Enhancing Unsupervised Anomaly Detection With Score-Guided Network.

Anomaly detection plays a crucial role in various real-world applications, including healthcare and finance systems. Owing to the limited number of anomaly labels in these complex systems, unsupervised anomaly detection methods have attracted great attention in recent years. Two major challenges faced by the existing unsupervised methods are as follows: 1) distinguishing between normal and abnormal data when they are highly mixed together and 2) defining an effective metric to maximize the gap between normal and abnormal data in a hypothesis space, which is built by a representation learner. To that end, this work proposes a novel scoring network with a score-guided regularization to learn and enlarge the anomaly score disparities between normal and abnormal data, enhancing the capability of anomaly detection. With such score-guided strategy, the representation learner can gradually learn more informative representation during the model training stage, especially for the samples in the transition field. Moreover, the scoring network can be incorporated into most of the deep unsupervised representation learning (URL)-based anomaly detection models and enhances them as a plug-in component. We next integrate the scoring network into an autoencoder (AE) and four state-of-the-art models to demonstrate the effectiveness and transferability of the design. These score-guided models are collectively called SG-Models. Extensive experiments on both synthetic and real-world datasets confirm the state-of-the-art performance of SG-Models.

Anomaly Detection of Time Series With Smoothness-Inducing Sequential Variational Auto-Encoder.

Deep generative models have demonstrated their effectiveness in learning latent representation and modeling complex dependencies of time series. In this article, we present a smoothness-inducing sequential variational auto-encoder (VAE) (SISVAE) model for the robust estimation and anomaly detection of multidimensional time series. Our model is based on VAE, and its backbone is fulfilled by a recurrent neural network to capture latent temporal structures of time series for both the generative model and the inference model. Specifically, our model parameterizes mean and variance for each time-stamp with flexible neural networks, resulting in a nonstationary model that can work without the assumption of constant noise as commonly made by existing Markov models. However, such flexibility may cause the model fragile to anomalies. To achieve robust density estimation which can also benefit detection tasks, we propose a smoothness-inducing prior over possible estimations. The proposed prior works as a regularizer that places penalty at nonsmooth reconstructions. Our model is learned efficiently with a novel stochastic gradient variational Bayes estimator. In particular, we study two decision criteria for anomaly detection: reconstruction probability and reconstruction error. We show the effectiveness of our model on both synthetic data sets and public real-world benchmarks.

Design and performance evaluation of dynamic wavelength scheduled hybrid WDM/TDM PON for distributed computing applications.

This paper investigates the design and implementation of distributed computing applications in local area network. We propose a novel Dynamical Wavelength Scheduled Hybrid WDM/TDM Passive Optical Network, which is termed as DWS-HPON. The system is implemented by using spectrum slicing techniques of broadband light source and overlay broadcast-signaling scheme. The Time-Wavelength Co-Allocation (TWCA) Problem is defined and an effective greedy approach to this problem is presented for aggregating large files in distributed computing applications. The simulations demonstrate that the performance is improved significantly compared with the conventional TDM-over-WDM PON.

Performance Study of 40-Gb/s RZ Signals Through Cascaded Thin-Film Filters with Large Dispersion Slope.

The performance of 40-Gb/s RZ signals through cascaded thinfilm filters is investigated by both numerical and analytical means. It is observed that the filtering effects can reduce the eye closure penalties caused by the large dispersion slope of the thin-film filters. In addition, the performance can be further improved by proper frequency detuning between the signal and the center of the filter. The combined effects of dispersion slope and filtering on 40-Gb/s signals are investigated analytically and explained for typical bit patterns.