Maximillian Panoff

Dr. Maximillian Panoff

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2021 in SN Computer Science
Verified
Journal Article
Closed access
PDF file
MPMaximillian Panoff
Maximillian Panoff
RDRaj Gautam Dutta
Raj Gautam Dutta
YHYaodan Hu
Yaodan Hu
KYKaichen Yang
Kaichen Yang
YJYier Jin
Yier Jin

3 September 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
RIRoberto Rodriguez III
Roberto Rodriguez III
RPRyan L. Perroy
Ryan L. Perroy
JLJames Leary
James Leary
DJDaniel Jenkins
Daniel Jenkins
MPMaximillian Panoff
Maximillian Panoff
PPPatricia Perez
Patricia Perez
Timely, accurate maps of invasive plant species are critical for making appropriate management decisions to eliminate emerging target populations or contain infestations. High-resolution aerial imagery is routinely used to map, monitor, and detect invasive plant populations. While conventional image interpretation involving human analysts is straightforward, it can require high demands for time and resources to produce useful intelligence. We compared the performance of human analysts with a custom Retinanet-based deep convolutional neural network (DNN) for detecting individual miconia (Miconia calvescens DC) plants, using high-resolution unmanned aerial system (UAS) imagery collected over lowland tropical forests in Hawai’i. Human analysts (n = 38) examined imagery at three linear scrolling speeds (100, 200 and 300 px/s), achieving miconia detection recalls of 74 ± 3%, 60 ± 3%, and 50 ± 3%, respectively. The DNN achieved 83 ± 3% recall and completed the image analysis in 1% of the time of the fastest scrolling speed tested. Human analysts could discriminate large miconia leaf clusters better than isolated individual leaves, while the DNN detection efficacy was independent of leaf cluster size. Optically, the contrast in the red and green color channels and all three (i.e., red, green, and blue) signal to clutter ratios (SCR) were significant factors for human detection, while only the red channel contrast, and the red and green SCRs were significant factors for the DNN. A linear cost analysis estimated the operational use of a DNN to be more cost effective than human photo interpretation when the cumulative search area exceeds a minimum area. For invasive species like miconia, which can stochastically spread propagules across thousands of ha, the DNN provides a more efficient option for detecting incipient, immature miconia across large expanses of forested canopy. Increasing operational capacity for large-scale surveillance with a DNN-based image analysis workflow can provide more rapid comprehension of invasive plant abundance and distribution in forested watersheds and may become strategically vital to containing these invasions.

20 September 2021 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
JHJiaji He
Jiaji He
HMHaocheng Ma
Haocheng Ma
MPMaximillian Panoff
Maximillian Panoff
HWHanning Wang
Hanning Wang
YZYiqiang Zhao
Yiqiang Zhao
YJYier Jin
Yier Jin
Electromagnetic (EM) side-channel analysis is a powerful attack for extracting secret information from cryptographic hardware implementations. Countermeasures have been proposed at the register-transfer level (RTL), layout level, and device level. However, existing EM radiation modeling and side-channel vulnerability mitigation methods do not consider the structural resilience of original designs, nor do they provide fine-grained security enhancements to those vulnerable submodules/components. These universal solutions may introduce unnecessary overheads on the circuit under protection and may not be optimized for individual designs. In this article, we propose a design/synthesis for side-channel security evaluation and optimization framework based on the ${t}$ -test evaluation results derived from RTL hardware implementations. While the framework apply to different side-channel leakage, we focus more on EM side channels. Supported by this framework, different RTL implementations of the same cryptographic algorithm will be evaluated for their side-channel resistance. In vulnerable implementations, submodules with the most significant side-channel leakages will be identified. Security design/synthesis rules will then be applied to these vulnerable submodules for security enhancements against side-channel attacks (SCAs). Experiments, including simulations and FPGA implementations on different AES designs, are performed to validate the effectiveness of the proposed framework as well as the security design/synthesis rules.

23 January 2023 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
HMHaocheng Ma
Haocheng Ma
MPMaximillian Panoff
Maximillian Panoff
JHJiaji He
Jiaji He
YZYiqiang Zhao
Yiqiang Zhao
YJYier Jin
Yier Jin
Electromagnetic (EM) emanation measurement and evaluation is one important testing for modern integrated circuits (ICs). Severe electromagnetic interference may degrade the performance of electronic devices or even cause system crashes. As a result, modern ICs need to follow strict electromagnetic compatibility (EMC) requirements. Moreover, EM emanations offer a covert channel for adversaries to steal secret information from fabricated ICs, causing side channel attacks. Due to the lack of fast and high-accuracy EM simulation tools, existing EM measurements often happen at the post-silicon stage. Any identification of side channel vulnerability or EM incompatibility may lead to high cost and delay the time-to-market. As a result, design-time EM simulation tools with fast simulation speed and high accuracy for pre-silicon designs are urgently needed. To this end, we propose EMSIM, a layout-level EM simulation framework that significantly speeds up the EM simulation process while maintaining high accuracy of the simulated EM emanations. To achieve this goal, we provide the theoretical explanation for the root cause of EM emanations from ICs. Guiding by this, EMSIM leverages techniques of parasitic network reduction and device model approximation to reduce the computation complexities while still ensuring high simulation accuracy. EMSIM further leverages Graphics Processing Unit (GPU) resources to solve equations for EM simulation. The efficiency and effectiveness of EMSIM are validated by showing the consistency between simulation results and physical measurements obtained from fabricated circuit designs.

28 November 2023 in Sensors
Verified
Journal Article
Open access
PDF file
ETErman Nghonda Tchinda
Erman Nghonda Tchinda
MPMaximillian Panoff
Maximillian Panoff
DKDanielle Tchuinkou Kwadjo
Danielle Tchuinkou Kwadjo
Christophe BobdaChristophe Bobda
Christophe Bobda
Image stitching involves combining multiple images of the same scene captured from different viewpoints into a single image with an expanded field of view. While this technique has various applications in computer vision, traditional methods rely on the successive stitching of image pairs taken from multiple cameras. While this approach is effective for organized camera arrays, it can pose challenges for unstructured ones, especially when handling scene overlaps. This paper presents a deep learning-based approach for stitching images from large unstructured camera sets covering complex scenes. Our method processes images concurrently by using the SandFall algorithm to transform data from multiple cameras into a reduced fixed array, thereby minimizing data loss. A customized convolutional neural network then processes these data to produce the final image. By stitching images simultaneously, our method avoids the potential cascading errors seen in sequential pairwise stitching while offering improved time efficiency. In addition, we detail an unsupervised training method for the network utilizing metrics from Generative Adversarial Networks supplemented with supervised learning. Our testing revealed that the proposed approach operates in roughly ∼1/7th the time of many traditional methods on both CPU and GPU platforms, achieving results consistent with established methods.

1 July 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
AHAntonio Hendricks
Antonio Hendricks
MPMaximillian Panoff
Maximillian Panoff
KXKaiwen Xiao
Kaiwen Xiao
ZWZhaoqi Wang
Zhaoqi Wang
SWSHUO WANG
SHUO WANG
Christophe BobdaChristophe Bobda
Christophe Bobda
The JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS) dataset has proven to be a foundational component of modern work on the skill analysis of robotic surgeons. In particular, methods using either the system's kinematics or video data have shown to be able to classify operators into distinct experience levels, and recent approaches have even ventured to recover numeric skill ratings assigned to assessment sessions. Although prior works have achieved positive results in these directions, challenges still remain with classification across all three levels of operator training amounts and objective skill rating regressions. To this end, we perform the first statistical analysis of the dataset itself and compile the results here. We find limited relationships between the amount of experience or training of an operator and their performance in JIGSAWS. Moreover, as operator-side kinematics have well-known relationships with their skill, previous works have used both robot and operator-side kinematics to classify operator skill; we find the first explicit relationships between pure robot-side kinematics and surgical performance. Finally, we analyze the robotic kinematic trends associated with high performance in JIGSAWS tasks and present how they may be used as indicators in human and automated surgeon training.