Relaxed constraints support vector machines for noisy data

Real-world data collected for computer-based applications are frequently impure. Differentiation of outliers and noisy data from normal ones is a major task in data mining applications. On the other hand, elimination of noisy and outlier data from training samples of a dataset may lead to over-fitting or information loss. A fuzzy support vector machine (FSVM) provides an effective means to deal with this problem. It reduces the effect of the noisy data and outliers by using a fuzzy membership functions. In this paper, a new formation for SVMs is introduced that considers importance degrees for training samples. The constraints of the SVM are converted to fuzzy inequalities. The proposed method, RSVM, shows better efficiency in the classification of data in different domains. Especially, using the proposed RSVM for multi-class classification of arrhythmia disease is presented at the end of this paper as a practical case study to show the effectiveness of the proposed system.     

Prediction of phosphorus content of electroless nickel–phosphorous coatings using artificial neural network modeling

A multilayer feedforward neural network with two hidden layers was designed and developed for prediction of the phosphorus content of electroless Ni–P coatings. The input parameters of the network were the pH, metal turnover, and loading of an electroless bath. The output parameter was the phosphorus content of the electroless Ni–P coatings. The temperature and molar rate of the bath were constant ( 91^° \textC, 0.4 \textNi^{\text + +} /\textH₂ \textPO₂ ^{- -} 91^\circ {\text{C}},\:0.4\,{\text{Ni}}^{{{\text{ + + }}}} /{\text{H}}_{2} {\text{PO}}_{2}^{{ - - }} ). The network was trained and tested using the data gathered from our own experiments. The goal of the study was to estimate the accuracy of this type of neural network in prediction of the phosphorus content. The study result shows that this type of network has high accuracy even when the number of hidden neurons is very low. Some comparison between the network’s predictions and own experimental data are given.     

Video transmission enhancement in presence of misbehaving nodes in MANETs

Mobile Ad-hoc NETworks (MANET) are infrastructureless networks where self-configuring mobile nodes are connected by wireless links. Because of its decentralized operation, these nodes rely on each other to store and forward packets. Video transmission over MANETs is more challenging than over conventional wireless networks due to rapid topology changes and lack of central administration. Most of the proposed MANET protocols assume that all nodes are working within a cooperative and friendly network context. However, misbehaving nodes that exhibit abnormal behaviors can disrupt the network operation and affect the network availability by refusing to cooperate to route packets due to their selfish or malicious behavior. In this paper, we examine the effect of packet dropping attacks on video transmission over MANETs. We also study the effects of mitigation using intrusion detection systems to MANET in presence of video traffic. To the best of our knowledge, this is the first attempt to study multimedia over such environments. We propose a novel intrusion detection system, which is an adaptive acknowledgment scheme (AACK) with the ability to detect misbehaved nodes and avoid them in other transmissions. The aim of AACK scheme is to overcome watchdog weaknesses due to collisions and limited transmission power and also to improve TWOACK scheme. To demonstrate the performance of our proposed scheme, simulation experiments are performed. The results of our experiments show that MPEG4 is more suitable for our simulation environment than H264 video traffic. The simulation results show that AACK scheme provides better network performance with less overhead than other schemes; it also shows that AACK outperforms both TWOACK and watchdog in video transmission applications in the presence of misbehaving nodes.     

User Activities Outliers Detection; Integration of Statistical and Computational Intelligence Techniques

In this article, a hybrid technique for user activities outliers detection is introduced. The hybrid technique consists of a two‐stage integration of principal component analysis and fuzzy rule‐based systems. In the first stage, the Hamming distance is used to measure the differences between different activities. Principal component analysis is then applied to the distance measures to find two indices of Hotelling's T² and squared prediction error. In the second stage of the process, the calculated indices are provided as inputs to the fuzzy rule‐based systems to model them heuristically. The model is used to identify the outliers and classify them. The proposed system is tested in real home environments, equipped with appropriate sensory devices, to identify outliers in the activities of daily living of the user. Three case studies are reported to demonstrate the effectiveness of the proposed system. The proposed system successfully identifies the outliers in activities distinguishing between the normal and abnormal behavioral patterns.     

A compact split step Padé scheme for higher-order nonlinear Schrödinger equation (HNLS) with power law nonlinearity and fourth order dispersion

In this paper we propose a compact split step Padé scheme (CSSPS) to solve the scalar higher-order nonlinear Schrödinger equation (HNLS) with higher-order linear and nonlinear effects such as the third and fourth order dispersion effects, Kerr dispersion, stimulated Raman scattering and power law nonlinearity. The stability of this method has been proved. It has been shown as well that the CSSPS method gives the same results as classical numerical methods like the split step Fourier method and Crank–Nicholson (CN) method but it presents many advantages over theme. It is more efficient. This proposed scheme is well suited to higher-order dispersion effects and readily generalized for nonlinear and dispersion managed fibers. We tested this scheme for the case of the quintic nonlinearity and confirmed that this effect has no significant role on the propagation of single solitons.     

Reconfigurable computing: design methodology and hardware tasks scheduling for real-time image processing

Technology evolution makes possible the integration of heterogeneous components as programmable elements (processors), hardware dedicated blocks, hierarchical memories and buses. Furthermore, an optimized reconfigurable logic core embedded within a System-on-Chip will associate the performances of dedicated architecture and the flexibility of programmable ones. In order to increase performances, some of the applications are carried out in hardware, using dynamically reconfigurable logic, rather than software, using programmable elements. This approach offers a suitable hardware support to design malleable systems able to adapt themselves to a specific application. This article makes a synthesis of the Ardoise project. The first objective of Ardoise project was to design and to produce a dynamically reconfigurable platform based on commercial FPGAs. The concept of dynamically reconfigurable architecture depends partially on new design methodologies elaboration as well as on the programming environment. The platform architecture was designed to be suitable for real-time image processing. The article outlines mainly the Ardoise tools aspect: development environment and real-time management of the hardware tasks. The proposed methodology is based on a dynamic management of tasks according to an application scenario written using C++ language.

Decentralized sliding-mode output-feedback control of interconnected discrete-delay systems

Global decentralized discrete sliding mode control of a class of interconnected system using only output information is considered in this paper. Matched and unmatched uncertainties as well as known and unknown interconnections are treated. Bounded time-varying delays are considered within the subsystems and through interconnections. The stability of the reduced-order interconnected systems is analyzed using the Lyapunov–Kraszovskii approach and a novel reachability condition of the composite sliding surfaces is established. The resultant dynamics are proved to be globally asymptotically stable. Simulations show the efficacy of the proposed scheme.     

Cost efficiency comparison of four video-based techniques for assessing upper arm postures

Many video-based techniques for assessing postures at work have been developed. Choosing the most appropriate technique should be based on an evaluation of different alternatives in terms of their ability to produce posture information at low input costs, i.e. their cost efficiency. This study compared four video-based techniques for assessing upper arm postures, using cost and error data from an investigation on hairdressers. Labour costs associated with the posture assessments from the video recordings were the dominant factor in the cost efficiency comparison. Thus, a work sampling technique associated with relatively large errors appeared, in general, to be the most cost-efficient because it was labour-saving. Measurement bias and other costs than labour cost for posture assessment influenced the ranking and economic evaluation of techniques, as did the applied measurement strategy, i.e. the numbers of video recordings and repeated assessments of them. PRACTITIONER SUMMARY: The cost efficiency of four video-based techniques for assessing upper arm postures was compared. Work sampling techniques were in general more cost efficient than continuous observations since they were labour-saving. Whilst a labour cost dominated the comparison, 'hidden costs', bias and measurement strategy also influenced this dominance.     

A sustainable approach to the recycling of rice straw through pelletization and controlled burning

A technique for controlled burning of rice straw is presented. It relies on well-designed rice straw pellets to be burned in fluidized bed. The developed pellets have high burning rate, no fly ashes emissions and minimum bed fouling. The pellets are manufactured from ground rice straw in a disc pelletizer with the aid of bonding and suitable additive materials. The pellets are tested under controlled conditions in a test rig, which represents a single pellet fluidized bed. It is equipped with a nitrogen gun to eject the pellet and freeze the reaction at any predetermined time during combustion. The ejected pellets are weighed as well as elementary analyzed for both carbon and hydrogen, to calculate the burning rate as well as the combustion efficiency, respectively. The effect of several parameters has been evaluated including straw particle size, pellet size, type and concentration of bonding material as well as anti-sintering additives. Also, the pellets’ mechanical characteristics have been evaluated. It has been found that char combustion phase represents the controlling phase of the pellet combustion. The burning rate is higher as the void fraction of the pellet is higher. Starch showed better combustion and mechanical characteristics out of the five tested bonding materials. Adding kaolin to the pellets results in improving the sintering characteristics of the pellets. The experimental results were compared with two combustion models: the oxygen diffusion controlled and the kinetic-diffusion models. It has been found that oxygen diffusion controlled model more accurately simulates the combustion of the pellet during its char combustion phase. The model has been used to evaluate the effect of some operational parameters on the pellet combustion characteristics such as bed temperature, gas flow and oxygen concentration.