One of the most important factors in training object recognition networks using convolutional neural networks (CNN) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation, the annotation process requires considerable human effort. In this paper, we propose a semi-supervised learning (SSL)-based training methodology for object detection, which makes use of automatic labeling of un-annotated data by applying a network previously trained from an annotated dataset. Because an inferred label by the trained network is dependent on the learned parameters, it is often meaningless for re-training the network. To transfer a valuable inferred label to the unlabeled data, we propose a re-alignment method based on co-occurrence matrix analysis that takes into account one-hot-vector encoding of the estimated label and the correlation between the objects in the image. We used an MS-COCO detection dataset to verify the performance of the proposed SSL method and deformable neural networks (D-ConvNets) [1] as an object detector for basic training. The performance of the existing state-of-the-art detectors (D-ConvNets, YOLO v2 [2], and single shot multi-box detector (SSD) [3]) can be improved by the proposed SSL method without using the additional model parameter or modifying the network architecture.

We propose an improved method to accurately localize objects from surveillance camera system. It includes clustering estimation method using clusters analysis and improved fuzzy c-means clustering. It is very useful for herds of cattle localization. Our evaluation shows high accuracy on datasets. Our dataset's target is Korean cattle shed. It means that our method is utilized for surveillance system in Korean cattle shed.

In this paper, we propose an enhanced handover mechanism with new additional primitives and parameters to the media independent handover (MIH) services defined in the IEEE 802.21. The proposed scheme can reduce handover latency for mobile IPv6 (MIPv6) by removing the router discovery time. Moreover, when the proposed mechanism is applied to the FMIPv6, we can increase the probability that the FMIPv6 can be performed in predictive mode by reducing the handover initiation time, thereby we can reduce the expected handover latency in the FMIPv6. In addition, with the proposed scheme, we can design the network cost-effectively by reducing coverage overlap between adjacent cells because the handover initiation time in the FMIPv6 is decreased

This paper presents an exact analysis of a general asymmetric polling system which has a finite-capacity buffer and exhaustive service discipline at each station. To analyze the system we consider a model system in which each station is assumed to have a temporary virtual buffer with infinite capacity attached to the real buffer, while the server is unavailable. It is introduced to store all the messages which are to be lost due to the limitation of the real buffer capacity during the vacation period. At the instant when the server visits a station, using the marginal queue length distribution of the station including the virtual buffer, the intervisit time distribution of the station is derived, The system behavior using the relationship between performance measures and the intervisit time distribution is then investigated.>