Haku
Viitteet 1-10 / 21
Automatic keyphrase extraction on Amazon reviews
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
People are facing severe challenges posed by big data. As an important type of the online text, product reviews have evoked much research interest because of their commercial potential. This thesis ...
An Improved Nearest Neighbor Based Entropy Estimator with Local Ellipsoid Correction and its Application to Evaluation of MCMC Posterior Samples
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Entropy estimation is an important technique to summarize the uncertainty of a distribution underlying a set of samples. It ties to important research problems in fields such as statistics, machine learning and so on. The ...
Deep neural networks to forecast cardiac and respiratory deterioration of intensive care patients
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Deep neural networks have proven valuable in several applications. The availability of electronic health records at high frequency has made it possible to provide realtime prediction to stay relevant to the user’s immediate ...
Considering the usability of an ERP system in a multicultural collaborative organizational context through Hertzum's images of usability
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Enterprise resource planning (ERP) systems, although common in organizations, are noted for their lack of usability considerations. They are often large and complex, and as such are difficult to learn and to use.
We set ...
User interface design principles for Finnish websites’ localization in China based on cultural dimensions
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Globalization has enabled distribution of market over multiple cultures around the world. For international businesses, they need to bring culture elements into consideration while doing websites’ localization. Studies ...
Predicting image social tags using a convolutional neural network
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Convolutional Neural Networks (CNN) are regarded as the state-of-the-art approach in image classification tasks, i.e. predicting appropriate labels for an image. Active ongoing research in the field has produced methods ...
Procedural text generation with stateful context-free grammars
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Context-free grammars have become an increasingly popular solution to procedural text generation. However, standard context-free grammars have inherent limitations with handling state and continuity. This thesis describes ...
Utilizing information systems in inter-organizational collaboration and information sharing
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
Information systems are becoming more commonly used in inter-organizational collaboration in attempt to improve the value chain performance. Information sharing is an important part of inter-organizational systems, but ...
What can we recommend to game players? - Implementing a system of analyzing game reviews
(2018)
Pro gradu -tutkielma
Pro gradu -tutkielma
With the rapid development of game industry, games take an increasing important role of entertainment in our daily life. With more and more new games coming to the market, it is difficult for players to choose suitable ...