway for yeast Saccharomyces cerevisiae. Significant features of this method are the ability to recover networks without inputting prior knowledge of the network topology, and the ability to be efficiently applied to large scale networks due to the convex nature of the method.

Modeling Driver Behavior at Intersections with Takagi-Sugeno Fuzzy Models

Due to the relatively high density of vehicles and humans at intersections, it is crucial for an Advanced Driver Assistance System (ADAS) to predict human driver behaviors to avoid crashes. Due to the complexity of humans behavior interacting with a vehicle, it is very difficult to find an explicit model to analysis the drivers behavior. In this paper Takagi-Sugeno is used as a data driven technique to model and predict drivers behavior at intersections. In the proposed technique, a Takagi-Sugeno model is trained for each maneuver using a Gath-Geva clustering based algorithm. The proposed models are then evaluated with real time experimental data, and the estimation results are presented.

Hierarchical hybrid modelling and control of an unmanned helicopter

In this paper, we propose a hybrid modelling and control design scheme for an unmanned helicopter. This control structure has a hierarchical form with three layers: the regulation layer, the motion planning layer, and the supervision layer. For each layer, a separate hybrid controller has been developed. Then, a composition operator is adopted to capture the interactions between these layers. The resulting closed-loop system can flexibly command the helicopter to perform different tasks, autonomously. The designed controller is embedded in the avionic system of an unmanned helicopter, and actual flight test results are presented to demonstrate the effectiveness of the proposed control structure.

Development of a Micro Aerial Vehicle

This paper presents a detailed, systematic procedure for developing a Micro Aerial Vehicle (MAV), which is capable of autonomous flight in GPS-denied environments. This MAV is designed for a gross weight of 490 g and flight endurance of 8 minutes. The hardware structure (including the sensors, processors, and mechanical components), the software architecture (including operating system, navigation, control, and data logging), the communication system, and the ground station unit are discussed in detail. The resulting system is able to autonomously carry out an indoor target searching mission with vision-based navigation relying on a monocular camera.