This page has only limited features, please log in for full access.
This paper addresses the tradeoff problem between hit ratio and content quality in edge caching systems for multiuser adaptive bitrate streaming (ABS) services. A dynamic policy for cache decision and quality level selection for each ABS content during every cache cycle is proposed. Achieving this policy is NP-complete. For this, the considered problem is transformed into a nested multidimensional 0/1 knapsack optimization problem which is then resolved by a cooperative transfer learning-accelerated genetic algorithm. Performance evaluation demonstrates an adaptation of the proposed algorithm on various video stream popularity models in terms of algorithmic convergence and cache balancing.
Nhu-Ngoc Dao; Duy Trong Ngo; Ngoc-Thanh Dinh; Trung V. Phan; Nam D. Vo; Sungrae Cho; Torsten Braun. Hit Ratio and Content Quality Tradeoff for Adaptive Bitrate Streaming in Edge Caching Systems. IEEE Systems Journal 2020, PP, 1 -4.
AMA StyleNhu-Ngoc Dao, Duy Trong Ngo, Ngoc-Thanh Dinh, Trung V. Phan, Nam D. Vo, Sungrae Cho, Torsten Braun. Hit Ratio and Content Quality Tradeoff for Adaptive Bitrate Streaming in Edge Caching Systems. IEEE Systems Journal. 2020; PP (99):1-4.
Chicago/Turabian StyleNhu-Ngoc Dao; Duy Trong Ngo; Ngoc-Thanh Dinh; Trung V. Phan; Nam D. Vo; Sungrae Cho; Torsten Braun. 2020. "Hit Ratio and Content Quality Tradeoff for Adaptive Bitrate Streaming in Edge Caching Systems." IEEE Systems Journal PP, no. 99: 1-4.
The previous recommendation system applied the matrix factorization collaborative filtering (MFCF) technique to only single domains. Due to data sparsity, this approach has a limitation in overcoming the cold-start problem. Thus, in this study, we focus on discovering latent features from domains to understand the relationships between domains (called domain coherence). This approach uses potential knowledge of the source domain to improve the quality of the target domain recommendation. In this paper, we consider applying MFCF to multiple domains. Mainly, by adopting the implicit stochastic gradient descent algorithm to optimize the objective function for prediction, multiple matrices from different domains are consolidated inside the cross-domain recommendation system (CDRS). Additionally, we design a conceptual framework for CDRS, which applies to different industrial scenarios for recommenders across domains. Moreover, an experiment is devised to validate the proposed method. By using a real-world dataset gathered from Amazon Food and MovieLens, experimental results show that the proposed method improves 15.2% and 19.7% in terms of computation time and MSE over other methods on a utility matrix. Notably, a much lower convergence value of the loss function has been obtained from the experiment. Furthermore, a critical analysis of the obtained results shows that there is a dynamic balance between prediction accuracy and computational complexity.
Nam D. Vo; Minsung Hong; Jason J. Jung. Implicit Stochastic Gradient Descent Method for Cross-Domain Recommendation System. Sensors 2020, 20, 2510 .
AMA StyleNam D. Vo, Minsung Hong, Jason J. Jung. Implicit Stochastic Gradient Descent Method for Cross-Domain Recommendation System. Sensors. 2020; 20 (9):2510.
Chicago/Turabian StyleNam D. Vo; Minsung Hong; Jason J. Jung. 2020. "Implicit Stochastic Gradient Descent Method for Cross-Domain Recommendation System." Sensors 20, no. 9: 2510.
Corporate social responsibility (CSR) has been receiving increasing attention in the international community since the Sustainable Development Goals (SDGs) emphasise effective corporate partnership. CSR is one of the most critical instruments linking corporate activities to the SDGs. Among various stakeholders, consumers can play an essential role in motivating companies to become socially responsible. However, there is little evidence from developing countries about the linkage between CSR and consumers. This paper, therefore, examines the relationship between consumers’ perception of a company’s CSR practices and their attitudes towards and intentions on purchasing its goods with empirical evidence from the Vietnamese food industry. The primary data was collected from 622 consumers using processed food in a self-administered survey in Northern Vietnam. Based on the structural equation modelling (SEM) analysis, this study shows that perception of CSR toward community has the most substantial influence on consumers’ attitude, followed by the perception of CSR toward employees and perception of fair operating practices responsibility. Although Vietnamese consumers have knowledge of the CSR in the food processing industry, their response to either good or bad CSR practices is still insufficient. Hence, the Vietnamese government and civil society should actively intervene to strengthen CSR regulations and enhance consumers’ CSR awareness.
Phuong-Mai Nguyen; Nam D. Vo; Nguyen Phuc Nguyen; Yongshik Choo. Corporate Social Responsibilities of Food Processing Companies in Vietnam from Consumer Perspective. Sustainability 2019, 12, 71 .
AMA StylePhuong-Mai Nguyen, Nam D. Vo, Nguyen Phuc Nguyen, Yongshik Choo. Corporate Social Responsibilities of Food Processing Companies in Vietnam from Consumer Perspective. Sustainability. 2019; 12 (1):71.
Chicago/Turabian StylePhuong-Mai Nguyen; Nam D. Vo; Nguyen Phuc Nguyen; Yongshik Choo. 2019. "Corporate Social Responsibilities of Food Processing Companies in Vietnam from Consumer Perspective." Sustainability 12, no. 1: 71.
This paper presents the basic concepts of a scalable recommendation framework (called DakGalBi) that can integrate all possible heterogeneous data sources to provide users with optimized recommendations. The framework consists of three components: the database management system (HBase), machine-learning engine (Spark), and indexing module (Elasticsearch). Hence, the framework enables recommendation systems to deal with heterogeneous data sources in various recommendation scenarios. Our early implementation proved that DakGalBi has significant performance in terms of working with heterogeneous data sources.
Dinh-Nam Vo; Jason J. Jung. Towards Scalable Recommendation Framework with Heterogeneous Data Sources: Preliminary Results. 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) 2018, 632 -636.
AMA StyleDinh-Nam Vo, Jason J. Jung. Towards Scalable Recommendation Framework with Heterogeneous Data Sources: Preliminary Results. 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS). 2018; ():632-636.
Chicago/Turabian StyleDinh-Nam Vo; Jason J. Jung. 2018. "Towards Scalable Recommendation Framework with Heterogeneous Data Sources: Preliminary Results." 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) , no. : 632-636.