[dipl] Insinööritieteiden korkeakoulu / ENG
Permanent URI for this collectionhttps://aaltodoc.aalto.fi/handle/123456789/18
Browse
Recent Submissions
Now showing 1 - 20 of 5682
- Maantiet kaduiksi - liikenneväylät asemakaava-alueilla
School of Engineering | Master's thesis(2024-12-05) Leukkunen, ElinaSection 83 of the Land Use and Building Act stipulates the purposes for which roads can be designated as road traffic areas in local plans. The power of control over planning is assigned to municipalities and cities, and in addition, the administrative classification of roads from road to street is not determined by a legally binding local plan but requires the municipality to complete the administrative change by issuing a street maintenance decision and updating the land register. There is no time frame specified in the legislation for completing this whole process, and on the other hand, there is no definition of long-distance traffic in the legislation. This study examines the current legislation and its functionality from the perspective of both municipalities and economic development, transport and environmental centres, as well as what kind of changes could possibly be made to the legislation to clarify the interface between roads and streets. The study also examines how street zoning, street maintenance decisions and real estate transactions could be promoted even in situations where the municipality does not have its own need to designate a road area as a street and make an administrative decision on the matter. In addition to these themes, the operational areas of the Pirkanmaa and Uusimaa ELY Centres are compared to see how the needs for changes regarding the administrative category are manifested. The methods used in the study are legal theory and interview research. During the study, the current legislation was studied, and in addition already repealed legislation was also studied, the effects of which are still partly visible in the valid local plans. At the time of writing the master's thesis, the legislation is partly in a state of transition, as the Land Use and Building Act, which has been in force since 2000, is changing and being divided into several new different acts, which may also have effects on the interface between roads and streets in the future. The interview study was conducted as semi-structured interviews, in which representatives of both the municipalities and the Pirkanmaa ELY Centre were interviewed. As a result of the study, it was found that the possibilities for changes to the legislation are ultimately quite limited, and the main means of coordinating the views of the ELY Centre and the municipalities is primarily cooperation between the authorities. - Integrating cotemporally acquired multibeam echosounder and mobile LiDAR data
School of Engineering | Master's thesis(2024-12-24) Häkkilä, HeikkiThis study explores the integration of cotemporally acquired 3D point cloud data from multibeam echosounder and mobile laser scanning systems. As both are kinematic mapping techniques, also the key concepts of satellite positioning and inertial navigation were reviewed in the literature view. For the empirical part, Riegl VMQ-1 mobile laser scanner and Teledyne SeaBat T20-P multibeam echosounder were mounted on the survey vessel. The data was collected cotemporally in the Southwest coast of Finland. The first phase was the orientation calibration of the SeaBat T20-P multibeam echosounder. The system was calibrated using a sonar patch test at a designated site, yielding orientation offsets of -0.14° for roll, +0.20° for pitch, and +0.25° for yaw. After the calibration, the height position of the sonar data was compared to the reference surveys made at the site. Sub 4 cm accuracy for the height component was achieved in relation to the reference measurements. While the integration process of sensor data produced promising results, the external accuracy analysis of the mobile laser scanning point cloud showed relatively large and consistent error compared to the reference points. The RMSE of the error residuals for XY and Z components were over 5 cm. Much lower standard deviation values (1.11 cm for XY and 1.30 cm for Z) indicated that the internal accuracy of the point cloud was superior to the external one. Examining the mutual alignment of the multibeam echosounder and mobile laser scanning data turned out to be challenging, as there was roughly 1 m vertical gap between the point clouds and not many suitable objects with well recognizable above ground and submerged parts. Based on the visual inspections and manual measurements taken from the point clouds, the multibeam echosounder and mobile laser scanning point clouds were aligned with an accuracy of under 5 cm. - Supporting inclusion experience in participatory budgeting: Case Vantaa
School of Engineering | Master's thesis(2024-12-18) Taira, KazuichiroAdaptations of participatory budgeting (PB) are place-based conditions since regulation and promotion for the deployment of PB can happen in any layer of governance, from municipality to national in the theories. Often, cases of PB adaptation in the EU happen on a municipal scale. Development of PB is moving forward on the online platform while it seems to be hybrid methods (online and offline) of participation, to keep attracting potential participants and hold an open space for discussions across government representatives, interest groups, private entities, and ordinary individuals. Finnish major cities have been piloting PB in different ways (targeting specific districts, themes, social group, or city-wide scale of PB). The city of Vantaa has paid attention to PB and deployed small pilot PB projects in seven districts, which are seen as clusters of socio-economically vulnerable residents. The city has tended to use PB as a part of community engagement and development tools to exchange ideas and opinions within those districts. The aim of the thesis was to investigate the current challenges associated with online and offline participation methods with experience of social inclusion aspects also cross-examine the overall of PB (generation to deployment also one cycle of PB process) to provide recommendations for solving these challenges, then materializing the connection between PB and relevant frameworks at the city. This was conducted by using findings from relevant study fields, published documents, three surveys, and information collected from 15 interviewees. As the research on PB is transdisciplinary and discuss divers aspects, this these establish linkage between PB development from global to Finnish contexts, focused on social inclusion and online and offline meetings. The research on the PB has been approached in divers academic domaines. In this thesis, literature review of the theme focused political science, management science, urban planning, and technology. Ambiguity of PB in the academic field must be noted here. So that, the baseline of monitoring or evaluation of PB must be place-based and context specific. Thus, the methods used in this thesis are surveys and interviews. Three series of survey data were shown collective residents perspectives in the general aspects of the city’s affair which included the PB projects. The main survey analysis was conducted based on the Experience of Social Inclusion Scales (ESIS). Internal and external interviews, in which individuals who have being facilitator of PB and have being resident of Vantaa. Mapping relations between PB and relevant documents, as well as result of internal interview established the importance of coordination in the strategic use of PB. The result latest general ESIS mean scores showed 79.6 and the mean score has been gradually in growing trend from 2020. In the latest survey with an analysis of the ESIS mean score by socio-demographics, which pointed out that survey respondents in youngest age groups and negative healthconditions shown their ESIS mean scores lower than the general ESIS mean score. ESIS mean scores from respondetns with foreign backgrounds by mother tongue and birthplace, which shown slightly higher ESIS mean score than the general ESIS mean. But, the survey respondents with foreign background were less represented in collection of survey to general populations. Thus, external interviews result shown the potential challenges in language barrier in onsite meetings. This described the need of affirmative use of alternative PB central body as existing civic council (influencing bodies) to promote social inclusion, also quality participation and increase of participants, when the PB in Vantaa further considered to deploy in the future. - Kulkumuotovalinnan ja koetun terveyden välinen yhteys Espoossa
School of Engineering | Master's thesis(2024-12-23) Hurme, NeaThis thesis tries to find connections between modal choice and perceived health in Espoo, Finland. Characteristics that are being observed in this thesis are sociodemographics, modal choice and destination trips in month, respondents’ valuation about how they perceive their own health, and reasons behind modal choice. The purpose of the thesis is to study with these characteristics does people who private drive more perceive their health worse than people who use more active transport modes. Connections between perceived health and modal choice are studied with statistical analysis tools and as a material-oriented qualitative content analysis in this thesis. The findings of this thesis show that higher income level refers to better perceived health. Modal choice did not seem to have connection to perceived health, which means that driving wasn’t associated with compromised perceived health, and neither was walking or cycling associated with better perceived health. People who perceive their health as compromised made even more trips by walking than people who perceived to have better health. From qualitative content analysis, the findings show that people who perceived their health worse chose their mode more often due to its’ speed than people who perceived their health better, when people who perceived their health better chose the mode more often due to its’ necessity. The lack of public transportation emerged from the justifications. No significant differences were found in modal choice and their justifications between the two studied groups, from which could have been drawn the connections between modal choice and perceived health. - Internal versus external management and operational efficiency of REITs
School of Engineering | Master's thesis(2024-12-24) Paloranta, JuliusA real estate investment trust (REIT) is a company that owns, operates, or finances income-producing real estate and follows specific regulatory requirements. For investors, REITs offer a convenient way to invest in professionally managed property portfolios without directly owning the properties. This study examines how the management structure of day-to-day operations (internal versus external) affects the operational efficiency of REITs and how op-erational efficiency can be measured. The study is conducted using panel data regression, and the data sample includes data from 89 U.S. Equity REITs, of which 15 are externally managed and 85 are internally managed. The data is collected for the years 2016-2023. The operational efficiency is measured as a ratio calculated by dividing total operating expenses by total revenues. As a result, the study finds that internally managed REITs are operationally more efficient than externally managed REITs. The difference is likely because internally managed REITs have more incentives to reduce costs, more knowledge about the properties, and a better understanding of how to maintain higher occupancy rates and thus increase revenues. However, the result is marginally significant, suggesting that further research is needed to confirm the results. - Classification and change detection of urban areas based on airborne laser scanning data
School of Engineering | Master's thesis(2024-12-18) Ikonen, LauraThe City of Helsinki procures yearly dense airborne laser scanning point cloud data of its neighbourhoods. This data is important in the upkeep of the three-dimensional city model, and monitoring of the urban landscape. The urban landscape changes quickly even in the span of a year, hence being able to detect larger changes is necessary for city planning. Additionally, the point cloud is part of the open data that the city provides for the public. Therefore, classification of the point cloud at an adequate level of accuracy is important and necessary. The current classification method is semi-automatic requiring significant manual correction, hence finding alternative methods for more automatised approaches would be beneficial. This thesis aims to provide an automatic classification procedure that utilises a random forest classifier in addition to comparing two methods of change detection, geometry-based and object-based. The trained classifier claims to have an overall accuracy of 0.96 and the trees and buildings have F1-scores of 0.98 and 0.96, respectively. The high accuracy values are contrasted by the visual results. The visual results show that the classifier can recall trees and buildings well, however, false positives decrease the reliability of the model. Trees and cars are mistakenly classified as buildings, and cranes, poles and building corners are segmented as trees. Hence, while the process is automatic, further manual correction is required to ensure adequate quality of results. The change detection methods are found to be contrasting. The geometry-based approach is faster since it can process raw point cloud data and can provide a decent overview of the larger changes. It cannot provide information on what has caused the change, unlike the object-based approach which provides labelled information of each change. However, the accuracy of the object-based approach is heavily tied to the accuracy of the classification; a poor classification will result in poor change detection results. - Chance-constraint optimization of district heating operation based on a long-term short-term neural network
School of Engineering | Master's thesis(2024-12-13) Toivanen, LinneaAlthough recognized as a key factor in reducing emissions of the heating sector, many district heating systems globally are still dependent on fossil fuels. The future of district heating relies on their decarbonization to maintain it a competitive technology in alignment with climate regulations. The use of renewable energy sources, such as biomass, along with electrification, will inevitably continue to grow in the sector. Their intermittent nature makes future district heating systems highly reliable on flexibility strategies to stabilize operational costs. These include energy storages, demand side management from load forecasting, and optimization. The listed technologies were studied in the field of district heating. Previous studies have highlighted the advantages of artificial intelligence, particularly its subset neural networks, in district heating load forecasting. A forecasting model with a long-term short-term architecture was chosen and trained for this study. To account for uncertainties, a chance-constrained programming model was selected for the optimization. As a result, the model gave hourly district heating load forecast values and an optimized power plant schedule for a forecasting horizon of seven days. The neural network model showcased good performance in capturing complex, non-linear relationships between district heating load and influencing parameters with a mean absolute percentage error of approximately 6 %. The integration of the model with chance-constrained programming allowed for an optimized dispatch of energy sources, minimizing both operational costs and reliance on fossil fuels while accommodating the inherent uncertainties in load forecasting. Utilizing renewable electricity significantly decreased operational costs, which urges for further electrification of district heating systems, and smart scheduling given by the optimization model encourages exploitation of advanced technologies. The error in the load forecast was dependent on weather forecasting errors, hence focus on improving the latter is essential. Next steps include experimenting with ensemble techniques, building an electricity price forecasting model, and exploring network-wide impacts of incorporating flexibility strategies in district heating. - Recent stress situations on the Finnish electricity market
School of Engineering | Master's thesis(2024-12-18) Malmipuro, IlonaIncreasing share of variable renewable energy requires flexibility in the power system, such as balancing power generation, and contributes to increased electricity price volatility, which has already been experienced on the Finnish electricity market during the past few years. After the war broke out in Ukraine in 2022, the unfolding European energy crisis raised concerns on the security of supply of energy and electricity. Energy prices and especially the price of natural gas skyrocketed during the crisis, leading to a consequent rise in electricity prices. High prices raised further concerns about affordability of electricity for businesses and private consumers. This data and literature review explores the European energy crisis in 2022 and its impacts on European and Finnish electricity and natural gas markets. The paper investigates two unprecedented stress situations on the Finnish electricity market: a market failure in November 2023 and a particularly tight power supply situation on the first week of 2024. The situations share exceptional extreme price peaks, which resulted in a notable change between actual and forecasted electricity demand in Finland. The situations were analysed by investigating the impacts of different temperature and wind conditions and available transmission capacity on power sufficiency based on reports, news articles, and power system and electricity market data. The paper also studied the role of day-ahead and intraday electricity markets in balancing the power system and estimated the impacts of the extreme prices on private consumers' electricity bills. The main observations were that the amount of demand response in both situations was approximately 1000 MW, contributing to roughly 10 % of hourly domestic electricity production, when the share of private consumers' spot-priced electricity contracts was 30 %. Therefore, demand response could have a significant role in balancing the power system in future peak load situations. Cold weather, low wind and unforeseen disruptions in power generation or transmission capacities were noticed to be the most essential factors impacting power sufficiency in these situations. Electricity imports from Estonia were also discovered to be important particularly on the first week of 2024. The role of intraday market was significant especially in the market failure situation, and its role might become more relevant when generation and demand increases in the future. - Sähkönjakeluverkon kehittämistarpeet
School of Engineering | Master's thesis(2024-12-30) Kilponen, MiikkaThe energy system is undergoing a major transformation, while energy production is shifting away from fossil fuels. In Finland, this change affects both electricity and heat production. This study examines the development needs of the electricity distribution network due to the energy transition. The research was conducted through a literature review and expert interviews. The results of the study show a significant gap between the investment capacity of electricity distribution companies and the national investment needs. Currently, distribution network companies are able to invest much less than the national investment requirements. The significantly lower investment capacity is expected to delay the implementation of clean transition projects, especially ones that would require increasing the capacity of the electricity distribution network. - Asukasosallisuuden vaikutukset lähiluonnon säilyttämisen näkökulmasta
School of Engineering | Master's thesis(2024-12-30) Härkönen, AntonThis master’s thesis focuses on examining the impact of participatory planning from the perspective of preservation of urban forests or nature. This thesis is a case study that explores the participatory processes in the local detailed planning of Laajasalo, Helsinki. The aim was to research how the residents have perceived the participatory planning processes, what kind of impact their nature views have had on the local detailed plans and what kind of issues or development needs can be identified in the current participatory processes. The thesis was conducted as qualitative research, and it included semi-structured interviews as well as document analysis as the primary methods. The data consisted of interviews of four resident activists, interview of a city planner involved in local detailed planning and participation reports from three different detailed plans in Laajasalo. The analysis was performed using ATLAS.ti. Based on the interviews and what was found in the participation reports, the residents of Laajasalo are dissatisfied with the participation processes. They feel that they are not genuinely heard, nor do their opinions matter. The impact of participatory planning on the preservation of urban forests is perceived as non-existent. Several issues and development needs can be identified in the participatory processes. The impact of the urban nature views of residents have been either insignificant or non-existent. For residents, it’s important to see their views concretely impacting the plan. Additionally, the information provided by planners should be comprehensible for non-experts and the process should be transparent. Participation should happen in the earliest stage possible, and the knowledge of residents should be in-cluded in planning more efficiently. - Solutions and design of a low-carbon tramway superstructure in Helsinki region
School of Engineering | Master's thesis(2024-12-20) Eilola, EllaOne way to reduce mobility-based emissions is efficient rail transit. Lately, tramway has regained its popularity as a part of public transport systems: traditional tram lines have been reconstructed and new, particularly the fast and efficient light rail lines, have been opened both in Europe and North America. This development is topical also in Finland, especially in the Helsinki region, but in other growing cities as well. The City of Helsinki has set a goal of being carbon neutral by 2030, and the Metropolitan Area Transport Ltd, which is responsible for the tramway infrastructure in Helsinki, is committed to the same goal. The new tramway infrastructure supports sustainable mobility, but its construction and maintenance causes emissions, the reduction of which is important in attaining the carbon neutrality goals. In this master’s thesis, measures to reduce the carbon footprint of tramway superstructure were studied. The superstructure includes major emission sources, such as rails, track slab and sleepers. In the design of the structure, significant decisions are made regarding the structure and the materials used. A large part of the life cycle emissions of tramway infrastructure arises during the construction stage and especially from the use of materials, which is why material efficiency is an essential part of reducing the carbon footprint of the track. The material consumption can be reduced both during the construction stage and later in the use stage by increasing the service life of the track parts. Design has a significant role in both cases. Low-carbon solutions for tramway superstructure were studied using expert interviews. After the individual interviews, the results were evaluated in a group interview, in which experts commented and complemented the solutions. The main solutions identified were structure optimisation, choice of the surface material, extending the service life of the rails and turnouts, low-carbon materials and products and material-efficient repairability. The earlier the low-carbon target is part of the tramway project, the more can be done to achieve it. Many of the solutions that reduce the amount of material and extend the service life of the track are made during the design stage. Developing and optimising the solutions require time and resources, but in the best case, the costs and the carbon footprint are reduced and more functional infrastructure is created simultaneously. - Maalämpölämpöjärjestelmien kytkentöjen elinkaarikustannusten vertailu uusissa asuinkerrostaloissa
School of Engineering | Master's thesis(2024-12-04) Juvonen, JussiThe objective of this study was to identify a recommended system configuration and dimensioning in three different geothermal heating systems, and to examine how consumption of domestic hot water affects the recommendation and dimensioning. The study analyzed the life cycle costs and energy efficiency of the configurations in two residential apartment buildings with varying hot water consumptions. The research was conducted as a simulation study using parametric analysis. Two of the geothermal configurations analyzed are typically used in Finland (configurations 1 and 2), and the third was a novel type developed by Hepacon Oy without a diverting valve (configuration 3). In the first building, the recommended sizing for the heat pumps ranged between 80…100 kW for all configurations. The proportion of domestic hot water usage in the heating energy consumption varied from 26…37 %. The life cycle costs associated with the heating systems for configurations 1, 2, and 3 averaged at 143 €/m², 130 €/m², and 127 €/m², respectively, with average E-values of 77, 73, and 72. In the second building, the recommended sizing ranged between 55…80 kW. The share of domestic hot water in heating energy consumption varied between 39…59 %. The life cycle costs for configurations 1, 2, and 3 averaged 92 €/m², 83 €/m² and 80 €/m², respectively, with average E-values of 71, 66, and 65. The differences between configurations 2 and 3 were not significant, but as the consumption of hot water increased, the advantage of configuration 3 became more pronounced. Configurations such as configuration 1 with only one heat pump should be avoided in residential apartment buildings. In addition to life cycle costs, simple payback periods were calculated for the geothermal heating systems compared to district heating at Helsinki's price levels. Payback periods varied between 9,1…17,1 years depending on the configuration and domestic hot water consumption, averaging at 11,5 years. - Deep heat energy system for shopping centers
School of Engineering | Master's thesis(2024-12-31) Soinio, TuomasThe global demand for sustainable and low-carbon energy solutions continues to rise every year, and utilization of renewable energy sources have become crucial. Finnish government has set up multiple future emission reduction targets, and a goal that Finland becomes carbon neutral by 2035. Geothermal energy, and especially deep heat energy systems, presents a promising approach for achieving energy security and environmental sustainability. Large commercial buildings, such as shopping centers, have a massive annual energy demand and many of them already are using zero-emission energy. Deep heat energy systems could be utilized in shopping centers to positively affect energy efficiency and total costs. Deep heat energy well consists of two main components, GSHP and geothermal well. GSHPs extract heat from the source side of the system and then increase or decrease the temperature of the heat energy. Geothermal well is typically constructed with either a U-tube collector or coaxial pipes. In deeper boreholes, coaxial pipes are the preferred method. The thesis objectives were to evaluate the financial impact when adding deep heat geothermal wells into a shopping center heating system. This was done by creating a simulation case of Sello shopping center and analyze the results of the simulation. Another objective was to assess the feasibility of constructing a deep heat energy system to old or new shopping centers based on the study results. The simulation created 14 scenarios for a project, which had a 20-year lifetime. Results showed that the total lifetime costs decreased when deep geothermal wells were added into the heating system. Due to the limitations of the simulation tool, a few assumptions were made to create proper results. This led to the conclusion that the financial benefits were not big enough to warrant adding geothermal energy wells into the heating system with this simulation setup. To make the geothermal wells more feasible, few concepts were presented, which can be utilized in a real-life project. Using the deep heat system for both heating and cooling would make the system more efficient and producing excess energy decreases. Another way to increase efficiency is to utilize energy storages, such as the borehole itself or a water tank storage. Finally, the concept of P2P thermal energy trading was introduced. P2P trading is a solution for the future, because it is not yet implemented anywhere. In P2P trading, a shopping center would act as a seller, thus increasing its profits. - Planering och potential för växttak i tättbebyggt område: fallet Busholmen
School of Engineering | Master's thesis(2024-12-28) Nuutinen, AnnaUrbanization and increasing density in cities have led to a reduction in traditional green spaces, creating a need for alternative solutions to maintain sustainable and livable urban environments. This study aims to investigate how green roofs can contribute to sustainable urban development in dense urban areas and their role in urban planning, with a specific focus on Jätkäsaari in Helsinki. By exploring the benefits that green roofs can bring to the urban environment and properties, the study hopes to shed light on their potential and the challenges they face in serving as a potential solution to the negative impacts of climate change in a densely built urban area. The research explores how green roofs can contribute to improving ecosystem services such as stormwater management, climate regulation, and biodiversity, as well as the role of legislation related to land use and urban planning. The study specifically focuses on the potential of densely built areas. The research is based on a combination of literature reviews and interviews with experts in urban planning, architecture, and ecology. The findings show that green roofs have significant potential to enhance the urban environment in densely built areas like Jätkäsaari. To enable their implementation, clearer planning guidelines, economic incentives, and better collaboration between stakeholders are required. Technical challenges, such as selecting vegetation suitable for Finland’s climate and ensuring long-term maintenance, must be addressed to secure sustainability. Moreover, a more integrated planning approach is needed, where green roofs become a natural part of the city’s green infrastructure and interact with other solutions, such as parks and green corridors. Experiences from Jätkäsaari demonstrate that a well-executed planning process is crucial and can serve as a model for future urban development projects. - Heat transfer in intensified synthesis reactors
School of Engineering | Master's thesis(2024-12-19) Goel, AnubhutiThis study investigates the heat transfer characteristics of various geometries—including diamond cells, TPMS (Triply Periodic Minimal Surface), and monolith structures—within a packed bed reactor. The literature review presents an overview of catalytic methanol production via CO₂ hydrogenation, emphasizing the role of structured metallic designs, such as honeycomb monoliths, foams, and Periodic Open Cellular Structures (POCS), in enhancing reactor performance. By focusing on process intensification within catalytic reactors, this study evaluates the effect of structured packed bed characteristics on heat transfer. During the experimental phase, several POCS lattice structures, primarily diamond cells and multiple TPMS geometries, were fabricated and dedicated heat transfer tests in a non-reactive setup were performed. Heat transfer was evaluated using a one-dimensional model to assess the influence of lattice structure, cell size, porosity, and wall contact on the air-side heat transfer coefficient. This study demonstrates that TPMS structures, particularly the diamond matrix, offer superior heat transfer performance compared to POCS structures and other TPMS geometries, such as the gyroid matrix. Smaller cell sizes within these structures further enhance heat transfer efficiency, making them ideal for optimizing thermal management in small-scale, distributed chemical production systems - Utilizing orthophotos for base map maintenance through building detection
School of Engineering | Master's thesis(2024-12-19) Puukko, JaakkoManaging the building inventory and keeping it up to date is a challenging task especially over large area. Orthophotos offer rich features to detect buildings such as textures, edges, corners and colours not to mention they can be enriched with other data like Lidar. Orthophotos are also georeferenced and orthorectified making precise mapping and comparison to existing map possible. The goal of the thesis was to find out whether missing buildings could be detected from orthophotos by comparing them to existing map. It was also explored how detected buildings could be determined to need updating. Study was conducted in the Helsinki area by having seven square kilometres of multichannel true orthophotos containing channels RGB + normalized digital surface model. Buildings were detected by utilizing Unet with ResNet34 as a backbone from Fastai and Pyrotch libraries. ImageNet weights were used for RGB channels. Training data was created with a script from multichannel true orthophotos that were manually labelled. The inference script was built to output predictions straight as georeferenced GeoTIFFs. A FME workspace was also built to read georeferenced pre-dictions and to compare them to existing base map. This study shows that missing buildings are possible to detect from orthophotos using deep learning methods and by modifying the output as georeferenced Geo-TIFFs. It was also found out that comparison to existing map is possible to do semi automatically by combining automatic and manual inspection. As a byproduct a pipeline to reproduce the study with different configurations was created. - Exploring spatial analysis on health and quality of life perception using participatory mapping data
School of Engineering | Master's thesis(2024-12-31) Maya, RosemarieThis master’s thesis aimed to explore the relationship between urban transport conditions and their environmental impacts on residents' perceptions of their quality of life and perceived health within individual activity spaces. The dataset was completed in 2020 as part of MyEspoo project using the Maptionnaire approach, as a part of the PPGIS (Public Participation GIS) method. A total of 1,127 respondents from Espoo and Kauniainen provided data on 13,801 marked locations (frequently visited places) across the Helsinki Metropolitan Area. These data were used for spatial modelling to assess individual activity space areas. The data about infrastructure availability and noise exposure level from urban streets were gathered from open data sources. Spearman’s Rank correlation was used to examine the relationship between explanatory and perceived variables. The results indicate that most of the respondents recorded their activity within the range of 66.12 km2. Within their individual activity spaces, most respondents have their activities with 3 -16 public transport stops per square kilometre, 23 intersections per square kilometre, and are exposed to noise in the range of 55-59 dB. The correlation between transport infrastructure availability with perceived variables is not significantly impacted. A minor increase in noise exposure can lead to different health perceptions, especially in prolonged periods. A similar pattern has been shown with the perceived quality of life towards noise exposure levels, as the noise increases, the perceived quality of life decreases. The results show the transport infrastructure may improve accessibility and connectivity, but not directly impact an individual. The noise from urban streets has a significant impact but does not immediately affect an individual's feelings about their well-being. - A machine learning framework for public transport ridership estimation using multi-source data fusion with low-cost bluetooth data
School of Engineering | Master's thesis(2024-12-31) Yung, ChrisAccurate information about demand volumes at certain locations within public transport networks is critical to making informed decision by transportation planners. Traditional manual counts to collect volumes, while accurate, are costly and labour intensive. Existing automatic passenger counting systems also face limitations in terms of cost, accuracy, or compatibility. This paper proposes a multi-source data fusion framework to improve the ca-pability of passenger counting using a low-cost Bluetooth sensor. The frameworks combine otherwise independent and unrelated raw Bluetooth counts, novel drone data and freely available General Transit Feed Specification - Real-Time and ferry schedule data into a unified and comparable format. The proposed framework leverages the advance capabilities of various machine learning models, K-Nearest Neighbour, XGBoost and Random Forest to estimate ridership of public transport vehicles in an area affected by nearby ferry operations. The results demonstrate the models generated using the framework achieve high accuracy and low errors when compared to the ground truth of manual counts. Machine learning model vastly outperform standard Linear Regression model with a R2 value of 0.86 compared to 0.62. Models incorporating variables develop from the framework significantly outperform those that rely solely on Bluetooth data (R2 of 0.86 vs -0.49). Notably, the framework is still able to draw similar conclusion when utilizing the drone counts as the ground truth which expose the model with significantly more data points then manual counts. However, discrepancy between manual count and drone count highlight the need for further validation to enhance the reliability of this approach. Nevertheless, the framework highlights the value of multi-sensor data fusion as a necessary enhancement to improve the utility and accuracy of the low-cost Bluetooth count. - Asset management of gravel roads: Mobile mapping and data science approach
School of Engineering | Master's thesis(2024-12-30) Zhao, WenchanGravel roads play a vital role in maintaining connectivity and supporting economic activities, particularly in rural areas. However, the assessment and maintenance of these roads face challenges due to their vulnerability to environmental conditions, such as erosion, rutting, and seasonal changes. Traditional manual inspections, commonly used for gravel road management, are labour-intensive, costly, and prone to errors, particularly when handling large-scale networks. Additionally, existing research in road geometry analysis often focuses on paved roads, leaving gravel roads underexplored. This creates a critical gap in developing automated, efficient, and reliable methods for detecting geometric anomalies specific to gravel roads, which are essential for ensuring road safety and serviceability. This thesis proposes an innovative approach to address this gap by integrating advanced mobile mapping techniques with data science algorithms. Using a laser scanning system, high-resolution road profile data were collected across 39,301 meters of gravel roads in Finland. The algorithm employs B-spline interpolation to reduce noise and smooth the road profiles, with gradient estimation and additional numerical tricks to detect key anomalies such as intersections, road widening, and structural features like bridges. Independent analysis of the left and right sides of the road enhances the algorithm’s ability to handle asymmetric features, while convolution-based smoothing ensures resilience to noise and irregularities in the dataset. The methodology was designed to address the limitations of traditional approaches by offering an automated and adaptive solution. The results demonstrate the robustness of the algorithm, with accurate detection of intersections, road widening, and bridges. This research addresses the limitations of traditional manual inspections by offering an automated, scalable solution. The findings contribute to proactive gravel road management strategies, aligning with Finland’s National Transport System Plan (2021–2032) to enhance road maintenance efficiency and sustainability. Future research will focus on improving label accuracy, addressing complex scenarios such as overlapping anomalies, and expanding the dataset to include varied geographic conditions, making this approach adaptable to broader global applications. - Experimental validation of machine learning- based predictive control algorithms for HVAC systems
School of Engineering | Master's thesis(2025-01-01) Ather, AfzaalThe significance of HVAC systems for buildings is immense as they consume a high portion of energy. This calls for the search optimized and energy-efficient solutions for the HVAC systems for a reduction in energy demand. Integration of Federated learning techniques with a machine learning (ML) predictive model is considered a novel solution that not only provides innovative solutions but also has the potential to improve the operational performance of HVAC systems. The experimental setup location of this thesis is at a university building at Aalto University. Three air handling units (AHUs) were selected to be considered as a part of the research. The values for building parameters and operational setpoints were shared using a building management system (BMS) network. This data was used to train the ML model on local datasets, creating an empirical graph network based on similarities between nodes to predict the supply air temperature parameter for adjusting the operational control of the AHUs. This will affect the overall energy requirement of the HVAC system of the building. The integration of an ML predictive model with real operative HVAC systems can provide us with real-time data, which can be communicated and monitored using a BACnet protocol network control (YABE) internet explorer was here used to access the BACnet protocol server through IT controllers. An IDA ICE simulation model was then developed and validated by using similar data for training the model to analyze the effect of predictive model control after integration with the HVAC system and perform an according energy use analysis.