Abstract--In power systems, an asset class is a group of power equipment that has the same function and shares similar electrical or mechanical characteristics. Predicting failures for different asset classes is critical for electric utilities towards developing cost-effective asset management strategies. Previously, physical age based Weibull distribution has been widely used to failure prediction. However, this mathematical model cannot incorporate asset condition data such as inspection or testing results. As a result, the prediction cannot be very specific and accurate for individual assets. To solve this important problem, this paper proposes a novel and comprehensive data-driven approach based on asset condition data: K-means clustering as an unsupervised learning method is used to analyze the inner structure of historical asset condition data and produce the asset conditional ages; logistic regression as a supervised learning method takes in both asset physical ages and conditional ages to classify and predict asset statuses. Furthermore, an index called average aging rate is defined to quantify, track and estimate the relationship between asset physical age and conditional age. This approach was applied to an urban distribution system in West Canada to predict medium-voltage cable failures. Case studies and comparison with standard Weibull distribution are provided. The proposed approach demonstrates superior performance and practicality for predicting asset class failures in power systems. I. INTRODUCTION oday, more and more electric utilities are mandated by regulators to develop cost-effective long-term asset management strategies to reduce overall cost while maintaining system reliability [1-2]. Sophisticated and optimal asset management strategies can only be established based on the accurate prediction of asset failures in the future.

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that, when equipped with expressive generative distributions (aka. decoders), VAE suffers from learning uninformative latent representations with the observation called KL Varnishing, in which case VAE collapses into an unconditional generative model. In this work, we introduce mutual posterior-divergence regularization, a novel regularization that is able to control the geometry of the latent space to accomplish meaningful representation learning, while achieving comparable or superior capability of density estimation. Experiments on three image benchmark datasets demonstrate that, when equipped with powerful decoders, our model performs well both on density estimation and representation learning.

We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we not only efficiently exploit multi-scale information via fast approximated computation of matrix power but also design learnable spectral filters. Being fully differentiable, LanczosNet facilitates both graph kernel learning as well as learning node embeddings. We show the connection between our LanczosNet and graph based manifold learning methods, especially the diffusion maps. We benchmark our model against several recent deep graph networks on citation networks and QM8 quantum chemistry dataset. Experimental results show that our model achieves the state-of-the-art performance in most tasks.

Abstract--Data in real-world application often exhibit skewed class distribution which poses an intense challenge for machine learning. Conventional classification algorithms are not effective in the case of imbalanced data distribution, and may fail when the data distribution is highly imbalanced. To address this issue, we propose a general imbalanced classification model based on deep reinforcement learning. We formulate the classification problem as a sequential decision-making process and solve it by deep Q-learning network. The agent performs a classification action on one sample at each time step, and the environment evaluates the classification action and returns a reward to the agent. The reward from minority class sample is larger so the agent is more sensitive to the minority class. The agent finally finds an optimal classification policy in imbalanced data under the guidance of specific reward function and beneficial learning environment. Experiments show that our proposed model outperforms the other imbalanced classification algorithms, and it can identify more minority samples and has great classification performance.

Companies new to the space can learn a great deal from early adopters who have invested billions into AI and are now beginning to reap a range of benefits. After decades of extravagant promises and frustrating disappointments, artificial intelligence (AI) is finally starting to deliver real-life benefits to early-adopting companies. Retailers on the digital frontier rely on AI-powered robots to run their warehouses--and even to automatically order stock when inventory runs low. Utilities use AI to forecast electricity demand. A confluence of developments is driving this new wave of AI development.

Richard Yu, CEO of Huawei, recently gave an interview with CNBC. During the chat, Yu confirmed a Huawei voice assistant will launch globally at some point soon. This upcoming voice assistant would be a direct competitor to Google Assistant, Amazon's Alexa, and Apple's Siri, all of which already have a global presence. "In the beginning, we are mainly using Google Assistant and Amazon Alexa" for its smartphones and other smart products, Yu said. "We need more time to build our AI services…later, we will expand this outside of China."

Atop those demands sits the ever-present threat of technology disruption, the forces of innovation that will disrupt their business in the coming years or possibly render it obsolete farther down the line. Emerging technologies fill the hearts and minds of technology's talented innovators with inspiration, hope and daring. They turn sci-fi dreams into reality and challenged accepted technology and computing paradigms. Before enterprise dreams become reality, businesses must to invest in the infrastructure and talent that will lay groundwork for future investments. Artificial intelligence-based and enabled technologies will heavily play into the next wave of enterprise computing capabilities, but innovators have to navigate and manage accountability, market support and hype. CIOs will push for emerging technologies and a customer-focused operating model, but they will also be held accountable for innovation that delivers.

If your paper is accepted by the conference committee, first you will receive an official acceptance letter. Then, you need to email us a pdf or jpeg copy of the first page of your passport for you to receive official invitation letter from Shanghai University for VISA application.

The world's largest tech conference has apparently learned a big lesson about gender equity. CES, the huge annual consumer-electronics show in Las Vegas, caught major flak from activists in late 2017 when it unveiled an all-male lineup of keynote speakers for the second year in a row. Although it later added two female keynoters, the gathering's'boys' club' reputation remained intact. Stripper robots perform at the Sapphire Gentlemen's Club on the sidelines of CES 2018 in Las Vegas. It didn't help that one of the unsanctioned events latching on to CES last year was a nightclub featuring female'robot strippers.'

Sonos is working on a brand new speaker that could arrive within weeks, according to new filings. Documents made public by the Federal Communications Commission show a brand new speaker that bring a whole host of features to its existing line-up. But those features remain mostly under wraps: the filing is redacted and so many of the most important are hidden. Clues inside the filings appear to indicate what the speaker could be intended to do, however. The filings, first reported by Variety, identify the new speaker as "S18" and describe it as a voice-controlled speaker that can connect using WiFi or Bluetooth and can be controlled with a host of microphones that listen to their owner. Beyond that, features or even the speakers design remain largely mysterious.