The adsorption and electronic properties of molecules (NO, H2S, SO2, NO2, NH3, N2, CO, CH4, CO2, H2O) on the C6N7 monolayer were systematically studied to explore possibilities C6N7-based toxic gas sensor scavenger by using first-principles methods. We found only NO, SO2 are adsorbed with high strength (ranging -0.853~-0.931 eV), meanwhile other all weak physisorption Ead -0.193~-0.547 eV. NO H2S could remarkably affect monolayer, indicating it is highly sensitive selective towards H2S....

Monitoring for early symptoms is a critical step in preventing pneumoconiosis. The signs of pneumoconiosis can be characterized by dyspnea, tachypnea, and cough. While traditional sensor-based methods are promising, they necessitate the wearing devices confine human physical movements. On other hand, camera-based have issues related to illumination, obstruction, privacy. Recently, wireless sensing has attracted significant amount research attention. Among signals, acoustic signals possess...

Object tracking is one of the challenging problems in field computer vision. Affected by unstructured environments, for example, occlusion, noise, and light, These factors can affect appearance specific object result failures when objects. To address this issue, we propose a novel visual method based on multimodal convolutional network learning. Our framework adopts parallel structure, which consists two shallow neural networks. First, used to draw different features RGB-T (RGB thermal) data...

This study proposes a new approach to gait recognition using LoRa signals, taking into account the challenging conditions found in underground coal mines, such as low illumination, high temperature and humidity, dust concentrations, limited space. The aim is address limitations of existing research, which relies on sensors or other wireless signals that are sensitive environmental factors, costly deploy, invasive, require close sensing distances. proposed method analyzes received signal...

This paper addresses the challenging problem of multishot person reidentification (Re-ID) in real world uncontrolled surveillance systems. A key issue is how to effectively represent and process multiple data with various appearance information due variations pose, occlusions, viewpoints. To this end, develops a novel subspace learning approach, which pursues regularized low-rank sparse representation for Re-ID. For images crossing certain camera, we assume that appearances those subset...

The partial penetrating waterproof curtain combined with pumping wells is widely applied to deep foundation pit dewatering engineering. filter tube of the well plays a critical role on environment effect that resulted from dewatering. This paper investigated impact groundwater drawdown outside provide theoretical basis for design. Three patterns according relative position and tube, which are called wall-well patterns, namely full-closed pattern, part-closed none-closed have been analyzed....

Prolonged exposure to coal mine dust has led various respiratory diseases among workers. Accurate monitoring of personal concentration is crucial for evaluating underground However, existing devices are expensive and bulky, limiting their widespread application resulting in unknown levels most miners. This study evaluated the performance two low-cost particulate matter (PM) sensors (PMS12 PMS16) at high low levels. The results showed that both possess good enough linearity (R2 = 0.92–0.93)...

A smart contract is a computable protocol that automatically enforces terms in computer, transforming real-world into digital promises of the virtual world. Early contracts have been stuck theoretical phase due to lack credible execution environment and means control assets. With emergence blockchain technology, it has solved problems mentioned above. Smart are stored on blockchain, ensuring credibility through joint by various nodes network. However, current technology blockchain-based...

The widely used K-means clustering is a hard algorithm. Here we propose Elastic model (EKM) using posterior probability with soft capability where each data point can belong to multiple clusters fractionally and show the benefit of proposed K-means. Furthermore, in many applications, besides vector attributes information, pairwise relations (graph information) are also available. Thus integrate EKM Normalized Cut graph into single formulation. Finally, provide several useful matrix...

In order to further explore the application of deep learning in predicting financial market time series data and improve accuracy prediction, this paper adopts a prediction method based on wavelet denoising, whale optimization algorithm long-short term memory (LSTM) neural network. This article chooses 10 common evaluation indexes as input, are denoised by analysis. Then optimal LSTM network parameters obtained (WOA). Finally, is used for stock output predicted closing price. To verify...

Reinforcement learning is an emerging approaches to facilitate multi-stage sequential decision-making problems. This paper studies a real-time stochastic power dispatch considering multivariate uncertainties. Current researches suffer from low generalization and practicality, that is, the learned policy can only handle specific scenario, its performance degrades significantly if actual samples training are inconsistent. To fill these gaps, novel contextual meta graph reinforcement (Meta-GRL)...

Early symptom monitoring is an essential measure for pneumoconiosis prevention. However, one severe limitation the high requirement a dedicated device. This paper proposes <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$p^{3}Warning$</tex> to realize low-cost warnings potential patients via contactless sensing. For first time, designed framework utilizes inaudible acoustic signal with pair of commercial speaker and microphone monitor early...

Aviation service plays an indispensable role in the process of social and economic development. In this process, problem flight punctuality becomes more serious. Flight delay will bring a variety implicit explicit losses to individual passengers airlines, so it is necessary analyze influencing factors rate. Complex network can be used study various objects with complex relations, obtain relations these calculate influence different indicators on objects. This article mainly has carried three...

In this article, we present a data-driven method for parametric models with noisy observation data. Gaussian process regression based reduced order modeling (GPR-based ROM) can realize fast online predictions without using equations in the offline stage. However, GPR-based ROM does not perform well complex systems since POD projection are naturally linear. Conditional variational autoencoder (CVAE) address issue via nonlinear neural networks but it has more model complexity, which poses...