Multi-feature Optimization Research Articles

Extracting winter wheat based on multi-feature optimization of short-time series synthetic aperture radar data with dual polarizations

Extracting winter wheat based on multi-feature optimization of short-time series synthetic aperture radar data with dual polarizations

Generating Radiology Reports via Multi-feature Optimization Transformer

Generating Radiology Reports via Multi-feature Optimization Transformer

Urban land use land cover classification based on GF-6 satellite imagery and multi-feature optimization

Urban land use/land cover (LULC) classification has long been a hotspot for remote sensing applications. With high spatio-temporal resolution and multispectral, the recently launched GF-6 satellite provides ideal open imagery for LULC mapping. In this study, we utilized multitemporal GF-6 images to generate six types of land features, including spectral bands, texture features, built-up, waterbody, vegetation, and red-edge indices. The minimum Redundancy Maximum Relevance (mRMR) algorithm was employed to optimize feature selection. Subsequently, Random Forest (RF) and Extreme Gradient Boosting (XGBT) were assessed using different feature selections. Besides, various feature configurations were designed for LULC classification and comparison. The results indicate that the mRMR-based RF method achieved the highest overall accuracy of 91.37%. The temporal red-edge indices were important features for urban LULC classification and contributed mainly to grassland and cropland. These results supplement existing classification methods and assist in improving LULC mapping in urban areas with complex landscapes.

Multi-feature Optimization of a Gas Sensor Array to Improve Component and Concentration Detection Performance of VOC Mixtures

Many studies focus on feature extraction and selection of gas sensor arrays for gas identification. In this work, we intended to find a feature subset obtained by selecting the most important features for simultaneously improving component and concentration detection performance of a gas sensor array to three harmful VOCs (toluene, methanol, and ethanol) and their mixtures. First, 30 features were extracted from 6 sensors’ responses to form a multi-feature set. Then, two feature selection methods based on Wilks’ Λ-statistic and random forest were employed to obtain the best feature combination. Seven out of 30 features were finally selected to form the optimal feature set. The gas identification accuracy is 94.3%, and the concentration estimation error is 0.79 ppm (RMSE). Through feature selection, not only qualitative and quantitative analyses performance of VOCs mixtures are significantly improved, but also system complexity (6 to 4 sensors) and computation cost (by about 15%) are effectively reduced.

Health prognosis for lithium-ion battery with multi-feature optimization

With the widespread use of lithium-ion batteries, battery failure will bring serious safety problems and economic losses. State of health (SOH) is a key and challenging issue in the prognostics and health management of lithium-ion batteries. In this paper, we propose a new SOH estimation method for lithium-ion batteries with multi-feature optimization. Firstly, we obtain the initial feature set by sampling the voltage curve and incremental capacity curve to comprehensively describe the battery aging process. Then, the Gaussian process regression model is improved by designing a dual kernel to track the long-term battery aging process with dynamic fluctuations. Finally, we introduce a genetic algorithm to optimize the SOH estimator establishing process by considering the estimation accuracy, the number of features, and the difficulty of feature acquisition. To verify the effectiveness of the proposed method, commercial batteries are tested under different charging and discharging conditions. The experimental results show that the proposed method with multi-feature optimization can achieve a prediction error of less than 0.6%.

Multi-Feature Optimization Study of Soil Total Nitrogen Content Detection Based on Thermal Cracking and Artificial Olfactory System

To improve the accuracy of detecting soil total nitrogen (STN) content by an artificial olfactory system, this paper proposes a multi-feature optimization method for soil total nitrogen content based on an artificial olfactory system. Ten different metal–oxide semiconductor gas sensors were selected to form a sensor array to collect soil gas and generate response curves. Additionally, six features such as the response area, maximum value, average differential coefficient, standard deviation value, average value, and 15th-second transient value of each sensor response curve were extracted to construct an artificial olfactory feature space (10 × 6). Moreover, the relationship between feature space and soil total nitrogen content was used to establish backpropagation neural network (BPNN), extreme learning machine (ELM), and partial least squares regression (PLSR) models were used, and the coefficient of determination (R2), root mean square error (RMSE), and the ratio of performance to deviation (RPD) were selected as prediction performance indicators. The Monte Carlo cross-validation (MCCV) and K-means improved leave-one-out cross-validation (K-means LOOCV) were adopted to identify and remove abnormal samples in the feature space and establish the BPNN model, respectively. There were significant improvements before and after comparing the two rejection methods, among which the MCCV rejection method was superior, where values for R2, RMSE, and RPD were 0.75671, 0.33517, and 1.7938, respectively. After removing the abnormal samples, the soil samples were then subjected to feature-optimized dimensionality reduction using principal component analysis (PCA) and genetic algorithm-based optimization backpropagation neural network (GA-BP). The test results showed that after feature optimization the model indicators performed better than those of the unoptimized model, and the PLSR model with GA-BP for feature optimization had the best prediction effect, with an R2 value of 0.93848, RPD value of 3.5666, and RMSE value of 0.16857 in the test set. R2 and RPD values improved by 14.01% and 50.60%, respectively, compared with those before optimization, and RMSE value decreased by 45.16%, which effectively improved the accuracy of the artificial olfactory system in detecting soil total nitrogen content and could achieve more accurate quantitative prediction of soil total nitrogen content.

Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images

Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images

Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM.

The number of wheat ears in the field is very important data for predicting crop growth and estimating crop yield and as such is receiving ever-increasing research attention. To obtain such data, we propose a novel algorithm that uses computer vision to accurately recognize wheat ears in a digital image. First, red-green-blue images acquired by a manned ground vehicle are selected based on light intensity to ensure that this method is robust with respect to light intensity. Next, the selected images are cut to ensure that the target can be identified in the remaining parts. The simple linear iterative clustering method, which is based on superpixel theory, is then used to generate a patch from the selected images. After manually labeling each patch, they are divided into two categories: wheat ears and background. The color feature “Color Coherence Vectors,” the texture feature “Gray Level Co-Occurrence Matrix,” and a special image feature “Edge Histogram Descriptor” are then exacted from these patches to generate a high-dimensional matrix called the “feature matrix.” Because each feature plays a different role in the classification process, a feature-weighting fusion based on kernel principal component analysis is used to redistribute the feature weights. Finally, a twin-support-vector-machine segmentation (TWSVM-Seg) model is trained to understand the differences between the two types of patches through the features, and the TWSVM-Seg model finally achieves the correct classification of each pixel from the testing sample and outputs the results in the form of binary image. This process thus segments the image. Next, we use a statistical function in Matlab to get the exact a precise number of ears. To verify these statistical numerical results, we compare them with field measurements of the wheat plots. The result of applying the proposed algorithm to ground-shooting image data sets correlates strongly (with a precision of 0.79–0.82) with the data obtained by manual counting. An average running time of 0.1 s is required to successfully extract the correct number of ears from the background, which shows that the proposed algorithm is computationally efficient. These results indicate that the proposed method provides accurate phenotypic data on wheat seedlings.

Multi-Feature Optimization of WEDM for Ti-6Al-4V by Applying a Hybrid Approach of Utility Theory Integrated With the Principal Component Analysis

In this study, multi-feature optimization is performed using a hybrid approach of utility theory (UT) combined with the principal component analysis (PCA) during wire electrical discharge machining (WEDM) of Ti-6Al-4V. Taguchi's L27 orthogonal collection is used to evaluate the effects of the pulse on time, pulse off time, peak current, servo voltage, wire feed rate and cable tension on surface roughness (SR), overcut and metal removal rate (MRR). The utility concept is employed to turn the multi-feature problem into a distinct equivalent feature called as overall efficiency index (OEI). Optimal sets of governing parameters using a hybrid approach are established as the pulse on time 114 machine unit, pulse off time 55 machine unit, servo voltage 20 volts, peak current 190 Amp., wire feed rate 5 m/min and cable tension 2 device unit. Scanning Electron Microscopic (SEM) analysis of cut surfaces shows a lump of debris, microvoids, micro-cracks, and large dark craters at high values of the pulse on time.

Face Recognition Based on Multi-feature Optimization Fusion of LBP， LPQ and Gabor with Multi-scale Blocks

Face Recognition Based on Multi-feature Optimization Fusion of LBP， LPQ and Gabor with Multi-scale Blocks

Global cultivated land mapping at 30 m spatial resolution

Abstract Cultivated land is one of the most important types of land cover in the global mapping of land cover, and its variation influences economic development, food security, and ecological environment protection. Existing products of global cultivated land mapping have a low resolution, and high spatial resolution products are in demand. This study uses global remote sensing image datasets in 2000/2010 with a spatial resolution of 30 m (Landsat TM/ETM+, HJ-1), MODIS 250 m NDVI time-serial data, and many types of reference data. An three-layer extraction method based on pixels, objects, and knowledge (POK) was adopted to ease cultivated land extraction in global-scale 30 m images, i.e., cultivated land classification based on pixel-scale multi-feature optimization, cultivated land automatic identification based on objects, and interactive object processing based on information service and priori knowledge. Global 30 m cultivated land mapping was accomplished for the two reference years (2000 and 2010), and statistical analysis was conducted on the data. Results showed that the total cultivated land area was 1.903 billion ha and 1.960 billion ha, respectively. Accuracy assessments showed that overall accuracy of global cultivated land mapping are higher than 92% for both the two reference years. The global cultivated land products in 2000/2010 developed in this research are superior to their international counterparts in terms of spatial resolution and classification accuracy. They also provide significant basic data on global food security, ecological environment supervision, and global change.

An Optimization Clustering Algorithm Based on Texture Feature Fusion for Color Image Segmentation

We introduce a multi-feature optimization clustering algorithm for color image segmentation. The local binary pattern, the mean of the min-max difference, and the color components are combined as feature vectors to describe the magnitude change of grey value and the contrastive information of neighbor pixels. In clustering stage, it gets the initial clustering center and avoids getting into local optimization by adding mutation operator of genetic algorithm to particle swarm optimization. Compared with well-known methods, the proposed method has an overall better segmentation performance and can segment image more accurately by evaluating the ratio of misclassification.

Role of conservative mutations in protein multi-property adaptation

Protein physicochemical properties must undergo complex changes during evolution, as a response to modifications in the organism environment, the result of the proteins taking up new roles or because of the need to cope with the evolution of molecular interacting partners. Recent work has emphasized the role of stability and stability–function trade-offs in these protein adaptation processes. In the present study, on the other hand, we report that combinations of a few conservative, high-frequency-of-fixation mutations in the thioredoxin molecule lead to largely independent changes in both stability and the diversity of catalytic mechanisms, as revealed by single-molecule atomic force spectroscopy. Furthermore, the changes found are evolutionarily significant, as they combine typically hyperthermophilic stability enhancements with modulations in function that span the ranges defined by the quite different catalytic patterns of thioredoxins from bacterial and eukaryotic origin. These results suggest that evolutionary protein adaptation may use, in some cases at least, the potential of conservative mutations to originate a multiplicity of evolutionarily allowed mutational paths leading to a variety of protein modulation patterns. In addition the results support the feasibility of using evolutionary information to achieve protein multi-feature optimization, an important biotechnological goal.

Super-proteins From Fitness-threshold Selection Statistics

It is in principle possible to assign a fitness value (organism reproductive rate) to every sequence of any given protein. The resulting fitness landscape can be regarded as the convolution of two mappings: one from genotype to phenotype with another mapping from phenotype to fitness. Despite this intrinsic complexity, we may expect organism fitness to depend on protein properties bearing upon catalysis, interactions with other molecules, stability, et cetera. However, the specific relation between fitness, sequence space, evolution and protein molecular properties is not understood, a fact which hampers efforts to tap the enormous potential for protein and organism engineering contained in the exponentially-growing sequence databases. Here we show that a simple evolutionary hypothesis on the statistics of purifying natural selection over a fitness threshold is operational and leads to protein multi-feature optimization. We thus obtain variants of E. coli thioredoxin showing simultaneous, large-scale optimizing modulations in stability, folding/unfolding kinetics, bulk-solvent oxidoreductase activity and the two chemically and evolutionary different mechanisms of enzymatic catalysis revealed by single-molecule force clamp spectroscopy. Furthermore, preliminary experiments suggest that these variants may induce in-vivo resistance to thermal and oxidative stresses. We anticipate, therefore, applications in fields that involve organism engineering (microbial biotechonology, synthetic biology).

Fuzzy linear-weight transformation simplex method and its application to a chemiluminescence method

The fuzzy linear-weight transformation simplex method is designed for multi-feature optimization. The mathematical principle is described. The fuzzy relation matrix is developed on the basis of membership functions, which are expressed here as a set of linear equations. The features to be optimized are weighted according to the needs of the user. The Basic program is operated on an Apple-II or compatible computer. The method is applied to select the optimum reaction conditions for the 1,10-phenanthroline/H 2O 2/CTMAB/Cu 2+ chemiluminescence system.