scholarly journals Ensemble Numerical Modeling Approach with Social Network Information to Optimize Flood Forecasting

10.29007/7crq ◽  
2018 ◽  
Author(s):  
Pin-Hao Liao ◽  
Dong-Sin Shih
Keyword(s):  
Numerical Modeling ◽  
Social Network ◽  
Heavy Rain ◽  
Flood Forecasting ◽  
Learning System ◽  
Physical Parameters ◽  
Peak Time ◽  
Rainfall Forecasting ◽  
Network Information ◽  
Section Data

The rivers in Taiwan are steep, the surface runoff is rushed into ocean quickly with high speeds and large discharges. When the typhoons hit Taiwan with heavy rain, how to predict correct peak time and peak stage of rivers is the most important aim in this research. Taiwan Typhoon and Flood Research Institute will produce a rainfall forecasting every six hours for disaster warning, according to different physical parameters setting. The research site, Xiuguluan River is steepest one of Taiwan central rivers. By cross section data、land use、slope、soils and the rainfall forecasting, we can get results of each member by integrating the physically based on model HEC-HMS and WASH123D.The research reveals that ensemble numerical modeling can predict precise peak stage of the river by analysis and correction by machine learning system TensorFlow. As for peak time forecasting, it becomes accurate by making use of the open social network information such as facebook、network news、PTT discussion to improve. Moreover, no matter peak time or peak stage, it has highly variation in members. In other words, no member is always the best of typhoons. But we can use the probability flood forecasting to predict and get the best results.

scholarly journals Profile reliability to improve recommendation in social-learning context

2018 ◽  
Vol 44 (2) ◽  
pp. 433-454 ◽  
Author(s):  
Corinne Amel Zayani ◽  
Leila Ghorbel ◽  
Ikram Amous ◽  
Manel Mezghanni ◽  
André Péninou ◽  
...  
Keyword(s):  
Social Network ◽  
Social Learning ◽  
Learning System ◽  
Learning Context ◽  
Content Type ◽  
Semantic Relationships ◽  
The Hierarchical Structure ◽  
E Learning ◽  
Many Sources

Purpose Generally, the user requires customized information reflecting his/her current needs and interests that are stored in his/her profile. There are many sources which may provide beneficial information to enrich the user’s interests such as his/her social network for recommendation purposes. The proposed approach rests basically on predicting the reliability of the users’ profiles which may contain conflictual interests. The paper aims to discuss this issue. Design/methodology/approach This approach handles conflicts by detecting the reliability of neighbors’ profiles of a user. The authors consider that these profiles are dependent on one another as they may contain interests that are enriched from non-reliable profiles. The dependency relationship is determined between profiles, each of which contains interests that are structured based on k-means algorithm. This structure takes into consideration not only the evolutionary aspect of interests but also their semantic relationships. Findings The proposed approach was validated in a social-learning context as evaluations were conducted on learners who are members of Moodle e-learning system and Delicious social network. The quality of the created interest structure is assessed. Then, the result of the profile reliability is evaluated. The obtained results are satisfactory. These results could promote recommendation systems as the selection of interests that are considered of enrichment depends on the reliability of the profiles where they are stored. Research limitations/implications Some specific limitations are recorded. As the quality of the created interest structure would evolve in order to improve the profile reliability result. In addition, as Delicious is used as a main data source for the learner’s interest enrichment, it was necessary to obtain interests from other sources, such as e-recruitement systems. Originality/value This research is among the pioneer papers to combine the semantic as well as the hierarchical structure of interests and conflict resolution based on a profile reliability approach.

Predictive Analytics of Social Networks

2018 ◽  
pp. 823-862
Author(s):  
Ming Yang ◽  
William H. Hsu ◽  
Surya Teja Kallumadi
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Predictive Analytics ◽  
Concept Drift ◽  
Customer Relationship ◽  
Community Formation ◽  
Heterogeneous Information ◽  
Network Information ◽  
Partial Data ◽  
Business To Consumer

In this chapter, the authors survey the general problem of analyzing a social network in order to make predictions about its behavior, content, or the systems and phenomena that generated it. They begin by defining five basic tasks that can be performed using social networks: (1) link prediction; (2) pathway and community formation; (3) recommendation and decision support; (4) risk analysis; and (5) planning, especially causal interventional planning. Next, they discuss frameworks for using predictive analytics, availability of annotation, text associated with (or produced within) a social network, information propagation history (e.g., upvotes and shares), trust, and reputation data. They also review challenges such as imbalanced and partial data, concept drift especially as it manifests within social media, and the need for active learning, online learning, and transfer learning. They then discuss general methodologies for predictive analytics involving network topology and dynamics, heterogeneous information network analysis, stochastic simulation, and topic modeling using the abovementioned text corpora. They continue by describing applications such as predicting “who will follow whom?” in a social network, making entity-to-entity recommendations (person-to-person, business-to-business [B2B], consumer-to-business [C2B], or business-to-consumer [B2C]), and analyzing big data (especially transactional data) for Customer Relationship Management (CRM) applications. Finally, the authors examine a few specific recommender systems and systems for interaction discovery, as part of brief case studies.

Competence Management over Social Networks Through Dynamic Taxonomies

2013 ◽  
pp. 103-120
Author(s):  
Giuseppe Berio ◽  
Antonio Di Leva ◽  
Mounira Harzallah ◽  
Giovanni M. Sacco
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Real World ◽  
Reference Model ◽  
Effective Solution ◽  
Network Information ◽  
The Social ◽  
Competence Management

The exploitation and integration of social network information in a competence reference model (CRAI, Competence, Resource, Aspect, Individual) are discussed. The Social-CRAI model, which extends CRAI to social networks, provides an effective solution to this problem and is discussed in detail. Finally, dynamic taxonomies, a model supporting explorative conceptual search, are introduced and their use in the context of the Social-CRAI model for exploring retrieved information available in social networks is discussed. A real-world example is provided.

Social Network Mining from the Web

2011 ◽  
pp. 149-175 ◽  
Author(s):  
Yutaka Matsuo ◽  
Junichiro Mori ◽  
Mitsuru Ishizuka
Keyword(s):  
Social Network ◽  
Search Engine ◽  
Relevant Information ◽  
Web Content ◽  
Message Boards ◽  
Network Information ◽  
Network Mining ◽  
Social Network Mining ◽  
The Social ◽  
The Web

This chapter describes social network mining from the Web. Since the end of the 1990s, several attempts have been made to mine social network information from e-mail messages, message boards, Web linkage structure, and Web content. In this chapter, we specifically examine the social network extraction from the Web using a search engine. The Web is a huge source of information about relations among persons. Therefore, we can build a social network by merging the information distributed on the Web. The growth of information on the Web, in addition to the development of a search engine, opens new possibilities to process the vast amounts of relevant information and mine important structures and knowledge.

scholarly journals Dynamic Credit Quality Evaluation with Social Network Data

2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Stanley Sewe ◽  
Philip Ngare ◽  
Patrick Weke
Keyword(s):  
Social Network ◽  
Continuous Time ◽  
Network Data ◽  
Linear Quadratic ◽  
Arrival Times ◽  
Network Information ◽  
Credit Quality ◽  
Social Network Data ◽  
Observation Process ◽  
Time Observation

We investigate the filtering problem where the borrower’s time varying credit quality process is estimated using continuous time observation process and her (in this paper we refer to the borrower as female and the lender as male) ego-network data. The hidden credit quality is modeled as a hidden Gaussian mean-reverting process whilst the social network is modeled as a continuous time latent space network model. At discrete times, the network data provides unbiased estimates of the current credit state of the borrower and her ego-network. Combining the continuous time observed behavioral data and network information, we provide filter equations for the hidden credit quality and show how the network information reduces information asymmetry between the borrower and the lender. Further, we consider the case when the network information arrival times are random and solve stochastic optimal control problem for a lender having linear quadratic utility function.

scholarly journals Study of the Effect of Simulated Rain on the Offset Parabolic Antenna at Ku-Band with Different Elevation Angles

2007 ◽  
Vol 2007 ◽  
pp. 1-5
Author(s):  
H. Mostafa ◽  
S. I. S. Hassan ◽  
J. S. Mandeep ◽  
M. F. Ain ◽  
H. A. Khedher
Keyword(s):  
Rain Rate ◽  
Water Layer ◽  
Heavy Rain ◽  
Horn Antenna ◽  
Physical Parameters ◽  
Worst Case ◽  
Atmospheric Propagation ◽  
First Case ◽  
Rf Signal ◽  
Ku Band

Effect of rain on the receiver antenna is a major factor to degrade the system performance in a frequency above 10 GHz. This paper deals with the wet antenna attenuation at Ku-band with three different frequencies at different rain rates. During the Ku-band propagation experiment, it was discovered that rain water on the antenna caused a significant attenuation. It is necessary to estimate the losses caused by water on the antenna in order to separate these losses from the atmospheric propagation losses. The experiment was done at USM Engineering Campus to study the attenuation for these physical parameters. A Ku-band RF signal was generated by a signal generator and transmitted via horn antenna. The signal was received using a smooth offset antenna of 60 cm by 54 cm (Astro dish) and measured using spectrum analyzer. In order to simulate a rain, pipes with bores of a same distance were implemented. Three cases were considered: in the first case one pipe was used to simulate low rain rate, the second case two pipes were used to simulate medium rain rate, and the third case three pipes were used to simulate heavy rain rate. In addition, the tap was used to control the flow of water in order to get more values of rain rate. The total attenuation of RF signals due to water layer on the feed and on the reflector feed was found to be 3.1 dB at worst case. On the other hand, the attenuation of RF signal due to the feed only was 2.83 dB, so the major attenuation occur was due to feed.

Sign in / Sign up

Export Citation Format

Share Document