Fraud is a common crime within the insurance industry, and insurance companies want to quickly identify fraudulent claimants as they often result in higher premiums for honest customers. Due to the digital transformation where the sheer volume and complexity of available data has grown, manual fraud detection is no longer suitable. This work aims to automate the detection of fraudulent claimants and gain practical insights into fraudulent behavior using unsupervised anomaly detection, which, compared to supervised methods, allows for a more cost-efficient and practical application in the insurance industry. To obtain interpretable results and benefit from the temporal dependencies in human behavior, we propose two variations of LSTM based autoencoders to classify sequences of insurance claims. Autoencoders can provide feature importances that give insight into the models' predictions, which is essential when models are put to practice. This approach relies on the assumption that outliers in the data are fraudulent. The models were trained and evaluated on a dataset we engineered using data from a Swedish insurance company, where the few labeled frauds that existed were solely used for validation and testing. Experimental results show state-of-the-art performance, and further evaluation shows that the combination of autoencoders and LSTMs are efficient but have similar performance to the employed baselines. This thesis provides an entry point for interested practitioners to learn key aspects of anomaly detection within fraud detection by thoroughly discussing the subject at hand and the details of our work. / <p>Gjordes digitalt via Zoom. </p>

No description available.

Inom sociologins, miljöpsykologins och kulturgeografins verksamhetsområde undersöks det bland annat hur människan påverkas av den byggda miljön. Det är därför väsentligt att undersöka hur människor förhåller sig till den byggda miljön och framför allt till byggnader genom att lyfta fram strukturer som kan användas i arbetet för jämställdhet. Ett sätt att bidra positivt i jämställdhetsintegrering vid byggnadsutformning är att lyfta fram genusperspektivet i samtliga processer vid ett byggnads- utformningsprojekt. För att lyckas med att utforma genusanpassade byggnader som tar hänsyn till brukarens olika behov, är tillgång till könsuppdelade data en förutsättning för att utformning av byggnader ska ske på ett jämställt sätt. Idag finns det brist på genusuppdelade data i många områden vilket leder till konsekvenser av olika grader.  Studien syftar till att bidra med ökad förståelse om hur brist på könsuppdelade data leder till byggnadsutformningar som inte är lämpliga för brukaren med olika kön. Målet är därmed att identifiera vilka utrymmen samt vilka byggnadsdelar i en byggnad som kan tänkas vara genuskritiska och beroende av könsuppdelade data. Ett annat syfte med arbetet är att undersöka hur bör data samlas in och användas för att byggnader utformas på ett sätt som passar bra för båda könen.  Studien baseras på en litteraturstudie samt en intervjustudie. Intervjustudien utgörs av fyra perspektiv varav en arkitekt, en politiker, en SIS:s projektledare inom bostadsutformning samt två byggherrar. Intervjuerna syftade till att undersöka hur ovannämnda aktörer förhåller sig till genusperspektivet inom byggnadsutformning och vilka utrymmen och delar i byggnader kan vara viktiga gällande genus- perspektivet, samt vad de ser för utmaningar och möjligheter med att samla in och använda köns- uppdelade data vid utformning av byggnader. Litteraturstudien utfördes delvis för att få en förståelse för ämnet samt för att kunna jämföra information från intervjustudien med resultatet från litteraturen.  Resultatet från studien visar att det är brukarens behov i form av genusuppdelade data som avgör hur en jämställd byggnad ska se ut. Litteraturstudien visade att trots byggnadsplanerarnas försök till en genusanpassad byggnadsutformning och implementering, kan upplevelse och användning av byggnader skiljas mellan män och kvinnor. Analysen av intervjustudien och dess jämförelse med litteraturstudien visade att byggnadsdelar så som kök, hygienrum, sovrum, gemensamma ytor samt toaletter på offentliga platser kan tänkas vara könskritiska utrymmen i en byggnad. Detta för att antropometriska mått hos män och kvinnor ökades något efter flera decennier då måttsättning av flesta byggnadsdelar är baserad på antropometriska studien som utfördes i slutet av 1960-talet. Dessutom biologiska förutsättningar så som graviditet, förlossning, klimakteriet, menstruation och så vidare ger upphov till att kvinnor har andra behov när det gäller användning av olika utrymmen och byggnadsdelar och därmed är de i behov av mer bättre anpassad utformning än dagens byggnadsutformning. En annan faktor som gör byggnadsdelar könskänsliga är styrkor hos olika kön. Analysen visade att faktorer så som köksinredning, fönstersättning, balkongens säkerhet, dörröppning, ljudisolering av sovrumsväggar samt termiska komforten kan leda till byggnadsfunktioner som kan ha könsspecifika betydelse.  Resultatet visar att det är centralt att man använder sig av data som är könsuppdelad och fri från partiskhet för att kunna uppnå byggnadsutformning som passar bra för båda könen. För att uppnå detta är det viktigt att det ska finnas konkreta byggregler som tar hänsyn till genusperspektivet, att aktörer har kommunikation och samråd genom en genomförandestrategi och processordning, att involvera brukaren i projektet vid ett tidigt skede samt att det finns en maktbalans mellan manliga och kvinnliga aktörer där jämnt antal män och kvinnor har beslutfattande och ledande roller, vilka ska ha relevanta kompetens och kunskap om genus- och jämställdhetsfrågor. Det är viktigt att ta fram ett verktyg som man kan kontrollera genuskvalitéerna på ett mätbart sätt eller i form av en checklista.  Forskningsområdet som har belysts i denna studie är under utveckling och kompletterande forskning är nödvändigt. Förslagsvis skulle fortsatta studier kunna undersöka om det finns skillnader på män och kvinnor med samma funktionsnedsättning vid användning av olika byggnadsdelar. Ett annat förslag skulle kunna vara att undersöka hur försäkringsbolagen och bankväsendet ser på genuskvalitéer inom en byggnadsutformning då de håller på att ta över bostadspolitiken. / In the field of sociology, environmental psychology, and cultural geography, it is investigated, among other things, how humans are affected by the built environment. It is therefore important to examine how people relate to the built environment and, especially to buildings by highlighting structures that can be used in the work for gender equality. One way to make a positive contribution to gender integration in building design is to highlight the gender perspective in all processes in a building design project. To succeed in designing buildings based on gender equality that consider the user's different needs, access to gender data is a prerequisite for the design of buildings to take place in an equal manner. Today, there is gender data gap in many areas, which leads to consequences with different degrees.  The aim of the study is to contribute to an increased understanding of how a gender data gap leads to building designs that are not suitable for the user with different genders. The goal is therefore to identify which spaces and components in a building may be gender critical and dependent on gender data and how data should be collected and used to ensure that buildings are designed in a way that is suitable for both sexes.  The study is based on a literature study and an interview study. The interview study considers the perspective of four actors which are an architect, a politician, a project manager in housing design from Swedish institute for standard and two investors. The interviews aimed to examine how the above- mentioned actors relate to the gender perspective in building design and what spaces, parts and functions in buildings can be important regarding the gender perspective and what they see as challenges and opportunities in collecting and using gender data in building design. The literature study was done to gain an understanding of the subject and to compare information from the interview study with the results from the literature.  The results from the study show that it is the user's needs in the form of gender data that determine what a gender-equal building should look like. The literature study showed that despite the building planners' attempts at a gender-adapted building design and implementation, the experience and use of buildings can be distinguished between men and women. The analysis of the interview study and its comparison with the literature study showed that spaces such as kitchens, hygiene rooms, bedrooms, common areas and toilets in public places can be considered gender-critical building components. This may be because anthropometric measurements in men and women increased slightly after several decades, as the measurement of most building components is based on the anthropometric study carried out in the late 1960s. In addition, biological conditions such as pregnancy, childbirth, menopause, menstruation and so on leads to women having different needs during using of different building components; therefore, they need different building designs than today's designs. Another factor that makes building components gender sensitive is the strengths of different genders. The analysis showed that factors such as kitchen interior design, window replacement, balcony security, door opening, sound insulation of bedroom walls and comfort temperature can lead to building functions that can have gender-specific significance.  The results show that it is pivotal to use gender data that is free from bias to achieve building designs that are suitable for both sexes. To accomplish this, it is important that there are specified building rules that consider the gender perspective; communication and consultation between actors through an implementation strategy and process order; to involve the user of the building in the project at an early stage and that there is a balance of power between men and women actors. An equal number of men and women that have decision-making and leadership roles, who must have relevant skills and knowledge of gender and equality issues are important factors for achieving gender-adapted building. It is necessary to have tool that enable checking the gender qualities in a measurable way or in the form of a checklist.  The research area in this study is under development and additional research is needed. For example, further studies could investigate whether there are differences between men and women with the same disability when using different building components or how insurance companies and the banking system view gender qualities in a building design when they are taking over housing policy.

Indiana University-Purdue University Indianapolis (IUPUI) / This thesis proposes an artificial neural network (NN) model to predict fuel consumption in heavy vehicles. The model uses predictors derived from vehicle speed, mass, and road grade. These variables are readily available from telematics devices that are becoming an integral part of connected vehicles. The model predictors are aggregated over a fixed distance traveled (i.e., window) instead of fixed time interval. It was found that 1km windows is most appropriate for the vocations studied in this thesis. Two vocations were studied, refuse and delivery trucks. The proposed NN model was compared to two traditional models. The first is a parametric model similar to one found in the literature. The second is a linear regression model that uses the same features developed for the NN model. The confidence level of the models using these three methods were calculated in order to evaluate the models variances. It was found that the NN models produce lower point-wise error. However, the stability of the models are not as high as regression models. In order to improve the variance of the NN models, an ensemble based on the average of 5-fold models was created. Finally, the confidence level of each model is analyzed in order to understand how much error is expected from each model. The mean training error was used to correct the ensemble predictions for five K-Fold models. The ensemble K-fold model predictions are more reliable than the single NN and has lower confidence interval than both the parametric and regression models.

Set-pieces such as free-kicks and corners have been thoroughly examined in studies related to football analytics in recent years. However, little focus has been put on the most frequently occurring set-piece: the throw-in. This project aims to investigate how football teams can optimize their throw-in tactics in order to improve the chance of taking a successful throw-in. Two different definitions of what constitutes a successful throw-in are considered, firstly if the ball is kept in possession and secondly if a goal chance is created after the throw-in. The analysis is conducted using logistic regression, as this model comes with high interpretability, making it easier for players and coaches to gain direct insights from the results. A substantial focus is put on the investigation of the logistic regression assumptions, with the greatest emphasis being put on the linearity assumption. The results suggest that long throws directed towards the opposition’s goal are the most effective for creating goal-scoring opportunities from throw-ins taken in the attacking third of the pitch. However, if the throw-in is taken in the middle or defensive regions of the pitch, the results interestingly indicate that throwing the ball backwards leads to increased chance of scoring. When it comes to retaining the ball possession, the results suggest that throwing the ball backwards is an effective strategy regardless of the pitch position. Moreover, the project outlines how feature transformations can be used to improve the fitting of the logistic regression model. However, it turns out that the most significant improvement in accuracy of logistic regression occurs when incorporating additional relevant features into the model. In such case, the logistic regression model achieves a predictive power comparable to more advanced machine learning methods. / Fasta situationer såsom frisparkar och hörnor har varit välstuderade i studier rörande fotbollsanalys de senaste åren. Lite fokus har emellertid lagts på den vanligast förekommande fasta situationen: inkastet. Detta projekt syftar till att undersöka hur fotbollslag kan optimera sin inkasttaktik för att förbättra möjligheterna till att genomföra ett lyckat inkast. Två olika definitioner av vad som utgör ett lyckat inkast beaktas, dels om bollinnehavet behålls och dels om en målchans skapas efter inkastet. Analysen görs med logistisk regression eftersom denna modell har hög tolkningsbarhet, vilket gör det lättare för spelare och tränare att få direkta insikter från resultaten. Stort fokus läggs på undersökning av de logistiska regressionsantagandena, där störst vikt läggs på antagandet gällande linjäritet. Resultaten tyder på att långa inkast riktade mot motståndarnas mål är de mest gynnsamma för att skapa en målchans från inkast tagna i den offensiva tredjedelen av planen. Om inkastet istället tas från de mellersta eller defensiva delarna av planen tyder resultaten intressant nog på att inkast riktade bakåt leder till ökad chans till att göra mål. När det kommer till att behålla bollinnehavet visar resultaten att kast bakåt är en gynnsam strategi, oavsett var på planen inkasten tas ifrån. Vidare visar projektet hur variabeltransformationer kan användas för att förbättra modellanpassningen för logistisk regression. Det visar sig dock att den tydligaste förbättringen fås då fler relevanta variabler läggs till i modellen. I sådant fall, får logistisk regression en prediktiv förmåga som är jämförbar med mer avancerade maskininlärningsmetoder.

No description available.

En el desarrollo del presente trabajo, se plantea desde el punto de vista técnico económico la importancia de la interacción de las partículas finas presentes en el mastic para dos técnicas que se presentan como innovadoras en el mundo de reciclado (RAP) de carreteras, tratamiento de carpetas con asfalto espumado y tratamiento con emulsiones asfálticas. Esta investigación se llevó a cabo en el proyecto “Servicio de reciclado Huancayo – Yanango – puente Herrería tramo III. Conforme se avanza en la investigación, se analiza y sintetiza una extensa revisión de bibliografía sobre la aplicación de las técnicas de tratamiento de carpetas con asfalto espumado y emulsiones asfálticas, de cada una se explica su historia, uso, producción, diseño para su desarrollo. Posteriormente, se explica la metodología para tener la secuencia del proceso para ambas técnicas, identificar la población, el tamaño de la muestra y las variables. Se da pase a la descripción del proyecto, en donde se presenta su ubicación, las características esenciales, el estudio de tráfico y estudio de la condición antes del proyecto. Además, se estudia las muestras y el resultado de los ensayos de pavimentos donde se ven las calicatas, el triturado de RAP a dimensiones de suelo, cálculo del número estructural de acuerdo con la resistencia saturada, resultados técnicos con asfalto espumado, con emulsión asfáltica, discusión de la solución adoptada y comparación económica de ambas técnicas. Finalmente, las conclusiones y recomendaciones que se encontraron en la presente investigación. / In the development of this work, the importance of the interaction of the fine particles present in the mast for two techniques that are presented as innovative in the world of road recycling (RAP), treatment of folders with foamed asphalt and treatment with asphalt emulsions. This research was carried out in the project "Recycling service Huancayo - Yanango - Herrería bridge section III. As the research progresses, an extensive review of the literature on the application of folder treatment techniques with foamed asphalt and asphalt emulsions is analyzed and synthesized, each of which explains its history, use, production, and design for its development. Subsequently, the methodology is explained to have the process sequence for the techniques, to identify the population, the sample size, and the variables. The description of the project is given, where its location, the essential characteristics, the traffic study and the condition study before the project are presented. In addition, the samples and the results of the tests of pavements where the test pits are seen, the grinding of RAP to soil dimensions, calculation of the structural number according to saturated resistance, technical results with foamed asphalt, with asphalt emulsion, are studied. discussion of the adopted solution and economic comparison of both techniques. Finally, the conclusions and recommendations found in the present investigation. / Tesis

<p>  </p> <p>Available literature indicated that construction projects have been experiencing significant time overruns from their planned duration. In many cases, the primary reasons for project delays were ineffective planning and scheduling methods, poor communication and collaboration between the key stakeholders, and the construction operations and task requirements have been overlooked.</p> <p>Construction project planning and scheduling are extensively studied topics, and several techniques have been developed to solve construction project scheduling problems. Traditional production planning and scheduling techniques are based on the push planning strategy, such as linear and network scheduling techniques. In the traditional method, the project scheduler calculates activity durations and then sequences them to determine when to complete the work. These techniques and planning methods have been criticized for lacking collaboration between project workers and realistic integration of the project time, location, and other essential resources to create a reliable work schedule. Furthermore, the inability to account for site operations, tasks, and workflow leads to waste and delay. </p> <p>Consequently, Ballard and Howell (1990) proposed the last planner system, and then Ballard et al. (2000) further developed the method. In the last planner system, all key stakeholders and the project management team actively communicate and coordinate to accomplish the project’s planned milestones. The last planner system and pull planning scheduling objective is improving workflow and increasing plan reliability. However, the pull planning scheduling method has some limitations. For instance, this method cannot be used to determine the available work capacity in each working space and show how much work can be completed at a given time. In addition, the pull planning and LPS system are highly descriptive and experienced-based, relying on the decision and experiences of the site supervisors. </p> <p>Available literature concerning construction project delay also indicated that ineffective planning and scheduling, slow decision-making, and poor communication and coordination had been the top critical causes of construction project delay.</p> <p>Therefore, this research was conducted to minimize construction project time and cost overrun due to poor scheduling and production planning. The study has been conducted in two main parts. In the first part of this study, critical causes of project delay have been analyzed, and the contribution of poor planning and scheduling to construction project delays in different environments has been assessed. The relative importance index and Spearman’s coefficient techniques have been utilized to analyze the collected data.  The second section of this research work was conducted to investigate the construction scheduling reliability and production efficiency and developed the enhanced production planning and scheduling method to improve schedule reliability and production plan efficiency.  The reason for developing the enhanced production planning and scheduling method was to find the best work option to optimize work duration and efficiently plan required resources per category of the identified activities. In addition, this study has automated the scheduling input data capturing from the project BIM model by utilizing the developed visual program.</p> <p>The study finding in the first section indicated that the top ten critical causes of identified causes of project delay in specified environments were significantly different. However, Ineffective project planning and scheduling had been among the most critical causes in all three conditions. Ineffective planning and scheduling were ranked number one in developed environment conditions, second in developing countries, and fifth in high-risk environments.</p> <p>Study results in the second section have shown that the case study's executed schedule had experienced significant changes in the planned dates of individual tasks, project milestones, and resource allocation. The project schedule critical path and critical activities were changed repeatedly after each update, and the project structure work was delayed for 30 days from its initial plan, as illustrated in figures 33 to 35. Subsequently, the enhanced planning methodology has been applied in the selected case study to validate the developed method and evaluate the result of the case study. The case study implemented work plan has been compared with the enhanced planning-based developed schedule. The total duration of the enhanced planning-based method has been calculated to be 240 work days, which shows 30 days less time from implemented case study plan and 50 days from the project base plan in the construction document, as illustrated in figures 39 to 41. </p> <p>Furthermore, the production schedule sensitivity analysis has shown that the production schedule and the case study base plan tasks duration have not been significantly different since both schedules were created based on the similar size of the work crew, but in terms of the number of the planned task, the production schedule had been created based on the most suitable work option. Another advantage of the production schedule is that it is more reliable because the schedule is created for a shorter duration, not long before the project work starts, and it is created after multiple collaborations and assessment steps. In addition, the developed program in this study using Revit dynamo automated the extraction of input data from the BIM model to create the project schedule. </p> <p>In conclusion, based on the case study results, the enhanced production planning methodology and developed metrics and indices can be applied to various building construction projects to find the most suitable work option and create a reliable and resource-efficient work schedule. </p>

This thesis tackles the problem of predicting the collision risk for vehicles driving in complex traffic scenes for a few seconds into the future. The method is based on previous research using dynamic Bayesian networks to represent the state of the system. Common risk prediction methods are often categorized into three different groups depending on their abstraction level. The most complex of these are interaction-aware models which take driver interactions into account. These models often suffer from high computational complexity which is a key limitation in practical use. The model studied in this work takes interactions between drivers into account by considering driver intentions and the traffic rules in the scene. The state of the traffic scene used in the model contains the physical state of vehicles, the intentions of drivers and the expected behaviour of drivers according to the traffic rules. To allow for real-time risk assessment, an approximate inference of the state given the noisy sensor measurements is done using sequential importance resampling. Two different measures of risk are studied. The first is based on driver intentions not matching the expected maneuver, which in turn could lead to a dangerous situation. The second measure is based on a trajectory prediction step and uses the two measures time to collision (TTC) and time to critical collision probability (TTCCP). The implemented model can be applied in complex traffic scenarios with numerous participants. In this work, we focus on intersection and roundabout scenarios. The model is tested on simulated and real data from these scenarios. %Simulations of these scenarios is used to test the model. In these qualitative tests, the model was able to correctly identify collisions a few seconds before they occur and is also able to avoid false positives by detecting the vehicles that will give way. / Detta arbete behandlar problemet att förutsäga kollisionsrisken för fordon som kör i komplexa trafikscenarier för några sekunder i framtiden. Metoden är baserad på tidigare forskning där dynamiska Bayesianska nätverk används för att representera systemets tillstånd. Vanliga riskprognosmetoder kategoriseras ofta i tre olika grupper beroende på deras abstraktionsnivå. De mest komplexa av dessa är interaktionsmedvetna modeller som tar hänsyn till förarnas interaktioner. Dessa modeller lider ofta av hög beräkningskomplexitet, vilket är en svår begränsning när det kommer till praktisk användning. Modellen som studeras i detta arbete tar hänsyn till interaktioner mellan förare genom att beakta förarnas avsikter och trafikreglerna i scenen. Tillståndet i trafikscenen som används i modellen innehåller fordonets fysiska tillstånd, förarnas avsikter och förarnas förväntade beteende enligt trafikreglerna. För att möjliggöra riskbedömning i realtid görs en approximativ inferens av tillståndet givet den brusiga sensordatan med hjälp av sekventiell vägd simulering. Två olika mått på risk studeras. Det första är baserat på förarnas avsikter, närmare bestämt att ta reda på om de inte överensstämmer med den förväntade manövern, vilket då skulle kunna leda till en farlig situation. Det andra riskmåttet är baserat på ett prediktionssteg som använder sig av time to collision (TTC) och time to critical collision probability (TTCCP). Den implementerade modellen kan tillämpas i komplexa trafikscenarier med många fordon. I detta arbete fokuserar vi på scerarier i korsningar och rondeller. Modellen testas på simulerad och verklig data från dessa scenarier. I dessa kvalitativa tester kunde modellen korrekt identifiera kollisioner några få sekunder innan de inträffade. Den kunde också undvika falsklarm genom att lista ut vilka fordon som kommer att lämna företräde.

Master's thesis is devoted to the study of the relationship to the appearance of women and its relationship to the theyself. The relevance of the study of this problem is due to continuously growing number of women who are not satisfied with their physical appearance that has a significant impact on various aspects of their lives, including the attitude towards themselves and, as a consequence, the quality of life. The use of modern approaches of domestic and foreign researchers allowed us to consider concepts related to the appearance and attitude toward themselves as multidimensional constructs. Because of this were found non-obvious relationships between different components of the concepts associated with age and the nature of the activities of the studied women (women leaders and female teachers of different age groups). This result is partially clarifies the nature of the influence of the relationship to the appearance of women in their attitude toward themselves, depending on the age and professional orientation that can be used in the course of psychological work with different categories of women suffering from dysfunctional attitudes toward themselves and their appearance. / Магистерская диссертация посвящена исследованию отношения к своей внешности женщин и его взаимосвязи с самоотношением. Актуальность изучения данной проблемы обусловлена непрерывно возрастающим числом женщин, которые не удовлетворены своей телесной внешностью, что оказывает значительное влияние на различные аспекты их жизни, в том числе, на отношение к себе и, как следствие, на качество жизни. Использование современных подходов отечественных и зарубежных исследователей позволило рассмотреть понятия отношение к внешности и отношение к себе как многомерные конструкты. Благодаря этому были найдены неочевидные взаимосвязи между различными компонентами рассматриваемых понятий, обусловленные возрастом и характером деятельности исследуемых женщин (женщины-руководители и женщины-педагоги различных возрастных категорий). Полученный результат частично проясняет характер влияния отношения к своей внешности женщин на их отношение к себе в зависимости от возраста и профессиональной направленности, что может быть использовано в ходе психологической работы с женщинами различных категорий, страдающими дисфункциональным отношением к себе и своей внешности.