Simultaneous localization and mapping (SLAM) is paramount for unmanned systems to achieve self-localization and navigation. It is challenging to perform SLAM in large environments, due to sensor limitations, complexity of the environment, and computational resources. We propose a novel approach for localization and mapping of autonomous vehicles using radio fingerprints, for example WiFi (Wireless Fidelity) or LTE (Long Term Evolution) radio features, which are widely available in the existing infrastructure. In particular, we present two solutions to exploit the radio fingerprints for SLAM. In the first solution-namely Radio SLAM, the output is a radio fingerprint map generated using SLAM technique. In the second solution-namely Radio+LiDAR SLAM, we use radio fingerprint to assist conventional LiDAR-based SLAM to improve accuracy and speed, while generating the occupancy map. We demonstrate the effectiveness of our system in three different environments, namely outdoor, indoor building, and semi-indoor environment.

The proliferation of smartphones has accelerated mobility studies by largely increasing the type and volume of mobility data available. One such source of mobility data is from GPS technology, which is becoming increasingly common and helps the research community understand mobility patterns of people. However, there lacks a standardized framework for studying the different mobility patterns created by the non-Work, non-Home locations of Working and Nonworking users on Workdays and Offdays using machine learning methods. We propose a new mobility metric, Daily Characteristic Distance, and use it to generate features for each user together with Origin-Destination matrix features. We then use those features with an unsupervised machine learning method, $k$-means clustering, and obtain three clusters of users for each type of day (Workday and Offday). Finally, we propose two new metrics for the analysis of the clustering results, namely User Commonality and Average Frequency. By using the proposed metrics, interesting user behaviors can be discerned and it helps us to better understand the mobility patterns of the users.

The AI algorithm was able to predict the presence and the location of nuclei in more than 8,000 cells. Scientists from the Singapore University of Technology and Design (SUTD) and the National University of Singapore and the Nanyang Technological University, Singapore have used artificial intelligence (AI) to demonstrate a correlation between cytoskeleton organisation and nuclear position. The study was recently published in PLOS. To ensure that the study's parameters would not be limited by human conceptualisation, they developed a unique generative algorithm to interpret the cytoskeleton of eukaryotic cells using qualitative data, without telling the system what it was observing and how to measure it. "We separated the information related to the nucleus and the fibres in independent databases of images, ensuring that there was not any information about the nucleus found in the images of the fibres, so that the system could not cheat. Then we trained the system to find the location of the nucleus using only information specific to fibres. To do so, the system had to take the qualitative data and figure out on its own if there was a relation between the organisation of the fibres and the position of the nucleus. This forced the programme to find the parameters defining the system, free from human interpretation and predefined concepts," Associate Professor Javier G. Fernandez explained.

The platform explores each topic alongside commentary and perspectives from 3M experts, scientists, engineers and designers at the forefront of their fields. Recommended AI News: H2O.ai Democratizes Deep Learning with H2O Hydrogen Torch "Every day, 3Mers around the world are unlocking the next phase of what's possible and exploring the latest trends in science and technology," says Kevin Gilboe, head of 3M Design, International. "3M Futures is a great opportunity for us to showcase the broad ways 3M is helping to shape the future -- developing, designing and engineering cutting-edge solutions within the most relevant global trends, while profiling the incredible talent across our company who are experts in their fields." The expert contributors chosen to participate include an array of 3M scientists, engineers, designers and other leaders at the forefront of their industries. From artificial intelligence to equity, each is passionate about their field and has a personal interest in broad applications of the relevant technology and science.

In 1966 a television series called "Star Trek" introduced the communicator, a device Captain Kirk flips open to talk to his crew remotely. Decades later, in the mid-1990s, Motorola released its StarTAC model phone--credited as the first flip phone and clearly inspired by the communicator device from the science fiction series. Likewise, "2001: A Space Odyssey," a movie released in 1968, introduced the idea of video calling, with which most of us have become all too familiar in the past year. And the list goes on--autonomous cars, cars that can fly, smartwatches and virtual reality, just to name a few more. There are several visionaries who have inspired our thinking and design principles.

Tour itinerary planning and recommendation are challenging tasks for tourists in unfamiliar countries. Many tour recommenders only consider broad POI categories and do not align well with users' preferences and other locational constraints. We propose an algorithm to recommend personalized tours using POI-embedding methods, which provides a finer representation of POI types. Our recommendation algorithm will generate a sequence of POIs that optimizes time and locational constraints, as well as user's preferences based on past trajectories from similar tourists. Our tour recommendation algorithm is modelled as a word embedding model in natural language processing, coupled with an iterative algorithm for generating itineraries that satisfies time constraints. Using a Flickr dataset of 4 cities, preliminary experimental results show that our algorithm is able to recommend a relevant and accurate itinerary, based on measures of recall, precision and F1-scores.

Scientists say buildings on Mars could be made from a substance found in fish scales and fungi called chitin. Chitin is one of the most ubiquitous organic polymers on Earth, and when mixed with Martian soil, it could make a sturdy enough material to build tools and shelters. The organic polymer could be sourced on Mars from the bio-conversion of organic waste by insects or fungi – which could be grown on farms. In preliminary tests of the material, the experts have constructed a wrench and a mini model of a Martian habitat with the resilience of plastics. Chitin could help NASA and private companies such as Elon Musk's SpaceX, which plan to establish human colonies on Mars in the next 20 years.

A successful digital economy requires cybersecurity to be a vital enabler, protecting the interests of individuals and businesses and enabling the resilience of businesses and services. Since 2013, Singapore's medium- to long-term directions for cybersecurity is to develop R&D expertise and capabilities to improve the trustworthiness of cyber infrastructures and systems with an emphasis on security, reliability, resilience, and usability among government agencies, academia, and industry. Various initiatives to support research, innovation, and enterprise have been implemented under the Whole-of-Government National Cybersecurity R&D (NCR) Programme.8 The program supports a synergistic range of initiatives to advance technological state-of-the-art in thematic National Satellites of Excellence in universities, grants for local research projects, international research collaborations, and joint technology developments with industry. Innovation is fostered through cross-sector R&D discussions and partnerships and fast-tracked by national testbeds for safe and repeatable cybersecurity experiments.