Examensarbeten på grundnivå // Basic Level Theses
Länka till denna samling:
Browse
Browsar Examensarbeten på grundnivå // Basic Level Theses efter Program "Datateknik 180 hp (högskoleingenjör)"
Visar 1 - 20 av 101
Sökresultat per sida
Sortera efter
- PostA model based approach to lane detection and lane positioning using OpenCV(2017) Posch, Daniel; Rask, Jesper; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)The aim of this thesis was to implement and develop a computer vision based method that would play a important part in the implementation of an autonomous RC car. In particular this thesis provides the initial steps of image pre-processing, an algorithm for lane detection, position identification and a communication model. The study was preformed with two main goals. The first goal consists of an investigation of a suitable algorithm to efficiently detect specific information from an image, to be able to act in a way based on the extracted data. The second goal was to determine what camera specifications are needed for the chosen algorithm. Using different approaches of algorithms for detecting a path between lanes, this thesis present an implementation of the B-snake model. The program is evaluated in the Udacity game simulator, as well as on real hardware with challenging benchmarks such as lanes with hard curvature, high speed and noisy environments. The program performed well in different environments together with a limited speed. However lanes with curvature which exceeds 25 degrees has to be further developed in the future.
- PostAI Word Plugin – Utveckling av ett Word plugin som använder sig av AI-text- och bildgenerering(2023) Gustavsson, Erik; Brottare, Oliver; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Svensson, Lars; Krook, RobertAnvändandet av AI bland allmänheten har ökat explosionsartat det senaste året. Många använder sig av AI-verktyg för att få hjälp med exempelvis programmering eller redigering av texter, medan många andra använder AI-verktyget av ren nyfikenhet. Syftet med detta projekt är att göra ett praktiskt hjälpmedel för skapandet av olika dokument med hjälp av AI-tekniken. Projektet realiseras med hjälp av Microsoft Word och OpenAI:s API. Programspråken som projektet är skrivet i är Javascript, HTML/CSS och Python. Stort fokus lades på att pluginet skulle vara lätthanterligt och en enkät gjordes för att mäta detta. Resultatet visar att det mycket väl går att skapa egna program för ett mer anpassat bruk av AI. Projektet ämnade även att behandla träning av egna AI-modeller för ett ännu mer specialiserat verktyg. En första model av AI-träning implementerades men finslipning av denna fick inte plats inom tidsramen.
- PostAnalys av dataloggar - Kategorisering och prioritering av loggar(2016) Edsinger, Daniel; Andersson, Ola; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Detta projekt är till för att underlätta Anturas felsökningsprocess genom att på ett lämpligt sätt tillämpa en algoritm som ska göra det enkelt för Antura att behandla de mest kritiska felen i deras produkt. När företag ska felsöka buggar och fel i sina mjukvaror efter hundratals felmeddelanden från sina kunder, görs det i en långsam process genom att läsa igenom dem en efter en. Deras innehåll hjälper till att felsöka problemet och möjligtvis återskapa felet. Detta arbetsätt är mycket vanligt hos företag som utvecklar applikationer, även hos Antura, företaget som arbetet gjordes för. Det vi har gjort är att förenkla denna process med ett program som med hjälp av Graylog, kunna prioritera och kategorisera alla loggar som skickas från kunderna. Vår slutprodukt består av: ett plugin till Graylog, en databas och ett externt program som heter Titan. Pluginet analyserar alla loggar som kommer in till Graylog och skickar dessa till databasen. Titans uppgifter är att visa alla loggar i olika kategoriseringar och prioritera dessa beroende på dess innehåll.
- PostAssisterad zonindelning – Zonindelningsförslag baserade på lastdata från entreprenadmaskiner(2023) Sargent, Jonathan; Claesson, Martin; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Svensson, Lars; Andreasson, CPAC, MathiasStenbrotts storlek och förändringshastighet är båda faktorer för hur resurskrävande det är för bolag att hålla kartor uppdaterade. I projektet används information genererat från existerande system i dumprar och hjullastare i en algoritm med 2 uppgifter, att kategorisera informationen och generera zoner baserat på de olika grupperna av noder. Vilket möjliggörs genom tillgång till geografisk, temporal information, samt information angående vad maskinen gjorde. Målet är att en potentiell integration till existerande system, som sedan skulle kunna vara hjälpmedel för maskin-förare. Genom problemdomänen definierar rapporten mål för en algoritm som ska kunna användas i produktion och vara till störst användning för maskinarbetare möjligt. En initial design har i samarbete med produktägaren använts som utgångspunkt och en mvp har utvecklats och raffinerats. Algoritmen har utvecklats genom agilt arbete med inspiration från scrum. Först skapades en simpel version som sedan förbättrades och reviderades efter bedömning från både utvecklare och produktägare. Genom användandet av biblioteket förenklar projektet utvärdering av de olika iterationerna. Som resultat erhåller projektet en algoritm som utöver att klara av prestandakraven genererar beskrivningar av information som kan vara till hjälp vid gruvdrift. För vidare utveckling rekommenderas undersökande av alternativ som exempelvis gruppering av noder genom maskinlärning. Ytterliggare förbättringar skulle kunna involvera förmåga för algoritmen att utgå från existerande resulterande zoner för att hoppa över delar av arbetet och därmed ytterligare optimeras i prestanda.
- PostAutomatisering och Digitalisering av ISO-9001 Dokumentationshantering(2016) Cuskic, Elvedin; Hult Pappas, Elias; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)ISO-9001 är en standard för ledningssystem i företag och organisationer som innehar certifieringen. Ett ledningssystem beskriver ett tillvägagångssätt för hur verksamheten ständigt skall förbättras och justeras för att möta kundernas behov. Genom att kontinuerligt utföra kvalitetsgranskningar ser verksamheten till att fortsättningsvis uppfylla de krav som finns uppställda i standarden, certifieringen blir ett bevis på att kvalitetsarbetet faktiskt håller måttet. För att komma ett steg närmare mot att automatisera kvalitetsgranskningsprocessen har en produkt tagits fram genom samarbete med Altran i syfte om att utveckla en mobillösning där utförandet av kvalitetsgranskningarna effektiviseras och tas digitalt. Arbetet har resulterat i en mobilanpassad applikation som låter användare utföra kvalitetsgranskningar enligt en mall digitalt i sin telefon. Vid avslutad kvalitetsgranskning genereras dokument utifrån ifylld mall. Resultatet är ett stort steg mot ett mer modernt och digitalt arbetssätt inom företag och organisationer vad gäller upprätthållandet av kvalitetsarbetet.
- PostBenefits and costs of enabling variability and traceability in source code via feature annotations(2023) Rymo, Love; Abunaj, Fadi; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Svensson, Lars; Berger, ThorstenFeatures, which drive the advancement of software systems, are often obscured in modern software projects due to the lack of clear and location-specific documentation. This absence creates significant challenges in software development, notably in time and resource efficiency. This lack of explicit feature documentation often leads to time-consuming efforts in locating features. This study tackles the problem by exploring an innovative approach: embedding feature annotations directly in the source code. It investigates both the benefits and potential costs associated with this practice, filling a gap in the current body of literature. To empirically evaluate this approach, a specialized tool, that we will refer to as an ’annotation logger’ was developed. The goal of the tool is to measure the time efficiency of feature annotations. Despite a few minor inaccuracies, the results of this evaluation demonstrated the tool’s reliability in gathering meaningful data. The findings suggest that, while introducing some additional overhead, feature annotations could fundamentally enhance the software development process by increasing location-specific clarity and reducing search times.
- PostBMS med Dynamisk CANopen Nod-ID Tilldelning(2018) EDWARDSON, JOHN; EMANUELSSON, EMIL; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)This project is intended to proceed with the developement of a battery management system (BMS) in an electric vehicle. The project has been issued from the company Clean Motion AB, and the work took place in a laboratory at Chalmers. In the purpose of being able to connect a set of batteries in parallel in the vehicle, the project examines the possibilities of connecting multiple BMS devices to a CAN bus. This should be done so that the data transmitted on the CAN bus does not collide with other data. Also the software of the BMS has been translated from BASIC to C and nally its features have been tested to verify the correctness. In the report the reader will nd an analysis and description of the BMS and its software. The reader will also nd a description on how the CAN bus is operating and how the BMS uses it. Thereafter the report evaluates a set of di erent possible solutions for avoiding collision of data on the CAN bus. And how it was nally implemented and tested.
- PostCentralt Backupsystem - System för monitoring av backups(2019) Dahlberg, Nikolai; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Consat Data AB manages other companies’ IT environment. For every customer there are backup servers with different softwares. These are responsible for creating backups of the customers’ servers and send reports to the administrators when done. Due to the number of customers and servers the administrators can receive up to 300 reports a day through mail and web interfaces. One administrator must read through all these reports every day which makes the work inefficient. This is what this project tries to solve. The goal of the project was to make Consats work with backups more efficient. This was done by creating a system that fetched backup data and presented this in a web interface. The system was split into two applications, one to handle the web interface and one python application to handle, fetch and read the backup data. While working on the goal the purpose of the project was to discover and examine different methods to fetch, handle and view backup data. The different methods were chosen depending on functionality, popularity and existing documentation. The work resulted in two working prototype applications. The first application is written in Python. The purpose of the application is to fetch mails and backup information to extract backup data. The second application is a web application with Node.JS as a base. It’s purpose is to show the extracted backup data in a webinterface.
- PostChatUp; En Chatbot med kontinuerligt lyssnande samt snabb respons.(2018) Martinson, Johan; Rydén, Daniel; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Interest in IT and especially artificial intelligence increases in Swedish companies by the day. Therefore a platform in the form of a robot to accommodate experiments in machine learning and machine intelligence has been developed. The idea is that this basic product will capture peoples’ interests during fairs and events. The developed software module ChatUp has been integrated into a Nao-robot, which is a small humalike robot, that takes in user requests, interprets them via a NLP and then selects an appropriate service to finally respond. Since the idea is that the robot should behave as humanlike as possible, the time between request and response should be shortened to a minimum. The project has therefore investigated sound segmentation algorithms, to remove silence and non-speech in audio this with the intention of minimizing the size of its data packet transmitted over the network, thus shortening the response time. The investigation has resulted in the fact that manipulation of live-streaming audio is not suitable while live streaming analysis can shorten response time noticeably. The results will be used as a basis for further development of the robot and the ChatUp module.
- PostClustering Non-Stationary Data Streams with Online Deep Learning(2016) Rising, Magnus; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)With more devices connected, sensor data logged and people active in social networks, the trend towards working with dynamic data is clear. The number of applications where it becomes essential to perform real time analysis on data streams grows accordingly, each with its own challenges. From this area of data stream analysis we benchmark the performance of current state of the art clustering algorithms: CluStream, DenStream and ClusTree. We also adapt a Variational Autoencoder to perform in the context of non-stationary data streams and assess its generative capabilities for dimensionality reduction. From this limited lab experiment we show that while there is a significant improvement in the clustering accuracy of high dimensional datasets after a dimensionality reduction with a Variational Autoencoder, not all clustering algorithms benefit in the same way from it. Additionally we show that regardless of the clustering algorithm, no relevant improvement in the purity of the clusters could be obtained after the dimensionality reduction.
- PostCombining Deep Learning with traditional algorithms in autonomous cars(2017) Falk, Albin; Granqvist, David; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Research of autonomous technologies in modern vehicles are being conducted as never before. For a long time, traditional computer vision based algorithms has been the primary method for analyzing camera footage, used for assisting safety functions, where decision making have been a product of manually constructed behaviours. During the last few years deep learning has demonstrated its extraordinary capabilities for both visual recognition and decision making in end-to-end systems. In this report we propose a solution of introducing redundancy by combining deep learning methods with traditional computer vision based techniques for minimizing unsafe behaviour in autonomous vehicles. The system consists of a computer vision based lane detection algorithm in combination with a fully connected Deep Neural Network, and combines the advantages of both technologies by constructing a control algorithm responsible for consolidating the sub systems calculations of the correct steering angle, used to keep the vehicle within the lane markings of the road. The solution proposed show that we can increase the performance of our system by applying a combination of the two technologies in a simulator resulting in a safer system than we could achieve with the technologies separately.
- PostDatakommunikation för signalsystem(2016) Luong, Quang; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Bombardiers signalsystem för järnväg, INTERFLO 150, består av flera delsystem som interagerar med varandra. Delsystemen inkluderar Centralised Traffic Control (CTC), Traffic Control Centre (TCC) och Object Controller System (OCS). Dessa tre delsystem tillåter fjärrstyrd kontroll av objekt längs järnvägsspår. Detta arbete är del av ett projekt som gick ut på att undersöka möjligheterna med samma kontroll, utan mellanliggande TCC för att skapa ett simplare signalsystem. Detta system skulle innebära en förmånligare lösning där det komplexa säkerhetssystemet TCC skulle vara överflödigt. Systemet skulle även kunna användas för att underlätta styrning av objekt, eftersom ett komplext mellansteg inte längre skulle behövas. Detta kan underlätta för t.ex. testning och användningsområden där ökad manuell styrning är önskvärd. Detta arbete skapade direkt kommunikation mellan CTC och OCS. För att möjliggöra detta utvecklades en kommunikationsmodul baserad på nätverksprotokollet vilket OCS använder för att kommunicera med TCC. Därefter integrerades denna modul i CTC. Lösningen har utvecklats i programmeringspråket Java, med Eclipse som utvecklingsmiljö. Projektet har utförts hos Bombardier Transportation Rail Control Solutions i Göteborg, Sverige.
- PostDesign and Implementation of a Modern Standard Marine Communication Phrases (SMCP) Language Learning Application(2023) Ghadri, Mirco; Omar, Zakariya; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Chalmers University of Technology / Department of Computer Science and Engineering; Svensson, Lars; Abdipour, MortezaThis Bachelor’s thesis describes the development of a modern and updated Standard Marine Communication Phrases (SMCP) language learning application for the shipping and marine technology division at Chalmers University of Technology. The aim of this project is to design and construct a functional demo application that serves as a proof of concept and provides valuable insights for future development. By conducting data gathering, iterative design prototyping, and software implementation, the project successfully accomplished its goals. The outcomes include the identification of user needs and the creation and evaluation of a design prototype. Online surveys were utilized for data gathering and evaluation, allowing for the collection of user feedback and insights. The project resulted in the development of a fully functional cross-platform application compatible with Web, iOS, and Android platforms. The evaluation process validated the effectiveness of the design, while also highlighting potential areas for future enhancement. Ultimately the project’s findings and insights have the potential to significantly impact SMCP learning at Chalmers University of Technology and beyond.
- PostDeveloping components for a data-driven trading system(2018) HEDENBERG, FRED; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Data is an important resource, which through data science can yield many interesting insights and predictions. To utilize data, it needs to be collected, stored, preprocessed and modelled. The purpose of this project was to develop components that together form a simple data-driven stock trading system. Firstly, software to web scrape publicly available news and pricing data from the Swedish stock exchange AktieTorget, is developed. Secondly, this data is then used to test whether it is possible to create models and tools able of aiding/performing trading decisions. To support the development of the above-mentioned software and models, some theory is provided about stock markets, together with a walkthrough of the workflow and components of data science. The result is a system that utilizes a Python module, Scrapy, to automatically collect news and pricing data and then pass it on to a MongoDB database. The characteristics of the collected pricing data made it hard to work with, which was partly solved by manually collecting data from Nasdaq OMX. In addition to the system to collect and store data, three experiments were conducted to test the model and tool developed. All three experiments gave interesting insights, even though the results weren’t assertive. The single most interesting result was the model’s predicting performance for clustered signals. As a notice of potential future work, an API connection to a broker (e.g. Nordnet) could be developed. This would enable models to be used for real time trading. Moreover, the news and pricing data can be used together with natural language processing to create more sophisticated models.
- PostDigital positionsspårning En förbättrad upplevelse för åskådare under motorsportsevent(2017) Fridén, Joachim; Aksöz, Mikael; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)The technology of today is very extensive and constantly evolving. In recent years, it is not uncommon to use this technology in different sports and racing events. This report describes the process of developing a visualization system that enhances the experience for the spectators present at the event. This system is designed and customized especially for motorsport events. The GPS-based system is developed to follow the participants’ progression on the track. It is designed to give the user the maximum experience when attending alongside the racetrack, and to overcome complications related to limitations in viewing. One of the foremost complications in viewing the racetrack and most importantly the vehicles today is that the racetrack often is obscured by hills, buildings, trees and other items. This report describes the choice of hardware and the development of software which forms a system that helps the spectators to digitally follow the participants position on the racetrack in real time. The work has resulted in a system where the one can take part of the Graphical User Interface by a monitor that receives information from the database. The database receives its information from cellular phone with GPS-transmitters located in the vehicles of the participants. Software, hardware and systems were developed based on the requirement specifications and demands from spectators and participants at the STCC in Falkenberg the ninth of July 2017. The system was developed in close cooperation with the company Cetrez Group AB, which is engaged in the production of similar products.
- PostDynamic Range Sound Compressor Unit(2017) Bonvik, Thorbjørn; Nilsson, Jesper; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)As music tends to get produced for low end speakers and to sound the loudest, this paper might suggest a solution to end the so called loudness war. If the destructive dynamic range compression can be applied at the end users level instead of in the sound file itself, the producers can master with high-fidelity in mind again, so this text will describe the development of a dynamic range compressor designed for this specific purpose and then break down if and/or how the results holds promise. The prototype is based on a small Linux computer with physical input and output through an external soundcard. The utilities JackD 2 and ALSA is used for the sound handling, and the code is written in C. Math concepts used to develop the code will be described in the Theory part, but the code itself will not be gone through in this paper. However, the code should be accessible online and it is open source.
- PostECU-brandvägg - Demonstration av ECU-brandvägg i AUTOSAR-miljö(2016) Edevåg, Michael; Swierczynski, Robert; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)I takt med att bilar blir mer och mer uppkopplade mot internet och användare tillåts att styra olika funktioner i bilen via sina telefoner blir säkerhetsaspekten viktig att tänka på. Utvecklingen av självkörande bilar har också bidragit till att mer vikt läggs på att säkerheten ska vara hög. AUTOSAR-standarden används idag av många biltillverkare för att definiera hur mjukvaran i bilens alla ECU-enheter ska vara skriven. AUTOSAR har dock inte någon klart definierad modul för en säkerhets-brandvägg. ArcCore AB arbetar med AUTOSAR-relaterade produkter och har skapat en implementering av AUTOSAR som heter Arctic Core. På uppdrag av ArcCore undersöker den här rapporten möjligheten att implemen-tera någon form av en brandvägg i Arctic Core. Någon ny modul har inte utvecklats, endast befintliga moduler har använts. Några starka krypterings-algoritmer har ej använts då rapportens fokus endast ligger på att visa att det är möjligt att kryptera. Resultatet av rapporten visar en metod för att implementera en brandvägg i AUTOSAR-miljö och erbjuder också ett enkelt demonstrationsprogram för att visa hur brandväggen både autentiserar användare och krypterar kommunikationen.
- PostEfficient Intersection of Terrain Geometry in Real-Time Applications(2017) SJÖSTRAND, TIM; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)n interactive computer graphics applications it is often desirable to draw some form of terrain; ground planes with visually interesting features such as valleys and hills. These are typically stored as a height map image file and converted into a collection of triangles at run-time. When such geometry is used it soon becomes necessary to calculate the intersection point of a ray through the geometry, most notably to map user cursor interaction into 3D space. However, such calculations scale poorly with the number of triangles generated from very large height maps. The traditional optimization has been to reduce the number of calculations required by utilizing a quadtree data structure to search the height map and discard triangles that do not lie inside quadtree leaf nodes along the path of the ray. This paper introduces an extension of this optimization by projecting the line through quad tree leaf nodes onto the height map plane, reducing the number of calculations by a considerable amount. Our testing of a worst-case scenario suggests improvements in calculation speed of about 50x compared to the traditional optimization, which should be interesting for anyone implementing 3D terrain based on a height map.
- PostEmbedding Prefetching of Audio Content in ARM Processors(2017) Spetz Rasmussen, Anders; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)This paper describes the design and implementation an audio amplifier host module. The hardware developed served as a physical interface between the amplifier and an ARM equipped evaluation board capable of running the Linux kernel. Both hardware and software development was carried out at amplifier manufacturer Lab.gruppen facilities according to specified technical requirements. The project resulted in a functioning embedded audio player prototype. More specifically, the project resulted in the necessary underlying hardware and firmware that is intended to serve as a platform for further development of the amplifier host module.
- PostEn chatbot med maskininlärning(2017) Lignell, Oskar; Punell, Robin; Chalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers); Chalmers University of Technology / Department of Computer Science and Engineering (Chalmers)Within the healthcare today communication is used with old fashion technology. Patients must make a phone call to get an answer on a general question. This could cause long idle times and is an inefficient method for simple things. The University hospital in Linköping, which has given the task to the company ÅF, is in need to simplify and make this communication more efficient. This report intends to give answers on how to make this communication more efficient with the help of a chatbot and a chat application. An investigation of different chatbots and their functionalities is also made. The prototype that has been developed is a chat application embedded in a website. The application can answer questions previously asked by patients over the phone. Depending on what type of question that was asked, the answer is presented in different ways. If the question is about where a department is located the answer will contain a picture of a map, or with a form if the patient want to book an appointment. The prototype does not store any personal information since nothing more than a demonstration of how a chat application can work has been made.