mdh.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 82) Show all publications
Suero, M., Gassen, C. P., Mitic, D., Xiong, N. & Leon, M. (2020). A Deep Neural Network Model for Music Genre Recognition. In: Advances in Intelligent Systems and Computing, vol. 1074: . Paper presented at 15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019 (pp. 377-384). Springer
Open this publication in new window or tab >>A Deep Neural Network Model for Music Genre Recognition
Show others...
2020 (English)In: Advances in Intelligent Systems and Computing, vol. 1074, Springer , 2020, p. 377-384Conference paper, Published paper (Refereed)
Abstract [en]

Convolutional neural networks (CNNs) have become increasingly important to deal with many image processing and pattern recognition problems. In order to use CNNs in music genre recognition, spectrograms (visual representation of the spectrum of frequencies of a signal as it varies with time) are usually employed as inputs of the network. Yet some other approaches used music features for genre classification as well. In this paper we propose a new deep network model combining CNN with a simple multi-layer neural network for music genre classification. Since other features are taken into account in the multi-layer network, the combined deep neural network has shown better accuracy than each of the single models in the experiments (Code available at: https://github.com/risengnom/Music-Genre-Recognition.).

Place, publisher, year, edition, pages
Springer, 2020
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-46637 (URN)10.1007/978-3-030-32456-8_41 (DOI)2-s2.0-85077008252 (Scopus ID)9783030324551 (ISBN)
Conference
15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019
Available from: 2020-01-02 Created: 2020-01-02 Last updated: 2020-01-02Bibliographically approved
Holmberg, J. & Xiong, N. (2020). Online Feature Selection via Deep Reconstruction Network. In: Advances in Intelligent Systems and Computing: . Paper presented at 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019 (pp. 194-201). Springer, 1063
Open this publication in new window or tab >>Online Feature Selection via Deep Reconstruction Network
2020 (English)In: Advances in Intelligent Systems and Computing, Springer , 2020, Vol. 1063, p. 194-201Conference paper, Published paper (Refereed)
Abstract [en]

This paper addresses the feature selection problems in the setting of online learning of data streams. Typically this setting imposes restrictions on computational resources (memory, processing) as well as storage capacity, since instances of streaming data arrive with high speed and with no possibility to store data for later offline processing. Feature selection can be particularly beneficial here to selectively process parts of the data by reducing the data dimensionality. However selecting a subset of features may lead to permanently ruling out the possibilities of using discarded dimensions. This will cause a problem in the cases of feature drift in which data importance on individual dimensions changes with time. This paper proposes a new method of online feature selection to deal with drifting features in non-stationary data streams. The core of the proposed method lies in deep reconstruction networks that are continuously updated with incoming data instances. These networks can be used to not only detect the point of change with feature drift but also dynamically rank the importance of features for feature selection in an online manner. The efficacy of our work has been demonstrated by the results of experiments based on the MNIST database. 

Place, publisher, year, edition, pages
Springer, 2020
Series
Advances in Intelligent Systems and Computing, ISSN 21945357
Keywords
Data streams, Non-stationary, Online feature selection, Digital storage, Soft computing, Computational resources, Data stream, Feature selection problem, Individual dimensions, Nonstationary, Off-line processing, Reconstruction networks, Feature extraction
National Category
Bioinformatics (Computational Biology) Computer Sciences
Identifiers
urn:nbn:se:mdh:diva-46598 (URN)10.1007/978-3-030-31967-0_22 (DOI)2-s2.0-85076084151 (Scopus ID)9783030319663 (ISBN)
Conference
5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019
Available from: 2019-12-20 Created: 2019-12-20 Last updated: 2019-12-20Bibliographically approved
Andersson, T., Kihlberg, A., Sundström, A. & Xiong, N. (2020). Road Boundary Detection Using Ant Colony Optimization Algorithm. In: Advances in Intelligent Systems and Computing, Volume 1074: . Paper presented at 15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019 (pp. 409-416). Springer
Open this publication in new window or tab >>Road Boundary Detection Using Ant Colony Optimization Algorithm
2020 (English)In: Advances in Intelligent Systems and Computing, Volume 1074, Springer , 2020, p. 409-416Conference paper, Published paper (Refereed)
Abstract [en]

A common problem for autonomous vehicles is to define a coherent round boundary of unstructured roads. To solve this problem an evolutionary approach has been evaluated, by using a modified ant optimization algorithm to define a coherent road edge along the unstructured road in night conditions. The work presented in this paper involved pre-processing, perfecting the edges in an autonomous fashion and developing an algorithm to find the best candidates of starting positions for the ant colonies. All together these efforts enable ant colony optimization (ACO) to perform successfully in this application scenario. The experiment results show that the best paths well followed the edges and that the mid-points between the paths stayed centered on the road.

Place, publisher, year, edition, pages
Springer, 2020
National Category
Computer Systems
Identifiers
urn:nbn:se:mdh:diva-46638 (URN)10.1007/978-3-030-32456-8_44 (DOI)2-s2.0-85077006690 (Scopus ID)9783030324551 (ISBN)
Conference
15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019
Available from: 2020-01-02 Created: 2020-01-02 Last updated: 2020-01-02Bibliographically approved
Andersson, T., Kihlberg, A., Sundström, A. & Xiong, N. (2020). Road Boundary Detection Using Ant Colony Optimization Algorithm. In: Advances in Intelligent Systems and Computing, vol 1074: . Paper presented at 15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019 (pp. 409-416). Springer
Open this publication in new window or tab >>Road Boundary Detection Using Ant Colony Optimization Algorithm
2020 (English)In: Advances in Intelligent Systems and Computing, vol 1074, Springer , 2020, p. 409-416Conference paper, Published paper (Refereed)
Abstract [en]

A common problem for autonomous vehicles is to define a coherent round boundary of unstructured roads. To solve this problem an evolutionary approach has been evaluated, by using a modified ant optimization algorithm to define a coherent road edge along the unstructured road in night conditions. The work presented in this paper involved pre-processing, perfecting the edges in an autonomous fashion and developing an algorithm to find the best candidates of starting positions for the ant colonies. All together these efforts enable ant colony optimization (ACO) to perform successfully in this application scenario. The experiment results show that the best paths well followed the edges and that the mid-points between the paths stayed centered on the road.

Place, publisher, year, edition, pages
Springer, 2020
Keywords
Ant colony optimization, Autonomous vehicles, Lane detection
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:mdh:diva-46631 (URN)10.1007/978-3-030-32456-8_44 (DOI)2-s2.0-85077006690 (Scopus ID)9783030324551 (ISBN)
Conference
15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019; Kunming; China; 20 July 2019 through 22 July 2019
Available from: 2020-01-02 Created: 2020-01-02 Last updated: 2020-02-24Bibliographically approved
Leon, M., Xiong, N., Molina, D. & Herrera, F. (2019). A Novel Memetic Framework for Enhancing Differential Evolution Algorithms via Combination With Alopex Local Search. International Journal of Computational Intelligence Systems, 12(2), 795-808
Open this publication in new window or tab >>A Novel Memetic Framework for Enhancing Differential Evolution Algorithms via Combination With Alopex Local Search
2019 (English)In: International Journal of Computational Intelligence Systems, ISSN 1875-6891, E-ISSN 1875-6883, Vol. 12, no 2, p. 795-808Article in journal (Refereed) Published
Abstract [en]

Differential evolution (DE) represents a class of population-based optimization techniques that uses differences of vectors to search for optimal solutions in the search space. However, promising solutions/ regions are not adequately exploited by a traditional DE algorithm. Memetic computing has been popular in recent years to enhance the exploitation of global algorithms via incorporation of local search. This paper proposes a new memetic framework to enhance DE algorithms using Alopex Local Search (MFDEALS). The novelty of the proposed MFDEALS framework lies in that the behavior of exploitation (by Alopex local search) can be controlled based on the DE global exploration status (population diversity and search stage). Additionally, an adaptive parameter inside the Alopex local search enables smooth transition of its behavior from exploratory to exploitative during the search process. A study of the important components of MFDEALS shows that there is a synergy between them. MFDEALS has been integrated with both the canonical DE method and the adaptive DE algorithm L-SHADE, leading to the MDEALS and ML-SHADEALS algorithms, respectively. Both algorithms were tested on the benchmark functions from the IEEE CEC'2014 Conference. The experiment results show that Memetic Differential Evolution with Alopex Local Search (MDEALS) not only improves the original DE algorithm but also outperforms other memetic DE algorithms by obtaining better quality solutions. Further, the comparison between ML-SHADEALS and L-SHADE demonstrates that applying the MFDEALS framework with Alopex local search can significantly enhance the performance of L-SHADE. 

Place, publisher, year, edition, pages
ATLANTIS PRESS, 2019
Keywords
Differential evolution, L-SHADE, Memetic algorithm, Alopex, Local search, Optimization
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:mdh:diva-45267 (URN)10.2991/ijcis.d.190711.001 (DOI)000483992100029 ()2-s2.0-85073320189 (Scopus ID)
Available from: 2019-09-19 Created: 2019-09-19 Last updated: 2019-10-31Bibliographically approved
Tidare, J., Leon, M., Xiong, N. & Åstrand, E. (2019). Discriminating EEG spectral power related to mental imagery of closing and opening of hand. In: 2019 9TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER): . Paper presented at 9th IEEE/EMBS International Conference on Neural Engineering (NER), MAR 20-23, 2019, San Francisco, CA (pp. 307-310). IEEE
Open this publication in new window or tab >>Discriminating EEG spectral power related to mental imagery of closing and opening of hand
2019 (English)In: 2019 9TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER), IEEE , 2019, p. 307-310Conference paper, Published paper (Refereed)
Abstract [en]

ElectroEncephaloGram (EEG) spectral power has been extensively used to classify Mental Imagery (MI) of movements involving different body parts. However, there is an increasing need to enable classification of MI of movements within the same limb. In this work, EEG spectral power was recorded in seven subjects while they performed MI of closing (grip) and opening (extension of fingers) the hand. The EEG data was analyzed and the feasibility of classifying MI of the two movements were investigated using two different classification algorithms, a linear regression and a Convolutional Neural Network (CNN). Results show that only the CNN is able to significantly classify MI of opening and closing of the hand with an average classification accuracy of 60.4%. This indicates the presence of higher-order non-linear discriminatory information and demonstrates the potential of using CNN in classifying MI of same-limb movements.

Place, publisher, year, edition, pages
IEEE, 2019
Series
International IEEE EMBS Conference on Neural Engineering, ISSN 1948-3546
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-44330 (URN)10.1109/NER.2019.8717059 (DOI)000469933200077 ()2-s2.0-85066765799 (Scopus ID)978-1-5386-7921-0 (ISBN)
Conference
9th IEEE/EMBS International Conference on Neural Engineering (NER), MAR 20-23, 2019, San Francisco, CA
Available from: 2019-06-20 Created: 2019-06-20 Last updated: 2020-02-04Bibliographically approved
Leon, M., Ballesteros, J., Tidare, J., Xiong, N. & Åstrand, E. (2019). Feature Selection of EEG Oscillatory Activity Related to Motor Imagery Using a Hierarchical Genetic Algorithm. In: 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings: . Paper presented at 2019 IEEE Congress on Evolutionary Computation, CEC 2019, 10 June 2019 through 13 June 2019 (pp. 87-94). Institute of Electrical and Electronics Engineers Inc.
Open this publication in new window or tab >>Feature Selection of EEG Oscillatory Activity Related to Motor Imagery Using a Hierarchical Genetic Algorithm
Show others...
2019 (English)In: 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc. , 2019, p. 87-94Conference paper, Published paper (Refereed)
Abstract [en]

Motor Imagery (MI) classification from neural activity is thought to represent valuable information that can be provided as real-time feedback during rehabilitation after for example a stroke. Previous studies have suggested that MI induces partly subject-specific EEG activation patterns, suggesting that individualized classification models should be created. However, due to fatigue of the user, only a limited number of samples can be recorded and, for EEG recordings, each sample is often composed of a large number of features. This combination leads to an undesirable input data set for classification. In order to overcome this constraint, we propose a new methodology to create and select features from the EEG signal in two steps. First, the input data is divided into different windows to reduce the cardinality of the input. Secondly, a Hierarchical Genetic Algorithm is used to select relevant features using a novel fitness function which combines the data reduction with a correlation feature selection measure. The methodology has been tested on EEG oscillatory activity recorded from 6 healthy volunteers while they performed an MI task. Results have successfully proven that a classification above 75% can be obtained in a restrictive amount of time (0.02 s), reducing the number of features by almost 90%.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers Inc., 2019
Keywords
EEG Signal, Hierarchical Genetic Algorithm, Motor Imagery, Classification (of information), Data reduction, Genetic algorithms, Input output programs, Neurons, Activation patterns, Classification models, Correlation features, EEG signals, Healthy volunteers, Real-time feedback, Feature extraction
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:mdh:diva-46543 (URN)10.1109/CEC.2019.8789948 (DOI)000502087100013 ()2-s2.0-85071317681 (Scopus ID)9781728121536 (ISBN)
Conference
2019 IEEE Congress on Evolutionary Computation, CEC 2019, 10 June 2019 through 13 June 2019
Available from: 2019-12-17 Created: 2019-12-17 Last updated: 2020-01-02Bibliographically approved
Zhou, Y., Li, S. & Xiong, N. (2019). Improved Vine Copula-Based Dependence Description for Multivariate Process Monitoring Based on Ensemble Learning. Industrial & Engineering Chemistry Research, 58(9), 3782-3796
Open this publication in new window or tab >>Improved Vine Copula-Based Dependence Description for Multivariate Process Monitoring Based on Ensemble Learning
2019 (English)In: Industrial & Engineering Chemistry Research, ISSN 0888-5885, E-ISSN 1520-5045, Vol. 58, no 9, p. 3782-3796Article in journal (Refereed) Published
Abstract [en]

This paper proposes a boosting vine copula-based dependence description (BVCDD) method for multivariate and multimode process monitoring. The BVCDD aims to improve the standard vine copula-based dependence description (VCDD) method by establishing an ensemble of submodels from sample directions based on a boosting strategy. The generalized Bayesian inference-based probability (GBIP) index is introduced to assess the degrees of a VCDD model (submodel) to depict different samples, which means how likely an observation is under the probabilistic model for the system. Every sample is weighted individually according to the depiction degree. The weights are then used to choose a certain number of samples for each succeeding submodel. In this way, the samples with large error in the preceding model can be selected for training the next submodel. Moreover, the number of submodels as well as the number of training samples chosen for every submodel are determined adaptively in the ensemble learning process. The proposed BVCDD method can not only solve weak sample problems but also remove redundant information in samples. To examine the performance, empirical evaluations have been conducted to compare the BVCDD method with some other state-of-the-art methods in a numerical example, the Tennessee Eastman (TE) process, and an acetic acid dehydration process. The results show that the developed BVCDD models are superior to those obtained by the counterparts on weak samples in both accuracy and stability. 

Place, publisher, year, edition, pages
American Chemical Society, 2019
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
urn:nbn:se:mdh:diva-42943 (URN)10.1021/acs.iecr.8b04081 (DOI)000460996700022 ()2-s2.0-85062615381 (Scopus ID)
Available from: 2019-03-22 Created: 2019-03-22 Last updated: 2019-03-29Bibliographically approved
Leon, M. & Xiong, N. (2018). Enhancing Adaptive Differential Evolution Algorithms with Rank-Based Mutation Adaptation. In: 2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC): . Paper presented at IEEE Congress on Evolutionary Computation (IEEE CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI) (pp. 103-109). IEEE
Open this publication in new window or tab >>Enhancing Adaptive Differential Evolution Algorithms with Rank-Based Mutation Adaptation
2018 (English)In: 2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), IEEE , 2018, p. 103-109Conference paper, Published paper (Refereed)
Abstract [en]

Differential evolution has many mutation strategies which are problem dependent. Some Adaptive Differential Evolution techniques have been proposed tackling this problem. But therein all individuals are treated equally without taking into account how good these solutions are. In this paper, a new method called Ranked-based Mutation Adaptation (RAM) is proposed, which takes into consideration the ranking of an individual in the whole population. This method will assign different probabilities of choosing different mutation strategies to different groups in which the population is divided. RAM has been integrated into several well-known adaptive differential evolution algorithms and its performance has been tested on the benchmark suit proposed in CEC2014. The experimental results shows the use of RAM can produce generally better quality solutions than the original adaptive algorithms.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Evolutionary Algorithm, Differential Evolution, Mutation strategy, Adaptation
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-41825 (URN)10.1109/CEC.2018.8477879 (DOI)000451175500015 ()2-s2.0-85056286107 (Scopus ID)
Conference
IEEE Congress on Evolutionary Computation (IEEE CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)
Available from: 2018-12-27 Created: 2018-12-27 Last updated: 2020-01-10Bibliographically approved
Ramos, J., Leon, M. & Xiong, N. (2018). MPADE: An Improved Adaptive Multi-Population Differential Evolution Algorithm Based on JADE. In: 2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC): . Paper presented at IEEE Congress on Evolutionary Computation (IEEE CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI) (pp. 1139-1146). IEEE
Open this publication in new window or tab >>MPADE: An Improved Adaptive Multi-Population Differential Evolution Algorithm Based on JADE
2018 (English)In: 2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), IEEE , 2018, p. 1139-1146Conference paper, Published paper (Refereed)
Abstract [en]

JADE is an state-of-the-art adaptive differential evolution algorithm which implements "DE/current-to-pbest" as its mutation strategy, adapts its mutation factor and crossover rate, and uses an optional external archive to keep track of potential removed individuals in previous generations. This paper proposes MPADE, which extends JADE by using a multi-populated approach to solve high dimensional real-parameter optimization problems. This mechanism helps preventing the two well-known problems affecting the differential evolution algorithm performance, which are premature convergence and stagnation. The algorithm was tested using the benchmark functions in IEEE Congress on Evolutionary Computation 2014 test suite. MPADE was compared using Wilcoxon test to JADE algorithm and with other state-of-the-art algorithms that either use a multi-population approach or adapt their parameters. The experimental results show that the proposed new algorithm improves significantly its precursor and it is also suggested that other state-of-the-art algorithms could benefit from the multi-populated based approach.

Place, publisher, year, edition, pages
IEEE, 2018
Keywords
Differential evolution, multi-population, coarse-grained parallel, population topology, adaptive parameter, global optimization, evolutionary optimization
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:mdh:diva-41826 (URN)10.1109/CEC.2018.8477764 (DOI)000451175500146 ()2-s2.0-85056280928 (Scopus ID)
Conference
IEEE Congress on Evolutionary Computation (IEEE CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)
Available from: 2018-12-27 Created: 2018-12-27 Last updated: 2020-01-10Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-9857-4317

Search in DiVA

Show all publications