Center for Intelligent Systems

Tallahassee, FL, United States

Center for Intelligent Systems

Tallahassee, FL, United States
SEARCH FILTERS
Time filter
Source Type

George K.,Center for Intelligent Systems | George K.,Bangalore University | Subramanian K.,Center for Intelligent Systems | Subramanian K.,Bangalore University
Proceeding - 2016 International Conference on Computer, Control, Informatics and its Applications: Recent Progress in Computer, Control, and Informatics for Data Science, IC3INA 2016 | Year: 2016

Satisfactory transient response is an important criterion by which a control design can be judged. It is well-known that these transients can become quite unacceptable when linear time-invariant systems with unknown parameters are adaptively controlled. In this paper, we extend the multiple models with second level adaptation approach to adaptively control a class of nonlinear systems linear in the unknown parameters and show satisfactory performance even in the presence of parametric faults. © 2016 IEEE.


Khosravani H.R.,University of Algarve | Ruano A.E.,University of Algarve | Ruano A.E.,Center for Intelligent Systems | Ferreira P.M.,University of Lisbon
2013 IEEE 8th International Symposium on Intelligent Signal Processing, WISP 2013 - Proceedings | Year: 2013

Selecting suitable data for neural network training, out of a larger set, is an important task. For approximation problems, as the role of the model is a nonlinear interpolator, the training data should cover the whole range where the model must be used, i.e., the samples belonging to the convex hull of the data should belong to the training set. Convex hull is also widely applied in reducing training data for SVM classification. The determination of the samples in the convex-hull of a set of high dimensions, however, is a time-complex task. In this paper, a simple algorithm for this problem is proposed. © 2013 IEEE.


Ruano A.E.,Center for Intelligent Systems | Ruano A.E.,University of Algarve | Madureira G.,Instituto Portugues do Mar e da Atmosfera | Barros O.,University of Algarve | And 4 more authors.
Neurocomputing | Year: 2014

This study describes research to design a seismic detection system to act at the level of a seismic station, providing a similar role to that of STA/LTA ratio-based detection algorithms.In a first step, Multi-Layer Perceptrons (MLPs) and Support Vector Machines (SVMs), trained in supervised mode, were tested. The sample data consisted of 2903 patterns extracted from records of the PVAQ station, one of the seismographic network's stations of the Institute of Meteorology of Portugal (IM). Records' spectral variations in time and characteristics were reflected in the input ANN patterns, as a set of values of power spectral density at selected frequencies. To ensure that all patterns of the sample data were within the range of variation of the training set, we used an algorithm to separate the universe of data by hyper-convex polyhedrons, determining in this manner a set of patterns that have a mandatory part of the training set. Additionally, an active learning strategy was conducted, by iteratively incorporating poorly classified cases in the training set. The proposed system best results, in terms of sensitivity and selectivity in the whole data ranged between 98% and 100%. These results compare very favourably with the ones obtained by the existing detection system, 50%, and with other approaches found in the literature.Subsequently, the system was tested in continuous operation for unseen (out of sample) data, and the SVM detector obtained 97.7% and 98.7% of sensitivity and selectivity, respectively. The classifier presented 88.4% and 99.4% of sensitivity and selectivity when applied to data of a different seismic station of IM.Due to the input features used, the average time taken for detection with this approach is in the order of 100. s. This is too long to be used in an early-warning system. In order to decrease this time, an alternative set of input features was tested. A similar performance was obtained, with a significant reduction in the average detection time (around 1.3. s). Additionally, it was experimentally proved that, whether off-line or in continuous operation, the best results are obtained when the SVM detector is trained with data originated from the respective seismic station. © 2014 Elsevier B.V.


Coyle E.J.,Embry - Riddle Aeronautical University | Roberts R.G.,Center for Intelligent Systems | Collins Jr. E.G.,Center for Intelligent Systems | Barbu A.,Florida State University
Autonomous Robots | Year: 2014

The observations used to classify data from real systems often vary as a result of changing operating conditions (e.g. velocity, load, temperature, etc.). Hence, to create accurate classification algorithms for these systems, observations from a large number of operating conditions must be used in algorithm training. This can be an arduous, expensive, and even dangerous task. Treating an operating condition as an inherently metric continuous variable (e.g. velocity, load or temperature) and recognizing that observations at a single operating condition can be viewed as a data cluster enables formulation of interpolation techniques. This paper presents a method that uses data clusters at operating conditions where data has been collected to estimate data clusters at other operating conditions, enabling classification. The mathematical tools that are key to the proposed data cluster interpolation method are Catmull-Rom splines, the Schur decomposition, singular value decomposition, and a special matrix interpolation function. The ability of this method to accurately estimate distribution, orientation and location in the feature space is then shown through three benchmark problems involving 2D feature vectors. The proposed method is applied to empirical data involving vibration-based terrain classification for an autonomous robot using a feature vector of dimension 300, to show that these estimated data clusters are more effective for classification purposes than known data clusters that correspond to different operating conditions. Ultimately, it is concluded that although collecting real data is ideal, these estimated data clusters can improve classification accuracy when it is inconvenient or difficult to collect additional data. © 2013 Springer Science+Business Media New York.


Prabhu S.,Bangalore University | George K.,Bangalore University | George K.,Center for Intelligent Systems
IFAC Proceedings Volumes (IFAC-PapersOnline) | Year: 2014

Model predictive control (MPC) has been attractive in practical designs due to the inherent manner in which both control and state constraints can be incorporated. An open problem is the choice of an appropriate prediction horizon that guarantees both stability and performance. The goal of this paper is to show that an optimal prediction window arrived at by switching between multiple receding-horizon controllers can provide closed loop stability and improve tracking performance. © 2014 IFAC.


Del Bosque J.,Center for Intelligent Systems | Hassard C.,Center for Intelligent Systems | Gordillo J.L.,Center for Intelligent Systems
Proceedings - 2011 10th Mexican International Conference on Artificial Intelligence: Advances in Artificial Intelligence and Applications, MICAI 2011 - Proceedings of Special Session | Year: 2011

Distributed control applications require a reliable network for information exchange. The network discussed on this paper uses CAN bus as a means of communication to control the speed of an electric vehicle. National Instruments Programmable Automation Controller, Compact RIO, based on Lab VIEW programming environment is used to execute one of two different speed control algorithms (PID or fuzzy logic) to test the performance of the implemented vehicle network and the control algorithm itself. It also acts as a human-machine interface via a personal computer. The proposed network provides robustness in terms of communication and opens the possibility of expansion to develop complete control architecture in order to successfully build a fully autonomous vehicle. © 2011 IEEE.


George K.,Center for Intelligent Systems | George K.,PES Institute of Technology | Makam R.,Center for Intelligent Systems | Makam R.,PES Institute of Technology
IEEE International Conference on Control and Automation, ICCA | Year: 2014

In this paper, we deal with the adaptive control of a class of decentralized systems in the presence of a wireless network between the output sensors and the local controller to each subsystem, and when the parameters of other subsystems are assumed to be unknown. Both network-induced packet delay and packet dropout are considered. Switching between actual information and locally available information is the key to the proposed adaptive laws. The multiple models, switching, and tuning methodology is required for further improving the transient performance. © 2014 IEEE.


Capehart T.,Center for Intelligent Systems | Moore C.A.,Center for Intelligent Systems
ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE) | Year: 2015

Some robot developers are considering elasticity to provide compliance for better adaption to a changing environment, shock resistance and safer human-robotic interactions (HRI). In this study we simulate a spherical continuously variable transmission (CVT) to validate its ability as the primary mechanism in a variable stiffness device for a 1D robotic hopper. The spherical CVT has been used in many robotic applications including cobots by Peshkin et al. [1] and as the driving unit in the load sensitive mechanism by Tadakuma et al. [2]. A CVT based variable stiffness/damping device intended for vibration mitigation was presented by Little [3]. That paper presented the kinematics and experiments of the CVT based variable stiffness/damping device for the specific application of vibration mitigation. This study considers the dynamics of the CVT based variable stiffness/damping device and modifies the device based on previous studies. We use ADAMS to simulate the modified system because it captures many of the real world dynamics arising from the CVT's rolling friction dynamics. Finally we present a conceptual design of the variable stiffness CVT and briefly discuss its use in a 1D legged hopper application. Copyright © 2015 by ASME.


Jalil A.,Pakistan Institute of Engineering and Applied Sciences | Cheema T.A.,Center for Intelligent Systems | Manzar A.,Center for Intelligent Systems | Qureshi I.M.,Air University
IET Image Processing | Year: 2010

This study carries out rotation and gray-scale-invariant texture analysis of the textures in Brodatz album. A radon and differential radon transform based technique has been proposed to extract the features of the different textures at different orientations. These features have been used to train one-dimensional hidden Markov models-one for each texture. Testing and classification was done using percentage of correct classification (PCC) as figure of merit. The best percentage achieved was 99.9%. © The Institution of Engineering and Technology 2009.


PubMed | Center for Intelligent Systems
Type: Journal Article | Journal: Bioinspiration & biomimetics | Year: 2015

This paper describes an approach to terrain identification based on pressure images generated through direct surface contact using a robot skin constructed around a high-resolution pressure sensing array. Terrain signatures for classification are formulated from the magnitude frequency responses of the pressure images. The initial experimental results for statically obtained images show that the approach yields classification accuracies [Formula: see text]. The methodology is extended to accommodate the dynamic pressure images anticipated when a robot is walking or running. Experiments with a one-legged hopping robot yield similar identification accuracies [Formula: see text]. In addition, the accuracies are independent with respect to changing robot dynamics (i.e., when using different leg gaits). The paper further shows that the high-resolution capabilities of the sensor enables similarly textured surfaces to be distinguished. A correcting filter is developed to accommodate for failures or faults that inevitably occur within the sensing array with continued use. Experimental results show using the correcting filter can extend the effective operational lifespan of a high-resolution sensing array over 6x in the presence of sensor damage. The results presented suggest this methodology can be extended to autonomous field robots, providing a robot with crucial information about the environment that can be used to aid stable and efficient mobility over rough and varying terrains.

Loading Center for Intelligent Systems collaborators
Loading Center for Intelligent Systems collaborators