In the monitoring of a complex electric grid, it is of paramount importance to provide operators with early warnings of anomalies detected on the network, along with a precise classification and diagnosis of the specific fault type. In this paper, we propose a novel multi-stage early warning system prototype for electric grid fault detection, classification, subgroup discovery, and visualization. In the first stage, a computationally efficient anomaly detection method based on quartiles detects the presence of a fault in real time. In the second stage, the fault is classified into one of nine pre-defined disaster scenarios. The time series data are first mapped to highly discriminative features by applying dimensionality reduction based on temporal autocorrelation. The features are then mapped through one of three classification techniques: support vector machine, random forest, and artificial neural network. Finally in the third stage, intra-class clustering based on dynamic time warping is used to characterize the fault with further granularity. Results on the Bonneville Power Administration electric grid data show that i) the proposed anomaly detector is both fast and accurate; ii) dimensionality reduction leads to dramatic improvement in classification accuracy and speed; iii) the random forest method offers the most accurate, consistent, and robust fault classification; and iv) time series within a given class naturally separate into five distinct clusters which correspond closely to the geographical distribution of electric grid buses.

This work studies the robustness certification problem of neural network models, which aims to find certified adversary-free regions as large as possible around data points. In contrast to the existing approaches that seek regions bounded uniformly along all input features, we consider non-uniform bounds and use it to study the decision boundary of neural network models. We formulate our target as an optimization problem with nonlinear constraints. Then, a framework applicable for general feedforward neural networks is proposed to bound the output logits so that the relaxed problem can be solved by the augmented Lagrangian method. Our experiments show the non-uniform bounds have larger volumes than uniform ones. Compared with normal models, the robust models have even larger non-uniform bounds and better interpretability. Further, the geometric similarity of the non-uniform bounds gives a quantitative, data-agnostic metric of input features' robustness.

Wildfires are destructive and inflict massive, irreversible harm to victims' lives and natural resources. Researchers have proposed commissioning unmanned aerial vehicles (UAVs) to provide firefighters with real-time tracking information; yet, these UAVs are not able to reason about a fire's track, including current location, measurement, and uncertainty, as well as propagation. We propose a model-predictive, probabilistically safe distributed control algorithm for human-robot collaboration in wildfire fighting. The proposed algorithm overcomes the limitations of prior work by explicitly estimating the latent fire propagation dynamics to enable intelligent, time-extended coordination of the UAVs in support of on-the-ground human firefighters. We derive a novel, analytical bound that enables UAVs to distribute their resources and provides a probabilistic guarantee of the humans' safety while preserving the UAVs' ability to cover an entire fire.

WASHINGTON - The top U.S. general said on Thursday that the Chinese military was benefiting from the work Alphabet Inc.'s Google was doing in China, where the technology giant has long sought to have a bigger presence. "The work that Google is doing in China is indirectly benefiting the Chinese military," Marine Gen. Joseph Dunford, chairman of the Joint Chiefs of Staff, said during a Senate Armed Services Committee hearing. "We watch with great concern when industry partners work in China knowing that there is that indirect benefit," he said. "Frankly, 'indirect' may be not a full characterization of the way it really is, it is more of a direct benefit to the Chinese military."

For the Defense Department, last month's executive order on artificial intelligence was the starting gun, and the department doesn't mean to lose the race it's been preparing for for some time. Air Force Lt. Gen. Jack Shanahan, director of the DoD's new Joint Artificial Intelligence Center, told lawmakers that he's already trying to stand up a small office around robotic process automation, a specific type of AI aimed towards improving business practices. He said he's already met with the department's chief management officer and chief data officer to discuss the matter, which he's convinced will yield many opportunities to help augment people currently doing those jobs. It's early in the process; he said the department wasn't concentrating on RPA a few months ago. But he's already prioritizing, and he thinks finance will be the first place to apply the new technology.

Artificial intelligence (AI) and machine learning tools are creeping into every part of the enterprise, including security. But while 71% of US businesses said they plan to spend more budget on AI and machine learning in their cybersecurity tools this year, 58% said they still aren't sure what the technology really does, according to a Webroot report released Thursday. The primary reason businesses are turning to these tools is because cybercriminals are, the report found. Some 86% of the 200 US IT professionals surveyed said they believe cybercriminals are using AI and machine learning to attack organizations. And 36% of organizations experienced a damaging cyberattack within the last year, the report found.

As political parties gear up for the 2019 general elections, Analytics India Magazine walks down the memory lane and takes stock of the times when leaders were quite gracious in praising and educating the mass about the importance of emerging technologies like artificial intelligence and machine learning. After his tumultuous election win, the Janata Dal (Secular) supremo, HD Kumaraswamy has stepped into the shoes of his predecessor with ease in Karnataka. In fact, Kumaraswamy has been quite vocal about the role of AI in shaping the future of the state's economy. On turning the state capital into a global innovation hub: With the government playing a crucial role in bringing various stakeholders from across the country under one roof, state-sponsored Bengaluru Tech Summit has played a vital role in ushering innovation and impact. While addressing a press meet the CM said, "Bengaluru has emerged as one of the global innovation hubs in the league of Tokyo in Japan, Silicon Valley in the US and Tel Aviv in Israel. The summit will provide a platform for knowledge sharing on emerging technologies like Artificial Intelligence, Robotics and Blockchain," Kumaraswamy said.

Artificial intelligence (AI), following on the heels of its older sibling RPA (robotic process automation), is no longer waiting to be born, but remains more of a toddler on the Federal IT scene–still learning to walk before trying to run, but bulking up from an appetite for serious Federal government tech interest and investment. Factors that stand in the way of rapid growth in use of the technology may be fairly said to include inertia, budget, lack of understanding, scarcity of obvious projects, insufficient compute power (legacy data centers), and a dearth of large data sets necessary to leverage the technology. But a host of Federal IT policy aims and nascent efforts at agencies are providing plenty of push for the AI Age to kick into higher gear, and point to what may become before too long the largest factor in shying away from AI: a lack of imagination. From the military, to the intelligence community, to civilian agencies, the growth in stated demand for AI projects is impossible to ignore. Intelligence agency officials ticked off a partial list of AI projects and priorities they'd like to pursue, and identified important long-term benefits from getting into the game including drastically reducing the amount of time analysts spend on lower-level monitoring work, and creating a workforce culture that is more comfortable with taking chances on new technology.

As the amount of data created daily increases (already at 2.5 Quadrillion bytes a day allegedly [1]) ML techniques are allowing us to cluster, organise and appropriate this data into actionable information. This is especially true in the realm of Cyber Security. Don't be scared of the term Machine Learning, it really just means a computer that can learn to do something without being explicitly programmed for that task. The process typically involves training the machine to do a task (i.e. Let's have a quick look at some of the ways we encounter ML every day in Cyber Security.

For the Defense Department, last month's executive order on artificial intelligence was the starting gun, and the department doesn't mean to lose the …