Drug repositioning is an attractive cost-efficient strategy for the development of treatments for human diseases. Here, we propose an interpretable model that learns disease self-representations for drug repositioning. Our self-representation model represents each disease as a linear combination of a few other diseases. We enforce the proximity between diseases to preserve the geometric structure of the human phenome network - a domain-specific knowledge that naturally adds relational inductive bias to the disease self-representations. We prove that our method is globally optimal and show results outperforming state-of-the-art drug repositioning approaches. We further show that the disease self-representations are biologically interpretable.

Oblivious to those depending on bananas for their favourite protein shake or breakfast fix, a deadly fungus has sneaked up on banana plantations in South America, threatening the fruit's future. An artificial intelligence-powered smartphone app developed for banana farmers can come in handy to stem further spread of the disease, its makers from Colombia, India and U.S., said. The artificial intelligence-powered tool built into the app called Tumaini – which means "hope" in Swahili- can detect pathogens at an early stage and help fast-track control and mitigation efforts, according to a statement by researchers who designed the application. The app has been developed by scientists from the Colombia-based International Center for Tropical Agriculture (CIAT), the Imayam Institute of Agriculture and Technology (IIAT), Tamil Nadu in India, and Texas A&M University, in the United States. The tool is being tested on three main banana-producing continents: Asia, Latin America and Africa. It has been tried in Colombia in South America; the Democratic Republic of Congo, Benin and Uganda in Africa; and India and China in Asia.

Complete report on Machine Learning in Finance market report spread across 100 pages, list of tables & figures, profiling 10 companies.

Texture is one of the most-studied visual attribute for image characterization since the 1960s. However, most hand-crafted descriptors are monochromatic, focusing on the gray scale images and discarding the color information. In this context, this work focus on a new method for color texture analysis considering all color channels in a more intrinsic approach. Our proposal consists of modeling color images as directed complex networks that we named Spatio-Spectral Network (SSN). Its topology includes within-channel edges that cover spatial patterns throughout individual image color channels, while between-channel edges tackle spectral properties of channel pairs in an opponent fashion. Image descriptors are obtained through a concise topological characterization of the modeled network in a multiscale approach with radially symmetric neighborhoods. Experiments with four datasets cover several aspects of color-texture analysis, and results demonstrate that SSN overcomes all the compared literature methods, including known deep convolutional networks, and also has the most stable performance between datasets, achieving $98.5(\pm1.1)$ of average accuracy against $97.1(\pm1.3)$ of MCND and $96.8(\pm3.2)$ of AlexNet. Additionally, an experiment verifies the performance of the methods under different color spaces, where results show that SSN also has higher performance and robustness.

In 2018, Brazil had over 230 million cows chewing their cuds – about 22% of the 1.02 billion cows living on this planet – and consequently was the world's largest exporter of beef that year. With the country's revenues from agriculture reaching $84.6 billion, it makes sense that there would be some agriculture technology (agtech) startups cropping up in the Land of the Holy Cross. The Brazilian Institute of Geography and Statistics has noted the efforts this South American country has been making to advance the use of technology in farming. For example, tractor use in the country has grown by almost 50% in the past decade while crop irrigation use has increased by 52%. The agricultural sector is now working hand-in-hand with the tech world to capture big data and turn it into insights for "precision farming," something we talked about in our article on 6 IoT in Agriculture Solutions from AgTech Startups.

The Modi 2.0 is all set to launch a national Artificial Intelligence (AI) Programme soon, which will see the formation of a task force under Principal Scientific Advisor K Vijay Raghavan to identify projects and initiatives in which to implement the AI technology. The policy will also include a national artificial intelligence centre, which has been delayed because of a long-standing tiff between NITI Aayog and the Ministry of Electronics and Information Technology (MeitY) on which will be the department that will anchor the project. The proposed policy and the centre could finally see the light of day as the finance ministry has cleared the NITI Aayog's Rs 7,000-crore plan. "The expenditure finance committee has cleared the spending of Rs 7,000 crore till 2024-25. The NITI Aayog is likely to be the line ministry for this initiative. The Cabinet note is being circulated by NITI Aayog and is likely to be cleared soon," said a government official.

Over three decades, the Internet has grown from a small network of computers used by research scientists to communicate and exchange data to a technology that has penetrated almost every aspect of our day-to-day lives. Today, it is hard to imagine a life without online access for business, shopping, and socialising. A technology that has connected humanity at a scale never before possible has also amplified some of our worst qualities. Online hate speech spreads virally across the globe with short- and long-term consequences for individuals and societies. These consequences are often difficult to measure and predict. Online social media websites and mobile apps have inadvertently become the platform for the spread and proliferation of hate speech.

My role spans positioning, competitive analysis, lead generation, customer engagement, and brand awareness for the GetResponse Enterprise platform. GetResponse has a growing, global team primarily based in Poland with offices in Brazil, Russia, Malaysia, Germany and in Boston, MA where I'm based. Today, the company has a team of more than 300 highly-skilled employees to create an innovative Marketing Automation platform known for great design, simplicity, and unmatched user experience. Throughout the industry, Marketing Automation tools have evolved a lot over the past few years. In fact, a recent Marketing survey conducted by GetResponse and Demand Metric shows that automation can yield 3X performance gains, yet fewer than 20 percent of marketers report full automation for any part of the funnel.

Armed forces in Latin America & the Caribbean are faced with the challenge of having to operate with a multi-dimensional mandate. In times of heightened civil unrest they are required to undertake peace-keeping operations, gang warfare driven by the arms-for-drugs trade calls for counter-insurgence style deployments and seasonal natural disasters often require their services to support the essential services under extreme conditions. With limited resources, every opportunity to prevent the unnecessary expenditure while maintaining effectiveness needs to be taken. In this post I will demonstrate how the application of the K-means clustering algorithm, in the context of how Naval Forces in Latin America and the Caribbean, can be used to schedule efficient Naval deployments and reduce the number of unnecessary operations. For this example I simulated 200 data points that represent the location of incidents that would result in the need for Naval resources to be deployed in the Caribbean Sea. The data have a timestamp that indicates the time of day of each incident on a 24-hour clock cycle.

We describe our methods to address both tasks of the ISIC 2019 challenge. The goal of this challenge is to provide the diagnostic for skin cancer using images and meta-data. There are nine classes in the dataset, nonetheless, one of them is an outlier and is not present on it. To tackle the challenge, we apply an ensemble of classifiers, which has 13 convolutional neural networks (CNN), we develop two approaches to handle the outlier class and we propose a straightforward method to use the meta-data along with the images. Throughout this report, we detail each methodology and parameters to make it easy to replicate our work. The results obtained are in accordance with the previous challenges and the approaches to detect the outlier class and to address the meta-data seem to be work properly.