Search

With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing. Although the application of machine learning (ML) techniques in electronic design automation (EDA) can trace its history back to the 90s, the recent breakthrough of ML and the increasing complexity of EDA tasks have aroused more interests in incorporating ML to solve EDA tasks. In this paper, we present a comprehensive review of existing ML for EDA studies, organized following the EDA hierarchy., Comment: Accepted by TODAES. The first 10 authors are ordered alphabetically

In this article, the vibration control effect of the multiunit impact damper under stationary random excitation and seismic excitation is studied, based on both the elastic and nonlinear benchmark structures. The benchmark structure is a nonlinear steel frame structure, which can calculate the nonlinear response by considering the material nonlinearity at the ends of the beam and column. To analyze the influence of various system parameters on the performance of the multiunit impact damper, such as the number of units, mass ratio, damping ratio, and gap clearance, a great number of parameter studies are carried out. In addition, the control effects of the multiunit impact damper on elastic and nonlinear structures are compared to analyze the influence of structural nonlinearity on the performance of the multiunit impact damper. The results show that a lightweight multiunit impact damper with reasonable parameters can significantly reduce the root mean square displacement response of the benchmark structure. Furthermore, the structural nonlinearity will lead to a decrease in the vibration control performance of the multiunit impact damper. The reasons for this phenomenon are that the effective momentum exchange and energy dissipation of the multiunit impact damper will decrease when the benchmark structure responds in a nonlinear state.

The Dark Web is a web-based content based on anonymous communication systems that protects users and protects anonymity through technologies such as traffic encryption, obfuscation, and forwarding. Due to the strong protection of anonymity, the Dark Web has gradually become the main channel for the sale and distribution of harmful content and banned items. The limited web-site coverage in the Dark Web, outdated stale data, and the lack of comprehensive and in-depth analysis and research motivated us to conduct an in-depth Dark Web research. On this basis, this article analyzes and summarizes the current status of Dark Web communication technology, Dark Web research methods and research status, and discusses the challenges of Dark Web re-search.

To achieve robust motion estimation in visually degraded environments, thermal odometry has been an attraction in the robotics community. However, most thermal odometry methods are purely based on classical feature extractors, which is difficult to establish robust correspondences in successive frames due to sudden photometric changes and large thermal noise. To solve this problem, we propose ThermalPoint, a lightweight feature detection network specifically tailored for producing keypoints on thermal images, providing notable anti-noise improvements compared with other state-of-the-art methods. After that, we combine ThermalPoint with a novel radiometric feature tracking method, which directly makes use of full radiometric data and establishes reliable correspondences between sequential frames. Finally, taking advantage of an optimization-based visual-inertial framework, a deep feature-based thermal-inertial odometry (TP-TIO) framework is proposed and evaluated thoroughly in various visually degraded environments. Experiments show that our method outperforms state-of-the-art visual and laser odometry methods in smoke-filled environments and achieves competitive accuracy in normal environments.

Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and under the forms of constant weights or fixed constraints. To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention weight and the other is modeled by a dynamic and context-aware attention weight. We also extend the social effects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that different social effects in two domains could interact with each other and jointly influence user preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social effects. Experiments on one benchmark dataset and a commercial dataset verify the efficacy of the key components in our model. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods., Comment: Accepted by WWW2019 as a full paper with oral presentation

This paper targets a general popularity prediction problem for event sequence, which has recently gained great attention due to its extensive applications in various domains. Feature driven method and point process method are two basic thinking paradigms to tackle the prediction problem, but both of them suffer from limitations. In this paper, we propose PreNets unifying the two thinking paradigms in an adversarial manner. On one side, feature driven model acts like a 'critic' who aims to discriminate the predicted popularity from the real one based on a set of temporal features from the sequence. On the other side, point process model acts like an 'interpreter' who recognizes the dynamic patterns in sequence to generate a predicted popularity that can fool the 'critic'. Through a Wasserstein learning based two-player game, the training loss of the 'critic' guides the 'interpreter' to better exploit the sequence patterns and enhance prediction, while the 'interpreter' pushes the 'critic' to select effective early features that helps discrimination. This mechanism enables the framework to absorb the advantages of both feature driven and point process methods. Empirical results show that PreNets achieves significant MAPE improvement for both Twitter cascade and Amazon review prediction.

The reinforced concrete (RC) frames infilled with masonry walls are widely used in buildings. It has been well recognized that the arrangement of tie-columns can improve the wall integrity and seismic performance. However, the existing cast-in-situ tie-column (CSTC) has some problems, and a new type of fabricated tie-column (FTC) which can be recycled for secondary use is proposed in this study. Two specimens, the wall constrained by the cast-in-situ tie-columns (W-CSTC) and the wall constrained by the fabricated tie-columns (W-FTC), were designed and constructed. Low cyclic loading tests were carried out and some parameters, such as the failure modes, hysteretic curves and so forth, were used to evaluate the applicability of the FTC. The results show the W-FTC has a certain initial stiffness and strength, favorable deformation capacity, and the FTC can not only enhance the wall integrity to meet the functional requirements of tie-columns, but also solve the connection problems and reduce the adverse effects on the frame structure.