This article presents our initial results in deep learning for channel estimation and signal detection in orthogonal frequency-division multiplexing (OFDM) systems. In this article, we exploit deep learning to handle wireless OFDM channels in an end-to-end manner. Different from existing OFDM receivers that first estimate channel state information (CSI) explicitly and then detect/recover the transmitted symbols using the estimated CSI, the proposed deep learning based approach estimates CSI implicitly and recovers the transmitted symbols directly. To address channel distortion, a deep learning model is first trained offline using the data generated from simulation based on channel statistics and then used for recovering the online transmitted data directly. From our simulation results, the deep learning based approach can address channel distortion and detect the transmitted symbols with performance comparable to the minimum meansquare error (MMSE) estimator. Furthermore, the deep learning based approach is more robust than conventional methods when fewer training pilots are used, the cyclic prefix (CP) is omitted, and nonlinear clipping noise exists. In summary, deep learning is a promising tool for channel estimation and signal detection in wireless communications with complicated channel distortion and interference.
This paper introduces a novel rotation-based framework for arbitrary-oriented text detection in natural scene images. We present the Rotation Region Proposal Networks (RRPN), which are designed to generate inclined proposals with text orientation angle information. The angle information is then adapted for bounding box regression to make the proposals more accurately fit into the text region in terms of the orientation. The Rotation Region-of-Interest (RRoI) pooling layer is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. The whole framework is built upon a regionproposal-based architecture, which ensures the computational efficiency of the arbitrary-oriented text detection compared with previous text detection systems. We conduct experiments using the rotation-based framework on three real-world scene text detection datasets and demonstrate its superiority in terms of effectiveness and efficiency over previous approaches.
Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature interactions with the same weight, as not all feature interactions are equally useful and predictive. For example, the interactions with useless features may even introduce noises and adversely degrade the performance. In this work, we improve FM by discriminating the importance of different feature interactions. We propose a novel model named Attentional Factorization Machine (AFM), which learns the importance of each feature interaction from data via a neural attention network. Extensive experiments on two real-world datasets demonstrate the effectiveness of AFM. Empirically, it is shown on regression task AFM betters FM with a 8.6% relative improvement, and consistently outperforms the state-of-the-art deep learning methods Wide&Deep [Cheng et al., 2016] and DeepCross [Shan et al., 2016] with a much simpler structure and fewer model parameters. Our implementation of AFM is publicly available at: https://github. com/hexiangnan/attentional factorization machine
Among all inorganic halide perovskite photovoltaic materials, CsPbIBr2 exhibits the most balanced features in terms of bandgap and stability. However, the poor quality of solution‐processed CsPbIBr2 films impedes further optimization of cells performance. Herein, a facile intermolecular exchange strategy for CsPbIBr2 film is demonstrated, wherein an optimized methanol solution of CsI is spin‐coated on CsPbIBr2 precursor film in conventional one‐step solution route. It surprisingly produces full‐coverage and pure‐phase CsPbIBr2 films featured with average grain size of ≈0.65 µm, few grain boundaries, high crystallinity, preferable (100) orientation, stoichiometric composition along with favorable electronic structures for effective dissociation and transfer of carriers. Hence, the cost‐effective, carbon‐based all‐inorganic planar perovskite solar cells based on them, yield an optimized efficiency of 9.16% with a stabilized value of 8.46% in ambient air conditions that highlight a particularly superb open‐circuit voltage of 1.245 V, all of which represent the highest values reported in pure CsPbIBr2 based cells so far. Moreover, the optimized cell without encapsulation shows excellent long‐term stability because it can retain 90% over 60 days and 97% over 7 days of its initial efficiency, when is stored controllably in ≈45% relative humidity at 25 or 85 °C at zero humidity, respectively.
Deep learning (DL) has shown great potentials to revolutionizing communication systems. This article provides an overview on the recent advancements in DL-based physical layer communications. DL can improve the performance of each individual block in communication systems or optimize the whole transmitter/receiver. Therefore, we categorize the applications of DL in physical layer communications into systems with and without block structures. For the DL-based communication systems with the block structure, we demonstrate the power of DL in signal compression and signal detection. We also discuss the recent endeavors in developing DL-based end-to-end communication systems. Finally, the potential research directions are identified to boost the intelligent physical layer communications.
In this paper, we develop a decentralized resource allocation mechanism for vehicle-to-vehicle (V2V) communications based on deep reinforcement learning, which can be applied to both unicast and broadcast scenarios. According to the decentralized resource allocation mechanism, an autonomous "agent", a V2V link or a vehicle, makes its decisions to find the optimal sub-band and power level for transmission without requiring or having to wait for global information. Since the proposed method is decentralized, it incurs only limited transmission overhead. From the simulation results, each agent can effectively learn to satisfy the stringent latency constraints on V2V links while minimizing the interference to vehicle-to-infrastructure (V2I) communications.
Classifying videos according to content semantics is an important problem with a wide range of applications. In this paper, we propose a hybrid deep learning framework for video classification, which is able to model static spatial information, short-term motion, as well as long-term temporal clues in the videos. Specifically, the spatial and the short-term motion features are extracted separately by two Convolutional Neural Networks (CNN). These two types of CNN-based features are then combined in a regularized feature fusion network for classification, which is able to learn and utilize feature relationships for improved performance. In addition, Long Short Term Memory (LSTM) networks are applied on top of the two features to further model longer-term temporal clues. The main contribution of this work is the hybrid learning framework that can model several important aspects of the video data. We also show that (1) combining the spatial and the short-term motion features in the regularized fusion network is better than direct classification and fusion using the CNN with a softmax layer, and (2) the sequence-based LSTM is highly complementary to the traditional classification strategy without considering the temporal frame orders. Extensive experiments are conducted on two popular and challenging benchmarks, the UCF-101 Human Actions and the Columbia Consumer Videos (CCV). On both benchmarks, our framework achieves to-date the best reported performance: 91.3% on the UCF-101 and 83.5% on the CCV.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.