Research

28 pages, 25880 KiB

Open AccessArticle

Improving Deep Interactive Evolution with a Style-Based Generator for Artistic Expression and Creative Exploration

by Carlos Tejeda-Ocampo, Armando López-Cuevas and Hugo Terashima-Marin

Entropy 2021, 23(1), 11; https://0-doi-org.brum.beds.ac.uk/10.3390/e23010011 - 24 Dec 2020

Cited by 2 | Viewed by 2963

Deep interactive evolution (DeepIE) combines the capacity of interactive evolutionary computation (IEC) to capture a user’s preference with the domain-specific robustness of a trained generative adversarial network (GAN) generator, allowing the user to control the GAN output through evolutionary exploration of the latent [...] Read more.

Deep interactive evolution (DeepIE) combines the capacity of interactive evolutionary computation (IEC) to capture a user’s preference with the domain-specific robustness of a trained generative adversarial network (GAN) generator, allowing the user to control the GAN output through evolutionary exploration of the latent space. However, the traditional GAN latent space presents feature entanglement, which limits the practicability of possible applications of DeepIE. In this paper, we implement DeepIE within a style-based generator from a StyleGAN model trained on the WikiArt dataset and propose StyleIE, a variation of DeepIE that takes advantage of the secondary disentangled latent space in the style-based generator. We performed two AB/BA crossover user tests that compared the performance of DeepIE against StyleIE for art generation. Self-rated evaluations of the performance were collected through a questionnaire. Findings from the tests suggest that StyleIE and DeepIE perform equally in tasks with open-ended goals with relaxed constraints, but StyleIE performs better in close-ended and more constrained tasks. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

41 pages, 1458 KiB

Open AccessArticle

New Interfaces and Approaches to Machine Learning When Classifying Gestures within Music

by Chris Rhodes, Richard Allmendinger and Ricardo Climent

Entropy 2020, 22(12), 1384; https://0-doi-org.brum.beds.ac.uk/10.3390/e22121384 - 07 Dec 2020

Cited by 6 | Viewed by 4076

Abstract

Interactive music uses wearable sensors (i.e., gestural interfaces—GIs) and biometric datasets to reinvent traditional human–computer interaction and enhance music composition. In recent years, machine learning (ML) has been important for the artform. This is because ML helps process complex biometric datasets from GIs [...] Read more.

Interactive music uses wearable sensors (i.e., gestural interfaces—GIs) and biometric datasets to reinvent traditional human–computer interaction and enhance music composition. In recent years, machine learning (ML) has been important for the artform. This is because ML helps process complex biometric datasets from GIs when predicting musical actions (termed performance gestures). ML allows musicians to create novel interactions with digital media. Wekinator is a popular ML software amongst artists, allowing users to train models through demonstration. It is built on the Waikato Environment for Knowledge Analysis (WEKA) framework, which is used to build supervised predictive models. Previous research has used biometric data from GIs to train specific ML models. However, previous research does not inform optimum ML model choice, within music, or compare model performance. Wekinator offers several ML models. Thus, we used Wekinator and the Myo armband GI and study three performance gestures for piano practice to solve this problem. Using these, we trained all models in Wekinator and investigated their accuracy, how gesture representation affects model accuracy and if optimisation can arise. Results show that neural networks are the strongest continuous classifiers, mapping behaviour differs amongst continuous models, optimisation can occur and gesture representation disparately affects model mapping behaviour; impacting music practice. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

22 pages, 581 KiB

Open AccessArticle

A Genetic Programming-Based Low-Level Instructions Robot for Realtimebattle

by Juan Romero, Antonino Santos, Adrian Carballal, Nereida Rodriguez-Fernandez, Iria Santos, Alvaro Torrente-Patiño, Juan Tuñas and Penousal Machado

Entropy 2020, 22(12), 1362; https://0-doi-org.brum.beds.ac.uk/10.3390/e22121362 - 30 Nov 2020

Cited by 2 | Viewed by 2206

Abstract

RealTimeBattle is an environment in which robots controlled by programs fight each other. Programs control the simulated robots using low-level messages (e.g., turn radar, accelerate). Unlike other tools like Robocode, each of these robots can be developed using different programming languages. Our purpose [...] Read more.

RealTimeBattle is an environment in which robots controlled by programs fight each other. Programs control the simulated robots using low-level messages (e.g., turn radar, accelerate). Unlike other tools like Robocode, each of these robots can be developed using different programming languages. Our purpose is to generate, without human programming or other intervention, a robot that is highly competitive in RealTimeBattle. To that end, we implemented an Evolutionary Computation technique: Genetic Programming. The robot controllers created in the course of the experiments exhibit several different and effective combat strategies such as avoidance, sniping, encircling and shooting. To further improve their performance, we propose a function-set that includes short-term memory mechanisms, which allowed us to evolve a robot that is superior to all of the rivals used for its training. The robot was also tested in a bout with the winner of the previous “RealTimeBattle Championship”, which it won. Finally, our robot was tested in a multi-robot battle arena, with five simultaneous opponents, and obtained the best results among the contenders. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

19 pages, 941 KiB

Open AccessArticle

Generating Artificial Reverberation via Genetic Algorithms for Real-Time Applications

by Edward Ly and Julián Villegas

Entropy 2020, 22(11), 1309; https://0-doi-org.brum.beds.ac.uk/10.3390/e22111309 - 17 Nov 2020

Cited by 2 | Viewed by 2841

Abstract

We introduce a Virtual Studio Technology (VST) 2 audio effect plugin that performs convolution reverb using synthetic Room Impulse Responses (RIRs) generated via a Genetic Algorithm (GA). The parameters of the plugin include some of those defined under the ISO 3382-1 standard (e.g., [...] Read more.

We introduce a Virtual Studio Technology (VST) 2 audio effect plugin that performs convolution reverb using synthetic Room Impulse Responses (RIRs) generated via a Genetic Algorithm (GA). The parameters of the plugin include some of those defined under the ISO 3382-1 standard (e.g., reverberation time, early decay time, and clarity), which are used to determine the fitness values of potential RIRs so that the user has some control over the shape of the resulting RIRs. In the GA, these RIRs are initially generated via a custom Gaussian noise method, and then evolve via truncation selection, random weighted average crossover, and mutation via Gaussian multiplication in order to produce RIRs that resemble real-world, recorded ones. Binaural Room Impulse Responses (BRIRs) can also be generated by assigning two different RIRs to the left and right stereo channels. With the proposed audio effect, new RIRs that represent virtual rooms, some of which may even be impossible to replicate in the physical world, can be generated and stored. Objective evaluation of the GA shows that contradictory combinations of parameter values will produce RIRs with low fitness. Additionally, through subjective evaluation, it was determined that RIRs generated by the GA were still perceptually distinguishable from similar real-world RIRs, but the perceptual differences were reduced when longer execution times were used for generating the RIRs or the unprocessed audio signals were comprised of only speech. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

30 pages, 7770 KiB

Open AccessArticle

A Computational Model of Tonal Tension Profile of Chord Progressions in the Tonal Interval Space

by María Navarro-Cáceres, Marcelo Caetano, Gilberto Bernardes, Mercedes Sánchez-Barba and Javier Merchán Sánchez-Jara

Entropy 2020, 22(11), 1291; https://0-doi-org.brum.beds.ac.uk/10.3390/e22111291 - 13 Nov 2020

Cited by 9 | Viewed by 3889

Abstract

In tonal music, musical tension is strongly associated with musical expression, particularly with expectations and emotions. Most listeners are able to perceive musical tension subjectively, yet musical tension is difficult to be measured objectively, as it is connected with musical parameters such as [...] Read more.

In tonal music, musical tension is strongly associated with musical expression, particularly with expectations and emotions. Most listeners are able to perceive musical tension subjectively, yet musical tension is difficult to be measured objectively, as it is connected with musical parameters such as rhythm, dynamics, melody, harmony, and timbre. Musical tension specifically associated with melodic and harmonic motion is called tonal tension. In this article, we are interested in perceived changes of tonal tension over time for chord progressions, dubbed tonal tension profiles. We propose an objective measure capable of capturing tension profile according to different tonal music parameters, namely, tonal distance, dissonance, voice leading, and hierarchical tension. We performed two experiments to validate the proposed model of tonal tension profile and compared against Lerdahl’s model and MorpheuS across 12 chord progressions. Our results show that the considered four tonal parameters contribute differently to the perception of tonal tension. In our model, their relative importance adopts the following weights, summing to unity: dissonance (0.402), hierarchical tension (0.246), tonal distance (0.202), and voice leading (0.193). The assumption that listeners perceive global changes in tonal tension as prototypical profiles is strongly suggested in our results, which outperform the state-of-the-art models. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

16 pages, 20160 KiB

Open AccessArticle

Generative Art with Swarm Landscapes

by Diogo de Andrade, Nuno Fachada, Carlos M. Fernandes and Agostinho C. Rosa

Entropy 2020, 22(11), 1284; https://0-doi-org.brum.beds.ac.uk/10.3390/e22111284 - 12 Nov 2020

Cited by 5 | Viewed by 3975

Abstract

We present a generative swarm art project that creates 3D animations by running a Particle Swarm Optimization algorithm over synthetic landscapes produced by an objective function. Different kinds of functions are explored, including mathematical expressions, Perlin noise-based terrain, and several image-based procedures. A [...] Read more.

We present a generative swarm art project that creates 3D animations by running a Particle Swarm Optimization algorithm over synthetic landscapes produced by an objective function. Different kinds of functions are explored, including mathematical expressions, Perlin noise-based terrain, and several image-based procedures. A method for displaying the particle swarm exploring the search space in aesthetically pleasing ways is described. Several experiments are detailed and analyzed and a number of interesting visual artifacts are highlighted. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

15 pages, 609 KiB

Open AccessArticle

On-The-Fly Syntheziser Programming with Fuzzy Rule Learning

by Iván Paz, Àngela Nebot, Francisco Mugica and Enrique Romero

Entropy 2020, 22(9), 969; https://0-doi-org.brum.beds.ac.uk/10.3390/e22090969 - 31 Aug 2020

Cited by 1 | Viewed by 2131

Abstract

This manuscript explores fuzzy rule learning for sound synthesizer programming within the performative practice known as live coding. In this practice, sound synthesis algorithms are programmed in real time by means of source code. To facilitate this, one possibility is to automatically create [...] Read more.

This manuscript explores fuzzy rule learning for sound synthesizer programming within the performative practice known as live coding. In this practice, sound synthesis algorithms are programmed in real time by means of source code. To facilitate this, one possibility is to automatically create variations out of a few synthesizer presets. However, the need for real-time feedback makes existent synthesizer programmers unfeasible to use. In addition, sometimes presets are created mid-performance and as such no benchmarks exist. Inductive rule learning has shown to be effective for creating real-time variations in such a scenario. However, logical IF-THEN rules do not cover the whole feature space. Here, we present an algorithm that extends IF-THEN rules to hyperrectangles, which are used as the cores of membership functions to create a map of the input space. To generalize the rules, the contradictions are solved by a maximum volume heuristics. The user controls the novelty-consistency balance with respect to the input data using the algorithm parameters. The algorithm was evaluated in live performances and by cross-validation using extrinsic-benchmarks and a dataset collected during user tests. The model’s accuracy achieves state-of-the-art results. This, together with the positive criticism received from live coders that tested our methodology, suggests that this is a promising approach. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

23 pages, 3116 KiB

Open AccessArticle

Gaze Information Channel in Van Gogh’s Paintings

by Qiaohong Hao, Lijing Ma, Mateu Sbert, Miquel Feixas and Jiawan Zhang

Entropy 2020, 22(5), 540; https://0-doi-org.brum.beds.ac.uk/10.3390/e22050540 - 12 May 2020

Cited by 2 | Viewed by 3215

Abstract

This paper uses quantitative eye tracking indicators to analyze the relationship between images of paintings and human viewing. First, we build the eye tracking fixation sequences through areas of interest (AOIs) into an information channel, the gaze channel. Although this channel can be [...] Read more.

This paper uses quantitative eye tracking indicators to analyze the relationship between images of paintings and human viewing. First, we build the eye tracking fixation sequences through areas of interest (AOIs) into an information channel, the gaze channel. Although this channel can be interpreted as a generalization of a first-order Markov chain, we show that the gaze channel is fully independent of this interpretation, and stands even when first-order Markov chain modeling would no longer fit. The entropy of the equilibrium distribution and the conditional entropy of a Markov chain are extended with additional information-theoretic measures, such as joint entropy, mutual information, and conditional entropy of each area of interest. Then, the gaze information channel is applied to analyze a subset of Van Gogh paintings. Van Gogh artworks, classified by art critics into several periods, have been studied under computational aesthetics measures, which include the use of Kolmogorov complexity and permutation entropy. The gaze information channel paradigm allows the information-theoretic measures to analyze both individual gaze behavior and clustered behavior from observers and paintings. Finally, we show that there is a clear correlation between the gaze information channel quantities that come from direct human observation, and the computational aesthetics measures that do not rely on any human observation at all. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

14 pages, 603 KiB

Open AccessArticle

Comparison of Outlier-Tolerant Models for Measuring Visual Complexity

by Adrian Carballal, Carlos Fernandez-Lozano, Nereida Rodriguez-Fernandez, Iria Santos and Juan Romero

Entropy 2020, 22(4), 488; https://0-doi-org.brum.beds.ac.uk/10.3390/e22040488 - 24 Apr 2020

Cited by 6 | Viewed by 2850

Abstract

Providing the visual complexity of an image in terms of impact or aesthetic preference can be of great applicability in areas such as psychology or marketing. To this end, certain areas such as Computer Vision have focused on identifying features and computational models [...] Read more.

Providing the visual complexity of an image in terms of impact or aesthetic preference can be of great applicability in areas such as psychology or marketing. To this end, certain areas such as Computer Vision have focused on identifying features and computational models that allow for satisfactory results. This paper studies the application of recent ML models using input images evaluated by humans and characterized by features related to visual complexity. According to the experiments carried out, it was confirmed that one of these methods, Correlation by Genetic Search (CGS), based on the search for minimum sets of features that maximize the correlation of the model with respect to the input data, predicted human ratings of image visual complexity better than any other model referenced to date in terms of correlation, RMSE or minimum number of features required by the model. In addition, the variability of these terms were studied eliminating images considered as outliers in previous studies, observing the robustness of the method when selecting the most important variables to make the prediction. Full article

(This article belongs to the Special Issue Artificial Intelligence and Complexity in Art, Music, Games and Design)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence and Complexity in Art, Music, Games and Design

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (9 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI