In the hot-rolling metal forming process, the consistency and accuracy of the thickness of the metal strip are the most important factors for the product quality control. The current method of utilizing a mechanism pr...
详细信息
In the hot-rolling metal forming process, the consistency and accuracy of the thickness of the metal strip are the most important factors for the product quality control. The current method of utilizing a mechanism prediction model with pre-defined parameters does not perform well due to some limits on the model assumptions and environmental interfer-ence. Manually tuning these parameters of the mechanism model may even result in worse performance. To resolve this problem, an advanced randomized learner model, termed stochastic configuration network (SCN), is employed to build a data-driven prediction model which can be trained by using a dataset collected from a real-world hot-rolling pro-duction site. Based on the rolling theory and gray relational analysis (GRA), 36 features are selected as the inputs of the prediction model. Experimental results with comparisons show that our proposed method is feasible and outperforms other machine learning meth-ods, such as deep learning models and the random vector functional link (RVFL) model. (c) 2022 Published by Elsevier Inc.
Post-acute sequelae of SARS-CoV-2 infection (PASC), also known as Long COVID, is an emerging medical condition in the aftermath of the COVID-19 pandemic. Research on this disease is limited by its newness and the lack...
详细信息
ISBN:
(纸本)9798350345346
Post-acute sequelae of SARS-CoV-2 infection (PASC), also known as Long COVID, is an emerging medical condition in the aftermath of the COVID-19 pandemic. Research on this disease is limited by its newness and the lack of reliable controls, which can hinder model development. The National COVID Cohort Collaborative (N3C)1 contains Electronic Health Record (EHR) data for 7 million COVID positive patients from 76 sites across the United States, of which there are fifty thousand Long COVID patients. For this study, we model our risk factor analysis as Positive Unlabeled (PU) problem, where we treat Long COVID patients as the positive sample and rest of the COVID positive patients as unlabeled data. We first curate reliable controls using a PU modeling technique called bagging. We then use this cohort of positive and the curated negative samples to model risk factors for Long COVID. We utilize an attention-based deep learning approach using Long Short Term Memory (LSTM) networks on historical diagnosis data prior to COVID-19 infection, to first predict for Long COVID and then extract the model attention values to score input diagnoses for each patient. Using this process, we achieve an Area Under the Receiver Operating Characteristic (AUROC) of 0.93 (0.88 F1 Score) for the prediction task, significantly outperforming the same model trained on randomly selected controls. We then use a scoring process to rank different input diagnoses for each correctly classified patient with attention values extracted from the trained model and find the temporal distribution of top diagnosis codes which, when represented graphically, becomes a helpful tool to for physicians to investigate diagnosis patterns that effect Long COVID and also evaluate model trustworthiness.
Aiming at the problem of poor fault detection in complex industrial processes, this paper proposes a fault detection method based on improved Euclidean distance control. First, the data is standardized and the Euclide...
详细信息
ISBN:
(纸本)9781665409841
Aiming at the problem of poor fault detection in complex industrial processes, this paper proposes a fault detection method based on improved Euclidean distance control. First, the data is standardized and the Euclidean distance is obtained;Secondly, the distance value with a larger data contribution rate is determined by the idea of exponential contribution;Thirdly, a parameter adaptive strategy is proposed to set the threshold of Euclidean distance statistics;Finally, fault detection is carried out on the statistical data, and the size of false negative rate and false alarm rate is calculated. In the fourth part of this paper, we use the fault detection method based on improved Euclidean distance control to detect the fault of the Eastman process in Tennessee. The simulation results show that the method proposed in this paper has more advantages than the traditional principal component analysis method, and can be effectively applied to complex industrial processes.
With the continuous improvement of China's comprehensive transportation system and tourism gradually becoming an important strategic pillar industry of the national economy, the integrated development of transport...
详细信息
Wireless Sensor Networks (WSNs) are essential in the collection of real time data across different fields, including environmental monitoring and processcontrol. However, due to the bounded amount of energy in sensor...
详细信息
The COVID-19 pandemic has had a significant and unprecedented worldwide influence across the globe, increasing the number of cases and fatalities in various nations. To effectively mitigate and prevent its spread, it ...
详细信息
Aiming at the low efficiency of sewage treatment caused by the difficulty of timely measurement of effluent ammonia nitrogen concentration in the process of sewage treatment, a prediction model of effluent ammonia nit...
详细信息
ISBN:
(纸本)9781665478960
Aiming at the low efficiency of sewage treatment caused by the difficulty of timely measurement of effluent ammonia nitrogen concentration in the process of sewage treatment, a prediction model of effluent ammonia nitrogen concentration based on BiLSTM & GRU combined algorithm is proposed. Firstly, VMD algorithm is introduced to obtain the local characteristics of six water quality factors affecting effluent ammonia nitrogen concentration, such as BOD, COD and SS, on different time scales, and then PCA algorithm is used to reduce the dimension to eliminate the redundancy and correlation between data;Then, based on BiLSTM prediction model, combined with the GRU model, the effluent ammonia nitrogen concentration is predicted, and the Sparrow Search Algorithm is introduced to determine the weight of each prediction model to make up for the limitations of a single prediction model. Finally, it is verified by the measured data of a sewage treatment plant for one month, the simulation results show that the accuracy of the proposed prediction model is higher than that of the traditional water quality prediction model.
The stabilization of second order time delay process with proportional-integral-derivative (PID) controllers is investigated in the paper. The t decomposition method is utilized to decompose and characterize the contr...
详细信息
Purpose – To showcase the importance of Statistical processcontrol (SPC) in detecting and preventing errors in radiopharmaceutical dose dispensing in Nuclear Medicine imaging techniques, such as Positron Emission To...
详细信息
Sarcasm detection is challenging in natural language processing since its peculiar linguistic expression. Thanks in part to the availability of considerable annotated resources for some datasets, current supervised le...
详细信息
ISBN:
(纸本)9783031516702;9783031516719
Sarcasm detection is challenging in natural language processing since its peculiar linguistic expression. Thanks in part to the availability of considerable annotated resources for some datasets, current supervised learning-based approaches can achieve promising performance in sarcasm detection. In real-world scenarios, annotating data for the peculiar language expression of sarcasm proves challenging. Consequently, recent studies have delved into unsupervised learning approaches for sarcasm detection, seeking to mitigate the labor-intensive process of annotation. In this paper, we present a novel unsupervised sarcasm detection method leveraging abundant unlabeled social media data. Our approach revolves around employing prompts as a cornerstone. Initially, we gathered approximately 3 million texts from Twitter through targeted hashtag-based searches, segregating them into sarcasm and non-sarcasm categories based on associated hashtags. Subsequently, these collected texts undergo training using a pre-trained BERT model, customized for masked language modeling and coined as SarcasmBERT. This step aims to enhance the model's grasp of sarcastic cues within the text. Finally, we devise prompts tailored for the unlabeled data to execute unsupervised sarcasm detection effectively. Our experimental findings across six benchmark datasets highlight the superiority of our method over state-of-the-art unsupervised baselines. Additionally, the integration of our SarcasmBERT into established BERT-based sarcasm detection methods showcases a direct avenue for enhancing performance, thereby illustrating its potential for immediate and substantial improvements.
暂无评论