Special Issue "Bioinspired Intelligence"

A special issue of Biomimetics (ISSN 2313-7673).

Deadline for manuscript submissions: closed (31 October 2019).

Special Issue Editor

Dr. Ing. Juan Luis Crespo Mariño
E-Mail Website
Guest Editor
PaRMa Group and LIANA Lab, Department of Mechatronics Engineering, Tecnológico de Costa Rica, 30101 Cartago, Costa Rica
Interests: computational intelligence; attentional systems; CI in applied physics; medical device development; CI approaches to biocomputation

Special Issue Information

Dear Colleagues,

Inspired by biological processes and structures, bioinspired intelligence is a new and exciting approach to artificial intelligence. Departing from the mainstream procedures and conventional models in the field of artificial intelligence, it is opening new doors in multiple areas, such as biodiversity conservation, biomedicine or security applications. 

This Special Issue aims to provide a forum for the current status and future perspectives of this rapidly emerging field. This Special Issue is cooperating with the IEEE International Work Conference on Bioinspired Intelligence (IWOBI) 2018 conference (http://iwobi.ulpgc.es/2018/). Registered participants of this conference are invited to submit their manuscripts to be considered for publication. Authors may consider to contribute an original research article or review in areas related to the conference themes.

Dr. Ing. Juan Luis Crespo Mariño
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Biomimetics is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • optimization and metaheuristic
  • biomathematics and biostatistics
  • numerical methods and differential equations modeling
  • pattern recognition and classification
  • machine learning and computational intelligence techniques
  • robotics
  • signal processing and analysis
  • computer vision
  • intelligent networks
  • bioinformatics
  • computational anatomy
  • natural sounds and speech recognition
  • models of biological learning

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Other

Article
Using a Convolutional Siamese Network for Image-Based Plant Species Identification with Small Datasets
Biomimetics 2020, 5(1), 8; https://doi.org/10.3390/biomimetics5010008 - 01 Mar 2020
Cited by 7 | Viewed by 1376
Abstract
The application of deep learning techniques may prove difficult when datasets are small. Recently, techniques such as one-shot learning, few-shot learning, and Siamese networks have been proposed to address this problem. In this paper, we propose the use a convolutional Siamese network (CSN) [...] Read more.
The application of deep learning techniques may prove difficult when datasets are small. Recently, techniques such as one-shot learning, few-shot learning, and Siamese networks have been proposed to address this problem. In this paper, we propose the use a convolutional Siamese network (CSN) that learns a similarity metric that discriminates between plant species based on images of leaves. Once the CSN has learned the similarity function, its discriminatory power is generalized to classify not just new pictures of the species used during training but also entirely new species for which only a few images are available. This is achieved by exposing the network to pairs of similar and dissimilar observations and minimizing the Euclidean distance between similar pairs while simultaneously maximizing it between dissimilar pairs. We conducted experiments to study two different scenarios. In the first one, the CSN was trained and validated with datasets that comprise 5, 10, 15, 20, 25, and 30 pictures per species, extracted from the well-known Flavia dataset. Then, the trained model was tested with another dataset composed of 320 images (10 images per species) also from Flavia. The obtained accuracy was compared with the results of feeding the same training, validation, and testing datasets to a convolutional neural network (CNN) in order to determine if there is a threshold value t for dataset size that defines the intervals for which either the CSN or the CNN has better accuracy. In the second studied scenario, the accuracy of both the CSN and the CNN—both trained and validated with the same datasets extracted from Flavia—were compared when tested on a set of images of leaves of 20 Costa Rican tree species that are not represented in Flavia. Full article
(This article belongs to the Special Issue Bioinspired Intelligence)
Show Figures

Figure 1

Article
Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement
Biomimetics 2020, 5(1), 1; https://doi.org/10.3390/biomimetics5010001 - 20 Dec 2019
Cited by 1 | Viewed by 1656
Abstract
Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in [...] Read more.
Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions. To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combinations of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation was made based on quality measurements of the signal’s spectrum, the training time of the networks, and statistical validation of results. In total, 120 artificial neural networks of eight different types were trained and compared. The results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, given that reduction in training time is on the order of 30%, in processes that can normally take several days or weeks, depending on the amount of data. The results also present advantages in efficiency, but without a significant drop in quality. Full article
(This article belongs to the Special Issue Bioinspired Intelligence)
Show Figures

Figure 1

Article
An Approximation of Heart Failure Using Cardiovascular Simulation Toolbox
Biomimetics 2019, 4(3), 47; https://doi.org/10.3390/biomimetics4030047 - 10 Jul 2019
Viewed by 1394
Abstract
In this paper, we present the simulation of 5 different heart failures with the help of the Cardiovascular Simulation Toolbox (CVST) proposed by O. Barnea et al. at Tel-Aviv University. This is a modified version of the CVST, proposed by G.Ortiz; here, we [...] Read more.
In this paper, we present the simulation of 5 different heart failures with the help of the Cardiovascular Simulation Toolbox (CVST) proposed by O. Barnea et al. at Tel-Aviv University. This is a modified version of the CVST, proposed by G.Ortiz; here, we show that the pathological failures can be covered by this tool. We varied the value of the tool blocks, included the results of the hemodynamic parameters and the P-V loop curves for each disease and compared them to the medical data to prove the effectiveness of the simulation. Based on these changes, we achieved an effective simulation of the following heart failures in the CVST: Diastolic Heart Failure (DHF), Systolic Heart Failure (SHF), Right Ventricle Heart Failure (RVHF), Low Output Heart Failure (LOHF) and High Output Heart Failure (HOHF). Full article
(This article belongs to the Special Issue Bioinspired Intelligence)
Show Figures

Figure 1

Article
Improving Post-Filtering of Artificial Speech Using Pre-Trained LSTM Neural Networks
Biomimetics 2019, 4(2), 39; https://doi.org/10.3390/biomimetics4020039 - 28 May 2019
Cited by 6 | Viewed by 1532
Abstract
Several researchers have contemplated deep learning-based post-filters to increase the quality of statistical parametric speech synthesis, which perform a mapping of the synthetic speech to the natural speech, considering the different parameters separately and trying to reduce the gap between them. The Long [...] Read more.
Several researchers have contemplated deep learning-based post-filters to increase the quality of statistical parametric speech synthesis, which perform a mapping of the synthetic speech to the natural speech, considering the different parameters separately and trying to reduce the gap between them. The Long Short-term Memory (LSTM) Neural Networks have been applied successfully in this purpose, but there are still many aspects to improve in the results and in the process itself. In this paper, we introduce a new pre-training approach for the LSTM, with the objective of enhancing the quality of the synthesized speech, particularly in the spectrum, in a more efficient manner. Our approach begins with an auto-associative training of one LSTM network, which is used as an initialization for the post-filters. We show the advantages of this initialization for the enhancing of the Mel-Frequency Cepstral parameters of synthetic speech. Results show that the initialization succeeds in achieving better results in enhancing the statistical parametric speech spectrum in most cases when compared to the common random initialization approach of the networks. Full article
(This article belongs to the Special Issue Bioinspired Intelligence)
Show Figures

Figure 1

Other

Jump to: Research

Conference Report
2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI): Conference Report
Biomimetics 2019, 4(1), 9; https://doi.org/10.3390/biomimetics4010009 - 25 Jan 2019
Cited by 1 | Viewed by 1267
Abstract
The International Work Conference on Bioinspired Intelligence (IWOBI) is an annual event that comprises both an international peer-reviewed scientific conference and a set of workshops and other activities in order to foster the research abilities and expertise of young researchers in the field [...] Read more.
The International Work Conference on Bioinspired Intelligence (IWOBI) is an annual event that comprises both an international peer-reviewed scientific conference and a set of workshops and other activities in order to foster the research abilities and expertise of young researchers in the field of bioinspired intelligence. IWOBI 2018 has been characterized by a strong transdisciplinary component. The main conference themes were at the intersection between classical engineering disciplines and computer science, and the life and health sciences. This was motivated by the scientific environment that defines research that is being conducted in Costa Rica. Even though IWOBI is an international event, it was very important for the local organizing committee to focus on knowledge areas that were considered of special interest to Costa Rican researchers and to students looking to start their scientific careers. With such great expectations, IWOBI 2018 has been the first IWOBI conference in history to have parallel tracks. In addition to a regular track, a biocomputation and related techniques track was developed, as well as another one devoted to high-performance computing (HPC) systems applications for life and health sciences applications. Workshops were another important resource developed within IWOBI 2018. They were considered a very important tool in order to foster and train young researchers within the country and they are a very valuable chance to establish direct networking with elite researchers from different countries and research interests. IWOBI 2018 was the first IWOBI conference that implemented real and effective workshops. There were two workshops, one of them devoted to COPASI software and the other one focused on the use of the message passing interface (MPI) parallel programming library. Full article
(This article belongs to the Special Issue Bioinspired Intelligence)
Back to TopTop