Accurate and real-time traffic forecasting plays an important role in the Intelligent Traffic System is of great significance for urban planning, management, control. However, has always been considered open scientific issue, owing to constraints road network topological structure law dynamic change with time, namely, spatial dependence temporal dependence. To capture simultaneously, we propose a novel neural network-based method, graph convolutional (T-GCN) model, which combination (GCN)...

Wireless power transfer via coupled magnetic resonance has many merits, which become one of the hot research spots in recent years. The progress technology field wireless is remarkable, but its and efficiency vary with impacts distance, orientation, center deviation on transmission. To suppress fast decrease efficiency, equivalent circuit model mutual inductance theory were presented. results provided critical insight into design improving using a novel method frequency tracking. measurement...

Thanks to the increasing availability of drug-drug interactions (DDI) datasets and large biomedical knowledge graphs (KGs), accurate detection adverse DDI using machine learning models becomes possible. However, it remains largely an open problem how effectively utilize noisy KG for detection. Due its sheer size amount noise in KGs, is often less beneficial directly integrate KGs with other smaller but higher quality data (e.g., experimental data). Most existing approaches ignore altogether....

One main challenge in tunnel constructions is to predict the geological conditions without excavation ensure safety during construction process. This paper proposes a data-driven framework for real-time interpreting operating data of boring machines (TBMs) interrupting tunneling operations, and eventually automate operation. In this framework, we first convert indexes original from discontinuous time continuous displacement. After screening outliers, more exhaustively explore inherent...

Racetrack memory is an emerging non-volatile based on spintronic domain wall technology. It can achieve ultra-high storage density. Also, its read/write speed comparable to that of SRAM. Due the tape-like structure cell, a "shift" operation introduced access racetrack memory. Thus, prior research mainly focused minimizing shift latency/energy while leveraging Yet reliability issue operation, however, not well addressed. In fact, suffers from unsuccessful due misalignment. Such problem called...

In the last few decades, production scheduling problems have been studied for optimizing efficiency involving time-related indicators, such as completion time, earliness/tardiness or flow time. Currently, with consideration of sustainable development, green problem has paid more and attention. Here, a job shop is considered to minimize sum energy-consumption cost completion-time in workshop. this paper, mathematical model first established multi-speed machines. A discrete whale optimization...

Recently, an emerging non-volatile memory called Racetrack Memory (RM) becomes promising to satisfy the requirement of increasing on-chip capacity. RM can achieve ultra-high storage density by integrating many bits in a tape-like racetrack, and also provide comparable read/write speed with SRAM. However, lack circuit-level modeling has limited design exploration RM, especially system-level. To overcome this limitation, we develop model, careful study device configurations circuit layouts....

First Page

Only a small fraction of patients with cancer receiving immune checkpoint therapy (ICT) respond, which is associated tumor microenvironment (TIME) subtypes and tumor-infiltrating lymphocytes (TILs).To examine whether germline variants natural killer (NK) cells, key component the system, are TIME subtypes, abundance TILs, response to ICT, clinical outcomes, risk.This genetic association study explored examined genomic information prognosis, risk. Clinical information, RNA sequencing,...

Artificial fish swarm algorithm is a kind of intelligence that imitates the behavior individuals and information interactions among them during feeding process in real environment. This paper proposes an improved artificial algorithm. First all, it adopts dynamic adjustments for view step length fish, which let keep large value early stage The will change from big to small thus realizes transformation rough search refined search. Secondly, move several steps towards better position foraging,...

Aircraft longitudinal control is the most important actuation system and its failures would lead to catastrophic accident of aircraft. This paper proposes an active fault-tolerant (AFTC) strategy for civil aircraft with different numbers faulty elevators. In order improve flight performance effective utilization surface, trimmable horizontal stabilizer (THS) considered generate extra pitch moment. A suitable switching mechanism improvement coefficient proposed determine when it worthwhile...

Abstract As a key aircraft component, hydraulic piston pumps must be developed with high reliability. However, collecting failure time data of such for reliability analysis is big challenge. To save testing time, performance degradation obtained from tests can used quick estimation pumps. This paper proposes an engineering‐driven method considering the nature mechanical wear First, mechanism type pump investigated. By taking into account close relationship between rate and mechanism, inverse...

In this study, the zero-error convergence of iterative learning control for a tracking problem is realised by incorporating uniform quantiser with an encoding and decoding mechanism. Under scheme, system output first transformed encoded. Then, encoded information transmitted back updating input. The results are extended to finite quantisation level situation under same framework simulation using permanent magnet linear motor performed demonstrate effectiveness proposed scheme.

Contaminated particles are important factor affecting the reliable operation of aircraft hydraulic systems. The complex movement mode contaminated in fluid makes it difficult to analyse system failures. This paper proposes a topology network model that can describe within system. Firstly, motion state inside pipelines is analysed, and particle based on drag force established. Then, pipeline component flow constructed. A cascading propagation constructed components. Finally, taking A380 civil...

In this paper, drive effect analysis and performance testing of a bionic jellyfish robot driven by SMA-based materials are carried out. Firstly, the design ideas driver overall structure presented. The eddy currents at end tentacles on swimming during its movement is investigated. constructed model subjected to two-way fluid-solid coupling simulation. propulsive paddle propulsion It demonstrated that robots exhibit passive energy recovery capabilities analogous those observed in real...