Hi [[ session.user.profile.firstName ]]

Anomaly Detection in Predictive Maintenance

We are all witnessing the current data explosion: social media data, clinical data, system data, CRM data, web data, and lately tons of sensor data! With the advent of the Internet of Things, system and monitoring applications are producing humongous amounts of data which undergo evaluation to optimise costs and benefits, predict future events, classify behaviours, implement quality control, and more.

The newest challenge lies in predicting the “unknown”, i.e. an anomaly. An anomaly is an event that is not part of the system past, an event that cannot be found in the system’s historical data. In the case of network data, an anomaly can be an intrusion, in medicine a sudden pathological status, in sales or credit card businesses a fraudulent payment, and, finally, in machinery a mechanical piece breakdown.

The problem here is: how can we predict something we have never seen, an event that is not in the historical data?

This presentation deals with the recognition of early signs of anomalies in the sensor signals monitoring a working rotor. Here, auto-regressive models are trained on historical data describing the rotor normal functioning over time, and therefore making possible the recognition of early signs of disruption.

During this webinar we will show you how!
Recorded Nov 11 2015 47 mins
Your place is confirmed,
we'll send you email reminders
Presented by
Rosaria Silipo, Data Scientist, KNIME
Presentation preview: Anomaly Detection in Predictive Maintenance

Network with like-minded attendees

  • [[ session.user.profile.displayName ]]
    Add a photo
    • [[ session.user.profile.displayName ]]
    • [[ session.user.profile.jobTitle ]]
    • [[ session.user.profile.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(session.user.profile) ]]
  • [[ card.displayName ]]
    • [[ card.displayName ]]
    • [[ card.jobTitle ]]
    • [[ card.companyName ]]
    • [[ userProfileTemplateHelper.getLocation(card) ]]
  • Channel
  • Channel profile
  • Customer Support through Natural Language Processing and Machine Learning Feb 22 2018 7:00 pm UTC 75 mins
    Robin Marcenac, Sr. Managing Consultant, IBM, Ross Ackerman, Dir. Digital Support Strategy, NetApp, Alex McDonald, SNIA CSI
    Watson is a computer system capable of answering questions posed in natural language. Watson was named after IBM's first CEO, Thomas J. Watson. The computer system was specifically developed to answer questions on the quiz show Jeopardy! (where it beat its human competitors) and was then used in commercial applications, the first of which was helping with lung cancer treatment.

    NetApp is now using IBM Watson in Elio, a virtual support assistant that responds to queries in natural language. Elio is built using Watson’s cognitive computing capabilities. These enable Elio to analyze unstructured data by using natural language processing to understand grammar and context, understand complex questions, and evaluate all possible meanings to determine what is being asked. Elio then reasons and identifies the best answers to questions with help from experts who monitor the quality of answers and continue to train Elio on more subjects.

    Elio and Watson represent an innovative and novel use of large quantities of unstructured data to help solve problems, on average, four times faster than traditional methods. Join us at this webcast, where we’ll discuss:

    •The challenges of utilizing large quantities of valuable yet unstructured data
    •How Watson and Elio continuously learn as more data arrives, and navigates an ever growing volume of technical information
    •How Watson understands customer language and provides understandable responses

    Learn how these new and exciting technologies are changing the way we look at and interact with large volumes of traditionally hard-to-analyze data.
  • Ep. 8 Using Splunk to Analyze Performance Metrics: Q&T SIG Talk Recorded: Feb 13 2018 18 mins
    Chris Trimper
    Using Splunk to Analyze Performance Metrics

    Chris Trimper will show you how to leverage Splunk for storing and analyzing performance data from LoadRunner. This allows for easy trending and possible collaboration with other application metrics stored in Splunk. We will also look at building self-service dashboards showing application performance metrics.

    You will be hearing about:

    • Introduction to Splunk
    • Process of preparing LR data for Splunk consumption
    • Building dashboards and performing analytics in Splunk

    Join us for the next upcoming SIG Talk on Tuesday, March 13, 2018: http://www.vivit-worldwide.org/events/EventDetails.aspx?id=1073255&group=.
  • FC vs. iSCSI Recorded: Jan 31 2018 63 mins
    Fred Knight, NetApp, John Kim, SNIA ESF Chair, Mellanox, Alex McDonald, SNIA ESF Vice Chair, NetApp
    In the enterprise, block storage typically handles the most critical applications such as database, ERP, product development, and tier-1 virtualization. The dominant connectivity option for this has long been Fibre Channel SAN (FC-SAN), but recently many customers and block storage vendors have turned to iSCSI instead. FC-SAN is known for its reliability, lossless nature, 2x FC speed bumps, and carefully tested interoperability between vendors. iSCSI is known for running on ubiquitous Ethernet networks, 10x Ethernet speed bumps, and supporting commodity networking hardware from many vendors.

    Because, FCoE also delivers increasing performance as Ethernet speeds increase – and, Fibre Channel also delivers increasing performance as FC speeds increase. Historically, FC delivered speed bumps at a more rapid interval (2x bumps), while Ethernet delivered their speed bumps at a slower pace (10x bumps), but that has changed recently with Ethernet adding 2.5G, 5G, 25G, 40G, and 50G to the traditional 1G, 10G, 100G timeline.

    As the storage world moves to more flash and other non-volatile memory, more cloud, and more virtualization (or more containers), it’s time to revisit one of the great IT debates: Should you deploy Fibre Channel or iSCSI? Attend this SNIA Ethernet Storage Forum webcast to learn:
    •Will Fibre Channel or iSCSI deliver faster performance? Does it depend on the workload?
    •How is the wire speed race going between FC and iSCSI? Does anyone actually run iSCSI on 100GbE? When will 128Gb Fibre Channel arrive?
    •Can any server or storage array actually support more than 32Gb/s or 40Gb/s speeds?
    •Do Linux, Windows, or hypervisors have a preference?
    •Is one really easier [to install/manage] than the other, or are they just different?
    •How does the new NVMe over Fabrics protocol affect this debate?

    Join SNIA experts as they compare FC vs. iSCSI and argue in an energetic yet friendly way about their differences and merits of each.
  • Enterprise Analytics Journey, the IBM point of view for IBM Z customers Recorded: Dec 14 2017 41 mins
    Hélène Lyon, IBM, Distinguished Engineer, IBM Z Solutions Architect
    IT is a key player in the digital and cognitive transformation of business processes delivering solutions for improved business value with analytics. This session will step by step explain the journey to secure production while adopting new analytics technologies leveraging mainframe core business assets
  • Big Data Analytics vs Privacy: Risks and Opportunities Recorded: Dec 14 2017 58 mins
    Rob Anderson, Head of Field Operations (Privitar),Tim Hickman, Associate (White & Case)
    Today's modern businesses gain competitive edge and remain innovative by using advanced analytics and machine learning. Utilising big data can build customer loyalty by improving personalised marketing campaigns; optimises fraud detection; and improves products and services by advanced testing. However, the data sets required for advanced analytics are often sensitive, containing personal customer information, and therefore come with an inherent set of privacy risks and concerns.

    This roundtable will cover a few key questions on data utility and privacy:

    - In what ways advanced analytics help businesses gain competitive edge?

    - What is defined as sensitive data?

    - Will GDPR affect the way you're allowed to use customer data?

    - What opportunities are there to utilise sensitive data?

    Unlocking the data’s true value is a challenge, but there are a range of tools and techniques that can help. This live discussion will focus on the data analytics landscape; compliance considerations and opportunities for improving data utility in 2018 and beyond.

    Key takeaways:

    - A view of the data protection landscape

    - How to remaining compliant with GDPR when using customer data

    - Use cases for advanced analytics and machine learning

    - Opportunities for maximising data utility in 2018
  • Multi-Cloud Storage: Addressing the Need for Portability and Interoperability Recorded: Dec 12 2017 43 mins
    John Webster, Senior Partner, Evaluator Group, Mark Carlson, SNIA CSI Co-Chair, Alex McDonald, SNIA CSI Chair
    In a recent survey of enterprise hybrid cloud users, the Evaluator Group saw that nearly 60% of respondents indicated that lack of interoperability is a significant technology-related issue that they must overcome in order to move forward. In fact, lack of interoperability was chosen above public cloud security and network security as significant inhibitors. This webcast looks at enterprise hybrid cloud objectives and barriers with a focus on cloud interoperability within the storage domain and the SNIA’s Cloud Storage Initiative to promote interoperability and portability of data stored in the cloud.
  • From Big Data to AI: Building Machine Learning Applications Recorded: Dec 12 2017 49 mins
    Maloy Manna Data engineering PM, AXA Data Innovation Lab
    The newest buzzword after Big Data is AI. From Google search to Facebook messenger bots, AI is also everywhere.

    Machine learning has gone mainstream. Organizations are trying to build competitive advantage with AI and Big Data.

    But, what does it take to build Machine Learning applications? Beyond the unicorn data scientists and PhDs, how do you build on your big data architecture and apply Machine Learning to what you do?

    This talk will discuss technical options to implement machine learning on big data architectures and how to move forward.
  • Applying Machine Learning to unstructured files and data for research Recorded: Dec 12 2017 45 mins
    Dr Tom Parsons, Research Director and Dr Stuart Bowe, Data Scientist from Spotlight Data
    Researchers generate huge amounts of valuable unstructured data and articles from research every day. The potential for this information is huge: cancer and pharmaceutical breakthroughs, advances in technology and cultural research that can improve the world we live in.

    This webinar discusses how text mining and Machine Learning can be used to make connections across this broad range of files and help drive innovation and research. We discuss using Kubernetes microservices to analyse the data and then applying Machine Learning and graph databases to simplify the reuse of the data.
  • Unprotected Files on a Public Cloud Server: Live Panel on the NSA Data Leak Recorded: Dec 8 2017 59 mins
    Chris Vickery, George Crump, David Linthicum, Charles Goldberg, Mark Carlson
    Public, private and hybrid cloud are nothing new, but protecting sensitive data stored on these servers is still of the utmost concern. The NSA is no exception.

    It recently became publicized that the contents of a highly sensitive hard drive belonging to the NSA (National Security Agency) were compromised. The virtual disk containing the sensitive data came from an Army Intelligence project and was left on a public AWS (Amazon Web Services) storage server, not password-protected.

    This is one of at least 5 other leaks of NSA-related data in recent years. Not to mention the significant number of breaches and hacks we’ve experienced lately, including Yahoo!, Equifax, WannaCry, Petya, and more.

    The culprit in this case? Unprotected storage buckets. They have played a part in multiple other recent exposures, and concern is on the rise. When it comes to storing data on public cloud servers like AWS, Azure, Google Cloud, Rackspace and more, what are the key responsibilities of Storage Architects and Engineers, CIOs and CTOs to avoid these types data leaks?

    Tune in with Chris Vickery, Director of Cyber Risk Research at UpGuard and the one who discovered the leak, along with George Crump, Chief Steward, Storage Switzerland, David Linthicum, Cloud Computing Visionary, Author & Speaker, Charles Goldberg, Sr. Director of Product Marketing, Thales e-Security, and Mark Carlson, Co-Chair, SNIA Technical Council & Cloud Storage Initiative, for a live panel discussion on this ever-important topics.
  • The New Business Reality of GDPR with David Siegel and Michael Shea Recorded: Nov 30 2017 52 mins
    David Siegel and Michael Shea (20|30)
    The new business reality of GDPR and how you use customer data is inexorably approaching, if you work in or are doing business with anyone in the EU you must deal with this regulation.

    With data protection, there are really only two options: protection of data through ever-more data centralization and security or turning the customer data paradigm on its head and decentralize the data.

    We have a new model: give your customers full control over their data, gain their trust, and lower your costs with the open-source Pillar Business Wallet. Join our conversation Thursday, 30th of November.
  • From Data with Love: How the data economy is impacting the insurance sector Recorded: Nov 20 2017 60 mins
    JS Gourevitch, Luca Schnettler, Petra Wildermann, Anil Celik, Thomas Lethenborg
    The data economy and digital technologies are deeply transforming almost all areas of our lives. One of the most heavily transformed revolve around insurance and healthcare with a number of really interesting development possibly redefining the way we take care of ourselves and the way we consumer and use insurance as well.

    From harnessing the power of data to better help mental health patients, carers and medical personnel with their treatments to assessing the risk of developing broad range of illnesses and engaging better with users to propose them personalised healthy life plans to using big data and analytics to track down and prepare for epidemics to using data to better cover cars and drivers with car insurances and finally using social media data for insurers to better engage with customers, this webinar will propose a fascinating exploration of the opportunities, risks, new models supporting the digital transformation in banking.

    Moderated by Jean-Stéphane Gourévitch
    With:
    Luca Schnettler, CEO and Founder, HealthyHealth (UK)
    Petra Wildermann, Business Development Director, Metabiota (Switzerland)
    Anil Celik, Co-founder and CEO Urbanstats (US)
    Thomas Lethenborg, CEO, Monsenso (Denmark)
  • Transactional Models & Their Storage Requirements Recorded: Oct 31 2017 63 mins
    Alex McDonald, SNIA-ESF Vice Chair, NetApp, J Metz, SNIA Board of Directors, Cisco
    We’re all accustomed to transferring money from one bank account to another; a credit to the payer becomes a debit to the payee. But that model uses a specific set of sophisticated techniques to accomplish what appears to be a simple transaction. We’re also aware of how today we can order goods online, or reserve an airline seat over the Internet. Or even simpler, we can update a photograph on Facebook. Can these applications use the same models, or are new techniques required?

    One of the more important concepts in storage is the notion of transactions, which are used in databases, financials, and other mission critical workloads. However, in the age of cloud and distributed systems, we need to update our thinking about what constitutes a transaction. We need to understand how new theories and techniques allow us to undertake transactional work in the face of unreliable and physically dispersed systems. It’s a topic full of interesting concepts (and lots of acronyms!). In this webcast, we’ll provide a brief tour of traditional transactional systems and their use of storage, we’ll explain new application techniques and transaction models, and we’ll discuss what storage systems need to look like to support these new advances.

    And yes, we’ll explain all the acronyms and nomenclature too.

    You will learn:

    •A brief history of transactional systems from banking to Facebook
    •How the Internet and distributed systems have changed and how we view transactions
    •An explanation of the terminology, from ACID to CAP and beyond
    •How applications, networks & particularly storage have changed to meet these demands

    After watching, check out our webcast Q&A blog http://sniaesfblog.org/?p=662
  • Three Ways To Accelerate Your Data Lake Migration To Cloud Recorded: Oct 25 2017 45 mins
    Kelly Stirman, VP Strategy, Dremio
    Public cloud deployments have become irresistible in terms of flexibility, low barriers to entry, security, and developer friendliness. But the sheer inertia of traditional data lakes make them difficult to transition to cloud. In this talk we'll look at examples of how leading companies have made the transition using open source technologies and hybrid strategies.

    Instead of following a "lift and shift" strategy for moving data lake workloads to the cloud, there are new considerations unique to cloud that should be considered alongside traditional approaches related to compute (eg, GPU, FPGA), storage (object store vs. file store), integrations, and security.

    Viewers will take away techniques they can immediately apply to their own projects.
  • Designing Data Lakes: Architecture options with open source tools Recorded: Oct 25 2017 63 mins
    Maloy Manna, PM Engineering, AXA Data Innovation Lab, Paris
    The concept of Data lakes evolved to address challenges and opportunities in managing big data.

    Organizations are investing massive amounts of time and money to upgrade existing data infrastructures and build data lakes whether on-premises or in the cloud.

    This talk will discuss architectures and design options to implement data lakes with open source tools. Also covered are challenges of upgrade & migration from existing data warehouses, metadata management, supporting self-service and managing production deployments.
  • Virtual Data Lake: A Reality Recorded: Oct 25 2017 42 mins
    Hélène Lyon, IBM, Distinguished Engineer, IBM Z Solutions Architect
    As an Enterprise customer, you are potentially using IBM Z in a hybrid cloud implementation. Let's understand how to benefit from cloud access to mainframe data without moving it outside z; thereby improving security, reducing integration challenges and answering your GDPR auditor's needs.
  • Using Docker to realise a modular Big Data Platform & Leveraging SANSA Stack Recorded: Oct 24 2017 43 mins
    Dr. Hajira Jabeen, Senior Researcher at the University of Bonn
    Join this webinar where senior researches will present:

    1) Big Data Integrator Platform
    - Use of Docker and Docker swarm to realize a modular Big Data Platform

    2) Semantic Analytics Stack
    - Use of Big data distributed processing engines to leverage Scalable
    processing for the Semantic Web (RDF data representation, Querying,
    Inference, and Machine Learning)

    3) Seven societal challenges in Big Data Europe
    -Combination of different Big Data tools to create Big Data Value Chain
    (Pipeline) for different Use cases representing the societal challenges
  • Advanced Analytics in the Cloud - the latest cloud analytics innovations Recorded: Oct 24 2017 64 mins
    Iver van de Zand
    Iver van de Zand will talk and demo on the latest SAP innovations for analytics in the cloud. Keywords are live connectivity and the closed loop of combined business intelligence, planning and predictive analytics all in one environment. Fully ready and prepared for big data.
  • The Emerging Impact of NVMe-oF and Storage Class Memory Recorded: Oct 17 2017 61 mins
    Jeff Kato, Senior Analyst & Consultant, Taneja Group
    Join us for a fast-paced and informative 60-minute roundtable as we discuss the latest—and potentially most game-changing—technology disruptors to traditional storage architectures since flash: NVMe over fabric and Storage Class Memory.

    It was just five years ago that Flash technology transformed the traditional storage market forever. Modern flash-first arrays are now the new normal for traditional storage. Will a new shared storage access protocol called NVM express over Fabric (NVMe-oF) combined with the advent of storage class memory (SCM) be equally disruptive to traditional storage over the next five years as NAND flash technology was in the past?

    Vendors are now announcing new products and future architectures to enable them to support these new technologies. With the help of a lively panel of experts from HPE, Pivot3, and Mellanox, we will unpack this topic and explore how their innovative approaches to leveraging Storage Class Memory and NVMe-oF can radically improve storage products and solutions.
  • Introduction to Blockchain: Bitcoin, Ethereum, Ledgers, and more Recorded: Oct 9 2017 71 mins
    David Siegel, Blockchain, decentralization and business agility expert
    Still confused about this whole Blockchain thing? Interested in investing in digital currencies, but not sure where to start? Want to get a better idea of the threats and opportunities?

    David Siegel is a Blockchain, decentralization and business agility expert who has been a high-level management & strategy consultant to companies like Sony, Hewlett Packard, Amazon, NASA, Intel, and many start-ups. David has been praised for being able to explain Blockchain in the most simple and interesting way.

    What you will learn:
    -What is Bitcoin?
    -What is the blockchain?
    -What is Ethereum? What is Ether?
    -What is a distributed application?
    -What is a smart contract?
    -What is a triple ledger?
    -What about identity and security?
    -What business models are at risk?
    -What are the opportunities?
    -What should we do?
  • Everything You Wanted to Know About Storage - Cyan: Storage Management Recorded: Sep 28 2017 57 mins
    Richelle Ahlvers, Broadcom, Mark Rogov, Dell EMC, Alex McDonald, NetApp, J Metz, Cisco
    Storage can be something of a “black box,” a monolithic entity that is at once mysterious and scary. That’s why we created “The Everything You Wanted To Know About Storage But Were Too Proud to Ask” webcast series. So far, we’ve explored various and sundry aspects of storage, focusing on “the naming of the parts.” Our goal has been to break down some of the components of storage and explain how they fit into the greater whole.

    This time, however, we’re going to open up Pandora’s Box and peer inside the world of storage management, uncovering some of the key technologies that are used to manage devices, storage traffic, and storage architectures. In particular, we’ll be discussing:

    •Storage networking management protocols
    •SMI-S – The bread-and-butter of vendor-neutral storage management
    •SNIA Swordfish – The new storage management solution gaining widespread momentum
    •Software-Defined Storage – the catch-all term for storage that includes architectures and management

    There’s so much to say on each of these subjects we could do a full webcast on any one of them, but for a quick overview of many of the technologies that affect storage in one place, we think you will find your time has been well spent.

    Check out the Q&A blog from this webcast http://sniaesfblog.org/?p=658
Making data intelligent
You've got data. It's time manage it. Find information here on everything from data governance and data quality, to master and metadata management, data architecture, and the thing that was just invented ten seconds ago.

Embed in website or blog

Successfully added emails: 0
Remove all
  • Title: Anomaly Detection in Predictive Maintenance
  • Live at: Nov 11 2015 12:00 pm
  • Presented by: Rosaria Silipo, Data Scientist, KNIME
  • From:
Your email has been sent.
or close