Activity recognition is a core aspect of ubiquitous computing applications. In order to deploy activity recognition systems in the real world, we need simple sensing systems with lightweight computational modules to a...Activity recognition is a core aspect of ubiquitous computing applications. In order to deploy activity recognition systems in the real world, we need simple sensing systems with lightweight computational modules to accurately analyze sensed data. In this paper, we propose a simple method to recognize human activities using simple object information involved in activities. We apply activity theory for representing complex human activities and propose a penalized naive Bayes classifier for performing activity recognition. Our results show that our method reduces computation up to an order of magnitude in both learning and inference without penalizing accuracy, when compared to hidden Markov models and conditional random fields.展开更多
为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographica...为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographical,categorical,and temporal factors,while simultaneously considering user activity),简称AU-GCTRS。首先,为缓解数据稀疏性和冷启动问题,引入多维上下文信息;其次,通过挖掘用户签到频率、签到兴趣点数量和签到时间,将用户划分为不同活跃度的群体;最后,综合用户活跃度与上下文分数,将得分高的前K个兴趣点推荐给用户。在真实数据集上进行实验表明,AU-GCTRS算法比其他流行算法更有效地缓解了数据稀疏性和冷启动问题,提高了推荐准确率和召回率。展开更多
Context-aware system is an emerging research area in recent years. Context plays an important role in these systems. In most existing work, context is treated as all rel- ative elements in the environment of an applic...Context-aware system is an emerging research area in recent years. Context plays an important role in these systems. In most existing work, context is treated as all rel- ative elements in the environment of an application, and the scope of context is predefined by the developers during the development. However, it is difficult to analyze, specify, and organize everything in the environment accurately and com- pletely; and even when it is possible, the developed applica- tions are difficult to extend or modify as the requests for en- vironment may change over time. In this paper, we focus on activity-oriented context-aware （AOCA） applications where the requests for environment are highly dependent on user activities, and propose a programming framework for devel- oping AOCA applications. In particular, we first present a concept model for describing the notions of activity-oriented context. Next, based on the concept model, we describe the details of the programming framework as well as a develop- ment tool. Moreover, we provide a platform to support the runtime of AOCA applications, and demonstrate the advan- tages of our programming framework through experimental evaluations.展开更多
基金supported by the Korea Research Foundation under Grant No. KRF-2008-357-D00221
文摘Activity recognition is a core aspect of ubiquitous computing applications. In order to deploy activity recognition systems in the real world, we need simple sensing systems with lightweight computational modules to accurately analyze sensed data. In this paper, we propose a simple method to recognize human activities using simple object information involved in activities. We apply activity theory for representing complex human activities and propose a penalized naive Bayes classifier for performing activity recognition. Our results show that our method reduces computation up to an order of magnitude in both learning and inference without penalizing accuracy, when compared to hidden Markov models and conditional random fields.
文摘为了提高兴趣点(point of interest,POI)推荐的准确性和个性化,提升用户对推荐结果的满意度,针对不同活跃度用户的特点,提出一种融合用户活跃度的上下文感知兴趣点推荐算法(A POI recommendation algorithm that integrates geographical,categorical,and temporal factors,while simultaneously considering user activity),简称AU-GCTRS。首先,为缓解数据稀疏性和冷启动问题,引入多维上下文信息;其次,通过挖掘用户签到频率、签到兴趣点数量和签到时间,将用户划分为不同活跃度的群体;最后,综合用户活跃度与上下文分数,将得分高的前K个兴趣点推荐给用户。在真实数据集上进行实验表明,AU-GCTRS算法比其他流行算法更有效地缓解了数据稀疏性和冷启动问题,提高了推荐准确率和召回率。
基金This research was funded by the National Ba- sic Research Program （973 program） （2015CB352202）, the National High Technology Research and Development Program （863 program） （2015AA01A203）, and the National Natural Science Foundation of China （Grant Nos. 91318301, 61373011, 61321491）.
文摘Context-aware system is an emerging research area in recent years. Context plays an important role in these systems. In most existing work, context is treated as all rel- ative elements in the environment of an application, and the scope of context is predefined by the developers during the development. However, it is difficult to analyze, specify, and organize everything in the environment accurately and com- pletely; and even when it is possible, the developed applica- tions are difficult to extend or modify as the requests for en- vironment may change over time. In this paper, we focus on activity-oriented context-aware （AOCA） applications where the requests for environment are highly dependent on user activities, and propose a programming framework for devel- oping AOCA applications. In particular, we first present a concept model for describing the notions of activity-oriented context. Next, based on the concept model, we describe the details of the programming framework as well as a develop- ment tool. Moreover, we provide a platform to support the runtime of AOCA applications, and demonstrate the advan- tages of our programming framework through experimental evaluations.
