Daniel Andres Salazar Martinez

Mr. Daniel Andres Salazar Martinez


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
31 May 2024 in Sensors
Verified
Journal Article
Open access
PDF file
KOKunle Oguntoye
Kunle Oguntoye
Simon LaflammeSimon Laflamme
Simon Laflamme
Roy SturgillRoy Sturgill
Roy Sturgill
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
DEDavid J. Eisenmann
David J. Eisenmann
AKAnne Kimber
Anne Kimber
Utility as-built plans, which typically provide information about underground utilities’ position and spatial locations, are known to comprise inaccuracies. Over the years, the reliance on utility investigations using an array of sensing equipment has increased in an attempt to resolve utility as-built inaccuracies and mitigate the high rate of accidental underground utility strikes during excavation activities. Adapting data fusion into utility engineering and investigation practices has been shown to be effective in generating information with improved accuracy. However, the complexities in data interpretation and associated prohibitive costs, especially for large-scale projects, are limiting factors. This paper addresses the problem of data interpretation, costs, and large-scale utility mapping with a novel framework that generates probabilistic inferences by fusing data from an automatically generated initial map with as-built data. The probabilistic inferences expose regions of high uncertainty, highlighting them as prime targets for further investigations. The proposed model is a collection of three main processes. First, the automatic initial map creation is a novel contribution supporting rapid utility mapping by subjecting identified utility appurtenances to utility inference rules. The second and third processes encompass the fusion of the created initial utility map with available knowledge from utility as-builts or historical satellite imagery data and then evaluating the uncertainties using confidence value estimators. The proposed framework transcends the point estimation of buried utility locations in previous works by producing a final probabilistic utility map, revealing a confidence level attributed to each segment linking aboveground features. In this approach, the utility infrastructure is rapidly mapped at a low cost, limiting the extent of more detailed utility investigations to low-confidence regions. In resisting obsolescence, another unique advantage of this framework is the dynamic nature of the mapping to automatically update information upon the arrival of new knowledge. This ultimately minimizes the problem of utility as-built accuracies dwindling over time.

9 September 2025
Verified
Conference Paper
Open access
PDF file
YCYang Kang Chua
Yang Kang Chua
ARArman Razmarashooli
Arman Razmarashooli
MMMohammad Mundiwala
Mohammad Mundiwala
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
MOMetrid Okumu
Metrid Okumu
Simon LaflammeSimon Laflamme
Simon Laflamme
High-rate systems, such as hypersonic vehicles and impact mitigation mechanisms, exhibit rapid, nonlinear, and rapid time-varying dynamics. These systems are often subjected to extreme accelerations (e.g., > 100 gn) over very short durations (e.g., < 100 ms), making them highly susceptible to uncertainties, non-stationarities, and external disturbances. In such environments, accurate and reliable state forecasting is essential for real-time decision-making and control. This paper presents a novel framework for high-rate multi-step forecasting that integrates recurrent neural networks (RNNs), topological data analysis (TDA), and conformal prediction for uncertainty quantification. RNNs are used to model temporal dependencies in high-dimensional system dynamics, while TDA-derived features capture the underlying topological structure of the system state. To provide robust and interpretable uncertainty estimates, we employ conformal prediction techniques—particularly inductive and block-based conformal methods— to construct statistically valid prediction intervals. These methods adapt to the non-exchangeable nature of time-series data, enabling coverage guarantees under temporal dependence. The effectiveness of the proposed framework is evaluated on experimental data from the Dynamic Reproduction of Projectiles in Ballistic Environments for Advanced Research (DROPBEAR) testbed. Results demonstrate that the model produces accurate multi-step forecasts with well-calibrated uncertainty bounds, which can be used to support high-rate system monitoring and decision-making.

26 August 2025
Verified
Book Chapter
Closed access
PDF file
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
ARArman Razmarashooli
Arman Razmarashooli
YCYang Kang Chua
Yang Kang Chua
SLSimon Laflamme
Simon Laflamme
CHChao Hu
Chao Hu
JDJacob Dodson
Jacob Dodson

9 September 2025
Verified
Conference Paper
Open access
PDF file
ARArman Razmarashooli
Arman Razmarashooli
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
YCYang Kang Chua
Yang Kang Chua
MOMetrid Okumu
Metrid Okumu
Simon LaflammeSimon Laflamme
Simon Laflamme
PSPaul T. Schrader
Paul T. Schrader
Real-time state estimation is essential for conducting efficient structural health assessment and enabling feedback control strategies in high-rate systems. High-rate systems are dynamic systems that experience extreme acceleration (> 100 gn where gn is the gravitational constant near the earth’s surface) within very short periods (< 1 millisecond), commonly observed in applications such as hypersonic systems and impact mitigation mechanisms. These engineering systems require control and feedback methodologies capable of operating within the sub-millisecond ranges, posing significant challenges for traditional prediction methods due to the underlying nonlinear and nonstationary behavior. This paper introduces and investigates a deep learning algorithm that combines topological data analysis (TDA) features with machine learning to enhance state estimation of high-rate systems. The algorithm consists of an ensemble of recurrent neural networks (RNNs) constructed with a parallel arrangement of long short-term memory cells. The ensemble incorporates predictions from multiple RNNs trained on varying window sizes and delays, allowing the system to capture both shortand long-term data dependencies. A Feedforward Neural Network is employed to predict and analyze the contribution of each RNN’s output to an overall state estimation using TDA-derived features such as the maximum persistence of the first dimensional persistence homology group, H1. The proposed approach is validated using data from the dynamic reproduction of projectiles in ballistic environments for advanced research (DROPBEAR) testbed. Results demonstrate the promise of the algorithm at predicting time series and system states over longer prediction horizons.

23 June 2026 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
ARArman Razmarashooli
Arman Razmarashooli
MOMetrid Okumu
Metrid Okumu
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
YCYang Kang Chua
Yang Kang Chua
Simon LaflammeSimon Laflamme
Simon Laflamme
Erik BlaschErik Blasch
Erik Blasch

29 September 2026 in Measurement Science and Technology
Verified
Journal Article
Open access
DMDaniel Andres Salazar Martinez
Daniel Andres Salazar Martinez
ARArman Razmarashooli
Arman Razmarashooli
YCYang Kang Chua
Yang Kang Chua
APAshim Panthi
Ashim Panthi
MOMetid Okumu
Metid Okumu
Simon LaflammeSimon Laflamme
Simon Laflamme
Topological data analysis (TDA) is a powerful tool for characterizing nonlinear and nonstationary dynamics, but the rapid computational growth of persistent homology filtrations, particularly Vietoris–Rips (VR) constructions, limits its use in high-rate and edge-computing applications. This paper introduces Fast topological data analysis (Fast TDA), a geometry-based framework designed to approximate one-dimensional persistent homology ( H 1 ) from two-dimensional (2D) delay-coordinate embeddings with reduced computational cost. Fast TDA bypasses explicit filtration construction by utilizing a pipeline of least-squares ellipse fitting and k -dimensional tree (KD-tree)-based inscribed circle extraction to achieve efficient geometry-guided feature extraction. The method is formulated for both single-loop regimes and multi-loop point-cloud structures, reconstructing multiple geometric primitives to track evolving topologies. The performance of Fast TDA is evaluated against persistent homology computed with VR and alpha-complex ( α -complex) filtrations across noisy synthetic harmonic signals, experimental high-rate Dynamic Reproduction of Projectiles in Ballistic Environments for Advanced Research testbed data, and the chaotic Lorenz attractor. Results demonstrate that, for single-harmonic regimes, Fast TDA operates in the sub-millisecond range, reducing runtime relative to both persistence-based baselines evaluated in this study while exhibiting strong noise robustness. For multi-frequency and complex multi-loop signals, α -complex persistence provides the lowest runtimes in the tested 2D embeddings, but its extracted descriptors remain more sensitive to noise in the multi-loop cases considered. In contrast, Fast TDA remains substantially faster than VR-based persistence and maintains stronger noise resilience while preserving sub-second execution. Overall, these results position Fast TDA as a scalable geometry-guided surrogate for real-time feature extraction when VR-based persistence is computationally prohibitive, and noise-resilient topology-informed descriptors are desired.