A NIR-II AIEgen-Based Supramolecular Nanodot for Peroxynitrite-Potentiated Mild-Temperature Photothermal Therapy of Hepatocellular Carcinoma

Compared to conventional photothermal therapy (PTT) which requires hyperthermia higher than 50 °C, mild-temperature PTT is a more promising antitumor strategy with much lower phototoxicity to neighboring normal tissues. However, the therapeutic efficacy of mild-temperature PTT is always restricted by the thermoresistance of cancer cells. To address this issue, a supramolecular drug nanocarrier is fabricated to co-deliver nitric oxide (NO) and photothermal agent DCTBT with NIR-II aggregation-induced emission (AIE) characteristic for mild-temperature PTT. NO can be effectively released from the nanocarriers in intracellular reductive environment and DCTBT is capable of simultaneously producing reactive oxygen species (ROS) and hyperthermia upon 808 nm laser irradiation. The generated ROS can further react with NO to produce peroxynitrite (ONOOˉ) bearing strong oxidization and nitration capability. ONOOˉ can inhibit the expression of heat shock proteins (HSP) to reduce the thermoresistance of cancer cells, which is necessary to achieve excellent therapeutic efficacy of DCTBT-based PTT at mild temperature (<50 °C). The antitumor performance of ONOOˉ-potentiated mild-temperature PTT is validated on subcutaneous and orthotopic hepatocellular carcinoma (HCC) models. This research puts forward an innovative strategy to overcome thermoresistance for mild-temperature PTT, which provides new inspirations to explore ONOOˉ-sensitized tumor therapy strategies.     

A Low-Hysteresis and Highly Stretchable Ionogel Enabled by Well Dispersed Slidable Cross-Linker for Rapid Human-Machine Interaction

Ionic conductive soft materials for mimicking human skin are a promising topic since they can be thought of as a possible basis for biomimetic sensing. In pursuit of devices with a long working range and low signal delay, conductive materials with low hysteresis and good stretchability are highly demanded. To overcome the challenges of highly stretchable conductive materials with good resilience, herein a chemical design is proposed where polyrotaxanes act as topological cross-linkers to enhance the stretchability by sliding-induced reduced stress concentration while the compatible ionic liquid is introduced as a dispersant for low hysteresis. The obtained ionogels exhibit versatile properties more than low hysteresis (residual strain = 7%) and good stretchability (550%), and also anti-fatigue, biocompatibility, and good adhesion. The low hysteresis is attributed to lower energy dissipation from the well-dispersed polyrotaxanes by compatible ionic liquids. The mechanism provides a new insight in fabricating highly stretchable and low-hysteresis slide-ring materials. Furthermore, the conductivity of the ionogels and their responses to strains and temperatures are measured. Benefiting from the good conductivity and low hysteresis, the ionogel is applied to develop a wireless communication system to realize rapid human-machine interactions.     

Spidermen Strategy for Stable 24% Efficiency Perovskite Solar Cells

The interface energetics-modification plays an important role in improving the power conversion efficiency (PCE) among the perovskite solar cells (PSCs). Considering the low carrier mobility caused by defects in PSCs, a double-layer modification engineering strategy is adopted to introduce the “spiderman” NOBF₄ (nitrosonium tetrafluoroborate) between tin dioxide (SnO₂ and perovskite layers. NO⁺, as the interfacial bonding layer, can passivate the oxygen vacancy in SnO₂, while BF₄⁻ can optimize the defects in the bulk of perovskite. This conclusion is confirmed by theoretical calculation and transmission electron microscopy (TEM). The synergistic effect of NO⁺ and BF₄⁻ distinctly heightens the carrier extraction efficiency, and the PCE of PSCs is 24.04% with a fill factor (FF) of 82.98% and long-term stability. This study underlines the effectiveness of multifunctional additives in improving interface contact and enhancing PCE of PSCs.     

Network Intrusion Detection in Internet of Blended Environment Using Ensemble of Heterogeneous Autoencoders (E-HAE)

Contemporary attackers, mainly motivated by financial gain, consistently devise sophisticated penetration techniques to access important information or data. The growing use of Internet of Things (IoT) technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation, as it facilitates multiple new attack vectors to emerge effortlessly. As such, existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection systems. To address this problem, we designed a blended threat detection approach, considering the possible impact and dimensionality of new attack surfaces due to the aforementioned convergence. We collectively refer to the convergence of different technology sectors as the internet of blended environment. The proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational autoencoder. An extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02% detection accuracy. Furthermore, performance of the proposed approach was compared with various single model (autoencoder)-based network intrusion detection approaches: autoencoder, variational autoencoder, convolutional variational autoencoder, and long short-term memory variational autoencoder. The proposed model outperformed all compared models, demonstrating F1-score improvements of 4.99%, 2.25%, 1.92%, and 3.69%, respectively.     

Study on Recognition Method of Similar Weather Scenes in Terminal Area

Weather is a key factor affecting the control of air traffic. Accurate recognition and classification of similar weather scenes in the terminal area is helpful for rapid decision-making in air traffic flow management. Current researches mostly use traditional machine learning methods to extract features of weather scenes, and clustering algorithms to divide similar scenes. Inspired by the excellent performance of deep learning in image recognition, this paper proposes a terminal area similar weather scene classification method based on improved deep convolution embedded clustering (IDCEC), which uses the combination of the encoding layer and the decoding layer to reduce the dimensionality of the weather image, retaining useful information to the greatest extent, and then uses the combination of the pre-trained encoding layer and the clustering layer to train the clustering model of the similar scenes in the terminal area. Finally, terminal area of Guangzhou Airport is selected as the research object, the method proposed in this article is used to classify historical weather data in similar scenes, and the performance is compared with other state-of-the-art methods. The experimental results show that the proposed IDCEC method can identify similar scenes more accurately based on the spatial distribution characteristics and severity of weather; at the same time, compared with the actual flight volume in the Guangzhou terminal area, IDCEC's recognition results of similar weather scenes are consistent with the recognition of experts in the field.     

CentroidNet：轻量快速的乳腺癌Ki67细胞核中心点检测模型

目的 Ki67分数是乳腺癌预后评估的重要指标,计算该分数的关键步骤是检测阴性与阳性癌细胞核。人工检测面临疲劳与主观差异的问题。卷积神经网络有望实现高质量、自动化的细胞核检测,然而需要病理专家为其标注细胞核。为了减轻标注的工作量,不少研究者提出以中心点标注训练卷积神经网络。然而这些方法采用过于复杂的卷积神经网络和后处理流程,未能充分提高易用性和效率、发挥卷积神经网络的质量。对此,提出CentroidNet模型,旨在提高中心点检测的质量、效率和易用性。方法 CentroidNet模型在图像上放置均匀排布的锚点,为每个锚点预测一个候选点,一部分候选点通过基于阈值的筛选策略成为预测点。本文提出最近锚点匹配策略用于生成训练标签,既保证了端到端推理,又规避了其他一对一标签匹配算法所具有的标签抖动问题。本文建议锚点间距应尽可能接近训练集答案点间最短距离的第一百分位数,并指出这样的锚点间距能够在前景标签数、坐标回归难度与效率之间取得良好的平衡。本文在设计卷积神经网络的结构时,没有采纳广为使用的U-Net或特征金字塔（feature pyramid network, FPN）中的多级上采样与旁路连接,反...     

Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

基于LabVIEW Vision的车牌识别系统设计

文中设计了一种基于LabVIEW Vision的车牌识别系统。该系统根据车牌颜色在HSL色彩空间上的特征,采用色彩阈值分割、腐蚀等图像处理方法将车辆图像转化成二值图,并在二值图中进行边缘检测,再根据检测到的车牌与背景间的边缘线的信息组建方程组,求出车牌边缘特征点的坐标,以确定车牌在图像中的位置。然后,以车牌在图像中的位置是否在指定区域内作为是否进行车牌识别以及当前车辆图像是否保存为车牌识别输入图像的触发条件。如果条件不满足,则系统将重新采集车辆图像,否则会根据车牌位置抓捕车牌,并采用均匀性度量法等方法对抓捕到的车牌进行二次处理,并将其转化成车牌二值图,再由OCR函数对该图进行字符识别。经实验验证,该系统具有较高的识别精确度与稳定性。     

电力电子设备及含电力电子设备电力系统实时仿真研究综述

大量电力电子设备接入电力系统给电磁暂态实时仿真技术带来了巨大的挑战。文中从多个角度对电力电子设备和含电力电子设备电力系统实时仿真领域近年来的研究成果进行了综述。在应用场景和利用范式方面,除了硬件在环测试等对仿真实时性具有严格要求的场景,实时仿真还被用于其他单纯对仿真效率有较高要求的场景。在建模与仿真方法方面,无论是基于分立元件的建模仿真,还是基于端口特性或电路等值的电力电子设备建模仿真,都有商业化应用的案例,但如何兼顾高频、复杂设备实时仿真的效率和精度仍是当前研究的热点与难点。在实时仿真硬件平台方面,现场可编程门阵列（FPGA）和图像处理单元（GPU）等具有天然硬件并行性的计算芯片成为除CPU之外的重要选择,特别是FPGA正被越来越多的商业化平台所采用,但所用仿真算法大多基于传统框架,尚未能充分发挥FPGA的硬件架构优势。此外,电力电子设备和含电力电子设备电力系统实时仿真的算法并行性、强刚性与数值稳定性问题仍具有巨大的研究空间。     

Neural network robust control of a 3-DOF hydraulic manipulator with asymptotic tracking

Multiaxial hydraulic manipulators are complicated systems with highly nonlinear dynamics and various modeling uncertainties, which hinders the development of high-performance controller. In this paper, a neural network feedforward with a robust integral of the sign of the error (RISE) feedback is proposed for high precise tracking control of hydraulic manipulator systems. The established nonlinear model takes three-axis dynamic coupling, hydraulic actuator dynamics, and nonlinear friction effects into consideration. A radial basis function neural network (RBFNN) is synthesized to approximate the uncertain system dynamics and external disturbance, which can greatly reduce the dependence on accurate system model. In addition, a continuous RISE feedback law is judiciously integrated to deal with the residual unknown dynamics. Since the major unknown dynamics can be estimated by the RBFNN and then compensated in the feedforward design, the high-gain feedback issue in RISE feedback control will be avoided. The proposed RISE-based neural network robust controller theoretically guarantees an excellent semi-global asymptotic stability. Comparative simulation is performed on a 3-DOF hydraulic manipulator, and the obtained results verify the effectiveness of the proposed controller.