We analyse the effectiveness of edge detection algorithms for the purpose of automatically extracting coastlines from satellite images. Four algorithms - Canny, Sobel, Scharr and Prewitt are compared visually and using metrics. With an average SSIM of 0.8, Canny detected edges that were closest to the reference edges. However, the algorithm had difficulty distinguishing noisy edges, e.g. due to development, from coastline edges. In addition, histogram equalization and Gaussian blur were shown to improve the effectiveness of the edge detection algorithms by up to 1.5 and 1.6 times respectively.

IBM has been warning about the cybersecurity skills gap for several years now and has recently released a report on the lack of artificial intelligence (AI) skills across Europe. The company said in a Friday email to SC Media that cybersecurity has been experiencing a significant workforce and skills shortage globally, and AI can offer a crucial technology path for helping solve it. "Given that AI skillsets are not yet widespread, embedding AI into existing toolsets that security teams are already using in their daily processes will be key to overcoming this barrier," IBM stated in the email. "AI has great potential to solve some of the biggest challenges facing security teams -- from analyzing the massive amounts of security data that exists to helping resource-strapped security teams prioritize threats that pose the greatest risk, or even recommending and automating parts of the response process." Oliver Tavakoli, CTO at Vectra, said the potential of machine learning (ML) and AI materially helping in the pursuit of a large set of problems across many industries has created an acute imbalance in the supply and demand of AI talent.

Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better classification. To address this shortcoming, in this paper, we propose three novel deep multilevel multimodal fusion frameworks to capitalize on different fusion strategies at various stages and to leverage the superiority of multilevel fusion. At input, we transform the depth data into depth images called sequential front view images (SFIs) and inertial sensor data into signal images. Each input modality, depth and inertial, is further made multimodal by taking convolution with the Prewitt filter. Creating "modality within modality" enables further complementary and discriminative feature extraction through Convolutional Neural Networks (CNNs). CNNs are trained on input images of each modality to learn low-level, high-level and complex features. Learned features are extracted and fused at different stages of the proposed frameworks to combine discriminative and complementary information. These highly informative features are served as input to a multi-class Support Vector Machine (SVM). We evaluate the proposed frameworks on three publicly available multimodal HAR datasets, namely, UTD Multimodal Human Action Dataset (MHAD), Berkeley MHAD, and UTD-MHAD Kinect V2. Experimental results show the supremacy of the proposed fusion frameworks over existing methods.

New teachers, new backpacks, new crushes--and algorithms trawling students' social media posts. Blake Prewitt, superintendent of Lakeview school district in Battle Creek, Michigan, says he typically wakes up each morning to twenty new emails from a social media monitoring system the district activated earlier this year. It uses keywords and machine learning algorithms to flag public posts on Twitter and other networks that contain language or images that may suggest conflict or violence, and tag or mention district schools or communities. In recent months the alert emails have included an attempted abduction outside one school--Prewitt checked if the school's security cameras could aid police--and a comment about dress code from a student's relative--district staff contacted the family. Prewitt says the alerts help him keep his 4,000 students and 500 staff safe.