Connected Vehicle – is far more than just the car…

schedule Aug 31st 03:30 PM - 04:15 PM place Jupiter people 48 Interested


For many IoT use cases there is a real challenge in streaming large amounts of data in real time, and the connected vehicle is no exception. Cars and trucks have the ability to generate TB of data daily, and connectivity can be spotty, especially in remote areas. To address this issue companies will want to move the analysis to the edge, on to the device where the data is generated. Will walk through the case in which there is an installed streaming engine on a gateway on a commercial vehicle. Data is analyzed locally on the vehicle, as it is generated, and alerts are communicated via cell connection. Models can be downloaded when a vehicle comes in for service, or over the air. Idea is to use data from the vehicle, like model, horsepower, oil temp, etc, to buid a decision tree to predict our target, turbo fault. Decision trees are nice in that that lay out the rules for you model clearly. In this case the model was predictive for certain engine horsepower ratings, time in service, model, and oil temps. Once this model generated acceptable accuracy with a 30 day window, plenty of time to act on the alert. Now in order to capture the value of this insight, we need to know immediately when a signal is detected, so this model will run natively on the vehicle, in our on board analytics engine.

 
8 favorite thumb_down thumb_up 14 comments visibility_off  Remove from Watchlist visibility  Add to Watchlist
 

Outline/structure of the Session

1. IOT (~2minutes)

2. Streaming of data(~2minutes)

3. Problem definition(~4minutes)

4. Online Analytics/Data Size/Algorithms(~15 minutes)

5. Offline Analytics(~15 minutes)

6. Alert Mechanism(~2 minutes)

7. Q/A (~5 minutes)

Learning Outcome

IOT

Automated Vehicle

Streaming Analytics

Target Audience

Advanced analytic users

schedule Submitted 5 months ago

Comments Subscribe to Comments

comment Comment on this Submission
  • Vishal Gokhale
    By Vishal Gokhale  ~  5 months ago
    reply Reply

    Thanks for the proposal, Savita ! :-)
    This is very interesting topic and I am sure many people in the audience will be interested in listening to analytics in the IoT context. 

    Would you be covering the trade-offs that one has to consider when deciding how much processing to push to the on-board analytics engine?

    I think the audience would benefit from knowing the following:
    1. What can be pushed to the on-board engine?
    ex. decision tree - yes, random forest - no (these examples may not be correct)

    2. How much can be pushed to the on-board engine?
    ex. processing data upto 1 month or 100 MB can be pushed ..but if data is bigger is than that, then the on-board engine only takes the latest available chunk etc.

    3. What is the spectrum of capabilities across devices?
    ex.  different hardwares will have different data size limits and certain algos may work better on certain platforms... 

    etc.

    Please share your thoughts.

    • Dr. Savita Angadi
      By Dr. Savita Angadi  ~  5 months ago
      reply Reply

      Hello Vishal,

      Thank you so much for your inputs. I will cover most of your queries. If possible will demo the approach too.

      Please add your more queries so that I can streamline my presentation accordingly. 

      -savita

      • Vishal Gokhale
        By Vishal Gokhale  ~  4 months ago
        reply Reply

        Welcome Savita!

        For the program committee to get an idea of your presentation style, can you please share a link to videos of your prior talks on this topic?
        If you would be presenting this talk for the first time, you may share a link to any other technical talks you may have delivered. If those are not available, you may record a trailer of this talk and share a link. 

        Thanks,
        V

        • Dr. Savita Angadi
          By Dr. Savita Angadi  ~  4 months ago
          reply Reply
           
          Hello Vishal,
           
          I dont have any  video recording of past presentation. I saw the same request for the other paper too. Is it pre requisite?  If so, I suppose it was part of the proposal submission too!
           
          As I am on business trip I will not be able to record the trial session and share with you.
           
          As per this mail thread, it will be hard for program committee to judge my presentation style without the recording. Hence I am taking back my proposal.
           
          Thank you for your support and understanding!
           
          Savita
          • Vishal Gokhale
            By Vishal Gokhale  ~  4 months ago
            reply Reply

            A trailer video is not a mandatory pre-requisite as such. If some program committee member/s can vouch for the presentation style of the speaker, then it is not required.

            We understand the logistical constraints and hence request you to join the committee members over a call to share a few highlights of your talk.

            Last but not least, it will definitely help to know more about the talks you have delivered. We don't intend to judge your resume.
            The intent is to only look at content to see if we can request you to include some elements from your other talks.

            • Dr. Savita Angadi
              By Dr. Savita Angadi  ~  4 months ago
              reply Reply

              Hello Vishal,

               

              As per the discussion with Naresh today morning, I have updated the time break for the proposal and also modified the timing from 20 minutes to 40 minutes. Also will try to upload the video today evening.

              Thanks.

              Savita

               

      • Naresh Jain
        By Naresh Jain  ~  4 months ago
        reply Reply

        Hi Savita,

        This is a very interesting topic. However, I feel 20 mins might be too short a time to do justice to all the topics listed in the outline.

        Can you please give a time break of how you plan to spend the 20 mins?

        If you feel 20 mins will not work, you've 2 options:

        • Descope some of the topics and focus on the core analytics part
        • Keep the current scope and increase the time to 45 mins
        • Dr. Savita Angadi
          By Dr. Savita Angadi  ~  4 months ago
          reply Reply

          Hello Naresh, I will increase the time to 45 minutes.

          Thank you. 

          • Naresh Jain
            By Naresh Jain  ~  4 months ago
            reply Reply

            Thank you, Savita. Please update the timing in the proposal and also give a time-wise breakup of how you plan to use the 45 mins.

            Also, can you please share a video from any past presentation, so the program committee can understand your presentation style.

            • Dr. Savita Angadi
              By Dr. Savita Angadi  ~  4 months ago
              reply Reply
              Hello Naresh,
               
              I dont have any  video recording of past presentation. I saw the same request for the other paper too. Is it pre requisite?  If so, I wish it was part of the proposal submission too!
               
              As I am on business trip I will not be able to record the trial session and share with you.
               
              As per this mail thread, it will be hard for program committee to judge my presentation style without the recording. Hence I am taking back both of my proposals.
               
              Thank you for your support.
               
              Savita
  • Joy Mustafi
    By Joy Mustafi  ~  5 months ago
    reply Reply

    I like the aspect of the submission. Are you also covering the typical Indian traffic scenario and how this approach would be aligned to give us insights?

    • Dr. Savita Angadi
      By Dr. Savita Angadi  ~  5 months ago
      reply Reply

      Hello Joy, Thank you for your inputs. I am not covering the Indian traffic scenario.

       

      Will try to cover:

      Customer Experience: Just think of the vehicle as another major channel to manage an omnichannel strategy. What automotive company doesn’t want to capture our attention with assistance, offers and support when we want it as we want it?
       
      Location-based services: If parking garages are outfitted with devices to signal what exact parking garage spots are open and those can talk to your vehicle, it brings to life “connected city talking to the connected vehicle”
      Safety & security: Certainly a primary concern and goal of any manufacturer … how can recalls be better issued (over-the-air updates even?) and what can be done to personalize messages giving advice to avoid specific risks on the road?


      Quality & reliability: The longer the product is operating, the more value it is to the owner. This is hands-down a golden-rule in any category. 


      Dealer operation: When vehicles can communicate with dealers, dealers can optimize their inventory based on likely demand for parts and service.

      • Prachi Saraph
        By Prachi Saraph  ~  5 months ago
        reply Reply

        Savita, very interesting and unique topic.

        Would like to understand the proposal better in terms of does you talk recommend an architecture to capture complexity of handshakes between various channels and technologies? 

        Are you proposing a generic flow? 

        Is this area under research and investigation or would some implementation examples are going to be discussed?

         

        • Dr. Savita Angadi
          By Dr. Savita Angadi  ~  5 months ago
          reply Reply

          Hello Prachi,

          Thank you for your comments.

          I am not sure how much I can cover the architecture part of the story in 20 minutes. My goal will be highlight end to end flow and focus on analytics part to the extent it is possible. Some part of it is under research and investigation. Will discuss the implementation examples.

          Hope this helps!

          -savita

           

           


  • Liked Santosh Vutukuri
    keyboard_arrow_down

    Santosh Vutukuri - Embedding Artificial Intelligence in Spreadsheet

    20 Mins
    Demonstration
    Intermediate

    In today's world all of us are growing our data science capabilities. There are many such organizations who think they are comfortable in spreadsheets (e.g. Microsoft Excel, Google Sheets, IBM Lotus, Apache OpenOffice Calc, Apple Numbers etc.), and they seriously do not want to switch into complex coding using R or Python, and not even into any other analytics tools available in the market. This proposal is for demonstrating how we can embed various artificial intelligence and machine learning algorithms into spreadsheet and get meaningful insights for business or research benefit. This would be helpful for the small scale businesses from the data analysis perspective. This approach with user friendly interface really creates value in decision making.

  • Liked Joy Mustafi
    keyboard_arrow_down

    Joy Mustafi - The Artificial Intelligence Ecosystem driven by Data Science Community

    45 Mins
    Talk
    Intermediate

    Cognitive computing makes a new class of problems computable. To respond to the fluid nature of users understanding of their problems, the cognitive computing system offers a synthesis not just of information sources but of influences, contexts, and insights. These systems differ from current computing applications in that they move beyond tabulating and calculating based on pre-configured rules and programs. They can infer and even reason based on broad objectives. In this sense, cognitive computing is a new type of computing with the goal of more accurate models of how the human brain or mind senses, reasons, and responds to stimulus. It is a field of study which studies how to create computers and computer software that are capable of intelligent behavior. This field is interdisciplinary, in which a number of sciences and professions converge, including computer science, electronics, mathematics, statistics, psychology, linguistics, philosophy, neuroscience and biology. Project Features are Adaptive: They MUST learn as information changes, and as goals and requirements evolve. They MUST resolve ambiguity and tolerate unpredictability. They MUST be engineered to feed on dynamic data in real time; Interactive: They MUST interact easily with users so that those users can define their needs comfortably. They MUST interact with other processors, devices, services, as well as with people; Iterative and Stateful: They MUST aid in defining a problem by asking questions or finding additional source input if a problem statement is ambiguous or incomplete. They MUST remember previous interactions in a process and return information that is suitable for the specific application at that point in time; Contextual: They MUST understand, identify, and extract contextual elements such as meaning, syntax, time, location, appropriate domain, regulation, user profile, process, task and goal. They may draw on multiple sources of information, including both structured and unstructured digital information, as well as sensory inputs (visual, gestural, auditory, or sensor-provided). {A set of cognitive systems is implemented and demonstrated as the project J+O=Y}

  • Liked Srijak Bhaumik
    keyboard_arrow_down

    Srijak Bhaumik - Let the Machine THINK for You

    20 Mins
    Demonstration
    Beginner

    Every organization is now focused on the business or customer data and trying hard to get actionable insights out of it. Most of them are either hiring data scientists or up-skilling their existing developers. However, they do understand the domain or business, relevant data and the impact, but, not essentially excellent in data science programming or cognitive computing. To bridge this gap, IBM brings Watson Machine Learning (WML), which is a service for creating, deploying, scoring and managing machine learning models. WML’s machine learning model creation, deployment, and management capabilities are key components of cognitive applications. The essential feature is the “self-learning” capabilities, personalized and customized for specific persona - may it be the executive or business leader, project manager, financial expert or sales advisor. WML makes the need of cognitive prediction easy with model flow capabilities, where machine learning and prediction can be applied easily with just a few clicks, and to work seamlessly without bunch of coding - for different personas to mark boundaries between developers, data scientists or business analysts. In this session, WML's capabilities would be demonstrated by taking a specific case study to solve real world business problem, along with challenges faced. To align with the developers' community, the architecture of this smart platform would be highlighted to help aspiring developers be aware of the design of a large-scale product.

  • Liked Dr. Savita Angadi
    keyboard_arrow_down

    Dr. Savita Angadi - What Chaos and Fractals has to do with Machine Learning?

    Dr. Savita Angadi
    Dr. Savita Angadi
    Sr. Analytical Consultant
    SAS
    schedule 5 months ago
    Sold Out!
    45 Mins
    Talk
    Advanced

    The talk will cover how Chaos and Fractals are connected to machine learning. Artificial Intelligence is an attempt to model the characteristics of human brain. This has lead to model that can use connected elements essentially neurons. Most of the biological systems or simulation related developments in neural networks have practical results from computer science point of view. Chaos Theory has a good chance of being one of these developments. Brain itself is an good example of chaos system. Several attempts have been made to take an advantage of chaos in artificial neural systems to reproduce the benefits that have met quite a bit success.

  • Liked Saibal Dutta
    keyboard_arrow_down

    Saibal Dutta - A Multi-criteria Decision Making Approach and its Applications in Business

    45 Mins
    Tutorial
    Intermediate

    We live in a world of information where decision takes a very important role. Human are considered one of the best species since we like to think and quantitatively analysis our decision process based on the available information. But the question may arise:


    1. How can we take a right decision or mathematically, optimal solution among the multiple alternatives?


    In academic world, this knowledge is known as Multiple criteria decision making (MCDM), that involves to making decisions in the presence of multiple, usually conflicting criteria and alternatives. Multi-Criteria Decision Aid (MCDA) or Multi-Criteria Decision Making (MCDM) methods have successfully utilized by researchers and practitioners in evaluating, assessing and ranking alternatives across diverse business problem. As we know, every decision involves trade-offs between risk and opportunity. So, the next question may arise:


    2. How to minimize the risk and define in mathematically for a given business problem?


    Many MCDA/MCDM methods developed to solve real-world decision problems, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) continues to work satisfactorily across different real business application areas. So, the next comes:


    3. How to apply TOPSIS methods to design and solve any practical business problem?


    In this session, we will try to understand the theory behind decision science and discuss step by step implementation of business cases in open source environment

    The overall objective of the session is how to design decision based on knowledge and planning in business.