All Outputs (45)

A lightweight deep learning-based approach for concrete crack characterization using acoustic emission signals. (2021)
Journal Article
HABIB, M.A., HASAN, M.J. and KIM, J.-M. 2021. A lightweight deep learning-based approach for concrete crack characterization using acoustic emission signals. IEEE access [online], 9, pages 104029-104050. Available from: https://doi.org/10.1109/ACCESS.2021.3099124

This paper proposes an acoustic emission (AE) based automated crack characterization method for reinforced concrete (RC) beams using a memory efficient lightweight convolutional neural network named SqueezeNet. The proposed method also includes a sig... Read More about A lightweight deep learning-based approach for concrete crack characterization using acoustic emission signals..

一种基于模糊成像机理的QR码图像快速盲复原方法. (2021)
Journal Article
CHEN, R., ZHENG, Z., ZHAO, H., REN, J. and TAN, H. 2021. 一种基于模糊成像机理的QR 码图像快速 盲复原方法. = [Fast blind restoration of QR code images based on blurred imaging mechanism]. Guangzi xuebao/Acta photonica sinica [online], 50(7), article 0710003. Available from: https://doi.org/10.3788/gzxb20215007.0710003

A fast blind restoration method of QR code images was proposed based on a blurred imaging mechanism. On the basis of the research on the centroid invariance of the blurred imaging diffuse light spots, the circular finder pattern is designed. When the... Read More about 一种基于模糊成像机理的QR码图像快速盲复原方法..

Deep recurrent neural networks with attention mechanisms for respiratory anomaly classification. (2021)
Conference Proceeding
WALL, C., ZHANG, L., YU, Y. and MISTRY, K. 2021. Deep recurrent neural networks with attention mechanisms for respiratory anomaly classification. In Proceedings of 2021 International joint conference on neural networks (IJCNN 2021), 18-22 July 2021, [virtual conference]. Piscataway: IEEE [online], article 9533966. Available from: https://doi.org/10.1109/IJCNN52387.2021.9533966

In recent years, a variety of deep learning techniques and methods have been adopted to provide AI solutions to issues within the medical field, with one specific area being audio-based classification of medical datasets. This research aims to create... Read More about Deep recurrent neural networks with attention mechanisms for respiratory anomaly classification..

An interactive evolution strategy based deep convolutional generative adversarial network for 2D video game level procedural content generation. (2021)
Conference Proceeding
JIANG, M. and ZHANG, L. 2021. An interactive evolution strategy based deep convolutional generative adversarial network for 2D video game level procedural content generation. In Proceedings of 2021 International joint conference on neural networks (IJCNN 2021), 18-22 July 2021, [virtual conference]. Piscataway: IEEE [online], article 9533847. Available from: https://doi.org/10.1109/IJCNN52387.2021.9533847

The generation of desirable video game contents has been a challenge of games level design and production. In this research, we propose a game player flow experience driven interactive latent variable evolution strategy incorporated with a Deep Convo... Read More about An interactive evolution strategy based deep convolutional generative adversarial network for 2D video game level procedural content generation..

Optimising the introduction of connected and autonomous vehicles in a public transport system using macro-level mobility simulations and evolutionary algorithms. (2021)
Presentation / Conference
HAN, K., CHRISTIE, L.A., ZAVOIANU, A.-C. and MCCALL, J. 2021. Optimising the introduction of connected and autonomous vehicles in a public transport system using macro-level mobility simulations and evolutionary algorithms. Presented at 2021 Genetic and evolutionary computation conference (GECCO 2021), 10-14 July 2021, [virtual conference].

The past five years have seen a rapid development of plans and test pilots aimed at introducing connected and autonomous vehicles (CAVs) in public transport systems around the world. Using a real-world scenario from the Leeds Metropolitan Area as a c... Read More about Optimising the introduction of connected and autonomous vehicles in a public transport system using macro-level mobility simulations and evolutionary algorithms..

Towards the landscape rotation as a perturbation strategy on the quadratic assignment problem. (2021)
Conference Proceeding
ALZA, J., BARTLETT, M., CEBERIO, J. and MCCALL, J. 2021. Towards the landscape rotation as a perturbation strategy on the quadratic assignment problem. In Chicano, F. (ed.) GECCO '21: proceedings of 2021 Genetic and evolutionary computation conference companion, 10-14 July 2021, [virtual conference]. New York: ACM [online], pages 1405-1413. Available from: https://doi.org/10.1145/3449726.3463139

Recent work in combinatorial optimisation have demonstrated that neighbouring solutions of a local optima may belong to more favourable attraction basins. In this sense, the perturbation strategy plays a critical role on local search based algorithms... Read More about Towards the landscape rotation as a perturbation strategy on the quadratic assignment problem..

Fast blind deblurring of QR code images based on adaptive scale control. (2021)
Journal Article
CHEN, R., ZHENG, Z., PAN, J., YU, Y., ZHAO, H. and REN, J. 2022. Fast blind deblurring of QR code images based on adaptive scale control. Mobile networks and applications [online], 26(6), pages 2472-2487. Available from: https://doi.org/10.1007/s11036-021-01780-y

With the development of 5G technology, the short delay requirements of commercialization and large amounts of data change our lifestyle day-to-day. In this background, this paper proposes a fast blind deblurring algorithm for QR code images, which ma... Read More about Fast blind deblurring of QR code images based on adaptive scale control..

Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation. (2021)
Conference Proceeding
DANG, T., NGUYEN, T.T., MORENO-GARCIA, C.F., ELYAN, E. and MCCALL, J. 2021. Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation. In Proceeding of 2021 IEEE (Institute of electrical and electronics engineers) Congress on evolutionary computation (CEC 2021), 28 June - 1 July 2021, Kraków, Poland : [virtual conference]. Piscataway: IEEE [online], pages 744-751. Available from: https://doi.org/10.1109/CEC45853.2021.9504929

In recent years, deep learning has rapidly become a method of choice for segmentation of medical images. Deep neural architectures such as UNet and FPN have achieved high performances on many medical datasets. However, medical image analysis algorith... Read More about Weighted ensemble of deep learning models based on comprehensive learning particle swarm optimization for medical image segmentation..

Landscape features and automated algorithm selection for multi-objective interpolated continuous optimisation problems. (2021)
Conference Proceeding
LIEFOOGHE, A., VEREL, S., LACROIX, B., ZĂVOIANU, A.-C. and MCCALL, J. 2021. Landscape features and automated algorithm selection for multi-objective interpolated continuous optimisation problems. In Chicano, F. (ed) Proceedings of 2021 Genetic and evolutionary computation conference (GECCO 2021), 10-14 July 2021, [virtual conference]. New York: ACM [online], pages 421-429. Available from: https://doi.org/10.1145/3449639.3459353

In this paper, we demonstrate the application of features from landscape analysis, initially proposed for multi-objective combinatorial optimisation, to a benchmark set of 1 200 randomly-generated multiobjective interpolated continuous optimisation p... Read More about Landscape features and automated algorithm selection for multi-objective interpolated continuous optimisation problems..

Weighted ensemble of gross error detection methods based on particle swarm optimization. (2021)
Conference Proceeding
DOBOS, D., NGUYEN, T.T., MCCALL, J., WILSON, A., STOCKTON, P. and CORBETT, H. 2021. Weighted ensemble of gross error detection methods based on particle swarm optimization. In Chicano, F. (ed) Proceedings of the 2021 Genetic and evolutionary computation conference (GECCO 2021), 10-14 July 2021, [virtual conference]. New York: ACM [online], pages 307-308. Available from: https://doi.org/10.1145/3449726.3459415

Gross errors, a kind of non-random error caused by process disturbances or leaks, can make reconciled estimates can be very inaccurate and even infeasible. Detecting gross errors thus prevents financial loss from incorrectly accounting and also ident... Read More about Weighted ensemble of gross error detection methods based on particle swarm optimization..

SLSNet: skin lesion segmentation using a lightweight generative adversarial network. (2021)
Journal Article
SARKER, M.M.K., RASHWAN, H.A., AKRAM, F., SINGH, V.K., BANU, S.F., CHOWDHURY, F.U.H., CHOUDHURY, K.A., CHAMBON, S., RADEVA, P., PUIG, D. and ABDEL-NASSER, M. 2021. SLSNet: skin lesion segmentation using a lightweight generative adversarial network. Expert systems with applications [online], 183, article 115433. Available from: https://doi.org/10.1016/j.eswa.2021.115433

The determination of precise skin lesion boundaries in dermoscopic images using automated methods faces many challenges, most importantly, the presence of hair, inconspicuous lesion edges and low contrast in dermoscopic images, and variability in the... Read More about SLSNet: skin lesion segmentation using a lightweight generative adversarial network..

Fast restoration for out-of-focus blurred images of QR code with edge prior information via image sensing. (2021)
Journal Article
CHEN, R., ZHENG, Z., YU, Y., ZHAO, H., REN, J. and TAN, H.-Z. 2021. Fast restoration for out-of-focus blurred images of QR code with edge prior information via image sensing. IEEE sensors journal [online], 21(16), article 103048, pages 18222-18236. Available from: https://doi.org/10.1109/JSEN.2021.3085568

Out-of-focus blurring of the QR code is very common in mobile Internet systems, which often causes failure of authentication as a result of a misreading of the information hence adversely affects the operation of the system. To tackle this difficulty... Read More about Fast restoration for out-of-focus blurred images of QR code with edge prior information via image sensing..

An explainable AI-based fault diagnosis model for bearings. (2021)
Journal Article
HASAN, M.J., SOHAIB, M. and KIM, J.-M. 2021. An explainable AI-based fault diagnosis model for bearings. Sensors [online], 21(12): sensing technologies for fault diagnostics and prognosis, article 4070. Available from: https://doi.org/10.3390/s21124070

In this paper, an explainable AI-based fault diagnosis model for bearings is proposed with five stages, i.e., (1) a data preprocessing method based on the Stockwell Transformation Coefficient (STC) is proposed to analyze the vibration signals for var... Read More about An explainable AI-based fault diagnosis model for bearings..

Novel gumbel-softmax trick enabled concrete autoencoder with entropy constraints for unsupervised hyperspectral band selection. (2021)
Journal Article
SUN, H., REN, J., ZHAO, H., YUEN, P. and TSCHANNERL, J. 2022. Novel gumbel-softmax trick enabled concrete autoencoder with entropy constraints for unsupervised hyperspectral band selection. IEEE transactions on geoscience and remote sensing [online], 60, article 5506413. Available from: https://doi.org/10.1109/TGRS.2021.3075663

As an important topic in hyperspectral image (HSI) analysis, band selection has attracted increasing attention in the last two decades for dimensionality reduction in HSI. With the great success of deep learning (DL)-based models recently, a robust u... Read More about Novel gumbel-softmax trick enabled concrete autoencoder with entropy constraints for unsupervised hyperspectral band selection..

Non-deterministic solvers and explainable AI through trajectory mining. (2021)
Conference Proceeding
FYVIE, M., MCCALL, J.A.W. and CHRISTIE, L.A. 2021. Non-deterministic solvers and explainable AI through trajectory mining. In Martin, K., Wiratunga, N. and Wijekoon, A. (eds.) SICSA XAI workshop 2021: proceedings of 2021 SICSA (Scottish Informatics and Computer Science Alliance) eXplainable artificial intelligence workshop (SICSA XAI 2021), 1st June 2021, [virtual conference]. CEUR workshop proceedings, 2894. Aachen: CEUR-WS [online], session 4, pages 75-78. Available from: http://ceur-ws.org/Vol-2894/poster2.pdf

Traditional methods of creating explanations from complex systems involving the use of AI have resulted in a wide variety of tools available to users to generate explanations regarding algorithm and network designs. This however has traditionally bee... Read More about Non-deterministic solvers and explainable AI through trajectory mining..

Nondestructive phenolic compounds measurement and origin discrimination of peated barley malt using near-infrared hyperspectral imagery and machine learning. (2021)
Journal Article
YAN, Y., REN, J., TSCHANNERL, J., ZHAO, H., HARRISON, B. and JACK, F. 2021. Nondestructive phenolic compounds measurement and origin discrimination of peated barley malt using near-infrared hyperspectral imagery and machine learning. IEEE transactions on instrumentation and measurement [online], 70, article 5010715. Available from: https://doi.org/10.1109/TIM.2021.3082274

Quantifying phenolic compound in peated barley malt and discriminating its origin are essential to maintain the aroma of high-quality Scottish whisky during the manufacturing process. The content of the total phenol varies in peated barley malts, whi... Read More about Nondestructive phenolic compounds measurement and origin discrimination of peated barley malt using near-infrared hyperspectral imagery and machine learning..

KonVid-150k: a dataset for no-reference video quality assessment of videos in-the-wild. (2021)
Journal Article
GÖTZ-HAHN, F., HOSU, V., LIN, H. and SAUPE, D. 2021. KonVid-150k: a dataset for no-reference video quality assessment of videos in-the-wild. IEEE access [online], 9, pages 72139-72160. Available from: https://doi.org/10.1109/access.2021.3077642

Video quality assessment (VQA) methods focus on particular degradation types, usually artificially induced on a small set of reference videos. Hence, most traditional VQA methods under-perform in-the-wild. Deep learning approaches have had limited su... Read More about KonVid-150k: a dataset for no-reference video quality assessment of videos in-the-wild..

Modeling and dynamic analysis of spiral bevel gear coupled system of intermediate and tail gearboxes in a helicopter. (2021)
Journal Article
ZHU, H., CHEN, W., ZHU, R., ZHANG, L., FU, B. and LU, X. 2021. Modeling and dynamic analysis of spiral bevel gear coupled system of intermediate and tail gearboxes in a helicopter. Proceedings of the Institution of Mechanical Engineers, part C: journal of mechanical engineering science [online], 235(22), pages 5975-5993. Available from: https://doi.org/10.1177/0954406221992798

The coupled dynamic model of the intermediate and tail gearboxes’ spiral bevel gear-oblique tail shaft-laminated membrane coupling was established by employing the hybrid modeling method of finite element and lumped mass. Among them, the dynamic equa... Read More about Modeling and dynamic analysis of spiral bevel gear coupled system of intermediate and tail gearboxes in a helicopter..

Two layer ensemble of deep learning models for medical image segmentation. [Preprint] (2021)
Working Paper
DANG, T., NGUYEN, T.T., MCCALL, J., ELYAN, E. and MORENO-GARCÍA, C.F. 2021. Two layer ensemble of deep learning models for medical image segmentation. arXiv [online]. Available from: https://doi.org/10.48550/arXiv.2104.04809

In recent years, deep learning has rapidly become a method of choice for the segmentation of medical images. Deep Neural Network (DNN) architectures such as UNet have achieved state-of-the-art results on many medical datasets. To further improve the... Read More about Two layer ensemble of deep learning models for medical image segmentation. [Preprint].

VEGAS: a variable length-based genetic algorithm for ensemble selection in deep ensemble learning. (2021)
Conference Proceeding
HAN, K., PHAM, T., VU, T.H., DANG, T., MCCALL, J. and NGUYEN, T.T. 2021. VEGAS: a variable length-based genetic algorithm for ensemble selection in deep ensemble learning. In Nguyen, N.T., Chittayasothorn, S., Niyato, D. and Trawiński, B. (eds.) Intelligent information and database systems: proceedings of the 13th Asian conference on intelligent information and database systems 2021 (ACCIIDS 2021), 7-10 April 2021, [virtual conference]. Lecture Notes in Computer Science, 12672. Cham: Springer [online], pages 168–180. Available from: https://doi.org/10.1007/978-3-030-73280-6_14

In this study, we introduce an ensemble selection method for deep ensemble systems called VEGAS. The deep ensemble models include multiple layers of the ensemble of classifiers (EoC). At each layer, we train the EoC and generates training data for th... Read More about VEGAS: a variable length-based genetic algorithm for ensemble selection in deep ensemble learning..