Societal and industrial infrastructures and systems increasingly leverage sensors that emit correlated time series. Forecasting of future values of such time series based on recorded historical values has important benefits. Automatically designed models achieve higher accuracy than manually designed models. Given a forecasting task, which includes a dataset and a forecasting horizon, automated design methods automatically search for an optimal forecasting model for the task in a manually designed search space, and then train the identified model using the dataset to enable the forecasting. Existing automated methods face three challenges. First, the search space is constructed by human experts, rending the methods only semi-automated and yielding search spaces prone to subjective biases. Second, it is time consuming to search for an optimal model. Third, training the identified model for a new task is also costly. These challenges limit the practicability of automated methods in real-world settings. To contend with the challenges, we propose a fully automated and highly efficient correlated time series forecasting framework where the search and training can be done in minutes. The framework includes a data-driven, iterative strategy to automatically prune a large search space to obtain a high-quality search space for a new forecasting task. It includes a zero-shot search strategy to efficiently identify the optimal model in the customized search space. And it includes a fast parameter adaptation strategy to accelerate the training of the identified model. Experiments on seven benchmark datasets offer evidence that the framework is capable of state-of-the-art accuracy and is much more efficient than existing methods.

Sensors in cyber-physical systems often capture interconnected processes and thus emit correlated time series (CTS), the forecasting of which enables important applications. The key to successful CTS forecasting is to uncover the temporal dynamics of time series and the spatial correlations among time series. Deep learning-based solutions exhibit impressive performance at discerning these aspects. In particular, automated CTS forecasting, where the design of an optimal deep learning architecture is automated, enables forecasting accuracy that surpasses what has been achieved by manual approaches. However, automated CTS solutions remain in their infancy and are only able to find optimal architectures for predefined hyperparameters and scale poorly to large-scale CTS. To overcome these limitations, we propose AutoCTS+, a joint, scalable framework, to automatically devise effective CTS forecasting models. Specifically, we encode each candidate architecture and accompanying hyperparameters into a joint graph representation. We introduce an efficient Architecture-Hyperparameter Comparator (AHC) to rank all architecture-hyperparameter pairs, and we then further evaluate the top-ranked pairs to select an architecture-hyperparameter pair as the final model. Extensive experiments on six benchmark datasets demonstrate that AutoCTS+ not only eliminates manual efforts but also is capable of better performance than manually designed and existing automatically designed CTS models. In addition, it shows excellent scalability to large CTS.

Correlated time series (CTS) forecasting plays an essential role in many cyber-physical systems, where multiple sensors emit time series that capture interconnected processes. Solutions based on deep learning that deliver state-of-the-art CTS forecasting performance employ a variety of spatio-temporal (ST) blocks that are able to model temporal dependencies and spatial correlations among time series. However, two challenges remain. First, ST-blocks are designed manually, which is time consuming and costly. Second, existing forecasting models simply stack the same ST-blocks multiple times, which limits the model potential. To address these challenges, we propose AutoCTS that is able to automatically identify highly competitive ST-blocks as well as forecasting models with heterogeneous ST-blocks connected using diverse topologies, as opposed to the same ST-blocks connected using simple stacking. Specifically, we design both a micro and a macro search space to model possible architectures of ST-blocks and the connections among heterogeneous ST-blocks, and we provide a search strategy that is able to jointly explore the search spaces to identify optimal forecasting models. Extensive experiments on eight commonly used CTS forecasting benchmark datasets justify our design choices and demonstrate that AutoCTS is capable of automatically discovering forecasting models that outperform state-of-the-art human-designed models.

Sentiment analysis or opinion mining for subject information extraction from the text has become more and more dependent on natural language processing, especially for business and healthcare, since the online products and service reviews affect the consuming behaviors. Word embeddings that can map the words to low-dimensional vector representations have been widely used in natural language processing tasks. But the word embeddings based on context such as Word2Vec and GloVe fail to capture the sentiment information. Most of existing sentiment analysis methods incorporate emotional polarity (positive and negative) to improve the sentiment embeddings for the emotion classification. This article takes advantage of an emotional psychology model to learn the emotional embeddings in Chinese first. In order to combine the semantic space and an emotional space, we present two different purifying models from local (LPM) and global (GPM) perspectives based on Plutchik's wheel of emotions to add the emotional information into word vectors. The two models aim to improve the word vectors so that not only the semantically similar words but also the sentimentally similar words can be closer than before. The Plutchik's wheel of emotions model can give eight-dimensional vector for one word in emotional space that can capture more sentiment information than the binary polarity labels. The obvious advantage of the local purifying model is that it can be fit for any pretrained word embeddings. For the global purifying model, we can get the final emotional embeddings at once. These models have been extended to handle English texts. The experimental results on Chinese and English datasets show that our purifying model can improve the conventional word embeddings and some proposed sentiment embeddings for sentiment classification and multi-emotion classification.

In practice, search keywords have quite different importance when users take search operations. In addition, such keywords may have a certain grammatical relationship among them, which reflect the importance of keywords from the user's perspective intuitively. However, the existing search techniques regard the search keywords as independent and unrelated. In this paper, for the first time, we take the relation among query keywords into consideration and design a keyword weighting algorithm to show the importance of the distinction among them. By introducing the keyword weight to the search protocol design, the search results will be more in line with the user's demand. On top of this, we further design a novel central keyword semantic extension ranked scheme. By extending the central query keyword instead of all keywords, our scheme makes a good tradeoff between the search functionality and efficiency. To better express the relevance between queries and files, we further introduce the TF-IDF rule when building trapdoors and the index. In particular, our scheme supports both data set and keywords updates by using the sub-matrix technique. Our work first gives a basic idea for the design of the central keyword semantic extension ranked scheme, and then presents two secure searchable encryption schemes to meet different privacy requirements under two different threat models. Experiments on the real-world data set show that our proposed schemes are efficient, effective, and secure.

Keyword-based search over encrypted outsourced data has become an important tool in the current cloud computing scenario. The majority of the existing techniques are focusing on multi-keyword exact match or single keyword fuzzy search. However, those existing techniques find less practical significance in real-world applications compared with the multi-keyword fuzzy search technique over encrypted data. The first attempt to construct such a multi-keyword fuzzy search scheme was reported by Wang et al., who used locality-sensitive hashing functions and Bloom filtering to meet the goal of multi-keyword fuzzy search. Nevertheless, Wang's scheme was only effective for a one letter mistake in keyword but was not effective for other common spelling mistakes. Moreover, Wang's scheme was vulnerable to server out-of-order problems during the ranking process and did not consider the keyword weight. In this paper, based on Wang et al.'s scheme, we propose an efficient multi-keyword fuzzy ranked search scheme based on Wang et al.'s scheme that is able to address the aforementioned problems. First, we develop a new method of keyword transformation based on the uni-gram, which will simultaneously improve the accuracy and creates the ability to handle other spelling mistakes. In addition, keywords with the same root can be queried using the stemming algorithm. Furthermore, we consider the keyword weight when selecting an adequate matching file set. Experiments using real-world data show that our scheme is practically efficient and achieve high accuracy.