Simona Dzitac

Hybrid modified Cuckoo Search-Neural Network in chronic kidney disease classification

Chronic kidney failure (chronic kidney disease ‘CKD’) is a serious disease that related to the gradual loss of kidney function. It is considered one of the health threats in the developing and undeveloped countries At early stages, few symptoms can be detected, where the CKD may not become obvious until significant kidney function impaired occur. CKD treatment focuses on reducing the kidney damage progression by controlling the underlying cause, which requires disease detection at initial stages. In early addition, the financial burden of the treatment and future consequences of CKD requires early detection. In the present work a modified Cuckoo Search (MCS) trained Neural Network (NN) or NN-MCS based model is proposed to detect CKD. The NN-MCS model has been proposed to overcome the problem of using local search based learning algorithms to train the NNs. The NN weight vector is optimized by applying MCS for NN training. A comparative study with eminent classifiers, namely the Multilayer Perceptron Feed-forward Network (MLP-FFN) and NN based on Particle Swarm Optimization (PSO-NN). The classifiers performance is measured in terms of different performance metrics. The experimental results depicted that the NN-MCS has the ability to detect CKD more efficiently compared to any other existing model.

Neutrosophic TOPSIS: A general view

In the last years, several papers in literature have treated the multi-criteria decision making (MCDM) problems in neutrosophic environment. This approach had a starting point the fact that in many real life problems, decision makers have indeterminate, inconsistent or incomplete information about the alternatives with respect to criteria. A brief survey on the applications of neutrosophic sets in MCDM problems is proposed in this paper, hoping that, in this way, we will stimulate further studies and approaches.

Decision Support Model for Production Disturbance Estimation

A current modeling framework for disturbance in manufacturing systems (MS) is given by concepts like discrete-event systems, stochastic fluid models and infinitesimal disturbance analysis. The goal of modeling is to achieve control and structural and functional optimization of MS. Objective functions of these optimization models are focused on quantities which reflect the level of reliability, the level of manufactured products, the quality of products or the impact on the environment of MS with disturbances. These models do not allow a dynamic evaluation of consequences of the disturbances which appears in the operation of MS machines and also do not allow an evaluation of the evolution in time of disturbance consequence indicators. Disturbances in technological lines of MS represent local bottlenecks of production with severe economic consequences in what regards production time losses. Good estimation of disturbances dynamics can be very helpful to both technological line designers, who can optimize their projects and production managers who can minimize their losses. Our model allows a dynamic evaluation of consequences of some disturbance of machine operation in MS, using indicators based on time, energy and costs. A MATLAB software package was developed for tests.

Preliminary issues on brain - machine contextual communication structure development

The increasing sophistication of computer programs and communication systems requires the development of more efficient and interactive human-computer interfaces. One solution to this problem could be the brain - machine interfaces. The aim of this paper is to explore the possibilities of using context dependent interpretations of EEG signals, in addition to signal processing techniques.

Prudent decisions to estimate the risk of loss in insurance

The directive 2009/138/EC „Solvency II”, provides the determination of insurance capital requirements based either on a standard formula or an internal model built by the company and approved by the regulatory authority. The build of an internal model involves the determination of an extreme quantile from the empirical distribution of portfolio. An estimate of this quantile, with a 99.5% confidence level, requires a large number of simulations, each taking into account different scenarios as: insufficient reserves, unfavourable developments of financial assets, etc. The present paper proposes to argue the necessity of the extreme value theory approach in order to estimate the risk of loss for the insurance issue, in accordance with European Directive „Solvency II”, from the perspective of making prudent decisions for the assessment of insurance capital requirements.

Epidemic Algorithm Based Optimal Power Flow in Electric Grids

Time-triggering and distributed nature of the grid are emerging as the major challenge in managing energy in distribution grids. This investigation presents an event triggered distributed optimal power flow (OPF) algorithm for energy grids. To generate the event triggers, we use the epidemic algorithm. The buses are classified into three: infected, susceptible, and dead. The network works in two modes: normal and optimization mode. In the normal mode, only event detection happens and when there are no event triggers, the system is said to be in normal mode. In optimization mode, event triggers that can be a change in generation or demand beyond a threshold value that necessitates the re-optimization of the network, the optimization mode begins. In this mode, the infected node which is infected by change in bus variable intimates it to the energy management application. The energy management application on sensing this change, will initiate the graph grammars which are a set of rules to change the bus nature by detecting the effect of the change on the particular bus. The network is re-optimized using a DC OPF formulation as it is convex and can be solved using simple matrix inversion on the stationary conditions. As a result, the solution of DCOPF problem becomes that of solving a system of linear equations of the form \(Ax=b\), which is solved using Krylov’s method or the Arnoldi algorithm in a distributed fashion. Each node solves the problem of its one-hop neighbours in parallel and this leads to a distributed implementation resulting significant reduction in complexity. The propossed approach is illustrated on a simple 3 bus network.

University Level Learning and Teaching via E-Learning Platforms

Abstract Web-based adaptive collaborative learning environments are more often used to support face to face teaching activities. This paper describes how the educational process may be improved and students may be motivated to do homework tasks and to attend classes in higher education. We describe the implementation and use of e-learning platforms and present our experience in using such platforms in our faculty. The performance of two groups of students is analyzed. The analysis focuses on two aspects: attendance on classes and homework tasks submission. Therefore, the first group had no contact with e-learning environment and they had to attend classes in a traditional way (face-to-face interaction) and to submit their homework via e-mail. The second group had to attend classes and also to use an e-learning platform where they could access course resources and homework tasks. They had also to submit their homework via the platform, while respecting a strict deadline and using the professors’ feedback to improve their homework quality. This paper highlights the importance and the benefits of using collaborative e-learning platforms in higher education to support face to face teaching.

Flight Stability Analysis of a Symmetrically-Structured Quadcopter Based on Thrust Data Logger Information

Quadcopter flight stability is achieved when all of the rotors–propellers generate equal thrust in hover and throttle mode. It requires a control system algorithm for rotor speed adjustment, which is related with the translational vector and rotational angle. Even with an identical propeller and speed, the thrusts generated are not necessarily equal on all rotors–propellers. Therefore, this study focuses on developing a data logger to measure thrust and to assist in flight control on a symmetrically-structured quadcopter. It is developed with a four load cells sensor with two-axis characterizations and is able to perform real-time signal processing. The process includes speed adjustment for each rotor, trim calibration, and a proportional integral derivative (PID) control tuning system. In the data retrieval process, a quadcopter was attached with data logger system in a parallel axis position. Various speeds between 1200 rpm to 4080 rpm in throttle mode were analyzed to determine the stability of the resulting thrust. Adjustment result showed that the thrust differences between the rotors were less than 0.5 N. The data logger showed the consistency of the thrust value and was proved by repeated experiments with 118 s of sampling time for the same quadcopter control condition. Finally, the quadcopter flight stability as the result of tuning process by the thrust data logger was validated by the flight controller data.

Tool-Wear Analysis Using Image Processing of the Tool Flank

Flexibility of manufacturing systems is an essential factor in maintaining the competitiveness of industrial production. Flexibility can be defined in several ways and according to several factors, but in order to obtain adequate results in implementing a flexible manufacturing system able to compete on the market, a high level of autonomy (free of human intervention) of the manufacturing system must be achieved. There are many factors that can disturb the production process and reduce the autonomy of the system, because of the need of human intervention to overcome these disturbances. One of these factors is tool wear. The aim of this paper is to present an experimental study on the possibility to determine the state of tool wear in a flexible manufacturing cell environment, using image acquisition and processing methods.

Decision Based Modeling of a Flexible Manufacturing Cell based on Hierarchical Timed Colored Petri Nets

Abstract The design techniques of flexible manufacturing systems deal, among other methods, with the application of high level Petri Nets. The modeling and simulation of a flexible manufacturing cell (FMC) can be done by implementing hierarchical techniques based on Colored Timed Petri Nets. This paper is focused on implementing decisions and strategies in a flexible manufacturing cell with colored and hierarchical techniques. In this context we discuss the decision making for machine, parts and allocated tools in transitions. The FMC model is designed based on the cell operating at the laboratory of the Faculty of Managerial and Technological Engineering, University of Oradea. In this article, we explain the design techniques using color and hierarchy to evaluate the overall performance of the cell based on part arrival decisions and part processing decisions in transitions of each sub-model of the cell.