Search

Besides the use of information transmission, vehicular communications also perform an essential role in intelligent transportation systems (ITS) for exchanging critical driving information among end users, vehicles, and infrastructures. Moreover, to enhance the understanding of the local environment, increasingly more data are collected by sensors, inducing an extensive use of deep learning (DL)-based algorithms in ITS. To further promote the development of DL-based algorithms in ITS, in this paper, we present a concise introduction of DL technologies. Then, we conduct an in-depth investigation on two popular DL-based applications used in ITS, traffic flow forecasting and trajectory prediction, focusing on when and how the authors employ different DL models and training schemes in these tasks. Finally, we raise two existing problems while employing DL-based algorithms in practical ITS and further discuss certain recent advances in DL-based research to tackle these challenges. To encourage more researchers to focus on the development of DL-based algorithms in ITS for a better world, we hope this paper can be treated as an informational material for prospective researchers, which contains the essential background knowledge of DL-based ITS applications; we also hope this paper will encourage experienced researchers to counter the open challenges and achieve a technical breakthrough to ITS. [ABSTRACT FROM AUTHOR]

Millimeter wave (mmWave) communication is an emerging technique to provide large bandwidth in cellular systems. However, mmWave signals experience more pathloss than the microwave signals adopted in current wireless communications. Therefore, a mmWave system tends to adopt a large number of antennas to combat pathloss with high beamforming gain. In conventional multi-antenna systems, both beamforming and precoding are done digitally in baseband. The high cost and power consumption of certain components in mmWave systems render conventional architecture infeasible. In this paper, we consider low complexity hybrid analog/digital precoding and low-resolution analog-digital converters (ADCs) (1-3 bits) in downlink multiuser mmWave MIMO systems. We propose a new transmission scheme involving rationale of beamspace MIMO communications and beam selection. We also develop a low complexity beam selection algorithm and evaluate adaptive selection on the RF configuration for energy efficiency (EE) optimization. Our analysis and simulation results show that the proposed scheme can significantly reduce system complexity and achieve good performance on energy efficiency and detection. [ABSTRACT FROM AUTHOR]

Market trends have been one of the highly debated phenomena in the financial industries and academia. Prior works show the profitability in exploiting transactions via market trend quantification; on the other hand, traders' behaviors and effects on the market trends can be better understood by market trend studies. In general, the trading strategies on the market trend include trend following strategies and contrarian strategies. Following the trend, trading strategies exploit the momentum effects. The momentum strategies profit in a long position with the rising market prices, as well as in a short position with the decreasing market prices. On the contrary, the view of contrarian trading strategy is based on the mean-reversion property, i.e., a long position is taken when the price moves down and a short position is taken when the price moves up. In this paper, we apply the stop-loss and stop-profit mechanisms to verify the market trends based on two new simple strategies, i.e., the BuyOp. strategy and the BuyHi.SellLo. strategy. We back-test these two strategies on the Taiwan Stock Exchange Capitalization Weighted Stock Index Futures (TAIEX Futures) during the period from May 25, 2010 to August 19, 2015. We compare the numerical results of its profits and losses through various stop-loss thresholds and stop-profit thresholds, and verify the existence of the momentum effect via applying these two new trading strategies. Besides, we analyze the market trends through the repeated simulations of random trades with the stop-loss and stop-profit mechanisms. Our numerical results reveal that there exist momentum effects in TAIEX Futures, which verifies the market inefficiency and the market profitability in exploiting the market inefficiency. In addition, the techniques of random trades are also applied to the other commodities, such as AAPL in NASDAQ, IBM, GOOG in NYSE, and, TSMC in TPE, and so on. Surprisingly, not all the stocks have the momentum effects. Our experimental results show that some stocks or markets are more suitable for the mean-reverse strategy. Finally, we propose a technique to quantify the momentum effect of a financial market by using Jensen-Shannon divergence. [ABSTRACT FROM AUTHOR]

The cooperative frequency reuse among base stations (BSs) can improve the system spectral efficiency by reducing the intercell interference through channel assignment and precoding. This paper presents a game-theoretic study of channel assignment for realizing network multiple-input multiple-output (MIMO) operation under time-varying wireless channel. We propose a new joint precoding scheme that carries enhanced interference mitigation and capacity improvement abilities for network MIMO systems. We formulate the channel assignment problem from a game-theoretic perspective with BSs as the players, and show that our game is an exact potential game given the proposed utility function. A distributed, stochastic learning-based algorithm is proposed where each BS progressively moves toward the Nash equilibrium (NE) strategy based on its own action-reward history only. The convergence properties of the proposed learning algorithm toward an NE point are theoretically and numerically verified for different network topologies. The proposed learning algorithm also demonstrates an improved capacity and fairness performance as compared to other schemes through extensive link-level simulations. [ABSTRACT FROM AUTHOR]