在这个时代，智能和低功率视网膜假体的需求高度要求，在这个时代，可穿戴和可植入的设备用于众多医疗保健应用。在本文中，我们提出了一个节能动态场景处理框架（Spikesee），该框架结合了尖峰代表编码技术和生物启发的尖峰复发性神经网络（SRNN）模型，以实现智能处理和极端的低功耗计算。尖峰表示编码技术可以用稀疏的尖峰火车来解释动态场景，从而减少数据量。采用受人视网膜特殊结构和尖峰加工方法的启发的SRNN模型，以预测神经节细胞对动态场景的响应。实验结果表明，所提出的SRNN模型的Pearson相关系数达到0.93，这表现优于视网膜假体的最先进的处理框架。得益于尖峰表示和SRNN处理，该模型可以以无倍数的方式提取视觉特征。与基于卷积的复发神经网络（CRNN）处理框架相比，该框架可实现12倍的功率。我们提出的Spikesee可以通过较低的能源消耗来更准确地预测神经节细胞的响应，从而减轻了视网膜假体的精度和功率问题，并为可穿戴或可植入的假体提供了潜在的解决方案。

闭环体系结构被广泛用于自动控制系统，并获得了杰出的性能。但是，经典的压缩传感系统采用了带有分离的采样和重建单元的开环体系结构。因此，通过将闭环框架引入传统压缩的传感系统中，提出了图像压缩传感（ICRIC）的迭代补偿恢复方法。提出的方法取决于任何现有方法，并通过添加负面反馈结构来升级其重建性能。对压缩传感系统负反馈的理论分析。还提供了所提出方法有效性的大致数学证明。在3个以上图像数据集上进行的仿真实验表明，该方法优于重建性能中的10种竞争方法。平均峰值信噪比的最大增量为4.36 dB，一个数据集的平均结构相似性的最大增量为0.034。基于负反馈机制的提议方法可以有效纠正现有图像压缩传感系统中的恢复误差。

如今，提出了几种深度学习方法来应对癫痫发作预测的挑战。但是，由于其大型硬件和相应的高功率消耗，这些方法仍然无法作为可植入或有效的可穿戴设备的一部分实现。他们通常需要复杂的功能提取过程，用于存储高精度参数的大存储器和复杂的算术计算，从而大大增加了所需的硬件资源。此外，可用的预测性能差，因为它们直接从图像识别应用程序中采用网络体系结构无法准确考虑EEG信号的特征。我们在本文中提出了一个适合二进制卷积神经网络（BSDCNN）的硬件友好网络，用于癫痫发作预测。 BSDCNN利用1D卷积内核来提高预测性能。除了第一层外，所有参数均已二进制以减少所需的计算和存储。在美国癫痫社会癫痫发作预测挑战（AES）数据集和CHB-MIT方面，曲线，灵敏度和虚假预测率的总面积达到0.915、89.26％，0.117/h和0.970，94.69％，0.095/h。所提出的体系结构的表现优于最新作品，同时提供了7.2和25.5倍的参数和计算大小。

客观的。深度神经网络（DNNS）在各种脑机界面应用中表现出了前所未有的成功，例如癫痫发作预测。但是，由于癫痫信号的高度个性化特征，现有方法通常会以特定于患者的方式训练模型。因此，只能将每个受试者的标记录音数量有限用于培训。结果，由于训练数据的不足，目前基于DNN的方法在一定程度上表现出较差的泛化能力。另一方面，与患者无关的模型试图利用更多的患者数据通过将患者数据汇总在一起为所有患者培训通用模型。尽管采用了不同的技术，但结果表明，由于患者的个体差异很高，与患者独立的模型相比性能要比患者特异性模型差。因此，在患者特异性和与患者无关的模型之间存在很大的差距。方法。在本文中，我们提出了一种基于知识蒸馏的新型培训计划，该方案利用了来自多个受试者的大量数据。首先，它从具有预训练的通用模型的所有可用受试者的信号中提取信息。然后可以借助蒸馏知识和其他个性化数据获得患者特异性的模型。主要结果。通过我们建议的计划，对波士顿-MIT儿童医院的Seeg数据库进行了四种最先进的癫痫发作预测方法。由此产生的准确性，敏感性和错误的预测率表明，我们提出的培训方案一致地提高了最先进方法的预测性能。意义。拟议的训练方案显着改善了患者特异性癫痫发作预测因子的性能，并弥合了患者特异性和与患者无关的预测因子之间的差距。

自动编码器由编码和解码单元组成，因此它们具有高性能数据压缩和信号压缩传感的固有潜力。当前自动编码器的主要缺点包括以下几个方面：研究目标不是数据重建，而是特征表示；忽略了数据恢复的绩效评估；即使是通过纯净的深度学习，也很难通过纯自动编码器实现无损数据重建。本文旨在对自动编码器进行图像重建，采用基于级联解码器的自动编码器，完善图像重建的性能，逐渐无损的图像恢复，并为基于自动编码器的图像压缩和压缩感提供可靠的理论和应用基础。提出的基于串行解码器的自动编码器包括多级解码器的架构和相关的优化算法。级联解码器由一般解码器，剩余解码器，对抗解码器及其组合组成。通过实验结果评估，所提出的自动编码器在图像重建的性能中优于经典自动编码器。

Climate change is expected to intensify and increase extreme events in the weather cycle. Since this has a significant impact on various sectors of our life, recent works are concerned with identifying and predicting such extreme events from Earth observations. This paper proposes a 2D/3D two-branch convolutional neural network (CNN) for wildfire danger forecasting. To use a unified framework, previous approaches duplicate static variables along the time dimension and neglect the intrinsic differences between static and dynamic variables. Furthermore, most existing multi-branch architectures lose the interconnections between the branches during the feature learning stage. To address these issues, we propose a two-branch architecture with a Location-aware Adaptive Denormalization layer (LOADE). Using LOADE as a building block, we can modulate the dynamic features conditional on their geographical location. Thus, our approach considers feature properties as a unified yet compound 2D/3D model. Besides, we propose using an absolute temporal encoding for time-related forecasting problems. Our experimental results show a better performance of our approach than other baselines on the challenging FireCube dataset.

Prostate cancer (PCa) is one of the most prevalent cancers in men and many people around the world die from clinically significant PCa (csPCa). Early diagnosis of csPCa in bi-parametric MRI (bpMRI), which is non-invasive, cost-effective, and more efficient compared to multiparametric MRI (mpMRI), can contribute to precision care for PCa. The rapid rise in artificial intelligence (AI) algorithms are enabling unprecedented improvements in providing decision support systems that can aid in csPCa diagnosis and understanding. However, existing state of the art AI algorithms which are based on deep learning technology are often limited to 2D images that fails to capture inter-slice correlations in 3D volumetric images. The use of 3D convolutional neural networks (CNNs) partly overcomes this limitation, but it does not adapt to the anisotropy of images, resulting in sub-optimal semantic representation and poor generalization. Furthermore, due to the limitation of the amount of labelled data of bpMRI and the difficulty of labelling, existing CNNs are built on relatively small datasets, leading to a poor performance. To address the limitations identified above, we propose a new Zonal-aware Self-supervised Mesh Network (Z-SSMNet) that adaptatively fuses multiple 2D, 2.5D and 3D CNNs to effectively balance representation for sparse inter-slice information and dense intra-slice information in bpMRI. A self-supervised learning (SSL) technique is further introduced to pre-train our network using unlabelled data to learn the generalizable image features. Furthermore, we constrained our network to understand the zonal specific domain knowledge to improve the diagnosis precision of csPCa. Experiments on the PI-CAI Challenge dataset demonstrate our proposed method achieves better performance for csPCa detection and diagnosis in bpMRI.

Information extraction from scholarly articles is a challenging task due to the sizable document length and implicit information hidden in text, figures, and citations. Scholarly information extraction has various applications in exploration, archival, and curation services for digital libraries and knowledge management systems. We present MORTY, an information extraction technique that creates structured summaries of text from scholarly articles. Our approach condenses the article's full-text to property-value pairs as a segmented text snippet called structured summary. We also present a sizable scholarly dataset combining structured summaries retrieved from a scholarly knowledge graph and corresponding publicly available scientific articles, which we openly publish as a resource for the research community. Our results show that structured summarization is a suitable approach for targeted information extraction that complements other commonly used methods such as question answering and named entity recognition.

Measuring growth rates of apple fruitlets is important because it allows apple growers to determine when to apply chemical thinners to their crops to optimize yield. The current practice of obtaining growth rates involves using calipers to record sizes of fruitlets across multiple days. Due to the number of fruitlets needed to be sized, this method is laborious, time-consuming, and prone to human error. In this paper, we present a computer vision approach to measure the sizes and growth rates of apple fruitlets. With images collected by a hand-held stereo camera, our system detects, segments, and fits ellipses to fruitlets to measure their diameters. To measure growth rates, we utilize an Attentional Graph Neural Network to associate fruitlets across different days. We provide quantitative results on data collected in an apple orchard, and demonstrate that our system is able to predict abscise rates within 3% of the current method with a 7 times improvement in speed, while requiring significantly less manual effort. Moreover, we provide results on images captured by a robotic system in the field, and discuss the next steps to make the process fully autonomous.

Continuous behavioural authentication methods add a unique layer of security by allowing individuals to verify their unique identity when accessing a device. Maintaining session authenticity is now feasible by monitoring users' behaviour while interacting with a mobile or Internet of Things (IoT) device, making credential theft and session hijacking ineffective. Such a technique is made possible by integrating the power of artificial intelligence and Machine Learning (ML). Most of the literature focuses on training machine learning for the user by transmitting their data to an external server, subject to private user data exposure to threats. In this paper, we propose a novel Federated Learning (FL) approach that protects the anonymity of user data and maintains the security of his data. We present a warmup approach that provides a significant accuracy increase. In addition, we leverage the transfer learning technique based on feature extraction to boost the models' performance. Our extensive experiments based on four datasets: MNIST, FEMNIST, CIFAR-10 and UMDAA-02-FD, show a significant increase in user authentication accuracy while maintaining user privacy and data security.