SAKSHI MUDGAL

• Synthetic Monitoring in Apica, which includes
• Configuring various browser checks.
• Creation and managing the alerts, scenarios reports etc.
• ZebraTester for Application testing.
• Splunk
• Creation of data objects like reports, alerts, dashboards.
• Infrastructure monitoring and data onboardings from different applications.
• Dbconnect onboardings.
• Selenium
• Creation of the automated scripts for browser sessions.
• Improved customer satisfaction by quickly and effectively addressing inquiries and complaints.

• ADM – InterOps
• Handling the day-to-day bug fix and redeployments in Azure Function Apps.
• To provide the uninterrupted service and data to the client.
• Reprocess the missing files and manage the data UpToDate.
• Handle the break and fix in Azure Data factory in production.
• Developing scripts in NodeJs to move date inbetween containers and pipeline.

NORMAL AND ABNORMAL ACTIVITY DETECTION
USING MACHINE LEARNING

With the increase in population, the number of incidents where laws are broken spread like
raging wildfire across the globe. The number of Law keepers pale in comparison to those who
break them. Thus there is a need for an automated detection system. Many institutions have
placed CCTV cameras to monitor people. A person in a developed country with a good
monitoring system get caught on camera as many as 75 times per day. A camera with the bare
minimum specs (704 x 576) resolution with 25 frames per second generates roughly 20 GB data
everyday. The quantity of data generated is too large for manual validation but requires
intelligent classification of objects.
Though there are a number of applications and system to detect these activities but in the run
time there are very few successful cases to detect thesis activities. In this paper a number of
activity detection, feature extraction, segmentation algorithms and the implication of the neural
networks are applied and for the classification different MATLAB codes are used.