Machine Learning - Machine Learning Applications

In this video, we are going to discuss machine learning applications

So, at first, we are considering the classification applications. So, one of the very common application is face recognition

So identify or verify a person from a digital image or a video frame

So the person's face will be detected from a video frame or from one image

Character recognition, that means from the handwritten characters or from the printed character

the characters are to be recognized, spam detection, medical diagnosis, determine which disease

or condition explains a person's symptoms and signs. Next one is the biometrics, that is

authentication using physical and or viereal characteristics, that is face, where I mean the

Irish data set we are having And then signature, etc. In the previous video, we have shown this

Irish data set, there you have seen that there are four attributes are there depending on that

where deciding the flower type. So these are the respective applications which are falling under the classification applications

Now let us go for the regression applications. So here you can find this economics, finance, predict the value of stock

And here our data set is continuous Next one is our epidemiology that is incidence distribution and possible control of diseases

and other factors relating to health. Next one is car or plane navigation

So angle of the steering wheel, accelerations and etc. So there you can use this machine learning models

So temporal trends, that is the weather over time. So, these are the respective applications for the regression applications

Now let us go for the other applications like your manufacturing. So predictive maintenance or condition monitoring

So this machine learning can suggest that which machine is supposed to get maintained right now

So maintenance will be required for which machines for which plant. So condition for the monitoring can also be done using machine learning

So warranty reserve estimations. demand forecasting, process optimization, and telemetics. In case of retail, we're having the predictive inventory planning

So, we can also predict that what will be the required inventory for different products

And then recommendation engines, upsell and cross-channel marketing, market segmentation, and targeting

So in this particular field the machine learning will have the respective applications that what will be the target audience for whom for whom this particular products are to be manufactured for how many pieces what is the quantity of that and then customer ROI and the lifetime value So these are the different aspects

where this machine learning can be applied on this retail. So customer returned on investment

So that is the ROI and the lifetime value. So in case of healthcare and life sense, we're having

the alerts and diagnostics from real-time patient data, disease identification and rigs stratification, patient triage optimization, protective health management, healthcare provider

sentiment ysis. These are the different cases where this particular machine learning

can be applied. So travel and hospitality, aircraft scheduling, and then we are going

for this dynamic pricing, social media, consumer feedback and introduction ysis. So from this consumer feedback, what are the steps are to be taken and whether this

consumer how much consumer feedback is neutral or positive negative and then customer complaint

resolution, traffic patterns and congestion management. So for this traffic pattern and congestion management with this particular machine learning

can be applied we know that traffic condition and congestion is not same throughout the day at different time depending upon the weekdays or depending upon the weekends the corresponding

the congestion pattern is changing. So, judging that one, getting a model trend on that

the respective congestion ysis and the congestion control and management can be done

We're having this risk ytics and regulation for financial services, customer segmentation

cross-selling and upselling, sales and marketing, campaign management, credit, worthiness, evaluation. So, these are different cases where these financial services, the machine learning can be applied

Energy, feed stock and utilities. So, power usage ytics, seismic data processing, carbon emissions and trading, customer-specific

pricing, smart grid management, energy demand. and supply optimization that is also very important so in this way we have discussed

that there are so many applications are there of machine learning in our daily

life and also in our personal life we're enjoying different applications of

machine learning and this tutorial in this particular tutorial we'll be discussing

multiple different algorithms where this algorithm these particular applications can get implemented thanks for watching this video