Sunbin Shin - Revision history

Kelab: /* Conditional Generative Adversarial Network-Based Travel Route Recommendation */

2025-10-05T15:15:46Z

Conditional Generative Adversarial Network-Based Travel Route Recommendation

← Older revision		Revision as of 00:15, 6 October 2025
Line 26:		Line 26:
	Sunbin Shin, Luong Vuong Nguyen, Grzegorz J. Nalepa, Paulo Novais, Xuan Hau Pham, Jason J. Jung; ISSN=1546-2226; DOI:10.32604/cmc.2025.070613;		Sunbin Shin, Luong Vuong Nguyen, Grzegorz J. Nalepa, Paulo Novais, Xuan Hau Pham, Jason J. Jung; ISSN=1546-2226; DOI:10.32604/cmc.2025.070613;

	Journal: Computers, Materials & ~~Criteria~~ (Tech Science Press)		Journal: Computers, Materials & Continua (Tech Science Press)

	https://doi.org/10.32604/cmc.2025.070613		https://doi.org/10.32604/cmc.2025.070613

	"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a users unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."		"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a users unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."

Kelab: /* Conditional Generative Adversarial Network-Based Travel Route Recommendation */

2025-10-05T15:14:00Z

Conditional Generative Adversarial Network-Based Travel Route Recommendation

← Older revision		Revision as of 00:14, 6 October 2025
Line 24:		Line 24:
	== Journal Publications ==		== Journal Publications ==
	=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===		=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===
	Sunbin Shin, Luong Vuong Nguyen, Grzegorz J. Nalepa, Paulo Novais, Xuan Hau Pham, Jason J. Jung; ISSN=1546-2226; DOI:10.32604/cmc.2025.070613		Sunbin Shin, Luong Vuong Nguyen, Grzegorz J. Nalepa, Paulo Novais, Xuan Hau Pham, Jason J. Jung; ISSN=1546-2226; DOI:10.32604/cmc.2025.070613;

			Journal: Computers, Materials & Criteria (Tech Science Press)

	https://doi.org/10.32604/cmc.2025.070613		https://doi.org/10.32604/cmc.2025.070613

	"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a users unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."		"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a users unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."

Kelab: /* Journal Publications */

2025-10-05T15:12:04Z

Journal Publications

← Older revision		Revision as of 00:12, 6 October 2025
Line 23:		Line 23:

	== Journal Publications ==		== Journal Publications ==
			=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===
			Sunbin Shin, Luong Vuong Nguyen, Grzegorz J. Nalepa, Paulo Novais, Xuan Hau Pham, Jason J. Jung; ISSN=1546-2226; DOI:10.32604/cmc.2025.070613

	https://doi.org/10.32604/cmc.2025.070613		https://doi.org/10.32604/cmc.2025.070613

	~~=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===~~		"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a users unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."
	"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a user’s profile. This vector uniquely fuses embeddings from a Heterogeneous Information Network (HIN) to model complex user-place-route relationships, a Recurrent Neural Network (RNN) to capture sequential path dynamics, and Neural Collaborative Filtering (NCF) to incorporate collaborative signals from the wider user base. This comprehensive condition, further enhanced with features representing user interaction confidence and uncertainty, steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations, effectively mitigating the data sparsity problem. Recommendations are then formulated using an Anchor-and-Expand algorithm, which selects relevant starting Points of Interest (POI) based on user history, then expands routes through latent similarity matching and geographic coherence optimization, culminating in Traveling Salesman Problem (TSP)-based route optimization for practical travel distances. Experiments on a real-world check-in dataset validate our model’s unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the ~~model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’~~ past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."

Kelab: /* Research Experience */

2025-10-05T15:06:11Z

Research Experience

← Older revision		Revision as of 00:06, 6 October 2025
Line 13:		Line 13:
	* Generative AI		* Generative AI
	* BigData		* BigData

	~~== Research Experience ==~~

	== Project ==		== Project ==

Kelab: /* Teaching */

2025-10-05T15:05:24Z

Teaching

← Older revision		Revision as of 00:05, 6 October 2025
Line 29:		Line 29:
	=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===		=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===
	"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a user’s profile. This vector uniquely fuses embeddings from a Heterogeneous Information Network (HIN) to model complex user-place-route relationships, a Recurrent Neural Network (RNN) to capture sequential path dynamics, and Neural Collaborative Filtering (NCF) to incorporate collaborative signals from the wider user base. This comprehensive condition, further enhanced with features representing user interaction confidence and uncertainty, steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations, effectively mitigating the data sparsity problem. Recommendations are then formulated using an Anchor-and-Expand algorithm, which selects relevant starting Points of Interest (POI) based on user history, then expands routes through latent similarity matching and geographic coherence optimization, culminating in Traveling Salesman Problem (TSP)-based route optimization for practical travel distances. Experiments on a real-world check-in dataset validate our model’s unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’ past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."		"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a user’s profile. This vector uniquely fuses embeddings from a Heterogeneous Information Network (HIN) to model complex user-place-route relationships, a Recurrent Neural Network (RNN) to capture sequential path dynamics, and Neural Collaborative Filtering (NCF) to incorporate collaborative signals from the wider user base. This comprehensive condition, further enhanced with features representing user interaction confidence and uncertainty, steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations, effectively mitigating the data sparsity problem. Recommendations are then formulated using an Anchor-and-Expand algorithm, which selects relevant starting Points of Interest (POI) based on user history, then expands routes through latent similarity matching and geographic coherence optimization, culminating in Traveling Salesman Problem (TSP)-based route optimization for practical travel distances. Experiments on a real-world check-in dataset validate our model’s unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’ past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."

	~~== Domestic Conference Papers ==~~

	~~== Teaching ==~~

Kelab: /* Research Experience */

2025-10-05T15:04:02Z

Research Experience

← Older revision		Revision as of 00:04, 6 October 2025
Line 21:		Line 21:
	** Hackathon in Ulsan - Scenery in Ulsan Taken with Drone		** Hackathon in Ulsan - Scenery in Ulsan Taken with Drone

	* Jan. 2023 - Nov. 2023: ~~SangMyung~~ University		* Jan. 2023 - Nov. 2023: Sang-Myung University
	** LSTM Stock Predict Application - iOS, Colab, NodeJS		** LSTM Stock Predict Application - iOS, Colab, NodeJS

Kelab: /* Journal Publications */

2025-10-05T15:03:26Z

Journal Publications

← Older revision		Revision as of 00:03, 6 October 2025
Line 25:		Line 25:

	== Journal Publications ==		== Journal Publications ==
			https://doi.org/10.32604/cmc.2025.070613

			=== '''Conditional Generative Adversarial Network-Based Travel Route Recommendation''' ===
			"Recommending personalized travel routes from sparse, implicit feedback poses a significant challenge, as conventional systems often struggle with information overload and fail to capture the complex, sequential nature of user preferences. To address this, we propose a Conditional Generative Adversarial Network (CGAN) that generates diverse and highly relevant itineraries. Our approach begins by constructing a conditional vector that encapsulates a user’s profile. This vector uniquely fuses embeddings from a Heterogeneous Information Network (HIN) to model complex user-place-route relationships, a Recurrent Neural Network (RNN) to capture sequential path dynamics, and Neural Collaborative Filtering (NCF) to incorporate collaborative signals from the wider user base. This comprehensive condition, further enhanced with features representing user interaction confidence and uncertainty, steers a CGAN stabilized by spectral normalization to generate high-fidelity latent route representations, effectively mitigating the data sparsity problem. Recommendations are then formulated using an Anchor-and-Expand algorithm, which selects relevant starting Points of Interest (POI) based on user history, then expands routes through latent similarity matching and geographic coherence optimization, culminating in Traveling Salesman Problem (TSP)-based route optimization for practical travel distances. Experiments on a real-world check-in dataset validate our model’s unique generative capability, achieving scores ranging from 0.163 to 0.305, and near-zero scores between 0.002 and 0.022. These results confirm the model’s success in generating novel travel routes by recommending new locations and sequences rather than replicating users’ past itineraries. This work provides a robust solution for personalized travel planning, capable of generating novel and compelling routes for both new and existing users by learning from collective travel intelligence."

	== Domestic Conference Papers ==		== Domestic Conference Papers ==

	== Teaching ==		== Teaching ==

Kelab: /* Project */

2024-03-25T06:20:54Z

Project

← Older revision		Revision as of 15:20, 25 March 2024
Line 17:		Line 17:

	== Project ==		== Project ==

			* Aug. 2018 - Aug. 2018
			** Hackathon in Ulsan - Scenery in Ulsan Taken with Drone

			* Jan. 2023 - Nov. 2023: SangMyung University
			** LSTM Stock Predict Application - iOS, Colab, NodeJS

	== Journal Publications ==		== Journal Publications ==

Kelab: /* Education */

2024-02-29T06:02:34Z

Education

← Older revision		Revision as of 15:02, 29 February 2024
Line 4:		Line 4:

	* Mar 2024 - Present: Chung-Ang University		* Mar 2024 - Present: Chung-Ang University
	** M.S. Knowledge Engineering, Computer Science & Engineering, Seoul, South Korea		** M.S. Degree Knowledge Engineering, Computer Science & Engineering, Seoul, South Korea

	* Mar 2020 - Feb. 2024: Sang-Myung University		* Mar 2020 - Feb. 2024: Sang-Myung University

Kelab: /* Education */

2024-02-29T06:02:11Z

Education

← Older revision		Revision as of 15:02, 29 February 2024
Line 4:		Line 4:

	* Mar 2024 - Present: Chung-Ang University		* Mar 2024 - Present: Chung-Ang University
	** Knowledge Engineering, Computer Science & Engineering, Seoul, South Korea		** M.S. Knowledge Engineering, Computer Science & Engineering, Seoul, South Korea

	* Mar 2020 - Feb. 2024: Sang-Myung University		* Mar 2020 - Feb. 2024: Sang-Myung University