Heavy-duty trucks are important links in the logistic chains of transport. Critical components in trucks include fuel injectors in which inaccuracies can lead to severe financial damage and higher emissions. Intelligent and efficient ways to detect such scenarios are thus of high importance. This thesis applies machine learning algorithms to measured or estimated engine data, focused on gas exchange signals, to detect inaccuracies in fueling quantities. The fueling inaccuracies considered were of low deviations from the nominal curve, with magnitudes not covered by the currently used fueling diagnostics. The data used for the models was generated from Scania test cell engines where different setups of injectors were deliberately set to over- or underfuel.  Seven different machine learning models were used on the data and evaluated on how well they could detect deviations from nominal fueling. The tests were mainly done with a pure data-driven approach but also improved through different data selection techniques and using domain knowledge. An investigation to connect the findings within the thesis to real customer data was initiated in order to make the results useful for e.g. predictive maintenance. The complications connected to why this was not ultimately achieved were discussed.

Bakgrund: E-handeln har på senare år genomgått radikala förändringar och dataanalys kan stå för 10 % av tillväxten hos 56 % av alla e-handelsföretag. Dataanalys erbjuder många fördelar och internationella företag hävdar att 30% av deras försäljning beror på dataanalys. Det finns tre olika lönsamhetsstrategier för att svenska e-handelsföretag ska öka lönsamheten. Dessa är (i) minska kostnader, (ii) öka omsättning, (iii) minska tillgångar och totalt kapital. Studien visar att 35 % av alla svenska e-handelsföretag har inte tillgång till relevanta data och det finns en oro för att dessa företag kommer att ligga efter i utvecklingen. Syfte och frågeställning: Studien syftar till att undersöka om e-handelsföretag tillämpar dataanalys vid utformning av lönsamhetsstrategier och vilka konsekvenser går det att identifiera av detta. Vilka lönsamhetsstrategier väljer svenska e-handelsföretag och hur används dessa strategier i kombination med dataanalys? Tillvägagångssätt: Studien använder en tvärsnittsdesign med datainsamling utifrån enenkätundersökning av e-handelsföretag där 93 respondenter svarat, 5 semi-strukturerade intervjuer och sekundärdata från 20 e-handelsföretag. Till analys av empiri användes univariat- och bivariat analys tillsammans med innehållsanalys. Empiri: Sextiofem av nittiotre respondenter i studien tillämpar dataanalys vid utformningav lönsamhetsstrategier, medan en tredjedel av deltagarna uppger att de inte tillämpardataanalys. Studien visade att de vanligaste analysverktygen är deskriptiv- och preskriptivanalys, medan de vanligaste lönsamhetsstrategierna är ökad omsättningen och minskade kostnader. Slutsats: Är att svenska e-handelsföretag fortfarande saknar resurser och kunskaper för att nyttja dataanalys fullt ut. En tredjedel av svenska e-handelsföretag går miste om fördelarna med dataanalys som även uppskattas bidra till 30 % av ökad försäljning. Dataanalys är den nya oljan och möjliggör för värdeskapande, därmed är slutsatsen av det här arbetet att svenska e-handelsföretag bör utvinna värde ur data och fokusera på att bli mer datadrivna. / Background: Over the last few years e-commerce has undergone radical changes, ten percent of which has been, among 56% of all e-commerce data analysis. Data analysis can provide many advantages; global corporations claim that 30% of their sales depend on it. There are three different strategies that Swedish e-commerce businesses can adopt to increase profitability. These are: 1. Reduce costs. 2. Increase revenue. 3. Minimise assets and total capital. Studies show that 35% of all Swedish e-commerce businesses do not have access to relevant data which could result in limiting future development. Purpose and Research Question: This study intends to examine and contribute to the knowledge of whether Swedish e-commerce businesses apply data analysis when developing profitability strategies. Which profitability strategies are used by Swedish ecommerce businesses and how do they utilise data analysis? Method: This study uses a cross-sectional design involving a survey of many e-commerce businesses of which 93 replied, five semi-structured interviews, and secondary data from 20e-commerce businesses. To analyse the empirical data, we used univariate and bivariate analysis together with content analysis. Empirical data: Sixty five out of ninety-three respondents apply data analysis when developing profitability strategies, but a third of the survey participants answered that they do not use them together. The study showed that the most common analytics tools used are descriptive and prescriptive analysis, whilst the most used profitability strategy is to increase revenue and to reduce costs. Conclusion: Swedish e-commerce businesses still lack the resources and knowledge to fully utilise data analysis. One third of Swedish e-commerce businesses do not take advantage of data analysis, even though it can increase sales by up to 30%. Data analysis is the new oil, which also enables value creation. Therefore, this study’s conclusion is that Swedish e-commerce businesses should utilise data analysis and become more data driven.

No description available.

No description available.

Continues field monitoring and searching sensor data remains an imminent element emphasizes the influence of the Internet of Things (IoT). Most of the existing systems are concede spatial coordinates or semantic keywords to retrieve the entail data, which are not comprehensive constraints because of sensor cohesion, unique localization haphazardness. To address this issue, we propose deep learning inspired sensor-rank consolidation (DLi-SRC) system that enables 3-set of algorithms. First, sensor cohesion algorithm based on Lyapunov approach to accelerate sensor stability. Second, sensor unique localization algorithm based on rank-inferior measurement index to avoid redundancy data and data loss. Third, a heuristic directive algorithm to improve entail data search efficiency, which returns appropriate ranked sensor results as per searching specifications. We examined thorough simulations to describe the DLi-SRC effectiveness. The outcomes reveal that our approach has significant performance gain, such as search efficiency, service quality, sensor existence rate enhancement by 91%, and sensor energy gain by 49% than benchmark standard approaches.

The advance of the Internet has resulted in an immensely interconnected world, which produces a tremendous amount of data. It has come to change our daily lives and behaviours tremendously. The trend is especially seen in the field of e-commerce where the customers have started to require more and more from the product and service providers. Moreover, with the rising competition, the companies have to adopt new ways of doing things to keep their position on the market as well as keeping and attracting new customers. One important factor for this is excelling customer service. Today, companies adopt technologies like BDA and AI to enhance and provide excellent customer service. This study aims to investigate how two Swedish cooperations extract value from their customer services with the help of BDA and AI. This study also strives to create an understanding of the expectations, requirements and implications of the technologies from the participants' perspectives that in this case are the employees of these mentioned businesses. Moreover, many fail to see the true potential that the technologies can bring and especially in the field of customer service. This study helps to address these challenges and by pinpointing the ’value- factors’ that companies participating in this study extracts, it might encourage the implementation of digital technologies in the customer service with no regard to the size of the company. This thesis was conducted with a qualitative approach and with semi-structured interviews and systematic observations with two Swedish companies acting on the Chinese market. The findings from the interviews, conducted with these selected companies, present that the companies actively use BDA and AI in their customer service. Moreover, several value-factors are pinpointed in the different stages of customer service. The most reoccurring themes are: ”proactive support”, ”relationship establishment”, ”identifying attitudes and behaviours” and ”real-time support”. Moreover, as for the value-creating factors before and after the actual interaction the reoccurring themes are ”competitive advantage”, ”high-impact customer insights”, ”classification”, ”practicality”, as well as ”reflection and development”. This essay provides knowledge that can help companies to further their understanding of how important customer service along with BDA and AI is and how they can support competitive advantage as well as customer loyalty. Since the thesis only focused on the investigation of Swedish organizations on the Shanghainese market, it would be of interest to continue further research on Swedish companies as China is seen to be in the forefront when it comes to utilizing these technologies.

Despite the increased cost of data breaches due to advanced, persistent threats from malicious sources, the adoption of big data security analytics among U.S. small businesses has been slow. Anchored in a diffusion of innovation theory, the purpose of this correlational study was to examine ways to increase the adoption of big data security analytics among small businesses in the United States by examining the relationship between small business leaders' perceptions of big data security analytics and their adoption. The research questions were developed to determine how to increase the adoption of big data security analytics, which can be measured as a function of the user's perceived attributes of innovation represented by the independent variables: relative advantage, compatibility, complexity, observability, and trialability. The study included a cross-sectional survey distributed online to a convenience sample of 165 small businesses. Pearson correlations and multiple linear regression were used to statistically understand relationships between variables. There were no significant positive correlations between relative advantage, compatibility, and the dependent variable adoption; however, there were significant negative correlations between complexity, trialability, and the adoption. There was also a significant positive correlation between observability and the adoption. The implications for positive social change include an increase in knowledge, skill sets, and jobs for employees and increased confidentiality, integrity, and availability of systems and data for small businesses. Social benefits include improved decision making for small businesses and increased secure transactions between systems by detecting and eliminating advanced, persistent threats.

En ökad användning av digitala produkter och tjänster skapar stora mängder av data för företag att behandla och analysera. Det gör att det finns ett behov av personer som har förmågan att hantera och analysera datamängderna för att skapa förutsättningar åt företag att ta beslut baserat på insamlad data. Dataanalys är ett område som växer i snabb takt vilket gör att nya arbetsroller och kompetensbehov skapas. Det gör att både näringsliv och akademi behöver vara ständigt uppdaterade inom IT-branschen för att möta efterfrågan från marknaden. Det för att se till att de nyutexaminerade besitter den kunskap och kompetens som behövs när de kommer ut i arbetslivet. Inom området för dataanalys finns det en brist på tidigare forskning angående vilka kompetenser en nyutexaminerad student inom dataanalys bör ha för att en övergång från akademi till arbetsliv ska bli lyckad. Därför ämnar denna studie att ta reda på vilka hårda- och mjuka kompetenser som är aktuella för en nyutexaminerad att besitta. Studien har utgått från en kvalitativ metod i form av semistrukturerade intervjuer med personer verksamma inom dataanalys för att få med deras erfarenheter och upplevelser och skapa en djupare förståelse för de aktuella kompetenserna. Genom en bearbetad analys har resultaten av studien resulterat i fem hårda, respektive sex mjuka kompetenser inom olika områden. De hårda kompetenserna omfattar import/ rengöring av data, datamodellering, molntjänster, visualiseringsverktyg och programmeringskunskaper. Av dessa framkom det att molntjänster är ett av de områden som nyutexaminerade har ofta begränsad kunskap eller kompetens inom. De mjuka innefattar kommunikation, nyfikenhet, intresse för utveckling, affärsförståelse, ödmjukhet och samarbetsförmåga. Resultaten visar att kommunikation och nyfikenhet/ intresse för utveckling är viktiga egenskaper för att lyckas inom IT-branschen som är en komplex och snabbt växande bransch.

For the second time, the Data Science Challenge took place as part of the 18th symposium “Database Systems for Business, Technology and Web” (BTW) of the Gesellschaft für Informatik (GI). The Challenge was organized by the University of Rostock and sponsored by IBM and SAP. This year, the integration, analysis and visualization around the topic of particulate matter pollution was the focus of the challenge. After a preselection round, the accepted participants had one month to adapt their developed approach to a substantiated problem, the real challenge. The final presentation took place at BTW 2019 in front of the prize jury and the attending audience. In this article, we give a brief overview of the schedule and the organization of the Data Science Challenge. In addition, the problem to be solved and its solution will be presented by the participants.

Data processing is generally defined as the collection and transformation of data to extract meaningful information. Data processing involves a multitude of processes such as validation, sorting summarization, aggregation to name a few. Many analytics engines exit today for largescale data processing, namely Apache Spark, Apache Flink and Apache Beam. Each one of these engines have their own advantages and drawbacks. In this thesis report, we used all three of these engines to process data from the Carbon Monoxide Daily Summary Dataset to determine the emission levels per area and unit of time. Then, we compared the performance of these 3 engines using different metrics. The results showed that Apache Beam, while offered greater convenience when writing programs, was slower than Apache Flink and Apache Spark. Spark Runner in Beam was the fastest runner and Apache Spark was the fastest data processing framework overall. / Databehandling definieras generellt som insamling och omvandling av data för att extrahera meningsfull information. Databehandling involverar en mängd processer som validering, sorteringssammanfattning, aggregering för att nämna några. Många analysmotorer lämnar idag för storskalig databehandling, nämligen Apache Spark, Apache Flink och Apache Beam. Var och en av dessa motorer har sina egna fördelar och nackdelar. I den här avhandlingsrapporten använde vi alla dessa tre motorer för att bearbeta data från kolmonoxidens dagliga sammanfattningsdataset för att bestämma utsläppsnivåerna per område och tidsenhet. Sedan jämförde vi prestandan hos dessa 3 motorer med olika mått. Resultaten visade att Apache Beam, även om det erbjuds större bekvämlighet när man skriver program, var långsammare än Apache Flink och Apache Spark. Spark Runner in Beam var den snabbaste löparen och Apache Spark var den snabbaste databehandlingsramen totalt.