DOCSLIB.ORG

Building Cognitive Applications with IBM Watson Services: Volume 1 Getting Started

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text

Load more

Front cover Building Cognitive Applications with IBM Watson Services: Volume 1 Getting Started Dr. Alfio Gliozzo Chris Ackerson Rajib Bhattacharya Addison Goering Albert Jumba Seung Yeon Kim Laksh Krishnamurthy Thanh Lam Angelo Littera Iain McIntosh Srini Murthy Marcel Ribas In partnership with IBM Skills Academy Program Redbooks International Technical Support Organization Building Cognitive Applications with IBM Watson Services: Volume 1 Getting Started June 2017 SG24-8387-00 Note: Before using this information and the product it supports, read the information in “Notices” on page v. First Edition (June 2017) This edition applies to IBM Watson services in IBM Bluemix. © Copyright International Business Machines Corporation 2017. All rights reserved. Note to U.S. Government Users Restricted Rights -- Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Contents Notices . .v Trademarks . vi Preface . vii Authors. vii Now you can become a published author, too! . .x Comments welcome. .x Stay connected to IBM Redbooks . xi Chapter 1. Introduction to cognitive computing . 1 1.1 Brief history of cognitive computing . 2 1.1.1 The eras of computing . 2 1.1.2 The future of computing is cognitive . 4 1.1.3 Impact of cognitive computing to our lives . 4 1.2 Basic concepts . 5 1.3 Characteristics of cognitive systems . 8 1.3.1 Solving real life problems with cognitive systems . 9 1.4 References . 10 Chapter 2. Cognitive business and IBM Watson . 11 2.1 Landscape of cognitive computing in the industry . 12 2.1.1 Consumer market: Cognitive computing offerings . 13 2.1.2 Enterprise market: Cognitive computing offerings . 14 2.1.3 Delivering cognitive services: Cloud and open source projects . 15 2.1.4 Cognitive computing and the future of jobs. 16 2.2 Introducing IBM Watson . 16 2.2.1 Watson APIs: Build with Watson. 17 2.2.2 IBM Watson applied to industries, businesses, and science . 18 2.2.3 Watson use cases. 23 2.2.4 Watson demonstrations . 26 2.3 References . 28 Chapter 3. Introduction to question-answering systems . 29 3.1 The Jeopardy! challenge. 30 3.2 DeepQA system architecture . 31 3.3 Exploring the DeepQA pipeline through an example . 34 3.3.1 Question analysis . 34 3.3.2 Primary search . 35 3.3.3 Hypothesis generation . 36 3.3.4 Hypothesis and evidence scoring . 36 3.3.5 Final merging and ranking . 38 3.4 References . 40 Chapter 4. Evolution from DeepQA to Watson Developer Cloud . 41 4.1 Why commercialize Watson . 42 4.2 Refresher of DeepQA architecture . 44 4.3 Evolution to Watson Developer Cloud . 46 4.3.1 Evolution of question analysis. 48 4.3.2 Microservices and robust tooling evolved from DeepQA . 54 © Copyright IBM Corp. 2017. All rights reserved. iii 4.4 Watson Conversation service . 56 4.5 Watson Discovery service. 58 4.6 Evolution summary . 60 4.7 References . 60 Chapter 5. Domain adaptation . 61 5.1 Introduction to domain adaptation. 62 5.2 IBM Watson Developer Cloud and domain adaptation . 63 5.2.1 Watson Conversation . 64 5.2.2 Watson Language Translator . 67 5.2.3 Watson Natural Language Classifier. 69 5.2.4 Watson Retrieve and Rank . 71 5.2.5 Watson Visual Recognition . 73 5.2.6 Watson Speech to Text. 75 5.2.7 Watson Text to Speech. 77 5.2.8 Watson Natural Language Understanding . 79 5.2.9 Watson Discovery . 80 5.3 Watson Knowledge Studio . 81 5.3.1 Watson Knowledge Studio domain adaptation overview . 82 5.3.2 Example: Creating a machine learning model . 84 5.3.3 Deploying a machine-learning annotator to Watson Natural Language Understanding . 104 5.3.4 Deploying a machine-learning annotator to Watson Discovery . 107 Related publications . 109 IBM Redbooks . 109 Online resources . 109 Help from IBM . 112 iv Building Cognitive Applications with IBM Watson Services: Volume 1 Getting Started Notices This information was developed for products and services offered in the US. This material might be available from IBM in other languages. However, you may be required to own a copy of the product or product version in that language in order to access it. IBM may not offer the products, services, or features discussed in this document in other countries. Consult your local IBM representative for information on the products and services currently available in your area. Any reference to an IBM product, program, or service is not intended to state or imply that only that IBM product, program, or service may be used. Any functionally equivalent product, program, or service that does not infringe any IBM intellectual property right may be used instead. However, it is the user’s responsibility to evaluate and verify the operation of any non-IBM product, program, or service. IBM may have patents or pending patent applications covering subject matter described in this document. The furnishing of this document does not grant you any license to these patents. You can send license inquiries, in writing, to: IBM Director of Licensing, IBM Corporation, North Castle Drive, MD-NC119, Armonk, NY 10504-1785, US INTERNATIONAL BUSINESS MACHINES CORPORATION PROVIDES THIS PUBLICATION “AS IS” WITHOUT WARRANTY OF ANY KIND,.
Recommended publications
  • Corporate Citizenship in India Transforming Business, Technology and Society

    Corporate Citizenship in India Transforming Business, Technology and Society

    IBM Corporate Citizenship Corporate Citizenship in India Transforming business, technology and society IBM’s longstanding, global commitment to corporate responsibility is a “At IBM, we leverage our demonstration of our values and the priorities that guide them. By thought leadership, integrating corporate responsibility with business strategy, we contrib- ute to the communities in which we do business while engaging our technologies and expertise clients, partners and employees. IBM’s technology and talent have the to help our clients and our power to help transform governments, institutions, communities and communities – making a the quality of life for people around the world. Whether it’s improving difference to where we live education, revitalizing cities, protecting the environment or driving and work. Our CSR focus economic growth, IBM and IBMers contribute innovative solutions to the world’s toughest societal challenges. in 2014 was on supporting the community Education through service grants, IBM’s Teachers TryScience (TTS) is a science portal and resources, helping build the capacity strategies and tutorial for science educators across the globe to spark students’ interest in science, technology, engineering and math of NGOs that we are (STEM). Through Teachers TryScience, teachers can improve their associated with to make a instruction of project-based learning, with a focus on engineering and larger or deeper impact. design. Teachers are encouraged to search for grade-specific lessons We continue to evolve our that are linked to online professional development that helps them approach on corporate further implement lessons in the classroom. The TTS Community of Practice or the online teachers community allows to share the best citizenship to provide the practices and experiences across each country.
  • Artificial Intelligence in Health Care: the Hope, the Hype, the Promise, the Peril

    Artificial Intelligence in Health Care: the Hope, the Hype, the Promise, the Peril

    Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril Michael Matheny, Sonoo Thadaney Israni, Mahnoor Ahmed, and Danielle Whicher, Editors WASHINGTON, DC NAM.EDU PREPUBLICATION COPY - Uncorrected Proofs NATIONAL ACADEMY OF MEDICINE • 500 Fifth Street, NW • WASHINGTON, DC 20001 NOTICE: This publication has undergone peer review according to procedures established by the National Academy of Medicine (NAM). Publication by the NAM worthy of public attention, but does not constitute endorsement of conclusions and recommendationssignifies that it is the by productthe NAM. of The a carefully views presented considered in processthis publication and is a contributionare those of individual contributors and do not represent formal consensus positions of the authors’ organizations; the NAM; or the National Academies of Sciences, Engineering, and Medicine. Library of Congress Cataloging-in-Publication Data to Come Copyright 2019 by the National Academy of Sciences. All rights reserved. Printed in the United States of America. Suggested citation: Matheny, M., S. Thadaney Israni, M. Ahmed, and D. Whicher, Editors. 2019. Artificial Intelligence in Health Care: The Hope, the Hype, the Promise, the Peril. NAM Special Publication. Washington, DC: National Academy of Medicine. PREPUBLICATION COPY - Uncorrected Proofs “Knowing is not enough; we must apply. Willing is not enough; we must do.” --GOETHE PREPUBLICATION COPY - Uncorrected Proofs ABOUT THE NATIONAL ACADEMY OF MEDICINE The National Academy of Medicine is one of three Academies constituting the Nation- al Academies of Sciences, Engineering, and Medicine (the National Academies). The Na- tional Academies provide independent, objective analysis and advice to the nation and conduct other activities to solve complex problems and inform public policy decisions.
  • DB2 UDB V8 and Websphere V5 Performance Tuning and Operation Guide

    DB2 UDB V8 and Websphere V5 Performance Tuning and Operation Guide

    Front cover DB2 UDB V8 and WebSphere V5 Performance Tuning and Operation Guide Best performance tuning practices for DB2 UDB and WAS integrated environment Gets you smoothly up and running DB2 UDB and WAS together Problem determination scenarios Whei-Jen Chen Peter Z. He Kang Yong Ying Sunminder S Saini Andreas Paulsen ibm.com/redbooks International Technical Support Organization DB2 UDB V8 and WebSphere V5 Performance Tuning and Operation Guide March 2004 SG24-7068-00 Note: Before using this information and the product it supports, read the information in “Notices” on page ix. First Edition (March 2004) This edition applies to IBM DB2 Universal Database Version 8.1 and IBM WebSphere Server V5.0.2, for use with IBM AIX 5.1 and Windows 2000 operating systems. © Copyright International Business Machines Corporation 2004. All rights reserved. Note to U.S. Government Users Restricted Rights -- Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Contents Notices . ix Trademarks . x Preface . xi The team that wrote this redbook. xii Become a published author . xiv Comments welcome. xv Chapter 1. Introduction. 1 1.1 IBM On Demand era . 2 1.1.1 The IBM On Demand operating environment . 2 1.2 Why DB2 UDB and WebSphere . 9 1.3 Key areas of performance . 10 1.3.1 Hardware. 11 1.3.2 Operating system . 11 1.3.3 Application Server and WebServer . 12 1.3.4 Database manager . 13 1.3.5 Application programs . 13 1.4 Performance tuning guidelines . 14 1.4.1 Initial efforts always pay . 14 1.4.2 Tune the identified constraints .
  • Troubleshooting Websphere Applications

    Troubleshooting Websphere Applications

    IBM WebSphere Application Server Network Deployment for Distributed Platforms, Version 8.0 Troubleshooting WebSphere applications Note Before using this information, be sure to read the general information under Notices” on page 349. Compilation date: July 29, 2011 © Copyright IBM Corporation 2011. US Government Users Restricted Rights – Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Contents How to send your comments ...........................vii Changes to serve you more quickly .........................ix Chapter 1. Troubleshooting ActivitySessions......................1 Troubleshooting ActivitySessions ...........................1 Chapter 2. Troubleshooting Application profiling ....................3 Application profiling exceptions ............................3 Chapter 3. Troubleshooting batch applications .....................5 Troubleshooting batch applications ..........................5 Adding log and trace settings to the batch environment ..................5 Batch common problems .............................5 Diagnosing problems using job logs .........................7 Chapter 4. Troubleshooting applications that use the Bean Validation API ..........9 Bean validation troubleshooting tips ..........................9 Chapter 5. Troubleshooting Client applications ....................11 Application client troubleshooting tips .........................11 Adding tracing and logging for stand-alone clients ....................17 Chapter 6. Troubleshooting Data access resources...................19
  • Real-Time System for Driver Fatigue Detection Based on a Recurrent Neuronal Network

    Real-Time System for Driver Fatigue Detection Based on a Recurrent Neuronal Network

    Journal of Imaging Article Real-Time System for Driver Fatigue Detection Based on a Recurrent Neuronal Network Younes Ed-Doughmi 1,* , Najlae Idrissi 1 and Youssef Hbali 2 1 Department Computer Science, FST, University Sultan Moulay Sliman, 23000 Beni Mellal, Morocco; [email protected] 2 Computer Systems Engineering Laboratory Cadi Ayyad University, Faculty of Sciences Semlalia, 40000 Marrakech, Morocco; [email protected] * Correspondence: [email protected] Received: 6 January 2020; Accepted: 25 February 2020; Published: 4 March 2020 Abstract: In recent years, the rise of car accident fatalities has grown significantly around the world. Hence, road security has become a global concern and a challenging problem that needs to be solved. The deaths caused by road accidents are still increasing and currently viewed as a significant general medical issue. The most recent developments have made in advancing knowledge and scientific capacities of vehicles, enabling them to see and examine street situations to counteract mishaps and secure travelers. Therefore, the analysis of driver’s behaviors on the road has become one of the leading research subjects in recent years, particularly drowsiness, as it grants the most elevated factor of mishaps and is the primary source of death on roads. This paper presents a way to analyze and anticipate driver drowsiness by applying a Recurrent Neural Network over a sequence frame driver’s face. We used a dataset to shape and approve our model and implemented repetitive neural network architecture multi-layer model-based 3D Convolutional Networks to detect driver drowsiness. After a training session, we obtained a promising accuracy that approaches a 92% acceptance rate, which made it possible to develop a real-time driver monitoring system to reduce road accidents.
  • IBM India Private Limited: Update on Material Event

    IBM India Private Limited: Update on Material Event

    October 20, 2020 IBM India Private Limited: Update on Material Event Summary of rating action Instrument* Rated Amount (Rs. crore) Rating outstanding [ICRA]AAA (Stable) / [ICRA]A1+; Long-term/Short-term – Proposed facilities 150.00 outstanding Short-term - Non-fund Based 20.00 [ICRA]A1+; outstanding Long-term (Interchangeable) (20.00) [ICRA]AAA (Stable); outstanding Total 170.00 Material Event On October 8, 2020, International Business Machines Corporation, USA (IBM Corporation; rated A2/stable/P1 by Moody’s) has announced its decision to spin off its managed infrastructure services unit of global technology services (GTS) division into a separate public company by the end of 2021, subject to regulatory approvals. The spin-off is to sharpen its focus on high-margin open hybrid cloud platform and artificial intelligence (AI) capabilities. Subsequently, on October 10, 2020, based on media articles, it is noted that the Indian operations, which are currently carried on under IBM India Private Limited (IBM India), would be restructured as well and around one-fourth of its employees will be part of the new entity catering to the needs of managed IT infrastructure services. Impact of the Material Event IBM India is one of the key global delivery centres for IBM Corporation with over 70% of its revenues being derived from export of services to the parent entity and its fellow subsidiaries, as part of the outsourcing business model. The company derives over 20% of its revenues from technology services, cloud platform and global business services division, wherein IBM India provides infrastructure services and technology support services to its clients.
  • AD112 Development and Deployment of Lotus Product Documentation Wikis

    AD112 Development and Deployment of Lotus Product Documentation Wikis

    AD112 Development and Deployment of Lotus Product Documentation Wikis Craig Lordan | Manager Kevin Giles | Advisory Software Engineer 2 12 Agenda 11 1 10 2 ● Background 9 3 ▬ IBM Lotus® product wikis overview 8 4 ▬ 7 5 Your speakers today 6 ▬ IBM Lotus® Domino® infrastructure ● Lotus Domino wiki application development ▬ First pass at Lotus Domino wikis ▬ Benefits of XPages for wikis ▬ XPages Wiki template on OpenNTF ▬ Custom development examples ● Real-world experience ▬ XPages deployment experience ▬ Our XPages lessons ▬ What about wikis in IBM Lotus® Connections? ● Project future ● Q&A 3 Lotus product wikis overview ● Product wikis for all Lotus and IBM WebSphere® Portal products ● Live on the Internet, open to all customers and users ▬ Visit www.lotus.com/ldd/wikis ● Added first wiki for IBM Lotus® Notes® and Lotus Domino in December 2007 ● Additional wikis added in 2008 ● Current content includes supplemental technical content and IBM Redbooks® Wiki listing IBM Composite Applications IBM Lotus Notes ● IBM LotusLive™ IBM Lotus Notes Traveler Plan is to use wikis for official product IBM Mashup Center IBM Lotus® Quickr IBM Lotus® ActiveInsight® IBM Lotus® Sametime® documentation Lotus Connections IBM Lotus® Symphony Lotus Domino IBM Lotus® Web Content ▬ IBM Lotus Domino Designer Management IBM Lotus® Expeditor, IBM Lotus® Foundations, Lotus Expeditor IBM Lotus® Workforce Management IBM Mashup Center already publish product doc to IBM Lotus® Forms IBM WebSphere Dashboard Lotus Foundations Framework wikis IBM Lotus® iNotes® WebSphere Portal IBM Lotus® Mobile Connect IBM WebSphere® Portlet Factory 4 Your speakers today ● Craig Lordan, Manager ▬ Craig Lordan is a manager at IBM Lotus. He joined Lotus in 1998 as a technical writer for Lotus Notes and Lotus Domino.
  • IBM India Private Limited: Ratings of [ICRA]AAA (Stable)/ [ICRA]A1+ Assigned

    IBM India Private Limited: Ratings of [ICRA]AAA (Stable)/ [ICRA]A1+ Assigned

    September 23, 2020 IBM India Private Limited: Ratings of [ICRA]AAA (Stable)/ [ICRA]A1+ assigned Summary of rating action Current Rated Amount Instrument* Rating Action (Rs. crore) Long-term/Short-term – Proposed facilities 150.00 [ICRA]AAA (Stable) / [ICRA]A1+; assigned Short-term - Non-Fund based 20.00 [ICRA]A1+; assigned Long-term (Interchangeable) (20.00) [ICRA]AAA (Stable); assigned Total 170.00 Rationale The assigned ratings favourably factor in the strong parentage of IBM India Private Limited (IBM India), being a step- down subsidiary of International Business Machines Corporation, USA (IBM Corporation; rated A2/stable/P1 by Moody’s), experienced management team, strong operational and strategic linkages with IBM Corporation, and its healthy financial and operational profile with presence across various end-user industries. Being part of IBM Corporation, a global leader in providing information technology (IT)-related services and products, IBM India has access to the strong expertise and capabilities in the business of the latter. India is a key market for IBM Corporation, although its share in the overall revenues is less (<5%) because of the demographic advantage of availability of low-cost labour and large, skilled talent pool. The company is one of the key global delivery centres at the Group level and derived over 70% of its revenues in FY2020 from export of services to its parent and fellow subsidiaries on a cost- plus model. IBM India’s credit profile is characterised by its large scale of operations, stable earnings and cashflows, net debt-free status and strong liquidity profile. The Covid-19 pandemic has adversely impacted the Indian and global IT services industry, causing disruption to both supply (restriction of movement of employees) and demand (like delayed offtake of new projects, reduced discretionary spend and IT budget cuts).
  • Integration of System for Research in Health with Computation in Cloud Using Artificial Intelligence

    Integration of System for Research in Health with Computation in Cloud Using Artificial Intelligence

    MOJ Proteomics & Bioinformatics Research Article Open Access Integration of system for research in health with computation in cloud using artificial intelligence Abstract Volume 7 Issue 4 - 2018 Currently the use of information technology is often applied in the health area. With regard 1 to scientific research, we have the SINPE© Integrated System of Electronic Protocols. Carlos Henrique Kuretzki, José Simão de 2 3 The purpose of this tool is to support the researcher in this area who until now did not Paula Pinto, José Claudio Vianna have statistical tests. The main objective of this work is to provide SINPE© users with the 1Professor of the Program for Analysis and Development of improvement in health data analysis through the use of cognitive computing technologies. Systems and Computer Engineering, Federal University, Brazil 2Professor of the Information Management Program, Federal Keywords: artificial intelligence, cloud computing, information systems University, Brazil 3Professor of the Computer Engineering, Universidade Positivo, Brazil Correspondence: Carlos Henrique Kuretzki, Professor of the Program for Analysis and Development of Systems and Computer Engineering, Federal University, Brazil, Email [email protected] Received: June 29, 2018 | Published: August 08, 2018 Introduction more quickly.4 IBM Watson is a cognitive computing technology and have been used to investigate the biological and health sciences. The health sector is one of the largest in most countries and can It is based on medical literature, patents, genetic, and chemical and significantly benefit from high‒quality, real‒time and location‒ pharmacological data.5 The IBM’s Watson platform combines some independent data. However, many healthcare professionals are capabilities, building a complete cognitive system, which is being not familiar with information technology solutions, business and called the new era of computing.
  • IBM Notes Traveler Administration

    IBM Notes Traveler Administration

    IBM C2040-412 IBM Notes Traveler Administration IBM C2040-412 Dumps Available Here at: https://www.certification-questions.com/ibm-exam/c2040-412-dumps.html Enrolling now you will get access to 118 questions in a unique set of C2040-412 dumps Question 1 Which option describes how a load balancer is used for an IBM Notes Traveler High Availability (HA) implementation? Options: A. secures connections between Notes Traveler servers and IBM Domino mail servers B. spreads the user to server connections across multiple Notes Traveler HA Pool members C. balances mail server traffic between Notes Traveler servers and clustered Domino mail servers D. spreads large amounts of data across multiple Notes Traveler servers when users are synchronizing a large attachment to a device Answer: B Question 2 Once IBM Notes Traveler servers are put into production, what average percentage should the CPU be below? Options: A. 65 B. 75 C. 85 D. 95 Answer: B Question 3 https://www.certification-questions.com IBM C2040-412 What is the minimum number of servers recommended for an IBM Notes Traveler 9.0 Service Pool, IBM Domino mail and database server with high availability for all components on Microsoft Windows or Linux platforms? Options: A. 5 B. 6 C. 7 D. 11 Answer: C Question 4 IBM Notes Traveler mobile client to server traffic is secured over which protocol? Options: A. Secure Socket Layer (SSL) B. Post Office Protocol 3 (POP3) C. HyperText Transfer Protocol (HTTP) D. Notes Remote Procedure Call (NRPC) Answer: A Question 5 How can an administrator ensure that the network communication between the IBM Notes Traveler server and the mail servers is optimized? Options: A.
  • Data Transfer Options and Requirements

    Data Transfer Options and Requirements

    Data Transfer Options and Requirements Original date 25 Jan 2005 Revision date 21 Aug 2018 Proprietary and Confidential Data Transfer Options and Requirements Summary of changes Date Short description of changes September 2016 Updated name of submission tool to SDSS. August 2018 Rebranded. Contacting support Support is available through the following link: https://www.ibm.com/software/support/watsonhealth/truven_support.html © Copyright IBM Corporation 2018 IBM Confidential 2 Data Transfer Options and Requirements Contents Summary of changes .................................................................................................................................... 2 Contacting support ........................................................................................................................... 2 Contents ........................................................................................................................................................ 3 Overview ....................................................................................................................................................... 5 Electronic data transfer methods ..................................................................................................... 5 Data suppliers ..................................................................................................................... 5 Data recipients ...................................................................................................................
  • Treatment and Differential Diagnosis Insights for the Physician's

    Treatment and Differential Diagnosis Insights for the Physician's

    Treatment and differential diagnosis insights for the physician’s consideration in the moments that matter most The role of medical imaging in global health systems is literally fundamental. Like labs, medical images are used at one point or another in almost every high cost, high value episode of care. Echocardiograms, CT scans, mammograms, and x-rays, for example, “atlas” the body and help chart a course forward for a patient’s care team. Imaging precision has improved as a result of technological advancements and breakthroughs in related medical research. Those advancements also bring with them exponential growth in medical imaging data. The capabilities referenced throughout this document are in the research and development phase and are not available for any use, commercial or non-commercial. Any statements and claims related to the capabilities referenced are aspirational only. There were roughly 800 million multi-slice exams performed in the United States in 2015 alone. Those studies generated approximately 60 billion medical images. At those volumes, each of the roughly 31,000 radiologists in the U.S. would have to view an image every two seconds of every working day for an entire year in order to extract potentially life-saving information from a handful of images hidden in a sea of data. 31K 800MM 60B radiologists exams medical images What’s worse, medical images remain largely disconnected from the rest of the relevant data (lab results, patient-similar cases, medical research) inside medical records (and beyond them), making it difficult for physicians to place medical imaging in the context of patient histories that may unlock clues to previously unconsidered treatment pathways.