No abstract available.
Proceeding Downloads
Distributed Photovoltaic Load Probability Forecasting Model Based on Clustering Characteristic
Accurate distributed photovoltaic load forecasting can effectively assist the overall power dispatch and then reduce the risk of grid operation. Different from the existing research, we deeply mine the clustering characteristics of load in the time ...
A Comparative Study of LSTM, LightGBM, and Autoregressive Model in Narrow-Based ETF Market Prediction with Multi-Ticker Models
Narrow-based Exchange-Traded Funds (ETFs) offer significant diversification compared to stock market investments while maintaining a reasonable level of predictability through asset combinations and industry dependencies, rendering them ideal for the ...
Short-term Load Forecasting Method of Power Distribution Station Area Integrating Multiple Temporal Characteristics
In order to solve the problem of short term power load forecasting and improve the accuracy of load forecasting in distribution station area, a short term power load forecasting model integrating multiple temporal series characteristics is proposed in ...
Shape and style Enhancement for Domain Generalization
Domain generalization requires that models trained only with source domain data also perform well on unknown target domain data, which requires that existing models trained with source domain have good generalization performance. Compared with semi-...
Research on Diabetes Prediction Based on Machine Learning
Diabetes is an irreversible, chronic metabolic disease, and is now the third most important non-communicable disease threatening human health. Therefore, early diagnosis of diabetes is essential. In this paper, after preprocessing the Pima Indian ...
CM: A Cross and Mixture unit for multitask recommendation
With the rapid development of deep recommendation models, Multitask Learning (MTL) enables models to have better generalization ability in the learning process by extracting relevant information from different tasks. Although many studies have focused on ...
A Fairness Parameter Selection Method for Convex Fairness-aware Classification Models
Fairness-aware classification has emerged as a focal point in a wide range of machine learning applications. To address fairness issues such as demographic parity and disparate mistreatment, researchers have developed fair classifiers. A common approach ...
Predictive Analysis of NBA Game Outcomes through Machine Learning
This study delved into the realm of sports analytics, employing machine learning techniques to predict the outcomes of NBA games based on player performance and team statistics. Through meticulous data collection, filtering, and model comparison, we ...
A Seed Expansion Algorithm Based on The CRITIC Method and Node Gravity
Complex networks are composed of nodes and complex relationships between nodes, which are the abstraction of various complex systems in the real world. Community structure is a remarkable characteristic of complex networks.Community detection algorithms ...
A Feature Saliency Based Hybrid Neural Network Model for Object Recognition
Accurate recognition of image targets is a fundamental intelligent perception task and extracting effective features is the prerequisite. However, there are still problems with both hand-crafted features and the ones learned by deep neural networks, such ...
Fusion of Image and Point Cloud for Accurate Obstacle Detection in Autonomous Driving
Obstacle detection is of great significance for autonomous driving. Accurately identifying obstacles and transmitting obstacle information to the underlying planning and control system is essential for effective and safe autonomous driving. Obstacle ...
Epilepsy seizure detection using hybrid features based on EEG-rhythm filter banks
Epilepsy, a chronic brain disease with recurrent attacks, is the most common neurological disease in humans. It is extremely important for patients with epilepsy to accurately and timely diagnose seizures. A new method based on Electroencephalogram (EEG) ...
MS-YOLOv5: Improved YOLOv5 Based on Multi-Head Self-Attention for Citrus Leaf Disease Severity Estimation
Accurate disease severity estimation is vital for fruit tree disease prevention and control. Most of the existing image processing methods for fruit tree disease severity estimation are based on a single leaf evaluation, and mostly, are done in ...
An Efficient Helmet Wearing Detection Method Based On YOLOv7-Tiny
In high-risk construction environments, ensuring safety is paramount. Accidents, often resulting in casualties, underscore the importance of wearing helmets correctly. To tackle the challenges posed by small, traditional targets and the complexity of ...
SIN OC_SORT: Multi-Object Tracking by Re-Correct the Equations of Motion
With the improvement in detector performance, the Kalman Filter can estimate object trajectories based on the basic assumption of short-term linear motion. However, in scenarios with severe object occlusion, this estimation may suffer from significant ...
Combining Dynamic Programming and GPU to accelerate k-Distance Discord Detection in Time Series Data
Detecting anomalous subsequences plays a vital role in time series analysis. Traditional approaches often rely on sliding windows to extract subsequences and identify anomalies. However, these methods encounter two difficulties: i) they are unable to ...
U-Net lesion segmentation network combining attention and pyramid fusion
In order to solve the problems of limited feature expression ability and low segmentation accuracy of the lesion segmentation network, CGM-UNet based on Coordinate Attention (CA), Multi-Head Self-Attention (MHSA) and Global Pyramid Guidance (GPG) was ...
An Effectiveness Study of Multi-Model Result Fusion in Satellite Image Semantic Segmentation Tasks
The field of atmospheric imaging has continually grappled with the complex task of accurate contrail detection, largely due to the intricate and variable nature of contrail formations within diverse atmospheric environments. Addressing this challenge, ...
Analysis and Identification of Evil Twin Attack through Data Science Techniques Using AWID3 Dataset
- Leandro Marcos da Silva,
- Vinícius Moraes Andreghetti,
- Roseli Aparecida Francelin Romero,
- Kalinka Regina Lucas Jaquie Castelo Branco
Wi-Fi is a widely used technology worldwide but can also be a source of insecurity. One of the most common forms of attack is the evil twin, where an attacker creates a fake Wi-Fi network with the same name as a legitimate network. Machine learning ...
Riemannian Space-based Mutual Learning for Cyber Attack Detection
With the continuous development of information technology, the popularity of intelligent devices not only provides great convenience to people's life, but also provides prerequisites for cyber attacks. Deep learning-based cyber attack detection methods ...
BiRNNs-SAT for Detecting BGP Traffic Anomalies in Communication Networks
Border Gateway Protocol (BGP) serves as a path vector protocol that manages network reachability information among Autonomous Systems (AS), is critical to the stability and reliability of the Internet. The single approach in previous studies fails to ...
A Novel Data Augmentation Method for Robotic Surgical Instrument Small Part Segmentation in Complex Scenes
Accurate and robust segmentation of surgical instrument parts is urgently required by AI enhanced intelligent surgery and automatic surgery skill evaluation. However, it is still a challenging problem due to the multiple small areas of frontal clasper ...
Simulation Design of Continuous Linear Multiple Intersection Intelligent Traffic Light
At urban intersections, traffic congestion often occurs. Currently, most of the traffic signal lights in China adopt fixed timing schemes, lacking intelligence, which leads to severe traffic congestion in cities. This study focuses on continuous linear ...
Intelligent Selection Mechanism for Grazing Strategies towards Sustainable Grassland Development
Within the grassland ecosystem, grazing has the most significant impact. A reasonable grazing strategy must account for both the income of pastoralists and the capacity of the grazing pasture to achieve sustainable development. To ensure the virtuous and ...
Swarm GAN: Stabilizing Training of Generative Adversarial Networks via Swarm Intelligence
Generative adversarial networks (GANs) have seen significant research interest over the past decade, yet core issues of training instability and mode collapse persist. This work proposes SwarmGAN, a novel GAN framework incorporating swarm intelligence ...
Research on Graph Signal Sampling and Reconstruction Method Based on Causal Emergence
Graph signal sampling and reconstruction techniques effectively reduce data dimensions while preserving the information and structure contained in networks. The distortion-free reduction of data dimensions not only aids in reducing the computational ...
Index Terms
- Proceedings of the 6th International Conference on Machine Learning and Machine Intelligence