A5050153953- Text and Document Classification Technologies
- Imbalanced Data Classification Techniques
- Advanced Text Analysis Techniques
- Advanced Neural Network Applications
- Internet of Things and AI
- Natural Language Processing Techniques
- Vehicle License Plate Recognition
- IoT and Edge/Fog Computing
- Video Surveillance and Tracking Methods
- Topic Modeling
- Sentiment Analysis and Opinion Mining
- Machine Learning and Data Classification
- Academic integrity and plagiarism
- Text Readability and Simplification
- Wireless Body Area Networks
United International University
2020-2023
K-Nearest Neighbour (KNN) is a lazy learning algorithm which has been successfully practiced in several real-life machine applications. However, it titled as learner because unable to learn decision line from historical training data and uses the itself for classification. KNN discovers closest neighbors around test instances; At same time considers majority voting of class label classify instances. In case noisy datasets, value K should be higher. It still struggling with complexity better...
Text mining is the procedure of exploring large unorganized text data. Due to availability numerous amounts data through online blogs, newspapers and other media, classification categorization hot topic nowadays. Many researches have been done on this English western languages. However, very few notable Bangla language. Unavailability a dataset in language another burden develop highperformance tool. In paper, we presented news tags approach. The has entirely based titles only with parallel...
Plagiarism is an act of literature fraud, which presenting others’ work or ideas without giving credit to the original work. All published and unpublished written documents are under cover this definition. Plagiarism, increased significantly over last few years, a concerning issue for students, academicians, professionals. Due this, there several plagiarism detection tools software available detect in different languages. Unfortunately, negligible has been done no Bengali language where one...
Headline generation is the process of generating headlines automatically from text articles. We model a comprehensive abstractive headline technique using Seq2Seq Recurrent Neural Networks with Global Attention in this work. Despite being one most spoken languages globally, very few significant works have been done on particular topic Bangla language. Thus, our solely based language, and we find that performance highly satisfactory at current stage. also propose an extensive dataset...
Precisely detecting and classifying distinct vehicle types are essential in numerous automated systems, including traffic monitoring detection, which of utmost significance computer vision. Surprisingly, deep learning methods for detection already widely accepted. Still, their applicability to Bangladeshi vehicles has yet be thoroughly studied, it is crucial develop an intelligent transportation system (ITS) Bangladesh. Real-time a goal, the You Only Look Once (YOLO) model proven most...