Gaston Lefranc

Olive Fruits Recognition Using Neural Networks

A new method for olive fruit recognition is presented. Olive fruits size and weight are used for estimating the best harvesting moment of olive trees. Olive fruit recognition is performed by analyzing RGB images taken from olive trees. The harvesting decision comprehends two stages, the first stage focused on deciding whether or not the candidate identified in the picture corresponds to an olive fruit, and the second stage focused on olives overlapping in the pictures. The analyses required in these two stages are performed by implementing a neural networks solution approach.

Lateral Control of Autonomous Vehicles Using Multi-Model and Fuzzy Approaches

Abstract This paper discusses the fundamental issues in vehicle lateral motion control within Automated Highway Systems. Lane keeping control and lane changing control are concerned. One major challenge for lateral controller design is the smoothness and robustness under different vehicle conditions. A multi-model fuzzy controller, which includes four local controllers, is then proposed for both the operations of lane keeping and lane changing. These four local controllers are set up for four vehicle speed regions respectively. A fusion block is then introduced to ensure smooth and accurate transition between the different local controllers. The proposed controller inherits the advantages of both the multi-model control and fuzzy control. Simulations show that it could get good performances in the whole range of operation speed, and could also repel the system uncertainties such as changes in vehicle load, movement inertia and wheel cornering stiffness. Furthermore, the calculation procedure of the proposed controller is not complex, and is rather rapid. It appears a promising control algorithm for realtime embedded applications.

A new method for olive fruits recognition

A model for the recognition of the diameter of olives is presented. The information regarding size of olive fruits is intended for estimating the best harvesting time of olive trees. The recognition is performed by analyzing the RGB images obtained from olive tree pictures

SVM and ANN Application to Multivariate Pattern Recognition Using Scatter Data

Several methods of Statistical Process Control (SPC) are used to analyze process measurements with the purpose to detect faults that affect the process stability. SPC has a major drawback because it indicates the presence of faults without explaining which ones and where are the faults. In practical applications, SPC just analyses univariate signals limiting the study of multiple measures. Nowadays, novel methods have been developed for fault analysis based on pattern recognition in control charts. However, the majority of these studies follow a univariate approach. This article proposes a multivariate pattern recognition approach using machine learning algorithms in conjunction with a scatter diagram as the proposed method. In particular the aim of this approach is to monitor quality characteristics of a product in a multivariate environment considering states in control and out of control without the constraints of statistical conditions with the possibility of its application in real time. Results using Support Vector Machines (SVM) and the FuzzyARTMAP neural network showed that multivariate patterns can be recognized successfully in 81% of the cases.

Integration of Algorithms for Maps Construction and Simultaneous Localization in a Mobile Robot

In this paper it is presented an integration of algorithms that permits maps construction and navigation of mobile robots. Simultaneous Localization and Mapping (SLAM) algorithm is used based on FastSLAM method. Navigation system is based on VHF to avoid obstacle and a spiral way trajectory method. To three different complex simulation maps are used to evaluate the system.

A fuzzy approach for on-line error compensation during robotic welding

During robot welding operations in the manufacturing industry there is a need to modify on-line the welding path due to a mismatch in the position of the components to be welded. These positioning errors are due to multiple factors such as ageing of the components in the part conveyor system, clamp fixtures, disturbances, etc. Therefore, robot reprogramming is needed which requires a stop in the production line and consequently an increment in production costs. In this article, we present an alternative solution to this problem that involves the use of structured lighting using a low-cost laser beam, a CMOS camera and a Fuzzy Controller. To validate the proposed control system, a robotic cell was designed using an industrial KUKA KR16 robot for welding metallic plates. The method was evaluated experimentally under lateral and vertical positioning errors. The control interface includes apart from the misalignment correction, the on/off control of the welding power supply, arc voltage and current adjustment, welding torch speed and the control of the distance between the torchs tip and the welding plate. Obtained results using the experimental design method showed a maximum error of 1.6mm, which is considered appropriate for the welding of industrial beads in metallic plates and which demonstrates the methods effectiveness in practical situations.

Conical Tank Level Control with Fractional PID

A simulation study of fractional order PID (FOPID) applied to level control in a conic tank is presented in this paper. An improved mathematical model to represent better the nonlinear dynamic of the conic tank is derived first. This new model is then used to design FOPID with tunning parameters optimized using Particle Swarm Optimization (PSO). The results obtained under reference level changes, are compared with those obtained using standard PID controllers with parameters tunned using the Root Locus Method (RLM) and also with PSO. From this comparison it is concluded that PSO tunned controllers present a better behavior as compared with RLM tunned controllers, considering the Integral of the Absolute Error (IAE) index. Among the PSO tunned controllers the FOPI is the one that had the lowest IAE.

A Fast Multifractal Model for Self-Similar Traffic Flows in High-Speed Computer Networks☆

This paper proposes a new multifractal model, with the aim of providing a possible explanation for the locality phenomenon that appears in the estimation of the Hurst exponent in stationary second order temporal series representing self-similar traffic flows in current high-speed computer networks. It is shown analytically that this phenomenon occurs if the network flow consists of several components with different Hurst exponents.

Using Background and Segmentation Algorithms Applied in Mobile Robots

Abstract In this article a segmentation algorithm for detecting moving objects is presented. The aim of the research is to integrate the algorithm in applications such as car parking video surveillance systems. One of the techniques used in this paper to detect motion in a sequence of images is the use of the background model, which is widely used. The technique allows to detect which objects are moving (without identification) which is the first stage for further processing in tasks such as tracking and object recognition. The results from the segmentation algorithm using several parameters are presented that validate the approach.

Discussion of the Analysis of Self-similar Teletraffic with Long-range Dependence (LRD) at the Network Layer Level

Traffic streams, sources as well as aggregated traffic flows, often exhibit long-range-dependent (LRD) properties. This paper presents the theoretical foundations to justify that the behavior of traffic in a high-speed computer network can be modeled from a self-similar perspective by limiting its scope of analysis to the network layer, since the most relevant properties of self-similar processes are consistent for use in the formulation of traffic models when performing this specific task.