The invention discloses a PM2.5 concentration value prediction method based on game neural network, which comprises the following steps: 1. Collecting raw data, wherein the raw data comprises PM2.5 concentration value historical data, PM2.5 concentration value index historical data and meteorological historical data; 2, generating simulation data by adopting that generate network; 3, adopting a discrimination network to judge whether that analog data is true or false; 4, adopting the game neural network to predict that concentration value of PM2.5. Besides the nonlinear correlation analysis between that historical data of the concentration value of PM2. 5, the historical data of PM2.5 concentration and meteorological historical data , a generation network is also introduced to mix the original data and noise to output the simulation data, and the simulation data are sent into the discrimination network for discrimination. According to the discrimination results, the intersection iteration and adjustment can be carried out. For small data sets, no preset target model is needed, and the time-varying rule of PM2.5 concentration value can be accurately described.

PM 2.5 concentration value prediction method based on hybrid neural network

A survey on dorsal hand vein biometrics

Adaptive finite-time backstepping control tracker for quadrotor UAV with model uncertainty and external disturbance

A Composite Adaptive Fault-Tolerant Attitude Control for a Quadrotor UAV with Multiple Uncertainties

The development of information technology has made it possible to replace traditional keys and passwords with biometric recognition. Among the various human recognition technologies, contactless palm-vein authentication is becoming increasingly popular because it is hygienic and safe. In the field of deep learning (DL), system security and multispectral compatibility are crucial issues that require outright solutions. One of the most widely investigated DL algorithms is the convolutional neural network (CNN), which has been proven to have strong feature extraction capability. However, the training of CNN requires large samples and thus entails a heavy computational load, resulting in high hardware and software costs. Therefore, this paper proposes an adaptive Gabor filter with enhanced imaging features and triplet loss function that captures sufficient palm-vein data. A multispectral palm database from the CASIA public database was employed in this study to analyze the proposed system. The experimental results show that the proposed method has a low recognition error rate of 0.0556% and uses only a few network parameters in a multispectral environment.

Contactless Multispectral Palm-Vein Recognition With Lightweight Convolutional Neural Network

Quad-rotor unmanned aerial vehicle (UAV) is a typical multiple-input-multiple-output underactuated system with couplings and nonlinearity. Usually, the flying environment is very complex, so that it is impossible for the UAV to avoid effects derived from disturbances and uncertainties. In order to improve the reliability of flight control, we established the dynamic model of quad-rotor UAV by Newton-Euler equation in unbalanced load conditions. Considering external disturbances in the attitude, a second-order sliding mode controller was designed with PID sliding mode surface and Extended State Observer (ESO). The simulation experiments have got good control performance, illustrating the effectiveness of our controller. Meanwhile, the controller was implemented in a quad-rotor UAV, which carried a pan-tilt camera for aerial photography. The actual flight experiments proved that this paper dealt with the high stabilization flight control problem for the quad-rotor UAV, which laid a good foundation for autonomous flight of the UAV.

A Second-Order Sliding Mode Controller of Quad-Rotor UAV Based on PID Sliding Mode Surface with Unbalanced Load

Some portions of dorsal hand may be occluded due to injuries, pigmentation, or tattoos, which significantly affects the performance of dorsal hand vein recognition systems. Biometric graph matching is a common shape-based feature extraction algorithm for vein recognition. However, this method does not consider edge attributes, which can provide additional discrimination ability. We present an improved biometric graph matching method that includes edge attributes for graph registration and a matching module to extract discriminating features. Moreover, we propose a recognition system for partially occluded dorsal hand vein. A database of normal hand vein images, three databases of images with artificially occluded dorsal hand vein with occlusions in different positions and ratios, and a database of images with tattooed hands are established to verify the validity of the proposed method. The experimental results demonstrated that the equal error rates and the accuracies were 0.0202 and 98.09% ± 0.28%, respectively for the normal hand vein images, 0.0453 and 96.58% ± 0.34%, respectively for images of artificially occluded dorsal hand vein with occlusion at all positions and area ratios (0 - 20%, mean occluded area ratio = 9.3%), and 0.0343 and 97.14% ± 0.29%, respectively for the images of tattooed hands.

/pdf/a-recognition-system-for-partially-occluded-dorsal-hand-vein-4lt4105ni6.pdf

A Recognition System for Partially Occluded Dorsal Hand Vein Using Improved Biometric Graph Matching

Provided is a classification method for metagenome contigs, pertaining to the technical field of bioinformatics analyses. The method is aimed at providing a classification method for contigs by utilizing an improved fuzzy c-average algorithm to solve imbalance of metagenome contigs. The method comprises following steps: assuming average coverage rate of c specifics, utilizing the improved fuzzy c-average algorithm to classify metagenome contigs based on the formula of determining the species number of metagenome contigs. The improved fuzzy c-average algorithm is utilized so that an improved algorithm is put forward on the basis of analyzing the underlying reason for poorer performance of imbalanced datasets with the conventional fuzzy c-average algorithm. The improved fuzzy c-average algorithm is capable of effectively improving defects of poor effect of a conventional method for imbalanced datasets and applied to the classification of contigs such that classification precision is greatly increased and a good foundation is provided for subsequent analyses of metagenome contigs.

Classification method for metagenome contigs

In order to extract better vein feathers, image preprocessing is necessary. So this paper propose a new approach to enhance images. The enhancement algorithm uses guided filter (GF) to process hand vein images. The guided filter is used as an edge-preserving smoothing operator. The guided filter enhancement algorithm is effective comparing with bilateral filter (BF), histogram equalization (HE), adaptive histogram equalization algorithm (AHE) and contrast limited adaptive histogram equalization (CLAHE). We use several methods to enhance dorsal hand vein images, the recognition rate with guided filter is the best. For the security, a fake vein detection algorithm is used to discriminate the real vein and fake vein images.

http://dpi-proceedings.com/index.php/dtcse/article/download/16030/15538

Dorsal Hand Vein Enhancement and Fake Vein Detection

The invention belongs to the field of control science and engineering, belongs to the field of environmental science and engineering, and relates to a soft sensing method of out-of-water TP (total phosphorus) for sewage treatment based on a reservoir network. Out-of-water TP concentration is an important monitoring index for urban sewage treatment plants and important index for water quality evaluation. In order to solve the problems, for example, out-of-water TP measurement process in current sewage treatment is complex, instrumentation and equipment are high in manufacture cost and high in maintenance cost and measurement results accuracy is low, the method of the invention employs principal component analysis to determine input variables of a soft sensing model; a reservoir structure optimizing algorithm based on contribution rate is designed, network structure is optimized, and network performance is improved; a soft sensing model of out-of-water TP is established based on a modified reservoir network to provide quick, effective and accurate measurement of out-of-water TP in sewage treatment, the level of real-time water quality monitoring is increased for urban sewage treatment plants, and normal treatment of urban sewage is guaranteed.

Shoukun Jiang

Papers

A Second-Order Sliding Mode Controller of Quad-Rotor UAV Based on PID Sliding Mode Surface with Unbalanced Load

A Recognition System for Partially Occluded Dorsal Hand Vein Using Improved Biometric Graph Matching

Classification method for metagenome contigs

Dorsal Hand Vein Enhancement and Fake Vein Detection

Soft sensing method of out-of-water TP (total phosphorus) for sewage treatment based on reservoir network