Monitoring nitrate levels in water bodies is crucial, as excessive nitrate concentrations can cause eutrophication and potentially harmful impacts on human. this paper presents the realization process of a nitrate sen...
详细信息
the proceedings contain 80 papers. the topics discussed include: a review of research on the security of train control networks;optimal replacement policy for wireless sensor networks considering loss;a study on relia...
ISBN:
(纸本)9798350356083
the proceedings contain 80 papers. the topics discussed include: a review of research on the security of train control networks;optimal replacement policy for wireless sensor networks considering loss;a study on reliability algorithm for complex electronic systems with periodic maintenance;research on risk assessment method for aircraft braking system based on improved FMEA;evaluating the A3RSRP handover to determine optimal performance in HetNet using stochastic petri net;preliminary research on human error analysis and accident risk assessment of operators with dynamic human-machine interaction simulation of advanced control room in nuclear power plants;intelligent fault diagnosis of rolling bearing based on incremental learning;and a remaining useful life prediction method for hydrogen fuel cell based on a multi-phase wiener process-based degradation model.
Learning trustworthy models is essential for machine learning tasks, as many researchers have revealed the vulnerability of machine learning models, especially when the fundamental independent and identically distribu...
详细信息
ISBN:
(纸本)9798350363029;9798350363012
Learning trustworthy models is essential for machine learning tasks, as many researchers have revealed the vulnerability of machine learning models, especially when the fundamental independent and identically distributed (IID) assumption is not satisfied. Building a trustworthy model is promising when training on big representative data but fails to work with limited data. In this paper, we focus on solving small sample problems and unstable prediction problems in machine learning. First, to deal with small sample problems, we propose using a uniform manifold approximation and projection (UMAP) algorithm to generate high-quality virtual samples. then, withthe generated big data and original small data, we use the stable learning method to achieve stable predictions. In addition to a detailed description of the UMAP algorithm and the stable learning algorithm, we also discuss the corresponding theoretical explanations and implementation details. Finally, several comparison studies are implemented on the Tennessee Eastman benchmark process to validate the effectiveness of the proposed method.
Nowadays, networks are increasingly reliant on software frameworks and virtualization. To obtain relevant pre-dictions of the behavior of their protocols, network emulation tools play a crucial role. However, as netwo...
详细信息
the proceedings contain 358 papers. the topics discussed include: high gain dc-dc converter based on quasi-Z-Source;short-term smart grid load forecasting based on CNN-BiLSTM with attention mechanism;research on maxim...
ISBN:
(纸本)9798350377798
the proceedings contain 358 papers. the topics discussed include: high gain dc-dc converter based on quasi-Z-Source;short-term smart grid load forecasting based on CNN-BiLSTM with attention mechanism;research on maximum power point tracking control method for ship photovoltaic system;effect of AC voltage frequency on partial discharge characteristics of GIS;distributed rapid fault self-healing scheme for active distribution networks;load optimization control method for multiple open rack vaporizers in liquefied natural gas station;analysis of transient stability in wind power grid integration systems;and random forest based heating power prediction for single crystal furnace.
Detecting human stress levels and emotional states with physiological body-worn sensors is a complex task, but one with many health-related benefits. Robustness to sensor measurement noise and energy efficiency of low...
详细信息
ISBN:
(纸本)9781665495127
Detecting human stress levels and emotional states with physiological body-worn sensors is a complex task, but one with many health-related benefits. Robustness to sensor measurement noise and energy efficiency of low-power devices remain key challenges in stress detection. We propose SELFCARE, a fully wrist-based method for stress detection that employs context-aware selective sensor fusion that dynamically adapts based on data from the sensors. Our method uses motion to determine the context of the system and learns to adjust the fused sensors accordingly, improving performance while maintaining energy efficiency. SELF-CARE obtains state-of-theart performance across the publicly available WESAD dataset, achieving 86.34% and 94.12% accuracy for the 3-class and 2-class classification problems, respectively. Evaluation on real hardware shows that our approach achieves up to 2.2x (3-class) and 2.7x (2-class) energy efficiency compared to traditional sensor fusion.
the article describes the capabilities of a real-time operating system (RTOS) from the point of view of its application in solving problems of controlling power electronics devices. Using the example of implemented po...
详细信息
In the distribution substation, edge computing can optimize the allocation and utilization of overall distributed resources, which is essential for ensuring efficient energy utilization and stable operation of the pow...
详细信息
the proceedings contain 289 papers. the topics discussed include: evaluation of cognitive computing and algorithms in engineering;a study on the application of using hypernetwork and low rank adaptation for text-to-im...
ISBN:
(纸本)9798350382891
the proceedings contain 289 papers. the topics discussed include: evaluation of cognitive computing and algorithms in engineering;a study on the application of using hypernetwork and low rank adaptation for text-to-image generation based on diffusion models;radar based lateral clearance decreasing warning system;improving production management and control with intelligent chatbot services;interrogation of SAW-resonator-based vibration sensor by low cost SDR;development of a beam steering system for a phased antenna array with variable duration of control pulses;algorithms for optimizing the values of parametric series of machine tools;metagraph storage implementation using relational database based on mutability/temporality approach;and quadrupole microwave diagnostics of azimuthally asymmetric plasma formations.
Multidimensional parallel training has been widely applied to train large-scale deep learning models like GPT-3. the efficiency of parameter communication among training devices/processes is often the performance bott...
详细信息
暂无评论