A5029995116- Natural Language Processing Techniques
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Handwritten Text Recognition Techniques
- Complex Network Analysis Techniques
- Advanced Text Analysis Techniques
- Data Management and Algorithms
- Adversarial Robustness in Machine Learning
- Meteorological Phenomena and Simulations
- Gait Recognition and Analysis
- Advanced Computing and Algorithms
- Advanced Computational Techniques and Applications
- Traffic Prediction and Management Techniques
- Face and Expression Recognition
- Data Mining Algorithms and Applications
- CCD and CMOS Imaging Sensors
- Hydrological Forecasting Using AI
- Energy Load and Power Forecasting
- Face recognition and analysis
- Rough Sets and Fuzzy Logic
- Vehicle License Plate Recognition
- Video Surveillance and Tracking Methods
- Biomedical Text Mining and Ontologies
- Image Processing and 3D Reconstruction
- Time Series Analysis and Forecasting
Inner Mongolia University of Technology
2019-2025
Serious information loss often occurs when the input data undergoes layer-by-layer feature extraction process through deep neural networks. In small-target detection tasks, this problem becomes more serious. The existing theory holds that bottleneck leads to decrease of an algorithm's recognition rate. order improve precision recognition, PGI-ViMamba is proposed in paper resist attenuation a network model. model mainly uses Multi-Level Attention-Gated Programmable Gradient Information (MLAG...
Writing is an important carrier of cultural inheritance, and the digitization handwritten texts effective means to protect national culture. Compared Chinese English handwriting recognition, research on Mongolian recognition started relatively late achieved few results due characteristics script itself lack corpus. First, according characters, random erasing data augmentation algorithm was modified, a dual (DDA) proposed by combining improved with horizontal wave transformation (HWT) augment...
With the development of natural language processing and neural machine translation, translation method end-to-end (E2E) network model has gradually become focus research because its high accuracy strong semantics translation. However, there are still problems such as limited vocabulary low loyalty, etc. In this paper, discriminant Conditional Random Field (CRF) were used to segment label stem affixes Mongolian in preprocessing stage Mongolian-Chinese bilingual corpus. Aiming at loyalty...
Neural machine translation (NMT) is a data-driven approach that has proven its superiority in large corpora, but it still much room for improvement when the corpus resources are not abundant. This work aims to improve quality of Traditional Mongolian-Chinese (MN-CH). First, baseline model constructed based on Transformer model, and then two different syntax-assisted learning units added encoder decoder. Finally, encoder’s ability learn Mongolian syntax implicitly strengthened, knowledge...
The core challenge of speech synthesis technology is how to convert text information into an audible audio form meet the needs users. In recent years, quality based on end-to-end models has been significantly improved. However, due characteristics Mongolian language and lack corpus, model achieved few results, there are still some problems with performance quality. First, phoneme was further improved a Bang-based pre-training constructed reduce error rate phonetic synthesized words. Second,...
Weather forecasting is an important factor affecting production and life. With the development of technology, weather methods such as map forecasting, numerical quantitative have emerged. However, these traditional data analysis shortcomings incomplete analysis, insufficient objectivity, inability to quantitatively predict weather, low prediction accuracy. The import neural networks into field helps alleviate above improve accuracy forecasting. In this paper, LSTM network CNN are used...
HotSpot is an algorithm that can directly mine association rules from real data. Aiming at the problem support threshold in cannot be set accurately according to actual scale of dataset and needs artificially experience, this paper proposes a dynamic optimization with minimum setting: S_HotSpot algorithm. The combines simulated annealing uses global search ability dynamically optimize solution space. Finally, Inner Mongolia sandstorm used for experiment while wine quality verification,...