Rayseerup0824

Event cameras as bioinspired vision sensors have shown great advantages in high dynamic range and high temporal resolution in vision tasks. Asynchronous spikes from event cameras can be depicted using the marked spatiotemporal point processes (MSTPPs). However, how to measure the distance between asynchronous spikes in the MSTPPs still remains an open issue. To address this problem, we propose a general asynchronous spatiotemporal spike metric considering both spatiotemporal structural properties and polarity attributes for event cameras. Technically, the conditional probability density function is first introduced to describe the spatiotemporal distribution and polarity prior in the MSTPPs. Besides, a spatiotemporal Gaussian kernel is defined to capture the spatiotemporal structure, which transforms discrete spikes into the continuous function in a reproducing kernel Hilbert space (RKHS). Finally, the distance between asynchronous spikes can be quantified by the inner product in the RKHS. The experimental results demonstrate that the proposed approach outperforms the state-of-the-art methods and achieves significant improvement in computational efficiency. Especially, it is able to better depict the changes involving spatiotemporal structural properties and polarity attributes.In a modern e-commerce recommender system, it is important to understand the relationships among products. Recognizing product relationships--such as complements or substitutes--accurately is an essential task for generating better recommendation results, as well as improving explainability in recommendation. Products and their associated relationships naturally form a product graph, yet existing efforts do not fully exploit the product graph's topological structure. They usually only consider the information from directly connected products. In fact, the connectivity of products a few hops away also contains rich semantics and could be utilized for improved relationship prediction. In this work, we formulate the problem as a multilabel link prediction task and propose a novel graph neural network-based framework, item relationship graph neural network (IRGNN), for discovering multiple complex relationships simultaneously. We incorporate multihop relationships of products by recursively updating node embeddings using the messages from their neighbors. An edge relational network is designed to effectively capture relational information between products. Extensive experiments are conducted on real-world product data, validating the effectiveness of IRGNN, especially on large and sparse product graphs.Synthetic aperture radar (SAR) has been widely applied in both civilian and military fields because it provides high-resolution images of the ground target regardless of weather conditions, day or night. In SAR imaging, the separation of moving and stationary targets is of great significance as it is capable of removing the ambiguity stemming from inevitable moving targets in stationary scene imaging and suppressing clutter in moving target imaging. The newly emerged generative adversarial networks (GANs) have great performance in many other signal processing areas; however, they have not been introduced to radar imaging tasks. In this work, we propose a novel shuffle GAN with autoencoder separation method to separate the moving and stationary targets in SAR imagery. The proposed algorithm is based on the independence of well-focused stationary targets and blurred moving targets for creating adversarial constraints. Note that the algorithm operates in a totally unsupervised fashion without requiring a sample set that contains mixed and separated SAR images. Experiments are carried out on synthetic and real SAR data to validate the effectiveness of the proposed method.Accurate and real-time fault diagnosis (FD) and working conditions identification (WCI) are the key to ensuring the safe operation of mechanical systems. We observe that there is a close correlation between the fault condition and the working condition in the vibration signal. Most of the intelligent FD methods only learn some features from the vibration signals and then use them to identify fault categories. They ignore the impact of working conditions on the bearing system, and such a single-task learning method cannot learn the complementary information contained in multiple related tasks. Therefore, this article is devoted to mining richer and complementary globally shared features from vibration signals to complete the FD and WCI of rolling bearings at the same time. To this end, we propose a novel multitask attention convolutional neural network (MTA-CNN) that can automatically give feature-level attention to specific tasks. The MTA-CNN consists of a global feature shared network (GFS-network) for learning globally shared features and K task-specific networks with feature-level attention module (FLA-module). This architecture allows the FLA-module to automatically learn the features of specific tasks from globally shared features, thereby sharing information among different tasks. see more We evaluated our method on the wheelset bearing data set and motor bearing data set. The results show that our method has a better performance than the state-of-the-art deep learning methods and strongly prove that our multitask learning mechanism can improve the results of each task.Hashing is a popular search algorithm for its compact binary representation and efficient Hamming distance calculation. Benefited from the advance of deep learning, deep hashing methods have achieved promising performance. However, those methods usually learn with expensive labeled data but fail to utilize unlabeled data. Furthermore, the traditional pairwise loss used by those methods cannot explicitly force similar/dissimilar pairs to small/large distances. Both weaknesses limit existing methods' performance. To solve the first problem, we propose a novel semi-supervised deep hashing model named adversarial binary mutual learning (ABML). Specifically, our ABML consists of a generative model GH and a discriminative model DH, where DH learns labeled data in a supervised way and GH learns unlabeled data by synthesizing real images. We adopt an adversarial learning (AL) strategy to transfer the knowledge of unlabeled data to DH by making GH and DH mutually learn from each other. To solve the second problem, we propose a novel Weibull cross-entropy loss (WCE) by using the Weibull distribution, which can distinguish tiny differences of distances and explicitly force similar/dissimilar distances as small/large as possible. Thus, the learned features are more discriminative. Finally, by incorporating ABML with WCE loss, our model can acquire more semantic and discriminative features. Extensive experiments on four common data sets (CIFAR-10, large database of handwritten digits (MNIST), ImageNet-10, and NUS-WIDE) and a large-scale data set ImageNet demonstrate that our approach successfully overcomes the two difficulties above and significantly outperforms state-of-the-art hashing methods.Molecular communication (MC) inspired drug delivery holds considerable promise as a new design for targeted therapy with high efficiency and minimal toxicity. The process of drug delivery can be modelled in a blood flow-based MC system, where nanoparticles (NPs) carry therapeutic agents through the blood vessel channels to the targeted diseased tissue. Most previous studies in the flow-based MC consider a Newtonian fluid with a laminar flow, which ignores the influence of red blood cells (RBCs). However, the nature of blood flow is a complex and non-Newtonian fluid composed of proteins, platelets, plasma and deformable cells, especially RBCs. The ability to change their shapes is essential to the proper functioning of RBCs in the microvasculature. Different shapes of RBCs have a great impact on the performance of blood flow. Changes in the properties and shapes of RBCs are often associated with different diseases, such as sickle cell anemia, diabetes, and malaria. Thus, it is highly important to establish a more realistic blood flow MC model considering the deformable cells. According to our previous study, the motion and adhesion of individual NPs are modelled through the Brownian adhesion dynamics. Subsequently, this paper establishes a particle-cell hybrid model in the flow-based MC, which focuses on the RBC deformation, aggregation, and dispersion in the blood suspension. Based on the state of the RBC deformation and aggregation in the vessels with different flow rates, this paper proposes a novel methodology for detecting the deformability of the cells. The blood state in terms of RBC deformability is determined by the difference in NPs' concentration at the receiving end., this paper sheds some light on the influence of RBCs on the motion of NPs, which provides new insights on the design of targeted drug delivery and the detection of vascular diseases.Misalignments between powered exoskeleton joints and the user's anatomical joints are inevitable due to difficulty locating the anatomical joint axis, non-constant location of the anatomical joint axis, and soft-tissue deformations. Self-aligning mechanisms have been proposed to prevent spurious forces and torques on the user's limb due to misalignments. Several exoskeletons have been developed with self-aligning mechanisms based on theoretical models. However, there is no experimental evidence demonstrating the efficacy of self-aligning mechanisms in lower-limb exoskeletons. Here we show that a lightweight and compact self-aligning mechanism improves the user's comfort and performance while using a powered knee exoskeleton. Experiments were conducted with 14 able-bodied subjects with the self-aligning mechanism locked and unlocked. Our results demonstrate up to 15.3% increased comfort and 38% improved performance when the self-aligning mechanism was unlocked. Not surprisingly, the spurious forces and torques were reduced by up to 97% when the self-aligning mechanism was unlocked. This study demonstrates the efficacy of self-aligning mechanisms in improving comfort and performance for sit-to-stand and position tracking tasks with a powered knee exoskeleton.Sensory abnormalities are experienced by 90 - 95% of individuals with Autism Spectrum Disorder (ASD), a developmental disorder that impacts at least 1 in 132 children worldwide. Virtual reality (VR) technologies can precisely present sensory stimuli and be integrated with human sensing technologies to automatically detect sensory responses, and thus has a potential to improve sensory assessment objectiveness and sensitivity, compared to traditional questionnaire-based methods. However, there is a lack of evidence to demonstrate this potential. Therefore, we designed and developed a preliminary sensory assessment VR system (SAVR) to objectively and precisely evaluate the visual and touch sensory processing differences between adolescents with ASD and their typically developing (TD) peers through game playing. A controlled experiment was conducted with 12 adolescents with ASD and 12 TD adolescents. Participants' sensory pattern was assessed by SAVR and a widely used traditional questionnaire-the Adult/Adolescent Sensory Profile (AASP).