A5100728740- Machine Learning in Bioinformatics
- RNA and protein synthesis mechanisms
- Genomics and Phylogenetic Studies
- Horticultural and Viticultural Research
- Fungal and yeast genetics research
- Fermentation and Sensory Analysis
- Advanced Clustering Algorithms Research
- Remote Sensing in Agriculture
- Complex Network Analysis Techniques
- Date Palm Research Studies
- Gene expression and cancer classification
- Microplastics and Plastic Pollution
- Leaf Properties and Growth Measurement
- Spectroscopy and Chemometric Analyses
- Biochemical and Structural Characterization
- Genetics, Bioinformatics, and Biomedical Research
- Phytochemical and Pharmacological Studies
- Smart Agriculture and AI
- Face and Expression Recognition
- Bioinformatics and Genomic Networks
- Metabolomics and Mass Spectrometry Studies
- Microbial Metabolic Engineering and Bioproduction
Nanjing Agricultural University
2016-2024
Different cultivars of pear trees are often planted in one orchard to enhance yield for its gametophytic self-incompatibility. Therefore, an accurate and robust modelling method is needed the non-destructive determination leaf nitrogen (N) concentration orchards with mixed cultivars. This study proposes a new technique based on in-field visible-near infrared (VIS-NIR) spectroscopy Adaboost algorithm initiated machine learning methods. The performance was evaluated by estimating N total 1285...
k-Means clustering algorithm is widely used in many machine learning tasks. However, the classic has poor performance on classification of non-convex data sets. We find that effect depends heavily measurement similarity between instances datasets. In novel algorithm, we define new distance scalable spatial density sets, and propose a cluster-center iterative model algorithm. Experimental results show compared with Euclidean based k-Means, our proposed generally perform more accurate several...
The prediction of apoptosis protein subcellular localization plays an important role in understanding the progress cell proliferation and death. Recently computational approaches to this issue have become very popular, since traditional biological experiments are so costly time-consuming that they cannot catch up with growth rate sequence data anymore. In order improve accuracy localization, we proposed a sparse coding method combined feature extraction algorithm complete representation...
In order to provide a theoretical basis for better understanding the function and properties of proteins, we proposed simple effective feature extraction method protein sequences determine subcellular localization proteins. First, introduced sparse coding combined with information amino acid composition extract values sequences. Then multilayer pooling integration was performed according different sizes dictionaries. Finally, extracted were sent into support vector machine test effectiveness...
Adaboost algorithm with improved K-nearest neighbor classifiers is proposed to predict protein subcellular locations. Improved classifier uses three sequence feature vectors including amino acid composition, dipeptide and pseudo composition of sequence. Blast in classification stage. The overall success rates by the jackknife test on two data sets CH317 Gram1253 are 92.4% 93.1%. novel an effective method for predicting locations proteins.基于Adaboost 算法对多个相似性比对K 最近邻 (K-nearest neighbor，KNN)...
Protein subcellular location prediction is an important problem in bioinformatics. It highly desirable to predict a protein's from its sequence. We propose novel model combined with locality-sensitive hashing (LSH)-based approximate nearest neighbor searching (ANNS) and global alignment dynamic programming algorithm. LSH was used hash map protein sequence amino acid composition vector features, where sequences similar features were placed into bucket of corresponding key values table. Then,...