Krishnappa R. Subramanian

A complex valued radial basis function network for equalization of fast time varying channels

This paper presents a complex valued radial basis function (RBF) network for equalization of fast time varying channels. A new method for calculating the centers of the RBF network is given. The method allows fixing the number of RBF centers even as the equalizer order is increased so that a good performance is obtained by a high-order RBF equalizer with small number of centers. Simulations are performed on time varying channels using a Rayleigh fading channel model to compare the performance of our RBF with an adaptive maximum-likelihood sequence estimator (MLSE) consisting of a channel estimator and a MLSE implemented by the Viterbi algorithm. The results show that the RBF equalizer produces superior performance with less computational complexity.

Development of a Self-Regulating Evolving Spiking Neural Network for classification problem

This paper presents a new spiking neural network for pattern classification problems, referred to as the Self-Regulating Evolving Spiking Neural (SRESN) classifier, that regulates the learning process of the network. It uses a two layered spiking neural network and the input layer consists of receptive field neurons, which convert a real valued input to spikes using the population coding scheme without any delays. The output layer consists of leaky integrate-and-fire neurons. Since SRESN does not use any delays, the number of network parameters for SRESN is significantly lower than that used by other spiking neural networks, used in this study. During training, the learning algorithm for SRESN, automatically evolves neurons in the output layer based on the training data stream and the current knowledge stored in the network. Depending on the knowledge in the sample and the class specific knowledge stored in the network, it can choose to either add a neuron or update the network parameters or skip learning the sample resulting in self-regulation of the learning process. In case of neuron addition, the weights for the newly added neuron are initialized using a modified rank order scheme which facilitates SRESN for use in online/sequential as well as batch learning modes. The parameter update strategy in SRESN ensures that connections with non-zero postsynaptic potential at the time of the spike are alone updated which helps prevent over training. While evaluating the performance of SRESN, first a study is conducted to assess the impact of various parameters on its performance and establish guidelines to choose suitable values for these parameters. Next, the performance of SRESN, operating in batch mode, is compared with other spiking neural classifiers, including SpikeProp and MuSpiNN, for the UCI benchmark problems of Iris flower classification and Wisconsin breast cancer. Subsequently, the performance of SRESN in online and batch learning mode is compared with an evolving spiking neural classifier for five benchmark data sets from the UCI machine learning repository. Finally, SRESN is applied to solve the practical problem of Epilepsy detection. The performance comparison clearly indicates that SRESN provides a higher generalization accuracy using fewer network parameters.

A Cooperative Game Theory Approach to Resource Allocation in Wireless ATM Networks

In the emerging wireless ATM networks, resource allocation with handoff consideration plays an important role in the quality of service (QoS) guarantee for multiple traffic sources. As efficiency is an important performance issue which is most widely used, the concept of fairness should also be considered. In this paper we investigate a fair and efficient resource allocation scheme for two types of traffics contending for the shared network resource. Based on the cooperative game theory, we model the fair and efficient allocation problem as a typical bargaining and arbitration problem, while the issues of efficiency and fairness are considered simultaneously by using the axiom approach. By modeling the corresponding queuing system as a Markov chain and using the Markov decision process (MDP) analysis, we convert the solution of optimal allocation policies into a typical linear programming problem for which the well-known simplex type algorithms can be easily implemented. Simulation results are also provided.

A subject-specific frequency band selection for efficient BCI- an interval type-2 fuzzy inference system approach

The Common Spatial Pattern (CSP) is an effective algorithm used in EEG based Brain Computer Interface (BCI) to extract discriminative features, however, its effectiveness depends upon the subject-specific frequency bands. Also, the generated features using CSP are non-stationary in nature. In this paper, we propose a Meta-cognitive Interval type-2 Neuro-Fuzzy Inference System to handle non-stationarity in CSP features with recursive band elimination to find subject-specific frequency bands, together known as (McIT2NFIS-RBE). McIT2NFIS uses the non-stationary features generated by CSP as its input and models it as uncertainty using Interval type-2 fuzzy sets in the antecedent of fuzzy rules. The recursive band elimination (RBE) employs the McIT2NFIS training algorithm to recursively eliminate all the features of a band, one at a time. It aims to improve the performance by removing features of a band one at a time, whose elimination will not have any effect on the training performance. The performance of McIT2NFIS-RBE is evaluated using the publicly available dataset-IIa from BCI competition dataset IV [26]. The results highlight the performance of McIT2NFIS-RBE over other algorithms.

Novel methods for the performance analysis of adaptive hybrid selective repeat ARQ

In this paper we present two novel approximation methods for the performance analysis of selective repeat (SR) ARQ protocol with any size of buffer. The methods are called sequential method (SM) and stable function method (SFM). Both SM and SFM methods provide highly accurate results as compared to other conventional methods of analysis. However, between SM and SFM methods, it is observed that SM is computationally more complex. Hence, SFM method is proposed for our analysis. Based on SFM, we present an ad hoc algorithm for an adaptive SR ARQ scheme to optimize the performance of SR ARQ. The performance of hybrid SR ARQ (an SR ARQ protocol combined with FEC) is also analyzed. It is concluded from a comparison of different methods of analyzing the SR ARQ protocol that the stable function method (SFM) provides a simple and novel approach for network analysis.

The admission control for integrated video-conferencing/voice/data services in broadband CDMA networks

Abstract We examine the performance of admission control for the integrated video-conferencing, voice and data services in broadband CDMA networks using analytical methods. The traffic access is based on the Packet Reservation Multiple Access (PRMA) protocol. For the admission control of video-conferencing and voice calls, firstly, we investigate a scheme by introducing a threshold which limits the active subscribers in the network, so that the quality of service (QoS) can be guaranteed. Secondly, we investigate another scheme which uses a Markovian decision process to optimize the performance of voice and video conferencing traffic. The performance of these admission control schemes is evaluated in terms of call blocking probability and idle-slot probability. For data transfer applications, the admission control is investigated under two different schemes: threshold control scheme and graceful degradation control scheme. Their performance is evaluated in terms of throughput, average delay and data packet loss probability.

Weighted fair discard scheme for buffer management in the presence of network congestion

Data discarding is widely used in networks as a mechanism for buffer management. It enables networks to satisfy various QoS requirements. In this paper, we propose a general weighted fair discard algorithm (WFD) for buffer management in the presence of network congestion and buffer overflow. WFD comprises two parts, discard weight and discard mechanism. Whenever there is a situation of buffer overflow, WFD removes some data from the buffer. The amount of data removed from individual connections is controlled by WFD and is proportional to connections discard weights. Since discard weights can be flexibly assigned and dynamically adjusted, WFD can thus optimize the performance of various applications more efficiently, as compared with other discard disciplines, such as drop tail. In addition, certain interesting attributes of WFD are also analyzed in this paper, and results show that we can estimate possible data losses in advance and control them in realtime, as they are extremely useful for multi-streaming or adaptive applications.

Novel neutral network approach to call admission control in high-speed networks.

This paper presents a novel Call Admission Control (CAC) scheme which adopts the neural network approach, namely Minimal Resource Allocation Network (MRAN) and its extended version EMRAN. Though the current focus is on the Call Admission Control (CAC) for Asynchronous Transfer Mode (ATM) networks, the scheme is applicable to most high-speed networks. As there is a need for accurate estimation of the required bandwidth for different services, the proposed scheme can offer a simple design procedure and provide a better control in fulfilling the Quality of Service (QoS) requirements. MRAN and EMRAN are on-line learning algorithms to facilitate efficient admission control in different traffic environments. Simulation results show that the proposed CAC schemes are more efficient than the two conventional CAC approaches, the Peak Bandwidth Allocation scheme and the Cell Loss Ratio (CLR) upperbound formula scheme. The prediction precision and computational time of MRAN and EMRAN algorithms are also investigated. Both MRAN and EMRAN algorithms yield similar performance results, but the EMRAN algorithm has less computational load.

Analysis of a full-memory multidestination ARQ protocol over broadcast links

Based on an assumption that a steady state exists in the full-memory multidestination automatic repeat request (ARQ) scheme, we propose a novel analytical method called steady-state function method (SSFM), to evaluate the performance of the scheme with any size of receiver buffer. For a wide range of system parameters, SSFM has higher accuracy on throughput estimation as compared to the conventional analytical methods.

Research: Throughput analysis of several reliable broadcast schemes for satellite communications

In this paper, a novel analytical method called steady-state function method (SSFM) is presented to investigate several full memory multidestination selective repeat (MSR) automatic repeat request (ARQ) schemes for reliable satellite broadcast communications. First the analytical method SSFM is presented for the throughput analysis of the basic MSR ARQ scheme. Using this method, the system throughput can be predicted with any finite receiver buffer. Simulation results show that for a wide range of system parameters, SSFM provides throughput estimation closer to simulation results. The accuracy of SSFM is higher than that of the conventional analytical methods for the MSR ARQ scheme. SSFM is also used to analyze the throughput of an optimal MSR ARQ scheme. In this paper, the throughput is optimized by choosing the optimal number of copies of a packet transmitted continuously to the receivers. Analytical results show that when the SSFM is used to evaluate the throughput of the optimal MSR ARQ scheme, the improvement on throughput of the MSR ARQ scheme is not apparent as revealed by other methods. Furthermore, SSFM is extended to analyze the performance of a type I hybrid MSR ARQ scheme in which the forward error correction (FEC) scheme is employed. Analytical results show that the hybrid MSR ARQ scheme has stronger capability of improving the throughput of the pure MSR ARQ scheme than the optimal MSR ARQ scheme. The decision of employing the hybrid MSR ARQ scheme depends on the packet error ratio in the communication environment.