Optimization of LSTM Ship Trajectory Prediction Based on Hybrid Genetic Algorithm

Accurate prediction of the movement trajectory of sea surface targets holds significant importance in achieving an advantageous position in the sea battle field.This prediction plays a crucial role in ensuring security defense and confrontation,and is essential for effective deployment of military strategy.Accurately predicting the trajectory of sea surface targets using AIS(Automatic Identification System)information is crucial for security defense and confrontation,and holds significant importance for military strategy deployment.In response to the problem of insufficient accuracy in ship trajectory prediction,this study proposes a hybrid genetic algorithm to optimize the Long Short-Term Memory(LSTM)algorithm.The HGA-LSTM algorithm is proposed for ship trajectory prediction.It can converge faster and obtain better parameter solutions,thereby improving the effectiveness of ship trajectory prediction.Compared to traditional LSTM and GA-LSTM algorithms,experimental results demonstrate that this algorithm outperforms them in both single-step and multi-step prediction.

Advancing Early Detection of Colorectal Adenomatous Polyps via Genetic Data Analysis: A Hybrid Machine Learning Approach

In this study, a hybrid machine learning (HML)-based approach, incorporating Genetic data analysis (GDA), is proposed to accurately identify the presence of adenomatous colorectal polyps (ACRP) which is a crucial early detector of colorectal cancer (CRC). The present study develops a classification ensemble model based on tuned hyperparameters. Surpassing accuracy percentages of early detection approaches used in previous studies, the current method exhibits exceptional performance in identifying ACRP and diagnosing CRC, overcoming limitations of CRC traditional methods that are based on error-prone manual examination. Particularly, the method demonstrates the following CRP identification accuracy data: 97.7 ± 1.1, precision: 94.3 ± 5, recall: 96.0 ± 3, F1-score: 95.7 ± 4, specificity: 97.3 ± 1.2, average AUC: 0.97.3 ± 0.02, and average p-value: 0.0425 ± 0.07. The findings underscore the potential of this method for early detection of ACRP as well as clinical use in the development of CRC treatment planning strategies. The advantages of this approach are highly expected to contribute to the prevention and reduction of CRC mortality.

Solar Radiation Estimation Based on a New Combined Approach of Artificial Neural Networks (ANN) and Genetic Algorithms (GA) in South Algeria

When designing solar systems and assessing the effectiveness of their many uses,estimating sun irradiance is a crucial first step.This study examined three approaches(ANN,GA-ANN,and ANFIS)for estimating daily global solar radiation(GSR)in the south of Algeria:Adrar,Ouargla,and Bechar.The proposed hybrid GA-ANN model,based on genetic algorithm-based optimization,was developed to improve the ANN model.The GA-ANN and ANFIS models performed better than the standalone ANN-based model,with GA-ANN being better suited for forecasting in all sites,and it performed the best with the best values in the testing phase of Coefficient of Determination(R=0.9005),Mean Absolute Percentage Error(MAPE=8.40%),and Relative Root Mean Square Error(rRMSE=12.56%).Nevertheless,the ANFIS model outperformed the GA-ANN model in forecasting daily GSR,with the best values of indicators when testing the model being R=0.9374,MAPE=7.78%,and rRMSE=10.54%.Generally,we may conclude that the initial ANN stand-alone model performance when forecasting solar radiation has been improved,and the results obtained after injecting the genetic algorithm into the ANN to optimize its weights were satisfactory.The model can be used to forecast daily GSR in dry climates and other climates and may also be helpful in selecting solar energy system installations and sizes.

Genetic analyses of ancient tea trees provide insights into the breeding history and dissemination of Chinese Assam tea(Camellia sinensis var.assamica)

Chinese Assam tea(Camellia sinensis var.assamica)is an important tea crop with a long history of cultivation in Yunnan,China.Despite its potential value as a genetic resource,its genetic diversity and domestication/breeding history remain unclear.To address this issue,we genotyped 469 ancient tea plant trees representing 26 C.sinensis var.assamica populations,plus two of its wild relatives(six and three populations of C.taliensis and C.crassicolumna,respectively)using 16 nuclear microsatellite loci.Results showed that Chinese Assam tea has a relatively high,but comparatively lower gene diversity(H_(S)=0.638)than the wild relative C.crassicolumna(H_S=0.658).Clustering in STRUCTURE indicated that Chinese Assam tea and its two wild relatives formed distinct genetic groups,with considerable interspecific introgression.The Chinese Assam tea accessions clustered into three gene pools,corresponding well with their geographic distribution.However,New Hybrids analysis indicated that 68.48%of ancient Chinese Assam tea plants from Xishuangbanna were genetic intermediates between the Puer and Lincang gene pools.In addition,10%of the ancient Chinese Assam tea individuals were found to be hybrids between Chinese Assam tea and C.taliensis.Our results suggest that Chinese Assam tea was domesticated separately in three gene pools(Puer,Lincang and Xishuangbanna)in the Mekong River valley and that the hybrids were subsequently selected during the domestication process.Although the domestication history of Chinese Assam tea in southwestern Yunnan remains complex,our results will help to identify valuable genetic resources that may be useful in future tea breeding programs.

Optimization of Multi-Execution Modes and Multi-Resource-Constrained Offshore Equipment Project Scheduling Based on a Hybrid Genetic Algorithm

Offshore engineering construction projects are large and complex,having the characteristics of multiple execution modes andmultiple resource constraints.Their complex internal scheduling processes can be regarded as resourceconstrained project scheduling problems(RCPSPs).To solve RCPSP problems in offshore engineering construction more rapidly,a hybrid genetic algorithmwas established.To solve the defects of genetic algorithms,which easily fall into the local optimal solution,a local search operation was added to a genetic algorithm to defend the offspring after crossover/mutation.Then,an elitist strategy and adaptive operators were adopted to protect the generated optimal solutions,reduce the computation time and avoid premature convergence.A calibrated function method was used to cater to the roulette rules,and appropriate rules for encoding,decoding and crossover/mutation were designed.Finally,a simple network was designed and validated using the case study of a real offshore project.The performance of the genetic algorithmand a simulated annealing algorithmwas compared to validate the feasibility and effectiveness of the approach.

Genetic Effects and Heterosis in Plant Height and Internode Traits of Japonica-Indica Hybrid Rice

[Objective] This study aimed to investigate the genetic effects and heterosis of plant height and internode traits of japonica-indica hybrid rice. [Methed] Incomplete diallel crosses were made between six japonica CMS lines and nine indica widecompatibility restorer lines; the genetic effects of plant height and internode traits of japonica-indica hybrid rice were analyzed using the additive-dominance genetic model. [Result] The ple, nt height, panicle length and the length of internode 1 of japonica-in- dica hybrid rice were mainly controlled by the additive effects; but the length of in- ternode 3, internode 4 and internode 5 were mainly controlled by dominance effects. Both the narrow sense heritability and broad sense heritability of plant height, panicle length, number of elongated internodes and length of most internodes reached signifi- cance level. The positive phenotypic correlation, genetic correlation, additive correla- tion and dominance correlation between plant height and panicle length, number of e- longated internodes and internode length were significant; and most of the other paired traits were significantly positively correlated. Heterosis analysis showed that the positive heterosis value over mid-parent and positive heterosis value over better- parent of the length of internode 3, internode 4, internode 5 and internode 6 reached significant level, and the heterosis value over mid-parent of plant height reached extreme significance level. [Conclusion] This study will provide reliable theoretical basis for the genetic improvement and heterosis utilization of plant height and internode traits in japonica-indica hybrid rice.

Changes in Agronomic Traits of Indica Hybrid Rice during Genetic Improvement

[Objective]The aim was to elucidate the changes of agronomical traits of indica hybrid rice during its genetic improvement.[Method]23 typical indica hybrid combinations cultivated in the middle and lower reaches of Yangtze River during the last 30 years were selected as experimental materials.All the hybrid rice combinations were grown in the same field;and then yield and morphological characters of single plant were compared;correlation and path analyses among agronomic characteristics were also conducted.[Result]During the 30 years of genetic improvement,the effective panicle number per plant was progressively decreased,which caused the decrease of grain yield and biomass per plant of hybrid rice combinations in spite of the slightly increased plant height,1 000-grain weight and number of grains per panicle.Although the transformation percentage of the matter in stem and sheath decreased after flowering,leave photosynthetic capacity after flowering was increased as panicle weight.Correlation and path analysis showed that although both biomass per plant and number of grains per panicle were significantly correlated with grain yield per plant,biomass per plant acted as the key factor affecting yield per plant.[Conclusion]It was suggested that in rice high yield cultivation,panicle number was as important as large panicle,and tillering ability should not be neglected in breeding.

Series-parallel Hybrid Vehicle Control Strategy Design and Optimization Using Real-valued Genetic Algorithm

Despite the series-parallel hybrid electric vehicle inherits the performance advantages from both series and parallel hybrid electric vehicle, few researches about the series-parallel hybrid electric vehicle have been revealed because of its complex co nstruction and control strategy. In this paper, a series-parallel hybrid electric bus as well as its control strategy is revealed, and a control parameter optimization approach using the real-valued genetic algorithm is proposed. The optimization objective is to minimize the fuel consumption while sustain the battery state of charge, a tangent penalty function of state of charge（SOC） is embodied in the objective function to recast this multi-objective nonlinear optimization problem as a single linear optimization problem. For this strategy, the vehicle operating mode is switched based on the vehicle speed, and an ＂optimal line＂ typed strategy is designed for the parallel control. The optimization parameters include the speed threshold for mode switching, the highest state of charge allowed, the lowest state of charge allowed and the scale factor of the engine optimal torque to the engine maximum torque at a rotational speed. They are optimized through numerical experiments based on real-value genes, arithmetic crossover and mutation operators. The hybrid bus has been evaluated at the Chinese Transit Bus City Driving Cycle via road test, in which a control area network-based monitor system was used to trace the driving schedule. The test result shows that this approach is feasible for the control parameter optimization. This approach can be applied to not only the novel construction presented in this paper, but also other types of hybrid electric vehicles.

Developmental Genetics Analysis for Plant Height in indica Hybrid Rice Across Environments

The developmental genetics of plant height was analyzed from two groups of three-line indica hybrid rice at two environmental conditions based on the NCII design, using the additive-dominant developmental genetics models and the statistic methods. The results showed that the rice genotypes and environmental conditions could both affect plant height, and the effects of environment on plant height decreased gradually with plant development. Additive and dominant effects both governed the performance of plant height at all developmental stages. However, the degrees of effect varied among the rice genotypes. Moreover, the interaction between environments and genotypes also affected plant height. The genetic effects differed at most developmental stages. Furthermore, the expressJon of additive effect was more active than that of dominant effect. Conditional interaction effects with environment also influenced plant height during genetic development, especially at the eady stage. Mid-parent heterosis （HMP） increased gradually with the developmental stage of plant height, and maximized at the latest stage, whereas the heterosis over the better parent （HBP） showed small differences among the genotypes, and kept stable at the later stage, with positive numeric value. At most developmental stages, conditional HMP was positively significant, while conditional HBP was negatively significant. All above results suggest that HMP and HBP have some new expressions in all developmental periods and the levels and directions are quite different.

Identification of vibration loads on hydro generator by using hybrid genetic algorithm

Vibration dynamic characteristics have been a major issue in the modeling and mechanical analysis of large hydro generators. An algorithm is developed for identifying vibration dynamic characteristics by means of hybrid genetic algorithm. From the measured dynamic responses of a hydro generator, an appropriate estimation algorithm is needed to identify the loading parameters, including the main frequencies and amplitudes of vibrating forces. In order to identify parameters in an efficient and robust manner, an optimization method is proposed that combines genetic algorithm with simulated annealing and elitist strategy. The hybrid genetic algorithm is then used to tackle an ill-posed problem of parameter identification, in which the effectiveness of the proposed optimization method is confirmed by its comparison with actual observation data.

Genetic variation in distant and inbred hybridization progenies from three sympodial bamboo parent species

To achieve germplasm innovation and study genetic variation of important traits of bamboo plants,we used Bambusa multiplex,B.chungii,and Dendrocalamus latiflorus as parent materials for distant and inbred hybridizations.Two hybrid populations and three inbred populations were obtained:two populations consisted of 57 hybrid progenies from B.multiplex 9 B.chungii,26 hybrid progenies from B.multiplex 9 D.latiflorus,and three inbred progenies were from B.multiplex,B.chungii,and D.latiflorus.Traits for growth,morphology,and fiber were examined from the five populations when plants were 3 years old.Two hybrid populations had significant growth advantages in terms of height,diameter at ground level and internodal length.In terms of variability in morphological traits,the two hybrid populations followed the same trend,namely,seven morphological traits showed phenotypes that were intermediate to those of their parents;three morphological traits showed strong maternal effects,and three other morphological traits showed strong paternal effects.Among the five populations,the two hybrid populations had high arithmetic average fiber length,lengthweighted average fiber length and mass-weighted average fiber length,moreover,extensive variations of these three traits were observed within these two hybrid populations.The establishment of distant hybrid populations from these three bamboo species increased the genetic diversity more than in the other species examined.This work provides excellent materials for breeding new varieties and lays the foundation for understanding the genetics of important traits by analyzing related functional genes.

Genetic Diversity of Tropical Hybrid Rice Germplasm Measured by Molecular Markers

Investigation of genetic diversity and relationships among breeding lines is of great importance to facilitate parent selection in hybrid rice breeding programs.In this study,we characterized 168 hybrid rice parents from International Rice Research Institute with 207 simple sequence repeat （SSR） and 353 single nucleotide polymorphism （SNP） markers.A total of 1 267 SSR and 706 SNP alleles were detected with the averages of 6.1 （SSR） and 2.0 （SNP） alleles per locus respectively across all lines.Based on the genetic distances estimated from the SSR and SNP markers separately and combined,the unrooted neighbor-joining cluster and STRUCTURE analyses consistently separated the 168 hybrid rice parents into two major groups：B-line and R-line,which is consistent with known parent pedigree information.The genetic distance matrices derived from the SSR and SNP genotyping were highly correlated （r=0.81,P 0.001）,indicating that both of the SSR and SNP markers have distinguishable power to detect polymorphism and are appropriate for genetic diversity analysis among tropical hybrid rice parents.A subset of 60 SSR markers were also chosen by the Core Hunter with 368 alleles,and the cluster analysis based on the total and subset of SSR markers highly corresponded at r=0.91 （P 0.001）,suggesting that fewer SSR markers can be used to classify and evaluate genetic diversity among parental lines.

A Multi-Objective Hybrid Genetic Based Optimization for External Beam Radiation

A multi-objective hybrid genetic based optimization algorithm is proposed according to the multi-objective property of inverse planning. It is based on hybrid adaptive genetic algorithm which combines the simulated annealing, uses adaptive crossover and mutation, and adopts niched tournament selection. The result of the test calculation demonstrates that an excellent converging speed can be achieved using this approach.

Genetic Relationships in Advanced Generation Hybrids Derived from Crosses between Texas (<i>Poa arachnifera</i>) and Kentucky (<i>Poa pratensis</i>) Bluegrass Using ISSR Markers

Fertile, advanced generation hybrids derived from crosses between Texas (Poa arachnifera Torr.) and Kentucky (Poa pratensis L.) bluegrass have been selected. The hybrids are currently being evaluated for low-input turf potential. Since they are derived from hand-harvested seed from first-generation hybrids located in field nurseries their exact genetic origin is unknown. This experiment was conducted to determine if there are still genetic relationships among the advanced generation hybrids and some of the Texas and Kentucky parents in their pedigrees. Four Inter Simple Sequence Repeat (ISSR) primer combinations resolved on 6% nondenaturing polyacrylamide gels resulted in 179 polymorphic bands that were scored to create a genetic similarity matrix and dendrogram based on Jaccard’s coefficient. The clustering of the advanced generation hybrids was generally in agreement with what would be expected based on their pedigrees and indicated it was more likely to select a fertile hybrid from an advanced generation, rather than the F1 generation.

Relationship Between Hybrid Performance and Genetic Diversity Based on SSRs and ISSRs in Brassica napus L.

To investigate the relationship between genetic distance (GD) and hybrid performance, two types of molecular markers, microsatellites (simple sequence repeats, SSRs) and intro-simple sequence repeats (ISSRs), were employed to detect the genetic diversity of 3 double low self-incompatible lines and 22 male parental varieties of Brassica napus from different geographical origins. Hybrids were produced in a NCⅡ mating design by hand-pollination. The result indicated that 25 parental varieties (lines) could be divided into six groups by Un-weighted Pair Group Mathematics Average (UPGMA) clustering based on GDs. SI-1300 and SI-1320 could be singly clustered into one group, respectively. Varieties from China could be separated into another group, SI-1310 and varieties from foreign countries could be separated into other three groups. The grouping was generally consistent with parental pedigrees and geographical origins. Significant differences in yield, quality and phenological period traits were observed among these parent groups. Although hybrid yield/plant showed significantly positive correlation with genetic distance based on SSR and ISSR markers, but the determination coefficient was low. It appeared to be unsuitable for using the genetic distance based on SSR and ISSR markers to predict heterosis and hybrid performance in Brassica napus.

Genetic Diversity among Parents of Hybrid Rice Based on Cluster Analysis of Morphological Traits and Simple Sequence Repeat Markers

The genetic diversity of 41 parental lines popularized in commercial hybrid rice production in China was studied by using cluster analysis of morphological traits and simple sequence repeat （SSR） markers. Forty-one entries were assigned into two clusters （i.e. early or medium-maturing cluster; medium or late-maturing cluster） and further assigned into six sub-clusters based on morphological trait cluster analysis, The early or medium-maturing cluster was composed of 15 maintainer lines, four early-maturing restorer lines and two thermo-sensitive genic male sterile lines, and the medium or late-maturing cluster included 16 restorer lines and 4 medium or late-maturing maintainer lines. Moreover, the SSR cluster analysis classified 41 entries into two groups （i.e, maintainer line group and restorer line group） and seven sub-groups. The maintainer line group consisted of all 19 maintainer lines, two thermo-sensitive genic male sterile lines, while the restorer line group was composed of all 20 restorer lines. The SSR analysis fitted better with the pedigree information. From the views on hybrid rice breeding, the results suggested that SSR analysis might be a better method to study the diversity of parental lines in indica hybrid rice.

Genetics and Improvement of Bacterial Blight Resistance of Hybrid Rice in China

Since 1980s, rice breeding for resistance to bacterial blight has been rapidly progressing in China. The gene Xa4 was mainly used in three-line indica hybrid and two-line hybrid rice. The disease has been ＇quiet＇ for 20 years in China, yet in recent years it has gradually emerged and been prevalent in fields planted with newly released rice varieties in the Changjiang River valley. Under the circumstances, scientists inevitably raised several questions： what causes the resurgence and what should we do next？ And/or is resistance breeding still one of the main objectives in rice improvement？ Which approach do we take on resistance breeding so that the resistance will be more durable, and the resistance gene will be used more efficiently？ A combined strategy involving traditional method, molecular marker-assisted selection, and transgenic technology should bring a new era to the bacterial blight resistance hybrid rice breeding program. This review also briefly discusses and deliberates on issues related to the broadening of bacterial blight resistance, and suitable utilization of resistance genes, alternate planting of available resistance genes; and understands the virulent populations of the bacterial pathogen in China even in Asia.

Analysis of drought tolerance and genetic and epigenetic variations in a somatic hybrid between Ipomoea batatas (L.) Lam. and I. triloba L.

The somatic hybrid KT1 was previously obtained from protoplast fusion between sweetpotato （Ipomoea batatas （L.） Lam.） cv. Kokei No. 14 and its wild relative I. triloba L. However, its genetic and epigenetic variations have not been investigated. This study showed that KT1 exhibited significantly higher drought tolerance compared to the cultivated parent Kokei No. 14. The content of proline and activities of superoxide dismutase （SOD） and photosynthesis were significantly increased, while malonaldehyde （MDA） content was significantly decreased compared to Kokei No. 14 under drought stress. KT1 also showed higher expression level of well-known drought stress-responsive genes compared to Kokei No. 14 under drought stress. Amplified fragment length polymorphism （AFLP） and methylation-sensitive amplified polymorphism （MSAP） analyses indicated that KT1 had AFLP and MSAP band patterns consisting of both parent specific bands and changed bands. Fur- ther analysis demonstrated that in KT1. the proportions of Kokei No. 14 specific genome components and methylation sites were much greater than those of I. triloba. KT1 had the same chloroplast and mitochondrial genomes as Kokei No. 14. These results will aid in developing the useful genes ofI. triloba and understanding the evolution and phylogeny of the cultivated sweetpotato.

Optimization of the seismic processing phase-shift plus finite-difference migration operator based on a hybrid genetic and simulated annealing algorithm

Although the phase-shift seismic processing method has characteristics of high accuracy, good stability, high efficiency, and high-dip imaging, it is not able to adapt to strong lateral velocity variation. To overcome this defect, a finite-difference method in the frequency-space domain is introduced in the migration process, because it can adapt to strong lateral velocity variation and the coefficient is optimized by a hybrid genetic and simulated annealing algorithm. The two measures improve the precision of the approximation dispersion equation. Thus, the imaging effect is improved for areas of high-dip structure and strong lateral velocity variation. The migration imaging of a 2-D SEG/EAGE salt dome model proves that a better imaging effect in these areas is achieved by optimized phase-shift migration operator plus a finite-difference method based on a hybrid genetic and simulated annealing algorithm. The method proposed in this paper is better than conventional methods in imaging of areas of high-dip angle and strong lateral velocity variation.

APPLICATION OF HYBRID GENETIC ALGORITHM IN AEROELASTIC MULTIDISCIPLINARY DESIGN OPTIMIZATION OF LARGE AIRCRAFT

The genetic/gradient-based hybrid algorithm is introduced and used in the design studies of aeroelastic optimization of large aircraft wings to attain skin distribution,stiffness distribution and design sensitivity.The program of genetic algorithm is developed by the authors while the gradient-based algorithm borrows from the modified method for feasible direction in MSC/NASTRAN software.In the hybrid algorithm,the genetic algorithm is used to perform global search to avoid to fall into local optima,and then the excellent individuals of every generation optimized by the genetic algorithm are further fine-tuned by the modified method for feasible direction to attain the local optima and hence to get global optima.Moreover,the application effects of hybrid genetic algorithm in aeroelastic multidisciplinary design optimization of large aircraft wing are discussed,which satisfy multiple constraints of strength,displacement,aileron efficiency,and flutter speed.The application results show that the genetic/gradient-based hybrid algorithm is available for aeroelastic optimization of large aircraft wings in initial design phase as well as detailed design phase,and the optimization results are very consistent.Therefore,the design modifications can be decreased using the genetic/gradient-based hybrid algorithm.