A signal suffers from nonlinear, linear, and additive distortion when transmitted through a channel. Linear equalizers are commonly used in receivers to compensate for linear channel distortion. As an alternative, novel equalizer structures utilizing neural computation have been developed for compensating for nonlinear channel distortion. In this paper, we propose a neural detector based on self-organizing map (SOM) in a 16 QAM system. The proposed scheme uses the SOM algorithm and symbol-by-symbol detector to form a neural detector, and it adapts well to the changing channel conditions, including nonlinear distortions because of the topology-preserving property of the SOM algorithm. According to the theoretical analysis and computer simulation results, the proposed scheme is shown to have better performance than traditional linear equalizer when facing with nonlinear distortion.

This paper presents a compensating method based on Self-Organizing Map (SOM) for nonlinear distortion, which is caused by high-power amplifier (HPA) in 16-QAM-OFDM system. OFDM signals are sensitive to nonlinear distortions and different methods are studied to solve them. In the proposed scheme, the correction is done at the receiver by a SOM algorithm. Simulations are carried out considering an additive white Gaussian (AWG) transmission channel. Simulation results show that the SOM algorithm brings perceptible gains in a complete 16-QAM-OFDM system.

This paper proposes a simple control method to improve the ignition behavior of cold cathode fluorescent lamp (CCFL) in digital-dimming control. Due to restriking manipulation in digital-dimming mode, the lamp life of CCFL is reduced substantially. To extend the lamp life, we realize a digital-dimming controller with soft-starting technique (DDC-SST) to reduce the high ignition voltage and to eliminate the ignition current spike. The half-bridge resonant inverter is employed in the presented backlight system. Complete analysis and design considerations are discussed in detail in this paper. Simulation and experimental results are close to the theoretical prediction. The overall efficiency of the system achieved at the rated power is over 91%. The ignition voltage is reduced about 30% without any lamp current spike occurred under digital-dimming operation.

Described here is an automatic text summarization system for Japanese newspaper articles on sassho-jiken (murders and bodily harms). We extract the pieces of information from a text, inter-connect them to represent the scenes and participants involved in the sassho-jiken, and finally produce a summary by generating sentences from the information extracted. An experiment and its evaluation show that, while a limitation being imposed on the domain, our method works well in depicting important information from the newspaper articles and the summaries produced are better in adequacy and readability than those obtained by extracting sentences.

In this paper, an automatic and unsupervised method using context-dependent hidden Markov models (CD-HMMs) is proposed for the prosodic labeling of speech synthesis databases. This method consists of three main steps, i.e., initialization, model training and prosodic labeling. The initial prosodic labels are obtained by unsupervised clustering using the acoustic features designed according to the characteristics of the prosodic descriptor to be labeled. Then, CD-HMMs of the spectral parameters, F0s and phone durations are estimated by a means similar to the HMM-based parametric speech synthesis using the initial prosodic labels. These labels are further updated by Viterbi decoding under the maximum likelihood criterion given the acoustic feature sequences and the trained CD-HMMs. The model training and prosodic labeling procedures are conducted iteratively until convergence. The performance of the proposed method is evaluated on Mandarin speech synthesis databases and two prosodic descriptors are investigated, i.e., the prosodic phrase boundary and the emphasis expression. In our implementation, the prosodic phrase boundary labels are initialized by clustering the durations of the pauses between every two consecutive prosodic words, and the emphasis expression labels are initialized by examining the differences between the original and the synthetic F0 trajectories. Experimental results show that the proposed method is able to label the prosodic phrase boundary positions much more accurately than the text-analysis-based method without requiring any manually labeled training data. The unit selection speech synthesis system constructed using the prosodic phrase boundary labels generated by our proposed method achieves similar performance to that using the manual labels. Furthermore, the unit selection speech synthesis system constructed using the emphasis expression labels generated by our proposed method can convey the emphasis information effectively while maintaining the naturalness of synthetic speech.

A new approach is proposed in this paper for the tracking of the optimal operating frequency in a Class E backlight inverter using the phase-locked loop (PLL) technique. First, a new single-stage backlight module is introduced to simplify the circuit and to raise the system efficiency. A piezoelectric transformer (PT) is used to drive the cold cathode fluorescent lamp (CCFL) to eliminate the downside of a conventional transformer and to reduce the dimension of the backlight module. Next, a PLL is embedded in the backlight system, as a feedback mechanism, to track the optimal operating frequency of the PT so that the PT's temperature effect is removed and, hence, the system efficiency and stability is improved. The feedback variable proposed is a phase angle rather than a lamp current amplitude traditionally used. A simplified model, along with its design procedure, is next presented. The complete analysis and design considerations are detailed. Finally, it is rather encouraging to observe that the experimental results match our analytical solutions closely.

The performance of a twisted-pair channel under ADSL environment is assumed to be dominated by far end crosstalk (FEXT) and additive white Gaussian noise (AWGN). In this paper, we study the channel capacity of the copper twisted pair and the optimum input power spectral density distribution at this channel capacity in the presence of ADSL environment. The channel capacity under different loop length and different input power will also be given. The simulation results show that the distribution of the optimum input power spectral density in the presence of AWGN and FEXT is not uniform. This is different from the situation where AWGN is the only interference, where the input power distribution is approximately uniform.

This paper proposes a backlight module which drives multiple cold-cathode fluorescent lamps (CCFLs) with a current mirror technique to equalize the driving current for each lamp. We first adopt a half-bridge parallel-resonant inverter as the main circuit and use a single-input, multiple-output transformer to drive the multi-CCFLs. Next, we introduce current-mirror circuits to create a new current-sharing circuit, in which its current reference node and the parallel-connected multi-load nodes are used to accurately equalize all CCFLs' driving current. This will balance each lamp's brightness and, consequently, improve the picture display quality of the related liquid crystal display (LCD). This paper details the design concept for each component value with the assistance of an actual design example. The results of the example are examined with its actual measurements, which consequently verify the correctness of the proposed control strategy.

Iterative decoding is a key feature of turbo code and each decoding results in additional power consumption of the decoder and decoding delay. In this letter, we propose an effective stop criterion based on the Gaussian assumption at the decoder output. Simulation results show that the proposed method can dynamically stop the iterative process with a negligible degradation of the error performance.

In a high-rate indoor wireless personal communication system, the delay spread due to multi-path propagation results in intersymbol interference which can significantly increase the transmission bit error rate (BER). The technique most commonly used for combating the intersymbol interference and frequency-selective fading found in communications channels is the adaptive equalization. In this paper, we propose a novel neural detector based on self-organizing map (SOM) to improve the system performance of the receiver. In the proposed scheme, the SOM is used as an adaptive detector of equalizer, which updates the decision levels to follow the received faded signal. To adapt the proposed scheme to the time-varying channel, we use the Euclidean distance, which will be updated automatically according to the received faded signal, as an adaptive radius to define the neighborhood of the winning neuron of the SOM algorithm. Simulations on a 16 QAM system show that the receiver using the proposed neural detector has a significantly better BER performance than the traditional receiver.

Recently, neural networks (NNs) have been extensively applied to many signal processing problem due to their robust abilities to form complex decision regions. In particular, neural networks add flexibility to the design of equalizers for digital communication systems. Recurrent neural network (RNN) is a kind of neural network with one or more feedback loops, whereas self-organizing map (SOM) is characterized by the formation of a topographic map of the input patterns in which the spatial locations (i.e., coordinates) of the neurons in the lattice are indicative of intrinsic statistical features contained in the input patterns. In this paper, we propose a novel receiver structure by combining adaptive RNN equalizer with a SOM detector under serious ISI and nonlinear distortion in QAM system. According to the theoretical analysis and computer simulation results, the performance of the proposed scheme is shown to be quite effective in channel equalization under nonlinear distortion.

Detection of nonlinearly distorted signals is an essential problem in telecommunications. Recently, neural network combined conventional equalizer has been used to improve the performance especially in compensating for nonlinear distortions. In this paper, the self-organizing map (SOM) combined with the conventional symbol-by-symbol detector is used as an adaptive detector after the output of the decision feedback equalizer (DFE), which updates the decision levels to follow up the nonlinear distortions. In the proposed scheme, we use the box distance to define the neighborhood of the winning neuron of the SOM algorithm. The error performance has been investigated in both 16 QAM and 64 QAM systems with nonlinear distortions. Simulation results have shown that the system performance is remarkably improved by using SOM detector compared with the conventional DFE scheme.

Linear adaptive digital filters are applied to various fields for their simplicity in the design and implementation. Considering many kinds of nonlinearities inherent in practical systems, however, nonlinear adaptive filtering will be more desirable. This paper presents a design method for multi-input single-output nonlinear adaptive digital filters using recurrent neural networks. Furthermore, in comparison with this method and the method based on the conventional linear theory, if the proposed method is used, better results can be obtained, and, it is possible that the learning efficiency is improved, because the parallel learning is carried out in this method. Finally, the results of computer simulation are presented to illustrate the effectiveness of the proposed method.