Search

A well-established financial trading system should well perform in resource allocation, risk management, and sustainability. In this paper, we propose a self-management portfolio system with adaptive association mining for practical applications. The system allocates funds into independent units for risk management, and utilizes association mining and adaptive closing mechanism for resource allocation and sustainability, and adopts a self-management module for monitoring positions. The proposed system boosts the annual return and Sharpe ratio to 9.1% and 0.578 (increased to 2.28 and 2.48 times), and reduces the drawdown risk to 34.6% (decreased to almost half). Furthermore, the system rapidly closes the stock positions to avoid drawdown risk in the bear markets, and gradually increases the stock positions when the market turns into bull. Compared with benchmarks, proposed system outperforms all benchmarks in all measurements and on randomly sampled dataset.

Short term load forecasting (STLF) plays an essential role for reliable and economic operation of a power system. In general, the accuracies of the STLF algorithms are dependent on the representation of the input raw data. This paper proposes to use Bag of Words (BoW) model as the data representation to achieve improved accuracy of STLF. As verified in the experiments, the proposed representation of time series load data can drastically improve various STLF algorithms for a microgrid system --- a rather challenging case for load forecasting due to its smaller capacity and higher randomness.

An anomaly, or outlier, is an object exhibiting differences that suggest it belongs to an as-yet undefined class or category. Early detection of anomalies often proves of great importance because they may correspond to events such as fraud, spam, or device malfunctions. By automating the creation of a ranking or list of deviations, we can save time and decrease the cognitive overload of the individuals or groups responsible for responding to such events. Over the years many anomaly and outlier metrics have been developed. In this paper we propose a clustering-based score ensembling method for outlier detection. Using benchmark datasets we evaluate quantitatively the robustness and accuracy of different ensemble strategies. We find that ensembling strategies offer only limited value for increasing overall performance, but provide robustness by negating the influence of severely underperforming models.

Unsupervised domain adaptation deals with scenarios in which labeled data are available in the source domain, but only unlabeled data can be observed in the target domain. Since the classifiers trained by source-domain data would not be expected to generalize well in the target domain, how to transfer the label information from source to target-domain data is a challenging task. A common technique for unsupervised domain adaptation is to match cross-domain data distributions, so that the domain and distribution differences can be suppressed. In this paper, we propose to utilize the label information inferred from the source domain, while the structural information of the unlabeled target-domain data will be jointly exploited for adaptation purposes. Our proposed model not only reduces the distribution mismatch between domains, improved recognition of target-domain data can be achieved simultaneously. In the experiments, we will show that our approach performs favorably against the state-of-the-art unsupervised domain adaptation methods on benchmark data sets. We will also provide convergence, sensitivity, and robustness analysis, which support the use of our model for cross-domain classification.

Botnets are one of most serious threats in cyber security. Many previous studies have been proposed for botnet detection. Among those approaches, one of main tracks focuses on extracting informative features from network traffic flows. Nevertheless, most features of interest are extracted from the information of a single connection, such as flow duration, flow packet size etc. In this paper, we proposed an novel feature, which is able to detect a long-term behavior of botnets. More specifically, we aim to extract a malware beacon from the periodic communication between bots and bot master. Besides the regular communication pattern, we also explore several types of botnet behavior to leverage the effectiveness of the proposed feature. Our experimental results show that our proposed periodic communication signature could be one of effective features for detecting compromised devices.

Debris flows are natural disasters, with soil mass, rocks, and water traveling down a mountainside slope. Debris flows are extremely dangerous; their occurrence incurs huge losses to life and property. The purpose of this research is to develop debris flow detection and emergency evacuation systems. A bag-of-words model is established for analyzing the features of debris flow events, and an anomaly-detection principal component analysis (PCA) model is proposed to detect debris flow. Using real-time debris flow prediction and monitoring, a stochastic optimization model for evacuation planning is formulated. Case studies of debris flow detection in Shenmu village and Fengchiu, central Taiwan, are conducted. Shenmu village and Fengchiu are areas of high potential debris flow, and each has a population of around 800 people. The results show that combining bag-of-words and anomaly-detection PCA methods could predict 6 out of 8 occurrences of actual events, providing a prediction rate of 75 %. In addition, the models make 13 predictions, and 6 of them are correct, providing a prediction accuracy of 46 %. Optimal parameters (including window size, bag length, filter ratio of training data, and anomaly threshold) of the models are also examined to increase the accuracy of debris flow prediction.

While the task of visual summarization aims to select representative images from an image collection, we solve a unique problem of style-oriented landmark retrieval and summarization from photographic images of a city. Instead of performing summarization or clustering on landmark images from a city, we allow the user to provide a query input which is not from the city of interest, while the goal is to retrieve and summarize the landmark images with similar style-dependent landmark images, followed by a style-consistent image summarization across landmark categories. As a result, our summarized outputs from various landmarks would exhibit similar image style as that of the query. Our experiments will confirm that the use of our proposed method is able to perform favorably against existing or baseline approaches with improved query-dependent style consistency.

In this paper, we propose a novel algorithm of Generalized Joint Distribution Adaptation (G-JDA) for heterogeneous domain adaptation (HDA), which associates and recognizes cross-domain data observed in different feature spaces (and thus with different dimensionality). With the objective to derive a domain-invariant feature subspace for relating source and target-domain data, our G-JDA learns a pair of feature projection matrices (one for each domain), which allows us to eliminate the difference between projected cross-domain heterogeneous data by matching their marginal and class-conditional distributions. We conduct experiments on cross-domain classification tasks using data across different features, datasets, and modalities. We confirm that our G-JDA would perform favorably against state-of-the-art HDA approaches.

While domain adaptation (DA) aims to associate the learning tasks across data domains, heterogeneous domain adaptation (HDA) particularly deals with learning from cross-domain data which are of different types of features. In other words, for HDA, data from source and target domains are observed in separate feature spaces and thus exhibit distinct distributions. In this paper, we propose a novel learning algorithm of Cross-Domain Landmark Selection (CDLS) for solving the above task. With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation. In addition, the adaptation capabilities of such cross-domain landmarks can be determined accordingly. This is the reason why our CDLS is able to achieve promising HDA performance when comparing to state-of-the-art HDA methods. We conduct classification experiments using data across different features, domains, and modalities. The effectiveness of our proposed method can be successfully verified.

Many real-world visual classification tasks require one to recognize test data in a particular domain of interest, while the training data can only be collected from a different domain. This can be viewed as the problem of unsupervised domain adaptation, in which the domain difference and the lack of cross-domain label/correspondence information make the recognition task very difficult. In this paper, we propose to exploit the cross-domain data correspondence using both observed data similarity and labels transferred from the source domain. This allows us to perform distribution matching for cross-domain data with recognition guarantees. Our experiments on three different cross-domain visual classification tasks would confirm the effectiveness of our method, which is shown to perform favorably against state-of-the-art unsupervised domain adaptation approaches.

In real-world video surveillance applications, one often needs to recognize face images from a very long distance. Such recognition tasks are very challenging, since such images are typically with very low resolution (VLR). However, if one simply downsamples high-resolution (HR) training images for recognizing the VLR test inputs, or if one directly upsamples the VLR inputs for matching the HR training data, the resulting recognition performance would not be satisfactory. In this paper, we propose a joint face hallucination and recognition approach based on sparse representation. Given a VLR input image, our method is able to synthesize its person-specific HR version with recognition guarantees. In our experiments, we consider two different face image datasets. Empirical results will support the use of our approach for both VLR face recognition. In addition, compared to state-of-the-art super-resolution (SR) methods, we will also show that our method results in improved quality for the recovered HR face images.