Emmanuel Mutabazi

ORCID: 0000-0003-4306-3880
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Metaheuristic Optimization Algorithms Research
  • Topic Modeling
  • Information Retrieval and Search Behavior
  • Advanced Text Analysis Techniques
  • Biomedical Text Mining and Ontologies
  • Anomaly Detection Techniques and Applications
  • Machine Learning in Materials Science
  • Robotics and Sensor-Based Localization
  • Indoor and Outdoor Localization Technologies
  • Data Quality and Management
  • Advanced Image and Video Retrieval Techniques
  • Human Pose and Action Recognition
  • Video Surveillance and Tracking Methods
  • Mass Spectrometry Techniques and Applications
  • Machine Learning and ELM
  • Optimization and Search Problems

Hohai University
2021-2023

Question Classification (QC) is the fundamental task for Answering Systems (QASs) implementation, and a vital task, as it helps in identifying question category. It plays big role predicting answer to while building QAS. However, classifying medical questions still challenging due complexity of terms. Many researchers have proposed different techniques solve these problems, but some problems remain partially solved or unsolved. With help deep learning technology, various text-processing...

10.3390/app13158623 article EN cc-by Applied Sciences 2023-07-26

Simultaneous Localization and Mapping (SLAM) is a challenging key issue in the mobile robotic fields. In terms of visual SLAM problem, direct methods are more suitable for expansive scenes with many repetitive features or less texture contrast feature-based methods. However, robustness weaker than that To deal this an improved sparse odometry loop closure (LDSO) proposed, where performance system under influence different imaging disturbances camera focused on. proposed method, method based...

10.1155/2022/4075910 article EN cc-by Computational Intelligence and Neuroscience 2022-08-22

In this paper, a background subtraction in region method is proposed to recognize actions and interactions the video. Firstly, video taken converted into frames. Preprocessing techniques are applied sampled images for noise reduction. Next, used extract foreground objects units. The combination of model, color object movement information employed get likelihood. Then, an Improved Adaptive decision function determines regions. Moreover, human detection produces bounding box surrounding...

10.12783/dtcse/cscbd2019/30077 article EN DEStech Transactions on Computer Science and Engineering 2019-01-01
Coming Soon ...