Browsing by Title
Now showing items 378-397 of 4026
-
(2022)Photocatalysis is a versatile method to use solar energy for chemical processes. Photocatalytic materials absorb light to generate energetic electron-hole pairs that can be used for redox reactions in production of hydrogen and other chemicals, degradation of pollutants, and many other applications. BiVO4 is a visible light absorbing oxide semiconductor with a band gap of about 2.4 eV, and it has received a lot of attention as a standalone photocatalyst and as a photoanode material. The literature part of this thesis explores how the electronic structure of semiconductors and the different processes in photocatalysis together affect the efficiency of the method. Semiconductor materials are classified based on their chemical composition and compared by selecting most researched materials as examples. Various strategies to improve the photocatalyst material properties are also discussed. Many strategies, such as nanostructured photocatalysts, benefit from deposition of semiconductor thin films. Atomic layer deposition (ALD), as a highly conformal and controllable chemical vapor deposition method, is an excellent choice for depositing semiconductors and various interfacial layers. The literature review also includes a survey of ALD processes for Bi2O3 and V2O5 and a thorough analysis of the existing BiVO4 ALD processes. From the selection of binary ALD processes, bismuth(III) 2,3-dimethyl-2-butoxide (Bi(dmb)3), tetrakis(ethylmethylamido)-vanadium(IV) (TEMAV), and water were chosen as precursors to develop a new ALD process for BiVO4. The binary processes were combined in various metal precursor ratios both completely mixed in supercycles and as nanolaminates, and the resulting films were annealed to crystallize the BiVO4. X-ray diffraction was used to characterize the crystalline phases of the films, and it was noticed that TEMAV reacts with Bi2O3 to make metallic bismuth, but it is reoxidized by annealing. Composition of the films was investigated with energy dispersive X-ray spectrometry and time-of-flight elastic recoil detection analysis (ToF-ERDA). Some sensitivity to process conditions was observed in the deposition, as the metal stoichiometry varied in unexpected manner between some sets of experiments. ToF-ERDA depth profiles also revealed that mixing of the nanolaminate layers was incomplete with annealing temperatures below 450 °C and with laminate layers over 10 nm in thickness. Scanning electron microscopy was used to study the morphology of the films and revealed a granular, non-continuous structure. The optical properties of the films grown on soda-lime glass were investigated with UV-vis spectrophotometry. The band gaps of the films were estimated to be 2.4–2.5 eV. The nanolaminate approach to depositing the films was deemed the best, as it avoids most of the reduction of bismuth by TEMAV. However, it is still not clear why this process is so sensitive to process conditions. This should be investigated to further optimize the film stoichiometry. The morphology of the films might be improved by using different substrates, but it is not a critical aspect of the process as there are methods to passivate the exposed substrate surface. Overall, this process has potential to deposit excellent BiVO4 films that are suitable for further research pertaining their photocatalytic properties and modifications such as nanostructured or doped photoanodes.
-
(2012)Graphene is the ultimately thin membrane composed of carbon atoms, for which future possibilities vary from desalinating sea water to fast electronics. When studying the properties of this material, molecular dynamics has proven to be a reliable way to simulate the effects of ion irradiation of graphene. As ion beam irradiation can be used to introduce defects into a membrane, it can also be used to add substitutional impurities and adatoms into the structure. In the first study introduced in this thesis, I presented results of doping graphene with boron and nitrogen. The most important message of this study was that doping of graphene with ion beam is possible and can be applied not only to bulk targets but also to a only one atomic layer thick sheet of carbon atoms. Another important result was that different defect types have characteristic energy ranges that differ from each other. Because of this, it is possible to control the defect types created during the irradiation by varying the ion energy. The optimum energy for creating a substitution for N ion is at about 50 eV (55%) and for B ion it is ca. 40% at about the same energy. Single vacancies are most probably created at an energy of about 125 eV for N (55%) and for B at ca. 180 eV (35%). For double vacancies, the maximum probabilities are roughly at 110 eV for N (16%) and at 70 eV for B (6%). The probabilities for adatoms are the highest at very small energies. A one atom thick graphene membrane is reportedly impermeable to standard gases. Hence, graphene's selectivity for gas molecules trying to pass through the membrane is determined only by the size of the defects and vacancies in the membrane. Gas separation using graphene membranes requires knowledge of the properties of defected graphene structures. In this thesis, I presented results of the accumulation of damage on graphene by ion irradiation using MD simulations. According to our results, graphene can withstand up to 35% vacancy concentrations without breakage of the material. Also, a simple model was introduced to predict the influence of the irradiation during the experiments. In addition to the specific results regarding ion irradiation manipulation of graphene, this work shows that MD is a valuable tool for material research, providing information on atomic scale rarely accessible for experimental research, e.g., during irradiation. Using realistic interatomic potentials MD provides a computational microscope helping to understand how materials behave at the atomic level.
-
(2022)Amorphous metal oxides have proven to deform in a plastic manner at microscopic scale. In this study the plastic deformation and elastic properties of amorphous metal oxides are studied at microscopic scale using classical molecular dynamics simulations. Amorphous solids differ from crystalline solids by not having a regular lattice nor long range order. In this study the amorphous materials were created in simulations by melt-quenching. The glass transition temperature (Tg) depends on the material and cooling rate. The effect of cooling rate was studied with aluminiumoxide (Al2O3) by creating a simulation cell of 115 200 atoms and melt-quenching it with cooling rates of 1011 , 1012 and 1013 K/s. It was observed that faster cooling rates yield higher Tg. The Al2O3 was cooled to 300 K and 50 K after which the material was stretched. The stress-strain curve of the material showed that samples with higher Tg deforms in plastic manner with smaller stresses. The system stretched at 50 K had higher ultimate tensile strength than the system stretched at 300 K and thus confirming the hypothesis proposed by Frankberg about activating plastic flow with work. In order to see if the plastic phenomena can be generalized to other amorphous metal oxides the tensile simulation was performed also with a-Ga2O3 by creating a simulation cell of 105 000 atoms, melt-quenching it and then stretching. Due to the lack of parameters for Buckingham potential these parameters were fitted with GULP using the elastic properties and crystalline structure of Ga2O3. The elastic properties of Ga2O3 with the fitted potential parameters agreed very well with the literature values. The elongated a-Ga2O3 behaved in a very similar fashion compared to a-Al2O3 cooled with the same cooling rate. Further work is needed to establish the Buckingham potential parameters of a-Ga2O3 by experimen tal work. The potential can also be developed further by using the elastic constants and structures of amorphous a-Ga2O3 in the fitting process, although the potential shows already very promising results.
-
(2019)Ion beams have been the subject of significant industry interest since the 1950s. They have gained usage in many fields for their ability to modify material properties in a controlled manner. Most important has been the application to semiconductor devices such as diodes and transistors, where the necessary doping is commonly achieved by irradiation with appropriate ions, allowing the development of the technology that we see in everyday use. With the ongoing transition to ever smaller semiconductor devices, the precision required of the manufacturing process correspondingly increases. A strong suite of modeling tools is therefore needed to advance the understanding and application of ion beam methods. The binary collision approximation (BCA) as a simulation tool was first introduced in the 1950s. It allows the prediction of many radiation-related phenomena for single collision cascades, and has been adopted in many experimental laboratories and industries due to its efficiency. However, it fails to describe chemical and thermodynamic effects, limiting its usefulness where ballistic effects are not a sufficient description. Parallel to BCA, the molecular dynamics (MD) simulation algorithm was developed. It allows a more accurate and precise description of interatomic forces and therefore chemical effects. It is, however, orders of magnitude slower than the BCA method. In this work, a new variant of the MD algorithm is developed to combine the advantages of both the MD and the BCA methods. The activation and deactivation of atoms involved in atomic cascades is introduced as a way to save computational effort, concentrating the performed computations in the region of interest around the cascade and ignoring surrounding equilibrium regions. By combining this algorithm with a speedup scheme limiting the number of necessary relaxation simulations, a speedup of one order of magnitude is reached for covalent materials such as Si and Ge, for which the algorithm was validated. The developed algorithm is used to explain the behavior of Ge nanowires under Xe ion irradiation. The nanowires were shown experimentally to bend towards or away from the ion beam, and computational simulations might help with the understanding of the underlying physical processes. In this thesis, the high-fluence irradiation of a Ge nanowire is simulated and the resulting defect structure analyzed to study the bending, doubling as a second test of the developed algorithm.
-
(2013)Tämän Pro gradu –tutkielman kirjallisuuskatsaus käsittelee atsa-Michael-reaktiota, joka on typpinukleofiilin additioreaktio elektroniköyhään kaksoissidokseen. Reaktio on tyypiltään konjugaattiadditio, eli elektrofiilinä toimiva alkeeni on konjugoitunut elektroneja puoleensa vetävään ryhmään kuten karbonyyliin tai nitriiliin. Atsa-Michael-reaktiota käytetään usein synteeseissä, jotka tähtäävät β-aminoituihin karbonyyleihin, alkoholeihin tai aldehydeihin ja reaktio on tällä saralla hyvin merkittävä, sillä se on Mannich-reaktion ohella yleinen tapa tuottaa edellä mainittuja yhdisteitä. Tutkielmassa käsitellään esimerkein reaktion teoriaa ja yleisimmin käytettyjä katalyyttejä. Tutkielman kokeellinen osuus käsittelee selluloosa-akrylaatin synteesiä ja tähän templaattiin suoritettuja atsa-Michael- ja Diels-Alder-reaktioita. Sekä selluloosa-akrylaatin synteesi että jatkoreaktiot tähän templaattiin onnistuivat hyvin.
-
(2022)Blockchain technologies and cryptocurrencies have gained massive popularity in the past few years. Smart contracts extend the utility of these distributed ledgers to distributed state machines, where anyone can store and run code and then mutually agree on the next state. This opens up a whole new world of possibilities, but also many new security challenges. In this thesis we give an up-to-date survey on smart contract security issues. First we give a brief introduction to blockchains and smart contracts and explain the most common attack types and some mitigations against them. Then we sum up and analyse our findings. We find out that many of the attacks could be avoided or at least severely mitigated if the coders followed good coding practices and used design patterns that are proven to be good. Another finding is that changing the underlying blockchain technology to counter the issues is usually not the best way, as it is hard and troublesome to do and might restrict the usability of contracts too much. Lastly, we find out that many new automated tools for security are being developed and used, which indicates movement towards more conventional coding where automated tools like scanners and analysers are being used to cover a large set of security issues.
-
(2015)Intresse är en viktig förutsättning för inlärning och framtida yrkesval. I Finland är högstadieelevernas intresse för kemi skrämmande lågt. Man kan dela in intresse i situationsintresse och djupare personligt intresse. Innan man kan skapa ett personligt intresse måste ett situationsintresse först uppstå. Situationsintresset är också det som läraren kan påverka. Väl utförda demonstrationer kan påverka både elevernas intresse och inlärning positivt. Det samma gäller för undervisningsvideor. I det här arbetet har det producerats en demonstrationsvideo för att höja högstadieelevers intresse för kemi. Elevernas reaktioner på videon samt deras allmänna åsikter om videor i kemiundervisningen har undersökts kvantitativt med hjälp av en enkät. Baserat på elevernas svar kan demonstrationsvideor vara ett beaktansvärt sätt att höja högstadieelevers intresse för kemi. Det skulle dock vara bra om videorna kunde produceras med större budjet än videon i det här projektet.
-
(2020)Sales forecasting is crucial for run any retail business efficiently. Profits are maximized if popular products are available to fulfill the demand. It is also important to minimize the loss caused by unsold stock. Fashion retailers face certain challenges which make sales forecasting difficult for the products. Some of these challenges are the short life cycle of products and introduction of new products all around the year. The goal of this thesis is to study forecasting methods for fashion. We use the product attributes for products in a season to build a model that can forecast sales for all the products in the next season. Sales for different attributes are analysed for three years. Sales for different variables vary for values which indicate that a model fitted on product attributes may be used for forecasting sales. A series of experiments are conducted with multiple variants of the datasets. We implemented multiple machine learning models and compared them against each other. Empirical results are reported along with the baseline comparisons to answer research questions. Results from first experiment indicate that machine learning models are almost doing as good as the baseline model that uses mean values as predictions. The results may improve in the upcoming years when more data is available for training. The second experiment shows that models built for specific product groups are better than the generic models that are used to predict sales for all kinds of products. Since we observed a heavy tail in the data, a third experiment was conducted to use logarithmic sales for predictions, and the results do not improve much as compared to results from previous methods. The conclusion of the thesis is that machine learning methods can be used for attribute-based sales forecasting in fashion industry but more data is needed, and modeling specific groups of products bring better results.
-
(2022)The content we see is increasingly determined by ever more advanced recommender systems, and popular social media platform TikTok represents the forefront of this development (See Chapter 1). There has been much speculation about the workings of these recommender systems, but precious little systematic, controlled study (See Chapter 2). To improve our understanding of these systems, I developed sock puppet bots that consume content on TikTok as a normal user would (See Chapter 3). This allowed me to run controlled experiments to see how the TikTok recommender system would respond to sock puppets exhibiting different behaviors and preferences in a Finnish context, and how this would differ from the results obtained by earlier investigations (See Chapter 4). This research was done as part of a journalistic investigation in collaboration with Long Play. I found that TikTok appears to have adjusted their recommender system to personalize content seen by users to a much lesser degree, likely in response to a previous investigation by the WSJ. However, I came to the conclusion that, while sock puppet audits can be useful, they are not a sufficiently scalable solution to algorithm governance, and other types of audits with more internal access are needed (See Chapter 5).
-
(Helsingin yliopistoHelsingfors universitetUniversity of Helsinki, 2012)Nonverbal communication is a very important part of face to face communication. Both explicit and implicit additions to verbal communication augment the information content of communication. Before telephones did not provide any means for adding nonverbal information to the communication, but now, as the technology has advanced, it is possible to start augmenting also the communication on the phone. Adding a haptic I/O device to a regular mobile phone opens possibilities to add value to communication. We conducted two user studies, one for exploring vibration as additional modality to the communication and one on how the contextual issues affect the pressure and behavior. These studies help to understand how the communication could be augmented and whether there is tacit information about the phone usage that could be delivered as part of the communication. Both studies were field studies. Using vibration as additional modality was studied in a longitude study with couples, while contextual impact was studied as a comparison of the laboratory and field discussions. We find that it is possible to add haptic devices to a mobile phone and create a bidirectional communication channel based on the pressure applied on the phone. When the pressure is mapped to a vibration, it offers a new way of messaging. In addition, we find that there are changes in phone usage even in static laboratory conditions, thus it is possible to collect information about pressure, posture and movement of a person and share it with the discussion partner. ACM Computing Classification System (CCS): H.5.2[User Interfaces]: Haptic I/O, I.3.6[Methodology and Techniques]: Interaction techniques,
-
(2022)Anomaly detection in images is the machine learning task of classifying inputs as normal or anomalous. Anomaly localization is the related task of segmenting input images into normal and anomalous regions. The output of an anomaly localization model is a 2D array, called an anomaly map, of pixel-level anomaly scores. For example, an anomaly localization model trained on images of non-defective industrial products should output high anomaly scores in image regions corresponding to visible defects. In unsupervised anomaly localization the model is trained solely on normal data, i.e. without labelled training observations that contain anomalies. This is often necessary as anomalous observations may be hard to obtain in sufficient quantities and labelling them is time-consuming and costly. Student-teacher feature pyramid matching (STFPM) is a recent and powerful method for unsupervised anomaly detection and localization that uses a pair of convolutional neural networks of identical architecture. In this thesis we propose two methods of augmenting STFPM to produce better segmentations. Our first method, discrepancy scaling, significantly improves the segmentation performance of STFPM by leveraging pre-calculated statistics containing information about the model’s behaviour on normal data. Our second method, student-teacher model assisted segmentation, uses a frozen STFPM model as a feature detector for a segmentation model which is then trained on data with artificially generated anomalies. Using this second method we are able to produce sharper anomaly maps for which it is easier to set a threshold value that produces good segmentations. Finally, we propose the concept of expected goodness of segmentation, a way of assessing the performance of unsupervised anomaly localization models that, in contrast to current metrics, explicitly takes into account the fact that a segmentation threshold needs to be set. Our primary method, discrepancy scaling, improves segmentation AUROC on the MVTec AD dataset over the base model by 13%, measured in the shrinkage of the residual (1.0 − AUROC). On the image-level anomaly detection task, a variant of the discrepancy scaling method improves performance by 12%.
-
(Helsingin yliopistoHelsingfors universitetUniversity of Helsinki, 2007)Monissa viimeaikaisissa tutkimuksissa on tutkittu aurinkotuulen dynaamisen paineen vaikutusta revontulialueen hiukkaspresipitaatioon. Tutkimukset ovat kuitenkin perustuneet muutamaan yksittäiseen tapaukseen ja laskevan dynaamisen paineen vaikutuksia ei juuri ole tarkasteltu. Tämän opinnäytetyön tavoitteena oli selvittää suuremmasta statistiikasta aurinkotuulen dynaamisen paineen nousujen ja laskujen vaikutusta ionosfäärin dynamiikkaan. Paineen muutoksia etsittiin ACE:n mittausdatasta vuosilta 1998 2004 ja ionosfäärin vastetta näihin muutoksiin tutkittiin käyttäen IMAGE-magnetometriverkon tuottamaa magneettisen aktiivisuuden indeksiä (IE-indeksi). Tutkimuksen kohteeksi valittiin 286 painepulssia, joita edelsi ja seurasi tasaisen paineen jakso, sekä 171 vastaavaa paineen laskua (negatiivista painepulssia). Näiden paineen muutosten ionosfäärivastetta tutkittaessa käytettiin tilastollista superposed epoch -menetelmää. Tutkimuksen tulokseksi saatiin selvä positiivinen korrelaatio IE-indeksin ja aurinkotuulen dynaamisen paineen välillä. Korrelaatio on vähemmän selkeää paineen laskujen kuin nousujen yhteydessä. Tälle on useita mahdollisia selityksiä: Tutkimusaineisto paineen laskuista oli suppeampi. Toisin kuin painepulsseihin, paineen laskuihin ei liittynyt aurinkotuulen nopeuden muutosta. Lisäksi IMF:n magnitudi kasvoi lähes kaikkien paineen laskujen aikana, joten magnitudin ja IE:n välinen positiivinen korrelaatio voisi peittää paineen laskun vaikutusta. Eteläisen IMF:n painepulssien aikana IE:n muutokset aiheutuivat enimmäkseen läntisen elektrojetin vahvistumisesta ja pohjoisen IMF:n aikana havaitut IE:n muutokset liittyivät enemmän itäiseen elektrojettiin. Aurinkotuulen dynaamisen paineen ja elektrojettien korrelaation selitykseksi tarjotaan ionosfääriin saapuvien kentänsuuntaisten virtojen välityksellä tapahtuvaa kytkentää aurinkotuuleen. IMF:n z-komponentin suunnalla oli odotetun merkittävä vaikutus IE:n yleiseen tasoon, mutta IE:n korrelaatio paineen muutosten kanssa oli samaa tasoa z-komponentin etumerkistä riippumatta. Myös IMF:n y-komponentti osoittautui merkittäväksi pohjoisen IMF:n aikana, sillä tällöin IE:n yleinen taso oli korkeampi ja paineen muutosten vaikutus paljon selkeämpi IMF:n y-komponentin ollessa positiivinen kuin negatiivinen.
-
(2017)Over past decade cloud services have enabled individuals and organizations to perform different types of tasks such as online storage, email services, on-demand movies and TV shows. The cloud services has also enabled on-demand deployment of applications, at cheap cost with elastic and scalable, fault tolerant system. These cloud services are offered by cloud providers who use authentication, authorization and accounting framework based on client-server model. Though this model has been used over decades, study shows it is vulnerable to different hacks and it is also inconvenient to use for the end users. In addition, the cloud provider has total control over user data which they are able to monitor, trace, leak and even modify at their will. Thus, the user data ownership, digital identity and use of cloud services has raised privacy and security concern for the users. In this thesis, Blockchain and its applications are studied and alternative model for authentication, authorization and accounting is proposed based on Ethereum Blockchain. Furthermore, a prototype is developed which enables users to consume cloud services by authenticating, authorizing and accounting with a single identity without sharing any private user data. Experiments are run with the prototype to verify that it works as expected. Measurements are done to assess the feasibility and scalability of the solution. In the final part of the thesis, pros and cons of the proposed solution are discussed and perspectives for further research are sketched.
-
(2022)Suomen lentosäähavainnot käyvät läpi murrosta kohti automaatiota. Automaattisiin havaintoihin liittyy laatuongelmia, joten syntyi idea tehdä aiheesta laajempi tutkimus. Tutkimusaineistona käytettiin Rovaniemen lentoaseman havainnontekijöiden vuodesta 2011 lähtien täyttämää verifiointitaulukkoa, jossa ideana on kirjata manuaalisen havainnon tekohetkellä ylös automaattijärjestelmän tarjoamat arvot eri sääsuureille. Vertailtavat parametrit ovat näkyvyys, pilven alaraja ja vallitseva sää. Parametrien automaatin ja ihmisen määrittämät arvot ristiintaulukoitiin jokaiselle kolmelle parametrille erikseen. Tulokset eivät antaneet kovin hyvää kuvaa automaattihavaintojen nykyisestä laadusta, sillä kaikkien kolmen parametrin osalta havainnoista löytyi merkittäviä puutteita arvojen tarkkuudessa ja ajantasaisuudessa. Erot tarkaksi oletettuihin ihmishavaintoihin olivat niin suuria, että esiin nousi kysymyksiä lentoturvallisuuteen ja automaattihavaintojen käytön järkevyyteen liittyen. Tulosten pohjalta esitetään ratkaisuksi merkittäviä parannuksia havaintojärjestelmään sekä havaintojen tilapäistä manualisointia parannusprosessin ajaksi. Tutkielmassa käydään varsinaisen tutkimusosion lisäksi läpi Suomen lentosäähavaintojen teoriaa. Tekstissä pureudutaan syvemmin manuaalisen ja automaattisen havaintomenetelmän perusperiaatteisiin sekä esitellään Suomen lentosäähavaintojen historiaa pääpiirteittäin.
-
(2021)Rapid growth and advancement of next generation sequencing (NGS) technologies have changed the landscape of genomic medicine. Today, clinical laboratories perform DNA sequencing on a regular basis, which is an error prone process. Erroneous data affects downstream analysis and produces fallacious result. Therefore, external quality assessment (EQA) of laboratories working with NGS data is crucial. Validation of variations such as single nucleotide polymor- phism (SNP) and InDels (<50 bp) is fairly accurate these days. However, detection and quality assessment of large changes such as the copy number variation (CNV) continues to be a concern. In this work, we aimed to study the feasibility of an automated CNV concordance analysis for the laboratory EQA services. We benchmarked variants reported by 25 laboratories against the highly curated gold standard for the son (HG002/NA24385) of the askenazim trio from the Personal Genome Project published by the Genome in a Bottle Consortium (GIAB). We employed two methods to conduct concordance of CNVs, the sequence based comparison with Truvari and the in-house exome-based comparison. For deletion calls of two whole genome sequencing (WGS) submissions, Truvari gained a value greater than 88% and 68% for precision and recall respectively. Conversely, the in-house method’s precision and recall score peaked at 39% and 7.9% respectively for one WGS submission for both deletion and duplication calls. The results indicate that automated CNV concordance analysis of the deletion calls for the WGS-based callset might be feasible with Truvari. On the other hand, results for panel-based targeted sequencing for the deletion calls showed precision and recall rates ranging from 0-80% and 0-5.6% respectively with Truvari. The result suggests that automated concordance analysis of CNVs for targeted sequencing remains a challenge. In conclusion, CNV concordance analysis depends on how the sequence data is generated.
-
(2019)Background: Electroencephalography (EEG) depicts electrical activity in the brain, and can be used in clinical practice to monitor brain function. In neonatal care, physicians can use continuous bedside EEG monitoring to determine the cerebral recovery of newborns who have suffered birth asphyxia, which creates a need for frequent, accurate interpretation of the signals over a period of monitoring. An automated grading system can aid physicians in the Neonatal Intensive Care Unit by automatically distinguishing between different grades of abnormality in the neonatal EEG background activity patterns. Methods: This thesis describes using support vector machine as a base classifier to classify seven grades of EEG background pattern abnormality in data provided by the BAby Brain Activity (BABA) Center in Helsinki. We are particularly interested in reconciling the manual grading of EEG signals by independent graders, and we analyze the inter-rater variability of EEG graders by building the classifier using selected epochs graded in consensus compared to a classifier using full-duration recordings. Results: The inter-rater agreement score between the two graders was κ=0.45, which indicated moderate agreement between the EEG grades. The most common grade of EEG abnormality was grade 0 (continuous), which made up 63% of the epochs graded in consensus. We first trained two baseline reference models using the full-duration recording and labels of the two graders, which achieved 71% and 57% accuracy. We achieved 82% overall accuracy in classifying selected patterns graded in consensus into seven grades using a multi-class classifier, though this model did not outperform the two baseline models when evaluated with the respective graders’ labels. In addition, we achieved 67% accuracy in classifying all patterns from the full-duration recording using a multilabel classifier.
-
(2020)Real estate appraisal, or property valuation, requires strong expertise in order to be performed successfully, thus being a costly process to produce. However, with structured data on historical transactions, the use of machine learning (ML) enables automated, data-driven valuation which is instant, virtually costless and potentially more objective compared to traditional methods. Yet, fully ML-based appraisal is not widely used in real business applications, as the existing solutions are not sufficiently accurate and reliable. In this study, we introduce an interpretable ML model for real estate appraisal using hierarchical linear modelling (HLM). The model is learned and tested with an empirical dataset of apartment transactions in the Helsinki area, collected during the past decade. As a result, we introduce a model which has competitive predictive performance, while being simultaneously explainable and reliable. The main outcome of this study is the observation that hierarchical linear modelling is a very potential approach for automated real estate appraisal. The key advantage of HLM over alternative learning algorithms is its balance of performance and simplicity: this algorithm is complex enough to avoid underfitting but simple enough to be interpretable and easy to productize. Particularly, the ability of these models to output complete probability distributions quantifying the uncertainty of the estimates make them suitable for actual business use cases where high reliability is required.
-
(2020)RPA (Robotic process automation) is an emerging field in software engineering that is applied in a wide variety of industries to automate repetitive business processes. While the tools to create RPA projects have evolved quickly, testing in these projects has not yet received much attention. The purpose of this thesis was to study how the regression testing of RPA projects created using UiPath could be automated while avoiding the following most common pitfalls of test automation projects: unreliability, too high cost, lack of re-usable components and too difficult implementation. An automated regression test suite was created as a case study with UiPath for an existing RPA project that is currently being tested manually. The results imply that UiPath can be used to also create the regression test suite, not just the RPA project. The automated test suite could be used to run all the tests in the regression test suite that is currently run manually. The common test automation project pitfalls were also mostly avoided: the structure of the project can be re-used for other test projects, the project can recover from unexpected errors and the implementation of the tests does not require a high level of programming knowledge. The main challenge proved to be the implementation cost which was increased by the longer then expected test development time. Another finding was that the measures taken to address test automation project pitfalls will likely work only with RPA projects that are simpler or as complex as the sample RPA project. With more complex projects, there will also likely be more challenges with test data creation. As a result, for complex projects, manual regression testing could be a better option.
-
(2020)Nowadays the Internet is being used as a platform for providing a wide variety of different services. That has created challenges related to scaling IT infrastructure management. Cloud computing is a popular solution for scaling infrastructure, either by building a self-hosted cloud or by using cloud platform provided by external organizations. This way some the challenges related to large scale can be transferred to the cloud administrators. OpenStack is a group of open-source software projects for running cloud platforms. It is currently the most commonly used software for building private clouds. Since initially published by NASA and Rackspace, it has been used by various organizations such as Walmart, China Mobile and Cern nuclear research institute. The largest production deployments of OpenStack clouds consist of thousands of physical server computers located in multiple datacenters. The OpenStack community has created many deployment methods that take advantage of automated software configuration management. The deployment methods are built with state of the art software for automating different administrative tasks. They take different approaches to automating infrastructure management for OpenStack. This thesis compares some of the automated deployment methods for OpenStack and examines the benefits of using automation for configuration management. We present comparisons based on technical documentations as well as reference literature. Additionally, we conducted a questionnaire for OpenStack administrators about the use of automation. Lastly, we tested one of the deployment methods in a virtualized environment.
-
(2013)This Master's Thesis describes one example on how to automatically generate tests for real-time protocol software. Automatic test generation is performed using model-based testing (MBT). In model-based testing, test cases are generated from the behaviour model of the system under test (SUT). This model expresses the requirements of the SUT. Many parameters can be varied and test sequences randomised. In this context, real-time protocol software means a system component of Nokia Siemens Networks (NSN) Long Term Evolution (LTE) base station. This component, named MAC DATA, is the system under test (SUT) in this study. 3GPP has standardised the protocol stack for the LTE eNodeB base station. MAC DATA implements most of the functionality of the Medium Access Control (MAC) and Radio Link Control (RLC) protocols, which are two protocols of the LTE eNodeB. Because complex telecommunication software is discussed here, it is challenging to implement MBT for the MAC DATA system component testing. First, the expected behaviour of a system component has to be modelled. Because it is not smart to model everything, the most relevant system component parts that need to be tested have to be discovered. Also, the most important parameters have to be defined from the huge parameter space. These parameters have to be varied and randomised. With MBT, a vast number of different kind of users can be created, which is not reasonable in manual test design. Generating a very long test case takes only a short computing time. In addition to functional testing, MBT is used in performance and worst-case testing by executing a long test case based on traffic models. MBT has been noticed to be suitable for challenging performance and worst-case testing. This study uses three traffic models: smartphone-dominant, laptop-dominant and mixed. MBT is integrated into continuous integration (CI) system, which automatically runs MBT test case generations and executions overnight. The main advantage of the MBT implementation is the possibility to create different kinds of users and simulate real-life system behaviour. This way, hidden defects can be found from test environment and SUT.
Now showing items 378-397 of 4026