IEEE Kharagpur Section

Talk on "Software-Defined Networking for Edge AI" by Dr. Ayan Mondal, Assistant Professor, IIT Indore We plan to explore how Software-Defined Networking (SDN) can transform Edge AI applications. SDN is capable of centralized control and programmable network infrastructure to facilitate dynamic resource allocation, increased network efficiency, and reduced latency, which are important for real-time AI processing. SDN separates the control from the data plane, thus enabling flexible and agile configurations of networks that handle complex workloads in terms of network configurations. In the NEST research group, we focus on the interaction between SDNs, edge devices, and AI models with a view toward the optimization of data flow and computational tasks within distributed environments. We are working towards improving the performance, scalability, and reliability of SDN-driven Edge AI with real-life examples such as autonomous vehicles, smart cities, and industrial IoT. In this talk, I will focus on how SDN eliminates hindrances to traditional networks, leading to the creation of novel AI-powered solutions and fueling rapid technological growth in industries. Speaker(s): , Dr. Ayan Mondal Virtual: https://events.vtools.ieee.org/m/430706

In this study conducted in Singapore, we aimed to enhance the urban soundscape by creating a soundscape intervention device. With the complex nature of the urban soundscape, it was crucial for the device to have the ability to sense the surrounding sound, select the most appropriate natural sound masker to mask negative noise (such as traffic noise), and adjust dynamically to changes in the acoustic environment.To achieve this, we utilized the power of cloud computing and the Internet of Things (IoT) to provide real-time listening and playback of the augmented sound via an array of ambisonics loudspeakers. The device features an innovative AI-based model to choose the optimal sound masker and determine its gain level, taking the burden offhuman supervision.We also created the Affective Responses to Urban Soundscapes (ARAUS) dataset to serve as a benchmark for evaluating models that predict and analyze soundscape perception. The working prototype of the system was first tested in a gazebo located in a university garden near a busy road, and several more units are being installed in residential areas to study the human response to the improved soundscape. By combining technology and nature, we hope to create a more pleasant and harmonious urban soundscape for all. Speaker(s): Dr. Gan Woon Seng, Virtual: https://events.vtools.ieee.org/m/428870

Alzheimer’s disease (AD) is known as the most common form of dementia and turns out to be one of the fatal neurodegenerative disorders particularly among the older population. More than 50 million people are affected globally because of this ailment and India, at present, experiences the burden of over 6 million AD patient. Because of the increased life expectancy, this type of geriatric diseases increases the financial burden of the society at large. As far as the progress in medical science is concerned, there is no such full proof diagnosis available to cure this disease and hence the only option left is to restrict the growth of its progression. Medical scientists and technologists have put their hands together to solve this biggest challenge of human society. It has come to the observation of the researchers that significant tissue loss from the different parts of the brain primarily becomes responsible for AD. In addition to this, synaptic region between two neurons is also affected because of the accumulation of protein elements. MRI images are predominantly used for the identification and understanding the severity of the disease. A number of well-developed algorithms have been introduced to distinguish a healthy brain from a demented one. Moreover, the severity of the disease can also be judged in the same way by identifying the mild cognitive impairment stage in between healthy and demented brain. These type of approaches seem to be extremely useful in the sense that they can raise appropriate signals to the patient concerned and to the society at large. Speaker(s): Dr. Abhijit Chandra, Virtual: https://events.vtools.ieee.org/m/424967