Keywords: Nonlinear Systems, Control System Design
Abstract: If a nonlinear system is differentially flat and a flat output is known, the design of a linearizing feedback law is straightforward. For state-space systems, this corresponds to the input-to-state linearization. Otherwise, i.e., if the system is not flat or no flat output can be found, we could carry out an input-output linearization provided the system is minimum phase. In this case, only certain parts of the systems dynamics are assigned by the control law. From a theoretical point of view, this method is based on the Byrnes-Isidori normal form. A less common approach is the usage of the non-flat output in order to carry out a linearization in connection with the generalized controller canonical form Fliess 1990. The linearization is achieved by a dynamic extension. The existence of an alternative linearization method may be advantageous from a computational point of view and gives additional degrees of freedom, e.g. allowing for a higher-order of the desired closed-loop dynamics. Both approaches are illustrated on the nonlinear boost converter model.

Keywords: Robust Control, Nonlinear Systems, Industrial Applications
Abstract: This paper discusses a method enabling optimal control of nonlinear systems that are subject to parametric uncertainty. A stochastic optimal tracking problem is formulated that can be expressed in function of the first two stochastic moments of the state. The proposed formulation allows to penalize system performance and system robustness independently. The use of polynomial chaos expansions is investigated to arrive at a computationally tractable formulation expressing the stochastic moments in function of the polynomial expansion coefficients rigorously. It is then demonstrated how the stochastic optimal control problem can be reformulated as a deterministic optimal control problem in function of these coefficients. The proposed method is applied to find a robust control input for the start-up of an eccentrically loaded drive train that is inherently prone to bifurcation behaviour. A reference trajectory is chosen to deliberately provoke a bifurcation. The proposed framework is able to avoid bifurcation behaviour regardlessly.

Keywords: Nonlinear Systems, Signal Processing, Software Engineering
Abstract: This paper aims at exploring numerical stability properties of various software sensors used in chemical science and engineering. These are applied commonly to evaluation of variables and/or parameters of chemical systems, which cannot be measured by technical means. Practical software sensors are often grounded in the extended Kalman filtering (EKF) method applied to estimation of this and that stochastic model. Usually, a conventional chemical system consists of an Ito-type stochastic differential equation representing the chemical reaction's dynamics and a discrete-time equation linking the model's state to the measurement information. The focus of this research is on the numerical stability of various EKF-based software sensors in the presence of round-off errors. Our case study exploration is fulfilled on the famous Van der Vusse reaction model but used with an ill-conditioned measurement function, here. We reveal that only square-root versions of the EKF-based software sensors (grounded in numerically stable orthogonal transformations) are the methods of choice for state and/or parameter estimations of stochastic chemical systems in the presence of round-off and other disturbances.

Keywords: System Identification and Modelling, Fault Diagnosis and Fault Tolerant Control, Nonlinear Systems
Abstract: The unmodelled rotor dynamics in accelerated flight have a negative effect in the robustness and performance of an unmanned quadcopter, which could result in mission failure in adverse conditions or rotor faults. The nonlinear identification of an unmanned quadcopter rotor dynamics is investigated in this paper. The rotor dynamics are considered in terms of a first-order flapping dynamic model with the dynamics estimated using the radial basis function (RBF) neural networks. A RBF structure based on a continuous forward algorithm (CFA) is implemented for the estimation of a longitudinal rotor flapping dynamic coefficient. This was achieved through optimal input design by the maximization of the spectral density function and predicting the resonant frequency response from the RBF output. This was computed at various trim speeds and training data noise levels and compared with a linear model. The prediction accuracy and robustness to noise of the CFA algorithm proved that the proposed approach can result in better understanding of quadcopter flapping dynamic for high fidelity flight controller design.

Keywords: Nonlinear Systems, Fault Diagnosis and Fault Tolerant Control
Abstract: The problem of reconfiguration in faulty systems containing non-smooth nonlinearities is considered. To solve the problem, the control law is constructed providing full decoupling with respect to fault effects. The suggested solution is based on so-called logic-dynamic approach. The main feature of this approach is that it allows to use well known linear methods for systems with non-smooth nonlinearities. Existing conditions are established and calculating relations are given for the control law. Theoretical results are illustrated by example.

Keywords: Control System Design, Nonlinear Systems
Abstract: Sit-to-stand (STS) movement is a complex functional task which requires coordination of movement, postural regulation and stability for successful execution. STS transfer consolidates the highly nonlinear musculoskeletal structure together with neural control and tactile system in human body. In this paper we propose a nonlinear control technique based on feedback linearization to emulate the control action of central nervous system in performing STS movement. We use 4-segments rigid body biomechanical model with 3 degrees-of-freedom built on average anatomical proportions. In this controlling scheme, we adopt the output feedback computing through physiologically relevant optimization based upon center of mass (COM) and ground reaction forces (GRF). Furthermore, the output feedback provides passive control action commands including a linear quadratic regulator (LQR) based function augmented with nonlinear function computed with feedback linearization. The reference trajectories generate active feedforward torques, in addition with passive torques to settle the motion profiles within human anatomical constraints. The simulation results show that feedback linearization in combination with LQR provides an optimal frame work for better results of biomechanical STS movement as compared to previous linear control design schemes.

Keywords: Manufacturing Systems, Other Topics
Abstract: The paper presents the design of an emulation framework and the associated services that provide the computing resources and services for the design of Manufacturing Systems with regards to Industry 4.0 requirements.

Keywords: Robotics, Control System Design, Biomedical Engineering
Abstract: Hyper-redundant robots of backbone types are generally driven by traction cables, making different curves for different segments in their body. This paper presents the structure of a hyper-redundant robot of backbone type having an electro-rheologhic system for position control. For proper operation, so for bending, we uses a cables system with DC motor-driven. The control system is made with a PIC microcontroller. Modeling the robot's position is done by bending it with cables, combined with locking the desired elements position through the electro-rheological system. The major advantage of this type of drive lies in the fact that the robot modeling can be done with a system with only three cables, the position lock system of an element or segment is relatively simple. Also presented is a modulated width pulse system in which the control variable is the duration of the input signal with constant amplitude and a control system based on a mixed control. This controller is used for control of ER valve, for control of robot curvature

Keywords: Manufacturing Systems, Robotics, Computer Vision
Abstract: The appearance of random event in autonomous processing systems is the main concern in this paper. The main scope is to embed different visual servoing systems (VSSs) with a processing/reprocessing mechatronics line (P/RML) in order to control different complex autonomous systems (CASs) while servicing the line in the operation of recovery of the pieces that did not pass the quality test. For achieving this objective, two different visual servoing systems are designed, tested and implemented for controlling different wheeled mobile robots (WMRs) equipped with robotic manipulators (RMs). To the first one, called eye in hand, the camcorder is located on the last link of the manipulator, thus the visual servoing system is mobile. To the second one, called eye to hand, the camcorder has a fixed position, usually positioned on a P/RML workstation. This paper is focused on video processing and control of different WMRs equipped with RM while serving the P/RML based on fixed or mobile VSSs.

Keywords: Control System Design, Robotics, Nonlinear Systems
Abstract: In this paper is presented the movement control job of a wheeled mobile robot consisting in two tasks. The first task is to solve the nonlinear control for the trajectory tracking problem in presence of uncertainties. This task is solved using a new enhanced Sliding Mode Control law with a saturation component to reduce the chattering phenomenon and to force the reaching time of the sliding surface in presence of disturbances and uncertainties. The second task is to precise move the wheeled mobile robot movement through narrow spaces like doors. This task is accomplished using a proposed laser based narrow space driving algorithm. The real-time experiment of the movement control job is also presented.

Keywords: Discrete Event Systems, Robotics, Manufacturing Systems
Abstract: This article proposes an extended approach to assembly/disassembly mechatronics lines (A/DML) modelling, in terms of service system typologies: autonomous mobile robots, collaborative mobile robots versus mobile robots with parallel action. The A/DML systems served by mobile robots have a specific typology and are modelled by specialized hybrid instruments belonging to Petri Nets class: Timed Petri Nets (TPN), Synchronised Hybrid Petri Nets (SHPN). For the reasons imposed by the production manufacturing management, for transporting components, are used mobile robotic platforms equipped with manipulators, which are dedicated or shared status between production manufacturing lines. The collaborative transport systems meet the specific concepts of shared resources with avoiding collisions while the parallel transport systems are subordinated of synchronized actions concepts. This paper focuses on SHPN models and off-line simulation results for the state, boundedness, viability and possible deadlock of process analysis. Task planning is used to identify synchronous events of SHPN model, the last one being useful for implementing of real-time control

Keywords: Computer Vision, Real Time Applications, Robotics
Abstract: In this paper a novel visual positioning system for slip correction of vehicles in GPS-denied environments based on Kalman filter is presented. Kalman filter fuses 2 sources of data; the first source of data is obtained from odometry, while a computer vision algorithm is used to obtain the second source of data. Using a plane-based pose estimation algorithm that employs four reference points and the Consensus-based Tracking and Matching algorithm (CMT) we were able to obtain pose estimation with centimeter accuracy. The four reference points correspond to the pixel coordinates of the corners of a rectangle closing a region in the roof where the camera should be pointing. Since the employed camera is mounted into the vehicle and it has eye fish lens, an image distortion correction method is used. As the CMT algorithm is robust to scale and rotations, position and orientation (POSE) estimation using computer vision is obtained even if the roof is not completely visible. Autonomous navigation of a ground wheeled vehicle was achieved using the proposed algorithm performing different courses on long period of time and no big slip was observed.

Keywords: Biomedical Engineering, Agent-based Systems, System Identification and Modelling
Abstract: In this paper, we investigate the possibility of using Agent-Based Models (ABMs) for describing a crop growing system. Even though ABMs have received increasing attention for modeling ecological systems, their use in modern farming is still limited. To develop such a model, a proper definition of the plants as agents can be provided following a standard protocol named ODD (overview, design concepts, and details). This description allows to define complex interaction between environment (e.g., soil, climatic conditions, and limited resources) and plants, and between plants. To validate this preliminary development, a comparative study is achieved with a classical crop-modeling environment, i.e., AquaCrop, using potato plants as sample crop.

Keywords: Nonlinear Systems, Hybrid Systems, System Identification and Modelling
Abstract: Complex dynamics arising in biological systems can be characterised by various kinds of attractors. To that end, the task of determining attractors becomes important in modern systems analysis. Biological systems are typically formalised as highly parametrised continuous-time ODE models. Such models can be abstracted in the form of parametrised graphs. In such abstractions, attractors are observed in the form of terminal strongly connected components (tSCCs). In this paper, we demonstrate a novel method for detecting tSCCs in parametrised graphs on several models of cyanobacteria taken from the domain-specific online platform e-cyanobacterium.org.

Keywords: Biomedical Engineering, Instrumentation, Robust Control
Abstract: This paper presents a systematic methodology for designing super-twisting observers. Thanks to a state transformation, the estimation error dynamics can be cast in a Linear Parameter Varying (LPV) framework and a design procedure based on LMIs can be developed ensuring practical stability and finite time convergence. This procedure is applied to the design of 3 super-twisting observers for estimating the reaction rates in a lipase production process from olive oil by Candida rugosa. The estimated rates can be used in an asymptotic observer to reconstruct the component concentrations.

Keywords: System Identification and Modelling, Modelling, Simulation and CAD Tools, Education and Training
Abstract: In this paper, an interactive user-friendly software system for identification of biotechnological processes models is proposed. It is based on optimization programmes using evolutionary algorithm which are built in the Graphical User Interface Development Environment (GUIDE) of MATLAB. The system facilities and functions are demonstrated by using an example of kinetics identification of a process for ethanol production with immobilized cells S. Cerevisiae. A direction for future investigations is outlined.

Keywords: Control System Design, Modelling, Simulation and CAD Tools, Nonlinear Systems
Abstract: This study investigates simultaneous pH and dissolved oxygen control (DO) in a closed photobioreactor (PBR), using a conventional linear feedback technique, i.e. individual PID and PID coupled with feedforward compensation. The proposed control scheme has been designed using linear approximations, whereas their evaluation has been done through simulation, considering a nonlinear process model, describing the complexity of this multivariable biological process. The proposed control including feedforward compensation present improved control performances, and consequently improves microorganism's growth conditions. This is of crucial importance in the case of lab scale set ups that have to provide fully controlled cultivation conditions for accurate study of growth dynamics.

Keywords: Adaptive Control, Nonlinear Systems, System Identification and Modelling
Abstract: In this paper, a novel multivariable adaptive control scheme for a lactic fermentation biotechnological process with unknown inputs taking place inside two sequenced Continuous Stirred Tank Reactors (CSTRs) is developed. The design of the control scheme is achieved under the hypothesis that the influent substrate concentrations and the reaction kinetics are unknown and time-varying, but also a part of the state variables are unmeasurable. The adaptive controller includes a linearizing controller connected with two state observers used for the real-time estimation of the unknown input substrate concentrations and with a parameter estimator which is used for kinetics estimation. The estimation of unknown influent substrate concentrations is realized by using the measurements of the internal substrate and lactic acid concentrations. The proposed parameter estimator employs the information which is provided on-line by two sliding-mode state observers. The performance of the designed control scheme is evaluated via simulation experiments conducted for a lactic acid production process carried out inside two sequenced CSTRs. The dynamics of the considered bioprocess is described by a nonlinear, incompletely known and time varying model.

Keywords: Software Engineering, Real Time Applications
Abstract: Byzantine music represents a vast and complex musical tradition which precedes contemporary Western music. Nowadays, it is used mostly within Eastern Christian churches. Few computer software applications deal with Byzantine music and the imperfect command of Byzantine music theory among singers often requires parallel classical notation staves. A software application written in C++ has been written, which enables the user to write simple musical scores using standard notation, as well as Byzantine music compositions using a subset of the specific Byzantine notation. The application can be used to produce transcriptions of Byzantine-notation compositions into their classical notation counterparts. Extensive data structures and algorithms for containing and manipulating the data, as well as interacting with the computer user, have been developed. Additionally, the application offers some serialization capabilities, as well as preliminary support for pitch tracking. By offering the functionality described above, the application is an example of modern technology being used to preserve cultural heritage.

Keywords: Software Engineering
Abstract: The retrieval of images depending on content is a recurrent research topic in medical imaging. Most CBIR systems are designed to help physicians in the diagnostic of the pathologies. Image retrieval according to the content of the texture features can be performed through various methods developed so far. Local texture features are very beneficial for the analysis of the texture, thus, they are extensively used in image retrieval. The original LBP is improved in this paper with a new addition for CBIR called uniform extended local ternary pattern (UELTP). The method decomposes the image into objects; local texture features are extracted and stored into n-dimensional texture feature vectors. Then, the images are frequently obtained from a huge database dedicated for images using these vectors. In this paper, the performance of LBP descriptor, LTP and ELTP are evaluated for CBIR. According to the results, uniform extended local ternary pattern more accurate than other descriptors in terms of image retrieval.

Keywords: Software Engineering, Other Topics
Abstract: Modern software applications are complex, and their maintenance implies elaborate analysis tools that reveal their structure and functionality, for purposes like software understanding or quality assessment. This paper introduces ViMC, a tool we have developed to support software engineers in analyzing the structure of object-oriented software applications, by focusing on measuring the various aspects that define the properties of the entities within a software project. The tool provides a set of predefined software metrics that can be applied to sets of classes and packages within a given software application, while allowing the user to dynamically create new metrics, as needed. The definition of custom metrics is done either through programming, or by interactively combining existing metrics via a user interface.

Keywords: Databases and Data Mining, Software Engineering, Other Topics
Abstract: Not until long ago, performing a study on how the graduates of a University programme have integrated in the labour market was a tedious task, requiring the sending and, hopefully, the receiving of (online) questionnaires. Fortunately, given the popularity of professional social networks, carrying out a survey is now much easier, as former students can simply export their online profiles while giving consent for processing their data. As a small-scale case-study, this paper uses professional information from a number of alumni of the Computer specialisations of the Faculty of Automation, Computers and Electronics, University of Craiova. Given its highly-interconnected structure, for modelling this snapshot of the local Information and Communication Technology (ICT) workforce, we chose to use Neo4j, the most popular graph database. By relying on a set of data visualisation techniques, the resulting system allowed for the uncovering of valuable feedback and insights from within this data. Several remarks are made regarding the observed trends among current employees. Moreover, a discussion is carried out on of how corporate information can unknowingly get leaked on social media by a collective of employees. While this case-study is limited for a very specific use-case, the proposed approaches can easily be extended for various scenarios.

Keywords: Software Engineering, Real Time Applications, Education and Training
Abstract: The present work demonstrates the mechanisms, programming design choices and paradigms of developing an Android-backed online turn-based social game application. Each step of the programming process is detailed, and the underlying implemented concepts and reasonings for the different modules are explained using the Model - View - Controller architectural pattern. Software engineering design choices are compared and exemplified at each stage of the development phases, giving suggestions for improving the logic behind such a distributed service. This paper also shortly presents insights on the usage of an online cloud database (Firebase, from Google) in order to handle player data in real-time using JSON format.

Keywords: Optimization, Discrete Event Systems, Theory of Algorithms
Abstract: Medical doctors working in hospitals should spend their working time taking care of the patients. However, in the Spanish hospitals, they also play the role of decision makers being involved, for example, in scheduling surgeries in operation rooms. Although some doctors might be doing this for a long time, which gives them experience in such decisions, the efficiency of the operation room can be improved with the help of some technical solutions that are the result of advanced research in planning and scheduling surgeries. Such technical solutions can also decrease the overtime hours and reduce the under/over utilization of some operating rooms. This paper's focus is to create such a solution that will help medical doctors to spend less time in managing tasks and have a better occupancy rate within the available capacity of the operation room. It will also decrease the stress level and allow the medical doctors to offer more of their time to healthcare. The contributions of this paper are: (i) a new heuristic algorithm for scheduling operations that do not require the use of any optimization tool, (ii) an in-built managing system for patients and operation rooms in the Operating Theater, and (iii) simulation results using real data in the proposed software tool. The created interface is intuitive and developed with direct feedback from doctors allowing different access level, for a better security of the medical data.

Keywords: Embedded Systems, Computer Vision, Robotics
Abstract: In this paper a method of controlling a wheelchair using the video streams from two cameras is proposed. The cameras are placed on the side of the wheelchair having as main purpose to detect the edge between the floor and the wall. The images obtained are processed, thus obtaining an inclination angular error and a lateral error from the desired trajectory, which is considered at the middle of the distance between the two lateral references. With the combined information from the camera and from the sensors conveniently placed on the system, the navigation inside a building with corridors delimited either by walls, by lines or by transitions is achieved.

Keywords: Computer Vision, Robotics, Discrete Event Systems
Abstract: Following the increased use of mobile platforms, the collision between the mobile platform and elements in its operating environment has become an issue of growing importance. Even if there are extensive researches about the ways to avoid those collisions (sensors, control strategies), in a real-life scenario the dynamics of all the other environmental elements leads to situations when the collision becomes unavoidable. In this paper we proposed, developed and evaluated a test stand for collision analysis, for a previously published theoretical model for planar link in contact with a granular material. The knowledge acquired during this work can be successfully used for impact tests for mobile platforms.

Keywords: Robotics
Abstract: This paper deals with several aspects of a medical wheelchair. There is a mechanical three-wheels type structure that contains a single simultaneous drive and steering wheel and two passive wheels mounted on the same rear axle. The direct kinematic model and the inverse kinematic model are first developed. Then, dynamic aspects of the medical wheelchair navigation on a required trajectory are presented and analyzed. This is constituted by the succession of different types of sections, linear or curvilinear. It is intended to develop driving laws that do not introduce sudden step variations to changing sections. In this respect, the paper presents two driving solutions on complex trajectories: driving strategy through direction and speed driving strategy, respectively. For each, aspects that are more particular are considered.

Keywords: Hybrid Systems, Manufacturing Systems, Robotics
Abstract: The main objective of this research is to obtain a good model for the tasks performed by a flexible manufacturing mechatronics line (FMML) with integrated complex autonomous systems (CASs). The FMML has four collaborative workstations, line shaped, and being serviced by two CASs, wheeled mobile robots (WMRs) with robotic manipulators (RMs), for caching, transporting and releasing work piece. The decision of a good or bad work piece is being taken after a quality test that is performed by last stations in the line. Following this hypothesis, the processing/reprocessing mechatronics line (P/RML) serviced by two complex autonomous systems, and visual servoing systems, was modelled as synchronized hybrid Petri nets (SHPN). The complex autonomous system are controlled in trajectory tracking using sliding mode control (SMC) method, while RMs are positioned by visual servoing systems for caching and releasing work piece.

Keywords: Control System Design, Linear Systems, Nonlinear Systems
Abstract: In this paper the problem of sample data cooperative output regulation for the leader-following formation (LFF) problem of a homogenous multi agent system is investigated. For sample data LFF problem a distributed design approach is proposed using luenberger observer, distributed observer and a zero-order hold circuit. The designed approach enables the robots to track a discrete reference signal generated by the leader and to achieve and maintain the desired formation for the provided initial conditions. A driving force is provided by the exogenous system which serve as a leader for the robot formation. In view of time varying interaction between robots, one case of fixed network topology and two cases of switching network topologies are considered to exhibit the multirobot network relationship. The theoretical results are verified through numerical simulations of four nonholonomic multirobot network. The simulation highlights that the robots are maintaining the desired formation and are also tracking the trajectory of the leader robot under fixed and switching topologies of the multinetwork system.

Keywords: Nonlinear Systems, Control System Design, Optimization
Abstract: This work presents the design of active disturbance rejection control (ADRC) strategy to position control of a single-link flexible joint robot manipulator. Two schemes of ADRC are presented, Linear Active Disturbance Rejection Controller (LADRC) and Nonlinear Active Disturbance Rejection Controller (NADRC). A comparison study in terms of transient performances, robustness characteristics and disturbance rejection capabilities has been made based on LADRC and NADRC. The robustness of both controllers is evaluated by measuring the amount of deviation in system performance due to uncertainty in system parameters. One issue with NADRC and LADRC is they include various parameters and unless they are properly tuned, will have an adverse effect on the estimation process and in turn, on the system performance. The particle swarm technique (PSO) has been selected as an optimal tuner to improve the estimation process and thereby, to enhance the system performance.

Keywords: Control System Design
Abstract: This paper aims to presents the results obtained in electromechanical wind speed emulator of distributed low power system. The results are obtained in insulated regime with a step up/down converter, battery bank and resistive load. All the operating regions are aimed, namely optimization and power limitation one, and also an intermediate operating region is considered in order to ensure smooth transition between these two regions. For control purpose an improved strategy is proposed. Hardware implementation is done under DS1103 controller board running under Matlab and ControlDesk software. This paper present results from a functional low power wind system, part of a distributed multisource low power system, which offer also the possibility of implementing the behavior and the control of such systems, in grid-connected or disconnected from the national grid. Experimental results show the effectiveness of the proposed system under various conditions.

Keywords: Computer Vision, Robotics, Real Time Applications
Abstract: One of the key features of a fully autonomous mobile robot is represented by the ability to recharge itself with energy. This paper proposes a solution for recharging an autonomous mobile robot with power so that it can perform tasks with little or no human intervention. This paper continues our work on the implementation of a mobile platform based on computer vision. In a previous paper, we implemented the foundation of the platform, in which a mobile robot detected several targets and navigated autonomously between them. We have shown that a small-size computer is perfectly capable of performing multiple tasks such as object detection, processing input data from distance sensors, sending movement commands to electric motors. The charging areas are marked with specific signs that the mobile robot can recognize using computer vision software and specific algorithms. The robot can navigate to such an area, connect to a socket, fully recharge with energy, disconnect and resume its preset activities. The prototype for this study uses in-house developed software based on OpenCV graphic library, Python language, Unix-like operating system - Debian Jessie and low-cost, high performance computer Raspberry Pi 3, model B with a CPU at 1.2 GHz 64bit quad-core ARM, 1GB of RAM, commercial robotic kits, ultrasonic sensors, Raspberry Pi camera, commercial Li-Po rechargeable battery and adaptor, a wireless charging kit, and a digital compass. The paper presents a series of promising results obtained with this structure, which could be used as a platform for future applications in various fields.

Keywords: Real Time Applications, Industrial Applications, Robotics
Abstract: The restrictions imposed on real-time functioning are sometimes particularly severe and require firm action. At the same time, the design of the control algorithms for perturbations rejection includes a multitude of theoretical and practical solutions that exist in the literature. Here, we can note the methods based on robustification, on algorithms with specific degrees of freedom, etc. The paper presents a method based on the very rapid switching of the control algorithms, proposing at the same time a new switching method. The solutions proposed are tested on an MIMO process in a real time application in the vehicle control area.

Keywords: Nonlinear Systems, System Identification and Modelling, Modelling, Simulation and CAD Tools
Abstract: A Permanent Magnet Synchronous Generator is chosen as a case study for this comparison. A continous model with a discrete integrator is shown to be the best solution for the discretization of the nonlinear model. Then, the Kalman Filter (KF), the Extended Kalman Filter (EKF) and the Unscented Kalman Filter are compared. The results are presented and it is shown that the EKF is the best suited for this application. Moreover, a discussion regarding the behaviour of the filters follows, where all are shown to act like proportional controllers.

Keywords: Nonlinear Systems, Control System Design, System Identification and Modelling
Abstract: The paper deals with the fuzzy control of a photoautotrophic microalgae growth process in photobioreactors. The non-linear mathematical model of the process is presented and a fuzzy control algorithm is implemented in order to control simultaneously the algal biomass concentration, the pH and the average irradiance inside the photobioreactor. The results of the fuzzy control are obtained in numerical simulation and experimentally. The experiments were developed using the photobioreactor designed in our laboratory, from "Dunarea de Jos" University of Galati. The microalga Desmodesmus Quadricauda supplied by the Biological Research Institute from Cluj-Napoca, Romania, was used within the experiments.

Keywords: Distributed Systems, Fault Diagnosis and Fault Tolerant Control, Computational Intelligence
Abstract: Water distribution is arguably the most important factor in modern times. The quality of service is nonetheless taken for granted while requiring regular maintenance and timely repairs. Therefore, there is an increased demand in efficient operation requiring modern solutions to age-old problems. Multiple theoretical and practical approaches exist for leak detection. In this paper, a model-based approach is extended with modern concepts from the field of Machine Learning for improving leak detection accuracy in water distribution systems.

Keywords: System Identification and Modelling, Computational Intelligence, Nonlinear Systems
Abstract: As large scale energy management strategies have gradually shifted the focus from the producer to the consumer side, buildings are starting to play a critical role in the efficient management of the electrical grid. Moreover some buildings have become prosumers by integrating local generation capabilities from renewable sources thus inducing additional complexity into the operation of the energy systems. As alternative to conventional energy consumption modelling techniques, a black-box input-output approach has the ability to capture underlying consumption patterns and trends while making use of the large quantities of data being generated and recorded through dense instrumentation of the buildings. The paper discusses and illustrates an approach to apply deep learning techniques, namely Recurrent Neural Networks implemented by means of Long Short-Term Memory layers, for load forecasting. We focus on large commercial buildings which can be better managed by central operators and where better models can result in significant energy savings and broad economic and social impact. The case study is illustrated on two university buildings from temperate climates over one year of operation using a reference benchmarking dataset for replicable results. The obtained results show promise and can be further used in reliable load management algorithms with limited overhead for periodic adjustments and model retraining.

Keywords: Biomedical Engineering, Signal Processing, Computer Architecture
Abstract: The paper presents how the skin cancer in forms of melanoma can be identified based on the digital image processing of the lesion. The solution is based on the extraction of seven features (deterministic and statistic) from the image of a skin lesion: perimeter, area, radius, fractal dimension, lacunarity, histograms of oriented gradients, and local binary patterns. Each feature has attached a specific classifier and the diagnosis is obtained by using a voting scheme in the final classifier. The experimental results on a free database demonstrate that the method provides a high accuracy.

Keywords: Manufacturing Systems, Internet of Things
Abstract: Today's industry is facing an increased need for implementing intelligent manufacturing solutions, capable of integrating existing machinery with new technologies. Current solutions do not provide support for analyzing vast amounts of data. Also, implementation of cloud architectures proved inappropriate for real-time or near real-time processing and control because of the network latency. Under these considerations, the new paradigm of fog computing provides promising characteristics enabling greater scalability, fast reaction time and increasing security through a local private processing cloud structure. This paper evaluates the integration capabilities between existing technologies with new devices for seamless integration of the fog computing paradigm and provides an architecture solution for this upgrade.

Keywords: Internet Security, Communication Systems
Abstract: Data security is one of the most important challenges in the information era; the extended use of big data leads to the necessity of hiding the content of a message from unauthorized users so that, prior to transmission, an encryption has to be performed. Chaotic cryptography, a field of modern cryptology, was recently developed as an application of nonlinear dynamics in the chaotic regime. The paper presents a new approach regarding the implementation of a chaos-based color images encryption algorithm, with a specific application that aims to ensure better information security.

Keywords: Theory of Algorithms, Nonlinear Systems, Education and Training
Abstract: The increasing use of satellite faraway sensing for civilian use has proved to be the most cost effective means of mapping and monitoring environmental changes. From this point, these new tools are now essential in monitoring operations for vegetation and non-renewable resources, especially in developing countries. Data can be gotten as frequently as required to deliver information for determination of quantitative and qualitative changes in terrain. In reaching the aim of studying the forest composition and the vegetation dynamics during the time using satelitar imagery a k-means algorithm of chromatic analysis is proposed. In this way, by using comparisons between chronologically ordered records, could be described the vegetation changes and its developments in a given area. The exposed method in the present work suggests the joining two successive phases: the first step were used resolution suitable satellite images in order to succeed in building a model. The study was conducted between 1990 and 2017 by using LANDSAT data set. In the second phase, are applied chromatic investigation algorithm in order to succeed in reaching a map of vegetation composition. The case study is that of Independenta Forest from Galati County. For discussion are presented three cases of September 2011, 2016 and 2017 Preliminary results on the composition evaluations are promising and the research is ongoing.

Keywords: Computational Intelligence, Education and Training, Other Topics
Abstract: In this paper we present a comparative analysis between statically methods based on PCA analysis and an expert system built to identify tree species based on their GC-FTIR and UV-VIS-IR spectra. We also present a spectroscopic analysis to evaluate the relevance of each type of sample set on which recognition of an unknown sample is based.

Keywords: Biomedical Engineering, Computational Intelligence
Abstract: The resource management is one of the key factors for any successful and safe activity. This is even more applicable in medical field, where particular demands are necessary. Thus, the physicians (and other medical stuff) are not only responsible for specific medical interventions; they have to also provide the health care environment that includes many other aspects. For instance, one significant activity performed by the medical stuff is the medication stock management. The purpose of this paper is to describe an automated system aimed to help them with this activity. This application is able, at the time being, to receive information from peripheral equipment, to store it into a database and to display all the actions performed by different users of the system. This way, any placement or displacement of medication vials and small dimension medical objects is automatically detected and registered by the system.

Keywords: Databases and Data Mining
Abstract: This paper attempts to discover a better entropy-based splitting criterion for the induction of the Decision Trees (DT) than the entropy-based splitting criteria known so far. Eight entropy-based splitting criteria along with the performance tests carried out by three DT built on their basis, were taken into account: unpruned DT, pessimistically pruned DT and error-based pruned DT. All of these DT types were trained on seven databases, and then executed on their test data. Our experiments highlight the very good performances achieved by the square information gain ratio1 splitting criterion, which has shown always a better behavior than the information gain ratio criterion used in C4.5 algorithm and than other six information entropy based splitting criteria.

Keywords: Modelling, Simulation and CAD Tools, Distributed Systems, Computational Intelligence
Abstract: This paper deals with the complex problem of reliability evaluation of stochastic networks in which both links and nodes failures are considered, and compares two approximate approaches able to reduce the computation time: a sum of disjoint products (SDP) approach and another based on Monte Carlo simulation. In case of the SDP approach, the reliability is computed based on the minimal paths. In a first stage, only the links of the network are considered, and a "multiple variables inversion" technique for developing the set of minimal paths into a sum of disjoint products is applied. Then, in a second stage, each term of the set of disjoint link-products is processed separately taking into consideration the reliability values for both links and adjacent nodes. In case of Monte Carlo simulation, for speeding up the method and reducing the computation time, both minimal paths and cuts are considered. Also, other acceleration techniques are applied.

Keywords: Education and Training, Agent-based Systems, Computational Intelligence
Abstract: The currently developing industry demands more and more IT specialists day by day. Many industrial systems are automated using servers based on Unix and Linux operating systems in industries like: automotive, telecommunications, production etc. Universities and other teaching organizations tend to lack human resources since most of the potential tutors are already employed in the IT industry having significant beneficial packages. In this context cloud enabled auto-generative learning objects can help in the process of training of new IT specialists. They offer the possibility to reuse learning patterns and to fill them with randomly generated and controlled data. Thus, students can learn, exercise and auto-assess their knowledge in Unix commands to be ready for employment in the IT industry.

Keywords: Optimization, Agent-based Systems, Biologically Inspired Systems
Abstract: Memetic Algorithms (MAs) are a class of stochastic global search heuristics in which Evolutionary Algorithms (EAs) - based approaches are combined usually with heuristic local searches. This hybridization is meant to reach solutions that would otherwise be unreachable by evolution or a local method alone. In this work, we propose three Local Search (LS) algorithms for hybridization with an existing Evolutionary Algorithm with Pareto ranking in order to define biological intelligence using the concepts of useful and utility and therefore to zoom on the basin of attraction of promising realistic solutions. Our experimental results with these memetic algorithms in the game of Checkers show how we can learn the organization of behaviors into paths of behaviors of different lengths and frequencies and then reveal the true nature of these behaviors.

Keywords: Automotive Control Systems, Computational Intelligence, Software Engineering
Abstract: It is becoming increasingly evident that data science and artificial intelligence are key technologies in the future of automotive industry. Artificial Intelligence (AI) successes are significant, with some limitations in terms of algorithms portability and code industrialization for mass production and deployment. This is because there are many domains where several software development process standards need to be applied.

The approach presented in this paper tries to overcome this issue by creating a unique platform with multiple artificial intelligence engines. By using state-of-the-art AI libraries, together with target-independent software, tackles the challenge of driving context recognition in embedded systems, and uses it as a validation method.