From smart speakers in the operating room to virtual diagnosis and treatment plans, The AEDITION looks at a few of the ways artificial intelligence is shaking up the medical industry. We may not be at the point where you overhear your surgeon saying, "Hey, Google, pass the scalpel," but artificial intelligence (AI) is gradually making its way into the healthcare industry and, by extension, dermatology and plastic surgery practices, too. Even in its limited use, AI is already helping providers offer their patients better care -- whether it's pre-op, in the OR, or during the recovery process. Here are three ways artificial intelligence is shaking up medicine. Your experience with a medical practice starts as soon as you look for information online.

Autonomous vehicles will fail to reach their full potential until ubiquitous and extremely reliable high-speed communications networks with very low latency are available. These networks are key to facilitating the realtime, instantaneous communications among vehicles and supporting infrastructure that must exist before vehicles can continuously and autonomously traverse city streets void of vigilant human oversight. The deployment of 5G (fifth generation) cellular technologies will represent a giant leap forward toward the use of autonomous vehicles for swift, efficient, and safe travel. However, the successful deployment of 5G (and subsequent) technologies depends upon the support of, and coordination among, federal, state, and local governments. Without this support and coordination, only the most lucrative markets will likely benefit from new technologies, and autonomous vehicles will remain technologically insular due to the scale of telecommunications investment required for the mass autonomous vehicle market.

We are going to the AIoT Summit on December 3rd with Ambiq Micro and TensorFlow, and we wanted to give you a sneak peek! On December 3rd, you will find SparkFun CTO Kirk Bennel and Creative Technologist Rob Reynolds at the AIoT Dev Summit! In collaboration with Ambiq Micro and TensorFlow, we are going to be running a hands-on workshop where you will be able to build your very own Harry Potter wand! That's right, all of us muggles out there can finally get a magic wand without ever having to break into Ollivanders like a certain dark wizard. This is an experiential and experimental workshop that focuses on the use of TensorFlow Lite on a low-power microcontroller to perform machine learning.

The U.S. needs to tackle the challenges of adapting artificial intelligence systems for modern warfare, much like the "titans of industry" transformed Detroit into an "arsenal of democracy" during World War II, Defense Secretary Mark Esper said yesterday. "Mastering artificial intelligence will require similar vision, ambition and commitment," Esper said at a conference hosted by the National Security Commission on Artificial Intelligence. "We need the full force of American intellect and ingenuity working in harmony across the public and private sectors." Artificial Intelligence, sometimes called "machine learning," refers to advanced computer algorithms that can use data to "learn" and therefore make choices without human input. Last week, a Pentagon advisory board released proposed guidelines for the ethical deployment of AI-enabled weapons on the battlefield.

This week researchers from the University of Florida published findings from an archaeological project that sheds new light on what life was like in North America before Christopher Columbus arrived. Using drones to scan the coastline of northwestern Florida, researchers discovered evidence of a settlement dated between 900 to 1200 AD. They discovered evidence of a settlement that could have supported between 200 and 300 people, who they believe worked to create one beads and decorative ornaments from shells that played an important role in Mississippian culture at the time. The settlement was discovered on Raleigh Island, halfway between Tampa and Tallahassee on Florida's northwestern coast, just outside the Cedar Keys Wildlife Refuge. The drone that discovered the settlement was equipped with a LiDAR system, according to a report by ArsTechnica. LiDAR sends out light rays and then measures the differences in how those rays are reflected back from the environment to create a three-dimensional image of the terrain.

Effectively capturing graph node sequences in the form of vector embeddings is critical to many applications. We achieve this by (i) first learning vector embeddings of single graph nodes and (ii) then composing them to compactly represent node sequences. Specifically, we propose SENSE-S (Semantically Enhanced Node Sequence Embedding - for Single nodes), a skip-gram based novel embedding mechanism, for single graph nodes that co-learns graph structure as well as their textual descriptions. We demonstrate that SENSE-S vectors increase the accuracy of multi-label classification tasks by up to 50% and link-prediction tasks by up to 78% under a variety of scenarios using real datasets. Based on SENSE-S, we next propose generic SENSE to compute composite vectors that represent a sequence of nodes, where preserving the node order is important. We prove that this approach is efficient in embedding node sequences, and our experiments on real data confirm its high accuracy in node order decoding.

Boilerplate removal refers to the problem of removing noisy content from a webpage such as ads and extracting relevant content that can be used by various services. This can be useful in several features in web browsers such as ad blocking, accessibility tools such as read out loud, translation, summarization etc. In order to create a training dataset to train a model for boilerplate detection and removal, labeling or tagging webpage data manually can be tedious and time consuming. Hence, a semi-supervised model, in which some of the webpage elements are labeled manually and labels for others are inferred based on some parameters, can be useful. In this paper we present a solution for extraction of relevant content from a webpage that relies on semi-supervised learning using Gaussian Random Fields. We first represent the webpage as a graph, with text elements as nodes and the edge weights representing similarity between nodes. After this, we label a few nodes in the graph using heuristics and label the remaining nodes by a weighted measure of similarity to the already labeled nodes. We describe the system architecture and a few preliminary results on a dataset of webpages.

The impressive performance of neural networks on natural language processing tasks attributes to their ability to model complicated word and phrase interactions. Existing flat, word level explanations of predictions hardly unveil how neural networks handle compositional semantics to reach predictions. To tackle the challenge, we study hierarchical explanation of neural network predictions. We identify non-additivity and independent importance attributions within hierarchies as two desirable properties for highlighting word and phrase interactions. We show prior efforts on hierarchical explanations, e.g. contextual decomposition, however, do not satisfy the desired properties mathematically. In this paper, we propose a formal way to quantify the importance of each word or phrase for hierarchical explanations. Following the formulation, we propose Sampling and Contextual Decomposition (SCD) algorithm and Sampling and Occlusion (SOC) algorithm. Human and metrics evaluation on both LSTM models and BERT Transformer models on multiple datasets show that our algorithms outperform prior hierarchical explanation algorithms. Our algorithms apply to hierarchical visualization of compositional semantics, extraction of classification rules and improving human trust of models.

In this paper we adopted state-of-the-art machine learning algorithms, namely: random forest (RF) and least squares boosting, to model crash data and identify the optimum model to study the impact of narrow lanes on the safety of arterial roads. Using a ten-year crash dataset in four cities in Nebraska, two machine learning models were assessed based on the prediction error. The RF model was identified as the best model. The RF was used to compute the importance of the lane width predictors in our regression model based on two different measures. Subsequently, the RF model was used to simulate the crash rate for different lane widths. The Kruskal-Wallis test, was then conducted to determine if simulated values from the four lane width groups have equal means. The test null hypothesis of equal means for simulated values from the four lane width groups was rejected. Consequently, it was concluded that the crash rates from at least one lane width group was statistically different from the others. Finally, the results from the pairwise comparisons using the Tukey and Kramer test showed that the changes in crash rates between any two lane width conditions were statistically significant.

With the increasing complexity of modern power systems, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the WECC composite load model (WECC CLM) has shown to effectively capture the dynamic load responses over traditional load models in various stability studies and contingency analyses. However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters. Enabled by the wide deployment of PMUs and advanced deep learning algorithms, proposed here is a double deep Q-learning network (DDQN)-based, two-stage load modeling framework for the WECC CLM. This two-stage method decomposes the complicated WECC CLM for more efficient identification and does not require explicit model details. In the first stage, the DDQN agent determines an accurate load composition. In the second stage, the parameters of the WECC CLM are selected from a group of Monte-Carlo simulations. The set of selected load parameters is expected to best approximate the true transient responses. The proposed framework is verified using an IEEE 39-bus test system on commercial simulation platforms.