No abstract available.
Proceeding Downloads
The Application of Machine Learning in Activity Recognition with Healthy Older People Using a Batteryless Wearable Sensor
The development of human activity monitoring has allowed for simulation and prediction in a variety of application scenarios. The battery-free wearable sensor is performed on sternum level clothing, mainly by script execution. It is essential to monitor ...
10k Logo Dataset for Machine Learning Logo Retrieval Purposes
Trademarks and logos are used worldwide to represent companies, malls, shops and restaurants. It is one of the first visual symbols a company creates in the early stages of planning for this business. The logo must be unique and captures the idea of ...
Comparison of LSTM, GRU and Hybrid Architectures for usage of Deep Learning on Recommendation Systems
This article shows the results of a performance analysis from LSTM, GRU and Hybrid Neural Network architectures in Recommendation Systems. To this end, prototypes of the networks were built to be trained using data from the user's browsing history of a ...
A Comparative Study of Parkinson Disease Diagnosis in Machine Learning
Parkinson's disease (PD) is a cumulative disorder in the nervous system. PD patients may experience difficulty in movement and speaking due to damages in certain parts in the brain. In this study, we propose using two types of Ensemble learning methods ...
Design of Deep Learning Experiment Teaching Case based on EMG Signal Analysis
Against the background of new engineer, universities pay more and more attention to the cultivation of innovative talents with cross-disciplines. The artificial intelligence-related courses are typical interdisciplinary and strong practical courses, and ...
Safety Risk Assessment for Children's Products Based on Reinforcement Learning
The prediction accuracy rate of the types of multi-factor associated injuries in the risk assessment model has been tested with 122 test data, resulting in that the correct recognition rate of the injury consequences of the adjusted model was about 75%, ...
A Method for Improving Unsupervised Intent Detection using Bi-LSTM CNN Cross Attention Mechanism
Spoken Language Understanding (SLU) can be considered the most important sub-system in a goal-oriented dialogue system. SLU consists of User Intent Detection (UID) and Slot Filling (SF) modules. The accuracy of these modules is highly dependent on the ...
Using Multi-Agent Microservices for a Better Dynamic Composition of Semantic Web services
The development of new technologies and recent paradigms should be explored to support interoperability in the medium and long term. This paper examines the integration of micro-services and multi-agent systems (MAS), implementing a new paradigm called ...
Increase the System Utilization by Adaptive Queue Management System with Time Restricted Reservation
Traditionally, the ticket queue technology is implemented to manage queuing system, but the disadvantage of the ticket queue is losing queue information. The queue-length and the waiting time is often overestimated when some customer abandons from the ...
DF-map: A Novel Variable Resolution Decision Forest Map for Localization
Localization is one of the most important tasks for self-driving vehicles. Existing localization methods usually rely on satellite signals or high-precision maps. However, the former is often limited by signal shielding, while the latter requires higher ...
Application of Artificial Neural Network for Daily Evaporation Forecasting Using Weather Data
Estimating evaporation is one of the most important works for meteorologists and hydrologists. This paper employed three artificial neural network (ANN) algorithms, which are linear regression (LR), multi-layer perceptron (MLP) and general regression ...
Learning Symbolic Action Definitions from Unlabelled Image Pairs
Task planners and goal recognisers often require symbolic models of an agent’s behaviour. These models are usually manually developed, which can be a time consuming and error prone process. Therefore, our work transforms unlabelled pairs of images, ...
CnnSound: Convolutional Neural Networks for the Classification of Environmental Sounds
The classification of environmental sounds (ESC) has been increasingly studied in recent years. The main reason is that environmental sounds are part of our daily life, and associating them with our environment that we live in is important in several ...
Transitioning from Traditional Learning to Blended Learning at Some Public Universities in Vietnam after the Covid-19 Pandemic
The Covid-19 pandemic has addressed critical impacts leading to the nationwide social distancing measures in Vietnam. School closures were mandated by the Government in an attempt to control the transmission of the virus. Online teaching and learning ...
The Current Situation of Senior High School Students Learning Mathematics with Online Problem-Solving Searching Software
With the rapid development of internet technology, more and more senior high school students try to solve math problems by using online problem-solving searching software (OPSSS) at present. This study explores the situation of mathematics learning of ...
The Importance of Soft Skills for University Students in the 21st Century
The world of employment has changed enormously together with the rise of globalization causing employability to become one of the main goals for education systems. Today's employers require employees to have soft skills in addition to technical skills. ...
Index Terms
- Proceedings of the 4th International Conference on Advances in Artificial Intelligence