scholarly journals Hashtag Sense Clustering Based on Temporal Similarity

2017 ◽  
Vol 43 (1) ◽  
pp. 181-200 ◽  
Author(s):  
Giovanni Stilo ◽  
Paola Velardi
Keyword(s):  
Clustering Algorithm ◽  
Usage Patterns ◽  
Similar Content ◽  
Time Periods ◽  
Multiple Languages

Hashtags are creative labels used in micro-blogs to characterize the topic of a message/discussion. Regardless of the use for which they were originally intended, hashtags cannot be used as a means to cluster messages with similar content. First, because hashtags are created in a spontaneous and highly dynamic way by users in multiple languages, the same topic can be associated with different hashtags, and conversely, the same hashtag may refer to different topics in different time periods. Second, contrary to common words, hashtag disambiguation is complicated by the fact that no sense catalogs (e.g., Wikipedia or WordNet) are available; and, furthermore, hashtag labels are difficult to analyze, as they often consist of acronyms, concatenated words, and so forth. A common way to determine the meaning of hashtags has been to analyze their context, but, as we have just pointed out, hashtags can have multiple and variable meanings. In this article, we propose a temporal sense clustering algorithm based on the idea that semantically related hashtags have similar and synchronous usage patterns.

462 Redefining Positive Airway Pressure Adherence Phenotypes Utilizing Deep Neural Networks and Unsupervised Clustering

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A182-A182
Author(s):  
Yoav Nygate ◽  
Sam Rusk ◽  
Chris Fernandez ◽  
Nick Glattard ◽  
Nathaniel Watson ◽  
...  
Keyword(s):  
Airway Pressure ◽  
Clustering Algorithm ◽  
Positive Airway Pressure ◽  
Treatment Success ◽  
Unsupervised Clustering ◽  
Additional Patient ◽  
Apnea Hypopnea Index ◽  
Obstructive Sleep ◽  
Usage Patterns ◽  
Usage Data

Abstract Introduction Improving positive airway pressure (PAP) adherence is crucial to obstructive sleep apnea (OSA) treatment success. We have previously shown the potential of utilizing Deep Neural Network (DNN) models to accurately predict future PAP usage, based on predefined compliance phenotypes, to enable early patient outreach and interventions. These phenotypes were limited, based solely on usage patterns. We propose an unsupervised learning methodology for redefining these adherence phenotypes in order to assist with the creation of more precise and personalized patient categorization. Methods We trained a DNN model to predict PAP compliance based on daily usage patterns, where compliance was defined as the requirement for 4 hours of PAP usage a night on over 70% of the recorded nights. The DNN model was trained on N=14,000 patients with 455 days of daily PAP usage data. The latent dimension of the trained DNN model was used as a feature vector containing rich usage pattern information content associated with overall PAP compliance. Along with the 455 days of daily PAP usage data, our dataset included additional patient demographics such as age, sex, apnea-hypopnea index, and BMI. These parameters, along with the extracted usage patterns, were applied together as inputs to an unsupervised clustering algorithm. The clusters that emerged from the algorithm were then used as indicators for new PAP compliance phenotypes. Results Two main clusters emerged: highly compliant and highly non-compliant. Furthermore, in the transition between the two main clusters, a sparse cluster of struggling patients emerged. This method allows for the continuous monitoring of patients as they transition from one cluster to the other. Conclusion In this research, we have shown that by utilizing historical PAP usage patterns along with additional patient information we can identify PAP specific adherence phenotypes. Clinically, this allows focus of PAP adherence program resources to be targeted early on to patients susceptible to treatment non-adherence. Furthermore, the transition between the two main phenotypes can also indicate when personalized intervention is necessary to maximize treatment success and outcomes. Lastly, providers can transition patients in the highly non-compliant group more quickly to alternative therapies. Support (if any):

Existentials and possessives in Modern Hebrew

2018 ◽  
Vol 42 (2) ◽  
pp. 389-417
Author(s):  
Nurit Melnik
Keyword(s):  
Language Change ◽  
Age Groups ◽  
Spoken Language ◽  
Possessive Constructions ◽  
Usage Patterns ◽  
Modern Hebrew ◽  
Time Periods ◽  
Additional Support ◽  
The Relationship ◽  
Two Populations

Abstract This paper considers the relationship between synchronic variation and language change in the context of the existential and possessive constructions in Modern Hebrew, which exhibit a normative – colloquial alternation. The study examines usage patterns across age groups and time periods, as represented in spoken-language corpora. It shows that the non-normative construction is used extensively in the contemporary speech of adults. Moreover, a comparison of the use of the normative – colloquial alternations by two populations, children and adults, in different time periods, provides evidence to suggest that these constructions are undergoing language change. A cross-linguistic perspective lends additional support: across languages the expression of existence involves non-canonical structures, which are particularly susceptible to language variation and, possibly, language change.

scholarly journals Data Mining Applications in Understanding Electricity Consumers’ Behavior: A Case Study of Tulkarm District, Palestine

Energies ◽  
2019 ◽  
Vol 12 (22) ◽  
pp. 4287 ◽  
Author(s):  
Maher AbuBaker
Keyword(s):  
Data Mining ◽  
Clustering Algorithm ◽  
Electricity Consumption ◽  
Support Vector ◽  
Consumer Segmentation ◽  
Time Period ◽  
Visualization Tools ◽  
Box Plot ◽  
Time Periods

This paper presents a comprehensive data analysis and visualization of electricity consumers’ prepaid bills of Tulkarm district. We analyzed 250,000 electricity consumers’ prepaid bills covering the time period from June to December 2018. The application of data mining techniques for understanding electricity consumers’ behavior in electricity consumption and their behavior in charging their electricity meter’s smart cards in terms of quantities charged and charging frequencies in different time periods, areas and tariffs are used. Understanding consumers’ behavior will support planning and decision making at strategic, tactical and operational levels. This analysis is useful for predicting and forecasting future demand with a certain degree of accuracy. Monthly, weekly, daily and hourly time periods are covered in the analysis. Outliers detection using visualization tools such as box plot is applied. K-means unsupervised machine learning clustering algorithm is implemented. The support vector machine classification method is applied. As a result of this study, electricity consumers’ behavior in different areas, tariffs and timing periods is understood and presented by numbers and graphs and new electricity consumer segmentation is proposed.

An improved algorithm for mining media content application patterns based on QPop increasing disk time domain segmentation and upgrading1

2020 ◽  
pp. 1-8
Author(s):  
Yang Xindi ◽  
Du Huanran
Keyword(s):  
Clustering Algorithm ◽  
Scheduling Algorithm ◽  
Data Migration ◽  
Media Content ◽  
Practical Applications ◽  
Basic Model ◽  
Usage Patterns ◽  
Object Usage ◽  
Content Object ◽  
Improved Algorithm

The intelligent scheduling algorithm for hierarchical data migration is a key issue in data management. Mass media content platforms and the discovery of content object usage patterns is the basic schedule of data migration. We add QPop, the dimensionality reduction result of media content usage logs, as content objects for discovering usage patterns. On this basis, a clustering algorithm QPop is proposed to increase the time segmentation, thereby improving the mining performance. We hired the standard C-means algorithm as the clustering core and used segmentation to conduct an experimental mining process to collect the ted QPop increments in practical applications. The results show that the improved algorithm has good robustness in cluster cohesion and other indicators, slightly better than the basic model.

A Modified Cosine Similarity for Cross Language Information Retrieval

2014 ◽  
Vol 931-932 ◽  
pp. 1348-1352
Author(s):  
Chatchai Inparaprapan ◽  
Kraisak Kesorn
Keyword(s):  
Information Retrieval ◽  
Cosine Similarity ◽  
Cross Language Information Retrieval ◽  
Similar Content ◽  
The Right ◽  
Modified Formula ◽  
Cross Language ◽  
Right Order ◽  
Multiple Languages ◽  
Ranking Technique

Since millions of documents are available on the Internet, some documents contain similar content but they are written in different languages by various authors. Unfortunately, the existing search engines do not support to all documents that are relevant to a single language query. Therefore, several researchers have put a huge effort to overcome such a problem. The major problems of a cross language search engine include 1) how to store information in a unify model and represent information of multiple languages documents effectively and 2) how to rank the retrieved multiple language documents and present to a user in the right order. This paper overcomes the first problem using an ontology model and we present a new ranking technique for a cross language information retrieval system (CLIR). Keyword weighting scheme in an ontology and document sections are introduced. Cosine similarity formula is modified to particularly support CLIR. The experimental results show the modified formula obtains more efficient ranking results than the existing method.

Analysis and application of martial arts video image based on fuzzy clustering algorithm

2020 ◽  
pp. 1-9
Author(s):  
Chao Zhao ◽  
Hongling Yang ◽  
Xiaoqian Li ◽  
Rui Li ◽  
ShouCun Zheng
Keyword(s):  
Clustering Algorithm ◽  
Scheduling Algorithm ◽  
Data Migration ◽  
Media Content ◽  
Practical Applications ◽  
Basic Model ◽  
Usage Patterns ◽  
Object Usage ◽  
Content Object ◽  
Time Segmentation

The intelligent scheduling algorithm for hierarchical data migration is a key issue in data management. Mass media content platforms and the discovery of content object usage patterns is the basic schedule of data migration. We add QPop, the dimensionality reduction result of media content usage logs, as content objects for discovering usage patterns. On this basis, a clustering algorithm QPop is proposed to increase the time segmentation, thereby improving the mining performance. We hired the standard C-means algorithm as the clustering core and used segmentation to conduct an experimental mining process to collect the ted QPop increments in practical applications. The results show that the improved algorithm has good robustness in cluster cohesion and other indicators, slightly better than the basic model.

scholarly journals Expert opinion on livestock antimicrobial usage indications and patterns in Denmark, Portugal and Switzerland

2018 ◽  
Vol 5 (1) ◽  
pp. e000288 ◽  
Author(s):  
Luís Pedro Carmo ◽  
Ilias Bouzalas ◽  
Liza Rosenbaum Nielsen ◽  
Lis Alban ◽  
Paulo Martins da Costa ◽  
...  
Keyword(s):  
Expert Opinion ◽  
Treatment Guidelines ◽  
Production Cycle ◽  
Antimicrobial Substances ◽  
Antimicrobial Usage ◽  
Usage Patterns ◽  
Production Cycles ◽  
Time Periods ◽  
Inform Decision Making ◽  
Indications For Use

We aimed at describing antimicrobial usage patterns throughout livestock production cycles, and comparing them across three countries from Northern, Central and Southern Europe. Given the difficulties to collect such detailed usage data, an expert opinion was deemed the most appropriate study design. This study provides new insights into the time periods and indications for which specific antimicrobial substances are used in different livestock sectors.Veterinary experts (n=67) from different livestock sectors (broilers, pigs, dairy cattle and veal/fattening calves) and countries (Denmark, Portugal and Switzerland) replied to a questionnaire focusing on the time periods in the production cycle when antimicrobial substances were administered, and the respective indications for treatment.Our results showed that for several antimicrobials, between-country and within-country variations exist regarding the temporal distributions of treatments and indications for use. These differences were also true for several critically important antimicrobials, which is a matter of concern. Furthermore, differences between countries were also evident regarding the antimicrobial substances licensed.Based on our results, it is recommended to establish and promote treatment guidelines, invest in the prevention of diseases during critical moments of the production cycle and target undifferentiated use of antimicrobials. Moreover, discrepancies between countries should be further investigated to better understand the factors underlying the identified patterns and to distinguish prudent from non-prudent use. The results can inform decision-making with the aim to foster antimicrobial prudent use in the veterinary setting and, therefore, protect public health from the threat of antimicrobial resistance.

Vocal Communications of a Developmentally Delayed Child

1987 ◽  
Vol 18 (2) ◽  
pp. 112-130
Author(s):  
Mary Ann Romski ◽  
Sharon Ellis Joyner ◽  
Rose A. Sevcik
Keyword(s):  
Language Learning ◽  
Developmental Delays ◽  
Developmentally Delayed ◽  
Language Impaired ◽  
Diary Data ◽  
Word Acquisition ◽  
Diary Studies ◽  
Usage Patterns ◽  
Vocal Communications ◽  
Impaired Children

Studies of first-word acquisition in typical language-learning children frequently take the form of diary studies. Comparable diary data from language-impaired children with developmental delays, however, are not currently available. This report describes the spontaneous vocalizations of a child with a developmental delay for 14 months, from the time he was age 6:5 to age 7:7. From a corpus of 285 utterances, 47 phonetic forms were identified and categorized. Analysis focused on semantic, communicative, and phonological usage patterns.

Predictors of Problematic Video Game Usage in Childhood and Adolescence

2013 ◽  
Vol 59 (3) ◽  
pp. 153-164 ◽  
Author(s):  
Thomas Mößle ◽  
Florian Rehbein
Keyword(s):  
Social Environment ◽  
School Children ◽  
Video Game ◽  
Video Gaming ◽  
Control Group ◽  
Childhood And Adolescence ◽  
Longitudinal Control ◽  
Peer Problems ◽  
Media Usage ◽  
Usage Patterns

Aim: The aim of this article is to work out the differential significance of risk factors of media usage, personality and social environment in order to explain problematic video game usage in childhood and adolescence. Method: Data are drawn from the Berlin Longitudinal Study Media, a four-year longitudinal control group study with 1 207 school children. Data from 739 school children who participated at 5th and 6th grade were available for analysis. Result: To explain the development of problematic video game usage, all three areas, i. e. specific media usage patterns, certain aspects of personality and certain factors pertaining to social environment, must be taken into consideration. Video game genre, video gaming in reaction to failure in the real world (media usage), the children’s/adolescents’ academic self-concept (personality), peer problems and parental care (social environment) are of particular significance. Conclusion: The results of the study emphasize that in future – and above all also longitudinal – studies different factors regarding social environment must also be taken into account with the recorded variables of media usage and personality in order to be able to explain the construct of problematic video game usage. Furthermore, this will open up possibilities for prevention.

Sign in / Sign up

Export Citation Format

Share Document