No abstract available.
Proceeding Downloads
A Frown-Based Thermal Comfort Detection Method of Facial Emotion Recognition
The development of artificial intelligence (AI) technologies has significantly improved the performance of automatic facial expression recognition. Expression recognition technology is applied to lots of fields such as mood and fatigue detection. In ...
Fast Traffic Light Recognition Using a Lightweight Attention-Enhanced Model
Traffic light recognition is a research hotspot in the field of intelligent transportation and unmanned driving. However, in the actual scene, the complexity of the surrounding environment increases the difficulty of traffic light detection, resulting ...
Accident detection and road monitoring in real time using deep learning and lane detection algorithms
Automating the monitoring of the roads would mean safer roads for both car drivers and pedestrians. The objectives of the system were to build a real time surveillance system for intelligent roads of the future. The system should be able to detect lane ...
C3MNet: Customized Multi-Channel Muscle Motion Network for Yawn-Based Fatigue Emotion Detection
In this paper, we propose an effective facial expression recognition (FER) method for yawn-based fatigue detection. Yawning is often considered an early symptom of fatigue. As facial expression however yawning and speaking have similar features. Our ...
Text Categorization of Filipino Tweets Using Naïve Byes Algorithm
The uses of social media platform twitter have progressed to a much wider array of uses due to the number of data it processes every day. It has been a storage for unstructured data that could be useful once arranged into meaningful formats and can ...
An Android Malware Detection and Malicious Code Location Method Based on Graph Neural Network
In recent years, enormously Android malware poses a significant threat to Android platform security. To detect malicious applications, researchers have done a lot of work, in which finding and locating malicious code segments is an important research ...
Coompetency-Based Mapping Tool in Personnel Management System using Analytical Hierarchy Process
Organizations that want to have a highly efficient and productive workforce should develop a skill mapping approach. However, research shows that most organizations fail to detect and effectively use their employees' competencies, keeping them from ...
Support Vector Machine Modelling for COVID-19 Prediction based on Symptoms using R Programming Language
SVM has been used in several studies in bioinformatics concerning disease classification. Currently, the world is experiencing a pandemic called COVID-19 which is a contagious disease that can be transferred through droplets in the air from the infected ...
A Lightweight Visual Question Answering Model based on Semantic Similarity
The key of visual question answering is to learn the semantic alignment of image objects and question words. The typical methods use the attention mechanism to achieve this goal. However, calculating the attention weight of image objects and question ...
ECO-DST: An Efficient Cross-lingual Dialogue State Tracking Framework
Data efficiency is a critical challenge for cross-lingual task-oriented dialogue state tracking (DST) due to high cost of collecting large amount of task-related labeled training set for specific language. Therefore, we focus on adapting high-...
IoT and RS Techniques for Enhancing Water Use Efficiency and Achieving Water Security
Water security is among the key elements and necessary to maintain sustainability. The arid and hyper arid countries have natural water resources with limited water recharge capacity to support its present population on natural water and to reduce its ...
Degradation Characteristics Analysis and Fault Prediction of Switching Power Supply Based on Data Mining
Fault prediction and health monitoring of DC-DC switching power supply plays an important role in the safe and reliable operation of power electronic equipment. In this paper, a long-term high temperature degradation test was carried out for DC-DC power ...
All-Optical Neural Network Tanh Architecture with MZI
Artificial neural networks (ANNs) have been widely used for industrial applications and have played a more and more important role in fundamental research but the electronic-based integrated circuits are limited by Moore's law. Optical neural networks (...
Multilevel and Multi-granularity of Remote Sensing Imagery Application based on Deep Learning and Machine Learning Algorithm
Deep learning classification has state-of-the-art machine learning approaches. Earlier work proves the deep convolutional neural network was successful and brilliant in different tasks such as image classification and image processing in remote sensing ...
Multi-angle Facial Expression Image Generation Method Based on Mask Vector Guided Generation Adversarial Network
In recent studies, the method of generative adversarial network to augment facial expression images has been widely used. However, the existing methods ignore the influence of face angle on facial expression image generation. To solve this problem, this ...
Dual Graph Convolution for Attributed Graph Clustering
It is challenging to jointly model dual heterogenous spaces including network topologies and node attributes, especially in the lack of label guidance. Our experimental investigation clearly shows the similarity matrix derived from either the ...
Sentiment Analysis of Facebook Posts Towards Good Governance Using SVM Algorithm: A Framework Proposal
Good governance means that the institutions are able to meet the needs of its stakeholders. It is participatory and inclusive through considering the opinions and sentiments of the stakeholders for decision-making. To analyze the massive number of ...
Additional time series features for preciseness improvement of LSTM-based COVID-19 spread forecasting model
The COVID-19 pandemic has spread rapidly since 2019. The worldwide uncontrollable outbreak has caused health and economic damage. Multiple deep learning predictable models have been proposed to forecast COVID-19 spread that can help monitor the ...
Random Undersampling on Imbalance Time Series Data for Anomaly Detection
Random Undersampling (RUS) is one of resampling approaches to tackle issues with imbalance data by removing instances randomly from the majority class. Anomaly is considered as a rare case, thus the number of instances in the anomaly class is usually ...
A Comparison between Deep Belief Network and LSTM in Chaotic Time Series Forecasting
The application of deep neural networks in forecasting time series data is increasingly popular, aiming to improve prediction accuracy in this problem. However, as for chaotic time series, a special kind of time series data generated from the ...
Dual Enhancement for Multi-Label Learning with Missing Labels
The goal of multi-label learning with missing labels (MLML) is assigning each testing instance multiple labels given training instances that have a partial set of labels. The most challenging issue is to complete the missing labels by leveraging input ...
What About Your Next Job? Predicting Professional Career Trajectory Using Neural Networks
Accurate and effective analysis of professional career trajectories can help job seekers make the right job switch quickly. However, it is a non-trivial task to develop an effective model to predict the next job of users. Previous works either focus on ...
Index Terms
- Proceedings of the 2021 4th International Conference on Machine Learning and Machine Intelligence