No description available.

Graph Neural Networks and Transformers are very powerful frameworks for learning machine learning tasks. While they were evolved separately in diverse fields, current research has revealed some similarities and links between them. This work focuses on bridging the gap between GNNs and Transformers by offering a uniform framework that highlights their similarities and distinctions. We perform positional encodings and identify key properties that make the positional encodings node embeddings. We found that the properties of expressiveness, efficiency and interpretability were achieved in the process. We saw that it is possible to use positional encodings as node embeddings, which can be used for machine learning tasks such as node classification, graph classification, and link prediction. We discuss some challenges and provide future directions.

Additive manufacturing (AM) is a process of creating objects from 3D model data by adding layers of material. AM technologies present several advantages compared to traditional manufacturing technologies, such as producing less material waste and being capable of producing parts with greater geometric complexity. However, deficiencies in the printing process due to high process uncertainty can affect the microstructural properties of a fabricated part leading to defects. In metal AM, previous studies have linked defects in parts with melt pool temperature fluctuations, with the size of the melt pool and the scan pattern being key factors associated with part defects. Thus being able to adjust certain process parameters during a part's fabrication, and knowing when to adjust these parameters, is critical to producing reliable parts. To know when to effectively adjust these parameters it is necessary to have models that can both identify when a defect has occurred and forecast the behavior of the process to identify if a defect will occur. This study focuses on the development of accurate forecasting models of the melt pool temperature distribution. Researchers at Mississippi State University have collected in-situ pyrometer data of a direct laser deposition process which captures the temperature distribution of the melt pool. The high-dimensionality and noise of the data pose unique challenges in developing accurate forecasting models. To overcome these challenges, a tensor decomposition modeling framework is developed that can actively learn and adapt to new data. The framework is evaluated on two datasets which demonstrates its ability to generate accurate forecasts and adjust to new data.

<p dir="ltr">The estimation of local irradiation conditions is a complex and crucial task with significant implications for reactor safety, operation, and spent nuclear fuel management. This study aims to investigate the feasibility of using measurements of a limited number of nuclides taken at the time of discharge to infer local irradiation conditions. Specifically, the focus is on determining the local operating power, void fraction, and burnup. These factors are required to calculate the isotopic composition of discharged reactor assemblies. Existing methods often struggle with substantial uncertainties when estimating these local conditions, leading to inaccuracies in isotopic calculations. Therefore, markedly different, this research aims to establish a relationship between local conditions and isotopic measurements, benefiting from the low uncertainty associated with experimental isotopic measurements. To achieve this goal, a two-step approach is employed. First, a mathematical inference procedure is developed to correlate the isotopic composition of discharged fuel with the local irradiation conditions. Second, given a certain prediction accuracy, efforts are made to minimize the number of isotopic measurements required at the time of discharge. To do so, this work develops an inference algorithm employing a simplified depletion model of a single pin in a BWR assembly using SCALE Polaris module. Polaris module generates the virtual measurement of 29 nuclides including actinides and fission products with assumed power and void fraction histories provided to SCALE Polaris as inputs. Employing these virtual measurements, a similarity measure metric is employed to minimize the number of nuclides to estimate irradiation conditions, and the inference method used to estimate the irradiation conditions is the ordinary least squares method.</p>

<p dir="ltr">Generating images from training samples solves the challenge of imbalanced data. It provides the necessary data to run machine learning algorithms for image classification, anomaly detection, and pattern recognition tasks. In medical settings, having imbalanced data results in higher false negatives due to a lack of positive samples. Generative Adversarial Networks (GANs) have been widely adopted for image generation. GANs allow models to train without computing intractable probability while producing high-quality images. However, evaluating GANs has been challenging for the researchers due to a need for an objective function. Most studies assess the quality of generated images and the variety of classes those images cover. Overfitting of training images, however, has received less attention from researchers. When the generated images are mere copies of the training data, GAN models will overfit and will not generalize well. This study examines the ability to detect overfitting of popular metrics: Maximum Mean Discrepancy (MMD) and Fréchet Inception Distance (FID). We investigate the metrics on two types of data: handwritten digits and chest x-ray images using Analysis of Variance (ANOVA) models.</p>

Cellular network deployment scenarios refer to how cellular networks are implementedand deployed by network operators to provide wireless connectivity to end users.These scenarios can vary based on capacity requirements, type of geographical area, populationdensity, and specific use cases. Radio Access Networks of different generations,such as 4G and 5G, may also have different deployments. Network deployment scenarioscover many aspects, but two major components are Configuration settings and PerformanceMeasures which refer to the network nodes, hardware build-up and softwaresettings, and the end user behavior and connectivity experience in the area covered by thewireless network.In this master thesis, the aim is to understand how different area types - such as Rural,Suburban, and Urban – affect the cellular network deployment in such areas. A novelframework was developed to label each node (base station) with the area type it is associatedwith. The framework utilizes spatial analytics on the dataset provided by Ericsson forthe LTE nodes working with 4G technology in combination with open-source libraries anddatasets such as GeoPy and H3 Kontur population dataset respectively, to create area typelabels. The area types are labeled based on the calculated population density served byeach node and are considered true labels based on manual sanity checks performed. A supervisedmachine learning model was used to predict the nodes based on the CM and PMdata to understand the strength of the relationship between the features and true labels.This thesis also includes analysis and insights about characteristic deployment scenariosunder different area types. The main goal of this master thesis is to utilize machinelearning to uncover the characteristic features of a variety of node groups inherent in atelecom network, which, in the long run, contributes to better service operation and optimizationof existing cellular infrastructure. Nodes (base station) are labeled in the datato be able to distinguish their associated area-type. In addition to this clustering is performedto uncover the inherent characteristic behavior groups in the data and comparethem against the output from the classification model. Lastly, the investigation was doneon the potential impact of node placements such as indoor or outdoor, on the correspondingfeatures.In conclusion, the study’s results showed us that a correlation exists between deploymentscenarios and the different areas. There are a few prevalent common denominatorsbetween the node groups such as Pathloss and NR Cell Relations that drive the classificationmodel to a better classification metric, F1 score. Clustering of CM and PM data uncoversinherent patterns in different node groups under different area types and providesinformation about characteristic features of the groups such as CM data displaying twoconfiguration setting clusters, and PM data showing three different user behavior patterns.

Amidst a world with emerging problems in workforce shortages, environmentalimpact, and energy crisis, it has become essential to increase production efficiency.Having data driven processes using artificial intelligence and machine learning canbe a step towards the solution. Nevertheless, these applications rely heavily on datascientists being able to create high quality models. Complications can arise becausethe data is normally generated in conjunction with processes outside the datascientist’s competency. Therefore, it is of great importance that the personnelworking in proximity to the data generation are instilled with some competency ofdata science. So that they can, not only communicate and aid data scientists in theirwork but, perform data analysis themselves. Combining the results from a literaturereview and discussions with experts in the field of production and data science, afive-step plan was made that engineers can follow to have a value adding impactwhen working with data scientists. The content of this paper relates to an industrialsetting, namely Scania which is where the project was performed, but in essence thismethod can be used by anyone working with high volume data. / I en värld präglad av problem kring brist på arbetskraft, miljöpåverkan, och energikrisblir det allt viktigare att öka produktionen samtidigt som man minskarresursanvändningen. Användningen av artificiell intelligens och maskininlärning kanvara ett steg mot lösningen. Dessa applikationer kräver att datavetare kan göra bramodeller, men problemet är att datagenerering ofta sker utanför en datavetareskärnkompetens. Det är således viktigt för personal som arbetar näradatagenereringen att ha vissa kunskaper inom datavetenskap, så att det inte barakan kommunicera och hjälpa datavetare, utan också själva utföra analyser. Genomatt kombinera resultatet av en litteraturstudie och intervjuer med experter inom fältetför produktion och datavetenskap har en femstegs plan gjorts som ingenjörer kananvända för att utvärdera sin data och jobba mer effektivt med datavetare. Innehålleti arbetet relaterar främst till industriella situationer, i synnerhet Scania vilket är därarbetet utgjorts, men kan i grunden användas av vem som helst som jobbar med enhög volym av data.

Machine learning has the potential of significantly improving daily operations in health care institutions but many persistent barriers are to be faced in order to ensure its wider acceptance. Among such obstacles are the accuracy and reliability. For a decision support system to be entrusted by the medical staff in clinical situations, it must perform with an accuracy comparable to or surpassing that of human medics, as well ashaving a universal applicability and not being subject to any bias. In this paper the MIMIC-IV Clinical Database will be utilized in order to: (1) Predict patient mortality and its associated risk factors in intensive care units (ICU) and: (2) Assess the reliability of utilizing the database as a basis for a clinical decision system. The cohort consisted of 523,740 hospitalizations, matched with each respective admitting diagnoses in ICD-9 format. The diagnoses were then converted from code to text-format, with the most frequently occurring factors (words) observed in deceased and surviving patients being analyzed with an Natural language Processing (NLP) algorithm. The results concluded that many of the observed risk factors were self-evident while others required further explanation, and that the performance was highly by selection of hyperparameters. Finally, the MIMIC-IV database can serve as a stable foundation for a clinical decision system but its reliability and universality shall also be taken into consideration. / Maskininlärninstekniker har en stor potential att gynna sjukvården men står inför ett flertal hinder för att fullständigt kunna tillämpas. Framförallt bör modellernas tolkningsbarhet och reproducerbarhet beaktas. För att att ett kliniskt beslutstodssystem skall vara fullständigt anförtrott av sjukvårdspersonal måste det kunna prestera med en jämförbar eller högre träffsäkerhet än sjukvårdspersonal, samt kunna tillämpas i åtskilliga sammanhang utan någon subjektivitet. Syftet med denna studie är att: (1) Förutspå patientdödsfall i intensivvårdsavdelningar och utreda dess riskfaktorer genom journalförd information från databasen MIMIC-IV och: 2) Bedöma databasens tillförlitlighet som underlag för ett kliniskt beslutstödssystem. Kohorten bestod av 523,740 insjuknanden som matchades med de diagnoser som ställdes vid deras sjukhusintag. Eftersom diagnoserna inskrevs i ICD-9-format omvandlades dessa till ord och de mest förekommande faktorerna (orden) för avlidna och överlevande patienter analyserades med en NLP-model (Natural Language Processing). Resultaten konkluderade att många av de förutspådda riskfaktorerna var uppenbara medan andra krävde ytterligare klargöranden. Dessutom kunde val av hyperparametrar stort påverka modellens kvalitet. MIMIC-IV-databasen kan utgöra ett gediget underlag för ett kliniskt beslutsystem men dess tillförlitlighet och relevans bör även tas i beaktande. / Kandidatexjobb i elektroteknik 2022, KTH, Stockholm

This cross-departmental initiative bridges Business and IT to establish a nexus for technological innovation, academic research, and tangible retail application, particularly in the realms of Robotics, Sensor Technology, Service Technology, Data Science driven by Artificial Intelligence within a retail setting. Conceived as both a living lab and an innovation hub, this project embodies a fully-operational retail store of the future, furnished with cutting-edge technologies and resourced by experts across varied disciplines and research domains. The overarching objective centers on facilitating knowledge generation and transfer among students, faculty, retailers, and technology companies. By doing so, the lab endeavors to foster collaborative solutions to aptly address the pressing challenges currently being faced by the retail industry, paving the way for sustainable, innovative developments for the future.

The companies’ support phase, as all of business’ functional areas and components, went through a heavy and rapid digitalization which has unlocked the availability of an unprecedented amount of data. Unlike other relevant business areas and components, the support phase seems to have experienced fewer improvements attributable to Data Science and machine learning. By focusing on two well-known problems of these two fields, Time Series Analysis and Regression Analysis, this project aims at understanding which techniques are applicable within the support phase and how these can improve the effectiveness and pro-activeness of this area. The goal within this project is to apply them to improve the handling of support tickets, the digital entity used to track issues and requests within support systems. Through the use of Time Series Analysis, we aim at forecasting the volume of tickets to be expected in a near-future time frame. Using Regression Analysis we intend to estimate the resolution time of a newly submitted ticket. The results produced by the two tasks were satisfactory. On one hand, the Time Series task produced accurate results and the models could be directly employed and bring some added value to help Elvenite’s support team. On the other hand, while the Regression Analysis results were not as good, they nonetheless proved that the task’s aim is achievable through improvements on both the data used and the models applied. Finally, both tasks successfully showcased how to investigate and evaluate the application of such techniques within the support phase of a business. / Supportfasen, likväl samtliga andra delar av företags affärsfunktionella områden och komponenter, har genomgått en intensiv och snabb digitalisering som har öppnat upp tillgången till en enastående mängd data. Till skillnad från andra relevanta affärsområden och komponenter verkar supportfasen ha upplevt färre förbättringar som kan attribueras till Datavetenskap och maskininlärning. Projektet syftar till att förstå det ovanstående genom att fokusera på två välkända tekniker: tidsserieanalys och regressionsanalys. Det är följaktligen viktigt att undersöka vilka metoder från föregående nämnda områden som är användbara inom supportsystemen, samt hur dessa kan förbättra effektiviteten och proaktiviteten inom området. Det genomgående målet för projektet är att tillämpa analysmetoderna för att förbättra hanteringen av supportbiljetter. Supportbiljetter är den digitala enheten som används för att spåra frågor och förfrågningar inom supportsystem. Genom att använda tidsserieanalys eftersträvas att prognostisera volymen av biljetter som kan förväntas inom en snar framtid. Regressionsanalys användas för att tillhandahålla en uppskattad tid för en nyanländ biljett att bli löst, baserat på lösningstiden för tidigare lösta liknande biljetter. De två tillvägagångssätten gav olika, men tillfredställande resultat. Till att börja med anses tidsserieanalysen vara tillfredsställande och kan vara av värde samt hjälp för Elvenites supportteam. Dessvärre var resultaten från regressionsanalysen inte lika optimala och modellerna skulle behöva förbättras ytterligare före de appliceras i verkligheten. De båda teknikerna kunde ändock framgångsrikt bevisa och påvisa hur man kan undersöka samt utvärdera liknande metoder inom supportfasen av ett företag.