Hun-Seok Kim

Hun-Seok Kim
University of Michigan | U-M

About

132
Publications
7,803
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,333
Citations

Publications

Publications (132)
Preprint
Massive machine type communication (mMTC) has attracted new coding schemes optimized for reliable short message transmission. In this paper, a novel deep learning-based near-orthogonal superposition (NOS) coding scheme is proposed to transmit short messages in multiple-input multiple-output (MIMO) channels for mMTC applications. In the proposed MIM...
Article
Each fall, millions of monarch butterflies across the U.S. and Canada migrate up to 4,000 km to overwinter in the same cluster of mountaintops in central Mexico. In spring, these migrants mate and remigrate northwards to repopulate their northern breeding territory over 2-4 partially overlapping generations. Because each migrant monarch completes o...
Article
Objective: Brain-machine interfaces (BMIs) have the potential to restore motor function but are currently limited by electrode count and long-term recording stability. These challenges may be solved through the use of free-floating "motes" which wirelessly transmit recorded neural signals, if power consumption can be kept within safe levels when s...
Conference Paper
A new GPS-less, daily localization method is proposed with deep learning sensor fusion that uses daylight intensity and temperature sensor data for Monarch butterfly tracking. Prior methods suffer from the location-independent day length during the equinox, resulting in high localization errors around that date. This work proposes a new Siamese lea...
Article
Intracortical brain-machine interfaces have shown promise for restoring function to people with paralysis, but their translation to portable and implantable devices is hindered by their high power consumption. Recent devices have drastically reduced power consumption compared to standard experimental brain-machine interfaces, but still require wire...
Preprint
In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods. Yet, all existing methods use both the visual and inertial measurements for every pose estimation incurring potential computational redundancy. While visual data processing is much more ex...
Preprint
Full-text available
With the expansion of cloud services, serious concerns about the privacy of users' data arise due to the exposure of the unencrypted data to the server during computation. Various security primitives are under investigation to preserve privacy while evaluating private data, including Fully Homomorphic Encryption (FHE), Private Set Intersection (PSI...
Preprint
Objective Brain-machine interfaces (BMIs) have the potential to restore motor function but are currently limited by electrode count and long-term recording stability. These challenges may be solved through the use of free-floating “motes” which wirelessly transmit recorded neural signals, if power consumption can be kept within safe levels when sca...
Conference Paper
Full-text available
Millimeter-scale embedded sensing systems have unique advantages over larger devices as they are able to capture, analyze, store, and transmit data at the source while being unobtrusive and covert. However, area-constrained systems pose several challenges, including a tight energy budget and peak power, limited data storage, costly wireless communi...
Preprint
Full-text available
Millimeter-scale embedded sensing systems have unique advantages over larger devices as they are able to capture, analyze, store, and transmit data at the source while being unobtrusive and covert. However, area-constrained systems pose several challenges, including a tight energy budget and peak power, limited data storage, costly wireless communi...
Preprint
Massive machine type communication (mMTC) hasattracted new coding schemes optimized for reliable short mes-sage transmission. In this paper, a novel deep learning basednear-orthogonal superposition (NOS) coding scheme is proposedfor reliable transmission of short messages in the additive whiteGaussian noise (AWGN) channel for mMTC applications. Sim...
Preprint
We present a novel adaptive deep joint source-channel coding (JSCC) scheme for wireless image transmission. The proposed scheme supports multiple rates using a single deep neural network (DNN) model and learns to dynamically control the rate based on the channel condition and image contents. Specifically, a policy network is introduced to exploit t...
Preprint
We propose a unified signal compression framework that uses a generative adversarial network (GAN) to compress heterogeneous signals. The compressed signal is represented as a latent vector and fed into a generator network that is trained to produce high quality realistic signals that minimize a target objective function. To efficiently quantize th...
Preprint
We investigate joint source channel coding (JSCC) for wireless image transmission over multipath fading channels. Inspired by recent works on deep learning based JSCC and model-based learning methods, we combine an autoencoder with orthogonal frequency division multiplexing (OFDM) to cope with multipath fading. The proposed encoder and decoder use...
Preprint
We present Versa, an energy-efficient processor with 36 systolic ARM Cortex-M4F cores and a runtime-reconfigurable memory hierarchy. Versa exploits algorithm-specific characteristics in order to optimize bandwidth, access latency, and data reuse. Measured on a set of kernels with diverse data access, control, and synchronization characteristics, re...
Conference Paper
A key challenge for near-infrared (NIR) powered neural recording ICs is to maintain robust operation in the presence of parasitic short circuit current from junction diodes when exposed to light. This is especially so when intentional currents are kept small to reduce power consumption. We present a neural recording IC that is tolerant up to 300 μW...
Article
Arrays of floating neural sensors with high channel count that cover an area of square centimeters and larger would be transformative for neural engineering and brain-machine interfaces. Meeting the power and wireless data communications requirements within the size constraints for each neural sensor has been elusive due to the need to incorporate...
Article
In existing physical layer security (PLS) and key generation protocols, major assumptions, including channel reciprocity, localization, and synchronization between the legitimate parties, are often considered. However, these assumptions are arguable in practice leading to major barriers in building systems based on PLS protocols. To overcome these...
Preprint
Full-text available
We present a deep learning based joint source channel coding (JSCC) scheme for wireless image transmission over multipath fading channels with non-linear signal clipping. The proposed encoder and decoder use convolutional neural networks (CNN) and directly map the source images to complex-valued baseband samples for orthogonal frequency division mu...
Article
This article presents an energy-efficient deep neural network (DNN) accelerator with non-volatile embedded resistive random access memory (RRAM) for mobile machine learning (ML) applications. This DNN accelerator implements weight pruning, non-linear quantization, and Huffman encoding to store all weights on RRAM, enabling single-chip processing fo...
Article
We propose an ultra-low-power (ULP) image signal processor (ISP) that performs on-the-fly in-processing frame compression/decompression and hierarchical event recognition to exploit the temporal and spatial sparsity in an image sequence. This approach reduces energy consumption spent processing and transmitting unimportant image data to achieve a 1...
Article
A stacked voltage domain SRAM is proposed as an effective leakage reduction technique where bit-cell arrays are split into two voltage domains (top and bottom) connecting in series between VDD and GND to generate a sub-threshold retention voltage directly from a nominal supply with no area penalty or efficiency loss compared to the conventional vol...
Article
Full-text available
The large power requirement of current brain–machine interfaces is a major hindrance to their clinical translation. In basic behavioural tasks, the downsampled magnitude of the 300–1,000 Hz band of spiking activity can predict movement similarly to the threshold crossing rate (TCR) at 30 kilo-samples per second. However, the relationship between su...
Article
Full-text available
A sparse matrix-matrix multiplication (SpMM) accelerator with 48 heterogeneous cores and a reconfigurable memory hierarchy is fabricated in 40-nm CMOS. The compute fabric consists of dedicated floating-point multiplication units, and general-purpose Arm Cortex-M0 and Cortex-M4 cores. The on-chip memory reconfigures scratchpad or cache, depending on...
Article
Ultralow-power (ULP) mm-scale Internet-of-Things (IoT) platforms enable newly emerging applications such as pervasive agricultural monitoring and biosensing. Although there is an increasing interest in node-to-node communication as defined in Bluetooth v5.0, prior research in mm-scale wireless systems is mostly limited to asymmetric node-to-gateway...
Preprint
Full-text available
Details of Monarch butterfly migration from the U.S. to Mexico remain a mystery due to lack of a proper localization technology to accurately localize and track butterfly migration. In this paper, we propose a deep learning based butterfly localization algorithm that can estimate a butterfly's daily location by analyzing a light and temperature sen...
Preprint
Full-text available
We propose a unified compression framework that uses generative adversarial networks (GAN) to compress image and speech signals. The compressed signal is represented by a latent vector fed into a generator network which is trained to produce high quality signals that minimize a target objective function. To efficiently quantize the compressed signa...
Article
In this paper, we propose a new approach for tracking a target maneuvering based on the multiple-constant-turns model. Usually, the interactive-multiple-model (IMM) algorithm based on the extended Kalman filter (EKF) is employed for this problem with successful tracking performance. Recently proposed IMM-particle filter (PF) shows outperforming res...
Article
In this paper, we propose a new framework of particle filtering that adopts the minimax strategy. In the approach, we minimize a maximized risk, and the process of the risk maximization is reflected when computing the weights of particles. This scheme results in the significantly reduced variance of the weights of particles that enables the robustn...
Preprint
Full-text available
Internet of Things (IoT) networks for smart sensor nodes in the next generation of smart wireless sensing systems require a distributed security scheme to prevent the passive (eavesdropping) or active (jamming and interference) attacks from untrusted sensor nodes. This paper concerns advancing the security of the IoT system to address their vulnera...
Conference Paper
In traditional sport settings, players with mobility disabilities typically do not have opportunities to engage in physical play with their peers without mobility aids and vice versa. In this paper, we present an interactive floor projection system, iGYM, designed to enable people with mobility disabilities to compete on par with, and in the same p...
Article
This article presents a voice and acoustic activity detector that uses a mixer-based architecture and ultra-low-power neural network (NN)-based classifier. By sequentially scanning 4 kHz of frequency bands and down-converting to below 500 Hz, feature extraction power consumption is reduced by 4x. The NN processor employs computational sprinting, en...
Conference Paper
A Sparse Matrix-Matrix multiplication (SpMM) accelerator with 48 heterogeneous cores and a reconfigurable memory hierarchy is fabricated in 40 nm CMOS. On-chip memories are reconfigured as scratchpad or cache and interconnected with synthesizable coalescing crossbars for efficient memory access in each phase of the algorithm. The 2.0 mm x 2.6 mm ch...
Article
A 40-nm CMOS IEEE 802.11ba low-power wake-up receiver (LP-WUR) is presented. It receives 802.11ba messages generated by an 802.11 orthogonal frequency-division multiplexing (OFDM) transmitter operating at 5.8 GHz. The power consumption of the RF front-end is minimized by removing active RF gain stages and using a third harmonic passive mixer with a...
Conference Paper
Physical play opportunities for people with motor disabilities typically do not include co-located play with peers without disabilities in traditional sport settings. In this paper, we present a prototype of a wheelchair-accessible interactive floor projection system, iGYM, designed to enable people with motor disabilities to compete on par with, a...
Article
Two prototypes of low-power back-channel (BC) Bluetooth low-energy (BLE) wake-up receivers are presented. The receivers scan the BLE advertising channels for modulated advertising channel patterns by hopping the local oscillator (LO) frequency. The BC message is modulated in the sequence of the three advertising channels in each advertising event....
Article
This paper presents a unified 6-D vision processor that enables dense real-time 3-D depth and 3-D motion perception at full-high-definition ( $1920 \times 1080 $ , FHD) resolution. The proposed design implements a neighbor-guided semi-global matching (NG-SGM) algorithm to unify the stereo depth and optical flow matching problem and to reduce compu...
Article
In this paper, we present an all-digital ring oscillator (RO)-based Bluetooth low-energy (BLE) transmitter (TX) for ultra-low-power radios in short range Internet-of-Things (IoT) applications. The power consumption of state-of-the-art BLE TXs has been limited by the relatively power-hungry local oscillator (LO) due to the use of LC oscillators for...
Conference Paper
This paper presents a voice and acoustic activity detector using mixer-based architecture and ultra-low power neural network-based classification. By sequential scanning 4kHz of frequency bands and down-converting to below 500Hz, power consumption of feature extraction is reduced by 4x. A neural network processor employs computational sprinting, en...
Article
Accurate, low-latency, and energy-efficient optical flow estimation is a fundamental kernel function to enable several real-time vision applications on mobile platforms. This paper presents neighbor-guided semi-global matching (NG-fSGM), a new low-complexity optical flow algorithm tailored for low-power mobile applications. NG-fSGM obtains high acc...