A5028943091- Natural Language Processing Techniques
- Topic Modeling
- Reproductive Biology and Fertility
- Sperm and Testicular Function
- Advanced Text Analysis Techniques
- Text and Document Classification Technologies
- Ovarian function and disorders
- Data Mining Algorithms and Applications
- Data Management and Algorithms
- Speech Recognition and Synthesis
- Speech and dialogue systems
- Semantic Web and Ontologies
- Sentiment Analysis and Opinion Mining
- Linguistics and Discourse Analysis
- Face and Expression Recognition
- Text Readability and Simplification
- Child and Animal Learning Development
- Geographic Information Systems Studies
- Genetic and phenotypic traits in livestock
- Multimodal Machine Learning Applications
- Algorithms and Data Compression
- Authorship Attribution and Profiling
- Machine Learning and Algorithms
- Reproductive Health and Technologies
- Advanced Manufacturing and Logistics Optimization
University of Guilan
2015-2024
Laboratoire d’Informatique Fondamentale de Marseille
2011-2016
Sharif University of Technology
2008-2011
Abstract Objectives This study aimed to assess the efficacy of deep learning applications for detection nasal bone fracture on X-ray lateral view. Methods In this retrospective observational study, 2,968 views trauma patients were collected from a radiology center, and randomly divided into training, validation, test sets. Preprocessing included noise reduction by using Gaussian filter image resizing. Edge was performed Canny edge detector. Feature extraction conducted gray-level...
Sentiment Analysis (SA) is a major field of study in natural language processing, computational linguistics and information retrieval. Interest SA has been constantly growing both academia industry over the recent years. Moreover, there an increasing need for generating appropriate resources datasets particular low resource languages including Persian. These play important role designing developing opinion mining platforms using supervised, semi-supervised or unsupervised methods. In this...
This paper focuses on how to extract opinions over each Persian sentence-level text. Deep learning models provided a new way boost the quality of output. However, these architectures need feed big annotated data as well an accurate design. To best our knowledge, we do not merely suffer from lack well-annotated sentiment corpus, but also novel model classify in terms both multiple and binary classification. So this work, first propose two deep comprises bidirectional LSTM CNN. They are part...
Sperm Morphology Analysis (SMA) is pivotal in diagnosing male infertility. However, manual analysis subjective and time-intensive. Artificial intelligence presents automated alternatives, but hurdles like limited data image quality constraints hinder its efficacy. These challenges impede Deep Learning (DL) models from grasping crucial sperm features. A solution enabling DL to learn sample nuances, even with data, would be invaluable. This study proposes a Knowledge Distillation (KD) method...
Online scientific communities are bases that publish books, journals, and papers, help promote knowledge. The researchers use search engines to find the given information including an expert collaborate with, publication venue, but in many cases due by keywords lack of attention content, they do not achieve desired results at early stages. can increase system efficiency respond their users utilizing a customized search. In this paper, using dataset bibliographic user’s publication, venues,...
Relation extraction is a challenging task in natural language processing. Syntactic features are recently shown to be quite effective for relation extraction. In this paper, we generalize the state of art syntactic convolution tree kernel introduced by Collins and Duffy. The proposed generalized more flexible customizable, can conveniently utilized systematic generation application specific sub-kernels. Using kernel, will also propose number novel sub-kernels These kernels show remarkable...