1 October 2018 in IEEE Access
The rapid growth of scientific papers makes it difficult to find relevant and appropriate citations. Contextaware citation recommendation aims to overcome this problem by providing a list of scientific papers given a short passage of text. In this paper, we propose a LSTM based model for context-aware citation recommendation, which firstly learns the distributed representations of the citation contexts and the scientific papers separately based on LSTM, and then measures the relevance based on the learned distributed representation of citation contexts and the scientific papers. Finally, the scientific papers with high relevance scores are selected as the recommendation list. In particular, we try to incorporate author information, venue information and content information in scientific paper distributed vector representation. Furthermore, we integrate author information of the given context in citation context distributed vector representation. Thus the proposed model makes personalized context-aware citation recommendation possible, which is a new issue that few papers addressed in the past. When conducting experiments on the ACL Anthology Network (AAN) and DBLP datasets, the results demonstrate the proposed LSTM based model for context-aware citation recommendation is able to achieve considerable improvement over previous context-aware citation recommendation approaches. The personalized recommendation approach is also competitive with the non-personalized recommendation approach.
27 April 2023 in IEEE Transactions on Industrial Electronics
Huge amounts of text data describing malfunction, defect, and safety hazard have been recorded in power maintenance sectors. Effectively mining such text data, and thus, classifying electrical fault types from text data bring the potential to considerably reduce the manpower in a variety of industrial applications such as power scheduling and periodic report generation. However, short sentences in verbal expressions, pervasive technical terms of electronics, and imbalanced fault type distribution put an enormous hindrance to fault diagnosis using unstructured data analytic approaches. It has conclusively been shown that deep learning is highly effective to learn representations for unstructured data. In this paper, we design and implement a deep-learning-based electrical fault identification framework, of which the core component is supervised Sentence Embedding combined with an Imbalanced Classification (SEIC) model. SEIC incorporates very little domain knowledge represented by class-related keywords into supervised sentence embedding. Meanwhile, both sentence embedding training and imbalanced multilabel classification training are guided by one unified objective. Experimental results on real-world dataset demonstrate that SEIC significantly improves the accuracy of electrical fault classification over existing deep models. Key factors affecting SEIC are carefully explored by an extensive ablation study.
22 April 2019 in IEEE Access
Quality of Service (QoS) value is usually unknown in service recommendation practice. There are some matrix factorization approaches for predicting the unknown value with a user-service model, which uses a single collaboration with the user’s neighbor when looking for different services. However, the QoS value is highly related to the service provider and participants. The services are considered in various collaboration based on different users. By considering the context of services, this paper proposes a QoS prediction model using tensor decomposition based on service collaboration, called Service-oriented Tensor (SOT). The prediction approach analyzes service collaboration from other similar services and relevant users by using a three-order tensor. Compared with the traditional model, the experiment results show that the proposed model achieves better prediction accuracy.
30 October 2019 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
High-level synthesis (HLS) allows hardware designers to think algorithmically and not worry about low-level, cycle-by-cycle details. This provides the ability to quickly explore the architectural design space and tradeoffs between resource utilization and performance. Unfortunately, security evaluation is not a standard part of the HLS design flow. In this article, we aim to understand the effects of memory-based HLS optimizations on power side-channel leakage. We use Xilinx Vivado HLS to develop different cryptographic cores, implement them on a Spartan-6 FPGA, and collect power traces. We evaluate the designs with respect to resource utilization, performance, and information leakage through power consumption. We have two important observations and contributions. First, the choice of resource optimization directive results in different levels of side-channel vulnerabilities. Second, the partitioning optimization directive can greatly compromise the hardware cryptographic system through power side-channel leakage due to the deployment of memory control logic. We describe an evaluation procedure for power side-channel leakage and use it to make best-effort recommendations about how to design more secure architectures in the cryptographic domain.