In this paper, we propose Squeezed Convolutional Variational AutoEncoder (SCVAE) for anomaly detection in time series data for Edge Computing in Industrial Internet of Things (IIoT). The proposed model is applied to labeled time series data from UCI datasets for exact performance evaluation, and applied to real world data for indirect model performance comparison. In addition, by comparing the models before and after applying Fire Modules from SqueezeNet, we show that model size and inference times are reduced while similar levels of performance is maintained.
30 March 2024 in International Journal of Medical Informatics
The global economy is under great shock again in 2020 due to the COVID-19 pandemic; it has not been long since the global financial crisis in 2008. Therefore, we investigate the evolution of the complexity of the cryptocurrency market and analyze the characteristics from the past bull market in 2017 to the present the COVID-19 pandemic. To confirm the evolutionary complexity of the cryptocurrency market, three general complexity analyses based on nonlinear measures were used: approximate entropy (ApEn), sample entropy (SampEn), and Lempel-Ziv complexity (LZ). We analyzed the market complexity/unpredictability for 43 cryptocurrency prices that have been trading until recently. In addition, three non-parametric tests suitable for non-normal distribution comparison were used to cross-check quantitatively. Finally, using the sliding time window analysis, we observed the change in the complexity of the cryptocurrency market according to events such as the COVID-19 pandemic and vaccination. This study is the first to confirm the complexity/unpredictability of the cryptocurrency market from the bull market to the COVID-19 pandemic outbreak. We find that ApEn, SampEn, and LZ complexity metrics of all markets could not generalize the COVID-19 effect of the complexity due to different patterns. However, market unpredictability is increasing by the ongoing health crisis.
The aim of this research is to propose a binary segmentation algorithm to detect the change points in financial time-series based on the Iterative Cumulative Sum of Squares (ICSS). The proposed algorithm, entitled KW-ICSS, utilizes the non-parametric Kruskal-Wallis test in cross-validation procedures. In this regard, KW-ICSS can quickly detect the change points in non-normally distributed time-series with a small number of observations after the change points than the state-of-the-art ICSS algorithm, entitled AIT-ICSS. For the simulated financial time-series whose true location of the change point is known, KW-ICSS detects the change points with the average true positive rate of 81% for the different number of change points, whereas AIT-ICSS only exhibits 72.57%. Also, KW-ICSS’s mean absolute deviation between the true and detected change points is less than that of AIT-ICSS for different significance levels. The experiment also finds that the significance level, the model parameter, should be set to less than 10%. For the real-world financial time-series whose true location of change points is unknown, KW-ICSS’s robust detection of change points is observed from fewer detected change points and longer intervals between them. Furthermore, KW-ICSS’s trend prediction for the short-term future performs with an average of 92.47% accuracy, whereas AIT-ICSS shows 90.69%. Therefore, we claim that KW-ICSS successfully improves AIT-ICSS.
Online advertising is becoming an important direction in the advertising industry with its strengths in diverse users, strong interactions, real-time feedback, and expandability. Online advertisement (Ads) can show great marketing ability by processing data from multiple channels to convey information, understanding what users want, and approaching them easily. Moreover, predicting the click-through rate (CTR) can increase advertisement revenue and user satisfaction. However, advertising data contains many features, and the amount is growing rapidly. This can be alleviated through the segmentation of users with similar interests. We assumed that the change of interest of a user could be predicted by other users’ change of interest. More specifically, similar users will change their interest in a similar direction. On the basis of this idea, we proposed a novel model, the Deep User Segment Interest Network, to improve CTR prediction. We suggested three novel layers for improving performance: i) an individual interest extractor, ii) a segment interest extractor, and iii) a segment interest activation. These layers captures the latent interest of each user and creates the expressive interest representation of the segment by aggregating each user’s interest. We conducted experiments using TaoBao data, which are a kind of real commercial data from an advertising platform, to confirm the CTR prediction improvement by reflecting the segment interest. The proposed algorithm obtained an AUC gain of 0.0029 with a behavior sequence length of 100. This performance exhibited the greatest improvement over other baselines, indicating the proposed method’s potential contribution to business improvement.