AI2FUTURE2019 –2 days, 4 keynotes, 20+ moving presentation
10th & 11th of October 2019, Kraš Auditorium, Zagreb, Croatia
AISoft Technology
Mislav Jakšić
Technical Lead
Mislav is the Technical Lead at AISoft Technology. He holds a MSc in Computer Science. He has worked as a consultant, a freelancer and a data analyst on projects big and small.
His achievements include making Apache Kafka more reliable and user friendly as well as being a regular Open Source contributor for more than two years. Mislav’s solutions have been deployed across different sectors including telecommunication and finance.
His interests include Data Engineering, Machine Learning, Finance and Medicine.
Mislav’s
Idea
AISoft Technology is developing innovative framework for building smart real-time monitoring and AI solutions for delivering seamless observability of big data systems, which in the end has a goal of reaching autonomous system operations and maintenance.
The hart of observability in big data systems is a powerful autonomous root cause analysis (aRCA) component. It is known that the problem of RCA does not have a single dominant solution which performs with optimal results over a range of application domains. Instead, a wide range of approaches can be applied and RCA solutions are often customized to a specific domain. We demonstrate how our machine learning approach is applied to fine-tune the parameters of dependency graph which is used in RCA. We also demonstrate early alarming scenarios upon detecting health problems in the core system infrastructure which streams data through Kafka. Within our framework we strive for a better user experience with the big data world, therefore we experiment with new methods of interaction based on virtual reality that utilize AI technologies, such as Leap Motion and natural speech chat bot.
The hart of observability in big data systems is a powerful autonomous root cause analysis (aRCA) component. It is known that the problem of RCA does not have a single dominant solution which performs with optimal results over a range of application domains. Instead, a wide range of approaches can be applied and RCA solutions are often customized to a specific domain. We demonstrate how our machine learning approach is applied to fine-tune the parameters of dependency graph which is used in RCA. We also demonstrate early alarming scenarios upon detecting health problems in the core system infrastructure which streams data through Kafka. Within our framework we strive for a better user experience with the big data world, therefore we experiment with new methods of interaction based on virtual reality that utilize AI technologies, such as Leap Motion and natural speech chat bot.
Meet