- Robotic Path Planning Algorithms
- Advanced Graph Neural Networks
- Complex Network Analysis Techniques
- Artificial Intelligence in Healthcare
- Multi-Criteria Decision Making
- Robot Manipulation and Learning
- Web Data Mining and Analysis
- Fuzzy Logic and Control Systems
- Advanced Text Analysis Techniques
- IoT and Edge/Fog Computing
- Dental Radiography and Imaging
- Topic Modeling
- Rough Sets and Fuzzy Logic
- Cognitive Computing and Networks
- Data Management and Algorithms
- Geographic Information Systems Studies
- AI-based Problem Solving and Planning
- Data Quality and Management
- Video Surveillance and Tracking Methods
- Advanced Database Systems and Queries
- Robotics and Sensor-Based Localization
- Medical Imaging and Analysis
- Advanced Clustering Algorithms Research
- Recommender Systems and Techniques
- Information Systems Theories and Implementation
Hanoi University of Science and Technology
2015-2024
University of Labor and Social Affairs
2024
Vietnam National University, Hanoi
2022
Ministry of Science and Technology
2022
Tokyo Institute of Technology
2007-2022
Hung Yen University of Technology and Education
2022
Thuyloi University
2022
Thai Nguyen University
2022
ChatGPT plays significant roles in the third decade of 21st Century. Smart cities applications can be integrated with various fields. This research proposes an approach for developing large language models using generative artificial intelligence suitable small- and medium-sized enterprises limited hardware resources. There are many AI systems operation development. However, technological, human, financial resources required to develop impractical enterprises. In this study, we present a...
Abstract The next generation of E-Government and healthcare has the potential to increase more intelligent governance with improvements in transparency, accountability, efficiency, effectiveness. It enables organizations use benefits information via big data analysis settle difficulties effectively. Big Data emerged which plays a significant role many sectors around world. Global trends taking advantage from are considered an overview US, European Union, several developing countries. To...
Precipitation nowcasting is one of the main tasks weather forecasting that aims to predict rainfall events accurately, even in low-rainfall regions. It has been observed few studies have devoted predicting future radar echo images a reasonable time using deep learning approach. In this paper, we propose novel approach, RainPredRNN, which combination UNet segmentation model and PredRNN_v2 for precipitation with images. By leveraging abilities contracting-expansive path model, number...
Deep learning methods predicated on convolutional neural networks and graph have enabled significant improvement in node classification prediction when applied to representation with embedding effectively represent the hierarchical properties of graphs. An interesting approach (DiffPool) utilises a differentiable pooling technique which learns ‘differentiable soft cluster assignment’ for nodes at each layer deep network mapped sets clusters. However, effective control process is difficult...
In practical dentistry, dentists use their experience to examine dental X-ray images and derive symptoms from patients for concluding possible diseases. This method is based solely on the own dentists' experience. Dental diagnosis X-Ray proposed support in decision making. paper presents an application of consultant system fuzzy rule. Fuzzy rule was applied many applications has important role computational intelligence, data mining, machine learning, etc. Based a image dataset, we C-Means...
Robotic path planning is a field of research which gaining traction given the broad domains interest to an important systemic requirement. The aim optimise efficacy robotic movement in defined operational environment. For example, robots have been employed many including: Cleaning (such as vacuum cleaners), automated paint spraying robots, window cleaning forest monitoring and agricultural (often driven using satellite geostationary positional data). Additionally, mobile systems utilised...
Problems of preeclampsia sign diagnosis are mostly based on symptom data with the characteristics collected periodically in uncertain, ambiguous, and obstetrician opinions. To reduce effects preeclampsia, many studies have investigated disease, prevention, complication. Conventional fuzzy inference techniques can solve several problems health such as systems (FIS), Mamdani complex rule reduction (M-CFIS-R), however, computation time is quite high. Recently, research direction approximate...
Human behaviour demonstrates environmental awareness and self-awareness which is used to arrive at decisions actions or reach conclusions based on reasoning inference. Environmental are traits autonomous robotic systems must have effectively plan an optimal route operate in dynamic operating environments. This paper proposes a novel approach enable achieve efficient coverage path planning, combines adaptation with knowledge techniques hedge algebras planning multiple decision-making under To...
Generative AI applications have played an increasingly significant role in real-time tracking many domains including, for example, healthcare, consultancy, dialog boxes (common types of window a graphical user interface operating systems), monitoring systems, and emergency response. This paper considers generative presents approach which combines hedge algebra multilingual large language model to find hidden rules big data ChatGPT. We present novel method extracting natural knowledge from...
Coverage path planning describes the process of finding an effective robots can take to traverse a defined dynamic operating environment where there are static (fixed) and (mobile) obstacles that must be located avoided in coverage planning. However, most methods limited their ability effectively manage coordination multiple concert. In this paper, we propose novel model (termed Multi-ST) which utilizes spiral-spanning tree algorithm with intelligent reasoning knowledge-based achieve optimal...
Robotics is a highly developed field in industry, and there large research effort terms of humanoid robotics, including the development multi-functional empathetic robots as human companions. An important function robot to find an optimal coverage path planning, with obstacle avoidance dynamic environments for cleaning monitoring robotics. This paper proposes novel approach enable robotic planning. The proposed combines reasoning knowledge techniques, hedge algebra, Spiral Spanning Tree...
<p>Badminton is widely favoured across many world countries, predominantly Asian nations. In Vietnam, it acknowledged not only as a sport but also means to enhance physical health and promote the cultural development of populace. This study aims identify several tests evaluate professional fitness talented male badminton students at Faculty Physical Education, Ho Chi Minh City University Education. The utilized standard research methods, including literature synthesis, interviews,...
Robots are a rapidly evolving development field encompassing variable domains ranging from industrial robots to empathetic for human companions. Future will be highly dependent on the ability understand, interpret, and generate representation of environment in which they operating, ideally both machine-readable formalism. An important element this process lies Path Planning (PP) with obstacle avoidance dynamic environments (including cleaning monitoring robotics) identify optimal coverage...
In the recent years, there are huge data extracted from social networks in both static and real-time analysis, such as Facebook, Twitter, LinkedIn, Instagram. Recently, most researchers have investigated classifying textual contents without user interests/behaviors of networks. This paper has presented a novel approach using Convolution Neural Network with its new contribution perceptions network to interests. Experimental results show that proposed model performs better than conventional...