Browsing by Author "Lu, Yi-Shu"

Now showing 1 - 6 of 6

A Grid-based Successive Point-of-Interest Recommendation Method
(2017-01-01)
Gau, Hung-Yi
;
Lu, Yi-Shu
;
Huang, Jiun-Long
;
資訊工程學系
;
Department of Computer Science
With the increasing popularity of location-based social networks (LBSNs), users are able to share the pointof- interests (POIs) they visited by check-ins. By analyzing the users' historical check-in records, POI recommendation can help users get better visiting experiences by recommending POIs which users may be interested in. Although recent successive POI recommendation methods consider geographical influence by measuring distances among POIs, most of them ignore the influence of the regions where the POIs are located. Therefore, we propose a grid-based successive POI recommendation method, named UGSE-LR, to take the regional influence into consideration when recommending POIs. UGSE-LR first splits an area into grids for estimating regional influence. Then, UGSE-LR applies Edge-weighted Personalized PageRank (EdgePPR) for modeling the successive transitions among POIs. Finally, UGSE-LR fuses user preference, regional preference and successive transition preference into a unified recommendation framework. Experimental results on two real LBSN datasets show that our method is more accurate than the state-of-the-art successive POI recommendation methods in terms of precision and recall.
A Skeleton and Gesture Based User Authentication System
(2015)
Lee, Hsueh-Fan
;
Lu, Yi-Shu
;
Huang, Jiun-Long
;
Hu, Chih-Lin
;
資訊工程學系
In this paper, we propose a skeleton and gesture-based user authentication system using depth cameras. When a user would like to register, our system will capture a user\'s skeleton and gesture information and store it into the database. When authenticating a user, our system will capture the user\'s skeleton and gesture information and compare it with the data stored in the database. Experimental results show that the combined use of skeleton and behavioral information is able to improve the accuracy of user authentication.
An Expected Win Rate-Based Real Time Bidding Strategy for Branding Campaign by the Model-Free Reinforcement Learning Model
(2020-01-01)
Shih, Wen-Yueh
;
Lu, Yi-Shu
;
Tsai, Hsiao-Ping
;
Huang, Jiun-Long
;
資訊工程學系
The bidding strategy plays the most important role to help the Demand Side Platforms (DSPs) making bidding decisions on a large number of bid requests in Real Time Bidding (RTB) to satisfy the different objectives of campaigns under the lifetime and budget constraints. In this paper, we focus on branding campaign whose objective is to obtain as many impressions as possible under the lifetime and budget constraints. To achieve the objectives of branding campaigns, we propose a novel expected win rate-based bidding strategy for branding campaign under the lifetime and budget constraints by utilizing a model-free reinforcement learning model. Specifically, to prevent missing good opportunities resulting from submitting extremely low bid prices, the concept of the base winning price is introduced to determine the lower bound of expected winning price. In addition, to obtain more impressions, the concept of the DSP-specified budget spending plan is proposed to determine the proper winning prices. The base expected win rate is then calculated based on the base winning price and the winning price determined by the DSP-specified budget spending plan. Since RTB is a dynamic environment, we propose a novel expected win rate-based bidding strategy named EWDQN which utilizes Deep Q Network (DQN) to dynamically determine the expected win rate according to the base expected win rate and the current status of the RTB market, and then determines the bid price according to the expected win rate. To the best of our knowledge, this is the first research applying the reinforcement learning technique on the bidding strategies for branding campaign. To measure the performance of EWDQN, several experiments are conducted on two real datasets. Experimental results show that EWDQN outperforms the-state-of-the-art bidding strategies for branding campaign in terms of the number of obtained impressions and CPM (cost per thousand impressions).
GLR: A graph-based latent representation model for successive POI recommendation
(2020-01-01)
Lu, Yi-Shu
;
Huang, Jiun-Long
;
資訊工程學系
;
Department of Computer Science
Point-of-Interest (POI) recommendation is an important service in location-based social networks (LBSNs) since it can help a user to discover new POIs for future visiting. In order to provide better recommendation experience, a novel POI recommendation paradigm, named successive POI recommendation, has been proposed. The difference between traditional POI recommendation and successive POI recommendation is that successive POI recommendation focuses on recommending POIs that the target user may like to visit within a time period (e.g., a few hours). To address this problem, we propose a new graph-based latent representation model called GLR, to obtain the latent vectors of temporal successive transition influence and temporal user preference based on the historical check-in records. We also propose a novel method named GLR_GT to employ these latent vectors and geographical influence of POIs to perform successive POI recommendation. Moreover, we also propose an extended method named GLR_GT_LSTM to employ a long short-term memory (LSTM) neural network to model users' complex transition behavior. Several experiments are conducted on some real-world LBSN datasets. Experimental results show that our proposed method GLR_GT_LSTM outperforms the other prior successive POI recommendation methods in terms of precision and recall. (C) 2019 Elsevier B.V. All rights reserved.
On successive point-of-interest recommendation
(2019-05-01)
Lu, Yi-Shu
;
Shih, Wen-Yueh
;
Gau, Hung-Yi
;
Chung, Kuan-Chieh
;
Huang, Jiun-Long
With the increasing popularity of location-based social networks (LBSNs), users are able to share the Point-of-Interests (POIs) they visited by check-ins. By analyzing the users' historical check-in records, POI recommendation can help users get better visiting experience by recommending POIs which users may be interested in. Although recent successive POI recommendation methods consider geographical influence by measuring the distances among POIs, most of them ignore the influence of the regions where the POIs are located. Therefore, we propose in this paper two models to tackle the problem of successive POI recommendation. First, a feature-based successive POI recommendation method, named UGSE-LR, is proposed to take the influence of regions, named regional influence, into consideration when recommending POIs. UGSE-LR first splits an area into grids for estimating regional influence. Then, UGSE-LR applies Edge-weighted Personalized PageRank (EdgePPR) for modeling the successive transitions among POIs. Finally, UGSE-LR fuses user preference, regional influence and successive transition influence into a unified recommendation framework. In addition, with the aid of Recurrent Neural Network (RNN), we propose a latent-factor based successive POI recommendation method, named PEU-RNN, to integrate the sequential visits of POIs and user preference to recommend POIs. First, PEU-RNN adopts the word embedding technique to transform each POI into a latent vector. Then, RNN is used to recommend the POIs depend on the users' historical check-in records. Experimental results on two real LBSN datasets show that our methods are more accurate than the state-of-the-art successive POI recommendation methods in terms of precision and recall. In addition, experimental results also show that PEU-RNN is suitable for the datasets with many check-in records, while UGSE-LR is suitable for the datasets with moderate check-in records.
SPENT: A Successive POI Recommendation Method Using Similarity-based POI Embedding and Recurrent Neural Network with Temporal Influence
(2019-01-01)
Wang, Mu-Fan
;
Lu, Yi-Shu
;
Huang, Jiun-Long
;
資訊工程學系
;
Department of Computer Science
In recent years, successive Point-of-Interest (POI) recommendation has attracted more and more attention and many methods have been proposed to address the problem of successive POI recommendation. In this paper, we propose the SPENT method which uses similarity tree to organize all POIs and applies Word2Vec to perform POI embedding. Then, SPENT uses a recurrent neural network (RNN) to model users' successive transition behavior. We also propose to insert a bath normalization layer in front of the LSTM and a temporal distance gate in the back of the LSTM to improve the performance of SPENT. To compare the performance of SPENT and other prior successive POI recommendation methods, several experiments are conducted on two real datasets, Gowalla and Foursquare. Experimental results show that SPENT outperforms the other prior methods in terms of precision and recall.