OpenPOWER Summit 2021

Next-gen Dynamic UAV using Power9 Systems
2021-10-28, 11:15–12:00, RoomA

ABSTRACT: Forest fires are on the increase worldwide. Forest fires are a threat to our environment, they spread quickly and can burn down acres of lush forest if they are not attended to. Forest fires occur due to various reasons. As climate changes continue and temperatures increase by a few degrees every year, the forest fires increase also. Trees that took many years to grow disappear in a very short time because of fires, leaving mountain areas barren, no longer providing protection from rains and mudslides following those rains, no longer providing oxygen clean air and shelter and food for birds and animals.
Usually the forest fires originate very discreetly and rangers gets notified about the fires until it’s too late, this is because fires occurring in dense forests where humans can’t possibly be poses a challenge for the rangers, So to overcome this problem we will use Drones to navigate into the thick part of the forest and integrate Computer Vision into this by utilizing a state-of-the-art Convolutional Neural Network (CNN) to achieve the task. The entire process is treated as classification task where the deep neural network model is responsible for classifying whether its fire or non-fire from the image provided by the camera which is attached to drone we deployed. The training is performed over a dataset of images containing both fire and non-fire images, collected from various sources.

KEYWORDS: Enterprise AI, POWER9, AC922, Deep Learning(DL), Neural Network.

PROPOSED SYSTEM: We will develop the proper neural network architecture for the problem based on the data and the goal set. Using a large set of data obtained from various resources and department of forestry we will train the neural network to provide the most optimal strategy. Using the test data we will test the neural network for its ability to provide the optimal strategy. We will use the forest fires of that year and have the domain experts to verify the optimality of the neural network’s strategy. Proposed models are very complicated, and require intrinsic knowledge about specific programming languages and tools, setting up the system for DL model is difficult. Personal systems lack in computational powers, and restricts the capabilities of DL models. Hence, a need for cloud based DL is required to help a large mass of people. To meet this need, IBM has revealed POWEER9 processor, the AC922 Power systems server, designed for compute heavy artificial intelligence workloads. The AC922 Power server includes a variety of next-generation I/O architectures, including PCle Gen4, CAPI2.0, OpenCAPI and Nvida® NVLINK™, to provide up to 5.6 times as much bandwidth for data-intensive workloads. We use this server to train our model and optimize our performance in an efficient way.


PROPOSED SYSTEM: We will develop the proper neural network architecture for the problem based on the data and the goal set. Using a large set of data obtained from various resources and department of forestry we will train the neural network to provide the most optimal strategy. Using the test data we will test the neural network for its ability to provide the optimal strategy. We will use the forest fires of that year and have the domain experts to verify the optimality of the neural network’s strategy. Proposed models are very complicated, and require intrinsic knowledge about specific programming languages and tools, setting up the system for DL model is difficult. Personal systems lack in computational powers, and restricts the capabilities of DL models. Hence, a need for cloud based DL is required to help a large mass of people. To meet this need, IBM has revealed POWEER9 processor, the AC922 Power systems server, designed for compute heavy artificial intelligence workloads. The AC922 Power server includes a variety of next-generation I/O architectures, including PCle Gen4, CAPI2.0, OpenCAPI and Nvida® NVLINK™, to provide up to 5.6 times as much bandwidth for data-intensive workloads. We use this server to train our model and optimize our performance in an efficient way.

Deepthi Babu is an intern at Object Automation Software Solutions, a startup company based in Chennai, India. Deepthi is familiar with a Hardware of drones and interested in adding new skills to her repertoire. She is proficient in Aerodynamic Stimulations and Gas Dynamics.

I am a senior student, currently doing a Bachelor of Technology degree, with Electrical Engineering as major, in Indian Institute of Technology, Madras, one of the best colleges in India. I hail from Kerala in South India. I am quite fluent in British English. My fields of interest include Machine Learning, VLSI and coding in python and Java.

Working as a Technical Lead in Object Automation Software Solutions Pvt. Ltd, with 10 years of experience in software development and management.