Cell detection and cell type classification from biomedical images play an important role for high-throughput imaging and various clinical application. While classification of single cell sample can be performed with standard computer vision and machine learning methods, analysis of multi-label samples (region containing congregating cells) is more challenging, as separation of individual cells can be difficult (e.g. touching cells) or even impossible (e.g. overlapping cells). As multi-instance images are common in analyzing Red Blood Cell (RBC) for Sickle Cell Disease (SCD) diagnosis, we develop and implement a multi-instance cell detection and classification framework to address this challenge. The framework firstly trains a region proposal model based on Region-based Convolutional Network (RCNN) to obtain bounding-boxes of regions potentially containing single or multiple cells from input microscopic images, which are extracted as image patches. High-level image features are then calculated from image patches through a pre-trained Convolutional Neural Network (CNN) with ResNet-50 structure. Using these image features inputs, six networks are then trained to make multi-label prediction of whether a given patch contains cells belonging to a specific cell type. As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples. Finally, for the purpose of SCD testing, we train another machine learning classifier to predict whether the given image patch contains abnormal cell type based on outputs from the six networks. Testing result of the proposed framework shows that it can achieve good performance in automatic cell detection and classification.

This paper proposes an improved design of the perceptron unit to mitigate the vanishing gradient problem. This nuisance appears when training deep multilayer perceptron networks with bounded activation functions. The new neuron design, named auto-rotating perceptron (ARP), has a mechanism to ensure that the node always operates in the dynamic region of the activation function, by avoiding saturation of the perceptron. The proposed method does not change the inference structure learned at each neuron. We test the effect of using ARP units in some network architectures which use the sigmoid activation function. The results support our hypothesis that neural networks with ARP units can achieve better learning performance than equivalent models with classic perceptrons.

The Cloud Machine Learning Market report provides an unbiased and detailed analysis of the on-going trends, opportunities/ high growth areas, market drivers, which would help stakeholders to device and align Cloud Machine Learning market strategies according to the current and future market The Cloud Machine Learning Market report covers the Global market and regional market analysis. The Cloud Machine Learning industry report examines, keep records and presents the worldwide market size of the important players in each region around the globe. Also, the report offers information of the leading market players in the Cloud Machine Learning market. Look insights of Global Cloud Machine Learning industry market research report at https://www.pioneerreports.com/report/519414 The overviews, SWOT analysis and strategies of each vendor in the Cloud Machine Learning market provide understanding about the market forces and how those can be exploited to create future opportunities.

Just like a knife can be used to slice a fruit as well as to commit a murder, artificial intelligence can be used for improving healthcare, but also for discrimination based on facial features and complexion; 3D printing can make organs as well as guns. Technologies are creating new jobs but also leading to displacing workers. Companies complain of difficulty in finding people with requisite skills, even as millions of graduates (and, even more others) remain jobless. Narendra Jadhav, prolific author and Rajya Sabha MP, explores these conundrums in New Age Technology and Industrial Revolution 4.0 and argues for development of a rubric of conducive public policies alongside development and deployment of technology. The book starts with an overview of technologies like AI, augmented reality (AR), additive manufacturing (aka 3D printing) and blockchain. Jadhav puts these within the realm of education, healthcare, digital payments, national security and jobs to discern policy aspects pertaining to economic growth, social inequalities and yes, financial services and banking.

On fields across the world, phones, tablets, drones, and other technologies are changing how food is grown. Through these devices, artificial intelligence (AI)--technology able to perform tasks that require human intelligence--may help farmers use the techniques they already know and trust on a bigger scale. And Big Data--data sets that reveal telling patterns about growth, yield, weather, and more--may help farmers make better decisions before crises strike. According to the report Refresh: Food Tech, From Soil to Supper released in 2018, AI and Big Data may help produce more food, use less water, limit resource consumption, redirect food waste, and lower food prices--all while improving the lives and incomes of farmers and food producers. "Recent advances have the potential for big breakthroughs in the ways we grow, store, transport, distribute, and consume food," says the Refresh Report.

On the other hand, Tropical race 4 (TR4), the virulent strain of fungus Fusarium oxysporum cubense that is threatening banana crop globally with the fusarium wilt disease has killed off millions of bananas in Africa and Asia (from the 1980s onwards). It had surfaced in the Cavendish group of bananas in parts of Bihar and is now spreading to Uttar Pradesh, Madhya Pradesh and even Gujarat, which could spell havoc for the country's banana industry. Even though India is the largest banana producing country in the world and third-largest orange-producing country, our exports for these crops are mainly to the Middle East and some neighbouring countries. Very little, if not any, is exported to the US or EU. In spite of such high production, India's banana exports generate a meager$49.8

A team of scientists led by researchers at the University of Georgia Center for Food Safety in Griffin has developed a machine-learning approach that could lead to quicker identification of the animal source of certain Salmonella outbreaks. In the research, published in the January 2019 issue of Emerging Infectious Diseases, Xiangyu Deng and his colleagues used more than a thousand genomes to predict the animal sources, especially livestock, of Salmonella Typhimurium. Deng, an assistant professor of food microbiology at the center, and Shaokang Zhang, a postdoctoral associate with the center, led the project, which also included experts from the Centers for Disease Control and Prevention, the U.S. Food and Drug Administration, the Minnesota Department of Health and the Translational Genomics Research Institute. According to the Foodborne Disease Outbreak Surveillance System, close to 3,000 outbreaks of foodborne illness were reported in the U.S. from 2009 to 2015. Of those, 900 -- or 30 percent -- were caused by different serotypes of Salmonella, including Typhimurium, Deng said.

Could the same technology that is used to unlock people's smartphones also help unlock the secrets of the universe? It may sound unlikely, but that's exactly what researchers from Switzerland's science and technology-focused university ETH Zurich are working to achieve. Using a variation of the type of artificial intelligence neural network behind today's facial recognition technology, they have developed new A.I. tools that could prove a game-changer in the discovery of so-called "dark matter." Physicists believe that understanding this mysterious substance is necessary to explain fundamental questions about the underlying structure of the universe. "The algorithm we [use] is very close to what is commonly used in facial recognition," Janis Fluri, a Ph.D. student who works in an ETH Zurich lab focused on applying neural networks to cosmological problems, told Digital Trends.

While Americans celebrated a long Labor Day weekend, millions of people in China enrolled in a giant experiment in the future of fake video. An app called Zao that can swap a person's face into movie and TV clips, including from Game of Thrones, went viral on Apple's Chinese app store. The app is popular because making and sharing such clips is fun, but some Western observers' thoughts turned to something more sinister. Zao's viral moment was quickly connected with the idea that US politicians are vulnerable to deepfakes, video or audio fabricated using artificial intelligence to show a person doing or saying something they did not do or say. That threat has been promoted by US lawmakers themselves, including at a recent House Intelligence Committee hearing on deepfakes.

What if there was no such thing as "real"? What if food could be made from thin air? What if electronics could last forever? These are some of the questions being tackled by Europe's top tech innovators identified by our team here at Sifted, in association with the co-working space Second Home and their Breakthrough event this month. This is not your ordinary innovator list. You may not have heard of these startups.