Due to environmental concerns, the energy-saving train regulation is necessary for urban metro transportation, which can improve the service quality and energy efficiency of metro lines. In contrast to most of the existing research of train regulatio...
Despite major advances in recent years, the field of Machine Learning continues to face research and technical challenges. Mostly, these stem from big data and streaming data, which require models to be frequently updated or re-trained, at the expens...
Virtual coupling (VC) technology has received much attention because of its significant advantages in enhancing the railway transport capacity; it achieves efficient train coupling operation through advanced communication technology. However, due to...
This paper presents a unified technical survey of Large Language Models (LLMs), connecting three layers of the modelling pipeline that existing surveys address in isolation: internal architecture, distributed training optimisation, and downstream ada...
The safe and efficient operation of high-speed trains is highly dependent on the reliability of their actuation systems, where actuator faults and input saturation pose significant challenges to control performance. Existing centralized control strat...
Virtual coupling (VC) technology, which determines the safe interval between trains based on relative braking distance, offers a promising solution by enabling tighter yet safe train-following intervals through advanced communication and control stra...
The recent unprecedented success of deep learning (DL) in various fields is underlied by its use of large-scale data and models. Training a large-scale deep neural network (DNN) model with large-scale data, however, is time-consuming. To speed up the...
AI provides a new method for massive simulated data calculations in molecular dynamics, materials, and other scientific computing fields. However, the complex structures and large-scale parameters of neural network models make them difficult to devel...
Artificial intelligence (AI) algorithms enhance distributed acoustic sensing (DAS) signal interpretation by leveraging large-scale acoustic data. However, heterogeneous deployment environments hinder model generalization ability and exacerbate label...
The ERTMS/ETCS is the newest automatic train protection system. This is a system that supports the driver in driving the train. It is currently being implemented throughout the European Union. This system’s latest specifications also provide ad...
Massive computational resources are required by a booming number of artificial intelligence (AI) services in the communication network of the smart grid. To alleviate the computational pressure on data centers, edge computing first network (ECFN) can...
The rapid scaling of large language model (LLM) training has intensified demand for Graphics Processing Unit (GPU) clusters balancing throughput with energy efficiency. While NVIDIA’s H100 and B200 architectures are increasingly deployed in pro...
The rapid growth of large language models (LLMs) has made training energy efficiency a major systems and sustainability challenge. Training requires substantial computation, memory, communication, and electrical energy, yet the literature often treat...
This paper delves into image detection based on distributed deep-learning techniques for intelligent traffic systems or self-driving cars. The accuracy and precision of neural networks deployed on edge devices (e.g., CCTV (closed-circuit television)...
In this work, we formalize the concept of differential model robustness (DMR), a new property for ensuring model security in federated learning (FL) systems. For most conventional FL frameworks, all clients receive the same global model. If there exi...
Despite substantial investments in artificial intelligence (AI) training, logistics organizations often struggle to translate these investments into measurable improvements in employee performance. Drawing on the extended Technology Acceptance Model...
Large-scale datasets, which have sufficient and identical quantities of data in each class, are the main factor in the success of deep-learning-based classification models for vision tasks. A shortage of sufficient data and interclass imbalanced data...
The hydrological response of a watershed is strongly influenced by the spatiotemporal dynamics of rainfall. Rainfall events of similar magnitude can produce markedly different flood processes due to variations in the spatiotemporal patterns of rainfa...
Transformer-based time series models are being increasingly employed for time series data analysis. However, their training remains memory intensive, especially with high-dimensional data and extended look-back windows, while model-level memory optim...
To solve the problems of autonomous decision making and the cooperative operation of multiple unmanned combat aerial vehicles (UCAVs) in beyond-visual-range air combat, this paper proposes an air combat decision-making method that is based on a multi...
Vision–Language–Action (VLA) policies remain brittle under modest distribution shift. On LIBERO-Plus, contemporary models that solve clean tasks at high rates can fall below
While the integration of large language models (LLMs) drives intelligent automation, their endogenous vulnerability to complex adversarial prompts engenders critical security threats. To address the limitations of existing defenses relying on prohibi...
Background: Establishment of an artificial intelligence model in gastrointestinal endoscopy has no standardized dataset. The optimal volume or class distribution of training datasets has not been evaluated. An artificial intelligence model was previo...
This paper investigates the problem of ensuring the stable operation of multiple high-speed train systems under the threat of False Data Injection (FDI) attacks. Due to the wireless communication characteristics of railway networks, high-speed train...
Background: The Global Positioning System (GPS) and wearable monitoring technologies are increasingly applied in sport science to quantify training load; however, data from female cross-country skiers in nations with emerging competitive programs rem...
This paper presents an analysis on using an on-board energy storage device (ESD) for enhancing braking energy re-use in electrified railway transportation. A simulation model was developed in the programming language C++ to help with the sizing of th...
Industrial radiography is a pivotal non-destructive testing (NDT) method that ensures quality and safety in a wide range of industrial sectors. Conventional human-based approaches, however, are prone to challenges in defect detection accuracy and eff...
Machine learning techniques are extensively employed in drug discovery, with a significant focus on developing QSAR models that interpret the structural information of potential drugs. In this study, the pre-trained natural language processing (NLP)...
Surface defects in hot-rolled steel strip alter the material’s properties and degrade its overall quality. Especially in real production environments, due to time sensitivity, lightweight Convolutional Neural Network models are suitable for ins...
Deep Neural Networks (DNNs) have established themselves as a fundamental tool in numerous computational modeling applications, overcoming the challenge of defining use-case-specific feature extraction processing by incorporating this stage into unifi...
This paper proposes a concept of Digital Stereotypes, observed during research on quantitative overrepresentation of one class over others, and its impact on the results of the training of Deep Learning models. The real-life observed data classes are...
When training a deep learning model with distributed training, the hardware resource utilization of each device depends on the model structure and the number of devices used for training. Distributed training has recently been applied to edge computi...
The Monte Carlo neutron transport method is used to accurately estimate various quantities, such as k-eigenvalue and integral neutron flux. However, in the case of estimating a distribution of a desired quantity, the Monte Carlo method does not typic...
Distributed training across several quantum computers could significantly improve the training time and if we could share the learned model, not the data, it could potentially improve the data privacy as the training would happen where the data is lo...
Federated learning is a distributed learning algorithm designed to train a single server model on a server using different clients and their local data. To improve the performance of the server model, continuous communication with clients is required...
Human parsing is an important technology in human–robot interaction systems. At present, the distribution of multi-category human parsing datasets is unbalanced, and the samples present a long-tailed distribution, which directly affects the per...
In machine learning applications, classification schemes have been widely used for prediction tasks. Typically, to develop a prediction model, the given dataset is divided into training and test sets; the training set is used to build the model and t...
10 October 2023
Generative Adversarial Networks are powerful generative models that are used in different areas and with multiple applications. However, this type of model has a training problem called mode collapse. This problem causes the generator to not learn th...
Forest managers demand reliable tools to evaluate post-fire vegetation and soil damage. In this study, we quantify wildfire damage to vegetation and soil based on the analysis of burn severity, using multitemporal and multispectral satellite data and...
Wearable sensors offer a promising platform for non-invasive glucose monitoring by indirectly predicting glucose levels from physiological signals. However, machine learning models trained on such data often suffer degraded performance when applied t...
Deep learning models have enabled significant performance improvements to remote sensing image processing. Usually, a large number of training samples is required for detection models. In this study, a dynamic simulation training strategy is designed...
Segmentation performance is measured against pixel-wise ground truth (GT); without it, that measurement cannot be made. Remote sensing segmentation models are evaluated likewise, yet operational systems receive new unlabeled images, and the propertie...
Panel methods have been applied to many fields of fluid owing to their computational efficiency. However, their applications are limited in simulating highly turbulent flow with separations due to the inviscid flow assumptions, such as those associat...
A deep semantic segmentation model-based method can achieve state-of-the-art accuracy and high computational efficiency in large-scale crop mapping. However, the model cannot be widely used in actual large-scale crop mapping applications, mainly beca...
The International Classification of Diseases (ICD) has an important role in building applications for clinical medicine. Extremely large ICD coding label sets and imbalanced label distribution bring the problem of inconsistency between the local batc...
Federated learning (FL) is a distributed machine learning paradigm under privacy preservation. However, data heterogeneity among clients leads to the shared global model obtained after training, which cannot fit the distribution of each client’...
Based on the theory of uniform finite-length incoherent line source radiation and real vehicle online test data of Shanghai Maglev trains, a prediction model for environmental noise is established using an equivalent segmented line sound source appro...
Federated learning (FL), as a privacy-preserving distributed machine learning paradigm, demonstrates unique advantages in addressing data silo problems. However, the prevalent statistical heterogeneity (data distribution disparities) and system heter...
With the widespread use of end devices, online multi-label learning has become popular as the data generated by users using the Internet of Things devices have become huge and rapidly updated. However, in many scenarios, the user data are often gener...
With the continuous development of artificial intelligence, effectively solving the problem of data islands under the premise of protecting user data privacy has become a top priority. Federal learning is an effective solution to the two significant...
of 124