scholarly journals Detecting Persistent User Behavior Using Probabilistic Counting in Network-Wide View

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Aiping Zhou ◽  
Jin Qian ◽  
Hang Yu
Keyword(s):  
User Behavior ◽  
Limited Resource ◽  
Relevant Information ◽  
Abnormal Behavior ◽  
Estimation Accuracy ◽  
Frequent User ◽  
Traffic Measurement ◽  
Traffic Collection ◽  
Multiple Monitors ◽  
Measurement Period

Persistent user behavior monitoring, which deals with finding users that occur persistently over a measurement period, is one hot topic in traffic measurement. It is significant for many applications, such as anomaly detection. Former works concentrate on monitoring frequent user behavior, such as users occurring frequently either over one measurement period or on one monitor. They have paid little attention to detect persistent user behavior over a long measurement period on multiple monitors. However, persistent users do not necessarily appear frequently in a short measurement period, but appear persistently in a long measurement period. Due to limited resource on monitors, it is not practical to collect a tremendous amount of network traffic in a long measurement period on one single monitor. Moreover, since network attackers deliberately send packets flowing through the entire managed network, it is difficult to detect abnormal behavior on one single monitor. To solve the above challenges, a novel method for detecting persistent user behavior called DPU is proposed, and it contains both online distributed traffic collection in a long measurement period on multiple monitors and offline centralized user behavior detection on the central server. The key idea of DPU is that we design the compact distributed synopsis data structure to collect the relevant information with users occurring in a long measurement period on each monitor, and we can reconstruct user IDs using simple calculations and bit settings to find users with persistent behavior on the basis of estimated occurrence frequency of users on the central server when user IDs are unknown in advance. The experiments are conducted on real traffic to evaluate the performance of detecting persistent user behavior, and the experimental results illustrate that our method can improve about 30% estimation accuracy, 40% detection precision, and accelerate about 3 times in comparison with the related method.

Supporting Policy-Makers with Social Media Analysis Tools to Get Aware of Citizens' Opinions

2014 ◽  
pp. 121-156
Author(s):  
Timo Wandhöfer ◽  
Steve Taylor ◽  
Miriam Fernandez ◽  
Beccy Allen ◽  
Harith Alani ◽  
...  
Keyword(s):  
Social Media ◽  
Information Overload ◽  
User Behavior ◽  
Relevant Information ◽  
Media Analysis ◽  
Control Group ◽  
Data Sets ◽  
Online Forums ◽  
Policy Makers ◽  
Facebook Pages

The role of social media in politics has increased considerably. A particular challenge is how to deal with the deluge of information generated on social media: it is impractical to read lots of messages with the hope of finding useful information. In this chapter, the authors suggest an alternative approach: utilizing analysis software to extract the most relevant information of the discussions taking place. This chapter discusses the WeGov Toolbox as one concept for policy-makers to deal with the information overload on Social Media, and how it may be applied. Two complementary, in depth case studies were carried out to validate the usefulness of the analysis results of the WeGov Toolbox components' within its target audience's everyday life. Firstly, the authors used the “HeadsUp” forum, operated by the Hansard Society. Here, they were able to compare the key themes and opinions extracted automatically by the Toolbox to a control group of manually pre-analyzed data sets. In parallel, results of analyses based on four weeks' intensive monitoring on policy area-specific Facebook pages selected by German policy makers, as well as topics on Twitter globally and local, were assessed by taking into account their existing experience with content discussed and user behavior in their respective public spheres. The cases show that there are interesting applications for policy-makers to use the Toolbox in combination with online forums (blogs) and social networks, if behavioral user patterns will be considered and the framework will be refined.

The correlation analysis between the service quality of intelligent library and the behavioral intention of users

2019 ◽  
Vol 38 (1) ◽  
pp. 95-112 ◽  
Author(s):  
Min Chen ◽  
Chien-wen Shen
Keyword(s):  
Service Quality ◽  
Behavioral Intention ◽  
User Behavior ◽  
Rapid Development ◽  
Service Innovation ◽  
Relevant Information ◽  
Content Type ◽  
Positive Correlation ◽  
Service Mode

Purpose The purpose of this study was to explore the effect of innovative service mode of intelligent library on improving the service quality and a series of impacts on user behavior. With the rapid development of information technology, internet of things has become an important carrier of people’s “intelligent life”. The emergence of intelligent library will no longer be limited by space; it is affecting people’s lives and work imperceptibly. This new service mode was studied here, and the relationship between the service quality of intelligent library and users’ behavior was analyzed from the perspective of user acceptance and use behavior of intelligent library. Moreover, this study explores how to optimize the service quality to let users accept this technology and service mode and thus realize the original idea. Design/methodology/approach Through 800 questionnaires issued to the users in the Zhejiang Provincial AI Library, the authors obtained the study data. Among the received questionnaires, 676 copies are valid, and 124 responses are either incomplete or not answered, and so, the efficient rate is 84.5 per cent. Findings There is a significantly positive correlation between service innovation and service quality. There is a significantly positive correlation between service quality and behavioral intention. There is a significantly positive correlation between service innovation and behavioral intention. Originality/value From the point of view of innovative service, this paper analyzes the effect of innovative service mode of intelligent library on improving the service quality and a series of impacts on user behavior. This study confirms that intelligent library is a relatively new service innovation. Users’ curiosity and exploration will make them access some relevant information. As a result, a reasonably innovative service is an important factor in users’ acceptance behavior.

The Building of User Model of Personalized Learning Teaching System Based on Data Mining

2013 ◽  
Vol 756-759 ◽  
pp. 2047-2050
Author(s):  
Wen Yan Rui ◽  
Hai Ying Mi
Keyword(s):  
Data Mining ◽  
User Behavior ◽  
Relevant Information ◽  
Personalized Learning ◽  
User Model ◽  
Teaching System ◽  
Individual User ◽  
Model Based

This paper analyzes the structure of the whole system, namely, how different users according to their own characteristics of its initiative to provide users with relevant information and content and to establish individual user model, based on user behavior to build personalized user model.

scholarly journals Mitigation of saturation in satellite pasture measurement via incorporation of a statistical pasture growth model

2020 ◽  
Vol 82 ◽  
pp. 191-198
Author(s):  
Grant Anderson ◽  
Mitchell Rawlings ◽  
Graeme Ogle
Keyword(s):  
Growth Model ◽  
Estimation Accuracy ◽  
Satellite Measurement ◽  
Satellite Measurements ◽  
Model Estimate ◽  
Improved Accuracy ◽  
The Impact ◽  
Accuracy Data ◽  
Satellite Estimate ◽  
Measurement Period

Measurement of pasture biomass is useful to farmers, as it enables timely and accurate management decisions. Satellite pasture measurement allows this information to be obtained with minimal time and labour on the part of the farmer. However, the accuracy of satellite measurements for high levels of pasture biomass can be impacted by a phenomenon called saturation, in which the response of the satellite estimate to increased biomass is diminished in situations of high biomass. In this investigation, a statistical pasture growth model was combined with satellite pasture measurements, with the aim of mitigating the effect of saturation on estimation accuracy. Data were captured for five farms, across two regions and an 18–21 month measurement period. Where satellite measurements appeared to be saturated, the growth model estimate was substituted. This process resulted in improved accuracy (R2 improved from 0.672 to 0.703; RMSE improved from 334 to 309 kg DM/ha; and average bias improved from -62 to -9 kg DM/ha). The statistical improvements were more pronounced where terrestrial estimates were higher so the impact of saturation would be greatest. These results indicate that the problem of saturation in satellite pasture measurement can be addressed by the incorporation of modelled data. Prior research has predicted that improved accuracy of pasture measurement would be associated with increased profitability, and this work helps achieve that goal for farmers using satellite measurement services.

Personalized Spatio-Temporal OLAP Queries Suggestion Based on User Behavior and a New Similarity Measure

2019 ◽  
pp. 105-128
Author(s):  
Olfa Layouni ◽  
Jalel Akaichi
Keyword(s):  
Probabilistic Model ◽  
User Behavior ◽  
Search Behavior ◽  
Relevant Information ◽  
Current User ◽  
Data Cube ◽  
Temporal Data ◽  
Query Suggestion ◽  
Spatio Temporal ◽  
User Search Behavior

Spatio-temporal data warehouses store enormous amount of data. They are usually exploited by spatio-temporal OLAP systems to extract relevant information. For extracting interesting information, the current user launches spatio-temporal OLAP (ST-OLAP) queries to navigate within a geographic data cube (Geo-cube). Very often choosing which part of the Geo-cube to navigate further, and thus designing the forthcoming ST-OLAP query, is a difficult task. So, to help the current user refine his queries after launching in the geo-cube his current query, we need a ST-OLAP queries suggestion by exploiting a Geo-cube. However, models that focus on adapting to a specific user can help to improve the probability of the user being satisfied. In this chapter, first, the authors focus on assessing the similarity between spatio-temporal OLAP queries in term of their GeoMDX queries. Then, they propose a personalized query suggestion model based on users' search behavior, where they inject relevance between queries in the current session and current user' search behavior into a basic probabilistic model.

Crucial Role of Data Analytics in the Prevention and Detection of Cyber Security Attacks

2021 ◽  
pp. 67-80
Author(s):  
Charulatha B. S. ◽  
A. Neela Madheswari ◽  
Shanthi K. ◽  
Chamundeswari Arumugam
Keyword(s):  
Business Process ◽  
Cyber Security ◽  
Data Analytics ◽  
User Behavior ◽  
Relevant Information ◽  
Cyber Attacks ◽  
Social Needs ◽  
Machine Learning Algorithms ◽  
Cyber Attack ◽  
Data Set

Data analytics plays a major role in retrieving relevant information in addition to avoiding unwanted data, missed values, good visualization and interpretation, decision making in any business, or social needs. Many organizations are affected by cyber-attacks in their business at a greater frequency when they get exposure to the internet. Cyber-attacks are plenty, and tracking them is really difficult work. The entry of cyber-attack may be through different events in the business process. Detecting the attack is laborious and collecting the data is still a hard task. The detection of the source of attack for the various events in the business process as well as the tracking the corresponding data needs an investigation procedure. This chapter concentrates on applying machine learning algorithms to study the user behavior in the process to detect network anomalies. The data from KDD'99 data set is collected and analyzed using decision tree, isolation forest, bagging classifier, and Adaboost classifier algorithms.

scholarly journals Prediction of user Behavior through Web usage Mining

2019 ◽  
Vol 8 (3S2) ◽  
pp. 422-426
Keyword(s):  
Behavior Analysis ◽  
Pattern Analysis ◽  
User Behavior ◽  
Real Life ◽  
Relevant Information ◽  
Internet Usage ◽  
Information Collection ◽  
User Behavior Analysis ◽  
Pattern Information ◽  
The Web

In real life, many users drew in towards online ticket reservation, so numerous transactions are in websites. A weblog includes sequences of entrances updating often by individual while opening the web site. Based upon the customer interest, it might be categorized as relevant & unassociated information. The relevant information might be thought about as success feedback; however, unassociated data could be deliberated as failing reaction. It analyzes the pattern of individual navigating while searching, for that internet use mining have to be examined. The stages consisting for the procedure of internet usage mining are preprocessing, discovery of pattern, information collection, and pattern analysis. Along these steps this paper gave the user behavior analysis

scholarly journals Trust evaluation model of cloud user based on behavior data

2018 ◽  
Vol 14 (5) ◽  
pp. 155014771877692 ◽  
Author(s):  
Zhenguo Chen ◽  
Liqin Tian ◽  
Chuang Lin
Keyword(s):  
User Behavior ◽  
User Authentication ◽  
Evaluation Model ◽  
Weighted Average ◽  
Threshold Value ◽  
Abnormal Behavior ◽  
Trust Evaluation ◽  
Cloud Platform ◽  
Cloud Users ◽  
Cloud User

In the process of using the cloud platform, how to ensure the safety of users is a matter we must concern. The user authentication can provide a certain degree of security, but when the user information was leaked, this method will not be effective. Therefore, this article proposes a trust evaluation model based on user behavior data. In this model, the user’s historical behavior will be used to construct a set of trusted behavior of the cloud users. On this basis, the direct trust of the user’s behavior can be obtained. Then, the recommendation trust can be calculated by the interaction between the users and other cloud users. Given the current historical trust, the comprehensive trust can be obtained using the weighted average method. Among them, the initial value of historical trust is set to a constant and then updated by the comprehensive trust. In order to control the user’s abnormal behavior more effectively, the suspicious threshold value and the abnormal threshold value were defined, which are used to punish the historical trust. Through the simulation of the virtual digital library cloud platform, the method can effectively evaluate the cloud users.

scholarly journals IKM-NCS: A Novel Clustering Scheme Based on Improved K-Means Algorithm

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Clustering Algorithm ◽  
User Behavior ◽  
Abnormal Behavior ◽  
Cluster Center ◽  
Initial Sample ◽  
Initial Cluster ◽  
Weight Calculation ◽  
Data Points ◽  
Abnormal Behaviors ◽  
Better Than

Aiming at the problems of distorted center selection and slow iteration convergence in traditional clustering analysis algorithm, a novel clustering scheme based on improved k-means algorithm is proposed. In this paper, based on the analysis of all user behavior sets contained in the initial sample, a weight calculation method for abnormal behaviors and an eigenvalue extraction method for abnormal behavior set are proposed and a set of abnormal behaviors is constructed for each user according to the behavior data generated by abnormal users. Then, on the basis of the traditional k-means clustering algorithm, an improved algorithm is proposed. By calculating the compactness of all data points and selecting the initial cluster center among the data points with high and low compactness, the clustering performance is enhanced. Finally, the eigenvalues of the abnormal behavior set are used as the input of the algorithm to output the clustering results of the abnormal behavior. Experimental results show that the clustering performance of this algorithm is better than the traditional clustering algorithm, and can effectively improve the clustering performance of abnormal behavior

Sign in / Sign up

Export Citation Format

Share Document