Jump to the main text


Hitachi America, Ltd.Hitachi America, Ltd.

Hitachi America, Ltd., Research & Development

Common Analytics Framework

There is a strong customer demand for complex big data analytics applications across vertical such as energy, healthcare, automotive, and mining. One approach to building such applications is to build them from scratch for every customer. However this approach has the drawbacks as follows.

  • Inefficient, resource intensive, expensive
  • Hard for domain experts to be involved in the development, hence incomplete
  • Loss of opportunities to leverage  learnings from other applications

This means that we need a different approach, which is shown in Fig.1 on the right hand side (the left hand side shows the first mentioned approach). By building a common analytics framework, we will be able to significantly reduce application development and deployment time.

Fig. 1 Two approaches to building analytics applications for a number of verticals

The framework consist of front end that empowers application builders easily to construct analytics logics as well as dashboards and back end that can take care of multiple execution platforms for analytics operations extending from simple to complex, such as  machine learning algorithms for predictive maintenance. The framework enables domain experts to build applications and it can keep incorporating “knowledge” from a new applications.

Oil & Gas with Big Data Analytics

Disruptive innovation in an unconventional oil and gas industry such as the shale industry offers a promise to change the world’s economies. Advances in technologies such as horizontal directional drilling and hydraulic fracturing have fueled growth in the industry. However, oil and gas industry operators are facing tough business challenges. Shale sub-surface geology poses challenges in terms of proper characterization. Operators want to maximize production output from their acreage through assembly-scale operations. The orthodox approach of modeling the shale upstream operations have proven inadequate. Big data technologies can augment traditional methods in developing a deep understanding of the shale oil and gas operations to address the challenges faced by operators in a holistic way. Hitachi prioritizes the requirements by understanding such customer challenges through voice-of-customer surveys. Collaboratively creating solutions with customers, and collaboratively evolving the lifecycle of the solution with the customer as the focus has been championed by Hitachi’s oil and gas analytics technology. Hitachi consolidates and builds analytics on data from multiple upstream processes which gives the customer multiple, rich contextual views.  For more information, please click the links below.

Predictive Maintenance (PdM)

The Big Data Laboratory (BDL) is developing a suite of technologies to address predictive maintenance use cases for solutions across verticals. Current focus is on understanding customer requirements, and developing solutions that address these requirements. The BDL data-driven technologies provide insights that enable the maintenance staff to take the right maintenance actions at the right time, resulting in avoidance of unexpected failures, decrease in maintenance costs, and increase in equipment availability.

The developed PdM technologies employ machine learning and data mining techniques over historical event and sensor data to:

  • monitor equipment,
  • detect performance degradation,
  • predict future events,
  • predict remaining useful life of equipment,
  • analyze root cause of failure or degradation,
  • measure maintenance effectiveness,
  • optimize manpower and resources for maintenance, and
  • recommend operating envelopes.

The developed technologies have use cases in a variety of verticals, including but not limited to: manufacturing, transportation and automotive, infrastructure management, oil and gas, mining, and health industry.

Improving Overall Equipment Effectiveness in Mining Industry

Big data analytics is getting popularity in mining industry as operational efficiency is the key issue for mining industry leaders. To improve overall equipment effectiveness, BDL team is focusing on technologies for increasing equipment availability and utilization. We are developing key technologies for monitoring, predictive maintenance and fleet management and optimization. Our solutions involve machine learning, optimization and simulation of mining operations using machine learning.

Dashboard for mining operational center

Video Analytics

Hitachi has performed video analytics research for more than a decade, and we have a variety of technologies that are applied on compelling real-world use cases. An example of such an application is an automotive stereo camera co-developed by Hitachi and a major OEM. It improves safety by performing pre-collision breaking and throttle management, lane departure warning and adaptive cruise control.

Our unique technology for similar image search can search through ten million of images per second on a single server. Our Gazopa Web site, which we used to demonstrate it, was selected as a TechCrunch50 finalist in September 2008.

We are currently working on applications of video analytics for transportation safety and public safety.

Decision Support System for Power Grid

  •  Building a high-performance framework to facilitate big data analytics in the power grid
    • Handling various types of data sources
    • Extendable analytics platform
    • Smart decision support
    • High-speed data access

Macintosh HD:Users:hwang:Desktop:power.png

  • Analyzing the correlations among the data collected from multiple PMUs in a wide area
    • Detecting disturbances in the transmission grid based on various patterns of PMU measurements in a wide area
    • Considering the abnormalities, such as small disturbances, switching events, and topology changes, which are usually hard to capture by operators.
    • Helping the operators to identify the root causes, locate the disturbances, and take appropriate countermeasures.
  • Decision Support System

Macintosh HD:private:var:folders:fn:45ddk26n2zvfjvp2nc649vf40000gn:T:TemporaryItems:00_simuration_room.jpg

  • Online abnormal event detection
    • High frequency PMU measurement data as inputs
    • Online situational awareness with multiple disturbance signatures
  • High speed event search for operational support
    • Similarity detection in comparison with historical events
    • High speed data retrieval with HADB
  • High performance dynamic grid simulation
    • Online stability assessment against  numerous contingency cases
    • Control optimization through dynamic simulation

Macintosh HD:Users:hwang:Documents:Research:PowerManage:map.png
Wide-area Monitoring

Macintosh HD:Users:hwang:Documents:Research:PowerManage:live.png
Live Streaming Data

Macintosh HD:Users:hwang:Documents:Research:PowerManage:1-line.png
Grid Topology

Macintosh HD:Users:hwang:Documents:Research:PowerManage:event.png
Event Detection

Similarity Search


Large amounts of data are being generated from all segments of healthcare. From image data coming from MRI machines and CAT scanners, to clinical data from Electronic Health Records, to device data from ICU devices, to financial data from payers, all the way to personal health data from wearables. The Big Data Laboratory (BDL) is looking at harnessing all this data, structured and unstructured, real-time and historical, to develop advanced analytics technologies to help Hospital Operations Management, Accountable Care Organizations (ACOs), Population Health Management, Comparative Effectiveness Research, Precision Medicine, Patient Monitoring, Clinical Decision Support Systems, and many other forward looking areas.

To help in these different areas of healthcare, the Big Data Laboratory (BDL) is creating key technologies to construct deep clinical signatures from patients, to match patients to past patients that had similar signatures, and to make key predictions based on what happened to those past patients. These predictions are then used to streamline the operations and the clinical decision making across the healthcare system.