Tertiary hash tree-based index structure for high dimensional multimedia data

Dominant features for the content-based image retrieval usually have high-dimensionality. So far, many researches have been done to index such values to support fast retrieval. Still, many existing indexing schemes are suffering from performance degradation due to the curse of dimensionality problem. As an alternative, heuristic algorithms have been proposed to calculate the answer with ??high probability?? at the cost of accuracy. In this paper, we propose a new hash tree-based indexing structure called tertiary hash tree for indexing high-dimensional feature data. Tertiary hash tree provides several advantages compared to the traditional extendible hash structure in terms of resource usage and search performance. Through extensive experiments, we show that our proposed index structure achieves outstanding performance.     

Handling Updates and Crashes in VoD Systems

Though there have been several recent efforts to develop disk based video servers, these approaches have all ignored the topic of updates and disk server crashes. In this paper, we present a priority based model for building video servers that handle two classes of events: user events that could include enter, play, pause, rewind, fast-forward, exit, as well assystem events such as insert, delete, server-down, server-up that correspond to uploading new movie blocks onto the disk(s), eliminating existing blocks from the disk(s), and/or experiencing a disk server crash. We will present algorithms to handle such events. Our algorithms are provably correct, and computable in polynomial time. Furthermore, we guarantee that under certain reasonable conditions, continuing clients experience jitter free presentations. We further justify the efficiency of our techniques with a prototype implementation and experimental results.     

Machine Learning-Based Two-Stage Data Selection Scheme for Long-Term Influenza Forecasting

One popular strategy to reduce the enormous number of illnesses and deaths from a seasonal influenza pandemic is to obtain the influenza vaccine on time. Usually, vaccine production preparation must be done at least six months in advance, and accurate long-term influenza forecasting is essential for this. Although diverse machine learning models have been proposed for influenza forecasting, they focus on short-term forecasting, and their performance is too dependent on input variables. For a country’s long-term influenza forecasting, typical surveillance data are known to be more effective than diverse external data on the Internet. We propose a two-stage data selection scheme for worldwide surveillance data to construct a long-term forecasting model for influenza in the target country. In the first stage, using a simple forecasting model based on the country’s surveillance data, we measured the change in performance by adding surveillance data from other countries, shifted by up to 52 weeks. In the second stage, for each set of surveillance data sorted by accuracy, we incrementally added data as input if the data have a positive effect on the performance of the forecasting model in the first stage. Using the selected surveillance data, we trained a new long-term forecasting model for influenza and perform influenza forecasting for the target country. We conducted extensive experiments using six machine learning models for the three target countries to verify the effectiveness of the proposed method. We report some of the results.     

Monitoring skin condition using life activities on the SNS user documents

Multimedia Tools and Applications - Social networks are not new to the IT landscape. Starting from bulletin boards and chat rooms, they have evolved to include desktop and mobile device...     

BCGAN: A CGAN-based over-sampling model using the boundary class for data balancing

The Journal of Supercomputing - A class imbalance problem occurs when a dataset is decomposed into one majority class and one minority class. This problem is critical in the machine learning...     

Hybrid Segmentation Scheme for Skin Features Extraction Using Dermoscopy Images

Objective and quantitative assessment of skin conditions is essential for cosmeceutical studies and research on skin aging and skin regeneration. Various handcraft-based image processing methods have been proposed to evaluate skin conditions objectively, but they have unavoidable disadvantages when used to analyze skin features accurately. This study proposes a hybrid segmentation scheme consisting of Deeplab v3+ with an Inception-ResNet-v2 backbone, LightGBM, and morphological processing (MP) to overcome the shortcomings of handcraft-based approaches. First, we apply Deeplab v3+ with an Inception-ResNet-v2 backbone for pixel segmentation of skin wrinkles and cells. Then, LightGBM and MP are used to enhance the pixel segmentation quality. Finally, we determine several skin features based on the results of wrinkle and cell segmentation. Our proposed segmentation scheme achieved a mean accuracy of 0.854, mean of intersection over union of 0.749, and mean boundary F1 score of 0.852, which achieved 1.1%, 6.7%, and 14.8% improvement over the panoptic-based semantic segmentation method, respectively.     

UFC-Net with Fully-Connected Layers and Hadamard Identity Skip Connection for Image Inpainting

Image inpainting is an interesting technique in computer vision and artificial intelligence for plausibly filling in blank areas of an image by referring to their surrounding areas. Although its performance has been improved significantly using diverse convolutional neural network (CNN)-based models, these models have difficulty filling in some erased areas due to the kernel size of the CNN. If the kernel size is too narrow for the blank area, the models cannot consider the entire surrounding area, only partial areas or none at all. This issue leads to typical problems of inpainting, such as pixel reconstruction failure and unintended filling. To alleviate this, in this paper, we propose a novel inpainting model called UFC-net that reinforces two components in U-net. The first component is the latent networks in the middle of U-net to consider the entire surrounding area. The second component is the Hadamard identity skip connection to improve the attention of the inpainting model on the blank areas and reduce computational cost. We performed extensive comparisons with other inpainting models using the Places2 dataset to evaluate the effectiveness of the proposed scheme. We report some of the results.     

Two-stage person re-identification scheme using cross-input neighborhood differences

The Journal of Supercomputing - Person re-identification aims to identify images of a particular person captured from different cameras or the same camera under different conditions. Person...     

Sliding window-based LightGBM model for electric load forecasting using anomaly repair

The Journal of Supercomputing - Smart grids have attracted much attention recently for their potential to reduce power system operating and management costs. Smart grid core components include...