Engineering Commons^™

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 30, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 35, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 36, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 37, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 77, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 77 Lidar, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 22, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Wads 3d Object Detection Dataset (Wads-3d) - Sequence 24, Yiming Yang, Jeremy P. Bos

WADS-3D

WADS-3D is a standard KITTI-format dataset designed for analyzing 3D object detection robustness in severe winter weather. Addressing the need for granular analysis of perception failure in snow, the dataset includes 4,100 frames and over 30,000 labeled car instances captured during heavy snowfall and winter-storm conditions. Derived from the large-scale multimodal WADS dataset, WADS-3D enables researchers to move beyond qualitative weather assessments and systematically evaluate how varying heavy snowfall intensities impact a wide range of neural network detectors.

Neurocore: A Gnn Approach To Configurable Ip Core Identification In Fpga Netlists, Dallin Dahl, Keenan Faulkner, James Usevitch, Jeffrey Goeders

Student Works

Netlist reverse engineering enables many applications, including detecting IP theft, verifying CAD tool correctness, and detecting hardware trojans. However, reconstructing high-level information and circuit structure from a flat, nameless netlist is challenging. In this work we focus on the problem of locating known IP cores in an FPGA netlist, which is especially challenging due to the prevalence of highly configurable IP cores. We present Neurocore: a graph neural network-based approach to classifying nodes in a netlist as instances of known IP cores, and present and evaluate different models for different use cases. We have created a large open-source dataset of …

Silent Sabotage: Internal State Triggered Backdoor Attacks On Llm-Powered Robotic Systems, Doniyorkhon Obidov, Shivayogi Akki, Tan Chen, Kaichen Yang

Michigan Tech Publications

The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning. While this paradigm shift accelerates progress, it also introduces novel security risks that remain largely unexplored. Current research into LLM backdoors has focused on attacks triggered by external stimuli, such as specific words, visual objects, or environmental states. These attacks, while potent, overlook a more insidious class of vulnerability where the trigger is internal to the agent’s own operational logic. This paper presents the first comprehensive study of history-based backdoor attacks on LLM-powered robotic systems. …

Biologically-Inspired Multiscale Neuromorphic Architecture, Christian O'Reilly, Ramtin Zand

Publications

This white paper proposes a biologically-inspired multiscale neuromorphic architecture that bridges key gaps between artificial neural networks (ANNs), spiking neural networks (SNNs), and biological neural networks (BNNs). While SNNs offer promising energy efficiency, their broader adoption remains limited by suboptimal performance and the need for novel learning paradigms. To address these challenges, the proposed framework integrates structural and functional principles observed in the brain, including hierarchical organization, sparse and modular connectivity, predictive coding, and diverse neuronal dynamics.

The architecture operates across micro-, meso-, and macro-scales, incorporating neuron-level diversity (e.g., excitatory/inhibitory and principal/support cells), canonical microcircuits (CMCs), and large-scale hierarchical organization. …

A Runtime-Adaptive Transformer Neural Network Accelerator On Fpgas, Ehsan Kabir, Jason D. Bakos, David Andrews, Miaoqing Huang

Electrical Engineering and Computer Science Faculty Publications and Presentations

Transformer neural networks (TNN) excel in natural language processing (NLP), machine translation, and computer vision (CV) without relying on recurrent or convolutional layers. However, they have high computational and memory demands, particularly on resource constrained devices like FPGAs. Moreover, transformer models vary in processing time across applications, requiring custom models with specific parameters. Designing custom accelerators for each model is complex and time-intensive. Some custom accelerators exist with no runtime adaptability, and they often rely on sparse matrices to reduce latency. However, hardware designs become more challenging due to the need for application-specific sparsity patterns. This paper introduces ADAPTOR, a …

Optical Fiber Sensors Using Vernier Effect In Cascaded Fiber Interferometers, Zhouchen Wang

Dissertations

The optical Vernier effect has emerged as a powerful tool to enhance the sensitivity of optical fiber interferometer-based sensors, opening new opportunities for developing highly sensitive fiber sensing systems. Optical fiber interferometric sensors based on the Vernier effect are widely used for various applications due to their ultra-compact size, high sensitivity, immunity to electromagnetic interference, electrical isolation, resistance to harsh environments, flexibility, multiplexing capability, and remote operation. The aim of this doctoral thesis was to gain a deeper fundamental understanding of the Vernier effect in optical fiber structures and to develop and investigate a series of novel Vernier effect optical …

The Role Of Spatial Abilities In Stem Learning And The Influence Of Individual Differences, Styliani Malkogeorgou

Masters

Students’ decisions to pursue education and careers in Science, Technology, Engineering, and Mathematics (STEM) are shaped by an interplay of cognitive, social, and motivational factors. Spatial ability is among the most reliable predictors of STEM success, yet less is known about how it relates to students’ STEM attitudes and aspirations, and whether visuospatial working memory (VSWM) explains this relationship. This study tested the hypotheses that (a) stronger spatial abilities and VSWM would be associated with more positive STEM attitudes and stronger STEM aspirations, and (b) VSWM would mediate the relationship between spatial abilities and STEM attitudes/aspirations, while examining the influence …

Machine Learning In Peak Demand Forecasting: Foundations, Trends, And Insights, Shuang Dai, Fanlin Meng, Hongsheng Dai, Qian Wang, Xizhong Chen, Wenlei Bai, Peizhi Shi, Richard Allmendinger, Yuchen Zhang, Jian Liu

Electrical and Computer Engineering Faculty Research & Creative Works

Peak demand forecasting involves predicting the maximum electricity demand within a specific period, which plays a key role in maintaining the efficiency and stability of power systems. The rapid evolution of power systems, driven by advanced metering infrastructure, local energy applications such as electric vehicles, and the increasing adoption of intermittent renewable energy, has introduced greater randomness and reduced predictability in peak demand. Given the pressing need to address more diverse implementation requirements across different contexts, accurate and reliable peak demand forecasting has become increasingly important. To the best of our knowledge, this study is the first to provide a …

The Impact Of A Structured Training Program On The Depth Perception Of Ab Initio Drone Pilots, John Murray, Steven Richardson, Keith Joiner, Graham Wild

Research outputs 2022 to 2026

Highlights: What are the main findings? First empirical assessment of depth-perception improvement from an official RPAS training program. Demonstrates measurable perceptual-skill gains despite no explicit syllabus objective for depth perception. What are the implications of the main findings? Conducted in authentic operational settings under regulated conditions, ensuring strong external validity. Establishes a validated baseline for future comparative and longitudinal studies on perceptual training effectiveness. Flying remotely requires accurate perception of the environment to ensure safe operation. While remotely piloted aircraft (RPA) bring unique opportunities, they also present new challenges for the pilot, including exercising accurate depth perception. The impact of …

The Risc-V Fpga (Rvfpga) Teaching Package, Daniel Chaver, Sarah Harris, Luis Pinuel, Olof Kindgren, Zubair Kakakhel, Chris Owen, Roy Kravitz, Jose I. Gomez-Perez, Fernando Castro, Katzalin Olcoz, Multiple Additional Authors

Electrical and Computer Engineering Faculty Publications and Presentations

RISC-V is a free and open-standard ISA based on RISC principles, allowing anyone to design, manufacture, and sell RISC-V chips and software. Its flexibility and growing ecosystem have made it popular in research, education, and industry, increasing the need for educational materials. This paper provides an in-depth description of the RVfpga course, which offers a solid introduction to computer architecture using the RISC-V instruction set and FPGA technology. It focuses on providing hands-on experience with real-world RISC-V cores, the VeeR EH1 and EL2 cores, developed by Western Digital and hosted by ChipsAlliance. The course targets students and educators in computing-related …

The Risc-V Fpga (Rvfpga) Teaching Package, Daniel Chaver, Sarah Harris, Luis Pinuel, Olof Kindgren, Zubair Kakakhel, Chris Owen, Jose I. Gomez-Perez, Fernando Castro, Katzalin Olcoz, Julio Villalba-Moreno, Alexander Grinshpun, Freddy Gabbay, Luke Seed, Rui Duarte, Manuel Lopez, Oscar Alonso, Robert Owen

Electrical & Computer Engineering Faculty Research

RISC-V is a free and open-standard ISA based on RISC principles, allowing anyone to design, manufacture, and sell RISC-V chips and software. Its flexibility and growing ecosystem have made it popular in research, education, and industry, increasing the need for educational materials. This paper provides an in-depth description of the RVfpga course, which offers a solid introduction to computer architecture using the RISC-V instruction set and FPGA technology. It focuses on providing hands-on experience with real-world RISC-V cores, the VeeR EH1 and EL2 cores, developed by Western Digital and hosted by ChipsAlliance. The course targets students and educators in computing-related …

Iron-Involved Orr Electrocatalysts Under The Lens Of In-Situ/Operando Mössbauer Spectroscopy, Sumbal Farid, Jun-Hu Wang

Journal of Electrochemistry

Exploring cost-effective and efficient catalysts for oxygen reduction reaction (ORR) poses a significant challenge, especially in the pursuit of alternatives to precious metals like platinum. Significant advancements have driven electrochemists to develop efficient ORR catalysts using abundant materials, particularly iron (Fe)-based, known for their exceptional performance in ORR. While the crucial function of Fe in boosting ORR catalytic activity is recognized, the connection between material attributes and catalytic performance remains enigmatic. Understanding the dynamic processes involved in oxygen electrocatalysis is paramount for designing precious-metals-free ORR electrocatalysts. Mössbauer spectroscopy stands out as a powerful technique for deciphering the structural characteristics of …

The Ntp Anode For Aqueous Sodium Ion Batteries: Recent Advances And Future Perspectives, Ming-Li Wang, Xue-Ying Su, Zheng-Xiang Shan, Shu-Zhe Yang, Heng-Rui Guo, Hao Luo, Dong-Liang Chao

Journal of Electrochemistry

Aqueous sodium-ion batteries (ASIBs) have attracted great attention in aqueous batteries due to their merit of high safety. However, the constrained work potential and insufficient chemical stability of anode materials in aqueous electrolytes hinder the large-scale application of ASIBs. Sodium titanium phosphate, NaTi₂(PO₄)₃ (NTP), is considered one of the most promising anode materials for ASIBs due to its excellent electrochemical performance and tunable structure. Recently, great achievements have been made in the development of NTP, however, a comprehensive review of existing studies is still lacking. This article firstly introduces the basic properties of NTP and …

Development Status And Existing Problems Of Ion-Solvation Membranes For Electrolysis Of Water, Zheng-Yuan Zhou, Yu-Tao Sun, Zheng-Bang Liu, Chuan-Zheng Wang, Yong-Nan Zhou, Xi Luo, Tian-Chi Zhou, Jin-Li Qiao

Journal of Electrochemistry

Ion-solvaing membranes (ISMs) have received extensive attention in recent years as a key component in electrochemical energy conversion and storage devices. This article provides an overview of structural composition, performance advantages, research progress, ion conduction mechanism and existing issues of ISMs, primarily classifying them according to the matrix structure. A detailed analysis of performance enhancement methods, key performance indicators of ISMs and performance influencing factors is also presented. The article contributes to further optimizing the design and application of ion-solvation membranes, providing theoretical support for the development of fields such as hydrogen production through electrolysis of water and electrochemical energy …

Carbon Supported Octahedral Ptni Nanoparticles (Oct-Ptni/C) As A Cathode Catalyst For Proton Exchange Membrane Fuel Cells (Pemfcs) With Improved Activity And Durability, Zi-Wei Feng, Hai-Zhong Chen, Xiao Duan, Ling Tang, Yun-Kun Zhao, Long Huang

Journal of Electrochemistry

Proton exchange membrane fuel cells (PEMFCs) are considered as a promising renewable power source. However, the massive commercial application of PEMFCs has been greatly hindered by their high expense and less-satisfied performance mainly due to the sluggish oxygen reduction reaction (ORR) kinetics even on state-of-the-art Pt catalyst. Octahedral PtNi nanoparticles (oct-PtNi NPs) with excellent ORR activity in a half-cell have been widely studied, while their performance in membrane electrode assembly (MEA) has much less reported. Herein, we investigated the MEA performance using the carbon supported oct-PtNi NPs (oct-PtNi/C) as the cathode catalyst. Under the mild acid washing condition, the surface …

In-Situ Eval: A Modular Framework For Custom And Real-Time Rag Benchmarking, Ritvik Garimella, Kaushik Roy, Chathurangi Shyalika, Amit Sheth

Publications

Retrieval-Augmented Generation (RAG) has become the standard approach for integrating domain knowledge into Large Language Models (LLMs). However, fair comparison of RAG pipelines remains difficult: data preparation is often ad hoc, subsampling methods are opaque, parameters vary across implementations, and evaluation is fragmented. We present In-Situ Eval, a unified and reproducible framework that operationalizes the full RAG pipeline with configurable subsampling strategies and both RAG-specific and generic evaluation metrics. The platform supports two execution modes: an offline Dataset mode for evaluating precomputed outputs, and a live Retrieval mode for benchmarking RAG variants with state-of-the-art LLMs. Users can flexibly select datasets, …

Hybrid Quantum-Classical Optimization Of The Resource Scheduling Problem, Tyler Christeson, Md Habib Ullah, Ali Arabnya, Amin Khodaei, Rui Fan

Electrical and Computer Engineering: Faculty Scholarship

Resource scheduling is critical in many industries, especially in power systems where the Unit Commitment (UC) problem determines the on/off status and output levels of generators under physical and economic constraints. Traditional exact methods, such as Branch-and-Bound, Branch-and-Cut, dynamic programming and mixed-integer linear programming (MILP), remain the backbone of UC solution techniques, but they often rely on linear approximations or exhaustive search, leading to high computational burdens as system size grows. Metaheuristic approaches, such as genetic algorithms, particle swarm optimization, and other evolutionary methods, have been explored to mitigate this complexity; however, they typically lack optimality guarantees, exhibit sensitivity to …

Fuzzy Pi Controller For Frequency Control Of A Diesel-Pv-Battery-Based Islanded Ac Microgrid, M. S. Elborlsy, Ramadan M. Mostafa, Hossam E. Keshta, Mohamed A. Ghalib

Mansoura Engineering Journal

Effective management of modern electrical grids requires intelligent and adaptable control mechanisms to effectively balance power supply and demand, particularly in times of significant disturbances. Microgrids predominantly harness renewable energy sources (RES), which are inherently variable, for electricity generation. However, due to these fluctuations, conventional control systems often struggle to optimize performance under diverse operational conditions. This study addresses the need for improved frequency regulation in isolated AC microgrids (MGs) by proposing a fuzzy PI (FPI) controller capable of dynamically adjusting control strategies to accommodate disturbances such as three-phase faults, sudden changes in load, and variations in solar irradiance. A …

Developing A Collaborative Tool To Foster Communication In Sustainability Research, Nina Hunter, Noëlle-Laetitia Perret, Martin Klepal

Electrical & Electronic Engineering

Climate change necessitates urgent responses based on knowledge produced by teams that transcend disciplinary boundaries, and with members whose work focuses on the generation of knowledge and on the application of knowledge, with some integrating both. Almost a third of Europe’s building stock consists of heritage buildings requiring renovation that is ideally sustainable as part of an energy transition response. The European transdisciplinary CALECHE study team with use-cases in France, Italy, Sweden and Switzerland aims to support decision-making on the sustainable renovation of heritage buildings, via research that employs co-design. However, team members are from various disciplines, with different skillsets …

Proposed Methodology For Correcting Fourier-Transform Infrared Spectroscopy Field-Of-View Scene-Change Artifacts, Kody A. Wilson, Michael L. Dexter, Benjamin F. Akers, Anthony L. Franz

Faculty Publications

Fourier-transform spectrometers are widely used for spectral measurements. Changes in the field of view during measurement introduce oscillations into the measured spectra known as scene-change artifacts. Field-of-view changes also introduce uncertainty about which target the measured spectrum represents. Though scene-change artifacts are often present in dynamic data, their significance is disputed in the current literature. This work presents a theoretical framework and experimental validation for scene-change artifacts. Field-of-view changes introduce variable interferogram offsets, which standard processing techniques assume are constant. The error between the interferogram offset and its estimate is Fourier-transformed, yielding scene-change artifacts, often confused with noise, in the …

Distribution System Reliability Evaluation Considering Protection Coordination Using Petri Nets, Rani Kumari, Bhukya Krishna Naick

Turkish Journal of Electrical Engineering and Computer Sciences

Maintaining reliable and high-quality power delivery becomes increasingly complex with expanding power grids. The lack of protection coordination poses a significant threat, compromising overall system reliability. This research addresses this challenge by proposing a method for coordinating protective devices within the distribution system, specifically during network faults. The proposed approach utilizes a stochastic timed Petri net (STPN) based methodology to model protective device coordination across various fault scenarios. This technique effectively captures the dynamic behavior and interactions of protective equipment, allowing for the anticipation of potential disturbances. This proactive insight facilitates preventative measures to address prewarning situations, thereby preventing cascading …

Cover And Contents

Turkish Journal of Electrical Engineering and Computer Sciences

No abstract provided.

Exploitation Prioritization And Residual Risk Assessment Based On Hybrid Mcdm Model, Zibo Wang, Yaofang Zhang, Sicai Lv, Yingzhou Wang, Hongri Liu, Bailing Wang

Turkish Journal of Electrical Engineering and Computer Sciences

Exploitation is one of the most significant ways to launch attacks using vulnerabilities. The increasing number of vulnerabilities and limited allocation of security resources make it impossible to eliminate all exploitations. Because not every vulnerability can be fixed, it is necessary to rank exploitations and subsequently assess the residual risk, which is defined as the remaining threat potential after each elimination. In this paper, a structured and flexible decision support framework based on a hybrid multicriteria decision-making model is proposed for prioritizing exploitations and assessing residual risk. Metrics are treated as criteria in the model. The hybrid model is developed …