检索结果-内蒙古大学图书馆

Mechanical ventilation intervention based on machine learning from vital signs monitoring: a scoping review

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第6期34卷 062001-062001页

作者： Baidillah, Marlin Ramadhan Busono, Pratondo Riyanto, Riyanto Natl Res & Innovat Agcy Res Ctr Elect Bandung 40135 Indonesia

Asynchronous breathing (AB) during mechanical ventilation (MV) may lead to a detrimental effect on the patient's condition. Due to the massive amount of data displayed in a large ICU, a machine learning algorithm (MLA) was proposed extensively to extract the patterns within the multiple continuous-in-time vital signs, to determine which are the variables that will predict the AB, to intervene in the MV as an early warning system, and finally to replace a highly demand of clinician's cognition. This study reviews the MLA for prediction and detection models from vital signs monitoring data for MV intervention. Publication on MLA development on MV intervention based on vital signs monitoring to support clinicians' decision-making process was extracted from the three electronic academic research databases Web of Science Core Collection (WoSCC), ScienceDirect, and PUBMED Central to February 2023. 838 papers from the electronic academic research databases are extracted. There are 14 review papers, while 25 related papers that pass with the quality assessments (QA). Few studies have been published that considered VS monitoring data along with the MV parameters waveforms for MV intervention. Vital signs monitoring data is not the only predictor in the developed MLA. Most studies suggested that developing the MLA for direct MV intervention requires more concern in the pre-processing of real-time data to avoid false positive and false detection than developing MLA itself.

关键词： mechanical ventilation multiple continuous-in-time vital signs machine learning algorithm asynchronous breathing

来源：评论

学校读者我要写书评

暂无评论

Co-pyrolytic interactions and products of brominated epoxy resin and polyethylene terephthalate: TG-FTIR analysis and machine learning prediction

引用

JOURNAL OF ANALYTICAL AND APPLIED PYROLYSIS 2023年 175卷

作者： Xu, Ziming Cheng, Can Zhong, Jian Gao, Wenhao Li, Jinping Liu, Jingxin Wuhan Text Univ Sch Environm Engn Wuhan 430073 Peoples R China Wuhan Text Univ Engn Res Ctr Clean Prod Text Dyeing & Printing Minist Educ Wuhan 430073 Peoples R China

Pyrolysis is an effective approach for organic waste utilization, and the co-pyrolysis of multiple materials holds potential for both environmental and economic benefits. Brominated epoxy resin (BER) and polyethylene terephthalate (PET) are widely used organic materials in modern society, and the productions of their corresponding wastes are increasing annually. However, limited research has been conducted on the co-pyrolysis of BER and PET. In this study, mixtures of BER and PET were prepared in various proportions, and thermogravimetry (TG) and thermogravimetry-Fourier transform infrared spectroscopy (TG-FTIR) analyses were employed to investigate the reaction characteristics, volatile product compositions, and evolution during co-pyrolysis. Synergistic effects were observed at lower temperatures in the major reaction stage for mixtures with PET content below 40%, while inhibitory effects were noted at higher temperatures. For mixtures with PET content over 40%, the antagonistic effect was more prominent. The main volatile products during co-pyrolysis were identified as CO2, benzoic acid, and alcohols, and their evolutions exhibited complex changes due to interactions. In addition, machine learning algorithms successfully predicted real-time volatile emissions, with the random forest model proving accurate. This study enhanced understanding of organics interactions during thermal treatment and would contribute to the reduction of environmental pollution.

关键词： Brominated epoxy resin (BER) Polyethylene terephthalate (PET) Co-pyrolysis characteristics Product identification machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Battery Temperature Prediction Using LSTM algorithm 4

Electric Vehicle Battery Temperature Prediction Using LSTM A...

引用

4th IEEE International Conference on Sustainable Energy and Future Electric Transportation, SEFET 2024

作者： Sridhar, B. Allirani, S. Reshmin Shafi, R.S. Rithvik Abinav, K.R. Siddharth, A. Sri Ramakrishna Engineering College Department of Eee Coimbatore India

ISBN: (纸本)9798350383997

In a rapidly evolving world, characterized by a growing emphasis on sustainable transportation, the pursuit of enhanced Electric Vehicle (EV) efficiency and reliability has become paramount. This abstract presents an innovative and intelligent system poised to redefine the management of EV batteries, prioritizing optimal performance and user safety. Our notable framework uses the capacities of cutting-edge LSTM machine learning algorithm to precisely anticipate, screen, and control EV battery temperatures. Its core objectives are clear: maintain battery temperatures within the optimal range and pre-emptively identify critical anomalies before they escalate. At the heart of this system lies its machine learning capabilities, continuously forecasting battery temperature trends. When optimal temperature is not within the stipulated range, the system swiftly takes action with dual purposes: heating or cooling the battery to safeguard its health and extend its lifespan. Yet, this system goes beyond mere reactivity to temperature extremes;it excels in predictive prowess, identifying irregularities in battery temperature patterns before they become critical issues. This proactive approach equips the system to issue timely alerts and intervene to prevent potential hazards. Statistics, enabling them to stay well-informed, take preventive actions, and experience worry-free journeys. © 2024 IEEE.

关键词： Electric Vehicle (EV) Long Short Term algorithm (LSTM) machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic Train Overpass Using Camera and Load Sensors and Obstacle Detection 2

Automatic Train Overpass Using Camera and Load Sensors and O...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Sharma, Aravendra Kumar Dubey, Ratnesh Kumar Mishra, Shubha Sharma, Suraj Itm University Csa Department Gwalior India Mits Center for Ai Department Gwalior India

ISBN: (纸本)9798350371055

In India, the most used means of transportation is rail. Enhancements are required to modern technology in order to make it safer for the general population. In this context, the research offers suggestions for automating railway gate operations. The level crossing responds to the arrival and departure of trains nearby by opening and closing on its own using Internet of Things load sensors and warning signals (buzzers or sirens). During the buffer closure period, an automobile may become stuck on the track in between crossing gates. It will be recognized by camera sensors, and Internet of Things sensors will alert the gate closing mechanism. This might significantly reduce the number of labor-intensive tasks and incidents at level crossings. © 2024 IEEE.

关键词： Automatic railway crossing Internet of things (IoT) machine learning algorithm unmanned crossing

来源：评论

学校读者我要写书评

暂无评论

Microheater Integrated Nanotube Array Gas Sensor for Parts-Per-Trillion Level Gas Detection and Single Sensor-Based Gas Discrimination

引用

ACS NANO 2022年第7期16卷 10968-10978页

作者： Tang, Wenying Chen, Zhesi Song, Zhilong Wang, Chen Wan, Zhu'an Chan, Chak Lam Jonathan Chen, Zhuo Ye, Wenhao Fan, Zhiyong Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Kowloon Hong Kong Peoples R China Hong Kong Univ Sci & Technol Shenzhen Res Inst Shenzhen 518057 Peoples R China

Real-time monitoring of health threatening gases for chemical safety and human health protection requires detection and discrimination of trace gases with proper gas sensors. In many applications, costly, bulky, and power-hungry devices, normally employing optical gas sensors and electro-chemical gas sensors, are used for this purpose. Using a single miniature low-power semiconductor gas sensor to achieve this goal is hardly possible, mostly due to its selectivity issue. Herein, we report a dual-mode microheater integrated nanotube array gas sensor (MINA sensor). The MINA sensor can detect hydrogen, acetone, toluene, and formaldehyde with the lowest measured limits of detection (LODs) as 40 parts-per-trillion (ppt) and the theoretical LODs of ~7 ppt, under the continuous heating (CH) mode, owing to the nanotubular architecture with large sensing area and excellent surface catalytic activity. Intriguingly, unlike the conventional electronic noses that use arrays of gas sensors for gas discrimination, we discovered that when driven by the pulse heating (PH) mode, a single MINA sensor possesses discrimination capability of multiple gases through a transient feature extraction method. These above features of our MINA sensors make them highly attractive for distributed low-power sensor networks and battery-powered mobile sensing systems for chemical/environmental safety and healthcare applications.

关键词： gas sensor pulse-heating trace gas detection machine learning algorithm single-sensor gas discrimination

来源：评论

学校读者我要写书评

暂无评论

Understanding Influencing Factors of Travel Mode Choice in Urban-Suburban Travel: A Case Study in Shanghai

引用

URBAN RAIL TRANSIT 2023年第2期9卷 127-146页

作者： Le, Jiankun Teng, Jing Tongji Univ Urban Mobil Inst 4800 Caoan Highway Shanghai Peoples R China Tongji Univ Coll Transportat Engn Key Lab Rd & Traff Engn Minist Educ 4800 Caoan Highway Shanghai Peoples R China Tongji Univ Shanghai Collaborat Innovat Res Ctr Multinetwork & Shanghai 201804 Peoples R China

After the rapid expansion of the subway system over the past two decades, some cities are preparing to build more suburban railways. The emergence of suburban railways is bound to change the choice of suburban passenger transportation. This paper studies the factors that affect the choice of travel mode at the construction stage of suburban railways, aiming to design a more rational suburban railway network and urban public transport service system. Taking Shanghai as an example, this study first surveyed revealed preference (RP) and stated preference (SP) among urban-suburban travelers. Then, we used discrete choice models (DCM) and machine learning algorithms to build a travel mode choice model based on data collection and analysis. Furthermore, the importance of each factor was analyzed, and the effects were predicted under several traffic demand management schemes. Finally, this study proposed some strategies for increasing the share of public transport. On the one hand, it is suggested that Shanghai should continue to develop suburban railways and maintain low pricing of public transport services. Considering the construction and operation costs, the government needs to provide certain subsidies to stabilize prices. On the other hand, as passengers are very sensitive to the "last mile" trips in their suburban railway travel, transport planners should strengthen the connection from and to the suburban railway stations by developing services such as shared bikes and shuttle buses. In addition, the results indicated that some traffic demand management measures can also contribute to a larger share of public transport.

关键词： Travel mode choice Urban-suburban transportation corridors Discrete choice models Influencing factors machine learning algorithm RP and SP survey

来源：评论

学校读者我要写书评

暂无评论

Creation of a machine learning-based prognostic prediction model for various subtypes of laryngeal cancer

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-14页

作者： Wang, Wei Wang, Wenhui Zhang, Dongdong Zeng, Peiji Wang, Yue Lei, Min Hong, Yongjun Cai, Chengfu Xiamen Univ Zhongshan Hosp Sch Med Dept Otolaryngol Head & Neck Surg Xiamen Peoples R China Xiamen Univ Sch Med Xiamen Peoples R China Haicang Hosp Xiamen Med Coll Otorhinolaryngol Head & Neck Surg Xiamen Peoples R China

Depending on the source of the blastophore, there are various subtypes of laryngeal cancer, each with a unique metastatic risk and prognosis. The forecasting of their prognosis is a pressing issue that needs to be resolved. This study comprised 5953 patients with glottic carcinoma and 4465 individuals with non-glottic type (supraglottic and subglottic). Five clinicopathological characteristics of glottic and non-glottic carcinoma were screened using univariate and multivariate regression for CoxPH (Cox proportional hazards);for other models, 10 (glottic) and 11 (non-glottic) clinicopathological characteristics were selected using least absolute shrinkage and selection operator (LASSO) regression analysis, respectively;the corresponding survival models were established;and the best model was evaluated. We discovered that RSF (Random survival forest) was a superior model for both glottic and non-glottic carcinoma, with a projected concordance index (C-index) of 0.687 for glottic and 0.657 for non-glottic, respectively. The integrated Brier score (IBS) of their 1-year, 3-year, and 5-year time points is, respectively, 0.116, 0.182, 0.195 (glottic), and 0.130, 0.215, 0.220 (non-glottic), demonstrating the model's effective correction. We represented significant variables in a Shapley Additive Explanations (SHAP) plot. The two models are then combined to predict the prognosis for two distinct individuals, which has some effectiveness in predicting prognosis. For our investigation, we established separate models for glottic carcinoma and non-glottic carcinoma that were most effective at predicting survival. RSF is used to evaluate both glottic and non-glottic cancer, and it has a considerable impact on patient prognosis and risk factor prediction.

关键词： Laryngeal carcinoma Survival analysis machine learning algorithm Individual prediction

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Support Vector machine (SVM) for Diabetes Disease Detection 5

Performance Analysis of Support Vector Machine (SVM) for Dia...

引用

5th International Conference on Artificial Intelligence and Data Sciences, AiDAS 2024

作者： Krisdianto, Ricky Apriani, Ivana Masada, Hossey Hidayaturrahman School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331528553

Diabetes is an important health problem and has a significant mortality rate in Indonesia, so it is one of the diseases that need further attention. In medical diagnosis, classification methods are extensively utilized to build models using machine learning algorithms for predicting medical outcomes based on patient data. Support Vector machine (SVM) is one of the machine learning algorithms used in predicting diseases including diabetes. The purpose of this study was to discover the optimal performance achieved by the SVM kernel model in predicting diabetes. Two datasets containing 9 and 22 features are being utilized in this research to identify the relationships influencing the model's accuracy performance. Also applying preprocessing methods based on the needs of each dataset to improve the accuracy of the model. The result of this research shows that the Radial Basis Function is the best kernel, achieving 97% accuracy in the first dataset and 87% accuracy in the second dataset. © 2024 IEEE.

关键词： Diabetes Disease Kernel Functions machine learning algorithm Radial Basis Function Support Vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Intelligent LoRa-Based Positioning System

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2022年第9期16卷 2961-2975页

作者： Chen, Jiann-Liang Chen, Hsin-Yun Ma, Yi-Wei Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei Taiwan

The Location-Based Service (LBS) is one of the most well-known services on the Internet. Positioning is the primary association with LBS services. This study proposes an intelligent LoRa-based positioning system, called AI@LBS, to provide accurate location data. The fingerprint mechanism with the clustering algorithm in unsupervised learning filters out signal noise and improves computing stability and accuracy. In this study, data noise is filtered using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm, increasing the positioning accuracy from 95.37% to 97.38%. The problem of data imbalance is addressed using the SMOTE (Synthetic Minority Over-sampling Technique) technique, increasing the positioning accuracy from 97.38% to 99.17%. A field test in the NTUST campus (***) revealed that AI@LBS system can reduce average distance error to 0.48m.

关键词： Location-Based Service LoRa Fingerprint Mechanism machine learning algorithm Synthetic Minority Over-sampling Technique (SMOTE) Density-Based Spatial Clustering of Applications with Noise (DBSCAB)

来源：评论

学校读者我要写书评

暂无评论

Utilization of random forest classifier and artificial neural network for predicting the acceptance of reopening decommissioned nuclear power plant

引用

ANNALS OF NUCLEAR ENERGY 2022年 175卷

作者： Ong, Ardvin Kester S. Prasetyo, Yogi Tri Velasco, Kenzo Emmanuel C. Abad, Eman David R. Buencille, Adrian Louis B. Estorninos, Ezekiel M. Labso Cahigas, Maela Madel Chuenyindee, Thanatorn Persada, Satria Fadil Nadlifatin, Reny Sittiwatethanasiri, Thaninrat Mapua Univ Sch Ind Engn & Engn Management 658 Muralla St Manila 1002 Philippines Yuan Ze Univ Dept Ind Engn & Management 135 Yuan Tung Rd Chungli 32003 Taiwan Mapua Univ Young Innovators Res Ctr 658 Muralla St Manila 1002 Philippines Mapua Univ Sch Grad Studies 658 Muralla St Manila 1002 Philippines Navaminda Kasatriyadhiraj Royal Air Force Acad Dept Ind Engn & Aviat Management Bangkok 10220 Thailand Bina Nusantara Univ BINUS Business Sch Undergrad Program Entrepreneurship Dept Jakarta 11480 Indonesia Inst Teknol Sepuluh Nopember Dept Informat Syst Kampus ITS Sukolilo Surabaya 60111 Indonesia

The Bataan Nuclear Power Plant (BNPP) is one of the many decommissioned Nuclear Power Plant (NPP) globally and its reopening has led to different perceptions among Filipinos. It was established in 1984 but was not utilized due to political liability and safety reasons. This study aimed to predict factors affecting the acceptance of the BNPP by utilizing machine learning algorithms (MLA). The MLAs utilized in this study were Decision Tree, Random Forest Classifier (RFC), and Artificial Neural Network (ANN) as a high -light to predict human behavior. 1,252 Filipinos voluntarily answered an online questionnaire which con -sist of 37 questions, leading to 46,324 datasets. MLA showed that Filipinos are knowledgeable about the benefits of NPPs, leading to the acceptance of the reopening of the BNPP. In addition, MLA indicated that perceived benefits (PB) was found to be the highest factor that affect the Filipino's acceptance of the reopening of BNPP. Job opportunities, economic growth, lower and clean energy consumption, and sus-tainability were the indicators for the acceptance of the reopening of BNPP. Interestingly, the result showed that PB relatively outweighed the perceived risk of the BNPP. ANN and RFC proved to be effective with accuracy rates of 93.44% and 97.00%, respectively. Finally, the MLA approach in this study can be applied and extended in predicting the acceptance of NPPs worldwide.(c) 2022 Elsevier Ltd. All rights reserved.

关键词： Bataan nuclear power plant Artificial neural network Random forest classifier machine learning algorithm Human behavior Bataan nuclear power plant Artificial neural network Random forest classifier machine learning algorithm Human behavior

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：