莫尔斯报务信号的检测和识别

目前莫尔斯报务信号的接收译码主要采用人工值守方式,长期工作在这种环境下会给收报员的心理和生理带来很大的影响,研究能够部分取代人的信号自动检测与识别方法十分必要。基于短时傅立叶变换的特性,在时频域上对莫尔斯信号进行特征捕捉,并对捕捉到的莫尔斯信号采用模糊c均值聚类算法(FCM)实现种类识别,以区分莫尔斯信号的点、划和间隔。实验表明,该算法具有较好的识别效果,在莫尔斯报务的自动识别上具有一定的实用价值。     

Grain size effects on cyclic fatigue and crack-growth resistance behaviour of partially stabilized zirconia

Cyclic fatigue crack growth and crack-resistance behaviour was studied in partially stabilized zirconia (PSZ) with three different cubic-phase grain sizes following sub-eutectoid heat treatments. Raman spectroscopy was used to determine the extent of phase transformation around the cracks for both cyclic and monotonic loading conditions. All tests were on long, through thickness cracks using compact-tension specimens. Predictions of crack-tip shielding were made following determination of toughening parameters using crackresistance data. It was found that the dominant factors affecting cyclic fatigue-crack growth were the level of crack-tip shielding, as a result of phase transformation, and the intrinsic toughness of the material. Grain size did not appear to significantly affect fatigue crack-growth behaviour.     

基于SURF-HOG与显著性特征的红外可见光图像配准融合北大核心CSCD

针对现有红外与可见光图像配准不精确,边缘及细节纹理缺失,融合时间较长,不能突出重点目标等不足,提出一种基于SURF-HOG描述符与红外显著性特征的红外与可见光图像融合方法。首先,在红外与可见光图像配准阶段,在SURF(Speed-Up Robust Features,SURF)框架内构建基于HOG(Histogram of Oriented Gradient,HOG)的特征点描述符,并通过NNDR(Nearest Neighbor Distance Ratio,NNDR)进行红外与可见光图像的特征点匹配;其次,在显著特征提取阶段,先通过四叉树算法对源红外图像分解,然后通过贝塞尔插值法重建红外图像背景,接着分别对红外图像中的背景及目标进行自适应抑制以提取目标红外显著性特征;最后,结合已配准的可见光图像与重建后的红外图像以获取最终融合结果。实验结果表明,所提方法对不同场景下的红外与可见光图像具有较高的配准精度,不同场景下的融合结果不但主观视觉上具有显著的目标特征,同时背景纹理和边缘细节清晰,整体对比度适宜,运行时间最短,并且在客观评价指标上也取得了较好的效果。     

中国电力中长期市场分时段交易价格形成机制及模型

电力中长期市场分时段交易是中国电力市场改革的重要举措之一。针对当前电力中长期市场分时段交易价格形成机制不合理、不完善的问题,提出了中国电力中长期市场分时段交易价格形成机制及其模型。首先,分析影响中国电力中长期分时段交易价格形成的因素,提出电力中长期交易的4种典型场景;然后,综合考虑生产成本和用户效用,探索性地提出适用于中长期分时段交易的系统平均成本定价、用户失负荷价值定价、系统边际成本定价和发电企业失负荷价值定价4种成本定价机制,构建了基于成本定价的分时段交易定价模型;最后,以某省实际数据为例进行测算,验证了模型的有效性。     

Comprehensively Strengthened Metal-Oxygen Bonds for Reversible Anionic Redox Reaction

Introducing anionic redox in layered oxides is an effective approach to breaking the capacity limit of conventional cationic redox. However, the anionic redox reaction generally suffers from excessive oxidation of lattice oxygen to O₂ and O₂ release, resulting in local structural deterioration and rapid capacity/voltage decay. Here, a Na_0.71Li_0.22Al_0.05Mn_0.73O₂ (NLAM) cathode material is developed by introducing Al³⁺ into the transition metal (TM) sites. Thanks to the strong Al–O bonding strength and small Al³⁺ radius, the TMO₂ skeleton and the holistic TM–O bonds in NLAM are comprehensively strengthened, which inhibits the excessive lattice oxygen oxidation. The obtained NLAM exhibits a high reversible capacity of 194.4 mAh g^-1 at 20 mA g^-1 and decent cyclability with 98.6% capacity retention over 200 cycles at 200 mA g⁻¹. In situ characterizations reveal that the NLAM experiences phase transitions with an intermediate OP4 phase during the charge–discharge. Theoretical calculations further confirm that the Al substitution strategy is beneficial for improving the overlap between Mn 3d and O 2p orbitals. This finding sheds light on the design of layered oxide cathodes with highly reversible anionic redox for sodium storage.     

Unveiling the Synergy of Interfacial Contact and Defects in α-Fe2O3 for Enhanced Photo-Electrochemical Water Splitting

Photo-electrochemical (PEC) water splitting is a promising method for converting solar energy into clean energy, but the mechanism of improving PEC efficiency through the interfacial contact and defect strategy remains highly controversial. Herein, reduced graphene oxide (rGO) and oxygen vacancies are introduced into α-Fe₂O₃ nanorod (NR) arrays using a simple spin-coating method and acid treatment. The resultant oxygen vacancy–α-Fe₂O₃/rGO-integrated system exhibits a higher photocurrent, four times than the pristine α-Fe₂O₃. It is well evidenced that the electronic interface interaction between α-Fe₂O₃ and rGO is boosted with the oxygen vacancies, facilitating electron transfer from α-Fe₂O₃ to rGO. Moreover, the oxygen vacancies not only create interband states in α-Fe₂O₃ that can trap photogenerated holes and thus facilitate charge separation but significantly also strengthen the adsorption of oxidative intermediates and reduce the energy barrier of rate-determining step during oxygen evolution reaction (OER). This study demonstrates an rGO–oxygen vacancy synergistic interfacial contact and defect modification approach to design semiconducting photocatalysts for high-efficiency solar energy capture and conversion. The generated principle is expected to be extendable to another material system.     

多姿态图像生成的行人重识别算法研究

不同行人的高度相似性以及相同行人外观姿态的差异性,使得不同摄像头下的行人重识别面临严峻的挑战。生成对抗网络可以合成新的图像,被认为是解决行人姿态变化的主要技术手段。提出一种基于多姿态图像生成的行人重识别算法,利用生成对抗网络生成不同姿态的行人图像,通过归一化消除姿态的影响,从而大幅度提升行人重识别的整体性能。该行人重识别算法包括多姿态行人图像生成、不同姿态的行人特征提取与融合、距离度量和重排序三部分内容。在Market-1501数据集和DukeMTMC-ReID数据集上的实验证实了所提出算法的有效性,通过与state-of-the-art行人重识别方法比较,展示了多姿态图像生成方法在行人重识别任务中的优越性,同时表明生成行人图像的特征与原始图像的特征是相互补充的。     

低视点下遮挡自适应感知的多目标跟踪算法

目的 针对低视点多目标跟踪场景的遮挡问题,提出一种能够遮挡自适应感知的多目标跟踪算法。方法 首先根据每帧图像的全局遮挡状态,提出了“自适应抗遮挡特征”,增强目标特征对遮挡的感知和调整能力。同时,采用“级联筛查机制”,减少由遮挡带来的目标特征剧烈变化而认定为“虚新入目标”的错误跟踪现象。最后,考虑到历史模板库中存在遮挡的模板对跟踪性能的影响,根据每一帧中目标的局部遮挡状态,提出自适应干扰模板更新机制,进一步提高对遮挡的应变和适应能力。结果 实验结果表明,本文算法在MOTA(multiple object tracking accuracy)、M OTP (multiple object tracking precision)、FN(false negatives)、Rcll (recall)、ML (mostly lost tracklets)等指标上明显优于STAM(spatial-temporal attention mechanism)、ATAF(aggregate tracklet appearance features)、STRN (spatial-temporal relat...     

Stock-Price Forecasting Based on XGBoost and LSTM

Using time-series data analysis for stock-price forecasting (SPF) is complex and challenging because many factors can influence stock prices (e.g., inflation, seasonality, economic policy, societal behaviors). Such factors can be analyzed over time for SPF. Machine learning and deep learning have been shown to obtain better forecasts of stock prices than traditional approaches. This study, therefore, proposed a method to enhance the performance of an SPF system based on advanced machine learning and deep learning approaches. First, we applied extreme gradient boosting as a feature-selection technique to extract important features from high-dimensional time-series data and remove redundant features. Then, we fed selected features into a deep long short-term memory (LSTM) network to forecast stock prices. The deep LSTM network was used to reflect the temporal nature of the input time series and fully exploit future contextual information. The complex structure enables this network to capture more stochasticity within the stock price. The method does not change when applied to stock data or Forex data. Experimental results based on a Forex dataset covering 2008–2018 showed that our approach outperformed the baseline autoregressive integrated moving average approach with regard to mean absolute error, mean squared error, and root-mean-square error.     

Intelligent wavelet fuzzy brain emotional controller using dual function-link network for uncertain nonlinear control systems

This study aims to propose a more efficient hybrid algorithm to achieve favorable control performance for uncertain nonlinear systems. The proposed algorithm comprises a dual function-link network-based multilayer wavelet fuzzy brain emotional controller and a sign(.) functional compensator. The proposed algorithm estimates the judgment and emotion of a brain that includes two fuzzy inference systems for the amygdala network and the prefrontal cortex network via using a dual-function-link network and three sub-structures. Three sub-structures are a dual-function-link network, an amygdala network, and a prefrontal cortex network. Particularly, the dual-function-link network is used to adjust the amygdala and orbitofrontal weights separately so that the proposed algorithm can efficiently reduce the tracking error, follow the reference signal well, and achieve good performance. A Lyapunov stability function is used to determine the adaptive laws, which are used to efficiently tune the system parameters online. Simulation and experimental studies for an antilock braking system and a magnetic levitation system are presented to verify the effectiveness and advantage of the proposed algorithm.