International Midwest Symposium on Circuits and Systems 

About: International Midwest Symposium on Circuits and Systems is an academic conference. The conference publishes majorly in the area(s): CMOS & Amplifier. Over the lifetime, 3998 publications have been published by the conference receiving 20676 citations.

Gate-variants of Gated Recurrent Unit (GRU) neural networks

Abstract: The paper evaluates three variants of the Gated Recurrent Unit (GRU) in recurrent neural networks (RNNs) by retaining the structure and systematically reducing parameters in the update and reset gates. We evaluate the three variant GRU models on MNIST and IMDB datasets and show that these GRU-RNN variant models perform as well as the original GRU RNN model while reducing the computational expense. In this comparative study, we simply refer to the three variants as, respectively, GRU1, GRU2, and GRU3 RNNs.

A novel CNTFET-based ternary logic gate design

Abstract: This paper presents a novel design of ternary logic inverters using carbon nanotube FETs (CNTFETs). Multiple-valued logic (MVL) circuits have attracted substantial interest due to the capability of increasing information content per unit area. In the past extensive design techniques for MVL circuits (especially ternary logic inverters) have been proposed for implementation in CMOS technology. In CNTFET device, the threshold voltage of the transistor can be controlled by controlling the chirality vector (i.e. the diameter); in this paper this feature is exploited to design ternary logic inverters. New designs are proposed and compared with existing CNTFET-based designs. Extensive simulation results using SPICE demonstrate that power delay product is improved by 300% comparing to the conventional ternary gate design.

NeuFlow: Dataflow vision processing system-on-a-chip

Abstract: This paper presents a bio-inspired vision system-on-a-chip - neuFlow SoC implemented in the IBM 45 nm SOI process. The neuFlow SoC was designed to accelerate neural networks and other complex vision algorithms based on large numbers of convolutions and matrix-to-matrix operations. Post-layout characterization shows that the system delivers up to 320 GOPS with an average power consumption of 0.6 W. The power-efficiency and portability of this system is ideal for embedded vision-based devices, such as driver assistance, and robotic vision.

RFID and GPS integrated navigation system for the visually impaired

Abstract: This paper describes an RFID and GPS integrated navigation system, Smart-Robot (SR) for the visually impaired. The SR uses RFID and GPS based localization while operating indoor and outdoor respectively. The portable terminal unit is an embedded system equipped with an RFID reader, GPS, and analog compass as input devices to obtain location and orientation. The SR can guide the user to a predefined destination, or create a new route on-the-fly for later use. While in navigation mode, the SR reaches the destination by avoiding obstacles using ultrasonic and infrared sensor inputs. The SR also provides user feedback through a speaker, and vibrating motors on the glove. The SR prototype has been successfully implemented and is operational.

Model predictive control for linear parameter varying systems using parameter dependent Lyapunov function

Abstract: In this paper, we propose a method for synthesizing a model predictive control (MPC) law for linear parameter varying (LPV) systems. The proposed MPC algorithm is reduced to the optimization problem with linear matrix inequality (LMI) constraints that are derived by using the parameter dependent Lyapunov function (PDLF). The proposed control law achieves less conservative results as compared with the existing method. A numerical example is provided to illustrate effectiveness of the proposed method.