In this letter, we propose a joint pilot design and channel estimation scheme based on the deep learning (DL) technique for multiuser multiple-input multiple output (MIMO) channels. To this end, we construct a pilot designer using two-layer neural networks (TNNs) and a channel estimator using deep neural networks (DNNs), which are jointly trained to minimize the mean square error (MSE) of channel estimation. To effectively reduce the interference among the multiple users, we also use the successive interference cancellation (SIC) technique in the channel estimation process. The numerical results demonstrate that the proposed scheme considerably outperforms the linear minimum mean square error (LMMSE) based channel estimation scheme.
We consider very general code-division-multiple-access (CDMA) systems, namely multiple-chip-rate CDMA systems, where signals can be transmitted at different chip rates, carrier frequencies, processing gains, and transmitted powers to satisfy the given quality of service (QoS) requirements. Also, non-zero and possibly different carrier frequency offsets are assumed for different users. For these systems, a closed-form bit error rate (BER) expression is derived based on the simplified improved Gaussian approximation. Unlike the conventional simplified improved Gaussian approximation, however, we utilize the correlations between chip waveforms and their integrations rather than using the correlations between chip sequences in order to obtain the closed-form BER expression. Numerical results demonstrate that the proposed method provides much more accurate BER values compared to the standard Gaussian approximation
This work studies the cooperative inference of deep neural networks (DNNs), in which a memory-constrained end device performs a delay-constrained inference process with an aid of an edge server. Although several works considered the cooperative inference of DNNs in the literature, it was assumed in those works that the memory footprints at end devices are unlimited, which is in practice not realistic. To address this issue, in this work, a memory-aware cooperative DNN inference is proposed. Specifically, we propose to adopt knowledge distillation to obtain high-performing lightweight DNNs. To minimize the inference delay, we first analyze the end-to-end delay required for processing the proposed cooperative DNN inference, and then we minimize the delay by jointly optimizing the DNN partitioning point and the intermediate data transmission rate. Also, a dynamic DNN selection scheme is developed by fully exploiting the available memory resource in order to maximize the performance of the inference task in terms of inference accuracy. Experimental results demonstrate that the proposed cooperative DNN inference considerably outperforms the comparable schemes while satisfying both the delay constraint and the memory constraint.
Unlike the existing detectors, which are developed for decode-and-forward (DF) networks in the ideal interference-free case, we consider a more practical scenario where arbitrary interference exists. We consider a DF cooperative network consisting of a source, multiple relays, a destination, and multiple interferers affecting both the relays and the destination. Each relay is equipped with multiple antennas and knows its local instantaneous channel state information (CSI). Assuming that the destination knows the instantaneous CSI of the source-relay, relay-destination, and source-destination channels, we develop, for the first time in the literature, the end-to-end optimum maximum-likelihood (ML) detectors in closed-form for DF systems employing either simultaneous or orthogonal transmissions in the presence of interference. Furthermore, theoretical analysis shows that the proposed detectors achieve full diversity gains in the presence of interference with finite interference-to-noise ratios. Numerical results demonstrate that the proposed optimum detectors substantially outperform the conventional schemes which simply ignore interference.
In this paper, we propose a joint pilot design and channel estimation scheme based on the deep learning (DL) technique for multiuser multiple-input multiple output (MIMO) channels. To this end, we construct a pilot designer using two-layer neural networks (TNNs) and a channel estimator using deep neural networks (DNNs), which are jointly trained to minimize the mean square error (MSE) of channel estimation. To effectively reduce the interference among the multiple users, we also use the successive interference cancellation (SIC) technique in the channel estimation process. The numerical results demonstrate that the proposed scheme considerably outperforms the state-of-the-art linear minimum mean square error (LMMSE) based channel estimation scheme.
We analyze the error performance of the physical-layer network coding (PNC) protocol without channel coding in bidirectional relay networks for binary phase shift keying (BPSK) over Rayleigh fading channels. It is assumed that a bidirectional relay network consists of two sources and a relay, where each node has a single antenna and operates in a half-duplex mode, and the PNC over finite GF(2) is employed. In this system, since the maximum-likelihood (ML) detection metric of the multiple access channel (MAC) at the relay is given by the sum of two exponential functions, it is not possible to utilize the classical Euclidean distance rule. To make the performance analysis tractable, we approximate the ML detection metric by adopting the max-log approximation. Then we derive tight upper and lower bounds in closed form for the average symbol error probability of the MAC at the relay. Finally, we obtain tight upper and lower bounds in closed form for the end-to-end average bit-error rate (BER).
As the number of Internet of things (IoT) devices increases exponentially, scheduling and managing the radio resources for IoT devices has become more important. To efficiently allocate radio resources, the base station (BS) needs the channel state information (CSI) of devices every time. Hence, each device needs to periodically (or aperiodically) report its channel quality indicator (CQI) to the BS. The BS determines the modulation and coding scheme (MCS) based on the CQI reported by the IoT device. However, the more a device reports its CQI, the more the feedback overhead increases. In this paper, we propose a long short-term memory (LSTM)-based CQI feedback scheme, where the IoT device aperiodically reports its CQI relying on an LSTM-based channel prediction. Additionally, because the memory capacity of IoT devices is generally small, the complexity of the machine learning model must be reduced. Hence, we propose a lightweight LSTM model to reduce the complexity. The simulation results show that the proposed lightweight LSTM-based CSI scheme dramatically reduces the feedback overhead compared with that of the existing periodic feedback scheme. Moreover, the proposed lightweight LSTM model significantly reduces the complexity without sacrificing performance.
In this paper, we propose a novel data partitioning scheme to im- prove data warehouse query performance in column-oriented data stores. The proposed partitioning method leverages column access patterns of a given workload in order to find the best multi-column partitions. Our proposed ap- proach is able to compute a set of multi-column partitions that yield the best performance for the given entire query workload, when storage is constrained.
In this paper, we study rate-energy (R-E) tradeoffs for simultaneous wireless information and power transfer (SWIPT). In the existing literature, by invoking a simplistic and ideal assumption of linear energy harvesting, the R-E tradeoff performance was analyzed only for the four SWIPT schemes: the dynamic power splitting, type-I on-off power splitting (OPS), static power splitting, and time switching. Different from such works, in this work, we consider the realistic and practical scenario of nonlinear energy harvesting. Furthermore, to characterize the R-E tradeoff with nonlinear energy harvesting, we propose a new SWIPT scheme, the generalized OPS (GOPS). As a special case of the proposed GOPS, we also investigate an additional SWIPT scheme, the type-II OPS. Through the analysis based on the realistic nonlinear models reported in the literature, we derive new theoretical results on the R-E tradeoff, which are in sharp contrast to those in the existing literature obtained with linear energy harvesting. Furthermore, we provide various useful insights into the SWIPT system with nonlinear energy harvesting.
'%3e%3cg id='b'%3e%3cpath id='a' stroke='%23000' stroke-width='2' d='M-6-25H6m-12 3H6m-12 3H6'/%3e%3cuse xlink:href='%23a' y='44'/%3e%3c/g%3e%3cpath stroke='%23fff' d='M0 17v10'/%3e%3ccircle r='12' fill='%23cd2e3a'/%3e%3cpath fill='%230047a0' d='M0-12A6 6 0 0 0 0 0a6 6 0 0 1 0 12 12 12 0 0 1 0-24z'/%3e%3c/g%3e%3cg transform='rotate(-123.69)'%3e%3cuse xlink:href='%23b'/%3e%3cpath stroke='%23fff' d='M0-23.5v3M0 17v3.5m0 3v3'/%3e%3c/g%3e%3c/svg%3e)
