Summary Rare class imbalance problems, which involve the classification of minority or rare class, are difficult, because the size of the rare class is smaller than the majority class. Since majority class prediction is easy, its accuracy seems to be also high. However, the minority classes cannot be accurately predicted, and for this reason, when the prediction model performance is evaluated by considering only the accuracy, it does not indicate whether the model can predict the minority classes. Therefore, a rare class prediction technique is required. In this study, a rare class prediction model is proposed for minority class prediction. In addition, a dataset of a semiconductor manufacturing process with class imbalance problems was used to create a fault detection model. This prediction model uses data preprocessing to build the characteristics and data set required by the rare classes. To distinguish the rare classes related to the required characteristics, we used standard deviation and Euclidean distance to perform the feature selection. In addition, a particle swarm optimization–deep belief network was applied to create a classifier. The model proposed in this research presents outstanding performance and is appropriate for highly class imbalance problems.

In this paper, the effect of the time difference of arrival (TDoA) on synchronous types or asynchronous types of OFDMA-based multi-hop relay (MR) systems is investigated. Effective SINRs for downlinks and uplinks are defined to measure the degree of interference due to TDoA in asymmetric MR systems. A path selection technique based on the effective SINR is then proposed to determine the optimal paths for the uplink and downlink independently. It is shown that asymmetric routing can improve the performance of OFDMA-based MR systems when the proposed technique is applied to the path selection of the uplink taking into account the effect of the TDoA.

In this paper, two receive diversity combining techniques are proposed for cooperative relay systems based on single-carrier frequency division multiple access (SC-FDMA) when DFT spreading sizes for a mobile station (MS) and relay station (RS) are different. A simplifled-MRC (S-MRC) technique performs diversity combining in the time-domain by using the estimated channel weights and initial estimates obtained by SC-FDMA signal detector. An interference rejection-MRC (IRMRC) technique performs diversity combining in the frequencydomain by adjusting DFT spreading size at the receiver. It is shown by computer simulation that the proposed receive combining techniques achieve a significant diversity gain over the conventional ones.

In this paper, a new handover procedure for OFDM-based multi-hop relay systems is proposed to reduce handover overhead by distinguishing an inter-cell handover event from an intra-cell handover event at the level of the physical layer using a preamble with a hierarchical design. A subcell ID concept that identifies RS in a cell is proposed in the hierarchical design that works in conjunction with the existing cell ID that identifies BS. The proposed handover procedure can simplify the scanning procedure and skip/simplify the network re-entry procedure, resulting in a significant reduction of handover overhead.

In spatially multiplexed MIMO systems that enable high-data-rate transmission over wireless communication channels, spatial demultiplexing at the receiver is a challenging task. Thus, various demultiplexing methods have been developed by many researchers. In this paper, a novel signal detection method that achieves near-ML performance in a computationally efficient manner is proposed. The proposed method is based on the well-known minimum mean squared error (MMSE) ordered successive interference cancellation (OSIC) method. However, unlike the conventional MMSE-OSIC, a number of candidates are selected at each layer, hence, it has been termed MMSE-OSIC with candidates (MMSE-OSIC2). In this study, it is demonstrated via a series of computer simulations that the MMSE-OSIC2achieves near-ML performance while requiring a complexity comparable to that of the conventional MMSE- OSIC. Also shown here is that the log likelihood ratio (LLR) values are successfully generated via the proposed method.

Due to high computational complexity of the optimal subcarrier allocation (SA) algorithm, various suboptimal algorithms with reduced complexity have been developed. However, since those algorithms are based on one dimensional (row or column) comparison of the channel gain, significant performance degradation is inevitable. The proposed algorithm is based on the two dimensional comparison of the channel gain to achieve higher system capacity. Simulation results demonstrate the efficacy of the proposed method.

In this paper, a decision-directed expectation maximization (DEM) algorithm is proposed to improve the performance of channel estimation in OFDM-based cellular systems. The DEM algorithm enables a mobile station (MS) with multiple antennas, located at the cell boundary, to increase the performance of channel estimation using transmit data, without decreasing spectral efficiency. Compared with the expectation maximization (EM) algorithm, the DEM algorithm can greatly reduce computational complexity while improving the performance of channel estimation in fast fading channels.

In this paper, we propose a novel signal detection method that achieves the maximum likelihood (ML) performance but requires much less computational complexity than the ML detection. When the well-known linear decoding method is used for space-time block coded (STBC) OFDM systems in fast-fading channels, co-channel interference (CCI) as well as inter-carrier interference (ICI) occurs. A maximum likelihood (ML) method can be employed to deal with the CCI; however, its computational complexity is very high. In this paper, we propose a signal detection method for orthogonal space-time coded OFDM systems that achieves the identical error performance as the ML method, but requires much less computational complexity.

In this paper, we address the QRM-MLD signal detection method for spatially multiplexed MIMO systems. Recently, the QRM-MLD signal detection method that can achieve a 1 Gbps transmission speed for the next generation mobile communications has been successfully implemented by the industry when the mobile is moving at a pedestrian speed. In this paper, we propose a novel signal detection method, the "low complexity QRM-MLD", which achieves an identical error performance to that of the conventional QRM-MLD while significantly reducing the computational complexity. We have rigorously compared these two detection methods in terms of computational complexity to confirm the reduction of the computational complexity in the proposed method. We have also performed computer simulations to demonstrate that the two detection methods have identical error performances.

This paper proposes to use candidate symbol table for the decoding of the first few substreams for spatially multiplexed system. In the new decoding algorithm, we generate candidate symbol table (CST) and do ordered successive interference cancellation (OSIC) for each candidates. At the end, Maximum Likelihood (ML) criteria is used to determine the optimum transmit symbol vector among the estimated candidates. Simulation result shows that the size of CST can be maintained to be small, even if the number of bits per symbol increases. Simulation results show that this algorithm gives us performance close to ML decoder, and outperforms maximum likelihood decision feedback equalizer (ML-DFE) and channel-based adaptive group detection based OSIC (AGD-OSIC).

In this paper, we propose a recursive space time decoding method for orthogonal frequency division multiplexing (OFDM) systems exploiting multiple transmit antenna diversity when the channels are fast fading. We first develop a computationally efficient space-time decoding method involving a matrix inversion to mitigate the channel variation effect. We then further reduce the computational complexity of the matrix inversion decoding method via a recursive formulation. Computer simulation results show that the proposed recursive decoding has much better BER performance than Alamouti decoding, requiring much less computation than the matrix inversion decoding. Moreover, the relative advantage in BER performance of the proposed scheme over Alamouti decoding stands out as the Doppler frequency increases

In this paper, we propose a multicarrier CDMA approach for forward link PDCH (forward packet data channel) of cdma2000 1xEV-DV which inherits the same architecture and bandwidth. The system utilizes the bandwidth efficient iterative technique (J. Kim et al., 2002) to recover cyclicity of OFDM symbol, and hence it has no cyclic prefix in frame structure for backward compatibility to the existing 1xEV-DV system. We report that the link-level performance of our system is significantly better than previous equalizer-based systems (J.S. Lee and L.E. Miller, 1998) (J.A.C. Bingham, 1990) in frequency selective fading channels

In orthogonal frequency division multiple access (OFDMA) systems, the cyclic prefix (CP) length needs to be no less than the longest channel delay spread of many users, reducing bandwidth efficiency more significantly than in single user OFDM systems. We propose a novel receiver for OFDMA systems with an insufficient CP, exploiting the unused subchannels for a user. With the aid of computer simulations, we demonstrate that the proposed equalization method is superior to the conventional equalization method using a time domain channel shortening filter in terms of the achievable SNR and the error performance

In conventional discrete multitone (DMT) systems, a multitap time-domain equalizer (TEQ) is used to shorten the channel length, so that the bandwidth efficiency reduction due to cyclic extension is relieved. The TEQ, however, tends to introduce spectral nulls which degrade the achievable signal-to-noise ratio at corresponding subchannels, thereby decreasing the bandwidth efficiency. Furthermore, computationally expensive joint TEQ initialization and optimal delay (introduced by TEQ) selection is necessary. In this paper, a novel subsymbol-equalization scheme is proposed, and is based on the observation that the high-bit-rate twisted-pair channels rarely contain a zero that is close to the unit circle. Although a delay of a fraction of a DMT symbol period is introduced, the proposed subsymbol-equalization scheme eliminates the necessity of both the channel shortening at the receiver and the cyclic extension at the transmitter. Simulation results demonstrate the computational efficiency (no TEQ) and the bandwidth efficiency of the proposed subsymbol-equalization scheme.

In this paper, receiver designs for orthogonal frequency-division multiplexing (OFDM) systems that exploit the Alamouti transmit diversity technique are addressed. In Alamouti space-time coded OFDM systems, the simple Alamouti decoding at the receiver relies on the assumption that the channels do not change over an Alamouti codeword period (two consecutive OFDM symbol periods). Unfortunately, when the channel is fast fading, the assumption is not met, resulting in severe performance degradation. In this paper, a sequential decision feedback sequence estimation (SDFSE) scheme with an adaptive threshold (AT), a traditionally single-carrier equalization technique, is used to mitigate the performance degradation. A new method to set the threshold value is proposed. For small signal constellations like BPSK and QPSK, the SDFSE with an AT requires much lower complexity than a previous minimum mean square error approach at the cost of a small performance degradation. Furthermore, we show that the performance difference becomes smaller when channel estimation error is included. An adaptive effort sequence estimation (AESE) scheme is also proposed to furthur reduce the average complexity of the SDFSE scheme with an AT. The AESE scheme is based on the observation that a high Doppler frequency does not necessarily mean significant instantaneous channel variation. Simulations show the efficacy of the proposed SDFSE with an AT and the AESE.

In this paper, a new bandwidth efficient OFDM transmission scheme is proposed. A bandwidth efficient iterative scheme for OFDM systems without using cyclic prefix was proposed before [3] which works well when a channel does not have a deep spectral null. But such a frequency domain deep null is common in a wireless channel. A bandwidth efficient scheme proposed in this paper works well regardless of the existence of spectral null. In the proposed scheme, OFDM symbols are recovered in two steps. In the first step, only a small portion of the time domain OFDM symbol is recovered by the frequency domain 1-tap equalizer. In the second step, the recovered small portion and the tail part of the previous symbol are used for the cyclic reconstruction and tail cancellation. Simulation experiments are conducted to validate the proposed scheme.