scholarly journals High Performance Energy Prediction using Hadoop with Spark

2018 ◽  
Vol 20 ◽  
pp. 02012
Author(s):  
Hung Duong-Ngoc ◽  
Hoan Nguyen-Thanh ◽  
Tam Nguyen-Minh

With the increasingly modern development of the power system. Along with that is the data source collected from them is huge. Combined with other systems such as GIS, MDMS-AMR (Automatic Meter Reading), weather forecast and socio-economic indicators. We consider performing an effective analysis of the data sources in order to understand the evolution, characteristics, and modeling of the power consumption system. Thereby predict future energy trends and build bases for the system model. To implement the issues raised, we appreciate using Hadoop platform for storage and segmentation data, enabling better handle large amounts of data initially. Then, the data was analyzed using the scalable machine learning algorithms - MLib was supported and developed on the Spark/SPARKNET platform. The Hadoop framework has recently evolved to the standard framework implementing the MapReduce model. In this paper, we evaluate Hadoop with Mlib/Sparknet performance in both the traditional model of collocated data and compute services as well as consider the impact of separating out the services. Energy modeling from multiple data sources such large may help to understand the change of the system according to consumer demand for practical, predictable trends of energy in the future and provide the basis for building energy models for similar systems.

Energies ◽  
2020 ◽  
Vol 13 (5) ◽  
pp. 1288 ◽  
Author(s):  
Philip Shine ◽  
John Upton ◽  
Paria Sefeedpari ◽  
Michael D. Murphy

The global consumption of dairy produce is forecasted to increase by 19% per person by 2050. However, milk production is an intense energy consuming process. Coupled with concerns related to global greenhouse gas emissions from agriculture, increasing the production of milk must be met with the sustainable use of energy resources, to ensure the future monetary and environmental sustainability of the dairy industry. This body of work focused on summarizing and reviewing dairy energy research from the monitoring, prediction modelling and analyses point of view. Total primary energy consumption values in literature ranged from 2.7 MJ kg−1 Energy Corrected Milk on organic dairy farming systems to 4.2 MJ kg−1 Energy Corrected Milk on conventional dairy farming systems. Variances in total primary energy requirements were further assessed according to whether confinement or pasture-based systems were employed. Overall, a 35% energy reduction was seen across literature due to employing a pasture-based dairy system. Compared to standard regression methods, increased prediction accuracy has been demonstrated in energy literature due to employing various machine-learning algorithms. Dairy energy prediction models have been frequently utilized throughout literature to conduct dairy energy analyses, for estimating the impact of changes to infrastructural equipment and managerial practices.


2014 ◽  
Vol 05 (03) ◽  
pp. 836-860 ◽  
Author(s):  
D.A. Hanauer ◽  
Y. Huang

SummaryBackground: Patient no-shows in outpatient delivery systems remain problematic. The negative impacts include underutilized medical resources, increased healthcare costs, decreased access to care, and reduced clinic efficiency and provider productivity.Objective: To develop an evidence-based predictive model for patient no-shows, and thus improve overbooking approaches in outpatient settings to reduce the negative impact of no-shows.Methods: Ten years of retrospective data were extracted from a scheduling system and an electronic health record system from a single general pediatrics clinic, consisting of 7,988 distinct patients and 104,799 visits along with variables regarding appointment characteristics, patient demographics, and insurance information. Descriptive statistics were used to explore the impact of variables on show or no-show status. Logistic regression was used to develop a no-show predictive model, which was then used to construct an algorithm to determine the no-show threshold that calculates a predicted show/no-show status. This approach aims to overbook an appointment where a scheduled patient is predicted to be a no-show. The approach was compared with two commonly-used overbooking approaches to demonstrate the effectiveness in terms of patient wait time, physician idle time, overtime and total cost.Results: From the training dataset, the optimal error rate is 10.6% with a no-show threshold being 0.74. This threshold successfully predicts the validation dataset with an error rate of 13.9%. The proposed overbooking approach demonstrated a significant reduction of at least 6% on patient waiting, 27% on overtime, and 3% on total costs compared to other common flat-overbooking methods.Conclusions: This paper demonstrates an alternative way to accommodate overbooking, accounting for the prediction of an individual patient’s show/no-show status. The predictive no-show model leads to a dynamic overbooking policy that could improve patient waiting, overtime, and total costs in a clinic day while maintaining a full scheduling capacity.Citation: Huang Y, Hanauer D.A. Patient no-show predictive model development using multiple data sources for an effective overbooking approach. Appl Clin Inf 2014; 5: 836–860http://dx.doi.org/10.4338/ACI-2014-04-RA-0026


Author(s):  
James M. Groh ◽  
Brittany Kasumi Yarnell

ObjectiveTo assess the prevalence of non-opioid substance use—including cocaine, methamphetamine and “spice”—within Marion County, Indiana and propose response recommendations utilizing a current opioid response plan.IntroductionCocaine, methamphetamine, and “spice” are addictive, non-opioid substances that negatively impact a person’s health through direct and indirect means. Direct health concerns of non-opioid substance use include anxiety, paranoia, seizure, heart attack, stroke, and potentially death while indirect health concerns include the acquisition of disease and infections, particularly sexually transmitted infections (STIs). Substance users experience an increased risk of acquiring STIs since they may exchange sex for substances, use substances within a social setting that may lead to sexual activity, or engage in risky sexual behavior as a result of impaired judgement associated with substance use. The current study evaluated the use of multiple data sources to monitor changes in the rate of cocaine, methamphetamine, and “spice” related emergency department visits as well as cocaine- and methamphetamine-related death rates, within Marion County, Indiana between 2013 and 2017.MethodsTwo data sources were used in this study. First, prevalence rates of non-opioid substance related emergency department (ED) visits were calculated using Marion County (IN) ED data from Electronic Surveillance System for the Early Notification of Community-Based Epidemics (ESSENCE) between 2013 and 2017. Second, cocaine and methamphetamine death rates were calculated using coroner toxicology data related to Marion County deaths between 2013 and 2017. Cocaine and methamphetamine deaths were defined as any death in which cocaine and methamphetamine was found in the toxicology results, respectively. All rates were calculated per 100,000 and age-adjusted to the 2000 U.S. Census using SAS Enterprise Guide v7.1.ResultsNon-opioid substance related ED visits have persistently risen between 2013 and 2017 (Figure 1). Methamphetamine and “spice” related ED visits exhibited similar prevalence patterns, increasing from 0.99 (0.72, 1.58) to 5.32 (4.67, 6.21) and 0.46 (0.28, 1.00) to 4.13 (3.57, 4.94) per 100,000, respectively, between 2013 and 2016. Cocaine-related ED visits consistently exhibited the highest prevalence rates, ranging from 3.72 (3.17, 4.44) to 23.56 (22.16, 25.11) per 100,000 in 2013 and 2016, respectively. In 2017, all non-opioid substance related ED visits drastically increased to 47.78 (45.79, 49.91), 48.48 (46.48, 50.67), and 42.08 (40.23, 44.13) per 100,000 for cocaine, methamphetamine, and “spice,” respectively. Further, we looked at cocaine- and methamphetamine-related death rates using coroner toxicology results. We found that between 2013 and 2017, the cocaine-related death rate nearly tripled, from 4.82 (4.20, 5.64) per 100,000 in 2013 to 13.01 (11.97, 14.23) per 100,000 in 2017 (Figure 2). Similarly, methamphetamine-related death rates increased from 1.31 (0.99, 1.92) per 100,000 in 2013 to 10.15 (9.25, 11.28) per 100,000 in 2017 (Figure 2). We did not calculate death rates of those who were found to have “spice” in their system at the time of death due to low prevalence.ConclusionsThe increase of non-opioid substance related ED visits in Marion County may indicate that non-opioid substance use—particularly cocaine, methamphetamine, and “spice”—may be an emerging public health issue in Marion County. This growing concern is further supported by the consistent increase in cocaine- and methamphetamine-related death rates. A limitation to our study is the inconsistent reporting of the substance in ED chief complaints and missing fields for discharge diagnoses and triage notes. As such, this inconsistency may have led to an underestimation of the prevalence rates of non-opioid substance related ED visits. The addition of triage notes and more reliable discharge diagnoses in 2017 ultimately culminated in a sharp increase in non-opioid substance related ED visits in 2017.Certain aspects of Marion County Public Health Department’s established opioid response plan may be used to address the growing concern of non-opioid substance use. These aspects include, but are not limited to, engaging community partners, creating a task force, establishing focus groups, and providing resources. While these aspects are critical to effectively respond to non-opioid substance use epidemics, establishing the various components prior to an outbreak enable communities to reduce the impact of such epidemics, if not prevent them from occurring. Additionally, it is important to incorporate participatory aspects into a non-opioid substance response plan such that community members are the driving force to provide context for the impact that non-opioid substance use is having on the community while also offering insight into which interventions would be most effective. 


2019 ◽  
Vol 13 (1) ◽  
pp. 1058-1069
Author(s):  
Mihai Păunică ◽  
Alexandru Manole ◽  
Cătălina Motofei ◽  
Gabriela-Lidia Tănase

Abstract In this paper, the authors aim to measure the influence of the macroeconomic indicators that characterize a national economy on some key national health indicators. The purpose is to obtain an updated evaluation of the population medical status, under the impact of either growth or economic decline. The analysis focuses especially on Romania but also on other countries, to be able to investigate comparatively national indicators and trends. Multiple data sources have been used for an in-depth analysis, to fit in an appropriate manner the purpose of the study. Static and econometric data analysis software was applied on primary data, as analysis instruments. The correlation coefficient and the regression were the tools used to obtain the study conclusions. We start from the premise that the potential of statistic data sources, combined with the processing power of the data analysis tools would be able to lead to the best result. We have also reviewed the previous studies performed on the same topic and, along with our data, the obtained conclusions should have a certain value and interest not only for current needs and utilization, but also for future researches. The authors are aware of the direct influence between the macroeconomic status (or performance) indicators and the indicators that characterize the health of the population, and will attempt to measure the intensity of this impact on several key selected domains.


1997 ◽  
Vol 77 (03) ◽  
pp. 504-509 ◽  
Author(s):  
Sarah L Booth ◽  
Jacqueline M Charnley ◽  
James A Sadowski ◽  
Edward Saltzman ◽  
Edwin G Bovill ◽  
...  

SummaryCase reports cited in Medline or Biological Abstracts (1966-1996) were reviewed to evaluate the impact of vitamin K1 dietary intake on the stability of anticoagulant control in patients using coumarin derivatives. Reported nutrient-drug interactions cannot always be explained by the vitamin K1 content of the food items. However, metabolic data indicate that a consistent dietary intake of vitamin K is important to attain a daily equilibrium in vitamin K status. We report a diet that provides a stable intake of vitamin K1, equivalent to the current U.S. Recommended Dietary Allowance, using food composition data derived from high-performance liquid chromatography. Inconsistencies in the published literature indicate that prospective clinical studies should be undertaken to clarify the putative dietary vitamin K1-coumarin interaction. The dietary guidelines reported here may be used in such studies.


2020 ◽  
Vol 39 (5) ◽  
pp. 6579-6590
Author(s):  
Sandy Çağlıyor ◽  
Başar Öztayşi ◽  
Selime Sezgin

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.


2020 ◽  
Vol 10 (3) ◽  
pp. 228-236 ◽  
Author(s):  
Lamia Taouzinet ◽  
Sofiane Fatmi ◽  
Allaeddine Khellouf ◽  
Mohamed Skiba ◽  
Mokrane Iguer-ouada

Background: Alpha-tocopherol is a potent antioxidant involved in sperm protection particularly during cryopreservation. However, its poor solubility limits the optimal protection in aqueous solutions. Objective: The aim of this study was to enhance the solubility of α-tocopherol by the use of liposomes. Methods: The experimental approach consisted to load vitamin E in liposomes prepared by ethanol injection method and the optimization carried out by an experimental design. The optimum solution was characterized by high performance liquid chromatography and scanning electron microscope. Finely, the impact on sperm motility protection was studied by the freezing technic of bovine sperm. Results: The optimum solution was obtained when using 10.9 mg/ml of phospholipids, 1.7 mg/ml of cholesterol and 2 mg/ml of vitamin E. The liposome size was 99.86 nm, providing 78.47% of loaded efficiency. The results showed also a significant positive impact on sperm motility after hours of preservation. Conclusion: In conclusion, the current results showed the interest of liposome preparation as an alternative to enhance vitamin E solubility and to protect spermatozoa during cryopreservation.


Sign in / Sign up

Export Citation Format

Share Document