Skip to content

Dr Mario Gongora

Job: Principal Lecturer

Faculty: Technology

School/department: School of Computer Science and Informatics

Research group(s): Centre for Computational Intelligence

Address: De Montfort University, The Gateway, Leicester, LE1 9BH

T: +44 (0)116 207 8226




Personal profile

Dr. Gongora is a Principal Lecturer in the Department of Informatics, Faculty of Technology at De Montfort University.  He got his MSc and PhD from the University of Warwick (UK).  He is part of the Centre for Computational Intelligence (CCI), and his research includes the application of Artificial Intelligence techniques to the identification, modelling, simulation and control of complex systems.  His expertise is mainly in using evolutionary computing and biologically inspired methods for this purpose.  He has ongoing projects in this area, mainly applied to analysis and modelling of complex systems and behaviour-based processes as well as in the control and decision making for autonomous systems.

Dr. Gongora also works in close contact with industry, applying his research results in the analysis of consumer behaviour and other complex industrial processes.  He has an active role in the Faculty's consultancy activities, taking the expertise from the University to Industry. 

Research group affiliations

Centre for Computational Intelligence (CCI) (Deputy Director).

Publications and outputs 

  • Fuzzy convolutional deep-learning model to estimate the operational risk capital using multi-source risk events
    Fuzzy convolutional deep-learning model to estimate the operational risk capital using multi-source risk events Peña, Alejandro; Patiño, Alejandro; Chiclana, Francisco; Caraffini, Fabio; Gongora, Mario Augusto; Gonzalez-Ruiz, Juan David; Eduardo, Duque-Grisales Operational Risk (OR) is usually caused by losses due to human errors, inadequate or defective internal processes, system failures or external events that affect an organization. According to the Basel II agreement, OR is defined by seven risk events: internal fraud, external fraud, labour relations, clients, damage to fixed assets, technological failures and failures in the execution & administration of processes. However, due to the large amount of qualitative information, the uncertainty and the low frequency at which these risk events are generated in an organization, their modeling is still a technological challenge. This paper takes up this challenge and presents a fuzzy convolutional deep-learning model to estimate, based on the Basel III recommendations, the ORLoss Component(OR-LC) in an organization. The proposed model integrates qualitative information as linguistic random variables, as well as risk events data from different sources using multi-dimensional fuzzy credibility concepts. The results show the stability of the proposed model with respect to the OR-LC estimation from both structural and dimensional point of views, making it an ideal tool for modeling OR from the perspective of: (a) the regulators (Basel Committee on Banking Supervision) by allowing the integration of experts’ criteria into the OR-LC; (b) the insurers by allowing the integration of risk events from different sources; and (c) organizations and financial entities by allowing the a priori evaluation of the OR-LC of new financial products based on technological platforms and electronic channels.
  • Deep Clustering for Metagenomics
    Deep Clustering for Metagenomics Gongora, Mario Augusto Metagenomics is an area that is supported by modern next generation sequencing technology, which investigates microorganisms obtained directly from environmental samples, without the need to isolate them. This type of sequencing results in a large number of DNA fragments from different organisms. Thus, the challenge consists in identifying groups of DNA sequences that belong to the same organism. The use of supervised methods for solving this problem is limited, despite the fact that large databases of species sequences are available, by the small number of species that are known. Additionally, by the required computational processing time to analyse segments against species sequences. In order to overcome these problems, a binning process can be used for the reconstruction and identification of a set of metagenomic fragments. The binning process serves as a step of pre-processing to join fragments into groups of the same taxonomic levels. In this work, we propose the application of a clustering model, with a feature extraction process that uses an autoencoder neural network. For the clustering a k-means is used that begins with a k-value which is large enough to obtain very pure clusters. These are reduced through a process of combining various distance functions. The results show that the proposed method outperforms the k-means and other classical methods of feature extraction such as PCA, obtaining 90% of purity.
  • A Robust Decision-Making Framework Based on Collaborative Agents
    A Robust Decision-Making Framework Based on Collaborative Agents Florez-Lozano, Johana; Caraffini, Fabio; Carlos, Parra; Gongora, Mario Augusto Making decisions under uncertainty is very challenging but necessary as most real-world scenarios are plagued by disturbances that can be generated internally, by the hardware itself, or externally, by the environment. Hence, we propose a general decision-making framework which can be adapted to optimally address the most heterogeneous real-world domains without being significantly affected by undesired disturbances. Our paper presents a multi-agent based structure in which agents are capable of individual decision-making but also interact to perform subsequent, and more robust, collaborative decisionmaking processes. The complexity of each software agent can be kept quite low without deterioration of the performance since an intelligent and robust-to-uncertainty decision-making behaviour arises when their locally produced measures of support are shared and exploited collaboratively. We show that by equipping agents with classic computational intelligence techniques, to extract features and generate measures of support, complex hybrid multi-agent software structures capable of handling uncertainty can be easily designed. The resulting multi-agent systems generated with this approach are based on a two-phases decision-making methodology which first runs parallel local decision making processes to then aggregate the corresponding outputs to improve upon the accuracy of the system. To highlight the potential of this approach, we provided multiple implementations of the general framework and compared them over four different application scenarios. Results are promising and show that having a second collaborative decisionmaking process is always beneficial. Open access article. This research received financial support from the internally funded DMU GCRF2020 project "Collaborative methodology for enhancing sustainability in rural communities and the use of land". Project webpages:
  • Training Data Set Assessment for Decision-Making in a Multiagent Landmine Detection Platform
    Training Data Set Assessment for Decision-Making in a Multiagent Landmine Detection Platform Florez-Lozano, Johana; Caraffini, Fabio; Parra, Carlos; Gongora, Mario Augusto Real-world problems such as landmine detection require multiple sources of information to reduce the uncertainty of decision-making. A novel approach to solve these problems includes distributed systems, as presented in this work based on hardware and software multi-agent systems. To achieve a high rate of landmine detection, we evaluate the performance of a trained system over the distribution of samples between training and validation sets. Additionally, a general explanation of the data set is provided, presenting the samples gathered by a cooperative multi-agent system developed for detecting improvised explosive devices. The results show that input samples affect the performance of the output decisions, and a decision-making system can be less sensitive to sensor noise with intelligent systems obtained from a diverse and suitably organised training set.
  • A Multi-Agent System for Modelling the Spread of Lethal Wilt in Oil-Palm Plantations
    A Multi-Agent System for Modelling the Spread of Lethal Wilt in Oil-Palm Plantations Fahy, Conor; Caraffini, Fabio; Gongora, Mario Augusto Lethal Wilt (Marchitez Letal) is a disease which affects Elaeis Guineensis, a plant used in the production of palm oil. The disease is increasingly common but the spatial dynamics of the infection spread remain poorly understood. It is particularly dangerous due to the speed at which it spreads and the speed at which infected plants show symptoms and die. Early identification, or even better, accurate prediction of areas at high risk of infection can slow the spread of the disease and limit crop waste. This study is based on data collected over a five-year period from an affected plantation in Colombia. The aim of the study is to analyse the collected data to better understand how the disease spreads and then to model the behaviour. Based on insights from the initial analysis a multi-agent-based system is proposed to model the pattern of infection. The model is comprised of two steps; first Kernel Density Estimation is used to create an estimation of the distribution from which newly infected plants are drawn and this density estimation is then used to direct agents on a biased-walk of the surrounding areas. Results show that the model can approximate the behaviour of the disease and can predict areas which are at high risk of future infection.
  • Shallow Buried Improvised Explosive Device Detection Via Convolutional Neural Networks
    Shallow Buried Improvised Explosive Device Detection Via Convolutional Neural Networks Colreavy-Donnelly, S.; Caraffini, Fabio; Kuhn, Stefan; Gongora, Mario Augusto; Florez-Lozano, Johana; Parra, Carlos The issue of detecting improvised explosive devices, henceforth IEDs, in rural or built-up urban environments is a persistent and serious concern for governments in the developing world. In many cases, such devices are plastic, or varied metallic objects containing rudimentary explosives, which are not visible to the naked eye and are difficult to detect autonomously. The most effective strategy for detecting land mines also happens to be the most dangerous. This paper intends to leverage the use of a Convolutional Neural Network (CNN) to aid in the discovery of such IEDs. As part of a related project, an autonomous sensor array was used to detect the devices in terrains too hazardous for a human to survey. This paper presents a CNN and its training methodology, suitable to make use of the sensor system. This convolutional neural network can accurately distinguish between a potential IED and surrounding undergrowth and natural features of the environment in real-time. The training methodology enabled the CNN to successfully recognise the IEDs with an accuracy of 98.7%, in well-lit conditions. The results are evaluated against other convolutional neural systems as well as against a deterministic algorithm, showing that the proposed CNN outperforms its competitors including the deterministic method. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
  • Oil Palm Detection via Deep Transfer Learning
    Oil Palm Detection via Deep Transfer Learning Bonet, Isis; Caraffini, Fabio; Pena, Alejandro; Puerta, Alejandro; Gongora, Mario Augusto This article presents an intelligent system using deep learning algorithms and the transfer learning approach to detect oil palm units in multispectral photographs taken with unmanned aerial vehicles. Two main contributions come from this piece of research. First, a dataset for oil palm units detection is carefully produced and made available online. Although being tailored to the palm detection problem, the latter has general validity and can be used for any classification application. Second, we designed and evaluated a state-of-the-art detection system, which uses a convolutional neural network to extract meaningful features, and a classifier trained with the images from the proposed dataset. Results show outstanding effectiveness with an accuracy peak of 99.5% and a precision of 99.8%. Using different images for validation taken from different altitudes the model reached an accuracy of 97.5% and a precision of 98.3%. Hence, the proposed approach is highly applicable in the field of precision agriculture.
  • Cooperative and distributed decision-making in a multi-agent perception system for improvised land mines detection
    Cooperative and distributed decision-making in a multi-agent perception system for improvised land mines detection Florez-Lozano, Johana; Caraffini, Fabio; Parra, Carlos; Gongora, Mario Augusto This work presents a novel intelligent system designed using a multi-agent hardware platform to detect improvised explosive devices concealed in the ground. Each agent is equipped with a different sensor, (i.e. a ground-penetrating radar, a thermal sensor and three cameras each covering a different spectrum) and processes dedicated AI decision-making capabilities. The proposed system has a unique hardware structure, with a distributed design and effective selection of sensors, and a novel multi-phase and cooperative decision-making framework. Agents operate independently via a customised logic adjusting their sensor positions - to achieve optimal acquisition; performing a preliminary “local decision-making” - to classify buried objects; sharing information with the other agents. Once sufficient information is shared by the agents, a collaborative behaviour emerges in the so-called “cooperative decision-making” process, which performs the final detection. In this paper, 120 variations of the proposed system, obtained by combining both classic aggregation operators as well as advanced neural and fuzzy systems, are presented, tested and evaluated. Results show a good detection accuracy and robustness to environmental and data sets changes, in particular when the cooperative decision-making is implemented with the neuroevolution paradigm. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link
  • Stochastic logistic fuzzy maps for the construction of integrated multirates scenarios in the financing of infrastructure projects
    Stochastic logistic fuzzy maps for the construction of integrated multirates scenarios in the financing of infrastructure projects Gonzalez-Ruiz, Juan David; Peña, Alejandro; Duque, Eduardo Alexander; Patiño, Alejandro; Chiclana, Francisco; Gongora, Mario Augusto In general, the development of economic infrastructure systems requires a behavioural comprehensive analysis of different financial variables or rates to establish its long-term success with regards to the Equity Internal Rate of Return (EIRR) expectation. For this reason, several financial organizations have developed economic scenarios supported by computational techniques and models to identify the evolution of these financial rates. However, these models and techniques have shown a series of limitations with regard to the financial management process and its impact on EIRR over time. To address these limitations in an inclusive way, researchers have developed different approaches and methodologies focused on the development of financial models using stochastic simulation methods and computational intelligence techniques. This paper proposes a Stochastic Fuzzy Logistic Model (S-FLM) inspired by a Fuzzy Cognitive Map (FCM) structure to model financial scenarios. Where the input consists in financial rates that are characterized as linguistic rates through a series of adaptive logistic functions. The stochastic process that explains the behaviour of the financial rates over time and their partial effects on EIRR is based on a Monte Carlo sampling process carried out on the fuzzy sets that characterize each linguistic rate. The S-FLM was evaluated by applying three financing scenarios to an airport infrastructure system (pessimistic, moderate/base, optimistic), where it was possible to show the impact of different linguistic rates on the EIRR. The behaviour of the S-FLM was validated using three different models: (1) a financial management tool; (2) a general FCM without pre-loaded causalities among the variables; and (3) a Statistical S-FLM model (S-FLMS), where the causalities between the concepts or rates were obtained as a result of an independent effects analysis applying a cross modelling between variables and by using a statistical multi-linear model (statistical significance level) and a multi-linear neural model (MADALINE). The results achieved by the S-FLM show a higher EIRR than expected for each scenario. This was possible due to the incorporation of an adaptive multi-linear causality matrix and a fuzzy credibility matrix into its structure. This allowed to stabilize the effects of the financial variables or rates on the EIRR throughout a financing period. Thus, the S-FLM can be considered as a tool to model dynamic financial scenarios in different knowledge areas in a comprehensive manner. This way, overcoming the limitations imposed by the traditional computational models used to design these financial scenarios. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
  • Validation of convolutional layers in deep learning models to identify patterns in multispectral images: Identification of palm units
    Validation of convolutional layers in deep learning models to identify patterns in multispectral images: Identification of palm units Peña, Alejandro; Bonet, Isis; Manzur, Diego; Gongora, Mario Augusto; Caraffini, Fabio The convolutional neural networks (CNN) are considered as a particular case of the Deep Learning neural networks, and have been widely used for the extraction of features in images, audio files or text recognition. For the automatic extraction of features from multispectral images, many researchers have appealed to the use of CNN models, which integrate layers with different structures in context with the solution of a problem, which suggests quite a challenge. That is why, in this article, we propose a method to evaluate the stability in the design of convolutional layers for labeling and identification of palm cultivation units from multispectral images. The structure of the proposed convolutional layer will be given in terms of a fuzzy feature map, obtained as a result of the Cartesian product of three vegetation indices commonly used to evaluate plant vigor in this type of crops (NDVI, GNDVI, RVI), represented as compact maps (radial basis functions). The stability in the design will be given in terms of the dominance of the main diagonal that defines the structure of a convolutional layer obtained as a result of the Cartesian product of two compact maps that represent the same multispectral image.

Click here to view a full listing of Mario Gongora's publications and outputs.

Research interests/expertise

  • Identification, Modelling and simulation using Computational Intelligence
  • Intelligent Data Mining and Behaviour Identification
  • Application of Computational Intelligence to industry and real world problems
  • Evolutionary programming
  • Intelligent Mobile Robots and Bioengineering.

Areas of teaching

Artificial Intelligence


Embedded programming


BSc, MSc, PhD 

Membership of external committees

Checkpoint of the Future expert group, IATA (International Air Transport Association), current member of the technology expert group.


  • On-line path optimisation using self simulation and genetic paradigm.
  • Path search for migrations of ancient populations using analysis of mDNA.
  • Analysis of Developmental Genetics Theory using Evolutionary Programming.

Consultancy work

Intelligent Data Mining

Automation and Robotics (including telemetry and instrumentation)

Computational Intelligence applications (e.g. optimisation, system identification, modelling and simulation)

Some consultancy/commercial projects worked for have for example: GSH (telemetry and automation for intelligent buildings), Rolls Royce (automation and instrumentation), Venuesim (intelligent data mining, modelling and simulation), among others.

Current research students

Currently supervising 10 research students. 

Externally funded research grants information

Has had funding from various sources (Royal Academy, EPSRC, TSB, ERDF, etc.).  Active projects:

Venuesim (spinout company created with seed/investment funding from Lachesis), commercialising research outcomes of intelligent data mining, modelling and simulation. Jan 2008 – current.

Intelligent GUI systems, KTP (TSB) funding to develop highly effective and intelligent GUI frameworks to present information from complex systems, in collaboration with Northrop Grumman. June 2012 – May 2014.

Internally funded research project information

Has had funding from various sources (PhD scholarships from EPSRC DTA, RIF, HEIF).  Active projects:

PhD student from EPSRC DTA, Oct 2009 – Sep 2012, working in Intelligent Data Mining.

Intelligent questionnaire, HEIF, developing intelligent autonomous surveying tools to support social services. May 2012 – Feb 2013.

Published patents

US Patent number 6,339,720 “Early warning apparatus for acute Myocardial Infarction in the first six hours of pain”, US government.

US Patent number 5,545,971 “AC voltage regulator”, US Government.

Professional esteem indicators

Journal reviewing: IEEE Transactions on Neural Networks, IEEE Transactions on Computational Intelligence and AI in Games, Elsevier Information Sciences, Elsevier Applied Soft Computing, Elsevier Evolving Systems, Springer Artificial Intelligence Review.

Case studies

Spinout company Venusim resulting from Dr. Gongora’s research in intelligent data mining.

Article in which is the only site focused on bringing the latest news about airport projects, trends, products and services for the global airport industry:

Invited by IATA (International Air Transport Association) to be a member in their expert group for the Checkpoint of the future, an international initiative to drive forward and contribute to aviation security science; by bringing together governments, industry and academic experts from across the world.