Search results for "Analytics"

Identifying legitimate Web users and bots with different traffic profiles — an Information Bottleneck approach

2020

Abstract Recent studies reported that about half of Web users nowadays are intelligent agents (Web bots). Many bots are impersonators operating at a very high sophistication level, trying to emulate navigational behaviors of legitimate users (humans). Moreover, bot technology continues to evolve which makes bot detection even harder. To deal with this problem, many advanced methods for differentiating bots from humans have been proposed, a large part of which relies on supervised machine learning techniques. In this paper, we propose a novel approach to identify various profiles of bots and humans which combines feature selection and unsupervised learning of HTTP-level traffic patterns to d…

Interpreting Heterogeneous Geospatial Data Using Semantic Web Technologies

2016

International audience; The paper presents work on implementation of semantic technologies within a geospatial environment to provide a common base for further semantic interpretation. The work adds on the current works in similar areas where priorities are more on spatial data integration. We assert that having a common unified semantic view on heterogeneous datasets provides a dimension that allows us to extend beyond conventional concepts of searchability, reusability, composability and interoperability of digital geospatial data. It provides contextual understanding on geodata that will enhance effective interpretations through possible reasoning capabilities. We highlight this through …

Qualifying semantic graphs using model checking

2011

International audience; Semantic interoperability problems have found their solutions using languages and techniques from the Semantic Web. The proliferation of ontologies and meta-information has improved the understanding of information and the relevance of search engine responses. However, the construction of semantic graphs is a source of numerous errors of interpretation or modeling and scalability remains a major problem. The processing of large semantic graphs is a limit to the use of semantics in current information systems. The work presented in this paper is part of a new research at the border of two areas: the semantic web and the model checking. This line of research concerns t…

CDnet 2014: An Expanded Change Detection Benchmark Dataset

2014

International audience; Change detection is one of the most important low-level tasks in video analytics. In 2012, we introduced the changedetection.net (CDnet) benchmark, a video dataset devoted to the evalaution of change and motion detection approaches. Here, we present the latest release of the CDnet dataset, which includes 22 additional videos (~70,000 pixel-wise annotated frames) spanning 5 new categories that incorporate challenges encountered in many surveillance settings. We describe these categories in detail and provide an overview of the results of more than a dozen methods submitted to the IEEE Change Detection Workshop 2014. We highlight strengths and weaknesses of these metho…

A Neural Network Meta-Model and its Application for Manufacturing

2015

International audience; Manufacturing generates a vast amount of data both from operations and simulation. Extracting appropriate information from this data can provide insights to increase a manufacturer's competitive advantage through improved sustainability, productivity, and flexibility of their operations. Manufacturers, as well as other industries, have successfully applied a promising statistical learning technique, called neural networks (NNs), to extract meaningful information from large data sets, so called big data. However, the application of NN to manufacturing problems remains limited because it involves the specialized skills of a data scientist. This paper introduces an appr…

Temporal Logic To Query Semantic Graphs Using The Model Checking Method

2012

International audience; Semantic interoperability problems have found their solutions due to the use of languages and techniques from the Semantic Web. The proliferations of ontologies and meta-information have improved the understanding of information and the relevance of search engine responses. However, the construction of semantic graphs is a source of numerous errors of interpretation or modeling, and scalability remains a major problem. The processing of large semantic graphs is a limit to the use of semantics in current information systems. The work presented in this paper is part of a new research at the border of two areas: the semantic web and the model checking. This line of rese…

Distinguished Scientist Award under the Chinese Academy of Science President’s international Fellowship Initiative 2020

2019

Classé parmi les 6000 chercheurs mondiaux les plus influents selon Highly Cited Researchers de Clarivate analytics (Microbiology), dont environ 170 F…

2019

Leveraging the benefits of big data with fast data for effective and efficient cybersecurity analytics systems : A robust optimisation approach

2020

In recent times, major cybersecurity breaches and cyber fraud within the public and private sectors are making international headlines. Majority of organisations are facing cybersecurity adversity and advanced threats. On the one hand, we have asynchronous cybersecurity practices, many standards and frameworks to consider while on the other hand, we have to deal and secure our organisations against cyber-criminals, organised hacktivists, insider threats, hackers and nation-states with malafide intentions. The Center for Cyber Safety and Education's Global Information Security Workforce Study (GISWS) confirms that globally we are not only loosing but also backpedalling against threats and ri…

Impact of information and in-home sensory exposure on liking and willingness to pay: The beginning of Fairtrade labeled coffee in France.

2015

This study was conducted to assess how the Fairtrade label interacts with the perception of intrinsic product characteristics on liking and purchase decisions and to estimate the evolution of this interaction after exposure to the coffees and/or exposure to ethical information. In a first session, 119 consumers gave liking scores for 2 regular and 2 Fairtrade coffees under a blind tasting condition. Then, they were asked to indicate the maximum price they would pay for each product in 2 auctions taking place under different information conditions. In the first auction, participants saw the packaging but did not taste the coffee; in the second auction, they could both taste the coffee and se…