![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
211 Result(s)
-
Article
Open AccessDynamic multi-label feature selection algorithm based on label importance and label correlation
Multi-label distribution is a popular direction in current machine learning research and is relevant to many practical problems. In multi-label learning, samples are usually described by high-dimensional featu...
-
Article
Undersampling based on generalized learning vector quantization and natural nearest neighbors for imbalanced data
Imbalanced datasets can adversely affect classifier performance. Conventional undersampling approaches may lead to the loss of essential information, while oversampling techniques could introduce noise. To add...
-
Article
The concept information of graph granule with application to knowledge graph embedding
Knowledge graph embedding (KGE) has become one of the most effective methods for the numerical representation of entities and their relations in knowledge graphs. Traditional methods primarily utilise triple f...
-
Article
An adaptive joint optimization framework for pruning and quantization
Pruning and quantization are among the most widely used techniques for deep learning model compression. Their combined application holds the potential for even greater performance gains. Most existing works co...
-
Article
Open AccessA Region-Selective Anti-compression Image Encryption Algorithm Based on Deep Networks
In recent years, related research has focused on how to safely transfer and protect the privacy of images in social network services while providing easy access by authorized users. To safeguard privacy, we su...
-
Article
Relabeling and policy distillation of hierarchical reinforcement learning
Hierarchical reinforcement learning (HRL) is a promising method to extend traditional reinforcement learning to solve more complex tasks. HRL can solve the problems of long-term reward sparsity and credit assi...
-
Article
Multi-class feature selection via Sparse Softmax with a discriminative regularization
Feature selection plays a critical role in many machine learning applications as it effectively addresses the challenges posed by “the curse of dimensionality” and enhances the generalization capability of tra...
-
Article
Autonomous gait switching method and experiments of a hexapod walking robot for Mars environment with multiple terrains
Mars exploration significantly advances our understanding of planetary evolution, the origin of life, and possibilities for Earth’s future. It also holds potential for discovering new mineral resources, energy...
-
Article
RSGNN: residual structure graph neural network
Compared to conventional artificial neural networks, Graph Neural Networks (GNNs) better handle graph-structured data. Graph topology plays an important role in learning graph representations and impacts the p...
-
Article
Equilibrium optimizer with generalized opposition-based learning for multiple unmanned aerial vehicle path planning
Multiple unmanned aerial vehicle (UAV) path planning is the benchmark problem of multiple UAV application, which belongs to the non-deterministic polynomial problem. Its objective is to require multiple UAV to...
-
Article
Evaluation model of aluminum electrolysis cell condition based on multi-source heterogeneous data fusion
Industrial process data have the characteristics of heterogeneity, dimensional inconsistency and multi time scales, which increase the difficulty of condition evaluation in industrial process using multi-sourc...
-
Article
Open AccessSpeech Keyword Spotting Method Based on Swin-Transformer Model
With the rapid advancements in deep learning technology, the Transformer-based attention neural network has shown promising performance in keyword spotting (KWS). However, this method suffers from high computa...
-
Article
Design and implementation of intelligent LiDAR SLAM for autonomous mobile robots using evolutionary normal distributions transform
This paper presents a method that employs an evolutionary normal distributions transform (NDT) for simultaneous localization and map** (SLAM) using light detection and ranging (LiDAR) for autonomous mobile r...
-
Article
A novel human-inspirited collectivism teaching–learning-based optimization algorithm with multi-mode group-individual cooperation strategies
Teaching–learning-based optimization (TLBO) algorithm is an excellent human-inspired optimization technique. This paper proposes an innovative improved version of TLBO—collectivism teaching–learning-based opti...
-
Article
Open AccessTransient Data Caching Based on Maximum Entropy Actor–Critic in Internet-of-Things Networks
With the rapid development of the Internet-of-Things (IoT), a massive amount of transient data is transmitted in edge networks. Transient data are highly time-sensitive, such as monitoring data generated by in...
-
Article
Construction of key parameter change model of human-computer interaction for intelligent decision-making under the condition of long time voyage
Under the long time voyage of the ship, finding out the task time regularity of human operator in the command and control system can help the intelligent system to carry out the task intelligent assignment and...
-
Article
An interpretable composite CNN and GRU for fine-grained martial arts motion modeling using big data analytics and machine learning
Martial arts involve highly complex motions with intricate poses and maneuvers. Current video analysis methods face challenges in robustly scaling across diverse data while accurately modeling the nuances of t...
-
Chapter and Conference Paper
Comprehensive Evaluation of the Performance of a New High-Speed Train Based on TOPSIS-Entropy Weight Method
In order to comprehensively evaluate the new generation of high-speed trains launched by China, Japan, Germany and France, and then determine the trains with the best comprehensive performance, a comprehensive...
-
Chapter and Conference Paper
Joint Task and Path Planning for Unmanned Surface Vehicle Surveillance Based on Beetle Antenna Search and Minimal Construct Visibility Graph
Task and path planning are critical to unmanned surface vehicles before sending off to commit surveillance tasks. In this paper, a hierarchical framework is proposed to resolve the problem where the lower-leve...
-
Chapter and Conference Paper
DWDM: Dynamically Weighted Three-Domain Mixing for Domain-Adaptive Semantic Segmentation
In unsupervised domain adaptation (UDA), the aim is to adapt a model trained on source data to target data without having access to target annotations. However, when the dissimilarity between the source and ta...