• Journal of the Korea Convergence Society
• /
• v.12 no.8
• /
• pp.131-144
• /
• 2021

In recent years, China has gradually made clear its decision to modernize the governance system and governance capacity of the government by the virtue of digital transformation. As for the smart prison, as a penal institution of the state, technological reform is a key element in the sustainable development of smart prisons; however, relying on technology does not necessarily lead to a better service experience. Service design concept, as a coordinator of technology and social sustainability, needs to be adapted to the technological integration of smart prisons and to the needs for service design in the prison context in a new mode of thinking about services. This paper takes the development of the Jail Pay financial services system, one of the twelve sub-systems of the Smart Prison, as an entry point to explore the characteristics and shortcomings of the service design approach in achieving sustainable service innovation in the Smart Prison, it proposes an experience-based lead collaborative design (EBLCD) that is suitable for the specific needs in the prison context. The EBLCD is a theoretical framework and practical experience for sustainable service innovation in the construction of smart prisons.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.53-59
• /
• 2018

Due to the recent developments in computer vision technology, complex actions can be recognized with reasonable accuracy in smart cities. In contrast, violence recognition such as events related to fight and knife, has gained less attention. The capability of visual surveillance can be used for detecting fight in streets or in prison centers. In this paper, we proposed a deep learning-based violence recognition method for surveillance cameras. A convolutional neural network (CNN) model is trained and fine-tuned on available benchmark datasets of fights and knives for violence recognition. When an abnormal event is detected, an alarm can be sent to the nearest police station to take immediate action. Moreover, when the probabilities of fight and knife classes are predicted very low, this situation is considered as normal situation. The experimental results of the proposed method outperformed other state-of-the-art CNN models with high margin by achieving maximum 99.21% accuracy.