Teshome Megersa Bekele
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Teshome Megersa Bekele has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
Wei Wang
Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, School of Software, Dalian University of Technology, Dalian, China
6 shared publications- Feng Xia
School of Computing Technologies, RMIT University
5 shared publications - Xiangjie Kong
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China
3 shared publications Xiaomei Bai
Dalian University of Technology
3 shared publicationsXiaoyan Su
Dalian University of Technology
3 shared publicationsHuizhen Jiang
Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province, School of Software, Dalian University of Technology, Dalian, China
2 shared publications
Latest Publications
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 203-208
A Catfish Effect Based Team Recommendation System
Motivated by the growing complex connectedness of modern society, which is found in many incarnations, especially in a team or a particular network, there has been a coming-together of multiple disciplines in an effort to understand how highly connected teams or networks operate and how to improve their work efficiency. As for teams, due to structural diversity, network heterogeneity and scope difference, team building is rather complicated. In order to build a universal recommendation system, we apply biological phenomena, known as the catfish effect, to built a team recommendation system. By extracting the factors which have a direct influence on team performance and modelling RBF neural network, we can predict the relationship between team performance and factors. We design a CTI(Catfish Identification) algorithm based on RBF i.e., RBF -CTI algorithm, which aims to calculate catfish index CI i.e., the intensity of cat-fish effect of each factor. According to CI, we can easily identify the skill of catf ish, namely the most potential impact factor for the team, as well as the indicator of team recommendation system. We apply the idea of the combination of multi-disciplines and give a universal framework of team recommendation system.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 203-208
A Catfish Effect Based Team Recommendation System
Motivated by the growing complex connectedness of modern society, which is found in many incarnations, especially in a team or a particular network, there has been a coming-together of multiple disciplines in an effort to understand how highly connected teams or networks operate and how to improve their work efficiency. As for teams, due to structural diversity, network heterogeneity and scope difference, team building is rather complicated. In order to build a universal recommendation system, we apply biological phenomena, known as the catfish effect, to built a team recommendation system. By extracting the factors which have a direct influence on team performance and modelling RBF neural network, we can predict the relationship between team performance and factors. We design a CTI(Catfish Identification) algorithm based on RBF i.e., RBF -CTI algorithm, which aims to calculate catfish index CI i.e., the intensity of cat-fish effect of each factor. According to CI, we can easily identify the skill of catf ish, namely the most potential impact factor for the team, as well as the indicator of team recommendation system. We apply the idea of the combination of multi-disciplines and give a universal framework of team recommendation system.
- 4 August 2017
- Published by Springer Nature in Scientometrics
- Vol. 113 (1) , 369-385
Exploring dynamic research interest and academic influence for scientific collaborator recommendation
- 4 August 2017
- Published by Springer Nature in Scientometrics
- Vol. 113 (1) , 369-385
Exploring dynamic research interest and academic influence for scientific collaborator recommendation
- 24 July 2017
- Published by Springer Nature in Scientometrics
- Vol. 113 (1) , 177-193
From triadic closure to conference closure: the role of academic conferences in promoting scientific collaborations
- 24 July 2017
- Published by Springer Nature in Scientometrics
- Vol. 113 (1) , 177-193
From triadic closure to conference closure: the role of academic conferences in promoting scientific collaborations
- 19 April 2017
- Published by Springer Nature in Scientometrics
- Vol. 112 (1) , 329-343
Scientific collaboration patterns vary with scholars’ academic ages
- 19 April 2017
- Published by Springer Nature in Scientometrics
- Vol. 112 (1) , 329-343
Scientific collaboration patterns vary with scholars’ academic ages
- Open Access
- 1 January 2017
- Published by Association for Computing Machinery (ACM)
- p. 1371-1377
Random Walk-based Beneficial Collaborators Recommendation Exploiting Dynamic Research Interests and Academic Influence
It is laborious for researchers to find proper collaborators who can provide researching guidance besides collaborating. Beneficial Collaborators (BCs), researchers who have a high academic level and relevant topics, can genuinely help researchers to enrich their research. Though many efforts have made to develop collaborator recommendation, most of existing works have mainly focused on recommending most possible collaborators with no intention to recommend specifically the BCs. In this paper, we propose the Beneficial Collaborator Recommendation (BCR) model that considers the dynamic research interest of researcher's and academic level of collaborators to recommend the BCs. First, we run the LDA model on the abstract of researchers' publications in each year for topic clustering. Second, we fix generated topic distribution matrix by a time function to fit interest dynamic transformation. Third, we compute the similarity between the collaboration candidate's feature matrix and the target researcher. Finally, we combine the similarity and influence in collaborators network to fix rank score and mine the candidates with high academic level and academic social impact. BCR generates the topN BCs recommendation. Extensive experiments on a dataset with citation network demonstrate that BCR performs better in terms of precision, recall, F1 score and the recommendation quality compared to baseline methods.
- 1 January 2017
- Published by Association for Computing Machinery (ACM)
- p. 1371-1377
Open AccessRandom Walk-based Beneficial Collaborators Recommendation Exploiting Dynamic Research Interests and Academic Influence
It is laborious for researchers to find proper collaborators who can provide researching guidance besides collaborating. Beneficial Collaborators (BCs), researchers who have a high academic level and relevant topics, can genuinely help researchers to enrich their research. Though many efforts have made to develop collaborator recommendation, most of existing works have mainly focused on recommending most possible collaborators with no intention to recommend specifically the BCs. In this paper, we propose the Beneficial Collaborator Recommendation (BCR) model that considers the dynamic research interest of researcher's and academic level of collaborators to recommend the BCs. First, we run the LDA model on the abstract of researchers' publications in each year for topic clustering. Second, we fix generated topic distribution matrix by a time function to fit interest dynamic transformation. Third, we compute the similarity between the collaboration candidate's feature matrix and the target researcher. Finally, we combine the similarity and influence in collaborators network to fix rank score and mine the candidates with high academic level and academic social impact. BCR generates the topN BCs recommendation. Extensive experiments on a dataset with citation network demonstrate that BCR performs better in terms of precision, recall, F1 score and the recommendation quality compared to baseline methods.
- Open Access
- 15 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4, 5408-5416
A Hybrid Mechanism for Innovation Diffusion in Social Networks
Innovation diffusion is the process of adopting novel things, which is deemed as the diffusion of human behaviors. Previous studies mainly posit an unclear distinction with information diffusion. However, there exist critical differences in both social and economic areas. Inspired by this observation, we propose a practical method for innovation diffusion based on the process of behavior diffusion, which integrates threshold model with social imitation strategy. The primary goal of our proposed model is to combine individuals' economic as well as social characteristics to study innovation diffusion. The interplay of these two strategies is studied in the context of a coordination game. According to the simulation results on Erdös-Rényi random networks and small-world networks, we find that the conjunction of these two approaches can greatly improve the efficiency of innovation diffusion. In addition, we further study the impacts of varied initial seeds' selection strategies on the overall performance of innovation diffusion using our proposed model.
- 15 September 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4, 5408-5416
Open AccessA Hybrid Mechanism for Innovation Diffusion in Social Networks
Innovation diffusion is the process of adopting novel things, which is deemed as the diffusion of human behaviors. Previous studies mainly posit an unclear distinction with information diffusion. However, there exist critical differences in both social and economic areas. Inspired by this observation, we propose a practical method for innovation diffusion based on the process of behavior diffusion, which integrates threshold model with social imitation strategy. The primary goal of our proposed model is to combine individuals' economic as well as social characteristics to study innovation diffusion. The interplay of these two strategies is studied in the context of a coordination game. According to the simulation results on Erdös-Rényi random networks and small-world networks, we find that the conjunction of these two approaches can greatly improve the efficiency of innovation diffusion. In addition, we further study the impacts of varied initial seeds' selection strategies on the overall performance of innovation diffusion using our proposed model.
- Open Access
- 19 June 2016
- Published by Association for Computing Machinery (ACM)
- p. 231-232
Can Academic Conferences Promote Research Collaboration?
- 19 June 2016
- Published by Association for Computing Machinery (ACM)
- p. 231-232
Open AccessCan Academic Conferences Promote Research Collaboration?
- Open Access
- 28 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 3, 1695-1703
Context-Based Collaborative Filtering for Citation Recommendation
Citation recommendation is an interesting and significant research area as it solves the information overload in academia by automatically suggesting relevant references for a research paper. Recently, with the rapid proliferation of information technology, research papers are rapidly published in various conferences and journals. This makes citation recommendation a highly important and challenging discipline. In this paper, we propose a novel citation recommendation method that uses only easily obtained citation relations as source data. The rationale underlying this method is that, if two citing papers are significantly co-occurring with the same citing paper(s), they should be similar to some extent. Based on the above rationale, an association mining technique is employed to obtain the paper representation of each citing paper from the citation context. Then, these paper representations are pairwise compared to compute similarities between the citing papers for collaborative filtering. We evaluate our proposed method through two relevant real-world data sets. Our experimental results demonstrate that the proposed method significantly outperforms the baseline method in terms of precision, recall, and F1, as well as mean average precision and mean reciprocal rank, which are metrics related to the rank information in the recommendation list.
- 28 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 3, 1695-1703
Open AccessContext-Based Collaborative Filtering for Citation Recommendation
Citation recommendation is an interesting and significant research area as it solves the information overload in academia by automatically suggesting relevant references for a research paper. Recently, with the rapid proliferation of information technology, research papers are rapidly published in various conferences and journals. This makes citation recommendation a highly important and challenging discipline. In this paper, we propose a novel citation recommendation method that uses only easily obtained citation relations as source data. The rationale underlying this method is that, if two citing papers are significantly co-occurring with the same citing paper(s), they should be similar to some extent. Based on the above rationale, an association mining technique is employed to obtain the paper representation of each citing paper from the citation context. Then, these paper representations are pairwise compared to compute similarities between the citing papers for collaborative filtering. We evaluate our proposed method through two relevant real-world data sets. Our experimental results demonstrate that the proposed method significantly outperforms the baseline method in terms of precision, recall, and F1, as well as mean average precision and mean reciprocal rank, which are metrics related to the rank information in the recommendation list.
- 1 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 458-462
Towards collaborative business process management development current and future approaches
Modern Business Process Management (BPM) expands to cover the partner organizations' business processes across organizational boundaries supports organizations' to coordinate the flow of information among organizations' and link their business processes. Over the years enterprises have constructed extensive networks of bridges to other organizations in order to deliver their corporate business services. Nowadays, competitive advantage in continuously changing business environment, organizations depends on ability to excel in key business processes. Collaborative BPM expands the scope of traditional BPM and is moving to priority number one as organizations search for an integrated solution that provides an environment to cope with dynamic and ever changing business processes. This paper covers basic concepts, collaborative BPM development technologies and gives a future research direction.
- 1 May 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 458-462
Towards collaborative business process management development current and future approaches
Modern Business Process Management (BPM) expands to cover the partner organizations' business processes across organizational boundaries supports organizations' to coordinate the flow of information among organizations' and link their business processes. Over the years enterprises have constructed extensive networks of bridges to other organizations in order to deliver their corporate business services. Nowadays, competitive advantage in continuously changing business environment, organizations depends on ability to excel in key business processes. Collaborative BPM expands the scope of traditional BPM and is moving to priority number one as organizations search for an integrated solution that provides an environment to cope with dynamic and ever changing business processes. This paper covers basic concepts, collaborative BPM development technologies and gives a future research direction.