Browsing by master's degree program "Tietojenkäsittelytieteen maisteriohjelma"

Quantum networking is developing fast as an emerging research field. Distributing entangled qubits between any two locations in a quantum network is one of the goals of quantum networking, in which repeaters can be used to extend the length of entanglement. Although researchers focus extensively on problems inside one quantum network, further study on communication between quantum networks is necessary because the next possible evolution of quantum networking is the communication between two or more autonomous quantum networks. In this thesis, we adapted a time slotted model from the literature to study the inter quantum network routing problem. Quantum routing problem can be split into path selection and request scheduling. We focus on the latter considering the previous one received considerable interest in the literature. Five request scheduling policies are proposed to study the impact of preference for certain request types on entanglement generation rate. Experiments also demonstrate other factors should be considered in context of entanglement rate in communication between quantum networks, e.g., the number and distribution of requests and inter-network distance.

The concept of big data has gained immense significance due to the constant growth of data sets. The primary challenge lies in effectively managing and extracting valuable conclusions from this ever-expanding data. To address this challenge, the need for more efficient data processing frameworks has become essential. This thesis delves deeply into the concept of big data by first introducing and defining it comprehensively. Subsequently, the thesis explores a range of widely used open-source frameworks, some of which have been in existence for a considerable period already, while others have been developed to enhance the efficiency and particular aspects further. At the beginning of the thesis, three popular frameworks—MapReduce, Apache Hadoop, and Spark—are introduced. Following this, the thesis introduces popular data storage concepts and SQL engines, highlighting the growing adoption of SQL as an effective way of interaction within the field of big data analytics. The reasons behind this choice are explored, and the performances and characteristics of these systems are compared. In the later sections of the thesis, the focus shifts towards big data cloud services, with a particular emphasis on AWS (Amazon Web Services). Alternative cloud service providers are also discussed in brief. The thesis culminates in a practical demonstration of data analysis conducted on a selected dataset within three selected AWS cloud services. This involves creating scripts to gather and process data, establishing ETL pipelines, configuring databases, conducting data analysis, and documenting the experiments. The goal is to assess the advantages and disadvantages of these services and to provide a comprehensive understanding of their functionalities.

Machine learning operations (MLOps) tools and practices help us continuously develop and de- ploy machine learning models as part of larger software systems. Explainable machine learning can support MLOps, and vice versa. The results of machine learning models are dependent on the data and features the models use, so understanding the features is important when we want to explain the decisions of the model. In this thesis, we aim to understand how feature stores can be used to help understand the features used by machine learning models. We compared two existing open source feature stores, Feast and Hopsworks, from an explainability point of view to explore how they can be used for explainable machine learning. We were able to use both Feast and Hopsworks to aid us in understanding the features we extracted from two different datasets. The feature stores have significant differences, Hopsworks being a part of a larger MLOps platform, and having more extensive functionalities. Feature stores provide useful tools for discovering and understanding the features for machine learning models. Hopsworks can help us understand the whole lineage of the data – where it comes from and how it has been transformed – while Feast focuses on serving the features consistently to models and needs complementing services to be as useful from an explainability point of view.

Software testing is an important part of ensuring software quality. Studies have shown that having more tests results in a lower count of defects. Code coverage is a tool used in software testing to find parts of the software that require further testing and to learn which parts have been tested. Code coverage is generated automatically by the test suites during test execution. Many types of code coverage metrics exist, the most common being line coverage, statement coverage, function coverage, and branch coverage metrics. These four common metrics are usually enough, but there are many specific coverage types for specific purposes, such as condition coverage which tells how many boolean conditions have been evaluated as true and false. Each different metric gives hints on how the codebase is tested. A common consensus amongst practitioners is that code coverage does not correlate much with software quality. The correlation of software quality with code coverage is a historically broadly researched topic, which has importance both in academia and professional practice. This thesis investigates if code coverage correlates with software quality by performing a literature review. Surprising results are derived from the literature review, as most studies included in this thesis point towards code coverage correlating with software quality. This positive correlation comes from 22 studies conducted between 1995-2021, which include Academic and Industrial studies, with studies put into multiple categories, such as Correlation or No correlation based on the key finding, and categories such as Survey studies, Case studies, Open-source studies, based on the study type. Each category has most studies pointing towards a correlation. This finding is in contradiction with the opinions of professional practitioners.

Improving the monitoring of health and well-being of dairy cows through the use of computer vision based systems is a topic of ongoing research. A reliable and low-cost method for identifying cow individuals would enable automatic detection of stress, sickness or injury, and the daily observation of the animals would be made easier. Neural networks have been used successfully in the identification of cow individuals, but methods are needed that do not require incessant annotation work to generate training datasets when there are changes within a group. Methods for person re-identification and tracking have been researched extensively, with the aim of generalizing beyond the training set. These methods have been found suitable also for re-identifying and tracking previously unseen dairy cows in video frames. In this thesis, a metric-learning based re-identification model pre-trained on an existing cow dataset is compared to a similar model that has been trained on new video data recorded at Luke Maaninka research farm in Spring 2021, which contains 24 individually labelled cow individuals. The models are evaluated in tracking context as appearance descriptors in Kalman filter based tracking algorithm. The test data is video footage from a separate enclosure in Maaninka and a group of 24 previously unseen cow individuals. In addition, a simple procedure is proposed for the automatic labeling of cow identities in images based on RFID data collected from cow ear tags and feeding stations, and the known feeding station locations.

The research group dLearn.Helsinki has created a software for defining the work life competence skills of a person, working as a part of a group. The software is a research tool for developing the mentioned skills of users, and users can be of any age, from school children to employees in a company. As the users can be of different age groups, the data privacy of different groups has to be taken into consideration from different aspects. Children are more vulnerable than adults, and may not understand all the risks imposed to-wards them. Thus in the European Union the General Data Protection Regulation (GDPR)determines the privacy and data of children are more protected, and this has to be taken into account when designing software which uses said data. For dLearn.Helsinki this caused changes not only in the data handling of children, but also other users. To tackle this problem, existing and future use cases needed to be planned and possibly implemented. Another solution was to implement different versions of the software, where the organizations would be separate. One option would be determining organizational differences in the existing SaaS solution. The other option would be creating on-premise versions, where organizations would be locked in accordance to the customer type. This thesis introduces said use cases, as well as installation options for both SaaS and on-premise. With these, broader views of data privacy and the different approaches are investigated, and it can be concluded that no matter the approach, the data privacy of children will always prove a challenge.

In this work, we seek robust methods for designing affirmative action policies for university admissions. Specifically, we study university admissions under a real centralized system that uses grades and standardized test scores to match applicants to university programs. For the purposes of affirmative action, we consider policies that assign bonus points to applicants from underrepresented groups with the goal of preventing large gaps in admission rates across groups, while ensuring that the admitted students are for the most part those with the highest scores. Since such policies have to be announced before the start of the application period, there is uncertainty about which students will apply to which programs. This poses a difficult challenge for policy-makers. Hence, we introduce a strategy to design policies for the upcoming round of applications that can either address a single or multiple demographic groups. Our strategy is based on application data from previous years and a predictive model trained on this data. By comparing this predictive strategy to simpler strategies based only on application data from, e.g., the previous year, we show that the predictive strategy is generally more conservative in its policy suggestions. As a result, policies suggested by the predictive strategy lead to more robust effects and fewer cases where the gap in admission rates is inadvertently increased through the suggested policy intervention. Our findings imply that universities can employ predictive methods to increase the reliability of the effects expected from the implementation of an affirmative action policy.

This thesis presents a scalable method for identifying anomalous periods of non-activity in short periodic event sequences. The method is tested with real world point-of-sale (POS) data from grocery retail setting. However, the method can be applied also to other problem domains which produce similar sequential data. The proposed method models the underlying event sequence as a non-homogeneous Poisson process with a piecewise constant rate function. The rate function for the piecewise homogeneous Poisson process can be estimated with a change point detection algorithm that minimises a cost function consisting of the negative Poisson log-likelihood and a penalty term that is linear to the number of change points. The resulting model can be queried for anomalously long periods of time with no events, i.e., waiting times, by defining a threshold below which the waiting time observations are deemed anomalies. The first experimental part of the thesis focuses on model selection, i.e., in finding a penalty value that results in the change point detection algorithm detecting the true changes in the intensity of the arrivals of the events while not reacting to random fluctuations in the data. In the second experimental part the performance of the anomaly detection methodology is measured against stock-out data, which gives an approximate ground truth for the termination of a POS event sequence. The performance of the anomaly detector is found to be subpar in terms of precision and recall, i.e., the true positive rate and the positive predictive value. The number of false positives remains high even with small threshold values. This needs to be taken into account when considering applying the anomaly detection procedure in practice. Nevertheless, the methodology may have practical value in the retail setting, e.g., in guiding the store personnel where to focus their resources in ensuring the availability of the products.

DevOps software development methodologies have steadily gained ground over the past 15 years. Properly implemented DevOps enables the software to be integrated and deployed at a rapid pace. The implementation of DevOps practices create pressure for software testing. In the world of fast-paced integrations and deployments, software testing must perform its quality assurance function quickly and efficiently. The goal of this thesis was to identify the most relevant DevOps software testing practices and their impact on software testing. Software testing in general is a widely studied topic. This thesis looks into the recent develop- ments of software testing in DevOps. The primary sources of this study consist of 15 academic papers, which were collected with the systematic literature review source collection methodolo- gies. The study combines both systematic literature review and rapid review methodologies. The DevOps software testing practices associated with high level of automation, continuous testing and DevOps culture adoption stood out in the results. These were followed by the practices highlighting the need for flexible and versatile test tooling and test infrastructures. DevOps adoption requires the team composition and responsibilities to be carefully planned. The selected testing practices should be carefully chosen. Software testing should be primarily organized in highly automated DevOps pipelines. Manual testing should be utilized to validate the results of the automatic tests. Continuous testing, multiple testing levels and versatile test tooling should be utilized. Integration and regression testing should be run on all code changes. Application monitoring and the collection of telemetry data should be utilized to improve the tests.

Discourse dynamics is one of the important fields in digital humanities research. Over time, the perspectives and concerns of society on particular topics or events might change. Based on the changing in popularity of a certain theme different patterns are formed, increasing or decreasing the prominence of the theme in news. Tracking these changes is a challenging task. In a large text collection discourse themes are intertwined and uncategorized, which makes it hard to analyse them manually. The thesis tackles a novel task of automatic extraction of discourse trends from large text corpora. The main motivation for this work lies in the need in digital humanities to track discourse dynamics in diachronic corpora. Machine learning is a potential method to automate this task by learning patterns from the data. However, in many real use-cases ground truth is not available and annotating discourses on a corpus-level is incredibly difficult and time-consuming. This study proposes a novel procedure to generate synthetic datasets for this task, a quantitative evaluation method and a set of benchmarking models. Large-scale experiments are run using these synthetic datasets. The thesis demonstrates that a neural network model trained on such datasets can obtain meaningful results when applied to a real dataset, without any adjustments of the model.