Predicting heat transfer of oscillating heat pipes for machining processes based on extreme gradient boosting algorithm

Qian, Ning; Wang, Xuesong; Fu, Yucan; Zhao, Zhengcai; Xu, Jie; Chen, Jiajia

doi:10.1016/j.applthermaleng.2019.114521

Cited by 56 publications

(29 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the logit approach, widely used in management studies, to a machine learning (ML) approach based on pattern recognition (Freund & Schapire, 1997 ; Friedman, 2002 ) since the language descriptors of a text provide a pattern. In particular, among the plethora of pattern recognition engines available in the ML tradition, we selected a gradient boosting algorithm (Chen & He, 2020 ; Friedman, 2001 , 2002 ; Natekin & Knoll, 2013 ; Qian et al, 2020 ; Ridgeway, 1999 ; Ridgeway & Ridgeway, 2004 ). The gradient boosting approach is based on a combination of Classification And Regression Trees (CART; Friedman, 2001 ; Friedman et al, 2000 ; Ridgeway, 1999 ; Therneau & Atkinson, 1997 ) as base classifiers, each obtained on a bootstrap replicate of the training set (e.g.…”

Section: Empirical Analysismentioning

confidence: 99%

“…Ultimately, CARTs on each bootstrap replicates will follow this over(under)-representation of patterns providing a low-performing family of classifiers. Nevertheless, their combination will provide a high-performing forecasting tool (Chen & He, 2020 ; Friedman et al, 2000 ; Friedman, 2001 , 2002 ; Natekin & Knoll, 2013 ; Qian et al, 2020 ; Ridgeway, 1999 ; Ridgeway & Ridgeway, 2004 ). Noteworthy, current implementations of gradient boosting machine provide a relative ranking of the variables ( predictors in the ML tradition) that can be operationally used.…”

Section: Empirical Analysismentioning

confidence: 99%

“…retweeted tweets). By applying an extension of the algorithm, xtreme gradient boosting (Chen & He, 2020 ; Qian et al, 2020 ) we obtained an overall performance of 83.58% of correct predictions including the 96.93% of negatives (i.e. not retweeted tweets) and the 9.63% of the positives (i.e.…”

Section: Empirical Analysismentioning

confidence: 99%

See 2 more Smart Citations

Linguistic drivers of misinformation diffusion on social media during the COVID-19 pandemic

2021

View full text Add to dashboard Cite

In the wake of the COVID-19 pandemic, unprecedent amounts of fake news and hoax spread on social media. In particular, conspiracy theories argued on the effect of specific new technologies like 5G and misinformation tarnished the reputation of brands like Huawei. Language plays a crucial role in understanding the motivational determinants of social media users in sharing misinformation, as people extract meaning from information based on their discursive resources and their skillset. In this paper, we analyze textual and non-textual cues from a panel of 4923 tweets containing the hashtags #5G and #Huawei during the first week of May 2020, when several countries were still adopting lockdown measures, to determine whether or not a tweet is retweeted and, if so, how much it is retweeted. Overall, through traditional logistic regression and machine learning, we found different effects of the textual and non-textual cues on the retweeting of a tweet and on its ability to accumulate retweets. In particular, the presence of misinformation plays an interesting role in spreading the tweet on the network. More importantly, the relative influence of the cues suggests that Twitter users actually read a tweet but not necessarily they understand or critically evaluate it before deciding to share it on the social media platform.

show abstract

Section: Empirical Analysismentioning

confidence: 99%

Section: Empirical Analysismentioning

confidence: 99%

See 1 more Smart Citation

Linguistic drivers of misinformation diffusion on social media during the COVID-19 pandemic

2021

View full text Add to dashboard Cite

show abstract

“…The XGBoost summarizes all weights provided from each CART and outputs a final score. Details about the XGBoost can be found in [29].…”

Section: Figure 1 Density Plot and Histogram Of Daily Mcp Datasetmentioning

confidence: 99%

Prediction of market-clearing price using neural networks based methods and boosting algorithms

Ipek

2021

International Advanced Researches and Engineering Journal

View full text Add to dashboard Cite

The development of Turkey's industry is contributing to a significant rise in electrical energy demand. Also, electricity is one of the critical elements in the household sectors. Therefore, the planning and managing of electrical energy is of great importance to support economic growth. In addition, effective prediction of market-clearing prices (MCP) is critical topic to meet the increasing energy demand and provide basis for decision making process. In this paper, MCP is predicted using artificial neural network (ANN), convolutional neural network (CNN), and also three boosting algorithms including extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and adaptive boosting (AdaBoost). Various performance metrics are employed to evaluate the prediction performance of proposed methods. The results showed that proposed methods provide reasonable prediction results for energy sector. Hence, producers and consumers can use these methods to determine the bidding strategies and to maximize their profits.

show abstract

“…The heat transfer analysis was studied to the point of the proof of concept. The heat transfer prediction model was built, and the start-up performance was also analyzed [23,24].…”

Section: Introductionmentioning

confidence: 99%

Heat Transport Capacity of an Axial-Rotating Single-Loop Oscillating Heat Pipe for Abrasive-Milling Tools

Qian

Marengo

et al. 2020

Energies

Self Cite

View full text Add to dashboard Cite

In order to enhance heat transfer in the abrasive-milling processes to reduce thermal damage, the concept of employing oscillating heat pipes (OHPs) in an abrasive-milling tool is proposed. A single-loop OHP (SLOHP) is positioned on the plane parallel to the rotational axis of the tool. In this case, centrifugal accelerations do not segregate the fluid between the evaporator and condenser. The experimental investigation is conducted to study the effects of centrifugal acceleration (0–738 m/s2), heat flux (9100–31,850 W/m2) and working fluids (methanol, acetone and water) on the thermal performance. Results show that the centrifugal acceleration has a positive influence on the thermal performance of the axial-rotating SLOHP when filled with acetone or methanol. As for water, with the increase of centrifugal acceleration, the heat transfer performance first increases and then decreases. The thermal performance enhances for higher heat flux rises for all the fluids. The flow inside the axial-rotating SLOHP is analyzed by a slow-motion visualization supported by the theoretical analysis. Based on the theoretical analysis, the rotation will increase the resistance for the vapor to penetrate through the liquid slugs to form an annular flow, which is verified by the visualization.

show abstract

Predicting heat transfer of oscillating heat pipes for machining processes based on extreme gradient boosting algorithm

Cited by 56 publications

References 48 publications

Linguistic drivers of misinformation diffusion on social media during the COVID-19 pandemic

Linguistic drivers of misinformation diffusion on social media during the COVID-19 pandemic

Prediction of market-clearing price using neural networks based methods and boosting algorithms

Heat Transport Capacity of an Axial-Rotating Single-Loop Oscillating Heat Pipe for Abrasive-Milling Tools

Contact Info

Product

Resources

About