1 | | SKOOL E..5 _ Trends and Applications CHAPTER 6 in Data Science University Prescribed Syllabus w.e.t Academic Year 2022-2023 Data Science : applications and case studies, Data science for text, image, video, audio, Data science for Multimodal applications, Sel-learring Topics: Image Net Largo Scale Visual Recognition Challenge (ILSVRC). 6.1 Data Science 62 Applications of Data Soien 63 Data Science Case studies, 6.4 Data science for Multimodal application 65 _ImageNet Large Scale Visual Recognition Challenge (ILSVRC)... 6.6 Multiple Choice Questions .n.nnnennsennsn + Chater EndsAl 8 DSA MU-Som 7.47) y 6.1 DATA SCIENCE + We are surrounded by data and in sbundanee, What do ‘we do with all of this data? + How do we make it use to us? What are its real- ‘world applications? These questions are the domain of data science, + Data science isthe domain of study that deals with vast volumes of data using modem tools and techaiques to find unseen pattems, derive meaningful information, and make bosiness decisions, + Ieinvolves techniques for identifying, collecting, and ‘exploring the data using colorful plots and graphs. + Data science uses complex machine learning algorithms to build predictive models. The data used for analysis can come from many different sources and presented in various formas + Data visualization, Data mining and Model building are some ofthe important phases in Data Science. + To understand Data Science, Consider this example. Jayesh loves books to read, but every time when he ‘wants to buy some book, he is always confused that Which book he should buy as there are plenty of choices in front of him. Now here, Data Science techniques willbe useful. * When he opens Amazon he will get product ‘recommendations on the basis of his past purchases. + When he chooses one of them, he also gets a recommendation to buy these books with this one as this setis mostly bought. + So, all recommendations of products and showing set ‘of books purchased collectively is one of the examples of Data Science. + A data scientist analyzes business data to extract meaningful insights. In other words, a data scientist solves business problems through a series of steps, including (1) Before tackling the data collection and analysis, the data scientist determines the problem by asking the right questions and gaining understanding. (MU-New Syllabus wef academic year 22-23)M7-62) la Scionc9)...Page ne rons ant appcatons in Data SeioneOh Page no. (6-2) ‘a The dm aes then determines th Cnc of variables and datas. ist gathers stud ang om eany disparate scuey public data et. ) The data scic unstructured data fro such as enterprise data, Once the data is collected, the data scieniy processes the raw data and converts it into a format suitable for analysis. This involves cleaning and validating the dala 10 guaranee uniformity, completeness, and accuracy. (5) After the data has been rendered into a usable form, it's fed into the analytic system which can be a machine learning algorithm oF @ statistical model. This is where the data scientists analyze and identify patterns and trends. (6) When the data has been completely rendered, the data scientist interprets the data to find ‘opportunities and solutions. (7) ‘The data scientists finish the task by preparing the results and insights to share with the appropriate stakeholders and communicating the results. Data scientists also rely heavily on atificial ly its subfields of machine Teaming and deep learning, o create models and make predictions using algorithms and other techniques. @ 16.2 APPLICATIONS OF DATA SCIENCE ‘The role of Data Science Applications hasn't evolved ‘overnight. Thanks to faster computing and cheaper storage, ‘we can now predict outcomes in minutes, which could take several human hours to process. Data science has found its applications in almost every industry. Healthcare 2 SelEDriving Cars Gaming 4. Image Recognition Recommendation Systems 6 Logistics Fraud Detection 8, Internet Search Targeted Advertsing 10. Speech Recognition 11, Aine Route Planning 12. Augmented Reality 14, Finance 13. Autocomplete 15. Cybersecurity 'ech-Neo Publications.. SACHIN SHAH Venture‘AL& DS:ll (MUSom 747) D1. Healthcare ‘+ Data science has led to a number the healthcare industry, OF brcalabroughs in + With avast network of data : now available vis everything from EMRS to clinical feel databases to personal fitness trackers, medical profesional are finding new ways (0 understand disease, practice preventive medici . aapnose dae ate es far and exe ew ‘treatment options. een ets companies a ing da ce to bel sophisticated medical instruments to detect and cure diseases, Self-Driving Cars Tesla, Ford and Volkswagen are all implementing predictive analytics in their new wave of autonomous vehicles. © These cars use thousands of tiny cameras and sensors to relay information in real-time. © Using machine learning, predictive analytics and data science, self-driving cars can adjust to speed limits, avoid dangerous lane changes and even take passengers ‘on the quickest route. > 3. Gaming Video and computer games are now being created with the help of data science and that has taken the gaming ‘experience tothe next level. > 4, Image Recognition Identifying patterns in images and detecting objects in fan image is one of the most popular data science applications. > 5, Recommendation Systems Netflix and Amazon give movie and product recommendations based on what you like to watch, purchase, or browse on their platforms. > 6, Logistics + Data Science is used by logistics companies to optimize routes to ensure faster delivery of products and increase operational efficiency. (MU-New Syilabus wae academic year 22-23)(M7-62) vids and Applications in Data Scionce)....Page no. (6-3) + Logistics UPS turns to data science to maximize efficieney, bot intemally and along is delivery routes. ‘© The company’s On-road Integrated Optimization and Navigation (ORION) tool uses data science-backed statistical modeling and algorithms that create optimal routes for delivery drivers based on weather, traffic, ‘construction, ete > 7. Braud Detection ‘Banking and financial institutions use data science and related algorithms to detect fraudulent transactions. > 8, Internet Search © There are many other search engines like Yahoo, Bing, ‘Ask, AOL, Google and so on. ‘© All these search engines make use of data science algorithms to deliver the best result for our searched query ina fraction of seconds. © Considering the fact that, Google processes more than 20 peta bytes of data every day. Had there been no data seience, Google wouldn't have been the ‘Google’ we know today. > 9, Targeted Advertising ‘© Starting from the display banners on various websites to the digital billboards at the airports, almost all of them are decided by using data science algorithms. © Thisis the reason why digital ads have been able to get ‘Jot higher CTR (Call-Through Rate) than traditional advertisements, They can be targeted based on a user's past behavi > 10, Speech Recognition ‘© Some of the best examples of speech recognition products are Google Voice, Siri, Cortana ete. ‘© Using the speech-recognition feature, even if you aren't ina position to type a message, your life woulda’t stop. * Simply speak out the message and it will be converted totext. > 11, Airline Route Planning, © Aiines companies started using data science to identify the strategic areas of improvements, Tb rech nic Pubtcatons_A SACHIN SHAN VerteAL&DSAtI(MU-Som 7.17) * Now using data science, the airline companies can predict flight delay, decide which class of aiplanes 10 ‘buy, whether to directly land at the destination or take & hhalt in between, effectively drive customer loyalty Programs. © Southwest Airlines, Alaska Airlines are among the top companies who've embraced data science to bring changes in their way of working. > 12, Augmented Reality © Data Science and Virtual Reality do have 2 relationship, considering a VR headset contains ‘computing knowledge, algorithms and data to provide ‘you with the best viewing experience. © A very small step towards this is the high-trending {game of Pokemon GO. ‘+ The ability to walk around things and look at Pokemon ‘on walls, streets things that aren't really there. > 13. Autocomplete © AutoComplete feature is an important part of Data Science where the user will get the facility to just type a few leters or words, and he will get the feature of auto-completing the line. * In Google Mail, when we are writing formal mail 10 someone 50 at that time data science concept of Auto complete feature is used where he/she is an efficient choice to auto-complete the whole line. ‘+ Also, in Search Engines in social media, in various apps, AutoComplete feature is widely used. > 14, Finance © Machine learning and data science have saved the financial industry millions of dollars, and Uunguantifiable amounts of time, For example, JP ‘Morgan's Contract Intelligence (COIN) platform uses Natural Language Processing (NLP) to process and extract vital data from about 12,000 commercial credit agreements a year. ‘© Thanks to data science, what would take around 360,000 manual labor hours to complete is now finished in a few hours, (MU-New Syllabus wes academic year 22-23)(M7-62) ta Scionce) (ends and Applications in Da » 15, Cybersecurity Data science is useful in every industry, bu it may be the most important in cybersecurity. Intemational cybersecurity firm Kaspersky is using data science and machine leaming to detect ove, "360,000 new samples of malware on a daily basis, Being able to instantaneously detect and lear new methods of cybercrime, through data science, is essential to our safety and security in the future, Wl 6.3__DATA SCIENCE CASE STUDIES ‘© Data science is a highly evolving domain with many practical applications and a huge open community. Solving a Data Science ease study means analyzing and solving a problem statement intensively. © Accase study in data science requires a systematic and ‘organized approach for solving the problem. © Generally, four main steps are needed to tackle every data science case study: (1) Defining the problem statement and strategy to solve it, (2) Gather and pre-process the data by making relevant assumptions. ) Select tool and appropriate algorithms to build ‘machine learning /deep learning models. (4) Make predictions, accept the solutions based on evaluation metres, and improve the model if necessary. 's See some case studies in Data Science. Case Study 1 : Data Science in Hotel Recommendation System A hotel recommendation system typically works on collaborative filtering that makes recommendations based on ratings given by other customers in the same category 3S the user looking for a product, Use Case: © We all plan trips and the first thing to do when Planning a trip is finding a hotel © There are so many Websites recommending the best hotel for our tip, SS recommending de Tech-Neo Publications..a SACHIN SHAH VentuteAL8 DS (MU-Som 7.17 Case Study 2: A hotel recommendation 5 hotel a user is most like hotels. So, to build this type of s to book the best hotel can do this using custor For example, stem aims to predict which 'y (0 choose from among all stem which will belp the user Ou of all the other hotels. We mer reviews, ° Suppose you want to go on a business trp, so the hotel recommendation system should show YoU the ttl which ter ena rtm ae for business travel, tants Tt is therefore also our approach to build a Tecommendation system based on customer reviews and ratings, ‘So, use the ratings and reviews given by customers who belong to the same category as the user and build a hotel recommendation system, Data Science in Entertainment Industry Due to the Pandemic, demand for OTT (Over:the-top) ‘media platforms has grown significantly. People prefer watching movies and web series or listening to the music of their choice at leisure in the convenience of their homes. ‘This sudden growth in demand has given rise to stiff competition. Every platform now uses data analytics in different capacities to provide __better-personalized recommendations to its subscribers and improve user experience. Use Case How Netflix uses data science to personalize the content and improve recommendations? Netfix is an extremely popular internet television platform with stream able content offered in several languages and caters to various audiences. In 2006, when Netflix entered this media streaming ‘market, they were interested in increasing the efficiency of their existing “Cinematch” platform by 10% and hence, offered a prize of $1 million to the winning team, ‘This approach was successful as they found a solution developed by the BellKor team at the end of the ‘competition that increased prediction accuracy by 10.06%. Over 200 work hours and an ensemble of 107 algorithms provided this result (MU-New Syllabus wee academic year 22-23)(M7-62) CTronds and Applications in Data Science)...Page no. (6-5). “These winning algorithms are now a part of the Netix recommendation system. Netflix also employs Ranking Algorithms to generate personalized recommendations of movies and TV Shows appealing tits users. Use Case Case Study 3: How Spotify uses big data to deliver a rich user experience for online musie streaming? Personalized online music streaming is another area where data science is being used. Spotify is a well- known on-demand music service provider launched in 2008, which effectively leveraged big data to create personalized experiences foreach user. It is a huge platform with more than 24 million subseribers and hosts a database of nearly 20million songs; they use the big data to offer a rich experience to its users Spotify uses this big data and various algorithms to train machine learning models to provide personalized content. Spotify offers a “Discover Weekly” feature that generates a personalized playlist of fresh unheard songs, ‘matching the user's taste every week, Using the Spotify “Wrapped” feature, users get an overview of their most favorite or frequently listened songs during the entice year in December. Spotify also leverages the data to run targeted ads to ‘grow its business. Thus, Spotify utilizes the user data, which is big data and some external data, to deliver a high-quality user experience Data Science in Banking and Finance Data science is extremely valuable in the Banking and Finance industry. Several high priority aspects of Banking and Finance like credit risk modeling (possibility of repayment of loan), fraud detection (detection of malicious or irregularities in transactional pattems using machine Jeaming), identifying customer lifetime value (prediction of bank performance based on existing and potential customers), customer segmentation (customer profiling based on behavior and characteristics for personalization of offers and services). Deb recricoPbicatins.A SACHIN SHAH VentreALB.DS4 (MU-Som 7-17) ion nally, data science is also used in realtime predictive iques to predict future events), Use Case + How HDFC utilizes Big Data Analytics to increase revenues and enhance the banking experience? + One of the major private barks in India, HDFC Bank, was an early adopter of Al + It started with Big Data analytics in 2004, intending to ‘row its revenue and understand its customers and markets better than its competitors. ‘+ Back then, they were trendsetters by setting up an enterprise data warehouse in the bank 10 be able to track the differentiation to be given to customers based ‘on their relationship value with HDC Bank + Data science and analytes have been crucial in helping HDFC bank segregate its customers and offer customized personal or commercial banking services. ‘© The analytics engine and SaaS use have been assisting the HDFC bank in eross-slling relevant ofers to its customers ‘+ Apart from the regular fraud prevention, it assists in keeping track of customer credit histories and bas also been the reason forthe speedy loan approvals offered by the bank. Case Study 4 : Data Science for Customer Personality Analysis ‘The analysis of customers i one of the most important roles that a data scientist has to do who is working at a product-based company. Use Case * Customer Personality Analysis isa detailed analysis of ‘a company’s ideal customers. ‘¢Ithelps a business to beter understand its customers and makes it easier for them to modify products according tothe s of different types of customers. ie needs, behaviors and concerns © We have to do an analysis that should help a business to modify its product based on its target customers {from different types of customer segments (MU-New Syllabus wes ademic year 22-23(M7-62) © For ex ew product t0 every customer In thE company, ‘Tanase, a company can analyZe which custome, Segment is most likely 10 buy the product and the, market the product only on that particular segment, case Study 5 : Data Science for Text Emotions Detection ‘The idea here is to train a machine learning model 1 enerate emojis based on input text. Then this machine Teaming model ean be used in training Artificial Intelligent Chatbots. Use Case ‘© Atuman can express his emotions in any form, such as the face, gestures, speech and text. ‘©The detection of text emotions is @ content-based classification problem. ‘© Detecting a person's emotions is a difficult task, but detecting the emotions using text written by a person i, even more difficult as a human can express his emotions in any form. ‘© Recognizing this type of emotion from a text written by ‘ person plays an important role in applications such as, chatbots, customer support forum, customer reviews tc. So, you have to train a machine learning model that can identify the emotion of a text by presenting the ‘most relevant emoji according tothe input text. Case Study 6: Covid 19 and Data Science + In the past two years of the Pandemic, the power of data science has been more evident than ever. Different pharmaceutical companies across the globe Could synthesize Covid 19 vaccines by analyzing the data to understand the trends and pattems of the outbreak, Data science made it possible to track the vieus in rea time, predict patterns, devise effective strategies © fight the Pandemic, and many mote. Use Case © How Johnson 4nd Johnson used data science to fight the Pandemic? ca data science team at Johnson and Johnso" "EPCS real-time data to track the spread of the Vis [Bh sco nanan asscun svenAL& DS (MU-Sem 7-11) ‘They built a glob survilancedatton @amaca to county level) hat helps them tack the Pendens progress, predict potential hotspots of the virus, and snow con hei pee ne oy nen investigational COVID-19 vaccine candidate. : ‘The team works wih incountry expe to determine wheter official number ae accurate and in the meat valid nfomation abou cas numbens, hospitalizations ‘montlity and testing rates, social compliance, and lea! policies to populate this dashboard 4 The team also studies the dt to build modes that ep the company ident groupe of invidoas a sk of sting affected by the vine and explo elective treatments o improve patient oucomes case Study ata Science in Ecommerce In the e-commerce sector, big data analytics can assist in customer analysis, reduce operational costs, forecast trends for better’ sales, provide personalized shopping experiences to customers, and many more. Use Case © How does Amazon use data science to personalize shopping experiences ‘customer satisfaction? ‘© Amazon is a globally leading eCommerce platform that offers a wide range of online shopping services. and improve ‘© Due to this, Amazon generates a massive amount of data that can be leveraged to understand consumer behavior and generate insights on competitors’ strategies. ‘© Amazon uses its data to provide recommendations to its users on different products and services. ‘© With this approach, Amazon is able to persuade its consumers into buying and making additional sales. + This approach works well for Amazon as it eams 35% of the revenue yearly with this technique. Additionally, ‘Amazon collects consumer data for faster order tracking and better deliveries. Amazon's virtual assistant ferent languages; uses speaker ‘Alexa, can Similarly, a converse in ‘camera to interact with the use! ‘+ Amazon utilizes the audio commands from users (0 lexa and deliver a better user experience. improve Al (0tu-New syllabus we f academic year 22-23)(M7-62) (Fronds and Applications in Data Scionoe)..Page no. (6-2). Case Study 8 : Data Science in Supply Chain Management # Predictive analyties and big data are driving innovation in domain. inthe Supply eh © They offer greater visibility into the company ‘operations, reduce costs and overheads, forecasting demands, predictive maintenance, product pricing, minimize supply chain interruptions, route optimization, fleet management, drive better performance, and more. Use Case ‘= Optimizing supply chain with big data analytics : UPS © UPS is a renowned package delivery and supply chain ‘management company. ‘© With thousands of packages being delivered every day, ‘on average, a UPS driver makes about 100 deliveries cach business day. On-time and safe package delivery are crucial to UPS's success. Hence, UPS offers an optimized navigation tool “ORION” (On-Road Integrated Optimization and Navigation), which uses highly advanced big data processing algorithms. This tool for UPS drivers provides route optimization concerning fuel distance, and time, UPS utilizes supply cchain data analysis in all aspects of its. shipping process. Data about packages and deliveries are captured through radars and sensors. The deliveries and routes are optimized using big data systems. Overall, this approach has helped UPS save 1.6 million gallons of gasoline in transportation every year, significantly reducing delivery costs. 7H 6.4 DATA SCIENCE FOR MULTIMODAL APPLICATIONS Multimodal Data ‘© Our experience of the world is multimodal: we see ‘objects, hear sounds, feel the texture, smell odors, and taste flavors. Tech-Neo Publications..A SACHIN SHAH VentureAL8. D-II (MU-Sem 7-7) * Modality refers to the way in which somethi oF is experienced and a research proble characterized as multimodal when such modalities, + In onder for Aniticial Ineligence to make progress in lunderstanding the world around us, it needs to be able {0 interpret such multimodal signals together. * Real-world applications usually involve data with various modalities, each containing valuable information, + In order to enhance the performance of these applications, it is essential to adequately analyze all of the information extracted from the different data modalities. ‘+ For example, images are usually associated with tags ‘and text explanations; texts contain images to more clearly express the main idea of the article. Different modalities are characterized by very different Facebook + In today’s era of digitalization, people spend hours on various social networking sites like Facebook, Instagram, WhatsApp, ete. Around 1.2 million people all over the globe upload 136,000 photos and update their status 293,000 times per minute. * Our various activities whether it be commenting, tweeting, uploading something or anything else ‘Benerates a large amount of data ‘+ In 2012, Facebook stated that it generates more than 500 terabytes of data every day. Data Science and many other Big Data technologies are helping Facebook to deal with such a large amount of data. (MU-New Syllabus wef academic year 22-23)MT-62) (trends and Applications in Data Science...Page no. (6. Some of the examples that show how Facebook 5, sing user data for developing smarter ideas and bey, products for bringing the world closer are: (a) The Flashback You might have observed that on some. speci ‘occasions like on your birthday, Facebook offers you jy share a video that consists of some of the photos fom your previous history. © This is called “Flashback” which is a video collection of some of your previous uploads that received themos. ‘number of likes and comments. (B) Celebrate Pride * Facebook introduced a feature called “Celebrate Pride” for supporting the supreme coun’s judgment empowering same-sex marriage. '* This feature enables people to decorate thei photos with the seven colors of the rainbow. The success of ep taken by Facebook was unbelievable, ‘* Millions of users changed their profile pictures in just a few hours. ‘The Data Science team of Facebook analyzed the user data and observed that a large number of people were showing their support for the judgment. The success of “Celebrate Pride” was the result ofthis analysis. Linkedin Linkedin is one of the most successful social media platforms that is connecting professionals across the lobe, * It. also uses customer data for providing better services ‘and customized user experience. Linkedin stores a large amount of user data including Several details like their contact information, previous history, interests, activities on different social Petworking sites, ete. in its data warchouse for being ‘wate of the tends and patterns, po Meche PubtctonA SACHIN Sa Ven‘© Using the insights gained from the user data, Linkedin connects individual users with their friends and people related to their areas of interest. It also helps them to make some decisions regarding the business. © According to the different trends, LinkedIn provides various articles and other services that might match user interests. Linkedin also enables users to promote their business to the right people by making use of targeting. Also, while using the customers’ data, LinkedIn makes sure that the data is secure and no scrapping of data takes place from thei Uber ‘# Uber is one of the fastest-growing companies and has sin 66 countries. established its roots across 449 cit ‘over the market with millions of © Itis completely ru users and around I billion Uber ides. The key behind this mesmerizing success story is the tise of Big Data and Data Science for extracting insights and making some smart game-changing. business decisions. Fake Pricing Policy User Accounts 999 9 Boitorcors Fake Rides (rag. 643 (tMu.New Sylabus wes academic year 22-23M7-62) no. (6-9) is and Applications in Dala Scions) © Data Science has helped Uber to deal with issues Uke pricing poficies, better cas, fake user accounts fake rides, ranking and much more. «Uber uses technologies like Hadoop and Spark for collecting data of each and every ride taken on Uber- Daa Scientists at Uber use tis data to understand the customers’ point of view for solving their problems efficiently The Data Science team at Uber performs a detailed analysis of data for various purposes like predicting the demand of rides, deciding the fares, identifying the cites with poor transportation services, et «© For maximizing their profit and the number of rides, Uber uses the idea of surge pricing. «With the help of realtime analysis of data, they always provide rides at times when you are running late but they charge more than around two or three times the usual fares. This is done by the use of surge pricing algorithms, They are now moving towards the use of Machine Learning algorithms for implementing surge pricing to predict the areas of higher demand, + This will help them to divert more and more drivers there, There are many other use cases that show the significance of Data Science at Uber. Spotity ‘© Music plays an important role inthe lives of people of almost all age groups. ‘+ We frequently listen to our favorite songs in our daily routine such as while traveling, in leisure time, etc. to release our stress and relax. Today, there are many ‘music playing applications in the market. + You all might have heard the name “Spotify” at least ‘once and mast probably, you might have even used it, ‘+ So, you must have observed that as soon as we start using it on a regular basis, it starts giving us personalized music recommendations and options to create customized playlists is what people like about it. Tel rechteoPubtcatonsA SACHIN SHAH VentureALS DS-Hl(MU-Som 7-11) (raFig. 6k + At the core of these personalized services lies a large amount of user data that Spotty, actually not only Spotify but most of the music playing applications are using. ‘© Spotify is using this data for optimizing their algorithms, improving user music experience, providing targeted ads, and making some good business strategies. ‘+ In the present scenario, Spotify has around 108 million subscribers and around 124 million free users. + The main goal of Spotfy is to provide such a great ‘experience to every user that will make them continue listening for hours. + To achieve this, they are using many advanced Data Science and Machine Learning techniques to extract, insights from the user data for matching with the music taste oftheir individual customer. ‘+ Some of the features provided by Spotify that shows the use of Data Science are (A) Discover Weekly This is one of the most loved features of Spotify. It provides customized playlists to the users based on their previous activities by using a Machine Learning Algorithm, ‘© This algorithm examines the previous songs played by the user and creates new playlists similar 10 those songs. Along with providing customized playlist, Spotty also analyzes the users’ reactions to individual songs. (MU-New Syllabus wef academic year 22-23)(M7-62) rend and Apple tons in Data Scionce)..Page no. (6-19) © whether the user played any son ey observe 1 on The edt afer a fo sexo wich ah to develop an overall idea of the taste of diferey them (B) Daily Mixes 65 Daily mixes are those playlists that Spotify generates by itself. ists i ngs that are either s “These playlists include the songs tl aa by the users or are of the artists followed by them or maybe something new that they may lke. TMAGENET LARGE SCALE VISUAL RECOGNITION CHALLENGE (ILSVRC) sv) ‘The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) has been running. annvallyfor five years (since 2010) and has become the standard benchmark for large-scale object recognition. ILSVRC follows in the footsteps of the PASCAL VOC challenge established in 2005,which set the precedent for standardized evaluation of recognition algorithms in the form of yearly competitions. ‘As in PASCAL VOC, ILSVRC consists of two components : (1) A publicly available dataset, and @) An annual competition and corresponding workshop. The dataset allows for the development and comparison of categorical object recognition algorithms, and the competition and worksbop Provide a way to track the progress and discuss the Jessons leamed from the most successful and innovative entries each year. ‘The publily released dataset contains a set of manually annotated training images, A Set of test images is also released, with the manual annotations withheld. Partcipans train their algorithms using the training “mages and then automatically annotate the test images. These pred i Predicted annotations are submitted 0 the evaluation server, Dalrechseo ra lications.. SACHIN SHAH Venture‘AL&. DSI (MU-Sem 7.11) + Results of the evaluation are revealed atthe end of the competition period and authors are invited to share insights at the workshop held at the International Conference on Computer Vision (ICCY)or European Conference on Computer Vision (ECCV}in alternate years. ILSVRC annotations fall into one of two categories (1) Image-level annotation of a binary label for the presence or absence of an object class in the image, e.g.” there are cars in this image” but “there are no tigers,” and (2) Objectevel annotation of a tight bounding box ‘and class label around an object instance in the image, eg, “there is a screwdriver centered at position (20,25)with width of 50 pixels and height (0f 30 pixels” © The Image Net dataset is the backbone of ILSVRC. Image Net is an image dataset organized according to the WordNet hierarchy. © Each concept in WordNet, possibly described by ‘multiple words or word phrases, is called a “synonym set” of “synset” '¢ImageNet populates 21,841 synsets of WordNet with an average of 650 manually verified and full resolution images. © As a result, ImageNet contains14,197,122. annotated images organized by the semantichierarchy of WordNet (as of August 2014), ImageNet is larger in scale and diversity than the other smage clasification datasets. ILSVRC uses a subset of ImageNet images for training the algorithms and some of ImageNet’s image collection protocols for annotating additional images for testing the algorithms. 16.6 MULTIPLE CHOICE QUESTIONS. 0.61 Which ofthe followings performed by Data Scents? (@) Define the question (©) Create reproducible code (©) Challenge results (@)_Allofthe mentioned Ans: (@) (Trends and Appicaions in Data Science)...Pago no. (6-11 @.62 Daa science is the process of diverse set of data through, (@)_ Organizing data () Processing data (©) Analysing data (@)_Allofthe above as ‘The applications of Data Science are (@) Healthcare (©) Fraud and Risk Detetion (©) Aitlne Rovte Planning (@) Allofthe above 0.644 Thedata science applications in healthcare are. (@) Data Science for Medical Imaging ()_ Data Science for Genomics (©) Drug Discovery with Data Science (@) Allofihe above Vans. :(@) Which of the following is comect skills for a Data Scientist? (2). Probability and Statistics (©) Machine Learning / Deep Learning (©) Data Wrangling (@ Allof the above Descriptive Questions ass ans. (@) 0.1 Whatis Data Science? @.2 Whatare different applications of Data Science? @.3 Explain applications of Data Science in Healthcare. 0.4 Explain applications of Data Science in Supply ‘Chain Management. Q.5 Explain applications of Data Scienco in Banking and Finance. ©.6 Explain applications of Data Science in Entertainment industy. ©.7 What are roles of Data Sciontist? a8 Using a case study, explain use of data scionce for ‘multimodal applications, (Chapter Ends aga