Ivan Ganchev | University of Limerick (original) (raw)
Papers by Ivan Ganchev
Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), 2017 South Eastern European, 2017
Recommendation systems employed on the Internet aim to serve users by recommending items which wi... more Recommendation systems employed on the Internet aim to serve users by recommending items which will likely be of interest to them. The recommendation problem could be cast as either a rating estimation problem which aims to predict as accurately as possible for a user the rating values of items which are yet unrated by that user, or as a ranking problem which aims to find the top-k ranked items that would be of most interest to a user, which s/he has not ranked yet. In contexts where explicit item ratings of other users may not be available, the ranking prediction could be more important than the rating prediction. Most of the existing ranking-based prediction approaches consider items as having equal weights which is not always the case. Different weights of items could be regarded as a reflection of items' importance, or desirability, to users. In this paper, we propose to integrate variable item weights with a ranking-based matrix factorization model, where learning is driven by Bayesian Personalized Ranking (BPR). Two ranking-based models utilizing different-weight learning methods are proposed and the performance of both models is confirmed as being better than the standard BPR method.
Bookmarks Related papers MentionsView impact
Springer LNCS, volume 10563
With the rapid growth of the Web, recommender systems have become essential tools to assist users... more With the rapid growth of the Web, recommender systems have become essential tools to assist users to find high-quality personalized recommendations from massive information resources. Content-based filtering (CB) and collaborative filtering (CF) are the two most popular and widely used recommendation approaches. In this paper, we focus on ways of taking advantage of both approaches based only on user-item rating data. Motivated by the user profiling technique used in content-based recommendation, we propose to merge user profiles, learnt from the items viewed by the users, as a new latent variable in the latent factor model, which is one of the most popular CF-based approaches, thereby generating more accurate recommendation models. The performance of the proposed models is tested against several widely-deployed state-of-the-art recommendation methods. Experimental results, based on two popular datasets, confirm that better accuracy can be indeed achieved.
Bookmarks Related papers MentionsView impact
Predict 2017
Bookmarks Related papers MentionsView impact
Wireless Communications and Mobile Computing, 2017
With the development of ubiquitous computing, recommendation systems have become essential tools ... more With the development of ubiquitous computing, recommendation systems have become essential tools in assisting users in discovering services they would find interesting. This process is highly dynamic with an increasing number of services, distributed over networks, bringing the problems of cold start and sparsity for service recommendation to a new level. To alleviate these problems, this paper proposes a hybrid service recommendation prototype utilizing user and item side information, which naturally constitute a heterogeneous information network (HIN) for use in the emerging ubiquitous consumer wireless world (UCWW) wireless communication environment that offers a consumer-centric and network-independent service operation model and allows the accomplishment of a broad range of smart-city scenarios, aiming at providing consumers with the “best” service instances that match their dynamic, contextualized, and personalized requirements and expectations. A layered architecture for the proposed prototype is described. Two recommendation models defined at both global and personalized level are proposed, with model learning based on the Bayesian Personalized Ranking (BPR). A subset of the Yelp dataset is utilized to simulate UCWW data and evaluate the proposed models. Empirical studies show that the proposed recommendation models outperform several widely deployed recommendation approaches.
Bookmarks Related papers MentionsView impact
Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2017 IEEE 2nd, 2017
Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold... more Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold start problems found in item-based collaborative filtering (CF) techniques, which are employed in recommendation systems. Additional item meta-data provides the foundation for generating a heterogeneous information network (HIN). The proposed approach is to enrich the item-based CF with diverse types of relationships existing between items in the HIN, to overcome the sparsity issue from implicit user feedback. Bayesian personalized ranking optimization technique is used for estimation and its performance is evaluated by comparing the results with the traditional item-based CF. The experimental tests prove that the proposed approach achieves better accuracy.
Bookmarks Related papers MentionsView impact
5th UL-NUIG Annual Research Day, Apr 22, 2015
Context-aware recommendation systems make recommendations by adapting to user's specific situatio... more Context-aware recommendation systems make recommendations by adapting to user's specific situation, and thus by exploring both the user preferences and the environment. In this paper, the design of a context-aware service recommendation framework utilising semantic knowledge in the Ubiquitous Consumer Wireless World (UCWW) is outlined. The main objective of the framework is to point to users the 'best' service instances that match their dynamic, contextualised and personalised requirements and expectations, thereby aligning to the always best connected and best served (ABC&S) paradigm.
Bookmarks Related papers MentionsView impact
Intelligent Computer Communication and Processing (ICCP), 2016 IEEE 12th International Conference on, 2016
The item-based collaborative filtering (CF) is one of the most successful approaches utilized by ... more The item-based collaborative filtering (CF) is one of the most successful approaches utilized by the recommendation systems. The basic concept behind it is to recommend those items to users which are similar to other items that these users have been interested in recently. This paper proposes a hybrid method that integrates user trust relations with item-based CF. This is achieved by incorporating user social similarities into the computation of item similarities. Performance evaluation of the proposed method is done by comparing the results with the traditional item-based CF. The experiment results demonstrate that the proposed approach achieves better accuracy.
Bookmarks Related papers MentionsView impact
Intelligent Systems (IS), 2016 IEEE 8th International Conference on, 2016
This paper describes the general service recommendation process matched to the telecommunication ... more This paper describes the general service recommendation process matched to the telecommunication service delivery characteristics of the Ubiquitous Consumer Wireless World (UCWW). The goal is to provide consumers with the `best' service instances that match their dynamic, contextualized and personalized requirements and expectations, thereby aligning their usage of mobile services to the always best connected and best served (ABC&S) paradigm. A four-tiered architectural configuration of the UCWW service recommendation framework is proposed along with a suitable service recommendation model. Specific and generic smart-city application examples are outlined. Other relevant social impact of the proposed approach is highlighted at the conclusion of the paper.
Bookmarks Related papers MentionsView impact
Much work on modelling pattern recognition by AI systems has focused on the stability and plastic... more Much work on modelling pattern recognition by AI systems has focused on the stability and plasticity of a system's ongoing response to novel inputs. This paper discusses a general learning mechanism for ART2 neural networks, which incorporates forgetting by long-term memory trace decay. Such approach enables the system to reuse memory resources and adapt to a huge in diversity or
Bookmarks Related papers MentionsView impact
This paper considers the problem of finding an optimal deployment of information resources on an ... more This paper considers the problem of finding an optimal deployment of
information resources on an InfoStation network in order to minimize the over-
head and reduce the time needed to satisfy user requests for resources. Two
formal models are developed for formalizing the problem – a static model and
a dynamic model. Ideas of how to use these models for solving the problem of
optimal deployment of resources are presented.
Bookmarks Related papers MentionsView impact
ACM SIGMOBILE Mobile Computing and Communications Review, 2006
Bookmarks Related papers MentionsView impact
2004 IEEE 59th Vehicular Technology Conference. VTC 2004-Spring (IEEE Cat. No.04CH37514), 2004
Bookmarks Related papers MentionsView impact
... Its role is to establish and maintain the connections, provide secure communication channel, ... more ... Its role is to establish and maintain the connections, provide secure communication channel, perform reliable ... services are provided in a personalised manner by adapting them to the currentcontext, eg to ... eg a laptop or PDA), s/he may access the complete hyper-media format of ...
Bookmarks Related papers MentionsView impact
The paper provides a general description of our approach to development of InfoStation-based eLea... more The paper provides a general description of our approach to development
of InfoStation-based eLearning architectures. The approach adopts the ideas
suggested in the MDA specification of OMG. The three levels of the prototype
system architecture developed by following this approach are discussed in detail.
The resultant InfoStation-based network architecture provides mobile access
to electronic services (eServices) and electronic content (eContent), for users
equipped with mobile wireless devices, via a set of InfoStations deployed in key
points around a university campus.
Bookmarks Related papers MentionsView impact
Within this chapter, an agent-oriented middleware created to support the delivery of context-awar... more Within this chapter, an agent-oriented middleware created to support the delivery of context-aware mLearning services provision is presented. This middleware architecture, based on the concept of InfoStations and developed within a University campus domain, is described in detail. Concepts for the control and management of service sessions and communications scenarios are also presented. The multi-agent approach adopted for the implementation of this system and indeed the system entity interactions involved in service delivery are discussed. The harvesting and utilisation of semantic information in order to facilitate the contextualisation and personalisation of mLearning services is also detailed.
Bookmarks Related papers MentionsView impact
... are strong foundation for seeking opportunities for adaptation to environment/context changes... more ... are strong foundation for seeking opportunities for adaptation to environment/context changes so as to ensure more efficient personalized learning (in ... environment/context changes over time. ... InfoStation-Based University Campus System Supporting Intelligent Mobile Services. ...
Bookmarks Related papers MentionsView impact
This chapter describes a generic, service-oriented and agent-based approach for the development o... more This chapter describes a generic, service-oriented and agent-based approach for the development of eLearning intelligent system architectures providing wireless access to electronic services (eServices) and electronic content (eContent) for users equipped with mobile devices, via a set of InfoStations deployed in key points around a University Campus. The approach adopts the ideas suggested by the Model Driven Architecture (MDA) specification of the Object Management Group (OMG). The architectural levels and iterations of the approach are discussed in detail and the resultant context-aware, adaptive middleware architecture is presented. The classification and models of the supporting agents are presented as well.
Bookmarks Related papers MentionsView impact
cttc.es
Bookmarks Related papers MentionsView impact
... Intelligent System Architectures Stanimir Stoyanov, Member, IEEE, Ivan Ganchev, Member, IEEE,... more ... Intelligent System Architectures Stanimir Stoyanov, Member, IEEE, Ivan Ganchev, Member, IEEE, Ivan Popchev, and Máirtín O'Droma, Senior Member, IEEE ... ISBN 0-7695-2338-2. 5-8 July 2005. [5] Stojanov S., T. Glushkova, M. Trendafilova, G. Cholakov. ...
Bookmarks Related papers MentionsView impact
Abstract This paper details the ongoing development of a context-sensitive InfoStation-based arc... more Abstract This paper details the ongoing development of a context-sensitive InfoStation-based architecture supporting the mobile eLearning service provision within a University campus domain. A general overview of this architecture is presented highlighting the main ...
Bookmarks Related papers MentionsView impact
Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), 2017 South Eastern European, 2017
Recommendation systems employed on the Internet aim to serve users by recommending items which wi... more Recommendation systems employed on the Internet aim to serve users by recommending items which will likely be of interest to them. The recommendation problem could be cast as either a rating estimation problem which aims to predict as accurately as possible for a user the rating values of items which are yet unrated by that user, or as a ranking problem which aims to find the top-k ranked items that would be of most interest to a user, which s/he has not ranked yet. In contexts where explicit item ratings of other users may not be available, the ranking prediction could be more important than the rating prediction. Most of the existing ranking-based prediction approaches consider items as having equal weights which is not always the case. Different weights of items could be regarded as a reflection of items' importance, or desirability, to users. In this paper, we propose to integrate variable item weights with a ranking-based matrix factorization model, where learning is driven by Bayesian Personalized Ranking (BPR). Two ranking-based models utilizing different-weight learning methods are proposed and the performance of both models is confirmed as being better than the standard BPR method.
Bookmarks Related papers MentionsView impact
Springer LNCS, volume 10563
With the rapid growth of the Web, recommender systems have become essential tools to assist users... more With the rapid growth of the Web, recommender systems have become essential tools to assist users to find high-quality personalized recommendations from massive information resources. Content-based filtering (CB) and collaborative filtering (CF) are the two most popular and widely used recommendation approaches. In this paper, we focus on ways of taking advantage of both approaches based only on user-item rating data. Motivated by the user profiling technique used in content-based recommendation, we propose to merge user profiles, learnt from the items viewed by the users, as a new latent variable in the latent factor model, which is one of the most popular CF-based approaches, thereby generating more accurate recommendation models. The performance of the proposed models is tested against several widely-deployed state-of-the-art recommendation methods. Experimental results, based on two popular datasets, confirm that better accuracy can be indeed achieved.
Bookmarks Related papers MentionsView impact
Predict 2017
Bookmarks Related papers MentionsView impact
Wireless Communications and Mobile Computing, 2017
With the development of ubiquitous computing, recommendation systems have become essential tools ... more With the development of ubiquitous computing, recommendation systems have become essential tools in assisting users in discovering services they would find interesting. This process is highly dynamic with an increasing number of services, distributed over networks, bringing the problems of cold start and sparsity for service recommendation to a new level. To alleviate these problems, this paper proposes a hybrid service recommendation prototype utilizing user and item side information, which naturally constitute a heterogeneous information network (HIN) for use in the emerging ubiquitous consumer wireless world (UCWW) wireless communication environment that offers a consumer-centric and network-independent service operation model and allows the accomplishment of a broad range of smart-city scenarios, aiming at providing consumers with the “best” service instances that match their dynamic, contextualized, and personalized requirements and expectations. A layered architecture for the proposed prototype is described. Two recommendation models defined at both global and personalized level are proposed, with model learning based on the Bayesian Personalized Ranking (BPR). A subset of the Yelp dataset is utilized to simulate UCWW data and evaluate the proposed models. Empirical studies show that the proposed recommendation models outperform several widely deployed recommendation approaches.
Bookmarks Related papers MentionsView impact
Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2017 IEEE 2nd, 2017
Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold... more Exploiting additional item meta-data is proposed in this paper for solving data sparsity and cold start problems found in item-based collaborative filtering (CF) techniques, which are employed in recommendation systems. Additional item meta-data provides the foundation for generating a heterogeneous information network (HIN). The proposed approach is to enrich the item-based CF with diverse types of relationships existing between items in the HIN, to overcome the sparsity issue from implicit user feedback. Bayesian personalized ranking optimization technique is used for estimation and its performance is evaluated by comparing the results with the traditional item-based CF. The experimental tests prove that the proposed approach achieves better accuracy.
Bookmarks Related papers MentionsView impact
5th UL-NUIG Annual Research Day, Apr 22, 2015
Context-aware recommendation systems make recommendations by adapting to user's specific situatio... more Context-aware recommendation systems make recommendations by adapting to user's specific situation, and thus by exploring both the user preferences and the environment. In this paper, the design of a context-aware service recommendation framework utilising semantic knowledge in the Ubiquitous Consumer Wireless World (UCWW) is outlined. The main objective of the framework is to point to users the 'best' service instances that match their dynamic, contextualised and personalised requirements and expectations, thereby aligning to the always best connected and best served (ABC&S) paradigm.
Bookmarks Related papers MentionsView impact
Intelligent Computer Communication and Processing (ICCP), 2016 IEEE 12th International Conference on, 2016
The item-based collaborative filtering (CF) is one of the most successful approaches utilized by ... more The item-based collaborative filtering (CF) is one of the most successful approaches utilized by the recommendation systems. The basic concept behind it is to recommend those items to users which are similar to other items that these users have been interested in recently. This paper proposes a hybrid method that integrates user trust relations with item-based CF. This is achieved by incorporating user social similarities into the computation of item similarities. Performance evaluation of the proposed method is done by comparing the results with the traditional item-based CF. The experiment results demonstrate that the proposed approach achieves better accuracy.
Bookmarks Related papers MentionsView impact
Intelligent Systems (IS), 2016 IEEE 8th International Conference on, 2016
This paper describes the general service recommendation process matched to the telecommunication ... more This paper describes the general service recommendation process matched to the telecommunication service delivery characteristics of the Ubiquitous Consumer Wireless World (UCWW). The goal is to provide consumers with the `best' service instances that match their dynamic, contextualized and personalized requirements and expectations, thereby aligning their usage of mobile services to the always best connected and best served (ABC&S) paradigm. A four-tiered architectural configuration of the UCWW service recommendation framework is proposed along with a suitable service recommendation model. Specific and generic smart-city application examples are outlined. Other relevant social impact of the proposed approach is highlighted at the conclusion of the paper.
Bookmarks Related papers MentionsView impact
Much work on modelling pattern recognition by AI systems has focused on the stability and plastic... more Much work on modelling pattern recognition by AI systems has focused on the stability and plasticity of a system's ongoing response to novel inputs. This paper discusses a general learning mechanism for ART2 neural networks, which incorporates forgetting by long-term memory trace decay. Such approach enables the system to reuse memory resources and adapt to a huge in diversity or
Bookmarks Related papers MentionsView impact
This paper considers the problem of finding an optimal deployment of information resources on an ... more This paper considers the problem of finding an optimal deployment of
information resources on an InfoStation network in order to minimize the over-
head and reduce the time needed to satisfy user requests for resources. Two
formal models are developed for formalizing the problem – a static model and
a dynamic model. Ideas of how to use these models for solving the problem of
optimal deployment of resources are presented.
Bookmarks Related papers MentionsView impact
ACM SIGMOBILE Mobile Computing and Communications Review, 2006
Bookmarks Related papers MentionsView impact
2004 IEEE 59th Vehicular Technology Conference. VTC 2004-Spring (IEEE Cat. No.04CH37514), 2004
Bookmarks Related papers MentionsView impact
... Its role is to establish and maintain the connections, provide secure communication channel, ... more ... Its role is to establish and maintain the connections, provide secure communication channel, perform reliable ... services are provided in a personalised manner by adapting them to the currentcontext, eg to ... eg a laptop or PDA), s/he may access the complete hyper-media format of ...
Bookmarks Related papers MentionsView impact
The paper provides a general description of our approach to development of InfoStation-based eLea... more The paper provides a general description of our approach to development
of InfoStation-based eLearning architectures. The approach adopts the ideas
suggested in the MDA specification of OMG. The three levels of the prototype
system architecture developed by following this approach are discussed in detail.
The resultant InfoStation-based network architecture provides mobile access
to electronic services (eServices) and electronic content (eContent), for users
equipped with mobile wireless devices, via a set of InfoStations deployed in key
points around a university campus.
Bookmarks Related papers MentionsView impact
Within this chapter, an agent-oriented middleware created to support the delivery of context-awar... more Within this chapter, an agent-oriented middleware created to support the delivery of context-aware mLearning services provision is presented. This middleware architecture, based on the concept of InfoStations and developed within a University campus domain, is described in detail. Concepts for the control and management of service sessions and communications scenarios are also presented. The multi-agent approach adopted for the implementation of this system and indeed the system entity interactions involved in service delivery are discussed. The harvesting and utilisation of semantic information in order to facilitate the contextualisation and personalisation of mLearning services is also detailed.
Bookmarks Related papers MentionsView impact
... are strong foundation for seeking opportunities for adaptation to environment/context changes... more ... are strong foundation for seeking opportunities for adaptation to environment/context changes so as to ensure more efficient personalized learning (in ... environment/context changes over time. ... InfoStation-Based University Campus System Supporting Intelligent Mobile Services. ...
Bookmarks Related papers MentionsView impact
This chapter describes a generic, service-oriented and agent-based approach for the development o... more This chapter describes a generic, service-oriented and agent-based approach for the development of eLearning intelligent system architectures providing wireless access to electronic services (eServices) and electronic content (eContent) for users equipped with mobile devices, via a set of InfoStations deployed in key points around a University Campus. The approach adopts the ideas suggested by the Model Driven Architecture (MDA) specification of the Object Management Group (OMG). The architectural levels and iterations of the approach are discussed in detail and the resultant context-aware, adaptive middleware architecture is presented. The classification and models of the supporting agents are presented as well.
Bookmarks Related papers MentionsView impact
cttc.es
Bookmarks Related papers MentionsView impact
... Intelligent System Architectures Stanimir Stoyanov, Member, IEEE, Ivan Ganchev, Member, IEEE,... more ... Intelligent System Architectures Stanimir Stoyanov, Member, IEEE, Ivan Ganchev, Member, IEEE, Ivan Popchev, and Máirtín O'Droma, Senior Member, IEEE ... ISBN 0-7695-2338-2. 5-8 July 2005. [5] Stojanov S., T. Glushkova, M. Trendafilova, G. Cholakov. ...
Bookmarks Related papers MentionsView impact
Abstract This paper details the ongoing development of a context-sensitive InfoStation-based arc... more Abstract This paper details the ongoing development of a context-sensitive InfoStation-based architecture supporting the mobile eLearning service provision within a University campus domain. A general overview of this architecture is presented highlighting the main ...
Bookmarks Related papers MentionsView impact