目的 在线公式识别是一种将在线输入手写轨迹点序列转换为公式文本的任务，其广泛应用在手机、平板等便携式设备上。众所周知，训练数据对于神经网络十分重要，但获取有标注的在线公式数据所需要的成本十分昂贵，在训练数据不足的情况下，深度神经网络在该任务上的泛化性和鲁棒性会受到影响。为此，提出了一个基于编码—解码模型的在线数据生成模型。方法 该模型从给定的公式文本生成对应的在线轨迹点序列，从而灵活地扩充训练数据规模。生成模型在编码器端设计了结合树形表示的文本特征提取模块，并且引入了基于位置的注意力算法，使模型实现了输入文本序列与输出轨迹序列间的对齐。同时，解码器端融入了不同手写人风格特征，使模型可以生成多种手写人风格的样本。结果 实验中，首先，将本文生成方法在不同类型输入文本和不同手写人风格上的结果可视化，并展示了模型在多数情况下的有效性。其次，生成模型合成的额外数据可作为训练集的增广，该数据被用...

We propose a novel decision-feedback maximum-likelihood decoder for fading channels. These channels have memory due to the fading correlation, and the complexity of maximum-likelihood decoding for such channels grows exponentially with memory length. Therefore, in practice, the encoded bit stream is typically interleaved prior to transmission and the deinterleaved bit stream is decoded as for a...

In this paper, the receivers with adaptive equalizer and turbo decoder are investigated for orthogonal frequency division multiplexing-code division multiple access (OFDM-CDMA) systems in multipath channels. The de-spreading equalizer which combines de-spreading and equalization is used to mitigate the MAI and ISI. The stochastic gradient based LMS algorithm is used as the adaptive algorithm fo...

(Abstract) A new coding scheme called "turbo coding" has generated tremendous interest in channel coding of digital communication systems due to its high error correcting capability. Two key innovations in turbo coding are parallel concatenated encoding and iterative decoding. A soft-in soft-out component decoder can be implemented using the maximum a posteriori (MAP) or the maximum likelihood ...

Physical unclonable functions (PUFs) can be used to generate cryptographic keys by making use of the intrinsic randomness resulting from manufacturing variations. Error correction codes (ECCs) help to make SRAM-PUFs, which are always effected by noise and environmental changes, suitable for security applications. In this paper, we propose practical error correction schemes for PUF-based secret ...

Aspects of the duality between the information-embedding problem and the Wyner–Ziv problem of source coding with side information at the decoder are developed and used to establish a spectrum new results on these and related problems, with implications for a number of important applications. The singleletter characterization of the information-embedding problem is developed and related to the c...

Reducing the product development cycle time is one of the most important and challenging problems faced by the industry today. As the functionality and complexity of devices increases, so does the time required to design, test, and develop the devices. Developing products rapidly in the face of this increasing complexity requires new methodologies and tools. This paper presents a methodology fo...