Region 1

[] This presentation describes open-source software and guides we have assembled into a digital audio effects development kit, and our efforts using these resources in our annual FX Hackathon event held at WPI. Audio processes and their uses in musical contexts is a challenging subject area. We have addressed this difficulty by creating an effect development kit including a software-based tool to facilitate rapid effect prototyping and guides for assembling hardware around a microcontroller housed in a guitar pedal stompbox-sized enclosure. With these resources, students need only focus on understanding the specific audio process they wish to implement into an effect and then use these resources to realize the effect in a standalone device. What is the Electric Guitar Innovation Lab (EGIL) @ WPI? Through the Electric Guitar Innovation Lab, WPI students and faculty work together in a variety of interdisciplinary and open-ended projects to develop new innovations related to the electric guitar, including the modification to instruments and components, stompboxes and other effects processors, amplifiers and speaker components, and related inventions and adaptations. We routinely reverse-engineer, 3D model ,3D scan, program and adapt existing parts and tools, and then create tool-pathing operations, fabricate parts, and perform real-world and software-based simulations. Speaker(s): V.J., Matt, Ryan Room: 190, Bldg: Engineering Research Center, Brown University, 345 Brook Street, Providence, Rhode Island, United States, 02912, Virtual: https://events.vtools.ieee.org/m/441044

Exploring the Potential of Deep-Learning and Machine-Learning in Dual-Band Antenna Design Keywords Antennas, Dual Band, Computational Modeling, Mathematical Models, Antenna Arrays, Training, Accuracy, Machine Learning, Deep Learning, Antenna Design, Dual Band Antennas, AI Antenna, Deep Learning, Antenna Design, Dual Band Antenna, Dual Band Antenna Design, Neural Network, Support Vector Machine, Design Process, Machine Learning Models, Machine Learning Techniques, Design Parameters, Internet Of Things, Reflection Coefficient, Operating Frequency, Regression Problem, Residual Network, Wireless Communication Systems, Internet Of Things Applications, Modern Communication, Antenna Performance, Residual Neural Network, Electromagnetic Simulation, Multiple Outputs, Neurons In Layer, Hidden Layer, Internet Of Things Devices, Res Net Model, Horizontal Stripes, Vertical Stripes, Simulation Technology, Traditional Antenna Abstract This article presents an in-depth exploration of machine learning (ML) and deep learning (DL) for the optimization and design of dual-band antennas in Internet of Things (IoT) applications. Dual-band antennas, which are essential for the functionality of current and forthcoming flexible wireless communication systems, face increasing complexity and design challenges as demands and requirements for IoT-connected devices become more challenging. The study demonstrates how artificial intelligence (AI) can streamline the antenna design process, enabling customization for specific frequency ranges or performance characteristics without exhaustive manual tuning. By utilizing ML and DL tools, this research not only enhances the efficiency of the design process but also achieves optimal antenna performance with significant time savings. The integration of AI in antenna design marks a notable advancement over traditional methods, offering a systematic approach to achieving dual-band functionality tailored to modern communication needs. We approached the antenna design as a regression problem, using the reflection coefficient, operating frequency, bandwidth, and voltage standing wave ratio as input parameters. The ML and DL models then are used to predict the corresponding design parameters for the antenna by using 1,000 samples, from which 700 are allocated for training and 300 for testing. This effectiveness of this approach is demonstrated through the successful application of various ML techniques, including Fine Gaussian Support Vector Machines (SVM), as well as Regressor and Residual Neural Networks (ResNet) with different activation functions, to optimize the design of a dual-band T-shaped monopole antenna, thereby substantiating AI's transformative potential in antenna design. Authors: RIDA GADHAFI 1 (Senior Member, IEEE), ABIGAIL COPIACO 1 (Member, IEEE), YASSINE HIMEUR 1 (Senior Member, IEEE), KIYAN AFSARI 2 (Member, IEEE), HUSAMELDIN MUKHTAR 1 (Senior Member, IEEE), KHALIDA GHANEM 3,4, AND WATHIQ MANSOOR 1 (Senior Member, IEEE) Agenda: 7:30 Tea and Coffee 7:45 Paper discussion 8:30 End 6 Flagstone Dr, Hudson, New Hampshire, United States, 03051, Virtual: https://events.vtools.ieee.org/m/442040