scholarly journals Usage Patterns Identification Using Graphs and Machine Learning

2021 ◽  
pp. 84-92
Author(s):  
Ovidiu-Dan Sonea
Keyword(s):  
Machine Learning ◽  
The Past ◽  
Usage Patterns ◽  
Using Data ◽  
Insight Into

AbstractDuring the past years, the number of platforms that are introducing a subscription plan is steadily increasing. This phenomenon helps support the developers as well as continuing to provide quality content. Since not so many individuals are willing to spend money or some simply do not have the means, they resort to sharing an account that has a subscription plan. This behavior can, in some instances, be harmful for the developers and, even if it is not, any provider can benefit from knowing what type of clients they have. The solution depicted and explored in this article will focus on using data that is easily available and structuring it in a way that can provide insight into each account activity.

scholarly journals Interesting fellow or tough old bird? 3rd person male referents in Ontario

2020 ◽  
pp. 1-22
Author(s):  
Karlien Franco ◽  
Sali A. Tagliamonte
Keyword(s):  
Social Network ◽  
20Th Century ◽  
Language Change ◽  
Urban Centre ◽  
Total N ◽  
Geographic Factors ◽  
The Past ◽  
Using Data ◽  
Insight Into ◽  
Network Type

English has many words to refer to an adult man, e.g. man, guy, dude, and these are undergoing change in Ontario dialects. This paper analyzes the distribution of these and related forms using data collected in Ontario, Canada. In total, N = 6788 tokens for 17 communities were extracted and analyzed with a comparative sociolinguistics methodology for social and geographic factors. The results demonstrate a substantive language change in progress with two striking patterns. First, male speakers in Ontario were the leaders of this change in the past. However, as guy gained prominence across the 20th century, women started using it as frequently as men. Second, these developments are complicated by the complexity of the sociolinguistic landscape. There is a clear urban vs. peripheral division across Ontario communities that also involves both population size and distance from the large urban centre, Toronto. Further, social network type and other local influences are also important. In sum, variation in 3rd person singular male referents in Ontario dialects provides new insight into the co-occurrence and evolution of sociolinguistic factors in the process of language change.

Towards the Polycentric Urban Region: Impacts on Centres and Milieus

2005 ◽  
Vol 30 (3) ◽  
pp. 9-16
Author(s):  
Sako Musterd ◽  
Marco Bontje ◽  
Wim Ostendorf
Keyword(s):  
Population Dynamics ◽  
Residential Mobility ◽  
Central City ◽  
Urban System ◽  
Urban Region ◽  
Urban Dynamics ◽  
Urban Regions ◽  
The Past ◽  
Using Data ◽  
Insight Into

Over the past four decades, many urban regions, including the Amsterdam region, have changed from compact monocentric urban entities to - albeit still fairly compact - polycentric urban regions. This has been illustrated frequently and in various ways, for example with daily interaction information. A question relevant to this transformation concerns the implications it poses to the different centres and milieus in the urban region, especially the “old” central city. Is the central city quickly losing position, or is it gaining a new, vital place in the urban region? Can the answer to that be deduced from the population dynamics in the urban region? Is insight into the residential mobility process helpful in understanding the changing residential structure and the functioning of the urban system? This paper addresses these questions, using data that make it possible to analyse urban dynamics.

scholarly journals Customer Churn Prediction in Telecommunication Industry Using Data Certainty

2020 ◽  
pp. 252-258
Author(s):  
V R Reji Raj ◽  
Rasheed Ahammed Azad .V
Keyword(s):  
Machine Learning ◽  
Market Value ◽  
Machine Learning Algorithms ◽  
Telecommunication Industry ◽  
Churn Prediction ◽  
Customer Churn ◽  
The Past ◽  
Customer Churn Prediction ◽  
Using Data ◽  
Data Certainty

Customer churn is a major problem affecting large companies, especially in telecommunication field. So the telecom industries have to take the necessary steps to retain their customers, to maintain their market value. So companies are seeking to develop methods that predict potential churned customers. We have to find out the factors that increase customer churn for making necessary actions to reduce churn. In the past, different data mining techniques have been used for predicting the churners. Here the most popular machine learning algorithms used for churn predicting are analysed. The conclusions are stated with the help of suitable tables.

Recovery boiler sootblowers: History and technological advances

TAPPI Journal ◽  
2015 ◽  
Vol 14 (1) ◽  
pp. 51-60
Author(s):  
HONGHI TRAN ◽  
DANNY TANDRA
Keyword(s):  
Cfd Modeling ◽  
Computing Systems ◽  
The Past ◽  
Technological Advances ◽  
Recovery Boilers ◽  
Computational Fluid Dynamics Cfd ◽  
Recovery Boiler ◽  
Steam Parameters ◽  
Insight Into ◽  
Deposit Removal

Sootblowing technology used in recovery boilers originated from that used in coal-fired boilers. It started with manual cleaning with hand lancing and hand blowing, and evolved slowly into online sootblowing using retractable sootblowers. Since 1991, intensive research and development has focused on sootblowing jet fundamentals and deposit removal in recovery boilers. The results have provided much insight into sootblower jet hydrodynamics, how a sootblower jet interacts with tubes and deposits, and factors influencing its deposit removal efficiency, and have led to two important innovations: fully-expanded sootblower nozzles that are used in virtually all recovery boilers today, and the low pressure sootblowing technology that has been implemented in several new recovery boilers. The availability of powerful computing systems, superfast microprocessors and data acquisition systems, and versatile computational fluid dynamics (CFD) modeling capability in the past two decades has also contributed greatly to the advancement of sootblowing technology. High quality infrared inspection cameras have enabled mills to inspect the deposit buildup conditions in the boiler during operation, and helped identify problems with sootblower lance swinging and superheater platens and boiler bank tube vibrations. As the recovery boiler firing capacity and steam parameters have increased markedly in recent years, sootblowers have become larger and longer, and this can present a challenge in terms of both sootblower design and operation.

Recent Progress in Machine Learning-based Prediction of Peptide Activity for Drug Discovery

2019 ◽  
Vol 19 (1) ◽  
pp. 4-16 ◽  
Author(s):  
Qihui Wu ◽  
Hanzhong Ke ◽  
Dongli Li ◽  
Qi Wang ◽  
Jiansong Fang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Drug Discovery ◽  
Large Scale ◽  
Recent Progress ◽  
High Specificity ◽  
Learning Approaches ◽  
Anticancer Peptides ◽  
The Past ◽  
Traditional Approaches ◽  
Large Scale Screening

Over the past decades, peptide as a therapeutic candidate has received increasing attention in drug discovery, especially for antimicrobial peptides (AMPs), anticancer peptides (ACPs) and antiinflammatory peptides (AIPs). It is considered that the peptides can regulate various complex diseases which are previously untouchable. In recent years, the critical problem of antimicrobial resistance drives the pharmaceutical industry to look for new therapeutic agents. Compared to organic small drugs, peptide- based therapy exhibits high specificity and minimal toxicity. Thus, peptides are widely recruited in the design and discovery of new potent drugs. Currently, large-scale screening of peptide activity with traditional approaches is costly, time-consuming and labor-intensive. Hence, in silico methods, mainly machine learning approaches, for their accuracy and effectiveness, have been introduced to predict the peptide activity. In this review, we document the recent progress in machine learning-based prediction of peptides which will be of great benefit to the discovery of potential active AMPs, ACPs and AIPs.

Upcoming Drifts In Bio-Similars

2020 ◽  
Vol 15 ◽  
Author(s):  
Geeta Aggarwal ◽  
Manju Nagpal ◽  
Ameya Sharma ◽  
Vivek Puri ◽  
Gitika Arora Dhingra
Keyword(s):  
Metabolic Diseases ◽  
Market Competition ◽  
Current Status ◽  
Medicinal Products ◽  
The Past ◽  
Biologic Activity ◽  
Emerging Trends ◽  
Regulatory Guidelines ◽  
Food Drug Administration ◽  
Insight Into

Background: Biopharmaceuticals such as Biologic medicinal products have been in clinical use over the past three decades and have benefited towards the therapy of degenerative and critical metabolic diseases. It is forecasted that market of biologics will be going to increase at a rate of 20% per year, and by 2025, more than ˃ 50% of new drug approvals may be biological products. The increasing utilization of the biologics necessitates for cost control, especially for innovators products that have enjoyed a lengthy period of exclusive use. As the first wave of biopharmaceuticals is expired or set to expire, it has led to various opportunities for the expansion of bio-similars i.e. copied versions of original biologics with same biologic activity. Development of biosimilars is expected to promote market competition, meet worldwide demand, sustain the healthcare systems and maintain the incentives for innovation. Methods: Appraisal of published articles from peer reviewed journals, PubMed literature, latest news and guidelines from European Medicine Agency, US Food Drug Administration (FDA) and India are used to identify data for review. Results: Main insight into the quality requirements concerning biologics, current status of regulation of biosimilars and upcoming challenges lying ahead for the upgrading of marketing authorization of bio-similars has been incorporated. Compiled literature on therapeutic status, regulatory guidelines and the emerging trends and opportunities of biosimilars has been thoroughly stated. Conclusion: Updates on biosimilars will support to investigate the possible impact of bio-similars on healthcare market.

Increase associated risk of gynaecological cancer due to long-term exposure to high concentration of atmospheric SO2 industrial pollutant

2021 ◽  
pp. 1420326X2110036
Author(s):  
Qian Xu ◽  
Chan Lu ◽  
Rachael Gakii Murithi ◽  
Lanqin Cao
Keyword(s):  
Time Windows ◽  
Air Pollutant ◽  
Gynaecological Cancer ◽  
High Concentration ◽  
The Past ◽  
Short And Long Term ◽  
Using Data ◽  
Air Quality Monitoring Stations ◽  
Control Study

A cohort case–control study was conducted in XiangYa Hospital, Changsha, China, which involved 305 patients and 399 healthy women, from June 2010 to December 2018, to evaluate the association between Chinese women’s short- and long-term exposure to industrial air pollutant, SO2 and gynaecological cancer (GC). We obtained personal and family information from the XiangYa Hospital electronic computer medical records. Using data obtained from the air quality monitoring stations in Changsha, we estimated each woman’s exposure to the industrial air pollutant, sulphur dioxide (SO2), for different time windows, including the past 1, 5, 10 and 15 years before diagnosis of the disease. A multiple logistic regression model was used to assess the association between GC and SO2 exposure. GC was significantly associated with long-term SO2 exposure, with adjusted odds ratio (95% confidence interval) = 1.56 (1.10–2.21) and 1.81 (1.07–3.06) for a per interquartile range increase in the past 10 and 15 years, respectively. Sensitivity analysis showed that different groups reacted in different ways to long-term SO2 exposure. We concluded that long-term exposure to high concentration of industrial pollutant, SO2 is associated with the development of GC. This finding has implications for the prevention and reduction of GC.

scholarly journals Using Machine Learning Methods to Identify Particle Types from Doppler Lidar Measurements in Iceland

2021 ◽  
Vol 13 (13) ◽  
pp. 2433
Author(s):  
Shu Yang ◽  
Fengchao Peng ◽  
Sibylle von Löwis ◽  
Guðrún Nína Petersen ◽  
David Christian Finger
Keyword(s):  
Machine Learning ◽  
Weather Conditions ◽  
Dust Storms ◽  
Machine Learning Algorithms ◽  
Lidar Data ◽  
Data Sets ◽  
Doppler Lidar ◽  
Lidar Measurements ◽  
Using Data ◽  
Filter Noise

Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different classes, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports.

scholarly journals Predicting Fraud Victimization Using Classical Machine Learning

Entropy ◽  
2021 ◽  
Vol 23 (3) ◽  
pp. 300
Author(s):  
Mark Lokanan ◽  
Susan Liu
Keyword(s):  
Machine Learning ◽  
Financial Literacy ◽  
Learning Algorithm ◽  
Demographic Characteristics ◽  
Financial Knowledge ◽  
The Past ◽  
Machine Learning Model ◽  
Long Time ◽  
Regulatory Organization ◽  
Investment Fraud

Protecting financial consumers from investment fraud has been a recurring problem in Canada. The purpose of this paper is to predict the demographic characteristics of investors who are likely to be victims of investment fraud. Data for this paper came from the Investment Industry Regulatory Organization of Canada’s (IIROC) database between January of 2009 and December of 2019. In total, 4575 investors were coded as victims of investment fraud. The study employed a machine-learning algorithm to predict the probability of fraud victimization. The machine learning model deployed in this paper predicted the typical demographic profile of fraud victims as investors who classify as female, have poor financial knowledge, know the advisor from the past, and are retired. Investors who are characterized as having limited financial literacy but a long-time relationship with their advisor have reduced probabilities of being victimized. However, male investors with low or moderate-level investment knowledge were more likely to be preyed upon by their investment advisors. While not statistically significant, older adults, in general, are at greater risk of being victimized. The findings from this paper can be used by Canadian self-regulatory organizations and securities commissions to inform their investors’ protection mandates.

Sign in / Sign up

Export Citation Format

Share Document