RESUMEN

To provide analytic materials for business management for smart retail solutions, it is essential to recognize various customer behaviors (CB) from video footage acquired by in-store cameras. Along with frequent changes in needs and environments, such as promotion plans, product categories, in-store layouts, etc., the targets of customer behavior recognition (CBR) also change frequently. Therefore, one of the requirements of the CBR method is the flexibility to adapt to changes in recognition targets. However, existing approaches, mostly based on machine learning, usually take a great deal of time to re-collect training data and train new models when faced with changing target CBs, reflecting their lack of flexibility. In this paper, we propose a CBR method to achieve flexibility by considering CB in combination with primitives. A primitive is a unit that describes an object's motion or multiple objects' relationships. The combination of different primitives can characterize a particular CB. Since primitives can be reused to define a wide range of different CBs, our proposed method is capable of flexibly adapting to target CB changes in retail stores. In experiments undertaken, we utilized both our collected laboratory dataset and the public MERL dataset. We changed the combination of primitives to cope with the changes in target CBs between different datasets. As a result, our proposed method achieved good flexibility with acceptable recognition accuracy.

Asunto(s)

RESUMEN

Customer activity (CA) in retail environments, which ranges over various shopper situations in store spaces, provides valuable information for store management and marketing planning. Several systems have been proposed for customer activity recognition (CAR) from in-store camera videos, and most of them use machine learning based end-to-end (E2E) CAR models, due to their remarkable performance. Usually, such E2E models are trained for target conditions (i.e., particular CA types in specific store spaces). Accordingly, the existing systems are not malleable to fit the changes in target conditions because they require entire retraining of their specialized E2E models and concurrent use of additional E2E models for new target conditions. This paper proposes a novel CAR system based on a hierarchy that organizes CA types into different levels of abstraction from lowest to highest. The proposed system consists of multiple CAR models, each of which performs CAR tasks that belong to a certain level of the hierarchy on the lower level's output, and thus conducts CAR for videos through the models level by level. Since these models are separated, this system can deal efficiently with the changes in target conditions by modifying some models individually. Experimental results show the effectiveness of the proposed system in adapting to different target conditions.

Asunto(s)

RESUMEN

Nowadays, due to the widespread usage of mobile devices and wireless network technologies, we can use various ICT services almost anytime, anywhere even if we are changing our location at that moment. Therefore, mobility management technology have been attracting attention. This technology is to keep communication alive even when a mobile node (MN), which is communicating with the server or some nodes, moves to another network domain. Software Defined Networking (SDN) is used for mobility management to realize effective intra-domain routing that optimizes routes when an MN moves inside an SDN domain. However, many of the approaches mainly focus on intra-domain routing and it is difficult to optimize inter-domain route. In this paper, we focus on this routing optimization problem and propose an SDN based end-to-end routing mechanism specified for mobility management. The proposed routing mechanism can optimize an end-to-end route based on various parameters such as bandwidth, number of domains, and flow operations for mobility after an MN has moved across SDN domains. We carried out some simulational experimentations to evaluate the effect of proposal. It is shown that the proposed routing mechanism can reduce communication delay and enhance network performance. Thus, the proposed routing mechanism can realize effective ICT services.

RESUMEN

As smartphones and other small portable devices become more sophisticated and popular, opportunities for communication and information sharing among such device users have increased. In particular, since it is known that infrastructure-less device-to-device (D2D) communication platforms consisting only of such devices are excellent in terms of, for example, bandwidth efficiency, efforts are being made to merge their information sharing capabilities with conventional infrastructure. However, efficient multi-hop communication is difficult with the D2D communication protocol, and many conventional D2D communication platforms require modifications of the protocol and terminal operating systems (OSs). In response to these issues, this paper reports on a proposed tree-structured D2D communication platform for Android devices that combines Wi-Fi Direct and Wi-Fi functions. The proposed platform, which is expected to be used with general Android 4.0 (or higher) OS equipped terminals, makes it possible to construct an ad hoc network instantaneously without sharing prior knowledge among participating devices. We will show the feasibility of our proposed platform through its design and demonstrate the implementation of a prototype using real devices. In addition, we will report on our investigation into communication delays and stability based on the number of hops and on terminal performance through experimental confirmation experiments.

RESUMEN

After the Great East Japan Earthquake we constructed a community health care information network system. Focusing on the authentication server and portal server capable of SAML&ID-WSF, we proposed an audit trail management system to look over audit events in a comprehensive manner. Through implementation and experimentation, we verified the effectiveness of our proposed audit trail management system.

Asunto(s)