Search results for "louhinta"

Anomaly Detection from Network Logs Using Diffusion Maps

2011

The goal of this study is to detect anomalous queries from network logs using a dimensionality reduction framework. The fequencies of 2-grams in queries are extracted to a feature matrix. Dimensionality reduction is done by applying diffusion maps. The method is adaptive and thus does not need training before analysis. We tested the method with data that includes normal and intrusive traffic to a web server. This approach finds all intrusions in the dataset. peerReviewed

Mining road traffic accidents

2009

Explaining information technology users’ ways of mitigating technostress

2017

Technostress refers to the inability of an individual to deal with information technology (IT) in a healthy manner. Researchers, practitioners, and medical professionals have emphasized the omnipresence of technostress and its severe outcomes, including poor well-being and burnout. Despite the importance of the phenomenon, prior research has paid limited attention to how technostress can be mitigated. The few existing studies examine organizational mitigation mechanisms, but we could not find any studies that focus on individual IT users’ own ways of mitigating technostress outside of work. To address the research gap, we conducted a qualitative study to uncover users’ ways of mitigating te…

The Effect of Textual Producer-Generated Descriptions on Demand of Mobile Applications

2017

We analyze the impact of different app description characteristics on app demand on the basis of panel data for six months and 1081 distinct apps. We use several text mining techniques in order to operationalize the descriptions’ textual characteristics. The extracted variables are then used in an econometric investigation to examine their impact on apps’ downloads. Our results provide evidence that app descriptions have an effect on demand. Apps with upfront price should be described in a neutral tone. Apps without an upfront price but with in-app purchase option should be offered with rather short descriptions that are written in a formal and subjective style. peerReviewed

Data Mining for the Security of Cyber Physical Systems Using Deep-Learning Methods

2022

Cyber Physical Systems (CPSs) have become widely popular in recent years, and their applicability have been growing exponentially. A CPS is an advanced system that incorporates a computation unit along with a hardware unit, allowing for computing processes to interact with the physical world. However, this increased usage has also led to the security concerns in them, as they allow potential attack vendors to exploit the possibilities of committing misconduct for their own benefit. It is of paramount importance that these systems have comprehensive security mechanisms to mitigate these security threats. A typical attack vector for a CPS is malicious data supplied by compromised sensors that…

Application of a Knowledge Discovery Process to Study Instances of Capacitated Vehicle Routing Problems

2020

Vehicle Routing Problems (VRP) are computationally challenging, constrained optimization problems, which have central role in logistics management. Usually different solvers are being developed and applied for different kind of problems. However, if descriptive and general features could be extracted to describe such problems and their solution attempts, then one could apply data mining and machine learning methods in order to discover general knowledge on such problems. The aim then would be to improve understanding of the most important characteristics of VRPs from both efficient solution and utilization points of view. The purpose of this article is to address these challenges by proposi…

Data-driven value creation in digitalizing public service

2022

Data has become an important asset in value creation. Organizations are dealing with a huge amount of data generated on different platforms. In dynamic environments, public organizations have an opportunity to make innovations by applying innovative technologies, implementing big data, and enabling data analytics capabilities that can create value. Evidence from the literature shows that organizations need data analytics capabilities to achieve data-driven value creation. In this chapter, based on a literature review and case example, the aim is to present the factors enabling public innovations from the big data analytics perspective; a theoretical framework for data-driven value creation …

Eettiset ongelmat massadatan ja tiedonlouhinnan hyödyntämisessä

2016

Niin julkiset kuin yksityisetkin organisaatiot keräävät ja hyödyntävät yhä enemmän dataa osana toimintaansa. Big data eli massadata on keskeinen teknologia suurten datamäärien hallitsemiseksi. Massadataa analysoidaan puolestaan usein tiedonlouhinnan menetelmin. Molempien innovaatioiden suosio on kasvanut trendinomaisesti ja niiden käytön ennustetaan yleistyvän jatkossakin. Massadataa ja tiedonlouhintaa on hyödynnetty myös arveluttaviin tarkoituksiin. Julkisuudessa on ollut esillä tapauksia, joissa yritykset ovat kohdentaneet markkinointiaan selvittämällä arkaluonteista tietoa asiakkaistaan. Tämä yhdistettynä ajatukseen uusiin teknologioihin liittyvistä käytäntötyhjiöistä toimii motiivina ai…

Incentive Mechanism for Edge-Computing-Based Blockchain

2020

Blockchain has been gradually applied to different Internet of Things (IoT) platforms. As the efficiency of the blockchain mainly depends on the network computing capability, how to make sure the acquisition of the computational resources and participation of the devices would be the driving force. In this work, we focus on investigating incentive mechanism for rational miners to purchase the computational resources. A edge computing-based blockchain network is considered, where the edge service provider (ESP) can provide computational resources for the miners. Accordingly, we formulate a two-stage Stackelberg game between the miners and ESP. The aim is to investigate Stackelberg equilibriu…

Semantic place recognition for context aware services

2012

Extracting the meaning of the most significant places, which are frequently visited by a mobile user, is a relevant problem in mobile computing. Predicting semantic meaning of such places is useful in many areas. The problem of place semantic annotation of a user location can be challenging for service providers. Awareness of user activities is very important for development of personalized applications, which can be used in health care systems, living systems, etc. Predicting location of mobile users not only enables development of high quality location-based services and applications, but also improves resource reservation in wireless networks. In this research several solutions for seman…