Abstract Hand-foot-mouth disease (HFMD) is a common infectious in children and particularly severe Guangxi, China. Meteorological conditions are known to play pivotal role the HFMD. Previous studies have reported numerous models predict incidence of In this study, we proposed new method for HFMD prediction using GeoDetector Long Short-Term Memory neural network (LSTM). The daily meteorological factors records Guangxi during 2014–2015 were adopted. First, potential risk occurrence identified...

Convolutional neural networks (CNN) have been widely used in the field of remote sensing (RS) scene classification, which achieved remarkable results. In RS local key objects are particularly crucial for classification However, most existing CNN methods directly utilize deep-level global features CNN, ignoring object-level information shallow or leading to redundant and erroneous when using features. To fully important features, we proposed an end-to-end contextual spatial-channel attention...

WiFi Channel State Information (CSI)-based activity recognition has sparked numerous studies due to its widespread availability and privacy protection. However, when applied in practical applications, general CSI-based models may face challenges related the limited generalization capability, since individuals with different behavior habits will cause various fluctuations CSI data it is difficult gather enough training cover all kinds of motion habits. To tackle this problem, we design a...

Abstract The relation between diet and lung cancer was studied among male residents of a mining community in Yunnan Province. After obtaining food frequency data from subjects or proxies, we compared diets 428 cases, aged 35–74 years, 1,011 age‐matched controls. Cases tended to consume slightly more rice, but less protein‐rich foods ( i.e. , bean curd, meat, eggs) vegetables than did relative risks across increasing quartiles meat pork) consumption, for example, were 1.00, 0.67, 0.72 0.46 p...

As a class of hard combinatorial optimization problems, the school bus routing problem has received considerable attention in last decades. For multi-school system, given trips for each school, scheduling aims at optimizing schedules to serve all within time windows. In this paper, we propose two approaches solving bi-objective problem: an exact method mixed integer programming (MIP) and metaheuristic which combines simulated annealing with local search. We develop MIP formulations...

Abstract Deep learning methods, particularly Convolutional Neural Network (CNN), have been widely used in hyperspectral image (HSI) classification. CNN can achieve outstanding performance the field of HSI classification due to its advantages fully extracting local contextual features HSI. However, is not good at long-distance dependency relation and dealing with sequence properties Thus, it difficult continuously improve CNN-based models because they cannot take full advantage rich...

Unmanned aerial vehicle (UAV) image object detection has great application value in the military and civilian fields. However, objects captured images from UAVs have problems of large-scale variation, complex backgrounds, a large proportion small objects. To resolve these problems, multi-scale detector based on coordinate global information aggregation is proposed, named CGMDet. Firstly, Coordinate Global Information Aggregation Module (CGAM) designed by aggregating local, coordinate,...

Abstract With the development of Internet technology, problem information overload has increasingly attracted attention. Nowadays, recommendation system with excellent performance in retrieval and filtering would be widely used business field. However, most existing systems are considered a static process, during which recommendations for internet users often based on pre-trained models. A major disadvantage these models is that they incapable simulating interaction process between their...

The complex background and small scale of objects in remote sensing images (RSIs) lead to poor detection performance. To solve these problems, a new object method named the residual feature enhancement network (RFEDN) is proposed. First, weaken interference irrelevant backgrounds, we introduce common-and-differential attention into cross-stage partial darknet−53, which can refine features both channel spatial dimensions so that pays meaningful features. After this, design enhancement-based...

Designing a system to solve school bus routing problems (SBRP), especially in large district, is very complex and expensive. One of the challenges resides designing routes for buses when they have mixed loads, where each transports students one or more schools at same time save total number required. This article aims explore whether algorithm originally developed pickup delivery problem with windows (PDPTW) can be employed solving load SBRP. We present PDPTW-based address SBRP focusing on...

In recent years, deep learning has been widely used in hyperspectral image (HSI) classification and shown good capabilities. Particularly, the use of convolutional neural network (CNN) HSI achieved attractive performance. However, contains a lot redundant information, CNN-based model is limited by receptive field CNN cannot balance performance depth model. Furthermore, considering that can be regarded as sequence data, models mine features well. this paper, we propose named SSA-Transformer...

Unmanned Aerial Vehicles (UAVs) image object detection has great application value in military and civilian fields. However, the objects captured images from UAVs have problems of large scale variation, complex backgrounds, a proportion small objects. To resolve these problems, multi-scale detector based on coordinate global information aggregation is proposed, named CGMDet. Firstly, Coordinate Global Information Aggregation Module (CGAM) designed by aggregating local, coordinate,...

The study aimed to determine if and how environmental factors correlated with asthma admission rates in geographically different parts of Guangxi province China.Guangxi, China.This was done among 7804 patients.Spearman correlation coefficient used estimate between hospitalisation multiple regions. Generalised additive model (GAM) Poisson regression effects on 14 regions Guangxi.The strongest effect carbon monoxide (CO) found lag1 Hechi, every 10 µg/m3 increase CO caused an 25.6% rate (RR...

Most deep learning methods in hyperspectral image (HSI) classification use local methods, where overlapping areas between pixels can lead to spatial redundancy and higher computational cost. This paper proposes an efficient global (EGL) framework for HSI classification. The EGL was composed of universal random stratification (UGSS) sampling strategy a model BrsNet. UGSS used solve the problem insufficient gradient variance resulted from limited training samples. To fully extract explore most...

Multi-compartment vehicle routing problem (MCVRP) is an extension of the classical capacitated where products with different characteristics are transported together in one multiple compartments. This paper deals this problem, whose objective to minimize total travel distance while satisfying capacity and maximum route length constraints. We proposed a hybrid iterated local search metaheuristic (HILS) algorithm solve it. In framework search, current solution was improved iteratively by five...

In order to efficiently solve the vehicle routing problem with time window (VRPTW), a hyper-heuristic algorithm based on reinforcement learning was proposed. Firstly, performance of underlying heuristic evaluated, and then multi-armed bandit (MAB) used select low-level algorithm. At same time, simulated annealing-based acceptance rule determine whether accept solution obtained by each lowlevel ensure diversity solutions. Experiments carried out some VRPTW benchmark instances, results show...