Case Study

Data Warehouse Offloading

One of our clients is a mass transit electric train service provider. As a public service company, our client is committed to improve their service quality by embracing the data-driven operation and management. To achieve it, they need a reliable and integrated data management system. Unfortunately their data warehouse was not able to keep up with their data needs, which is why they decided to adopt big data technology.

Yava247 Data Management and Data Engineering Platform were chosen as the platform and tool for these advantages:

1. Scalable Architecture and Suitable Implementation Strategy.
They started with small cluster and add more nodes as the requirement increases.The implementation was also done gradually, by providing a training, software trial, a simple project and then implement the data management and analysis as a complete system.

2. Longer data retention.
The horizontal scalability of Hadoop cluster enable longer retention period. The data also stored and managed in a structured, systematic and compressed format, which leads to further efficiency.

3. Best Performance with minimum cost.
By employing the right data format and structure, and utilizing the right technology stack, the reports and data trace can be displayed more quickly and concisely, which was not possible in the legacy system. The regular licensed-based applications tend to be slow to access, and incurring substantial cost periodically.

4. Experience in Implementation and Total Supports.
Yava247 is built on popular and stable open source big data components, with wide community support and adopters. Combined with our strong experience in data and our total support, it ensures successful implementation and delivered working solutions.

Existing challenges to deal with:

  • Heavy load on the data warehouse
  • Unscalable architecture
  • Unreliable data source from mediation
  • Unable to provide up-to-date report
  • High cost of hardware acquisition and maintenance

YAVA247 Data Engineering Platform

Data Lake and CDR Mediation

Our client is one of the biggest Cellular Operators in Indonesia who needs to improve their end-to-end Business Intelligence architecture as well as their reporting to address some pain points:

  • Inefficient ETL process in dealing with large volume of data.
  • Limitation in processing unstructured data due to overly expensive licenses.
  • Too much dependence on Mediation System so that any problems in Mediation will impact the downstream system including ETL, Data Warehouse and Enterprise Reporting.

To answer those challenges, they decided to implement big data management platform.

Benefit For Business

  • Provide faster report to adapt the market
  • Allow faster customer service
  • Cost efficiency

Technical Benefit

  • More data type available
  • Scalable platform to grow the business
  • Real-time access to data
  • Lower cost of HW, SW and resources with more data
  • No dependency to Hadoop Distribution
  • More adaptable with user requirement

Use Cases

  • Data Lake
  • CDR Inquiry
  • Mediation
  • Legacy System Offloading

YAVA247 Data Engineering Platform

Media Analytics

Digital and social media have become very important parts in our everyday life. They can influence people’s decision and reflect how people think and feel about certain things. Therefore, it becomes imperative for business and decision makers to consider the digital and social media to make better decisions.


  • Media and social insights enable any business to :
  • Know where to reach new and relevant customer
  • Understand what message will engage them most effectively
  • Track specific campaign and customer interaction to know what works and what does not work
  • Categorize and measure customer interaction to learn about brand perception, exposure method, and future opportunities
  • Identify key areas of success to quantify ROI through changes in intent to purchase and competitor benchmarking

YAVA for Media Analysis facilitates with these advantages

  • Easy to use in operational and monitoring
  • Drag and drop interface
  • Build topology faster
  • Complete
  • Secure
  • Enable various input (Social Media, Forums, Blogs, Online News, etc)
  • Provide data analysis to support decision makers
  • Process large-scale data faster

Use Cases

  • Competition Analysis
  • Brand Exposure Analysis
  • Campaign Development and Evaluation
  • Product Development and Evaluation
  • Customer Insight Development
  • Marketing Strategy Development
  • Risk Mitigation

Technology Used
YAVA247 Media Analytics

Operational Intelligence

As one of the biggest cellular providers in Indonesia, our client must deal with an unprecedented amount of connectivity points and serve their customers who expect fast and reliable service. However, their current system was infficient and incapable of handling the data from all region they cover. They turn to us and decided to implement operational intelligence analytics with Hadoop cluster and YAVA247 Data Engineering Platform. Operational Intelligent insights enables them to:

  • Obtain faster report to identify unusual issues in customer behaviour
  • Resolve unusual behaviour in CDR transaction faster
  • Manage more data sources and increase their infrastructure efficiency

YAVA247 Data Integration and Engineering Tools facilitates with these technology advantages:

  • More data types support
  • Support any Hadoop distribution and avoid vendor locking
  • Easy to use in operational and monitoring
  • Provide data analysis to support decision making
  • Process large scale data faster
  • More adaptable with user requirement

Use Cases

  • Data Collection
  • CDR Inquiry
  • Operations

Technology Used
YAVA247 Data Engineering Platform

Face Recognition

Wide availability of powerful and low-cost computing systems has created an enormous interest in automatic processing of digital images in a variety of applications, including biometric authentication. Biometric pattern recognition is an alternative for replacing regular password. One of the most popular biometric pattern recognition is face recognition. The advantages of using face recognition among other biometric recognition is: face can be captured at distance.

Existing Challenges to Deal with :

  • Low accuration on distance recognition
  • Bad face detection on low-light condition
  • Heavy matching process
  • A big database need to deal with large-deployment
  • Non scalable architecture

Methods to Address the Above Points

  • Apply image processing to increase contrast and brightness
  • Capture a higher resolution input
  • Do matching process in Big Data tool
  • Detect and recognize face in multi orientation

YAVA247 for Image Recognition Has Advantages :

  • Multi-parallel recognition processing
  • Easy to Build and maintain
  • Faster matching process
  • A large and fast-accessing database to save and access pattern of objects
  • Provides deep learning analysis from recognized face
  • Secure

Implementation for Face Recognition

  • Preventing and eliminating crime
  • Catching thieves identity
  • Greeting guests
  • Taking attendance
  • Identifying lost children
  • Door key substitution

Weather Modelling with Big Data and AI

Climate changes due to global warming has become a very serious problem. There are many natural and human factors affecting climate changes, one of them is rainfall rate. Indonesia has a very high rainfall rate so that it needs a specific method to use in weather modelling. Humidity, temperature, and industrial development are also important factors for weather modelling. Those various factors make weather modelling a hard task.

One of the important task in weather modeling is how to capture the data from the environment. Solusi247 in collaboration with prominent research partners has developed FMCW radar to observe the weather parameters. For the modeling task, Solusi247 also developed YAVA247 for Weather Modeling.

Existing Challenges to Deal with :

  • Many parameters to observe
  • Indonesia has a different weather and need a specific approach
  • Minor change of weather data needs an accurate measurement sensor
  • Heavy weather data process
  • The needs to extend radar scope observation to get more data

Methods to Address the Above Points

  • Use Ensemble Kalman Filter(EnKF) to observe various weather data
  • Develop a suitable weather model that suit for Indonesia weather (numerical weather prediction)
  • Do process in Apache Spark
  • Use high resolution and sensitivity polarimetric-radar
  • Increase radar transmit power to extend its maximum range

YAVA247 for Weather Modelling Advantages :

  • Fast and simple weather data process with Apache Spark
  • High performance and large database storage
  • User friendly platform that ease the data pipeline development and increase productivity
  • More accurate prediction with deep learning analysis


  • More accurate weather prediction that meets observation need
  • More suitable weather modelling for Indonesian climate
  • Data lake for weather data for more usage in the future
  • An early warning system for anomalous and extreme weather changes
  • Assisting the community in planning important activities, carry out disaster mitigation, and other activities related to climate and weather
  • Raising awareness in climate changes and global warming effects

Multi Target Tracking in Marine Surveillance System

Object tracking and detection support is a mandatory function in an advanced radar system. For marine and coastal radar, ship movement is one of the most important observation. Ship movement has its own unique characteristics that sets it apart from other object movements such as cars and aircrafts. Ships sail in low speed and their track have many distortion caused by sea currents and waves. Therefore ship movement need a specific approach to model.

Multiple target tracking (MTT) is a complex process, where the complexity increased as the number of target (ship) increased. It also has other challenges which are :

  • Data association process between prediction and real outcome movement that requires significant amount of resources and time
  • Separate two or more close targets is a challenging task
  • Unpredictable track due to sea current and waves disturbances

Methods to Address the Above Points

  • Use Ensemble Kalman Filter to get better next move ship prediction
  • Run data association process in Big Data tools
  • Apply image processing to image display radar
  • Use high resolution radar and suitable prediction modelling for ship movement

YAVA for Multi Target Tracking in Marine Surveillance System Has Advantages :

  • Multi-parallel process support
  • Faster data processing and analytics, important for a large number of target tracking and detection process
  • User friendly platform that ease the data pipeline development and increase productivity
  • More accurate prediction with deep learning analysis

Features and Functions

  • Real-time multi target detection and tracking
  • Advanced sea surveillance system
  • Provide estimation track of ships
  • Risk mitigation

Benefits and use cases

  • Provide accurate prediction of ship motion to increase sailing safety
  • Warning for ships collisions prevention
  • Prevents illegal fishing by detecting where the ship come from and analyze its movement
  • Reduce crime in shipping transportation
  • Finding lost ship

Sensor Fusion

In an integrated ship monitoring system, the use of multiple sensor is a must. Involvement of multiple sensors are very important for detection, identification, and categorization of moving objects. A complete ship monitoring system must have at least four different sensors with different functions, which are Radar, AIS Receiver, Long Range Camera, and Direction Finder. Each sensor provides different format and type of data.

Existing Challenges to Deal with :

  • Sensors integration
  • Storage and computing resource to handle large volume of data collected from sensors
  • Comparing and combining data between same kind sensor
  • The need to model, predict, and categorize various incoming data

Methods to Address the Above Points

  • Run multi-parallel processing to handle incoming data from many sensors using YAVA247 Data Platform
  • Apply Kalman filter to the same kind data and choose which data to use
  • Use deep learning approach to process and analyze various sensors data

YAVA247 for Sensor Fusion Advantages :

  • Support Multi-parallel process
  • Able to handle all incoming sensor data easily
  • Integrate and analyze all sensing datas using deep learning to provide more accurate prediction
  • Easy to build using drag and drop interface

Benefits and use cases

  • Provide complete information of sea traffic
  • Provide more accurate and reliable prediction by integrating all data sensing
  • Help government monitoring the sea transportation and protecting sea resource
  • Reduce ship collision accident caused by inaccuracies of sensing device