Sociala medier innehåller idag massor av information som kan bidra till att ge applikationer och produkter ett stort mervärde genom att ge en förbättrad användarupplevelse. I vissa fall kan sådan information inte erhållas utan att först matcha data från en eller flera datakällor genom en data fusion.   Eniro Initiatives AB vill undersöka möjligheter för att genomföra en automatiserad data fusion genom att koppla företag från sitt API till motsvarande företag på sociala medier. Problematiken ligger i att den enda helt säkra källan till matchning av alla svenska företag är dess organisationsnummer, vilket är data som inte finns tillgänglig hos API:er från utländska företag. Syftet var att undersöka möjligheter för att på automatiserat sätt kunna matcha relaterad data från olika datakällor.   I detta examensarbete har en prototyp utvecklats som matchar företag från Eniros API med företags sidor från Facebooks API. Resultatet från tester av denna prototyp visar dock brister, då det uppkom fall där redundant information bidrog till att prototypen kunde godkänna inofficiella sidor med koppling till det relevanta företaget, vilket inte var önskvärt. / Social media today contains a lot of information that can add a great value for applications and products by achieve an improved user experience. In some cases, such information cannot be obtained without matching data from one or several data sources through a data fusion.   Eniro Initiatives AB wants to explore opportunities to implement an automated data fusion model by matching companies from its own API to the corresponding company on social media. The problem is that the only completely secured data of matching of all Swedish companies is its corporate identity, which is data that is not available with APIs that origin from foreign companies. The aim was to explore possibilities for the automated way to match related data from different data sources.   In this thesis, a prototype was developed to match companies from Eniro’s API with company pages from Facebook's API. The results from the tests of this prototype shows small deficiencies where redundant information made the prototype able to approve unofficial pages with links to the relevant company, which was not desirable.

No description available.

Simulation is an important tool for prediction and assessment of the behavior of complex systems and situations. The importance of simulation has increased tremendously during the last few decades, mainly because the rapid pace of development in the field of electronics has turned the computer from a costly and obscure piece of equipment to a cheap ubiquitous tool which is now an integral part of our daily lives. While such technological improvements make it easier to analyze well-understood deterministic systems, increase in speed and storage capacity alone are not enough when simulating situations where human beings and their behavior are an integral part of the system being studied. The problem with simulation of intelligent entities is that intelligence is still not well understood and it seems that the field of Artificial Intelligence (AI) has a long way to go before we get computers to think like humans. Behavior-based agent modeling has been proposed in mid-80's as one of the alternatives to the classical AI approach. While used mainly for the control of specialized robotic vehicles with very specific sensory capabilities and limited intelligence, we believe that a behavior-based approach to modeling generic autonomous agents in complex environments can provide promising results. To this end, we are investigating a behavior-based model for controlling groups of collaborating and competing agents in a geographic terrain. In this thesis, we are focusing on scenarios of military nature, where agents can move within the environment and adversaries can eliminate each other through use of weapons. Different aspects of agent behavior like navigation to a goal or staying in group formation, are implemented by distinct behavior modules and the final observed behavior for each agent is an emergent property of the combination of simple behaviors and their interaction with the environment. Our experiments show that while such an approach is quite efficient in terms of computational power, it has some major drawbacks. One of the problems is that reactive behavior-based navigation algorithms are not well suited for environments with complex mobility constraints where they tend to perform much worse than proper path planning. This problem represents an important research question, especially when it is considered that most of the modern military conflicts and operations occur in urban environments. One of the contributions of this thesis is a novel approach to reactive navigation where goals and terrain information are fused based on the idea of transforming a terrain with obstacles into a virtual obstacle-free terrain. Experimental results show that our approach can successfully combine the low run-time computational complexity of reactive methods with the high success rates of classical path planning. Another interesting research problem is how to deal with the unpredictable nature of emergent behavior. It is not uncommon to have situations where an outcome diverges significantly from the intended behavior of the agents due to highly complex nonlinear interactions with other agents or the environment itself. Chances of devising a formal way to predict and avoid such abnormalities are slim at best, mostly because such complex systems tend to be be chaotic in nature. Instead, we focus on detection of deviations through tracking group behavior which is a key component of the total situation awareness capability required by modern technology-oriented and network-centric warfare. We have designed a simple and efficient clustering algorithm for tracking of groups of agent suitable for both spatial and behavioral domain. We also show how to detect certain events of interest based on a temporal analysis of the evolution of discovered clusters.

In a dynamically monitored environment the analyst team need timely and accurate information to conduct proactive action over complex situations. Typically, there are thousands of reported activities in a real time operation, therefore steps are taken to direct the analyst’s attention to the most important activity. The data fusion community have introduced the information fusion model, with multiple situational assessments. Each process lends itself to ranking the most important activities into a predetermined order. Unfortunately, the capability of a real time system can be hindered by the knowledge limitation problem, particularly when the underlying system is processing multiple sensor information. Consequently, the situational awareness domains may not rank the identified situation as perfect, as desired by the decision-making resources. This thesis presents advanced research carried out to evaluate the ranking capability of information from the situational awareness domains: perception, comprehension and projection. The Ranking Capability Score (RCS) has been designed for evaluating the prioritisation process. The enhanced (RCS) has been designed for addressing the knowledge representation problem in the user system relation under a situational assessment where the proposed number of tracking activities are dynamically shifted. Finally, the Scheduling Capability Score was designed for evaluating the scheduling capability of the situational awareness system. The proposed performance metrics have been successful in fulfilling their objectives. Furthermore, they have been validated and evaluated using an analytical approach, through conducting a rigorous analysis of the prioritisation and scheduling processes, despite any constraints related to a domain-specific configuration.

In this thesis, an extension of the existing localization system of the ABSOLUT project is presented, with the aim of making it more resistant to GNSS errors. This enhanced system is based on the integration of a LiDAR sensor. Initially, a 3D map of the traversed route is created using the LiDAR sensor. This process employs an existing factor graph-based SLAM algorithm, which is made more stable and accurate through the inclusion of a surveyed elevation profile of the environment, the integration of vehicle odometry sensors, and bias estimates of the IMU. The generated map is used during the drive to determine the vehicle's position by comparing it with the currently captured point clouds. This procedure relies on a newly developed Error-State Kalman Filter that fuses LiDAR odometry with absolute LiDAR position estimates. To optimally use the pose estimation from the various sensor systems, an approach is proposed that adaptively combines the estimates based on the environment. The performance of the developed system is evaluated using real driving data.

No description available.

No description available.

No description available.

Axlebox bearings are one of the most critical components of a rail vehicle with regard to safety. An axlebox bearing that breaks during operation can be dangerous for the passengers and expensive for the operator. In-service failure of axlebox bearings has been the cause of many catastrophic accidents. Thus, it is of utmost importance to predict bearing failures as early as possible. This will increase reliability and safety of the vehicle as well as reduce the vehicle maintenance cost. Monitoring of roller bearings is an active research eld, and many methods have been proposed by other researchers. Many of these methods employ complex algorithms to make the most use of the given measurements. The algorithms often lack interpretability and have high computational costs, making them dicult to employ in an on-board system. This thesis proposes an interpretable and transparent algorithm that predicts bearing damages with high accuracy. Meanwhile, it tries to retain interpretability as much as possible. The algorithm is based on Empirical Mode Decomposition (EMD) and Singular Value Decomposition (SVD). These two techniques extract essential and meaningful information from the axlebox accelerations. The algorithm is benchmarked on two benchmark datasets, and the results are compared to the respective literature. Then the algorithm is employed on the railway axlebox acceleration measurements that were taken on an axlebox test bench available at SWJTU. The proposed algorithm can be extended to incorporate additional measurements of dierent types, e.g. sound or temperature measurements. The incorporation of other types of measurements will improve the performance of the algorithm even further. / Axelbox lager är en av de viktigaste komponenterna i ett järnvägsfordon när det berör säkerheten. Ett axelbox lager som havererar under drift kan vara farligt for passagerarna och även dyrt för operatören. Driftfel av lagren har varit orsaken till många katastrofala olyckor. Därför är det av yttersta vikt att förutsäga lagerfel så tidigt som möjligt. Detta ökar fordonets tillförlitlighet och säkerhet samt minskar underhållskostnaderna. Mycket forskning har utförts inom övervakning av rullager. Många metoder använder komplexa algoritmer för att maximalt utnyttja matningarna. Algoritmerna saknar ofta tolkbarhet och har höga beräkningskostnader, vilket gör dem svåra att använda i ett integrerat system. Denna avhandling kombinerar era metoder för databehandling och maskininlärning till en algoritm som kan förutsäga lagerskador med hög precision, samtidigt som tolkningsförmågan bibehalls. Bland andra välkända metoder sa använder algoritmen Empirical Mode Decomposition (EMD) och Singular Value Decomposition (SVD) för att extrahera väsentlig information for vibrationsmätningarna. Algoritmen testas sedan med tre olika vibrationsdatamängder, varav en mättes specikt med tanke på simulering av axelbox lager. Ett annat mål med algoritmen är att göra den tillämpad för ytterligare mätningar. Det bör vara möjligt att inkludera mätningar av olika slag, dvs ljud- eller temperaturmätningar, och därigenom förbättra resultaten. Detta skulle minska implementeringskostnaden avsevärt eftersom befintliga sensorer används för detta ändamål. I händelsen av att de föreslagna metoderna inte fungerar med nya mätningar är det även möjligt att integrera ytterligare funktioner i algoritmen.

Intra-dialytic hypotension (IDH) is the most common complication in haemodialysis (HD) treatment and has been linked with increased mortality in HD patients. Despite various approaches towards understanding the underlying physiological mechanisms giving rise to IDH, the causes of IDH are poorly understood. Heart Rate Variability (HRV) has previously been suggested as a predictive measure of IDH. In contrast to conventional spectral HRV measures in which the frequency bands are defined by fixed limits, a new spectral measure of HRV is introduced in which the breathing rate is used to identify and measure the physiologically-relevant peaks of the frequency spectrum. The ratio of peaks leading up to the IDH event was assessed as a possible measure for IDH prediction. Changes in the proposed measure correlate well with the magnitude of abrupt changes in blood pressure in patients with autonomic dysfunction, but there is no such correlation in patients without autonomic dysfunction. At present, routine clinical vital sign monitoring beyond simple weight and blood pressure measurements at the start and end of each session has not established itself in clinical practice. To investigate the benefits of continuous vital sign monitoring in HD patients with regard to detecting and predicting IDH, different population-based and patient-specific models of normality were devised and tested on data from an observational study at the Oxford Renal Unit in which vital signs were recorded during HD sessions. Patient-specific models of normality performed better in distinguishing between IDH and non-IDH data, primarily due to the wide range of vital sign data included as part of the training data in the population-based models. Further, a patient-specific data fusion model was constructed using Parzen windows to estimate a probability density function from the training data consisting of vital signs from IDH-free sessions. Although the model was constructed using four vital sign inputs, novelty detection was found to be primarily driven by blood pressure decreases.