Recursive Research Articles

A Statistical Analysis of the NLMS and NLMS Algorithms for Correlated Gaussian Signals DOI: 10.14209/jcis.2005.8

The Nonnalized LMS adaptive algorithm is widely used in real life adaptive filtering and control applications mainly due to its simplicity and robustness to input signal power variations. This last characteristic is a consequence of its intrinsic nonnalization procedure. However, in practical applications it is usual the addition of a small positive constant to the nonnalization factor in order to avoid divisions by zero or overflow. In this case, the adaptive algorithm is named e-NLMS. This work presents a statistical analysis of the e-NLMS for Gaussian input signals. Deterministic recursive equations are obtained for the mean weight behavior and mean square error for a large number of adaptive coefficients. In addition, a closed expression is provided for the steady state misadjustment. Monte Carlo simulations show an excellent agreement between theoretical predictions and the algorithm's behavior in steady state. During transient, the new model is conservative and more accurate than the existing models. The developed equations can be lIsed with e =0 to predict the behavior of the NLMS algorithm. Simulations illustrate the better quality of the new NLMS model when compared to others already available in the literature.

Performance analysis and parameter setting for Tong detection algorithm

Tong detection algorithm is a common used signal detection algorithm. But the overall conclusions about statistical performance and parameter setting of Tong detection algorithm are absent. Aiming at these problems,statistical and recursive analysis methods were used to carry on theoretical analysis about mean value and variance of dwell times in signal search unit in detail,the corresponding expressions were given,a maximum dwell times constraint method was offered according to the 3Sigma principle. The relationships between detection probability,average dwell times of noise search unit and signal search unit,initial value and maximum value of algorithm counter,pre-detection signal to noise ratio were analyzed. Analysis results indicate that the parameters of Tong detection algorithm should be set according to signal strength and search modes,and the influence of parameter setting on detection probability and average dwell times of noise search unit or signal search unit should be balanced.

Prognostic analysis of 102 elderly cancer patients with brain metastases

Objective To explore the related factors for the prognosis in elderly cancer patients with cerebral metastases, to study the adaptability of brain metastasis in recursive partitioning analysis(RPA)and the prognosis Assessment (GPA) Scale, in order to provide the basis for the prognosis assessment and treatment in the elderly patients with brain metastasis. Methods A retrospective analysis was studied in 102 elderly cancer patients with brain metastasis (aged 60 years and over) with complete follow-up data in our hospital from January 2005 to January 2012. Survival analysis was performed by using the Kaplan-Meier method. Univariate analysis of ethnicity, age, Karnofsky score, gender, smoking, primary tumor origin, the number of intracranial metastatic tumor, intracranial and extracranial metastasis, the efficacy of treatment for primary tumor, the treatment of brain metastases were analyzed by Log-rank test. Results The median survival time was 6 months. The 6-month and 12- month survival rates were 54.90% and 16.67% respectively. Univariate analysis showed that Karnofsky score, smoking, the number of intracranial metastatic tumor, time to diagnosis and treatment, the efficacy of treatment for primary tumor and other underlying diseases were the relative factors for prognosis of elderly cancer patients with brain metastases (χ2= 20.828, 5.737, 7.395, 5.379, 11.556, 6.844, all P<0.05). Cox multivariate regression analysis showed that the Karnofsky score, the number of intracranial metastatic tumor, the efficacy of treatment for primary tumor and other underlying diseases were the independent prognostic factors (all P<0.05). The median survival periods in RPA class Ⅰ, Ⅱ, Ⅲ were 11, 7, 4 month respectively (χ2=27.358, P<0.001). The median survival periods in GPA classⅠ, Ⅱ, Ⅲ-Ⅳ were 5, 8, 13 months respectively (χ2=29.570, P<0.001). Conclusions Karnofsky score, the number of intracranial metastatic tumor, the efficacy of treatment for primary tumor and other underlying diseases are the independent factors for the prognosis in elderly cancer patients with cerebral metastases. RPA and GPA classification have a good adaptability in elderly patients with brain metastases. Key words: Neoplasm metastasis; Brain Prognosis

Performance Analysis of the Recursive LeastSquares Algorithm

Adaptive filter algorithm is a widely used method in communication systems, control systems, digital signal processing etc. This method helps to find out the unknown parameters iteratively by adjusting the filter parameters. There are many efficient adaptive filter algorithms. But among them, the basic algorithms are: Least Mean Square (LMS) and Recursive Least Square (RLS) Algorithms. The LMS algorithm is based on gradient optimization and the RLS algorithm is based on direct form FIR and lattice realization. The RLS algorithm is popular because of its fast convergence although the LMS algorithm is very simple to implement. There are modified LMS algorithms and they are: Leaky Least Mean Square (LLMS) Algorithm and Normalized Least Mean Square (NLMS) Algorithm. „Step size‟ is an important parameter which is used to implement any of these LMS algorithms. In case of RLS algorithm, one term „forgetting factor‟ plays an important role in times of implementing any system.

Kernel Regression Based Online Boosting Tracking

Although online boosting algorithm has received an increasing amount of interest in visual tracking, it is susceptible to class-label noise. Slight inaccuracies in the tracker can result in incorrectly labeled examples, which degrade the classifier and cause drift. This paper proposes a kernel regression based online boosting method for robust visual tracking. A nonlinear recursive least square algorithm which performs linear regression in a high-dimensional feature space induced by a Mercer kernel is employed to derive weak classifiers. Online sparsification to filter samples in feature space is adopted to reduce the computational cost of the recursive least square algorithm. In our method, weak classifiers themselves can be modified adaptively to cope with scene changes. Experimental results compared with several relevant tracking methods demonstrate the good performance of the proposed algorithm under challenging conditions.

Analysis and implementation of FURLS algorithm for active vibration control system with positive feedback

While positive feedback exists in an active vibration control system,it may cause instability of the whole system.To solve this problem,a feedforward adaptive controller is proposed based on the Filtered-U recursive least square(FURLS) algorithm.Algorithm development process is presented in this paper.Real time active vibration control experimental tests were done.The experiment results show that the active control algorithm proposed in this paper has good control performance for both narrow band disturbances and broad band disturbances.

Periodic Safety Message Broadcasting in VANETs Using Recursive Algorithm

Faster and more reliable connection establishment is the primary purpose of periodic safety broadcasting in VANETs. For this purpose we propose a sublayer in the application layer to increase the reliability of safety applications. Our proposed method uses several rebroadcasting schemes safety messages, which considerably improves the overall reliability. It also handles the synchronized collision problem as well as congestion problem and vehicle-to-vehicle channel loss. We propose a zone based algorithm to increase reliability of safety messages. We also use a Recursive Algorithm to give priority for the safety message being generated. We use wi-fi protocol instead of dsrc protocol in order to improve the reliability. Based on this model, a upper bound for the network coding algorithm is derived. Using the results based on analysis and ns-2 simulations we conclude that our method overcomes the previous problems.

Routine and capability dynamics: duality and recursion competitiveness organizational

Routine and capability dynamics: duality and recursion competitiveness organizational

The acquisition of coordination and recursion of PPS: how to fare the development of these computations?

A recursividade, um cálculo implementado através da inserção de um constituinte dentro de outro, é amplamente reconhecido como uma capacidade cognitiva fundamental. Uma discussão interessante sobre o tema gira em torno da especificidade do domínio dessa cognição, ou seja, se ela está nas bases da capacidade de linguagem ou se é parte integral de recursos cognitivos gerais e é posta em ação na linguagem como um fator externo. Naturalmente, é primordial para essa discussão saber quando a recursividade é adquirida. Este estudo quer contribuir para esta discussão ampla, concentrando-se na aquisição de uma instância recursiva - a dos sintagmas preposicionais (PPs) em Português do Brasil. Os resultados apontam para a faixa etária de 4 anos como sendo a idade em que a recursividade começa a ser processada de forma significativa.

RECURSIVELY ENUMERABLE SETS AND WELL-ORDERING OF THEIR ENUMERATIONS

A b s t r a c t. We will introduce the special kind of the order relations into recursively enumerable sets and prove that they can be used to distinguish (albeit in a non-constructive way) between recursive and non-recursive sets.

Investigating the leverage effect in commodity markets with a recursive estimation approach

This paper investigates the presence of the leverage effect in commodities, in comparison with financial markets. The EGARCH model with a Mixture of Normals distribution (EGARCH-MN) is used to capture (i) heavy tails and skewness in the conditional returns, and (ii) leverage effects and time-varying long-term component in the volatility specification. Besides, the estimation strategy relies on an innovative recursive (REC) method, which allows disentangling the leverage effect from the unconditional skewness as an empirical result. When applied to a broadly diversified dataset of assets during 1995–2012, the EGARCH-MN models offers state-of-the-art specifications with leverage and fat-tailed skewed densities, that allow to contrast the specific characteristics of commodities with traditional assets (equities, bonds, FX).

Denoising of 3D magnetic resonance images by using higher-order singular value decomposition.

The denoising of magnetic resonance (MR) images is important to improve the inspection quality and reliability of quantitative image analysis. Nonlocal filters by exploiting similarity and/or sparseness among patches or cubes achieve excellent performance in denoising MR images. Recently, higher-order singular value decomposition (HOSVD) has been demonstrated to be a simple and effective method for exploiting redundancy in the 3D stack of similar patches during denoising 2D natural image. This work aims to investigate the application and improvement of HOSVD to denoising MR volume data. The wiener-augmented HOSVD method achieves comparable performance to that of BM4D. For further improvement, we propose to augment the standard HOSVD stage by a second recursive stage, which is a repeated HOSVD filtering of the weighted summation of the residual and denoised image in the first stage. The appropriate weights have been investigated by experiments with different image types and noise levels. Experimental results over synthetic and real 3D MR data demonstrate that the proposed method outperforms current state-of-the-art denoising methods.

The new product development process: a sphenomorphic management model

This paper introduces a new model of the management of the new product development process (NPDP), especially as it applies to the complex environment of engineering–based NPDPs. A review of previous attempts at modelling the process concludes that such models are becoming inadequate in view of the increasing complexity and changing conditions now influencing the process. By looking in detail at the NPDP, the problems relating to the management of the process are addressed. Current ideas on managing complexity and chaotic systems are used to develop a recursive model, which, from its wedge–like shape, is termed a 'sphenomorph'. A hierarchical collection of sphenomorphs combine to form the complete engineering programme. Further, each sphenomorph comprises four distinct stages, each requiring a different management style for success. The need for adaptive managers, capable of dealing with all four stages of the development process, is considered and methods are reviewed whereby such management characteristics may be identified and encouraged through appropriate training and development.

THE MODELLING AND OPTIMIZATION OF AN ELECTRICAL VEHICLE USING JOINT ANALYSIS

Finite element analysis is an excellent method for structural analysis. For finite element analysis, accurate modelling is very important to obtain precise information. Stick modelling is a convenient way in that it is easy and simple. When the stick model is utilised, the joints are modified in the tuning process. A tuning method for the joints has been developed. Joints are modelled by designated beam elements. and the beam properties are tuned to have target values which are evaluated from experiments. An optimisation method called 'Goal Programming' is employed to impose the target values. With the tuned joints, the entire optimisation has been carried out. Using a recursive quadratic programming algorithm, the optimisation process determines the configuration of the entire structure and sizes of all the sections. For example, the structure of an electrical vehicle is modelled and analysed by the method. The stick model works very well since the structure is made of aluminium frames. Although the example is for an electrical vehicle, this method can be applied to general vehicle structures.

Intelligent Dynamic Acquisition Learning Fuzzy Modeling Systems Design

Technologies of fuzzy knowledge-based discovery can be exploited to extract appropriate behaviors for identified modeling problems. A proposed novel data acquisition learning algorithm (DALA) is dynamically applied to examine the initial recognitions of the training data set, where it can automatically establish the number of cluster centers and their associated positions. The characteristics of the training data set are dynamically mined by the DALA, and the primary architecture of the fuzzy system is initially represented with the collected information. Because the prototypes of the collected training data are determined with DALA, the initial populations of the particle swarm optimization (PSO) are generated and distributed around them. The hybrid PSO and recursive least-squares (RLS) learning schemes referred to as RPSO are applied to design an appropriate fuzzy modeling system. The approximation of the proposed fuzzy modeling system shows that it automatically determines suitable fuzzy membership functions and resolves the local optimal problem of identifying appropriate parameters for fuzzy systems to swiftly approach desired functions. A comparison between computer simulations and other modeling methods shows the excellent performance of the dynamic acquisition learning fuzzy modeling system in explaining nonlinear and inverted pendulum function approximations. Simulation results show that the generated fuzzy system with the DALA scheme can be adapted to balance the pole position for various initial conditions. The proposed control rules swiftly recover the sudden and large imported noise.

Designing a Wireless Sensor Network for Ocean Status Notification System

Reliable and energy efficient routing protocols are considered as critical issues of discussion in Wireless Sensor Networks (WSN). In this paper, we proposed a novel scheme based on Wireless Sensor Networks for Ocean Status Notification System (WOSNS) so that the environmental conditions of the oceans can be monitored. According to the proposed approach, all the sensed data in each area will be transmitted to the related cluster head; then, they will be forwarded to the nearest sink. We used two sinks in appropriate positions. We used the proposed Smart Inner Routing Algorithm (SIRA) for routing data from the cluster heads to the related sink. Furthermore, we proposed a Binary Recursive Convergent (BRC) algorithm for aggregating data in each area. Multi-hop delivery was used to conduct the routing operations. We also introduced a Bidirectional Duplicate Elimination Technique (BDET to eliminate the duplicate data of the sinks. Simulation results indicated that the proposed method is better than the other protocols in terms of average delivery ratio, network lifetime and network traffic.

Multimodel Modeling of Doubly Fed Induction Motor

As the electric drives are highly complex and nonlinear systems subject of several disturbances, it is a great problem to represent them via a unique model with sufficient precision and simple structure. Thus, this paper presents a new doubly fed induction motor (DFIM) model based on multimodel approach as a robust modeling method able to replace the complex system by a set of simpler local models. This approach consists of four steps which are clusters estimation, structure identification, parametric identification and local models combination. The collected data on DFIM are, firstly, clustered into several groups through a Chui’s clustering algorithm. Then, the structure identification is performed on each group using the instrumental ratio (RDI) method. Parameters of each sub model are identified using recursive least square (RLS) method. Finally, obtained sub models are combined using the validity concept. A detailed dynamic model of a DFIM with grid-connected stator and PWM inverter connected rotor, side is presented in the dq-synchronous reference frame in order to generate the input/output data. Simulation results are presented and analyzed up under Matlab/Simulink environment

Neuro identification for flexible cantilever beam structure

In this study, system identification of a flexible beam which undergoes a small deflection due to the disturbance force was conducted. Recursive Least Square (RLS) and several intelligent Neuro identifications were established to acquire the dynamic model of the beam based on One Step-Ahead (OSA) prediction. Comparative assessment between conventional and intelligent methods was investigated in this study with the aim to find the best model that can represents the flexible beam. Neural Network (NN) can be classified according to their structures and learning algorithms. For the purpose of this study, Focused Time-Delay Neural Network (FTDNN), Distributed Time-Delay Neural Network (DTDNN), Nonlinear Autoregressive with Exogeneous Variables (NARX), Elman NN and Radial Basis Function (RBF) were compared their effectiveness in emulating the dynamic behaviour of the system. The performance of the network was observed based on its capability to represents the system with the lowest Mean- Squared-Error (MSE) between the actual and predicted output responses of the models.

I-Delaporte Process and Applications

In this paper we introduce a mixed Polya-Aeppli process with shifted gamma mixing distribution and call it an Inated-parameter Delaporte process (I-Delaporte). We derive the pro bability mass function, recursion formulas and some basic properties. Then we de ne the process as a pure birth process and derive differential equations for the probabilities. As application, we consider a risk model in which the claim counting process is the de ned I-Delaporte process. For the defined risk model we derive the joint distribution of the time to ruin and the de cit at ruin as well as the ruin probability. We discuss in detail the particular case of exponentially distributed claims.

Global Stabilization of a Class of Inherently Nonlinear Systems under Sampled-data Control

For a class of inherently nonlinear systems with uncertain parameters, the global stabilization problem via sampled-data control is investigated in this paper. First of all,based on the technique of adding a power integrator and a recursive argument, a class of sampled-data state feedback controllers are proposed. Then under the proposed controller, by using a suitable Lyapunov functional, it is shown that there is a maximum allowable sampling period which can guarantee the global asymptotical stability of the closed-loop system. Since the proposed controller is discrete-time, it can be easily implemented by computers. Finally, an example is given to verify the efficiency of the proposed method.