WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Remaining useful life prediction for degrading systems with random shocks considering measurement uncertainty

Degradation data have been widely used for the remaining useful life (RUL) prediction of systems. Most existing works apply a preset model to capture the degradation process and focus on the degradation process without shocks or constant shock effects. More generally, the actual degradation path is unobservable due to the existence of measurement uncertainty, which interferes with the determination of the degradation model. Besides, the effect of random shocks is usually fluctuating. Given these problems, a general degradation model with the random shock fluctuant effects considering the measurement uncertainty is first developed to describe the degradation process, and a two-step approach combining the arithmetic average filter and the Bayesian information criterion is adopted to identify the degradation path. Subsequently, the transfer processes of the actual degradation state and the abrupt change caused by shocks are depicted using a two-dimensional state-space model, and an expectation-maximization algorithm combined with the particle filtering is developed for parameter estimation. Furthermore, the explicit solution of RUL distribution is obtained when only considering harmful shocks, while a simulation method of RUL distribution is provided when both harmful and beneficial shocks exist. Finally, the effectiveness of the proposed method is verified by a numerical example and two practical case studies.     

Model-Based Design Space Exploration for FPGA-based Image Processing Applications Employing Parameterizable Approximations

The increasing demand for low power consumption and high computational performance is outpacing available technological improvements in embedded systems. Approximate computing is a novel design paradigm trying to bridge this gap by leveraging the inherent error resilience of certain applications and trading in quality to achieve reductions in resource usage. Numerous approximation methods have emerged in this research field. While these methods are commonly demonstrated in isolation, their combination can increase the achieved benefits in complex systems. However, the propagation of errors throughout the system necessitates a global optimization of parameters, leading to an exponentially growing design space. Additionally, the parameterization of approximated components must consider potential cross-dependencies between them. This work proposes a systematic approach to integrate and optimally configure parameterizable approximate components in FPGA-based applications, focusing on low-level but high-bandwidth image processing pipelines. The design space is explored by a multi-objective genetic algorithm which takes parameter dependencies between different components into account. During the exploration, appropriate models are used to estimate the quality-resource trade-off for probed solutions without the need for time-consuming synthesis. We demonstrate and evaluate the effectiveness of our approach on two image processing applications that employ multiple approximations. The experimental results show that the proposed methods are able to produce a wide range of Pareto-optimal solutions, offering various choices regarding the desired quality-resource trade-off.     

A High-Throughput Screening System Based on Fluorescence-Activated Cell Sorting for the Directed Evolution of Chitinase A

Chitinases catalyze the degradation of chitin, a polymer of N-acetylglucosamine found in crustacean shells, insect cuticles, and fungal cell walls. There is great interest in the development of improved chitinases to address the environmental burden of chitin waste from the food processing industry as well as the potential medical, agricultural, and industrial uses of partially deacetylated chitin (chitosan) and its products (chito-oligosaccharides). The depolymerization of chitin can be achieved using chemical and physical treatments, but an enzymatic process would be more environmentally friendly and more sustainable. However, chitinases are slow-acting enzymes, limiting their biotechnological exploitation, although this can be overcome by molecular evolution approaches to enhance the features required for specific applications. The two main goals of this study were the development of a high-throughput screening system for chitinase activity (which could be extrapolated to other hydrolytic enzymes), and the deployment of this new method to select improved chitinase variants. We therefore cloned and expressed the Bacillus licheniformis DSM8785 chitinase A (chiA) gene in Escherichia coli BL21 (DE3) cells and generated a mutant library by error-prone PCR. We then developed a screening method based on fluorescence-activated cell sorting (FACS) using the model substrate 4-methylumbelliferyl β-d-N,N′,N″-triacetyl chitotrioside to identify improved enzymes. We prevented cross-talk between emulsion compartments caused by the hydrophobicity of 4-methylumbelliferone, the fluorescent product of the enzymatic reaction, by incorporating cyclodextrins into the aqueous phases. We also addressed the toxicity of long-term chiA expression in E. coli by limiting the reaction time. We identified 12 mutants containing 2–8 mutations per gene resulting in up to twofold higher activity than wild-type ChiA.     

基于GA-BP的汽车风振噪声声品质预测模型

目前对于汽车风振噪声的优化研究主要以声压级（Sound pressure level，SPL）作为单一评价指标，既不能全面反映噪声的物理属性，也无法考虑人耳对噪声的主观认知过程。为准确评价风振噪声，引入声品质，运用大涡模拟（Large eddy simulation，LES）对风振噪声进行数值仿真，根据实车道路试验判断仿真的准确性；对仿真结果进行声品质客观评价与主观评价，综合声品质客观评价参数与声品质主观评价试验结果建立BP神经网络预测模型；利用遗传算法（Genetic algorithm，GA），进一步对BP神经网络的结构参数进行优化，建立GA-BP声品质预测模型。研究结果表明，GA-BP声品质预测模型在训练速度和预测精度上都优于BP神经网络预测模型。预测模型基于声品质主客观评价结果，其预测值可以代替传统的声压级评价指标，为风振噪声提供更为准确合理的评价。     

基于Prophet人工智能算法的网络潮汐效应预测研究

本文使用Prophet人工智能算法研究与预测移动通信网络“潮汐效应”现象，探索网络“潮汐效应”在优化网络资源配置实现网络降本增效的作用。Prophet人工智能算法是一种简单、有效，且易于实现的人工智能算法。通过facebook的人工智能开源框架fbprophet，研究4G网络PRB利用率等网络资源指标的“潮汐效应”，并预测这些网络资源指标在未来的变化趋势，用来指导当前4G网络减容、扩容和4/5G节电节能等，实现优化网络资源配置达到降本增效的目的。     

Sub-band coding of hexagonal images

According to the circle-packing theorem, the packing efficiency of a hexagonal lattice is higher than an equivalent square tessellation. Consequently, in several contexts, hexagonally sampled images compared to their Cartesian counterparts are better at preserving information content. In this paper, novel mapping techniques alongside the wavelet compression scheme are presented for hexagonal images. Specifically, we introduce two tree-based coding schemes, referred to as SBHex (spirally-mapped branch-coding for hexagonal images) and BBHex (breadth-first block-coding for hexagonal images). Both of these coding schemes respect the geometry of the hexagonal lattice and yield better compression results. Our empirical results show that the proposed algorithms for hexagonal images produce better reconstruction quality at low bits per pixel representations compared to the tree-based coding counterparts for the Cartesian grid.     

基于VMD和改进TCN的短期光伏发电功率预测

光伏发电功率存在波动性,且光伏出力易受各种气象特征影响,传统TCN网络容易过度强化空间特性而弱化个体特性。针对上述问题,文中提出一种基于VMD和改进TCN的短期光伏发电功率预测模型。通过VMD将原始光伏发电功率时间序列分解为若干不同频率的模态分量,将各个模态分量以及相对应的气象数据输入至改进TCN网络进行建模学习。利用中心频率法确定VMD的最优分解模态分解个数。在传统TCN预测模型的基础上,使用DropBlock正则化取代Dropout正则化以达到抑制卷积层中信息协同的效果,并引入注意力机制自主挖掘并突出关键气象输入特征的影响,量化各气象因素对光伏发电的影响,从而提高预测精度。以江苏省某光伏电站真实数据为例进行仿真实验,结果表明所提预测方法的RMSE为0.62 MW,MAPE为2.03%。