32 research outputs found
HistoryMA_danish_childhood_1999_2011
No full text<p>README</p><p>This is an archive containing items that hold significance for the Danish authors' childhood in the period late 1990's to early 2010's. The authors of the archive are Emma Falbe-Hansen, Andreas Emil Mikkelsen, Asta Bøtkjær Naamansen and Karoline Støjberg Sejersen. The filetypes of the archive are TIFF for pictures and MP3 for sound clips. </p><p>This Zenodo folder contains a media file with the items and a dataset which also includes metadata descriptions and author information. The media file is 164 MB and the dataset is 16.7 KB.</p>
Artificial Intelligence and Machine Learning
No full textWith the ever-expanding digitalisation, more information or data is generated and is available within the digital ecosystem. The expansion of available data and the increased competition caused by globalisation contribute to why manufacturers are looking for more advanced methods to optimise their production and products. The general usage of artificial intelligence (AI) within different fields is expanding. As part of Industry 4.0, AI is also gaining interest within the industrial sector, where companies are expanding and trying different usages of AI, both within their production and as a product or service
Artificial intelligence and internet of things in small and medium-sized enterprises:A survey
No full textInternet of things (IoT) and artificial intelligence (AI) are popular topics of Industry 4.0. Many publications regarding these topics have been published, but they are primarily focused on larger enterprises. However, small and medium-sized enterprises (SMEs) are considered the economic backbone of many countries, which is why it is increasingly important that these kinds of companies also have easy access to these technologies and can make them operational. This paper presents a comprehensive survey and investigation of how widespread AI and IoT are among manufacturing SMEs, and discusses the current limitations and opportunities towards enabling predictive analytics. Firstly, an overview of the enablers for AI and IoT is provided along with the four analytics capabilities. Hereafter a comprehensive literature review is conducted and its findings showcased. Finally, emerging topics of research and development, making AI and IoT accessible technologies to SMEs, and the associated future trends and challenges are summarised.</p
Concept of Easy-to-use Versatile Artificial Intelligence in Industrial Small & Medium-sized Enterprises
Full text linkIn this paper, the concept of what we call AI-Box is presented. This concept is targeting small and medium-sized enterprises within the manufacturing industry sector. The AI-Box aims to bring technologies from Industry 4.0 to them, with the use of easy-to-use and versatile implementation. Preliminary experiments have been conducted at Aalborg University and at an industrial partner to solve vision tasks, which would be too expensive with conventional vision techniques. Moreover, three different convolutional neural networks were tested to find the best- suited architecture. The three networks tested were the simple AlexNet, the complex ResNeXt, and small and complex SqueezeNet. Our results show that it is possible to solve the classification problem in a few epochs. Furthermore, with the use of augmented data, the performance can be improved. Our preliminary results also showed that the simpler convolutional neural network architecture from AlexNet yields a better result when classifying simple data
Robot Learning From a Human Expert Using Inverse Reinforcement Learning: A Deep Reinforcement Learning Approach for Industrial Applications
No full textThe need for adaptable models, e.g. reinforcement learning (RL), have in recent years been more present within the industry. However, the number of commercial solutions using RL is limited, one reason being the complexity related to the design of RL. Therefore, a method to identify complexities of RL for industrial applications is presented in this thesis. It was used on 15 applications inspired from four industrial companies. Complexity was especially identified in relation to the reward functions. Thus two Linear Inverse RL (IRL) algorithms in which the reward function is represented as a linear combination of features, was tested using expert data. Some of the tests indicated a visual better result than tests carried out using RL. The process of designing features shared similarities with the process of designing a reward function. The added complexity of implementing Linear IRL and constructing expert data is thus not always a simpler approach. The IRL method GAIL, which requires no feature construction, was furthermore tested showing potential
Revisiting ‘Little Jiffy, Mark IV’: Towards a Bayesian KMO index
No full textThe Kaiser-Meyer-Olkin (KMO) index is a measure of sampling adequacy used by researchers to assess whether a data matrix is factorable prior to a factor analysis. Since its conception, the KMO index has remained a Frequentist statistic, leaving researchers unable to employ the advantages of Bayesian inference when assessing sampling adequacy. Building on the increasing relevance of the Bayesian statistical approach, as well as advancements in Markov-Chain Monte Carlo methods, the author proposes a re-conceptualization of the KMO index within the Bayesian framework that enables researchers to incorporate prior information and make coherent probabilistic statements about the sampling adequacy of a data matrix.©
Keywords: Kaiser-Meyer-Olkin index, KMO index, Bayesian Kaiser-Meyer-Olkin index, BKMO index, Measure of Sampling Adequacy, MSA, Bayesian Measure of Sampling Adequacy, BMSA, Bootstrap KMO index, Robust BKMO index, Bayesian inference, Frequentist inferenc
Transferring Human Manipulation Knowledge to Robots with Inverse Reinforcement Learning
Full text linkThe need for adaptable models, e.g. reinforcement learning, have in recent years been more present within the industry. In this paper, we show how two versions of inverse reinforcement learning can be used to transfer task knowledge from a human expert to a robot in a dynamic environment. Moreover, a second method called Principal Component Analysis weighting is presented and discussed. The method shows potential in the use case but requires some more research
'En uproblematisk, stort set afsluttet lille affære' - En nærsproglig analyse af en novelle af Jan Sonnergaard
No full textThis study examines how an unreliable narrator affects an overall interpretation of fiction. The short story, “Historie om en ung mand, der tvinges ind I et klædeskab, fordi et ubehageligt væsen bryder ind i hans kærlighedsliv på de mest umulige og ubelejlige tidspunkter”, from the collection of short stories Radiator by the Danish author Jan Sonnergaard, is the case of this study. Peripeteic texts or P-texts by Simon Uffe Borchmann and the cooperative principle, implicatures and the pragmatics of language by Paul Grice are the theoretical bases of this study. Moreover, the concept of the unreliable narrator by the literary theorist Wayne C. Booth as well as the redevelopment of this concept by James Phelan and Mary Patricia Martin’s will be introduced and applied. The analysis of the short story, which is structured after Borchmann’s peripeteic process of understanding, discovers that the unreliability of the narrator plays a vital role in the process of interpretation, which can be said about fiction in general. When it comes to the role of the different characters and how they are linked, the first reliable interpretation differs greatly from the second suspicious interpretation. Therefore, it is necessary to discuss the possibility of a symptom reading of the unreliability of the narrator, as well as the role in which the interpretation of the reader plays on the exposing of unreliability.This study examines how an unreliable narrator affects an overall interpretation of fiction. The short story, “Historie om en ung mand, der tvinges ind I et klædeskab, fordi et ubehageligt væsen bryder ind i hans kærlighedsliv på de mest umulige og ubelejlige tidspunkter”, from the collection of short stories Radiator by the Danish author Jan Sonnergaard, is the case of this study. Peripeteic texts or P-texts by Simon Uffe Borchmann and the cooperative principle, implicatures and the pragmatics of language by Paul Grice are the theoretical bases of this study. Moreover, the concept of the unreliable narrator by the literary theorist Wayne C. Booth as well as the redevelopment of this concept by James Phelan and Mary Patricia Martin’s will be introduced and applied. The analysis of the short story, which is structured after Borchmann’s peripeteic process of understanding, discovers that the unreliability of the narrator plays a vital role in the process of interpretation, which can be said about fiction in general. When it comes to the role of the different characters and how they are linked, the first reliable interpretation differs greatly from the second suspicious interpretation. Therefore, it is necessary to discuss the possibility of a symptom reading of the unreliability of the narrator, as well as the role in which the interpretation of the reader plays on the exposing of unreliability
A New Piano Reduction of the Nielsen Flute Concerto
No full textabstract: The purpose of this research is to create a new piano reduction of Carl Nielsen’s Flute Concerto. Danish composer Carl Nielsen was born in 1865 and died in 1931. His compositional focus on orchestral writing made him renowned for his symphonies and concerti for flute and clarinet. Today his concerti are often performed by both professional musicians and students.
The first published piano reduction of the Flute Concerto was issued in 1952 by the composer’s son-in law, Emil Telmányi, who was a Hungarian violinist and conductor. This reduction was published by Samfundet til Udgivelse af Dansk Musik. In 2003, as part of The Carl Nielsen Edition, Edition Wilhelm Hansen published a new revised edition of the concerto. The piano reduction of this edition was written by Danish pianist Per Salo, and is the most frequently used by pianists today. This edition contains much information pertaining to the orchestration, but this often causes the piano part to become challenging or unplayable in many passages.
For collaborative pianists, playing concerti requires both the ability to imitate the orchestral sound, and to understand and show the main ideas of each passage. However, as this concerto is often performed in universities by flutists and pianists of different skill levels, creating a simplified version of the piano reduction will support many pianists by helping them to learn this music in a more approachable and easily performable context.Dissertation/ThesisDoctoral Dissertation Music 201
