�ݺ�ߣshows by User: CarolHargreaves

�ݺ�ߣshows by User: CarolHargreaves / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: CarolHargreaves / Wed, 24 May 2017 10:59:32 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: CarolHargreaves 10 Tips for women to build a career in data science /slideshow/10-tips-for-women-to-build-a-career-in-data-science/76293031 10tipsforwomentobuildacareerindatascience-170524105932
This presentation highlights the 10 things women should focus on when building a career in Data Science. Starting with the business question is key. Talking to the business users, business managers. stakeholders to understand the business question and how the results will impact the different employee roles is most important. Next is using only the relevant data to solve the business problem. After that, we should have good evaluation methods to ensure the analytical solution is sound. And lastly, but not least, show how the analytical results and models impact business in terms of its revenue, profitability, and operational efficiency.]]>
This presentation highlights the 10 things women should focus on when building a career in Data Science. Starting with the business question is key. Talking to the business users, business managers. stakeholders to understand the business question and how the results will impact the different employee roles is most important. Next is using only the relevant data to solve the business problem. After that, we should have good evaluation methods to ensure the analytical solution is sound. And lastly, but not least, show how the analytical results and models impact business in terms of its revenue, profitability, and operational efficiency.]]> Wed, 24 May 2017 10:59:32 GMT /slideshow/10-tips-for-women-to-build-a-career-in-data-science/76293031 CarolHargreaves@slideshare.net(CarolHargreaves) 10 Tips for women to build a career in data science CarolHargreaves This presentation highlights the 10 things women should focus on when building a career in Data Science. Starting with the business question is key. Talking to the business users, business managers. stakeholders to understand the business question and how the results will impact the different employee roles is most important. Next is using only the relevant data to solve the business problem. After that, we should have good evaluation methods to ensure the analytical solution is sound. And lastly, but not least, show how the analytical results and models impact business in terms of its revenue, profitability, and operational efficiency. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/10tipsforwomentobuildacareerindatascience-170524105932-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation highlights the 10 things women should focus on when building a career in Data Science. Starting with the business question is key. Talking to the business users, business managers. stakeholders to understand the business question and how the results will impact the different employee roles is most important. Next is using only the relevant data to solve the business problem. After that, we should have good evaluation methods to ensure the analytical solution is sound. And lastly, but not least, show how the analytical results and models impact business in terms of its revenue, profitability, and operational efficiency.

10 Tips for women to build a career in data science from Carol Hargreaves

]]> 202 6 https://cdn.slidesharecdn.com/ss_thumbnails/10tipsforwomentobuildacareerindatascience-170524105932-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Ship Emission Rating Index (SERI) /slideshow/ship-emission-rating-index-seri-62604906/62604906 shipemissionratingindexseri-160601072725
Carbon emissions are depleting the ozone layer. Globally, we need to half the carbon emissions by 2050. The Ship Emission Rating Index (SERI) helps ships to compare their emission rating with similar ships. SERI also helps to motivate ship owners to be the best they can be by striving to be on the leaderboard for being in the top class for environment friendly rated ships, demonstrated through their Ship Emission Rating. SERI will motivate ships to reduce their emissions as no ship would like to be at the bottom of the ratings. Ships with good Emission Ratings will have an advantage when seeking bank loans and insurance cover as banks and insurance companies will prefer to insure and lend environmental friendly ships that are highly rated and ranked. ]]>
Carbon emissions are depleting the ozone layer. Globally, we need to half the carbon emissions by 2050. The Ship Emission Rating Index (SERI) helps ships to compare their emission rating with similar ships. SERI also helps to motivate ship owners to be the best they can be by striving to be on the leaderboard for being in the top class for environment friendly rated ships, demonstrated through their Ship Emission Rating. SERI will motivate ships to reduce their emissions as no ship would like to be at the bottom of the ratings. Ships with good Emission Ratings will have an advantage when seeking bank loans and insurance cover as banks and insurance companies will prefer to insure and lend environmental friendly ships that are highly rated and ranked. ]]> Wed, 01 Jun 2016 07:27:25 GMT /slideshow/ship-emission-rating-index-seri-62604906/62604906 CarolHargreaves@slideshare.net(CarolHargreaves) Ship Emission Rating Index (SERI) CarolHargreaves Carbon emissions are depleting the ozone layer. Globally, we need to half the carbon emissions by 2050. The Ship Emission Rating Index (SERI) helps ships to compare their emission rating with similar ships. SERI also helps to motivate ship owners to be the best they can be by striving to be on the leaderboard for being in the top class for environment friendly rated ships, demonstrated through their Ship Emission Rating. SERI will motivate ships to reduce their emissions as no ship would like to be at the bottom of the ratings. Ships with good Emission Ratings will have an advantage when seeking bank loans and insurance cover as banks and insurance companies will prefer to insure and lend environmental friendly ships that are highly rated and ranked. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/shipemissionratingindexseri-160601072725-thumbnail.jpg?width=120&height=120&fit=bounds" /> Carbon emissions are depleting the ozone layer. Globally, we need to half the carbon emissions by 2050. The Ship Emission Rating Index (SERI) helps ships to compare their emission rating with similar ships. SERI also helps to motivate ship owners to be the best they can be by striving to be on the leaderboard for being in the top class for environment friendly rated ships, demonstrated through their Ship Emission Rating. SERI will motivate ships to reduce their emissions as no ship would like to be at the bottom of the ratings. Ships with good Emission Ratings will have an advantage when seeking bank loans and insurance cover as banks and insurance companies will prefer to insure and lend environmental friendly ships that are highly rated and ranked.

Ship Emission Rating Index (SERI) from Carol Hargreaves

]]> 909 5 https://cdn.slidesharecdn.com/ss_thumbnails/shipemissionratingindexseri-160601072725-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Anomaly Detection /slideshow/anomaly-detection-60638948/60638948 anomalydetection-160408042328
This presentation will present topics such as "What is Anomaly Detection? What are the different types of Data that may be used? What are the popular techniques may be used to identify anomalies. What are the best practices in anomaly detection? What is the Value of Anomaly Detection?]]>
This presentation will present topics such as "What is Anomaly Detection? What are the different types of Data that may be used? What are the popular techniques may be used to identify anomalies. What are the best practices in anomaly detection? What is the Value of Anomaly Detection?]]> Fri, 08 Apr 2016 04:23:28 GMT /slideshow/anomaly-detection-60638948/60638948 CarolHargreaves@slideshare.net(CarolHargreaves) Anomaly Detection CarolHargreaves This presentation will present topics such as "What is Anomaly Detection? What are the different types of Data that may be used? What are the popular techniques may be used to identify anomalies. What are the best practices in anomaly detection? What is the Value of Anomaly Detection? <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetection-160408042328-thumbnail.jpg?width=120&height=120&fit=bounds" /> This presentation will present topics such as "What is Anomaly Detection? What are the different types of Data that may be used? What are the popular techniques may be used to identify anomalies. What are the best practices in anomaly detection? What is the Value of Anomaly Detection?

Anomaly Detection from Carol Hargreaves

]]> 4431 9 https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetection-160408042328-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Green Ship Research Dr Carol Hargreaves /slideshow/green-ship-research-dr-carol-hargreaves/53587270 greenshipresearch23092015-151006085655-lva1-app6891
Globally we need to halve the carbon emissions by 2050. Through the release of Greenhouse Gases (GHG), the industry also contributes significantly to climate change.Several reulations has been put in place to help recude CO2 emissions but the shipping industry is still faced by some challenges. Big Data is helping to cut fuel bills and CO2 emissions. Objective is to build a ship rating tool for ranking and rating ships on their emissions.]]>
Globally we need to halve the carbon emissions by 2050. Through the release of Greenhouse Gases (GHG), the industry also contributes significantly to climate change.Several reulations has been put in place to help recude CO2 emissions but the shipping industry is still faced by some challenges. Big Data is helping to cut fuel bills and CO2 emissions. Objective is to build a ship rating tool for ranking and rating ships on their emissions.]]> Tue, 06 Oct 2015 08:56:55 GMT /slideshow/green-ship-research-dr-carol-hargreaves/53587270 CarolHargreaves@slideshare.net(CarolHargreaves) Green Ship Research Dr Carol Hargreaves CarolHargreaves Globally we need to halve the carbon emissions by 2050. Through the release of Greenhouse Gases (GHG), the industry also contributes significantly to climate change.Several reulations has been put in place to help recude CO2 emissions but the shipping industry is still faced by some challenges. Big Data is helping to cut fuel bills and CO2 emissions. Objective is to build a ship rating tool for ranking and rating ships on their emissions. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/greenshipresearch23092015-151006085655-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds" /> Globally we need to halve the carbon emissions by 2050. Through the release of Greenhouse Gases (GHG), the industry also contributes significantly to climate change.Several reulations has been put in place to help recude CO2 emissions but the shipping industry is still faced by some challenges. Big Data is helping to cut fuel bills and CO2 emissions. Objective is to build a ship rating tool for ranking and rating ships on their emissions.

Green Ship Research Dr Carol Hargreaves from Carol Hargreaves

]]> 755 12 https://cdn.slidesharecdn.com/ss_thumbnails/greenshipresearch23092015-151006085655-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Recommender Systems Dr Carol Hargreaves /CarolHargreaves/recommender-systems-dr-carol-hargreaves recommendersystemsdrcarolhargreaves-151006084644-lva1-app6892
Recommender systems are viewed as prediction problems in which the user profiles and their rated target items reflect the degree of the user's preference for that item. Recommender Systems should account for temporal effects, reflecting the dynamic, time-drifting nature of user-item interactions. Averages should be avoided as they lack context. Good recommendations will take context and product associations into account when making recommendations]]>
Recommender systems are viewed as prediction problems in which the user profiles and their rated target items reflect the degree of the user's preference for that item. Recommender Systems should account for temporal effects, reflecting the dynamic, time-drifting nature of user-item interactions. Averages should be avoided as they lack context. Good recommendations will take context and product associations into account when making recommendations]]> Tue, 06 Oct 2015 08:46:44 GMT /CarolHargreaves/recommender-systems-dr-carol-hargreaves CarolHargreaves@slideshare.net(CarolHargreaves) Recommender Systems Dr Carol Hargreaves CarolHargreaves Recommender systems are viewed as prediction problems in which the user profiles and their rated target items reflect the degree of the user's preference for that item. Recommender Systems should account for temporal effects, reflecting the dynamic, time-drifting nature of user-item interactions. Averages should be avoided as they lack context. Good recommendations will take context and product associations into account when making recommendations <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/recommendersystemsdrcarolhargreaves-151006084644-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds" /> Recommender systems are viewed as prediction problems in which the user profiles and their rated target items reflect the degree of the user's preference for that item. Recommender Systems should account for temporal effects, reflecting the dynamic, time-drifting nature of user-item interactions. Averages should be avoided as they lack context. Good recommendations will take context and product associations into account when making recommendations

Recommender Systems Dr Carol Hargreaves from Carol Hargreaves

]]> 306 8 https://cdn.slidesharecdn.com/ss_thumbnails/recommendersystemsdrcarolhargreaves-151006084644-lva1-app6892-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Diabetes Risk Reduction App with mHealth Gamification /slideshow/diabetes-risk-reduction-app-with-mhealth-gamification/38485531 diabetesriskreductionappwithgamificationbymhealthgamification-140829064126-phpapp02
The key challenges we found were that, the more overweight children are, the greater the risk of Diabetes. Nearly 1 in every 3 American adults is obese & almost 2/3 are overweight. More, seriously, Obesity is continuing on the rise. Recently, the US Surgeon General has declared Obesity in children & adolescents in the US – an EPIDEMIC. Adolescents are being diagnosed with type 2 Diabetes at an alarming rate! Some of the reasons for this trend is a lack of physical activity & increased consumption of fast foods that are high in calories & fat. We hope that this Diabetes Risk Reduction App with mHealth Gamification will motivate people who are at high risk of obtaining Diabetes to use our App regularly, and thereby exercising more often and always eating healthy.]]>
The key challenges we found were that, the more overweight children are, the greater the risk of Diabetes. Nearly 1 in every 3 American adults is obese & almost 2/3 are overweight. More, seriously, Obesity is continuing on the rise. Recently, the US Surgeon General has declared Obesity in children & adolescents in the US – an EPIDEMIC. Adolescents are being diagnosed with type 2 Diabetes at an alarming rate! Some of the reasons for this trend is a lack of physical activity & increased consumption of fast foods that are high in calories & fat. We hope that this Diabetes Risk Reduction App with mHealth Gamification will motivate people who are at high risk of obtaining Diabetes to use our App regularly, and thereby exercising more often and always eating healthy.]]> Fri, 29 Aug 2014 06:41:26 GMT /slideshow/diabetes-risk-reduction-app-with-mhealth-gamification/38485531 CarolHargreaves@slideshare.net(CarolHargreaves) Diabetes Risk Reduction App with mHealth Gamification CarolHargreaves The key challenges we found were that, the more overweight children are, the greater the risk of Diabetes. Nearly 1 in every 3 American adults is obese & almost 2/3 are overweight. More, seriously, Obesity is continuing on the rise. Recently, the US Surgeon General has declared Obesity in children & adolescents in the US – an EPIDEMIC. Adolescents are being diagnosed with type 2 Diabetes at an alarming rate! Some of the reasons for this trend is a lack of physical activity & increased consumption of fast foods that are high in calories & fat. We hope that this Diabetes Risk Reduction App with mHealth Gamification will motivate people who are at high risk of obtaining Diabetes to use our App regularly, and thereby exercising more often and always eating healthy. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/diabetesriskreductionappwithgamificationbymhealthgamification-140829064126-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds" /> The key challenges we found were that, the more overweight children are, the greater the risk of Diabetes. Nearly 1 in every 3 American adults is obese & almost 2/3 are overweight. More, seriously, Obesity is continuing on the rise. Recently, the US Surgeon General has declared Obesity in children & adolescents in the US – an EPIDEMIC. Adolescents are being diagnosed with type 2 Diabetes at an alarming rate! Some of the reasons for this trend is a lack of physical activity & increased consumption of fast foods that are high in calories & fat. We hope that this Diabetes Risk Reduction App with mHealth Gamification will motivate people who are at high risk of obtaining Diabetes to use our App regularly, and thereby exercising more often and always eating healthy.

Diabetes Risk Reduction App with mHealth Gamification from Carol Hargreaves

]]> 780 4 https://cdn.slidesharecdn.com/ss_thumbnails/diabetesriskreductionappwithgamificationbymhealthgamification-140829064126-phpapp02-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Carol anne hargreaves profile /slideshow/carol-anne-hargreaves-profile/31256772 carolannehargreavesprofile-140216010634-phpapp01
Carol Anne Hargreaves Profile : Who am I?]]>
Carol Anne Hargreaves Profile : Who am I?]]> Sun, 16 Feb 2014 01:06:34 GMT /slideshow/carol-anne-hargreaves-profile/31256772 CarolHargreaves@slideshare.net(CarolHargreaves) Carol anne hargreaves profile CarolHargreaves Carol Anne Hargreaves Profile : Who am I? <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/carolannehargreavesprofile-140216010634-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Carol Anne Hargreaves Profile : Who am I?

Carol anne hargreaves profile from Carol Hargreaves

]]> 1330 3 https://cdn.slidesharecdn.com/ss_thumbnails/carolannehargreavesprofile-140216010634-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Statistics applied to the interdisciplinary areas of marketing /slideshow/statistics-applied-to-the-interdisciplinary-areas-of-marketing/31256005 statisticsappliedtotheinterdisciplinaryareasofmarketing-140215234411-phpapp01
Optimising price and marketing mix. Concept of learning. When an account/product has too little sales data, bayesian shrinkage allows us to borrow information from other accounts. Deals with outliers, by shrinking estimates towards each other. Allows one hierarchical model instead of multiple models. More robust, stable estimates with significant regional and account variation in estimates that cannot be done in a classical linear model. Provides price elasticity measure that shows the impact of price changes on volume ]]>
Optimising price and marketing mix. Concept of learning. When an account/product has too little sales data, bayesian shrinkage allows us to borrow information from other accounts. Deals with outliers, by shrinking estimates towards each other. Allows one hierarchical model instead of multiple models. More robust, stable estimates with significant regional and account variation in estimates that cannot be done in a classical linear model. Provides price elasticity measure that shows the impact of price changes on volume ]]> Sat, 15 Feb 2014 23:44:11 GMT /slideshow/statistics-applied-to-the-interdisciplinary-areas-of-marketing/31256005 CarolHargreaves@slideshare.net(CarolHargreaves) Statistics applied to the interdisciplinary areas of marketing CarolHargreaves Optimising price and marketing mix. Concept of learning. When an account/product has too little sales data, bayesian shrinkage allows us to borrow information from other accounts. Deals with outliers, by shrinking estimates towards each other. Allows one hierarchical model instead of multiple models. More robust, stable estimates with significant regional and account variation in estimates that cannot be done in a classical linear model. Provides price elasticity measure that shows the impact of price changes on volume <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/statisticsappliedtotheinterdisciplinaryareasofmarketing-140215234411-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Optimising price and marketing mix. Concept of learning. When an account/product has too little sales data, bayesian shrinkage allows us to borrow information from other accounts. Deals with outliers, by shrinking estimates towards each other. Allows one hierarchical model instead of multiple models. More robust, stable estimates with significant regional and account variation in estimates that cannot be done in a classical linear model. Provides price elasticity measure that shows the impact of price changes on volume

Statistics applied to the interdisciplinary areas of marketing from Carol Hargreaves

]]> 626 4 https://cdn.slidesharecdn.com/ss_thumbnails/statisticsappliedtotheinterdisciplinaryareasofmarketing-140215234411-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Relating outcomes of a chronic disease to individual patient characteristics /slideshow/relating-outcomes-of-a-chronic-disease-to-individual-patient-characteristics/31255882 relatingoutcomesofachronicdiseasetoindividualpatientcharacteristics-140215233018-phpapp01
Several biostatistical techniques are available for relating the outcome of a chronic disease to individual patient characteristics.The stochastic process approach updates the information available at the time of initial presentation and makes it responsive to the individual clinical course.At any point in a patient’s history the most recently occupied state contains all of the information which is relevant to the patient’s future course. This is called the Markov Property.Mantel-Haenszel (MH) procedures proved quite useful, in estimating relative risks of death for the various states by using the strata defined by the time intervals. ]]>
Several biostatistical techniques are available for relating the outcome of a chronic disease to individual patient characteristics.The stochastic process approach updates the information available at the time of initial presentation and makes it responsive to the individual clinical course.At any point in a patient’s history the most recently occupied state contains all of the information which is relevant to the patient’s future course. This is called the Markov Property.Mantel-Haenszel (MH) procedures proved quite useful, in estimating relative risks of death for the various states by using the strata defined by the time intervals. ]]> Sat, 15 Feb 2014 23:30:18 GMT /slideshow/relating-outcomes-of-a-chronic-disease-to-individual-patient-characteristics/31255882 CarolHargreaves@slideshare.net(CarolHargreaves) Relating outcomes of a chronic disease to individual patient characteristics CarolHargreaves Several biostatistical techniques are available for relating the outcome of a chronic disease to individual patient characteristics.The stochastic process approach updates the information available at the time of initial presentation and makes it responsive to the individual clinical course.At any point in a patient’s history the most recently occupied state contains all of the information which is relevant to the patient’s future course. This is called the Markov Property.Mantel-Haenszel (MH) procedures proved quite useful, in estimating relative risks of death for the various states by using the strata defined by the time intervals. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/relatingoutcomesofachronicdiseasetoindividualpatientcharacteristics-140215233018-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds" /> Several biostatistical techniques are available for relating the outcome of a chronic disease to individual patient characteristics.The stochastic process approach updates the information available at the time of initial presentation and makes it responsive to the individual clinical course.At any point in a patient’s history the most recently occupied state contains all of the information which is relevant to the patient’s future course. This is called the Markov Property.Mantel-Haenszel (MH) procedures proved quite useful, in estimating relative risks of death for the various states by using the strata defined by the time intervals.

Relating outcomes of a chronic disease to individual patient characteristics from Carol Hargreaves

]]> 304 2 https://cdn.slidesharecdn.com/ss_thumbnails/relatingoutcomesofachronicdiseasetoindividualpatientcharacteristics-140215233018-phpapp01-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-CarolHargreaves-48x48.jpg?cb=1521637578 Head of Business Analytics Practice at the Institute of Systems Science at the National University of Singapore (NUS). Business Analytics Lecturer & Business Analytics Consultant with many years experience in Statistics, Analytics, SPSS, SAS, Data Mining, Problem solving and data analysis. In the data analytics area, strong industry experience in Customer Analytics, Business Analytics, Predictive Modelling, Churn Modelling, Acquisition Modeling, Response Modelling, and Risk Modelling. My goal is to contribute in educating corporates on how to apply business analytics and use statistical techniques in their companies and deliver increased Return on Investments (ROI) through teaching and... http://www.iss.nus.edu.sg https://cdn.slidesharecdn.com/ss_thumbnails/10tipsforwomentobuildacareerindatascience-170524105932-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/10-tips-for-women-to-build-a-career-in-data-science/76293031 10 Tips for women to b... https://cdn.slidesharecdn.com/ss_thumbnails/shipemissionratingindexseri-160601072725-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/ship-emission-rating-index-seri-62604906/62604906 Ship Emission Rating I... https://cdn.slidesharecdn.com/ss_thumbnails/anomalydetection-160408042328-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/anomaly-detection-60638948/60638948 Anomaly Detection