This report aims to present a project in the field of unsupervised clustering on human behavior in a parking application. With increasing opportunities to collect and store data, the demands to utilize the data in meaningful ways also increase. The purpose of this work is to explore common behaviors within the app and what those reveal about its usage. Transforming event based data into user sessions was the first step. The next step was to establish how to measure the similarity between sequences. This was achieved using two different approaches. One approach based on a combination of string metrics and heuristics. The other approach creates array representations of the sessions using an autoencoder. With these two ways of representing the similarity between sessions, we utilize clustering algorithms to assign labels to all sessions. Due to the unknown attributes of the data set, the versatile clustering algorithm HDBSCAN was employed on both representations of the session separately. The clusters produced by HDBSCAN were compared to those produced by simple partitioning algorithms. The noisy nature of human behavior allowed HDBSCAN to create better clusters with distinct behaviors in comparison to the simpler partitioning algorithms. Without a ground truth to rely on, evaluating the models proved to be a difficult part of the project. We utilized both quantitative metrics, as well as qualitative methods for evaluation. In conclusion, our work provides a new way of evaluating user behavior. It brings new insights into different ways the customer achieves their goals within the app. And finally it lays ground for connecting user behavior with transaction data. / Denna rapport syftar till att presentera ett projekt inom oövervakat klustrande av mänskligt beteende i en parkeringsapplikation. Med ökande möjligheter att samla in och lagra data ökar också kraven på att använda informationen på meningsfulla sätt. Syftet med detta arbete är att undersöka vanligt förekommande beteenden inom applikationen och vad dessa avslöjar om användningen. Första steget var att omvandla händelsesbaserad data till användarsessioner. Nästa steg var att etablera hur man mäter likheten mellan sekvenser. Detta uppnåddes genom att använda två olika metoder. Första metoden var baserad på en kombination av strängmått och heuristik. Den andra metoden skapade vektorreprestation av sessionerna med hjälp av en autokodare. Med dessa två sätt att representera likheten mellan sessioner användes klustringsalgoritmer för att tilldela etiketter till alla sessioner. På grund av de okända attributen hos datasetet applicerades den mångsidiga klustringsalgoritmen HDBSCAN för båda representationer av sessionerna. Klustren som skapades från HDBSCAN jämfördes med de kluster som skapades med hjälp av enkla partitioneringsalgoritmer. Bruset som mänskligt beteende medför gjorde att HDBSCAN kunde skapa bättre kluster med tydliga beteenden jämfört med de simpla partitionsalgoritmerna. Utan en grundläggande sanning att utgå ifrån visade sig utvärderingen av modellerna vara en svår del av projektet. Vi använde både kvantitativa mätvärden och kvalitativa metoder för utvärderingen. Sammanfattningsvis resulterade vårt arbete i ett nytt sätt att utvärdera användarbeteende. Vidare skapades nya insikter kring de olika sätt som användare navigerar applikationen för att uträtta olika ärenden. Slutligen lägger arbetet grunden för att koppla samman användarbeteende med transaktionsdata i framtida projekt.

The cost of developing new drugs is high and the aim of computer-assisted drug discovery is to reduce that development cost, either through virtual screening or generating novel compounds. System biology is one approach to drug discovery where the response of a biological system is the subject of study, instead of drug target interaction. One way to observe a biological system is through microscopy images that are taken of cells perturbed with compounds. Image software extracts information called morphological profiles from the images that can be used for data hungry models. One of the ways artificial intelligence has been applied to drug discovery is with generative models that can generate new compounds. One such generative model is reinforcement learning that employs a critic to guide the generation of compounds towards desirable behaviors. In this study different machine learning models were tested if they could predict the morphological response of COVID-19 infected cells to compounds from their structure. No modells showed any promising results. The reason that no model performed well was because of the dataset. There is a lot of variance in the dataset, meaning that the response to the same compound varies. There was also a lot of difference between the compounds in the dataset, meaning that any representation that the model learns does not transfer over to other compounds. The data set was also imbalanced with more inactive compounds.

In a variance component model,(Formula presented.), Pukelsheim (1981) proved that the non-negative and unbiased estimation of the variance components σ(Formula presented.), j=1, …, c, entails a transformation of the original model to Q(Formula presented.) (called Q-reduced model). The maximum likelihood (ML) approach based on the likelihood of Q(Formula presented.) (denoted Q-ML) is considered and applied to an incomplete block design (IBD) model. The Q-ML estimators of variance components and are shown to be more efficient in the mean squared error sense than the non-negative MINQUE’s (minimum norm quadratic unbiased estimators) in the IBD. The effect of using Q-ML estimators of the variance components to estimate the variance ratio in the combined estimator of the treatment contrast is also considered.

This thesis evaluates the AMLAS methodology. To support the evaluation, literature studies are conducted and a machine learning dependent system that detects people and helmets is implemented. The practical work is performed according to the documentation of AMLAS. Alongside this work, a user interface is developed. The user interface and the machine learning component is merged to create the complete system. The results show that AMLAS contributes with safety, structure and reliability to the system. However, the findings show that AMLAS is missing some aspects. / <p>Examensarbetet är utfört vid Institutionen för teknik och naturvetenskap (ITN) vid Tekniska fakulteten, Linköpings universitet</p>

In the modern digital landscape, mobile devices serve as crucial data generators.Their usage spans from simple communication to various applications such as userbehavior analysis and intelligent applications. However, privacy concerns associatedwith data collection are persistent. Deep learning technologies, specifically Convo-lutional Neural Networks, have been increasingly integrated into mobile applicationsas a promising solution. In this study, we evaluated the performance of a CNN im-plemented on iOS smartphones using the CIFAR-10 data set, comparing the model’saccuracy and execution time before and after conversion for on-device deployment.The overarching objective was not to design the most accurate model but to inves-tigate the feasibility of deploying machine learning models on-device while retain-ing their accuracy. The results revealed that both on-cloud and on-device modelsyielded high accuracy (93.3% and 93.25%, respectively). However, a significantdifference was observed in the total execution time, with the on-device model re-quiring a considerably longer duration (45.64 seconds) than the cloud-based model(4.55 seconds). This study provides insights into the performance of deep learningmodels on iOS smartphones, aiding in understanding their practical applications andlimitations.

Automatic machine learning (AutoML) systems have been shown to perform better when they use metamodels trained offline. Existing offline metalearning approaches treat ML models as black boxes. However, modern ML models often compose multiple ML algorithms into ML pipelines. We expand previous metalearning work on estimating the performance and ranking of ML models by exploiting the metadata about which ML algorithms are used in a given pipeline. We propose a dynamically assembled neural network with the potential to model arbitrary DAG structures. We compare our proposed metamodel against reasonable baselines that exploit varying amounts of pipeline metadata, including metamodels used in existing AutoML systems. We observe that metamodels that fully exploit pipeline metadata are better estimators of pipeline performance. We also find that ranking pipelines based on dataset metafeature similarity outperforms ranking based on performance estimates.

L'apprentissage du violon classique occidental s'effectue généralement dans un contexte pédagogique contraignant où l'enseignement, centré sur le professeur (Young, Burwell et Pickup, 2003), laisse peu de latitude décisionnelle à l'élève (Persson, 1995). Intégrer des activités pédagogiques qui encouragent la latitude décisionnelle et la créativité des jeunes violonistes apparaît comme une alternative pertinente à cette problématique. L'improvisation, à qui l'on accorde de multiples bénéfices pédagogiques (Azzara, 2002) dont notamment le développement de la pensée créative (Webster, 2002), est souvent absente de l'enseignement du violon (Riveire, 1997). Cette situation est attribuable au manque de connaissances des professeurs sur le sujet et à l'absence d'outils pédagogiques adéquats (Ibid.). Dans le but de pallier à ces lacunes, notre recherche doctorale visait à mettre au point un outil pédagogique facilitant l'intégration de l'improvisation dans l'enseignement du violon au cours des trois premières années d'apprentissage. Suivant une méthodologie de recherche de développement (Van der Maren, 2003) et puisant, tant dans la littérature scientifique que dans l'expérience pratique de la chercheuse et de trois professeurs collaborateurs, cet outil a été rigoureusement conçu. Visant le développement de l'ensemble des habiletés requises pour former un jeune instrumentiste autonome et créatif, il propose une démarche s'appuyant sur le modèle de l'enseignement stratégique de Tardif (1997) et des activités pédagogiques où l'improvisation est intégrée à l'apprentissage du violon. L'outil pédagogique, présenté sous la forme d'un document écrit accompagné de deux DVDs, a été validé par la chercheuse et les trois professeurs collaborateurs auprès d'élèves correspondant à la population cible, soit des enfants âgés de 6 à 11 ans durant leurs trois premières années d'apprentissage. Les données générées par des essais in situ, des captations vidéo et des entretiens semi-dirigés ont donné lieu à une analyse qualitative dont les résultats ont permis d'optimiser le contenu et la forme de l'outil.

Internet of Things (IoT) is a revolutionary paradigm approaching both industries and consumers everyday life. It refers to a network of addressable physical objects that contain embedded sensing, communication and actuating technologies, to sense and interact with the environment where being deployed. It can be considered as a modern expression of Mark Weiser's vision of ubiquitous computing where tiny networked computers become part of everyday objects, fusing together the virtual world and the physical word. Recent advances in hardware solutions have led to the emergence of powerful wireless IoT systems that are entirely energy-autonomous. These systems extract energy from their environment and operate intermittently, only as power is available. Battery-less sensors present an opportunity for the pervasive wide-spread of remote sensor deployments that require little maintenance and have low cost. As the number of IoT endpoint grows -- industry forecast trillions of connected smart devices in the next few years -- new challenges to program, manage and maintain such a huge number of connected devices are emerging. Web technologies can significantly ease this process by providing well-known patterns and tools - like cloud computing - for developers and users. However, the existing solutions are often too heavyweight or unfeasible for highly resource-constrained IoT devices. This dissertation presents a comprehensive analysis of two of the biggest problems that the IoT is currently facing: R1) How are we going to provide connectivity to all these devices? R2) How can we improve the quality of service provided by these tiny autonomous motes that rely only on limited energy scavenged from the environment? The first contribution is the study and deployment of a Low-Power Wide-Area-Network as a feasible solution to provide connectivity to all the expected IoT devices to be deployed in the following years. The proposed technology offers a novel communication paradigm to address discrete IoT applications, like long-range (i.e., kilometers) at low-power (i.e., tens of mW). Moreover, results highlight the effectiveness of the technology also in the industrial environment thanks to the high immunity to external noises. In the second contribution, we focus on smart metering presenting the design of three smart energy meters targeted to different scenarios. The first design presents an innovative, cost-effective smart meter with embedded non-intrusive load monitoring capabilities intended for the domestic sector. This system shows an innovative approach to provide useful feedback to reduce and optimize household energy consumption. We then present a battery-free non-intrusive power meter targeted for low-cost energy monitoring applications that lower both installation cost due to the non-intrusive approach and maintenance costs associated to battery replacement. Finally, we present an energy autonomous smart sensor with load recognition capability that dynamically adapts and reconfigures its processing pipeline to the sensed energy consumption. This enables the sensor to be energy neutral, while still providing power consumption information every 5 minutes. In the third contribution, we focus on the study of low-power visual edge processing and edge machine learning for the IoT. Two different implementations are presented. The first one discusses an energy-neutral IoT device for precision agriculture, while the second one presents a battery-less long-range visual IoT system, both leveraging on deep learning algorithms to avoid unnecessary wireless data communication. We show that there is a clear benefit from implementing a first layer of data processing directly in-situ where the data is acquired, providing a higher quality of service to the implemented application.

No description available.

In networked systems engineering, operational datagathered from sensors or logs can be used to build data-drivenfunctions for performance prediction, anomaly detection, andother operational tasks [1]. Future telecom services will share acommon communication and processing infrastructure in orderto achieve cost-efficient and robust operation. A critical issuewill be to ensure service quality, whereby different serviceshave very different requirements. Thanks to recent advances incomputing and networking technologies we are able to collect andprocess measurements from networking and computing devices,in order to predict and forecast certain service qualities, such asvideo streaming or data stores. In this paper we examine thesetechniques, which are based on statistical learning methods. Inparticular we will analyze traces from testbed measurements andbuild predictive models. A detailed description of the testbed,which is localized at KTH, is given in Section II, as well as in[2]. / Inom nätverk och systemteknik samlas operativ data från sensorer eller loggar som sedan kan användas för att bygga datadrivna funktioner för förutsägelser om prestanda och andra operationella uppgifter [1]. Framtidens teletjänster kommer att dela en gemensam kommunikation och bearbetnings infrastruktur i syfte att uppnå kostnadseffektiva och robusta nätverk. Ett kritiskt problem med detta är att kunna garantera en hög servicekvalitet. Detta problem uppstår till stor del som ett resultat av att olika tjänster har olika krav. Tack vare nyliga avanceringar inom beräkning och nätverksteknologi har vi kunnat samla in användningsmätningar från nätverk och olika datorenheter för att kunna förutspå servicekvalitet för exempelvis videostreaming och lagring av data. I detta arbete undersöker vi data med hjälp av statistiska inlärningsmetoder och bygger prediktiva modeller. En mer detaljerat beskrivning av vår testbed, som är lokaliserad på KTH, finns i [2]. / Kandidatexjobb i elektroteknik 2020, KTH, Stockholm