The main objective of this diploma thesis is to design and develop a cloud hosted service that allows developers of games for Windows Phone 7 platform to extend their products with social and competitive aspect using Platform as a Service solution Windows Azure for hosting the backend of this system. The first part of the thesis analyses systems that are available on the market and that are providing similar services for the target platform. Based on this analysis, functional and general requirements for the future application are specified in the second part. Based on these requirements, use case analysis is made. The third part of the thesis is dedicated to description of the most important features, APIs and specifics of the Windows Phone 7 software platform. The fourth part is dedicated to Windows Azure as a Cloud platform both in terms of most important services, their characteristics and APIs used to utilise them and in terms of their business and pricing conditions. The fifth part addresses the architecture and the most important implementation details of the application. The final part contains the user guide for both the Windows Phone 7 application and for developers interested in using the library containing the API during the development of their game. The output of this thesis is the designed and implemented application with client-server architecture ready to have its backend deployed in Windows Azure environment and to have its frontend deployed on Windows Phone 7 devices. The client part of the system is comprised of a library intended for developers of games, which encapsulates the API needed to access the backend on the Internet, and a graphic frontend intended for end users. The server part, which contains most of the application logic, has REST interface. The applications architecture allows future development in terms of new functionality and expansion on more client platforms.

El presente proyecto desarrolla una propuesta de implementación de arquitectura empresarial integrada con tecnologías de inteligencia artificial. El resultado es proveer una propuesta de solución enfocada a la problemática identificada en los procesos comerciales del área de Soporte a la Operación: Identificar Oportunidades Comerciales y Gestionar Oportunidades Comerciales, los cuales actualmente son realizados de manera manual por especialistas del negocio, y la ejecución de tareas operativas o de análisis que, en diversos casos, se convierten en cuellos de botella, conlleva a la pérdida de oportunidades comerciales. Para ello, se ha propuesto un cambio en los procesos de negocio, con el objetivo de automatizar las actividades que demandan más tiempo y tienen alto impacto en el desarrollo de las oportunidades comerciales. El presente documento está compuesto por seis capítulos. Se inicia con la presentación de la empresa objeto de estudio, la problemática que se desea resolver, los objetivos del proyecto, incluyendo cómo medir su cumplimiento, el impacto que tendrá el proyecto en la empresa objeto de estudio y el análisis de factibilidad, tanto técnica como económica. Luego, se presenta el marco teórico, que contiene los conceptos claves que han brindado soporte a la solución propuesta, y bajo los marcos de trabajo TOGAF y ZACHMAN, utilizando la metodología ADM, se desarrolla el análisis del negocio y la identificación de requerimientos. Por último, se presenta el resultado del proyecto, que contiene la definición de la arquitectura del sistema propuesto y el plan de dirección del proyecto, que recoge las buenas prácticas del PMBOK® sexta edición y la metodología desarrollada por la empresa objeto de estudio. / This project develops a proposal to implement a business architecture integrated with artificial intelligence technologies. The result is to provide a solution proposal focused on the problem identified in the business processes of the Operation Support area: Identify Business Opportunities and Manage Business Opportunities, which are currently performed manually by business specialists, and the execution of operational or analytical tasks that, in some cases, become bottlenecks leading to the loss of business opportunities. In order to achieve this, a change in business processes has been planned, with the objective of automating activities that require more time and have a high impact on the development of business opportunities. This document is comprised of six chapters. It begins with the presentation of the company under study, the problem to be solved, the objectives of the project, including how to measure compliance, technical and economic impact the project will have on the company under study and the feasibility analysis. Then, the theoretical framework which contains the key concepts that have provided support to the proposed solution is presented and the business analysis and the identification of requirements are developed under the TOGAF and ZACHMAN frameworks, using the ADM methodology. Finally, the result of the project which contains the definition of the architecture of the proposed system and the project management plan is provided, which includes good practices of the PMBOK®️ sixth edition and the methodology developed by the company under study. / Tesis

Este proyecto tiene como objeto de estudio a una empresa pesquera nacional líder en su sector, dedicada a la extracción, transformación y comercialización de recursos hidrobiológicos para consumo humano indirecto y directo. La presente tesis propone el análisis, diseño e implementación de un asistente virtual para gestionar permisos y atención de consultas para reducir los tiempos en los cierres de planillas semanales de tripulantes y obreros. Los procesos de estudio son la gestión de permisos y la gestión de consultas del área de Gestión Humana. En el primer proceso, las solicitudes del personal tripulante y obrero se realizan con formatos físicos y son registrados de forma manual en el sistema por los responsables de administración de personal, lo que está sujeto a errores de digitación y a que no se realicen en el tiempo oportuno lo que produce pagos incorrectos en la nómina y reprocesos. En el segundo proceso, las consultas que los colaboradores realizan a los responsables de administración de personal sobre temas relacionados a sus pagos son recurrentes todas las semanas debido a que necesitan conocer cómo se calculan sus pagos semanales que dependen de factores variables derivados de la producción. También, realizan consultas variadas como los tipos de beneficios, seguros y otras gestiones personales. Bajo esta premisa, nuestra propuesta de solución en este proyecto se basa en un asistente virtual con reconocimiento de lenguaje natural utilizando inteligencia cognitiva, con acceso mediante una aplicación móvil, para que los tripulantes y obreros puedan auto gestionar sus descansos y consultas de manera oral o escrita mediante un asistente virtual tal como si lo hicieran con una persona real. Además, dejamos abierto este canal para que pueda ser usado por otros procesos del área y de otras áreas de la empresa. Todo esto, ayudará a minimizar el tiempo de horas hombre que se invierte en registrar descansos y gestionar las consultas para que el área de Gestión Humana se pueda enfocar al cálculo correcto y oportuno de los cierres de planillas semanales, y en otras funciones propias del área. / This project aims to study a leading national fishing company, a leader in its sector, dedicated to the extraction, transformation, and commercialization of hydrobiological resources for indirect and direct human consumption. This thesis proposes the analysis, design, and implementation of a virtual assistant to manage permits and attend inquiries to reduce the closing times of weekly payroll for crew and workers. The study processes are the management of permits and the management of queries from the Human Management area. In the first process, the requests of the crew and worker personnel are made with physical formats and are manually registered in the system by those responsible for personnel administration, which is subject to typing errors since they are not always carried out in a timely fashion which produces incorrect payroll payments and the need for corrections. In the second process, the consultations that collaborators make to those responsible for personnel administration on issues related to their payments are recurring every week because they need to know how their weekly payments are calculated, which depend on variable factors derived from production. Also, they carry out various queries such as types of benefits, insurance, and other personal procedures. Under this premise, our solution proposal in this project is based on a virtual assistant with natural language recognition using cognitive intelligence, with access through a mobile app, so that crew members and workers can self-manage their breaks and consultations orally or in writing. using a virtual assistant as if they were doing it with a real person. In addition, we leave this channel open so that it can be used by other processes in the area and other areas of the company. All this will help to minimize the man-hour time that is invested in recording breaks and managing inquiries so that the Human Management area can focus on the correct and timely calculation of weekly payroll closings, and on other functions of the area. / Tesis

Klassificering av dagliga aktiviteter (ADL) kan användas i system som bevakar människors aktiviteter i olika syften. T.ex., i nödsituationssystem. Med machine learning och bärbara sensor som samlar in data kan ADL klassificeras med hög noggrannhet. I detta arbete, ett proof-of-concept system med tre olika machine learning algoritmer utvärderas och jämförs mellan tre olika dataset, ett som är allmänt tillgängligt på (Ugulino, et al., 2012), och två som har samlats in i rapporten med hjälp av en android enhet. Algoritmerna som har använts är: Multiclass Decision Forest, Multiclass Decision Jungle and Multiclass Neural Network. Sensorerna som har använts är en accelerometer och ett gyroskop. Resultatet visar hur ett konceptuellt system kan byggas i Azure Machine Learning Studio, och hur tre olika algoritmer presterar vid klassificering av tre olika dataset. En algoritm visar högre precision vid klassning av Ugolino’s dataset, jämfört med machine learning modellen som ursprungligen används i rapporten. / Classifying Activities of daily life (ADL) can be used in a system that monitor people’s activities for different purposes. For example, in emergency systems. Machine learning is a way to classify ADL with high accuracy, using wearable sensors as an input. In this paper, a proof-of-concept system consisting of three different machine learning algorithms is evaluated and compared between tree different datasets, one publicly available at (Ugulino, et al., 2012), and two collected in this paper using an android device’s accelerometer and gyroscope sensor. The algorithms are: Multiclass Decision Forest, Multiclass Decision Jungle and Multiclass Neural Network. The two sensors used are an accelerometer and a gyroscope. The result shows how a system can be implemented using Azure Machine Learning Studio, and how three different algorithms performs when classifying three different datasets. One algorithm achieves a higher accuracy compared to the machine learning model initially used with the Ugolino data set.

På företaget AFRY i Karlstad har en medarbetare med fika varje fredag och turordningen för detta sker i dagsläget med en Excel-fil vilket är problematiskt då inte alla har tillgång till filen och kan då inte se när det är deras tur att ta med fika, vilket resulterar i att det glöms av att ta med fika. Författaren har fått i uppdrag av AFRY att ta fram en webbaserad applikation där personalen kan se schemat för vems tur det är att ta med fika. En kravspecifikation upprättades av uppdragsgivaren tillsammans med en lista på den tekniska uppsättningen för webbapplikationen som gäller. Studiens syfte är att undersöka vilka komplikationer som uppstår vid implementationen samt hur användarna mottar applikationen. För detta har två undersökningsfrågor upprättats som ligger till grund för studien: Vad resulterar utvärderingarna i och vilka förslag till förbättring mottogs? Vilka komplikationer uppstår vid implementationen och hur har dessa lösts? Design Science Research applicerades som forskningsstrategi för studien där momenten Specificera krav, Implementering och Utvärdering användes för att skapa artefakten som det studeras kring. En agil arbetsmetod låg till grund för att föra arbetet framåt där det utvecklades i tre sprintar. Artefakten utvärderades av testpersoner som var personal hos uppdragsgivaren och det genomfördes Black Box- och Manuella tester där testpersonerna fick uttrycka och reflektera kring implementationen som utförts. Data samlades in med hjälp av strukturerade intervjuer där författaren förde anteckningar på vad som uttrycktes. Utvärderingarna resulterade i att det som implementerades saknade funktionalitet som testpersonerna efterfrågade. Flertalet data samlades in som påvisar att de krav som ställdes skulle behövt specificerats ytterligare för att uppnå högre tillfredsställelse från testpersonerna. De komplikationer som påträffades under implementationen kunde antingen lösas genom att läsa dokumentationen för teknik som användes eller att testpersonerna, som innehar mer erfarenhet än författaren, kunde lösa dessa. Slutsatsen för studien är att krav som ställs måste specificeras mer detaljrikt för att artefakten skall bli så likt användarnas bild av den som möjligt.

In the data-driven landscape of modern business, predictive analytics plays a pivotal role inanticipating and mitigating customer churn—a critical challenge for organizations. However, thetraditional complexities of machine learning hinder accessibility for decision-makers. EnterMachine Learning as a Service (MLaaS), offering a gateway to predictive modeling without theneed for extensive coding or infrastructure.This thesis presents a comprehensive evaluation of cloud-based and cloud-agonostic AutoML(Automated Machine Learning) platforms for customer churn prediction. The study focuses onfour prominent platforms: Azure ML, AWS SageMaker, GCP Vertex AI, and Databricks. Theevaluation encompasses various performance metrics including accuracy, AUC-ROC, precision,recall to assess the predictive capabilities of each platform. Furthermore, the ease of use andlearning curve for model development are compared, considering factors such as data preparation,training steps, and coding requirements. Additionally, model training times are analyzed toidentify platform efficiencies. Preliminary results indicate that AWS SageMaker exhibits thehighest accuracy, suggesting strong predictive capabilities. GCP Vertex AI excels in AUC,indicating robust discriminatory power. Azure ML demonstrates a balanced performance,achieving notable accuracy and AUC scores. Databricks being platform independent is a winnerand has also shown good metrics. Its capability to generate notebook is an added advantage whichcan be modified by experts to fine tune the results more. This research provides valuable insightsfor organizations seeking to implement different AutoML solutions for customer churnprediction.

Tidigare forskning har påvisat brister i olika former av autentiseringsprocesser som leder till autentiseringsattacker. Målet med vår studie är att presentera ett antal riktlinjer som företag och privatpersoner kan följa för att minimera risken för autentiseringsattacker. Metoderna som användes för att komma fram till dessa riktlinjer var kvalitativa där en praktisk observationsstudie, en litteraturstudie samt en enkätundersökning låg till grund för vår insamlade data. Resultatet av studien pekar på att Google Cloud Platform, Amazon Web Services och Microsoft Azure alla har en stark autentiseringsprocess i jämförelse med kritik från tidigare forskning. Enkätundersökningen visade dessutom att olika former av alternativ autentisering, såsom Two Factor Authentication (2FA) och Multi Factor Authentication (MFA), rekommenderas för ett starkt försvar mot autentiseringsattacker.Uppsatsens resultat pekar även på att användarens egenansvar i autentiseringsprocessen är av stor vikt för att minimera risken för autentiseringsattacker. Säkra lösenord bör konstrueras och frekvent bytas ut. Även alternativ autentisering och begränsning av användarens tillgång till känslig information bör tillämpas. / Previous research has shown deficiencies in various forms of authentication processes that lead to authentication attacks. The goal of our study is to present a number of guidelines that businesses and individuals can follow to minimize the risk of authentication attacks. The methods used to reach these guidelines were qualitative. They consisted of a practical observational study, a literature review and a survey, which formed the basis of our collected data. The results of the study indicate that Google Cloud Platform, Amazon Web Services and Microsoft Azure all have a strong authentication process in comparison with the criticism of previous research. The survey also showed that different forms of authentication methods, such as the Two Factor Authentication (2FA) and Multi Factor Authentication (MFA), are recommended for a strong defense against authentication attacks.The thesis’ results also points to the user’s own responsibility in the authentication process are essential to minimize the risk of authentication attacks. Secure passwords should be designed and frequently replaced. Alternative authentication and restricted access to sensitive information for the user should also be applied.

This report compares the performance of container orchestration architecture and serverless computing platforms within cloud computing. The focus is on their application in managing real-time communications for electric vehicle(EV) charging systems using the Open Charge Point Protocol (OCPP). With the growing demand for efficient and scalable cloud solutions, especially in sectors using Internet of Things (IoT) and real-time communication technologies, this study investigates how different architectures handle high-load scenarios and real-time data transmission. Through systematic load testing of Kubernetes (for container orchestration) and Azure Functions (for serverless computing), the report measures and analyzes response times, throughput, and error rates at various demand levels. The findings indicate that while Kubernetes performs robustly under consistent loads, Azure Functionsexcel in managing dynamic, high-load conditions, showcasing superior scalability and efficiency. A controlled experiment method ensures a precise and objective assessment of performance differences. The report concludes by proposing a hybrid model that leverages the strengths of both architectures to optimize cloud resource utilization and performance.

The expanding adoption of cloud computing services by businesses has transformed IT infrastructure and data management in the computing space. Cloud computing offers advantages such as availability, scalability, and cost-effectiveness, making it a favored choice for businesses of all sizes. The aim of this thesis is to compare private and public cloud computing services in terms of pricing and implementation effort as well as comparing the cloud providers to each other. The top three cloud providers that will be examined are Google GCP, Microsoft Azure, and Amazon AWS. The study examines different pricing models and evaluates their effectiveness in different business scenarios. In addition, the thesis also discusses the challenges associated with building and maintaining private infrastructure and the deployment of applications to cloud computing service are examined. The research methodology involves data collection, analysis, and a case study of developing and deploying a ticketing system application on different cloud platforms. The ticket system helps to provide a realistic example and investigation of the cloud providers. The findings will help companies make informed decisions regarding the selection of the most appropriate cloud computing service based on pricing models and implementation efforts. The thesis provides valuable information on private and public cloud computing and recommends appropriate pricing models for different scenarios. This study adds to existing knowledge by analyzing current pricing models and deployment concepts in cloud computing. The thesis does not propose new solutions but follows a structured format compiling information on private, and public cloud computing and a comprehensive review of cloud computing pricing models and marketing efforts. / Den växande adoptionen av molntjänster inom företag har förändrat IT-infrastrukturen och datahanteringen inom datorområdet. Molntjänster erbjuder fördelar såsom tillgänglighet, skalbarhet och kostnadseffektivitet, vilket gör det till ett populärt val för företag i alla storlekar. Syftet med denna avhandling är att jämföra privata och offentliga molntjänster med avseende på prissättning och implementeringsinsatser samt att jämföra molnleverantörerna med varandra. De tre främsta molnleverantörerna som kommer att undersökas är Google GCP, Microsoft Azure och Amazon AWS. Studien undersöker olika prismodeller och utvärderar deras effektivitet i olika affärsscenarier. Dessutom diskuterar avhandlingen också utmaningarna med att bygga och underhålla privat infrastruktur samt implementeringen av applikationer till molntjänster. Forskningsmetodologin omfattar datainsamling, analys och en fallstudie av utveckling och implementering av ett support system på olika molnplattformar. Supportsystemet hjälper till att ge ett realistiskt exempel och undersökning av molnleverantörerna. Resultaten kommer att hjälpa företag att fatta informerade beslut när det gäller valet av lämpligaste molntjänst baserat på prismodeller och implementeringsinsatser. Avhandlingen tillhandahåller värdefull information om privat och offentlig molntjänst och rekommenderar lämpliga prismodeller för olika scenarier. Denna studie bidrar till befintlig kunskap genom att analysera nuvarande prismodeller och implementeringskoncept inom molntjänster. Avhandlingen föreslår inga nya lösningar, men följer en strukturerad format genom att sammanställa information om privat och offentlig molntjänst samt en omfattande översikt av prismodeller och marknadsinsatser inom molntjänster.

The current proliferation of mobile systems, such as smart phones, PDA and tablets, has led to their adoption as the primary computing platforms for many users. This trend suggests that designers will continue to aim towards the convergence of functionality on a single mobile device. However, this convergence penalizes the mobile system in computational resources such as processor speed, memory consumption, disk capacity, as well as in weight, size, ergonomics and the user’s most important component, battery life. Therefore, this current trend aims towards the efficient and effective use of its hardware and software components. Hence, energy consumption and response time are major concerns when executing complex algorithms on mobile devices because they require significant resources to solve intricate problems. Current cloud computing environments for performing complex and data intensive computation remotely are likely to be an excellent solution for off-loading computation and data processing from mobile devices restricted by reduced resources. In cloud computing, virtualization enables a logical abstraction of physical components in a scalable manner that can overcome the physical constraint of resources. This optimizes IT infrastructure and makes cloud computing a worthy cost effective solution. The intent of this thesis is to determine the types of applications that are better suited to be off-loaded to the cloud from mobile devices. To this end, this thesis quantitatively and qualitatively compares the performance of executing two different kinds of workloads locally on two different mobile devices and remotely on two different cloud computing providers. The results of this thesis are expected to provide valuable insight to developers and architects of mobile applications by providing information on the applications that can be performed remotely in order to save energy and get better response times while remaining transparent to users.