IBM Research | Haifa

DEFFEND - Dispersed Financial Fraud Enhanced Detection

Protect clients from fraud with the help of their mobile phones

IBM DEFFEND takes fraud detection to the next level, with personalized protection that is built into your clients’ personal smartphone devices.

Learn more

Wearables and IoT for employee safety

Enhanced employee safety at NorthStar Bluescope Steel using the Internet of Things

North Star BlueScope Steel is applying IBM Watson Internet of Things technology and wearable devices to pioneer novel approaches to help protect workers in extreme environments. North Star is piloting the IBM Employee Wellness and Safety Solution to identify potentially problematic conditions by collecting data from various sensors that continuously monitor the worker’s skin body temperature, heart rate, galvanic skin response and level of activity, correlated with sensor data for ambient temperature and humidity. The solution then alerts North Star management so they can provide personalized safety guidelines to each individual employee.

Learn more

Cognitive Assistant for Radiologists

The project aims at producing a sieve that filters essential clinical and diagnostic imaging information to form anomaly-driven summaries and recommendations

Medical Sieve is an ambitious long-term exploratory grand challenge project to build a next generation cognitive assistant with advanced multimodal analytics, clinical knowledge and reasoning capabilities that is qualified to assist in clinical decision making in radiology and cardiology. It will exhibit a deep understanding of diseases and their interpretation in multiple modalities (X-ray, Ultrasound, CT, MRI, PET, Clinical text) covering various radiology and cardiology specialties. The project aims at producing a sieve that filters essential clinical and diagnostic imaging information to form anomaly-driven summaries and recommendations that tremendously reduce the viewing load of clinicians without negatively impacting diagnosis.

Learn more

Affective computing

Developing computers that have an Emotional Quotient (EQ) to monitor human reactions to guide responses in cognitive systems

Our goal is to develop computers that have an Emotional Quotient (EQ), so we can monitor people’s reactions and use them to guide the subsequent responses and behavior of cognitive systems. Affective computing could help a system respond to emotional states. For example, a computer could sense the stress in the voice of someone calling customer service and instruct the agent to answer in a calming voice, or maybe warn us to wait and rethink before we sell stocks as a reaction to a news article we just read. In the educational environment, it might identify a student who is frustrated or having trouble with a particular point, and help the student to refocus, give additional assistance or trigger their memory about the subject being taught. Healthcare applications could be enhanced to help diagnose diseases that have emotional markers, such as depression or Parkinson's. Marketing, business, and even security companies could benefit from tracking and analyzing emotional responses and behavior patterns.

Learn more

Augmented reality and computer vision

Our mission is to extend and enhance people's vision with cognitively-driven object recognition and interacted information using augmented reality to support decision-making.

Current projects

Hybrid Remote Expert

Our Augmented Reality (AR) technology helps field technicians, making their workflow safer, more accurate, and more efficient with the assistance of a remote cognitive system or remote human expert. The Hybrid Remote Expert technology enables rapid training of new environments, procedural troubleshooting, as well as self-service just-in-time operations. The AR is combined with intuitive, natural voice and gesture interactions via smart hand-held or hands-free devices, such as smart glasses. Using AR, the technician consumes relevant documents, IoT telemetry, or other AR adjusted step-by-step procedures, according to the operation conducted. Compliance and audit actions are ensured by requiring the technician to have a direct line-of-sight with the machine under maintenance. Without changing the industrial setting for ease of tracking, the technology can be implemented immediately in the field with minimal ramp up time.

Extended Show Room

Extend a show room and customer engagement by providing augmented information on existing objects. For example, provide a client with information on a favorite next car model located on the street; experience augmented reality of various configurations and options. Client use of the application may provide a dealership with leads for future sales!

Learn more

Planogram Compliance Management

Our technology analyzes the compliance levels according to business severity of a mistreated issue, and enables operators to prioritize labor for rapidly fixing such issues. In addition, managers can keep track of historical changes, and report ongoing improvement and adherence to the compliance level agreement. The technology can visually recognize tens and hundreds of items on shelves or other displays in a retail store, avoiding the need for RFID or bar-codes. The Object Recognition and the Augmented Reality overlay can assist in store operational efficiency and drive an increase in sales. Retailers and manufacturers get immediate feedback on their product assortment and availability, they can deduce compliance agreement levels, and trigger just-in-time purchase orders to boost sales.

Find out more about person centric care

Cloud Analytics

Building a fast bridge to the cloud.

It is not possible to manually process even terabytes of information, let alone petabytes or exabytes. The only way one can make sense out of these quantities of data is through analytics, machine learning, and cognitive computing. Apache Spark is rapidly growing as the bulk data analytics platform of choice and is particularly amenable for use with machine learning and cognitive algorithms.

Given the importance of Apache Spark, we needed a fast connector that would allow Apache Spark to efficiently process data in an object store. And now scientists at IBM Research – Haifa have built just that. Called Stocator, the connector allows Spark to efficiently ‘talk’ to an object store.

Learn more