The use of closed circuit television (CCTV) surveillance devices is increasing every year to prevent abnormal behaviors, including shoplifting. However, damage from shoplifting is also increasing every year. Thus, there is a need for intelligent CCTV surveillance systems that ensure the integrity of shops, despite workforce shortages. In this study, we propose an automatic detection system of shoplifting behaviors from surveillance videos. Instead of extracting features from the whole frame, we use the Region of Interest (ROI) optical-flow fusion network to highlight the necessary features more accurately.

Visual surveillance through closed circuit television (CCTV) can help to prevent crime. In this paper, we propose an automatic visual surveillance network (AVS-Net), which simultaneously performs image processing and object detection to determine the dangers of situations captured by CCTV. In addition, we add a relation module to infer the relationships of the objects in the images. Experimental results show that the relation module greatly improves classification accuracy, even if there is not enough information.

This study proposes a method to reduce the playing-related musculoskeletal disorders (PRMDs) that often occur among pianists. Specifically, we propose a feasibility test that evaluates several state-of-the-art deep learning algorithms to prevent injuries of pianist. For this, we propose (1) a C3P dataset including various piano playing postures and show (2) the application of four learning algorithms, which demonstrated their superiority in video classification, to the proposed C3P datasets. To our knowledge, this is the first study that attempted to apply the deep learning paradigm to reduce the PRMDs in pianist. The experimental results demonstrated that the classification accuracy is 80% on average, indicating that the proposed hypothesis about the effectiveness of the deep learning algorithms to prevent injuries of pianist is true.

Recently, the importance of mobile cloud computing has increased. Mobile devices can collect personal data from various sensors within a shorter period of time and sensor-based data consists of valuable information from users. Advanced computation power and data analysis technology based on cloud computing provide an opportunity to classify massive sensor data into given labels. Random forest algorithm is known as black box model which is hardly able to interpret the hidden process inside. In this paper, we propose a method that analyzes the variable impact in random forest algorithm to clarify which variable affects classification accuracy the most. We apply Shapley Value with random forest to analyze the variable impact. Under the assumption that every variable cooperates as players in the cooperative game situation, Shapley Value fairly distributes the payoff of variables. Our proposed method calculates the relative contributions of the variables within its classification process. In this paper, we analyze the influence of variables and list the priority of variables that affect classification accuracy result. Our proposed method proves its suitability for data interpretation in black box model like a random forest so that the algorithm is applicable in mobile cloud computing environment.

A top- k query processing is widely used in many applications and mobile environments. An index is used for efficient query processing and layer-based indexing methods are representative to perform the top- k query processing efficiently. However, the existing methods have a problem of high index building time for multidimensional and large data; thus, it is difficult to use them. In this paper, we proposed a new concept of constructing layer-based index, which is called unbalanced layer (UB-Layer). The existing methods construct a layer as a balanced layer with outermost data and wrap the rest of the input data. However, UB-Layer constructs a layer as an unbalanced layer that does not wrap the rest of the data. To construct UB-Layer, we fist divide the dimension of the input data into divided-dimensional data and compute the convex hull in each divided-dimensional data. And then, we combine divided-convex hull to build UB-Layer. We also propose UB-SelectAttribute algorithm for dividing the dimension with major attributes. We demonstrate the superiority of the proposed methods by the performance experiments.

Abstract In order to secure the content of simple object access protocol (SOAP) messages in Web services, several security standards of Web service security, such as XML digital signature, are used. However, the content of a SOAP message, protected with XML digital signature, can be altered without invalidating the signature. Existing methods for detecting XML rewriting attacks are inefficient because the cost of performing detection operation is linear to the height of the SOAP message tree. Thus, each element of SOAP message needs to be accessed and checked. In this paper, we propose an efficient method for detecting XML rewriting attacks on SOAP messages using a histogram. With our method, once the source of attacks is identified, we save it in the form of a histogram, which enables us to maintain a statistical information about the location of the attack in the SOAP message. We can use this information to detect attacks in the future and thus avoid unnecessary check of all elements in the SOAP message. Experiments show that our methods outperform existing methods by several times in many cases. Copyright © 2014 John Wiley & Sons, Ltd.

Many entrepreneurship applications use data as the core concept of their business to better understand the needs of their customers. However, as the size of databases used by these entrepreneurship applications grows and as more users access data through various interactive interfaces, obtaining the result for a top-k query may take long time if the query matches millions of the tuples in the database. Traditionally, layer-based indexing methods are representative for processing top-k queries efficiently. These methods form tuples into a list of layers where the ith layer holds the tuples that can be the top-i answer. Layer-based indexing methods enable us to obtain top-k answers by accessing at most k layers. Most of these methods achieve high accuracy of query answer at the expense of enlarged index construction time. However, we can adjust between accuracy and index construction time to achieve an optimal performance. Thus in this paper, we propose a method, called the adaptive convex skyline (AdaptCS) for efficient-processing top-k queries in entrepreneurship applications. AdaptCS first prunes the data with a virtual threshold point and finds skyline points over the pruned data. Here, by adjusting virtual threshold we are able to achieve optimal performance. Then, AdaptCS divides the skyline into m subregions with projection partitioning method and constructs the convex hull m times for each subregion with virtual objects. Lastly, AdaptCS combines the objects obtained by computing the convex hull. The experimental results show that the proposed method outperforms the existing methods.