电子封装常用名称及术语汇集

电子封装常用名称及术语汇集下面，按英文字母顺序，汇集并解释了与目前ＬＳＩ（包括ＩＣ）正在采用的主要封装形式相关联的名称术语等。这些名称术语参考并引用了日本国内１２个半导体制造公司，其他国家７个半导体制造公司＊与ＬＳＩ封装相关的资料、日本电子机械工业会...     

一种改进的矢量量化码字搜索算法

该文利用图像矢量的平均值和方差,结合了最近邻域搜索算法,构造了一种新的快速矢量量化编码算法。将一个输入矢量分为两个子矢量,分别计算原始矢量、两个子矢量的和以及方差值,利用在这些数值基础上建立的一组三角不等式来排除不可能的码字。仿真结果表明新算法在所需时间和计算复杂度方面优于改进的EENNS算法,为矢量量化算法的研究提供了一种新的思路。     

采用空间矢量组合的小波图像分类矢量量化

该文提出了采用空间矢量组合对小波图像进行分类矢量量化的新方法。该方法充分利用了各高频子带系数的频率相关性和空间约束性将子带系数重组，依据组合矢量能量和零树矢量综合判定进行分类，整幅图像只需单一量化码书，分类信息占用比特数少，并采用了基于人眼视觉特性的加权均方误差准则进行矢量量化，提高了量化增益。仿真结果表明，该方法实现简单，在较低的编码率下，可达到很好的压缩效果。     

一种改进的深度神经网络应用于推荐系统

推荐系统是信息过滤的一种重要工具。随着互联网和大数据的介入,推荐系统的技术革新面临着新的挑战。近年来,深度学习的革命性进步在语音识别、图像分析和自然语言处理方面都受到了广泛关注。与此同时,一种应用于许多复杂任务的最先进的机器学习技术被用于推荐系统,以提高推荐的质量。由于其一流的性能表现和高质量的推荐结果,深度学习可以更好地理解用户需求、项目特征及其之间的历史性互动。文章提出将一种改进的深度神经网络应用于推荐系统。实验结果表明,该方法的效果令人瞩目。     

Amplitude based keyless optical encryption system using deep neural network

Double random phase encryption (DRPE) system is a simple and powerful encoding technique that consists of only two lenses and two random phase masks. However, there are many issues for applying to actual security systems such as phase acquisition, vulnerability to phase retrieval techniques, and data throughput. Although various extensions of DRPE have addressed each issue, there is no comprehensive solution. To tackle all the issues of DRPE, we propose a new amplitude-based DRPE (ADRPE) system using deep learning. The encoding is the same as the current ADRPE system, and the decoding is achieved by an inverse ADRPE system using convolution neural networks. Our system can achieve a real-time end-to-end encryption system without any additional optical devices and exposure of the keys. To demonstrate our method, we applied it to simulations with various datasets such as passwords, Quick-Response (QR) codes, and fingerprints.     

Structure-prior deep neural network for lane detection

Lane detection is an important task of road environment perception for autonomous driving. Deep learning methods based on semantic segmentation have been successfully applied to lane detection, but they require considerable computational cost for high complexity. The lane detection is treated as a particular semantic segmentation task due to the prior structural information of lane markings which have long continuous shape. Most traditional CNN are designed for the representation learning of semantic information, while this prior structural information is not fully exploited. In this paper, we propose a recurrent slice convolution module (called RSCM) to exploit the prior structural information of lane markings. The proposed RSCM is a special recurrent network structure with several slice convolution units (called SCU). The RSCM could obtain stronger semantic representation through the propagation of the prior structural information in SCU. Furthermore, we design a distance loss in consideration of the prior structure of lane markings. The lane detection network can be trained more steadily via the overall loss function formed by combining segmentation loss with the distance loss. The experimental results show the effectiveness of our method. We achieve excellent computation efficiency while keeping decent detection quality on lane detection benchmarks and the computational cost of our method is much lower than the state-of-the-art methods.     

EEG-based prediction of driver's cognitive performance by deep convolutional neural network

We considered the prediction of driver's cognitive states related to driving performance using EEG signals. We proposed a novel channel-wise convolutional neural network (CCNN) whose architecture considers the unique characteristics of EEG data. We also discussed CCNN-R, a CCNN variation that uses Restricted Boltzmann Machine to replace the convolutional filter, and derived the detailed algorithm. To test the performance of CCNN and CCNN-R, we assembled a large EEG dataset from 3 studies of driver fatigue that includes samples from 37 subjects. Using this dataset, we investigated the new CCNN and CCNN-R on raw EEG data and also Independent Component Analysis (ICA) decomposition. We tested both within-subject and cross-subject predictions and the results showed CCNN and CCNN-R achieved robust and improved performance over conventional DNN and CNN as well as other non-DL algorithms.     

A new hardware Trojan detection technique using deep convolutional neural network

The involvement of external vendors in semiconductor industries increases the chance of hardware Trojan (HT) insertion in different phases of the integrated circuit (IC) design. Recently, several partial reverse engineering (RE) based HT detection techniques are reported, which attempt to reduce the time and complexity involved in the full RE process by applying machine learning or image processing techniques in IC images. However, these techniques fail to extract the relevant image features, not robust to image variations, complicated, less generalizable, and possess a low detection rate. Therefore, to overcome the above limitations, this paper proposes a new partial RE based HT detection technique that detects Trojans from IC layout images using Deep Convolutional Neural Network (DCNN). The proposed DCNN model consists of stacking several convolutional and pooling layers. It layer-wise extracts and selects the most relevant and robust features automatically from the IC images and eliminates the need to apply the feature extraction algorithm separately. To prevent the over-training of the DCNN model, a new stopping condition method and two new metrics, namely Accuracy difference measure (ADM) and Loss difference measure (LDM), are proposed that halts the training only when the performance of our model genuinely drops. Further, to combat the issue of process variations and fabrication noise generated during the RE process, we include noisy images with varying parameters in the training process of the model. We also apply the data augmentation and regularization techniques in the model to address the issues of underfitting and overfitting. Experimental evaluation shows that the proposed technique provides 99% and 97.4% accuracy on Trust-Hub and synthetic ISCAS dataset, respectively, which is on-an-average 15.83% and 21.69% higher than the existing partial RE based techniques.     

Wavelet image coding using variable blocksize vector quantization with optimal quadtree segmentation

In this paper, we propose an image coding scheme by using the variable blocksize vector quantization (VBVQ) to compress wavelet coefficients of an image. The scheme is capable of finding an optimal quadtree segmentation of wavelet coefficients of an image for VBVQ subject to a given bit budget, such that the total distortion of quantized wavelet coefficients is minimal. From our simulation results, we can see that our proposed coding scheme has higher performance in PSNR than other wavelet/VQ or subband/VQ coding schemes.     

Distributed video coding based on vector quantization: Application to capsule endoscopy

We present in this paper a new distributed video coding (DVC) architecture for wireless capsule endoscopy. It is based on the state of the art DVC systems, but without using key frames. Instead, it uses an adapted vector quantization (VQ) with a searching complexity that is shifted to the decoder. VQ allows creating a good side information (SI) by exploiting the similarities in human anatomy. Thus, SI is created from a codebook (CB) rather than by motion compensated prediction. This approach decreases largely the complexity of the encoder, which codes only Wyner-Ziv frames, and allows a progressive decoding. The encoder of the proposed DVC generates only a simple hash that is used by the decoder to select the corresponding VQ codeword. The obtained experimental results show that rate-distortion results are better than those of JPEG, and show the possibility of using scalable coding to control the used rate and energy.     

METHOD OF VECTOR QUANTIZATION CODING USING RECTANGULAR TRANSFORM FOR IMAGE COMPRESSION

First of all a simple and practical rectangular transform is given,and then thevector quantization technique which is rapidly developing recently is introduced.We combinethe rectangular transform with vector quantization technique for image data compression.Thecombination cuts down the dimensions of vector coding.The size of the codebook can reasonablybe reduced.This method can reduce the computation complexity and pick up the vector codingprocess.Experiments using image processing system show that this method is very effective inthe field of image data compression.     

Fast competitive learning with classified learning rates for vector quantization

In this paper, we present a new competitive learning algorithm with classified learning rates, and apply it to vector quantization of images. The basic idea is to assign a distinct learning rate to each reference vector. Each reference vector is updated independently of all the other reference vectors using its own learning rate. Each learning rate is changed only when its corresponding reference vector wins the competition, and the learning rates of the losing reference vectors are not changed. The experimental results obtained with image vector quantization show that the proposed method learns more rapidly and yields better quality of the coded images than conventional competitive learning method with a scalar learning rate.     

采用深度卷积神经网络方法的毫米波图像目标检测

通过收集大量的毫米波图像并建立相应的人体数据集进行检测,提出基于Faster R-CNN深度学习的方法检测隐藏于人体上的危险物品。该方法将区域建议网络和VGG19训练卷积神经网络模型相结合,构建了面向毫米波图像目标检测的深度卷积神经网络。为了提高毫米波图像的处理能力,采用Caffe深度学习框架在图形处理单元上进行训练和测试。实验结果证明了基于Faster R-CNN深度卷积神经网络的目标检测方法能有效检测毫米波图像中的危险物品,并且目标检测的平均准确率约94%,检测速度约为6 frame/s,对毫米波安检系统的智能化发展有着极其重要的参考价值。     

Improved hybrid layered image compression using deep learning and traditional codecs

Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional image codecs. At the encoder, we first use a convolutional neural network (CNN) to obtain a compact representation of the input image, which is losslessly encoded by the FLIF codec as the base layer of the bit stream. A coarse reconstruction of the input is obtained by another CNN from the reconstructed compact representation. The residual between the input and the coarse reconstruction is then obtained and encoded by the H.265/HEVC-based BPG codec as the enhancement layer of the bit stream. Experimental results using the Kodak and Tecnick datasets show that the proposed scheme outperforms the state-of-the-art deep learning-based layered coding scheme and traditional codecs including BPG in both PSNR and MS-SSIM metrics across a wide range of bit rates, when the images are coded in the RGB444 domain.     

基于矢量量化的层次分形编码方法

文中提出了一种新的分形图像压缩方法,该方法将矢量量化的概念应用于分形块编码中,对图像的平缓区进行矢量量化的线性组合编码,对图像的丰富细节区用分形编码,并且在分形编码时,采取了层次处理。实验表明,与基本的分形块编码方法相比,本文提出的矢量量化层次分形编码方法在保证一定的重建图像质量下,使图像的压缩比有了明显的提高,并且大大提高了编码和解码速度。     

ENHANCED MULTISTAGE VECTOR QUANTIZATION FOR SAR RAW DATA COMPRESSION

Multistage Vector Quantization(MSVQ) can achieve very low encoding and storage complexity in comparison to unstructured vector quantization. However, the conventional MSVQ is suboptimal with respect to the overall performance measure. This paper proposes a new technology to design the decoder codebook, which is different from the encoder codebook to optimise the overall performance. The performance improvement is achieved with no effect on encoding complexity, both storage and time consuming, but a modest increase in storage complexity of decoder.     

Multiple shell structured hypercube feature maps for vector quantization of images

A new neural network architecture is proposed for spatial domain image vector quantization (VQ). The proposed model has a multiple shell structure consisting of binary hypercube feature maps of various dimensions, which are extended forms of Kohonen's self-organizing feature maps (SOFMs). It is trained so that each shell can contain similar-feature vectors. A partial search scheme using the neighborhood relationship of hypercube feature maps can reduce the computational complexity drastically with marginal coding efficiency degradation. This feature is especially proper for vector quantization of a large block or high dimension. The proposed scheme can also provide edge preserving VQ by increasing the number of shells, because shells far from the origin are trained to contain edge block features.     

基于深度神经网络的自适应波束形成算法

阵列天线接收到的期望信号和干扰信号,其入射的到达角度(Angle of Arrival,AOA)总是快速变化的,而传统波束形成算法计算量大,无法实时计算。针对这一问题,提出了一种基于深度神经网络的自适应波束形成(Deep Neural Network Adaptive Beamforming,DNNABF)算法,用入射信号AOA组成的向量作为网络输入,网络输出逼近最小方差无失真响应(Minimum Variance Distortionless Response,MVDR)算法求得的权矢量。仿真结果表明,卷积神经网络(Convolutional Neural Network,CNN)与DNNABF方法都能准确拟合MVDR算法权矢量,可在入射信号AOA快速变化时自适应地形成波束和零陷,但DNN计算速度相对MVDR有将近6.5倍的提升,训练模型时间也远低于CNN。     

基于矢量量化压缩密集连接层的图像压缩研究

针对卷积神经网络(CNN)在图像压缩耗费较大存储空间问题,文中通过研究压缩CNN参数的矢量量化方法解决了CNN模型的存储问题。通过压缩密集连接层的存储方式使得矢量量化方法比现有的矩阵分解方法更具优势。将k-均值聚类(KM)应用于权重和乘积量化可以在模型大小和识别精度之间取得较好的权衡。实验结果表明,结构化量化方法的效果明显优于其他方法,通过对图像压缩检索验证了压缩模型的泛化能力。