Recently, network representation learning has been widely used to mine and analyze characteristics, it is also applied blockchain, but most of the embedding methods in blockchain ignore heterogeneity network, so difficult accurately describe characteristics transaction. As smart society evolves, Ethereum makes contracts reality, while transaction appearing on platform scarce; thus, there an urgent need from contract transfer. In this article, we propose a heterogeneous method implicit...

The rapid development of information technology such as the Internet Things, Big Data, artificial intelligence, and blockchain has changed transaction mode financial industry greatly improved convenience transactions, but it also brought about new hidden frauds, which have caused huge losses to IoT finance. As size data continues grow, traditional machine-learning models are increasingly difficult use for fraud detection. Some graph-learning methods been widely used detection, however, these...

With Ethereum blockchain advancement, the platform gathers numerous users. In this context, traditional phishing appears new fraud methods, resulting in significant losses. Currently, network embedding methods are considered effective solutions field of detection. However, investigating existing node detection algorithms finds they not optimal and still face two issues. Firstly, network's topology is unsatisfactory, with nodes exhibiting a long-tail distribution their degree. Current...

Riser recoil control is a complicated nonlinear problem. An intelligent methodology proposed to the riser response based on fuzzy theory. A dynamic model of drilling riser/tensioner coupling system established for analysis. The divided into several elements and effect between discharged mud considered in model. controller opening valve designed control. comprehensive analysis method simulation. Simulation results show that can effectively response. adaptability also proved by simulation...

Collaborative robots sensing and understanding the movements intentions of their human partners are crucial for realizing human-robot collaboration. Human skeleton sequences widely recognized as a kind data with great application potential in action recognition. In this letter, multi-scale skeleton-based recognition network is proposed, which leverages spatio-temporal attention mechanism. The achieves high-accuracy prediction by aggregating multi-level key point features applying mechanism...

S-sulfhydration, a crucial post-translational protein modification, is pivotal in cellular recognition, signaling processes, and the development progression of cardiovascular neurological disorders, so identifying S-sulfhydration sites for studies cell biology. Deep learning shows high efficiency accuracy compared to traditional methods that often lack sensitivity specificity accurately locating nonsulfhydration sites. Therefore, we employ deep tackle challenge pinpointing In this work,...

Remote sensing image segmentation plays an important role in many industrial-grade processing applications. However, the problem of uncertainty caused by intraclass heterogeneity and interclass blurring is prevalent high-resolution remote images. Moreover, complexity information images leads to a large amount background around objects. To solve this problem, new fuzzy convolutional neural network proposed paper. This resolves ambiguity feature introducing neighbourhood module deep learning...

With the development of Industrial Internet Things (IoT), work large-scale data collection makes spatiotemporal crowdsensing (SC) play an important role. Mobile devices equipped with sensors could act as workers to collect and process for uploading. In task allocation process, a fully static fails meet needs realistic conditions, while completely dynamic achieve desired results. Therefore, we assume task-scheduled execution scenario that combines above two conditions. pre-allocation original...

Three-level sparse neutral point clamped inverter is employed in this paper due to low harmonic, fewer switching devices, and less dc-link capacitor voltage imbalance problems. Model predictive control (MPC) methods are proposed fully exploit the advantages of while ensuring balance maintaining computational complexity. First, desired vector reference constructed realize current tracking based on model three-level inverter. Second, n-type or p-type small vectors carefully tuned minimize...

Vienna rectifier, which is a nongenerative-boost-type widely used in industrial applications, such as wind turbine systems. However, the rectifier will face challenge of reducing common-mode voltage (CMV), maintaining sinusoidal input currents, and balancing neutral-point (NP) practice. As these issues are mutually coupled, conventional space vector modulation (SVM) various types enhanced schemes cannot solve problems properly, especially under nonunity power factor operation. To overcome...

With the rapid progression of mobile crowdsourcing (MCS) technology, its growing influence in our daily lives has established it as a crucial component modern society. However, while convenience MCS is widely appreciated, also poses significant threats to personal privacy, particularly location privacy. This article introduces novel system for personalized privacy protection MCS. The divided into three main parts. first part presents an innovative algorithm that calculates level crowd...

The purpose of this work is to demonstrate an ultra-fast reconstruction technique for digital tomosynthesis (DTS) imaging based on the algorithm proposed by Feldkamp, Davis, and Kress (FDK) using standard general-purpose graphics processing unit (GPGPU) programming interface. To end, FDK-based DTS was programmed “in-house” with C language utilization 1) GPU 2) central (CPU) cards. card consisted 480 cores (2 × 240 dual chip) 1,242 MHz clock speed 1,792 MB memory space. In terms CPU hardware,...

Semantic segmentation of high-resolution remote sensing images plays an important role in the community. However, many indistinguishable objects are prevalent within urban images, and some belonging to same class different that do not belong similar. These tricky make exhibit low-interclass variance high-intraclass variance, which significantly limits performance. Therefore, a fresh insight was presented alleviate this issue by incorporating fuzzy pattern recognition method deep-learning...

Mobile crowdsourcing (MCS) is a new paradigm that uses various mobile devices to collect sensed data. edge computing (MEC) can effectively utilize the device resources of edge, greatly relieve pressure network bandwidth and improve response speed. In this article, we construct four-party evolutionary game model consisting platform, crowd workers, task requesters, servers. The tasks are conducted on servers, which reduce remote data transmission operating costs service quality. Taking into...

Multi-view graph clustering can divide similar objects into the same category through learning relationship among samples. To improve efficiency, instead of all sample-based learning, bipartite method achieve efficient by establishing between data points and a few anchors, so it becomes an important research topic. However, most these graph-based multi-view approaches focused on consistent information views, ignored diversity each view, which is not conductive to precision. address this...

Purpose: Utilization of respiratory correlated four‐dimensional cone‐beam computed tomography (4DCBCT) has enabled verification internal target motion and volume immediately prior to treatment. However, with current standard CBCT scan, 4DCBCT poses challenge for reconstruction due the fact that multiple phase binning leads insufficient number projection data reconstruct thus cause streaking artifacts. The purpose this study is develop a novel algorithm framework called motion‐map constrained...

Siamese networks are prevalent in person re-identification (re-id) tasks to address the similarity and dissimilarity among video frames. It mainly focuses on inter-video variation between spatio-temporal features extracted from different videos, while of same has been rarely discussed. In this paper, we introduce concept "mean-body" define an intra-video loss video. A novel is presented boost training re-id by combining proposed loss. Specifically, uses unique mean-body each camera viewpoint...

This paper presents a preliminary design methodology for small unmanned battery powered tailsitters. Subsystem models, including takeoff weight, power and energy consumption discharge model, were investigated, respectively. Feasible space was given by simulation with mission weight constraints, while the influences of wing loading ratio analyzed. Case study carried out according to process, results validated previous designs. The can be used determine key parameters make necessary...

Convolutional neural-network-based autoencoders, which can integrate the spatial correlation between pixels well, have been broadly used for hyperspectral unmixing and obtained excellent performance. Nevertheless, these methods are hindered in their performance by fact that they treat all spectral bands information equally procedure. In this article, we propose an adaptive spectral–spatial attention autoencoder network, called SSANet, to solve mixing pixel problem of image. First, design...