In this paper fraudulent crediting of amounts is the primary challenge that clients encounter in the finance sector. On the other side, frauds have accompanied credit card innovation since it began. Many rule-based te...
详细信息
This study presents an optimized machinelearning-driven profit forecasting model tailored for the backup clamps of transmission line conductors and ground wires, critically enhancing the financial planning in power t...
详细信息
In today's society, the output of garbage is more and more, and people are indispensable for the management and classification of garbage. The recycling of garbage is also a hot topic today. The project will propo...
详细信息
Induction motors (IMs) have been a cornerstone in industrial applications for decades due to their robustness, reliability, and efficiency. However, as the reliance on these motors has increased, so has the necessity ...
详细信息
Aiming at the problems of single feature dimension and low accuracy in condition monitoring only from vibration characteristics and tool wear characteristics. In this paper, a tool wear state recognition method based ...
详细信息
ISBN:
(纸本)9798350375084;9798350375077
Aiming at the problems of single feature dimension and low accuracy in condition monitoring only from vibration characteristics and tool wear characteristics. In this paper, a tool wear state recognition method based on multi-source feature fusion and deep learning is proposed. The main innovation of our work lies in two aspects: firstly, the tool wear data is processed by multi-source feature fusion method, which effectively fuses multiple sensor signals and improves the efficiency and accuracy of data processing. Secondly, we optimize GRU (Gated Recursive Unit) model by combining whale algorithm for parameter optimization and add XGBoost to improve the prediction performance and robustness. Different milling wear experimental data sets are used to verify the recognition performance of the training model. The experimental results show that compared with the traditional methods, our proposed method has obvious advantages in tool wear state recognition.
Chronic kidney disease (CKD) is a significant global health problem with a high mortality and morbidity rate that also contributes to other ailments. Since there aren't any evident symptoms during the early stages...
详细信息
This paper explores significant advances in machinelearning (ML) in the field of natural language processing (NLP), with an emphasis on transformative innovations such as transformer models and large language models ...
详细信息
Glass was introduced to China from West Asia and Egypt through the early Silk Road. Its primary raw material is quartz sand, which has a high melting point. Therefore, during refinement, a flux is added to lower the m...
详细信息
ISBN:
(纸本)9798350375084;9798350375077
Glass was introduced to China from West Asia and Egypt through the early Silk Road. Its primary raw material is quartz sand, which has a high melting point. Therefore, during refinement, a flux is added to lower the melting point. The performance of glass artifacts is influenced by different materials, making the analysis and identification of chemical composition crucial in the study of ancient Chinese glass. In this paper, non-parametric tests and machinelearning techniques, including cluster analysis and KNN algorithm, are employed to analyze and identify a collection of ancient glass artifacts. This research investigated the relationship between the weathering condition of glass and its type, patterns, and colors, and predicted the chemical composition of these artifacts prior to weathering. Additionally, a detailed sub-classification and analysis of the chemical composition of glass artifacts is conducted to accurately identify different types of glass, focused on the classification patterns of two specific types of glass, namely high-potassium glass and lead-barium glass as well. Furthermore, the correlation between the chemical compositions of glass artifacts from different categories is also analyzed.
The combination of neural network-based predictive analytics is the focus of this study, which introduces a novel approach to IoT-based real-time health monitoring systems. Using techniques such as RSME, SVM, and LSTM...
详细信息
The combination of neural network-based predictive analytics is the focus of this study, which introduces a novel approach to IoT-based real-time health monitoring systems. Using techniques such as RSME, SVM, and LSTM, an exhaustive investigation of the performance of prediction models are conducted. The proposed model demonstrates significant improvements in accuracy, with a 98.25% LSTM accuracy, an 83.73% RSME accuracy, and an 86.25% SVM accuracy. The findings of this study demonstrate that, in comparison to the currently used models, the accuracy of LSTM is greater while maintaining competitive performance in RSME and SVM. Integrating neural network-based predictive analytics with the IoT enables responsible deployment in healthcare applications, improving accuracy and reliability in real-time health monitoring. To enhance patient care and well-being, this endeavor contributes to advancing the area of health monitoring systems based on the IoT by providing technologically sound solutions.
With the advent of 5G and the Internet of Things (IoT), the demand for stable and reliable communication services continues to rise steadily. The deployment of Space-Air-Ground Integrated Network (SAGIN) is poised to ...
详细信息
ISBN:
(纸本)9798350375084;9798350375077
With the advent of 5G and the Internet of Things (IoT), the demand for stable and reliable communication services continues to rise steadily. The deployment of Space-Air-Ground Integrated Network (SAGIN) is poised to accelerate the fulfillment of future communication service requirements by leveraging a combination of unmanned aerial vehicles (UAVs) and satellite communications to complement the insufficient ground communication infrastructure. In this paper, we propose a comprehensive Non-Terrestrial Network (NTN) architecture comprising High Altitude Platforms (HAPS) and Low Altitude Platforms (LAPS). Considering the intricate characteristics of heterogeneity, resource complexity, and mobility flexibility inherent in SAGIN, we present a joint three-dimensional trajectory design and channel allocation optimization algorithm. The aim is to maximize network capacity while ensuring fairness in wireless resource allocation for the aerial base stations composed of HAPS and UAVs. Through the utilization of Deep Reinforcement learning (DRL), the efficacy of our proposed approach is validated via computer simulations.
暂无评论