H. Hagras

University of Essex, Colchester, England, United Kingdom

Are you H. Hagras?

Claim your profile

Publications (164)77.81 Total impact

  • [show abstract] [hide abstract]
    ABSTRACT: The global economic meltdown of the late 2000s exposed many organisations around the world, this drove the need to build robust frameworks for predicting and assessing risks in financial applications. Such predictive frameworks helped organisations to increase the quality and quantity of their transactions hence increasing the revenues and reducing the risks. Many organisations around the World still use statistical regression techniques which are well established for many problems such as fraud detection or risk analysis. However, recent years have seen the application of computational intelligence techniques to develop predictive models for financial applications. Some of the computational intelligence techniques like neural networks provide good predictive models, nevertheless they are considered as black box models which do not provide an easy to understand reasoning about a given decision or even a summary of the generated model. However, in the current economic situation, transparency became an important factor where there is a need to fully understand and analyze a given financial model. In this paper, we will present a Genetic Type-2 Fuzzy Logic System (FLS) for the modeling and prediction of financial applications. The proposed system is capable of generating summarized models from a specified number of linguistic rules, which enables the user to understand the generated financial model. The system is able to use this summarized model for prediction within financial applications. We have performed several evaluations in two distinctive financial domains, one for the prediction of good/bad customers in a financial real-world lending application and the other domain was in the prediction of arbitrage opportunities in the stock markets. The proposed Genetic type-2 FLS has outperformed white box models like the Evolving Decision Rule procedure (which is a white based on Genetic Programming and decision trees) and gave a comparable performance to black box models like neural networks while the proposed genetic type-2 FLS provided a white box model which is easy to understand and analyse by the lay user.
    Soft Computing 12/2013; 17(12). · 1.12 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: The intention of this demonstration is to present a novel immersive telepresence system that enables remote students to participate in seminars and lectures using online streaming video and audio connections. In this system, a virtualized video view is created using a 360° panoramic video projected onto a 180° curved projected screen (immersive shell). This recreates a more natural human-like perception of real environments and thereby stimulating the learning process. 3D audio is also collected and reproduced at the remote location adding to the realism. To accomplish this we us a 360° mirror situated in the classroom which we use with a camera to transmit a panoramic image to the remote users where they reconstruct the original image from spherical to Cartesian. To process the audio we use a small array of microphones at the classroom end. In addition, we provide various tools to allow the participants to control their position within the virtualized views, thereby creating an innovative technology and user experience. We will be demonstrating this system at the conference.
    11/2013;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Historically, learning has been seen as part of the human process to achieve a status, income and a better future. Traditionally students travel to attend lectures or participate in brainstorming and training sessions benefiting from the interaction afforded by the physical learning environment, the classroom, and the wider University facilities. However, financial pressures arising from national and global competition are putting pressure on Universities to find more cost-effective ways of delivering education. While distant learning has been always there, it is clear that this approach needs substantial improvements in order to deliver a similar learning experience to physically attending a university. To these end, this paper presents a novel immersive telepresence system that allows remote or distant students to customize their virtual presence at seminars and lectures based on a 360° panoramic video projected onto a 180° curved projected screen (an immersive shell). Audio is also collected with 3D information in order to be reproduced more naturally at the remote location. The arrangement is intended to provide online learners with a more faithful replication of human perception, akin to what they would experience in a real learning environment. Technically, to do this we use a 360° mirror to capture the lecture room scene and transmit it to remote locations where it is reconstructed the original image from spherical to Cartesian coordinates providing a novel but natural immersive experience. This paper describes the motivation, model, computational architecture and our main findings.
    iED Europe Summit - London 2013, London, UK; 11/2013
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: This describes research into a mechanism that enables geographically dispersed participants in telepresence system to be placed in artificial views that better mimics a real life lecture or meeting room situation. In support of this we present a novel solution for collaborative activity that converts participant's into Mixed Reality's visual objects allowing them to interact more naturally from any location, enhancing their communication. The system enables people to logon, choose a seat or location (which also assigns them a virtual presence in that location) thereby enabling them to talk and interact, with their virtual neighbors. The sound volume can be controlled so as to produce a kind of virtual bubble that surrounds the participants allowing the audio to be directional and selective. In addition, attendees to the real environment can interact with the remote attendees.
    Journal of Ambient Intelligence and Smart Environments 07/2013; 17:478-488. · 1.30 Impact Factor
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: The general focus of this paper concerns the development of telepresence within intelligent immersive environments. The overall aim is the development of a system that combines multiple audio and video feeds from geographically dispersed people into a single environment view, where sound appears to be linked to the appropriate visual source on a panoramic viewer based on the gaze of the user. More specifically this paper describes a novel directional audio system for telepresence which seeks to reproduce sound sources (conversations) in a panoramic viewer in their correct spatial positions to increase the realism associated with telepresence applications such as online meetings. The intention of this work is that external attendees to an online meeting would be able to move their head to focus on the video and audio stream from a particular person or group so as decrease the audio from all other streams (i.e. speakers) to a background level. The main contribution of this paper is a methodology that captures and reproduces these spatial audio and video relationships. In support of this we have created a multiple camera recording scheme to emulate the behavior of a panoramic camera, or array of cameras, at such meeting which uses the Chroma key photographic effect to integrate all streams into a common panoramic video image thereby creating a common shared virtual space. While this emulation is only implemented as an experiment, it opens the opportunity to create telepresence systems with selectable real time video and audio streaming using multiple camera arrays. Finally we report on the results of an evaluation of our spatial audio scheme that demonstrates that the techniques both work and improve the users' experience, by comparing a traditional omni directional audio scheme versus selectable directional binaural audio scenarios.
    9th International Conference on Intelligent Environments (IE), 2013, Athens, Greece; 07/2013
  • 01/2013;
  • S. Naim, H. Hagras, A. Bilgin
    [show abstract] [hide abstract]
    ABSTRACT: Selecting a suitable lighting level for reading is crucial to the overall success of reading comprehension. The light level preferences vary amongst the various users specifically according to changing environment conditions. Hence, there is a need to employ intelligent decision making systems which can consider the various preferences and criteria in order to achieve the convenience of the various readers. In this paper, we propose a Fuzzy Logic-Multi Criteria Group Decision Making (FL-MCGDM) system which provides a comprehensive valuation from a group of decision makers. The decision making system was developed based on the aggregation of users' opinion on preferred lighting levels while reading. The proposed FL-MCGDM system employs an interval type-2 fuzzy logic and hesitation (from Intuitionistic Fuzzy Sets (IFSs)) index. We have carried out various experiments in the intelligent apartment (iSpace) located in the University of Essex. It was found that the Footprint of Uncertainty (FOU) (of interval type 2 fuzzy sets) and hesitation index of intuitionistic fuzzy sets (IFSs) are able to provide a measure of the uncertainties present among the various decision makers in the proposed FL-MCGDM system. The extended (Type-2-IFS) membership function in the FL-MCGDM system is more inline/agreement with the users' decision compared to type-1 membership function and interval type-2 membership function.
    Advances in Type-2 Fuzzy Logic Systems (T2FUZZ), 2013 IEEE Symposium on; 01/2013
  • T. Kumbasar, H. Hagras
    [show abstract] [hide abstract]
    ABSTRACT: In this paper, we will present a big bang-big crunch optimization (BB-BC) based approach for the design of an interval type-2 fuzzy PID controller. The implemented global optimization algorithm has a low computational cost and a high convergence speed. As a consequence, the BB-BC method is a very efficient search algorithm when the number of the optimization parameters is relatively big. The optimized type-2 fuzzy controller is compared with PID and type-1 fuzzy PID controllers which were optimized with either the BB-BC optimization method or conventional design strategies. The paper will also show the effect the extra degrees of freedom provided by the antecedent interval type-2 fuzzy sets on the closed loop system performance. We will present a comparative study performed on the highly nonlinear cascaded tank process to show the superiority of the optimized interval type-2 fuzzy PID controller compared to its optimized PID, type-1 counterparts.
    Fuzzy Systems (FUZZ), 2013 IEEE International Conference on; 01/2013
  • Christian Wagner, Hani Hagras
    01/2013: pages 65-80;
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: One of the key components in the development of intelligent environments is the recognition and analysis of human behaviour. However, the majority of traditional non-fuzzy machine vision based approaches rely on assumptions such as known spatial locations and temporal segmentations or they employ computationally expensive approaches such as sliding window search through a spatio-temporal volume. Hence, it is difficult for such traditional non-fuzzy methods to scale up and handle the high-levels of uncertainties available in real-world applications. This paper presents a system which is based on Interval Type-2 Fuzzy Logic S ystems (IT2FLS s) for robust human behaviour recognition using machine vision in intelligent environments. We will present several experiments which were performed on the publicly available Weizmann human action dataset. It will be shown that the proposed IT2FLS outperformed the Type-1 FLS (T1FLS) counterpart as well as outperforming other traditional non-fuzzy systems.
    IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013)IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013); 01/2013
  • K. Almohammadi, H. Hagras
    [show abstract] [hide abstract]
    ABSTRACT: E-learning involves the computer and network-enabled transfer of skills and knowledge. The recent years have witnessed an increased interest in intelligent E-Learning platforms that incorporate adaptive educational systems which enable the creation of personalized learning environments to suit the students' individual requirements and needs. Such systems aim to correlate the student characteristics (such as knowledge level, personality and learning style) with instructional variables, (such as the presentation of learning materials and feedback). Various artificial intelligence based methodologies have been used to realize adaptive educational systems. However, the vast majority of the existing adaptive educational systems do not learn from the users' behaviors to create white box models which could be easily read and analyzed by the lay user. This paper presents a fuzzy logic based system that can learn the users' preferred knowledge delivery based on the students characteristics to generate a personalized learning environment. The proposed methodology employs a self-learning system which enables to generate a fuzzy logic based model from data. The fuzzy model is generated from data representing various students' capabilities and their desired learning needs. The learnt fuzzy based model is then used to improve the knowledge delivery to the various students based on their individual characteristics. The proposed system is adaptive where it is continuously adapting in a lifelong learning mode to make sure that the generated models adapt to the students individual preferences. We will present experiments carried with the proposed system which involved 17 students. The experiments will show how the proposed system learnt the students' preferences and created a model which allowed providing a personalized learning environment tailored according to the students' needs and requirements. This allowed improving the knowledge delivery which resulted in improving the - tudents' performance.
    Fuzzy Systems (FUZZ), 2013 IEEE International Conference on; 01/2013
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In this paper, we present an approach to interpret the Computing With Words (CWWs) paradigm merging the advancements from neuroscience, psychology and artificial intelligence. The presented approach will incorporate fuzzy composite concepts (FCCs), a special case of linguistic weighted average (LWA) and case-based reasoning (CBR). The focus of the paper is on the inception of the CWWs paradigm to bridge the gap between the human and machine intelligence. The investigation of FCCs processing is performed using linear general type-2 (LGT2) and interval type-2 (IT2) fuzzy sets. The results show that LGT2 fuzzy sets outperform IT2 fuzzy sets in the processing time of complete rule base evaluation, in providing better modeling of the human perceptual judgment, and in producing richer range of output intervals.
    IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013)IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2013); 01/2013
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In recent years, antimalware applications represented one of the most important research topics in the area of network security threat. In addition, mal-ware have become a growing important problem for governments and commercial organizations. The key point of the research on the network security is to judge and validate the similarity metrics among the malicious software. Indeed, most com-puter network issues are also caused by malware. As a consequence, one enhanced system to analyze the behavior of malwares is needed to try to predict the malicious actions and to minimize the computer damages caused by the malware. However, the conventional data analysis tools lack the ability to deal with the computer safety because the environments malwares operating are with high levels of imprecision and vagueness. For this reason, we have developed Taiwan Malware Analysis Net (TWMAN) to improve the accuracy of malware behavioral analysis. This chapter
    01/2013: pages 113-131; , ISBN: 978-3-642-35488-5
  • [show abstract] [hide abstract]
    ABSTRACT: Ambient intelligence is a new information paradigm, where people are empowered through a digital environment that is “aware” of their presence and context and is sensitive, adaptive, and responsive to their needs. Hence, one of the important requirements for ambient intelligent environments (AIEs) is the ability to localize the whereabouts of the user in the AIE to address her/his needs. In order to protect user privacy, the use of cameras is not desirable in AIEs, and hence, there is a need to rely on nonintrusive sensors. There are various localization means that are available for outdoor spaces such as those which rely on satellite signals triangulation. However, these outdoor localization means cannot be used in indoor environments. The majority of nonintrusive and noncamera-based indoor localization systems require the installation of extra hardware such as ultrasound emitters/antennas, radio-frequency identification (RFID) antennas, etc. In this paper, we propose a novel indoor localization system that is based on WiFi signals which are free to receive, and they are available in abundance in the majority of domestic spaces. However, free WiFi signals are noisy and uncertain, and their strengths and availability are continuously changing. Hence, we present a fuzzy logic-based system which employs free available WiFi signals to localize a given user in AIEs. The proposed system receives WiFi signals from a large number of existing WiFi access points (up to 170 access points), where no prior knowledge of the access points locations and the environment is required. The system employs an incremental lifelong learning approach to adjust its behavior to the varying and changing WiFi signals to provide a zero-cost localization system which can provide high accuracy in real-world living spaces. We have compared our system in both simulated and real environments with other relevant techniques in the literature, and we have found that our system outperfo- ms the other systems in the offline learning process, whereas our system was the only system which is capable of performing online learning and adaptation. The proposed system was tested in real-world spaces from a living lab intelligent apartment (iSpace) to a town center apartment to a block of offices. In all these experiments, our system has been highly accurate in detecting the user in the given AIEs, and the system was able to adapt its behavior to changes in the AIE or the WiFi signals. We envisage that the proposed system will play an important role in AIEs, especially for privacy concerned situations like elderly care scenarios.
    IEEE Transactions on Fuzzy Systems 01/2013; 21(4):702-718. · 5.48 Impact Factor
  • B. Bostanci, H. Hagras, J. Dooley
    [show abstract] [hide abstract]
    ABSTRACT: This paper aims to investigate the development of an intelligent refrigerator through embedding intelligent agents in normal refrigerators. The proposed intelligent refrigerator will be able to recognize various food items and learn user consumption habits via the proposed intelligent agent. The system incorporates a low-cost camera which feeds its input to the fuzzy agent in order to classify different food items and track their amounts. Using this information, consumption patterns representing the amount of items taken by users are generated and fed into a neural network system which is aimed to learn user habits and provide feedback to the user in cases where he/she consumes an unusual number of items. The system employs a second camera to distinguish between different users so that user specific information such as items consumed and calories taken can be stored separately. The resulting system has an accuracy of ≃ 90% for item identification and shows a very good performance for learning the habits of different users. The system also provides a graphical interface to display available items which allows users to generate an automated shopping list.
    Fuzzy Systems (FUZZ), 2013 IEEE International Conference on; 01/2013
  • D. Bernardo, H. Hagras, E. Tsang
    [show abstract] [hide abstract]
    ABSTRACT: Following the global economic crisis, many financial organisations around the World are seeking efficient frameworks for predicting and assessing financial risks. However, in the current economic situation, transparency became an important factor where there is a need to fully understand and analyse a given financial model. In this paper, we will present a Genetic Type-2 Fuzzy Logic System (FLS) for the modelling and prediction of financial applications. The proposed system is capable of generating summarized optimised type-2 FLSs based financial models which are easy to read and analyse by the lay user. The system is able to use the summarized model for prediction within financial applications. We have performed several evaluations in two distinctive financial domains one for the prediction of good/bad customers in a credit card approval application and the other domain was in the prediction of arbitrage opportunities in the stock markets. The proposed Genetic type-2 FLS has outperformed white box financial models like the Evolving Decision Rule (EDR) procedure (which is based on Genetic Programming (GP) and decision trees) and gave a comparable performance to black box models like neural networks while the proposed system provided a white box model which is easy to understand and analyse by the lay user.
    Fuzzy Systems (FUZZ), 2013 IEEE International Conference on; 01/2013
  • [show abstract] [hide abstract]
    ABSTRACT: For the recent few years, resource planning has become an interesting research topic for many companies, especially within telecommunications domain. Resource planning is basically trying to provide a high quality of service while trying to keep the cost as low as possible. The main aim of resource planning is to utilize the available resources as much as possible so that they can match the expected demand for services. Tactical resource planning looks at medium-term planning periods, i.e. weeks to months, and aims to establish coarse-grain resource deployments. In our previous work we introduced an experimental fuzzy based resource planning approach modeled for a delivery unit in British Telecom (BT) [1]. We presented a hierarchical based fuzzy logic system, which calculates the compatibility between resources and the allocated tasks, and then matches the most compatible tasks and resources to each other. The proposed hierarchical fuzzy logic based system (in an experimental setting) was able to achieve very good results in comparison to the original system, where the proposed system was able to achieve 12.2% improvement in tasks done per resource. In this paper, we introduce a hierarchical fuzzy logic based system that uses evolutionary systems to tune the fuzzy membership functions, which result in an improvement in the overall output of the system. The new fuzzy-genetic based system was able achieve better improvement in tasks done per resource than the hierarchical fuzzy logic based system that was tuned by experts.
    Evolving and Adaptive Intelligent Systems (EAIS), 2013 IEEE Conference on; 01/2013
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: Within the last two decades, the paradigm of Computing With Words (CWW) has been gaining more attention. Mainly, CWW has an exciting vision which tries to tackle the problem of human intelligence by taking the human mind as a role model. The human intelligence has been investigated by various disciplines including psy- chology, philosophy, neuroscience, linguistics, computer science, and cognitive sciences. Notably, it is not a straightforward task to map the human’s brain reasoning into computer processes. In this paper, we propose to facilitate such mapping by investigating a key element, which is to identify the step-by-step formation of percep- tual judgments. Herein, we first introduce an approach that employs general type-2 fuzzy logic to dynamically model the human perceptions based on the human experience. This approach can be regarded as a step to enable the CWW vision. We have deployed the proposed approach in real-world settings and we will present two sets of real- world experiments which were conducted in the intelligent apartment (iSpace) in the University of Essex. The first set of experiments demonstrates the results of the proposed approach for the adaptive modeling of ambient luminance perception. In the second set of experiments, we show that our approach performs better in the rule base evaluation processing time and in output accuracy with comparison to an interval type-2 fuzzy logic system.
    Soft Computing 01/2013; 17. · 1.12 Impact Factor
  • S. Naim, H. Hagras
    [show abstract] [hide abstract]
    ABSTRACT: Decision making could be viewed to include Multi-Criteria Group Decision Making (MCGDM). MCGDM is a decision tool which it is able to find a unique agreement from number of decision makers/users by evaluating the uncertain judgment among them. Several fuzzy logic based approaches have been employed in MCGDM to handle the linguistic uncertainties and hesitancy. However, there is a need to handle the high level of uncertainties that exist in decision making problems involving numbers of decision makers/experts/users with varying points of view. In this paper, we present a general type-2 fuzzy logic based approach for MCGDM. The proposed system aims to handle the high levels of uncertainties which exist due to the varying Decision Makers' (DMs) judgments and the vagueness of the appraisal. The proposed method utilizes general type-2 fuzzy sets. The aggregation operation in the proposed method aggregates the various DMs opinions which allow handling the disagreements of DMs' opinions into a unique approval. We will present results from the proposed system deployment for the assessment of the postgraduate study. The proposed system was able to model the variation in the group decision making process exhibited by the various decision makers' opinions. In addition, the proposed system showed agreement between the proposed method and the real decision outputs from DMs (as quantified by the Pearson Correlation) which outperformed the MCGDM systems based on type-1 fuzzy sets, interval type-2 fuzzy sets and interval type-2 fuzzy sets with hesitation index.
    Fuzzy Systems (FUZZ), 2013 IEEE International Conference on; 01/2013
  • Source
    [show abstract] [hide abstract]
    ABSTRACT: In a broad sense, the Computing With Words (CWW) vision tries to tackle the problem of human intelligence by taking the human mind as a role model. A key element to facilitate the mapping of the human's brain reasoning into computer processes is to identify the step-by-step formation of perceptual judgments. In this paper, we present an approach that employs general type-2 fuzzy logic which enables the human perceptions to be dynamically modeled and adapted depending on the human experience. This approach can be regarded as a step to enable the CWW vision. We will present real-world experiments which were conducted with real users in the intelligent apartment (iSpace) in the University of Essex. The experiments demonstrate the results of the proposed approach for the adaptive modeling of ambient luminance perception.
    UK Workshop on Computational Intelligence 2012; 09/2012

Publication Stats

1k Citations
77.81 Total Impact Points

Institutions

  • 1970–2013
    • University of Essex
      • School of Computer Science and Electronic Engineering
      Colchester, England, United Kingdom
  • 2008–2009
    • The German University in Cairo
      Al Qāhirah, Al Qāhirah, Egypt
  • 2005
    • Loughborough University
      Loughborough, England, United Kingdom
  • 2004
    • University of Oviedo
      Oviedo, Asturias, Spain
  • 2002
    • University of Bridgeport
      Bridgeport, Connecticut, United States
  • 2000
    • University of Hull
      • Department of Computer Science
      Hull, ENG, United Kingdom