Zhanshan Li

ORCID: 0000-0003-1648-8138
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Constraint Satisfaction and Optimization
  • Data Management and Algorithms
  • Advanced Database Systems and Queries
  • AI-based Problem Solving and Planning
  • X-ray Diffraction in Crystallography
  • Crystallization and Solubility Studies
  • Scheduling and Timetabling Solutions
  • Domain Adaptation and Few-Shot Learning
  • Model-Driven Software Engineering Techniques
  • Rough Sets and Fuzzy Logic
  • Data Mining Algorithms and Applications
  • Text and Document Classification Technologies
  • Metaheuristic Optimization Algorithms Research
  • Advanced Image Fusion Techniques
  • Image and Signal Denoising Methods
  • Face and Expression Recognition
  • Crystallography and molecular interactions
  • Oxidative Organic Chemistry Reactions
  • Synthesis and Biological Evaluation
  • Catalytic C–H Functionalization Methods
  • Advanced Neural Network Applications
  • Bayesian Modeling and Causal Inference
  • Industrial Technology and Control Systems
  • Radical Photochemical Reactions
  • Machine Learning and ELM

Jilin University
2015-2024

Jilin Province Science and Technology Department
2011-2024

Jilin Medical University
2011-2023

Lanzhou University
2011-2013

Il-Yang Pharmaceutical (South Korea)
2011

Thermo Fisher Scientific (Japan)
2002

K-means algorithm is one of the most famous unsupervised clustering algorithms. Many theoretical improvements for performance original algorithms have been put forward, while almost all them are based on single instruction data (SISD) architecture processors (GPUs), which partly ignored inherent paralleled characteristic In this paper, a novel multiple (SIMD) (GPUs) k-means proposed. algorithm, in order to accelerate compute-intensive portions traditional k-means, both objects assignment and...

10.1109/csie.2009.491 article EN 2009-01-01

An efficient synthesis of quinoxalin-2(1H)-ones or spiro[cyclohexene-1,2'-imidazol]-4'-ones has been achieved in moderate to high yields by the visible light-induced and N-bromosuccinimide-mediated cyclization reaction 2-azido-N-phenylacetamides at ambient temperature. Both regioselectivity speed are affected substituents attached phenyl ring. For example, quinoxalin-2-ones produced as main products when substrates bear electron-withdrawing groups para-position ring; contrast, obtained...

10.1021/ol401338e article EN Organic Letters 2013-07-22

10.1016/j.eswa.2020.114490 article EN Expert Systems with Applications 2020-12-13

Binary butterfly optimization approach (bBOA) is a recent high performing feature selection algorithm presented in 2018 which based on the food foraging behavior of butterflies. This paper tries to improve structure bBOA enhance its classification accuracy, dimension reduction and reliability task for who are interested fields data mining pattern recognition. The new initialization strategy differential evolution applied reduce randomness bBOA's local search process. Then, parameter added...

10.1109/access.2020.2985986 article EN cc-by IEEE Access 2020-01-01

Crying serves as the primary means through which infants communicate, presenting a significant challenge for new parents in understanding its underlying causes. This study aims to classify infant cries ascertain reasons behind their distress. In this paper, an efficient graph structure based on multi-dimensional hybrid features is proposed. Firstly, are processed extract various speech features, such spectrogram, mel-scaled MFCC, and others. These then combined across multiple dimensions...

10.1016/j.kjs.2024.100221 article EN cc-by Kuwait Journal of Science 2024-03-26

Micro-expression recognition (MER) presents a significant challenge due to the transient and subtle nature of motion changes involved. In recent years, deep learning methods based on attention mechanisms have made some breakthroughs in MER. However, these still suffer from limitations insufficient feature capture poor dynamic adaptation when coping with instantaneous movement micro-expressions. Therefore, this paper, we design an Adaptive Hierarchical Multi-Scale Attention Network...

10.48550/arxiv.2501.02539 preprint EN arXiv (Cornell University) 2025-01-05

Feature selection is an important method to reduce the number of attributes high-dimensional data and essential preprocess work in classification. It eliminates irrelevant, redundant, noisy features improves performance model reduces computational burden. Fruit fly optimization algorithm a new proposed recent years, which imitates foraging behavior fruit fly. To best our knowledge, it has not been systematically applied feature selection. This paper uses as search strategy designs...

10.1109/access.2019.2917502 article EN cc-by-nc-nd IEEE Access 2019-01-01

10.1016/j.ins.2022.09.013 article EN Information Sciences 2022-09-11

Abstract An efficient synthesis of paullone and kenpaullone derivatives in moderate to high yields has been achieved through photocyclizations (2‐chloro‐1 H ‐indole‐3‐yl)‐ N ‐arylacetamides acetone at room temperature. Paullone have obtained easily by deprotection the photocyclization products.

10.1002/ejoc.201101508 article EN European Journal of Organic Chemistry 2011-12-21

A one-pot synthesis of indolo[2,3-<i>c</i>]quinolin-6(7<i>H</i>)-ones was achieved by sequential photocyclizations 3-(2-azidophenyl)-<i>N</i>-phenylacrylamides in moderate to high yields. The reactions proceeded via photochemical cyclization aryl azides form <i>N</i>-phenylindol-2-carbamides and subsequent 6π-electrocyclic reaction oxidative aromatization afford the corresponding indolo[2,3-<i>c</i>]quinolin-6(7<i>H</i>)-ones.

10.1055/s-0032-1317703 article EN Synlett 2012-12-05

A concise synthesis of 3-(1-alkenyl)isoindolin-1-ones and 5-(1-alkenyl)pyrrol-2-ones has been achieved by the coupling reactions N-acyliminium ions produced from 3-hydroxyisoindol-1-ones or 5-hydroxy-1-pyrrol-2-ones with unactivated olefins in presence BF(3)·OEt(2) at room temperature. For most olefins, afforded C(sp3)-C(sp2) cross-coupling products, but for α-methylstyrene 1-hexene, C(sp3)-C(sp3) products were obtained.

10.3762/bjoc.8.21 article EN cc-by Beilstein Journal of Organic Chemistry 2012-02-06

Simple Tabular Reduction algorithms (STR) work well to establish Generalized Arc Consistency (GAC) on positive table constraints. However, the existing STR are useless for negative In this work, we propose a novel algorithm and its improvement, which Our preliminary experiments performed some random instances certain benchmark instances. The results show that new outperform GAC-valid MDD-based GAC algorithm.

10.1609/aaai.v27i1.8519 article EN Proceedings of the AAAI Conference on Artificial Intelligence 2013-06-29
Coming Soon ...