- Today’s top AR news: iPhone 8 to get 3D-sensing tech for AR apps.
- Today’s top AI/machine learning news: Machine learning, satellite imagery estimate corn crop production.
- Today’s top computer vision/machine vision news: 7D Surgical receives FDA clearance for spine surgery image guidance system.
- Apple iPhone 8 to get 3D-sensing tech for AR apps.
- Find anything with new AR tracking device Pixie Points.
- Celebrating Chinese New Year with AR.
- Picture framing store to launch AR app.
- ML, satellite imagery to estimate corn crop production.
- ML helps match liver transplant donors and recipients.
- Amplero leverages influencer marketing with machine learning.
- 10 key machine learning capabilities for chatbots.
- Build ML model with MicrosoftML package.
- Power Transforms for Time Series Forecast Data w/Python.
- Deep learning algorithm identifies skin cancer.
- datalog.ai introduces natural language understanding platform for bots, VAs.
- NASA to use AI to explore alient oceans for evidence of life.
- Singapore to use ML for metro buildout.
- 7D Surgical receives FDA clearance for image guidance system for spine surgery.
- Machine vision helps spot new drug treatments.
- Mikrotron’s high-speed, high-res machine vision cameras.
- AI can crack Pattern Lock from afar.
- Valmet introduces revised version of IQ Web Monitoring System.
- Topplus launches perma-free face alignment engine.
- Augmented Reality
- New Tracker Uses Augmented Reality (NWA Homepage)
- Apple iPhone 8 To Get 3D-Sensing Tech For Augmented-Reality Apps (Investors)
- Manchester firm creates an augmented reality Chinese New Year (Prolific North)
- Picture Worth Custom Framing to Launch Augmented Reality App (PR Web)
- Artificial Intelligence/Machine Learning
- Machine Learning Helps Match Liver Transplant Donors With Organ Recipients (University Herald)
- Amplero enlists machine learning to leverage influencer marketing (Marketing Land)
- 10 Key Machine Learning Capabilities to Fuel Your Chatbot (KDnuggets)
- Building a machine learning model with the MicrosoftML package (Revolutionary Analytics)
- How to Use Power Transforms for Time Series Forecast Data with Python (Machine Learning Mastery)
- Deep learning algorithm does as well as dermatologists in identifying skin cancer (Stanford News)
- datalog.ai® Introduces Breakthrough Natural Language Understanding Platform for Bots and Virtual Assistants (Yahoo! Finance)
- Nasa to use artificial intelligence to explore alien oceans in search of LIFE (The Sun)
- Machine-learning to inspire Singapore metro buildout (UPI)
- Using Machine Learning and Satellite Imagery to Estimate Corn Crop Production (GIS Lounge)
- Computer Vision/Machine Vision
- Machine Vision Helps Spot New Drug Treatments (Technology Review)
- Mikrotron’s high-resolution, high-speed machine vision cameras (Novus Light)
- 7D Surgical Receives FDA 510(K), Health Canada MDL Clearance for Breakthrough Image Guidance System for Spine Surgery (PR Newswire)
- New AI can crack your Pattern Lock from afar (Tech Republic)
- Valmet introduced a revised version of the Valmet IQ Web Monitoring System (Lesprom)
- China’s Topplus Launches Face Alignment Engine for Free Permanently (Yahoo! Finance)
New Tracker Uses Augmented Reality (NWA Homepage)
It’s a tracker called Pixie Points. To “pixify” your items, you place Pixie Points on everything from your keys, wallet, and remotes to your luggage and pets. To find the items, users open the Pixie app with an IOS device and tap the misplaced item they need to find.
Apple’s (AAPL) upcoming iPhone 8 smartphone will include a 3D-sensing module to enable augmented-reality applications, Rosenblatt Securities analyst Jun Zhang said Wednesday.
Apple has included the 3D-sensing module in all three current prototypes of the iPhone 8, which have screen sizes of 4.7, 5.1 and 5.5 inches, he said.
With Tango, digital information is overlaid on live video taken with the phone’s rear camera. The technology superimposes virtual objects, directions and other data on what the camera sees.
Manchester firm creates an augmented reality Chinese New Year (Prolific North)
Manchester tech company Sparta Digital will offer augmented reality experiences on its Buzzin app during Manchester’s Chinese New Year celebrations.
The first experience will be Zodiac Hunt – an interactive quest in which 12 Chinese Zodiac animals are virtually scattered around the city centre. Users will be provided with a map displaying the locations of the animals and once they find any three of them using the AR camera built into the app, they will be able to collect a prize from Swatch in Manchester Arndale.
Picture Worth Custom Framing to Launch Augmented Reality App (PR Web)
Picture Worth Custom Framing, a top-rated Houston wall décor company, announced today that it expects to launch its highly anticipated augmented reality app, uncover: HOUSTON, February 3.
Through the uncover: HOUSTON app, visitors and residents of Houston can use their smartphones to scan signage, promotional materials, and objects to reveal new, interactive content.
Picture Worth is offering area businesses the chance to seize on the new marketing opportunity though a limited number of sponsorships. By purchasing a sponsorship, businesses would have the opportunity to embed content in their business’ various promotional materials and signage for viewing within the uncover: HOUSTON app.
Artificial Intelligence/Machine Learning
Machine Learning Helps Match Liver Transplant Donors With Organ Recipients (University Herald)
Two medical specialists at the Austin Health’s Liver Transplant Unit in Melbourne, Australia developed an algorithm that matches potential liver donor with patients. The specialists said that they modeled the algorithm from the dating site, eHarmony, hoping to make the process faster which will, eventually, save more lives.
After that, they used the machine learning algorithm to assess the results of 75 patients who have undergone transplants. The algorithm is 84 percent accurate compared to the traditional method of matching donors and recipients which is only 68 percent.
Amplero enlists machine learning to leverage influencer marketing (Marketing Land)
Influencer marketing tries to leverage a popular person’s network of friends and followers.
Called Influencer Optimization, the new approach identifies users with substantial networks of contacts, and then uses machine intelligence to make the least offer that would generate the biggest ripple.
What differs about Amplero’s approach, Fleckenstein said, is that the machine learning is continually testing the lowest offer that will deliver results, as well as figuring out the targeted customer’s network of influence.
As a smart bot, your bot will obviously need to understand natural language in order to be able to interact with humans in a natural way.
One of the most essential features you’ll need is the ability to identify the user’s sentiment. Meaning, analyzing the given text to return the sentiment as positive, negative or neutral (and the level / score).
This one is about extracting useful information from the given text, such as places, people (names), companies, phone numbers, etc.
Concept mining is a fascinating field which can come in handy when building your smart bot. It uses techniques such as data mining and text mining to pull the main topics and ideas discussed in a given text.
The ability to transcribe the given audio (or video) to text. This capability is obviously optional and only relevant to bots which handle audio.
By using a graph of entities and their connections, your bot can really do interesting things, such as give you more meaningful answers and understand things that are related to what you asked about (by building a graph of connected nodes).
A useful chatbot should know its users. But when anomalies occur, we would want our chatbot to discover it, let us know about it and possibly take action.
Another way our chatbot can give us new insights is by using predictive analytics.
Providing our smart bot with image recognition capabilities can be very powerful.
Being able to understand where we are by mapping a set of coordinates to a geographical region can help us in many ways, such as suggesting nearby places.
Building a machine learning model with the MicrosoftML package (Revolutionary Analytics)
Once you have access to Microsoft R Server (or Client), this R script walks you through the process of:
- Loading the MicrosoftML package
- Importing the NYC Taxi Data from SQL Server (it comes preinstalled on the Data Science Virtual Machine)
- Splitting the data into a test set and a training set, with the binary value “tipped” (whether or not the driver was tipped) as the response
- Fitting several predictive models: logistic regression, linear model,, fast forest, and neural network.
- Making predictions on the test data
- Evaluating model performance by comparing AUC (area under the ROC curve)
How to Use Power Transforms for Time Series Forecast Data with Python (Machine Learning Mastery)
Running the example creates two plots, the first showing the time series as a line plot and the second showing the observations as a histogram.
The dataset is non-stationary, meaning that the mean and the variance of the observations change over time. This makes it difficult to model by both classical statistical methods, like ARIMA, and more sophisticated machine learning methods, like neural networks.
A time series that has a quadratic growth trend can be made linear by taking the square root. Running the example plots the series both as a line plot over time and a histogram of observations.
During testing, the researchers used only high-quality, biopsy-confirmed images provided by the University of Edinburgh and the International Skin Imaging Collaboration Project that represented the most common and deadliest skin cancers – malignant carcinomas and malignant melanomas. The 21 dermatologists were asked whether, based on each image, they would proceed with biopsy or treatment, or reassure the patient. The researchers evaluated success by how well the dermatologists were able to correctly diagnose both cancerous and non-cancerous lesions in over 370 images.
The algorithm’s performance was measured through the creation of a sensitivity-specificity curve, where sensitivity represented its ability to correctly identify malignant lesions and specificity represented its ability to correctly identify benign lesions. It was assessed through three key diagnostic tasks: keratinocyte carcinoma classification, melanoma classification, and melanoma classification when viewed using dermoscopy. In all three tasks, the algorithm matched the performance of the dermatologists with the area under the sensitivity-specificity curve amounting to at least 91 percent of the total area of the graph.
datalog.ai® Introduces Breakthrough Natural Language Understanding Platform for Bots and Virtual Assistants (Yahoo! Finance)
datalog.ai, an artificial intelligence (AI) start-up that brings human-like conversation to bots, virtual assistants, IoT devices, and business applications, has today achieved a major breakthrough in AI with its launch of the MyPolly platform. MyPolly is the world’s first product that introduces continuous conversation via natural language understanding.
Chien runs the Artificial Intelligence Group which is currently developing AI for underwater drones.
Nasa recently revealed what the drones – or space-colonising humans of the future – might see if they ever touch down on another planet.
They released an incredible video which makes viewers feel as if they are hurtling straight toward the Pluto’s slushy ice oceans.
Scientists supplied their algorithm with both ridership and land-use distribution data. Researchers plotted the paths of more than 20 million bus and subway journeys over the course of week. They combined ridership patterns with information on the concentration of lands used for business, industry, residence and outdoor recreation.
Descartes Lab, a start-up organization, has created crop production analysis that uses millions of satellite images and machine learning to produce accurate data about the production of agricultural crops. Descartes Lab created a tiled, spatio-temporal mosaic of the planet to make predictions about agricultural production. Despite the relative youth of the project, it has already made more accurate predictions than the US Department of Agriculture has.
The project takes new satellite images and updates them daily, giving the data set a high level of present day accuracy as well as a historical data set. The data has so far been focused on the United States’ extensive corn and soy crops, which is heavily subsidized by the government.
Computer Vision/Machine Vision
Machine Vision Helps Spot New Drug Treatments (Technology Review)
Recursion uses software to read out the results of high-throughput screening, which automates drug testing in cells. That isn’t a new idea, but Recursion uses algorithms that inspect cells at an unusual level of detail. The software measures a thousand features of a cell, such as the size and shape of its nucleus or the distance between different internal compartments.
In the company’s labs in Salt Lake City, automated microscopes feed image recognition software that scrutinizes hundreds of thousands of images each week of human cells modified to model genetic diseases. They’re watching for signs that one of the more than 2,000 compounds Recursion is testing on sick cells can make them look more like healthy ones.
Recursion says it has already identified 15 potential treatments for rare diseases, defined as those afflicting fewer than 200,000 people in the U.S.
Mikrotron will present its new line of compact high-resolution, high-speed CoaXPress and CameraLink machine vision cameras at SPIE Photonics West 2017, held from 28 January to 2 February 2017 in San Francisco, California (US).
All three new camera models, namely EoSens 25CXP+, EoSens 12CXP+ and EoSens 25CL+, are powered by an advanced OnSemi Python CMOS sensor. The high resolution of the CMOS global shutter camera models, combined with a precise trigger and synchronization, a high frame rate and short integration times, support image quality and allow, for example, capturing even the smallest details of components in PCB assembly in high speed. The photo-sensitivity of the high-speed cameras of 5.8 V/lux*s @550nm delivers reliable image information even in low-light conditions. All camera models are based on a unique, robust and compact design (80 x 80 x 66 mm) and are engineered for use in rough environments. The fan-less design supports vibration-free operation.
7D Surgical Receives FDA 510(K), Health Canada MDL Clearance for Breakthrough Image Guidance System for Spine Surgery (PR Newswire)
7D Surgical announced today that it has received both 510(k) clearance from the U.S. Food and Drug Administration (FDA) and a medical device license from Health Canada enabling the North American commercial launch of its innovative Machine-vision Image Guided Surgery (MIGS™) system for spine surgery, the 7D Surgical System.
The 7D Surgical System employs cutting-edge 3D optical technologies and machine vision algorithms to eliminate the long-standing barriers to adoption of existing surgical navigational platforms. This new technology can easily register spinal surgery patients automatically using only visible light.
New AI can crack your Pattern Lock from afar (Tech Republic)
Video and computer vision algorithm software can now be used to crack the Pattern Lock on your Android home screen—and can do so without even seeing the screen itself. University researchers used the software to track fingertip movements and produce options for a potential adversary to use to gain access to the device, as noted in their research.
The new research was able to unlock 95% of its test patterns within the five attempt limit, the research said.
The research used 120 patterns collected from 215 independent users, relying on video footage from smartphone cameras. Additionally, complex patterns didn’t seem any more secure, as they would limit the number of potential patterns that could be used. The research abstract noted that, with complex patterns, the researchers had a 97.5% success rate.
Valmet has introduced a completely renewed version of its Valmet IQ Web Monitoring System, which is an integral element of the Valmet IQ Process and Quality Vision System.
The web monitoring system is now more compact in size. Its enhanced features provide pulp and papermakers with higher-quality images than before for analysis purposes, enabling them to take virtually instantaneous corrective measures. These features maximize production line efficiency and product quality.
China’s Topplus Launches Face Alignment Engine for Free Permanently (Yahoo! Finance)
Topplus, a computer vision solution start-up based in China’s interior hub of Chengdu, announced today the global launch of “Voome”, a free inclusive platform, with a current algorithm engine of face alignment for both iOS and Android platforms.
Developers have the freedom to integrate it into their dazzling applications, to meet R&D demands in R&D of gaming, live streaming, marketing and e-commerce.