Fernando Martinez Lopez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Fernando Martinez Lopez has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Yijun Zhao
Computer and Information Sciences Department, Fordham University, New York, USA
4 shared publications - Elizabeth S. Thrall
Fordham University
2 shared publications - Joshua Schrier
Department of Chemistry and Biochemistry, Fordham University, 441 East Fordham Road, The Bronx, New York 10458, United States
2 shared publications Mohamed Rahouti
2 shared publicationsAlexander Borelli
Computer and Information Sciences Department, Fordham University, New York, USA
1 shared publicationAli Alfatemi
Fordham University,Computer Information Science Dept.,NY,USA,10023
1 shared publication
Latest Publications
- 1 January 2027
- Published by American Society of Civil Engineers (ASCE) in Journal of Civil Engineering Education
- Vol. 153 (1)
A Machine-Learning Approach to Examine Personality, Adjustment, and Engineering Identity among College Engineering Students
This study examined the relationship between personality, college adjustment, and student outcomes among undergraduate engineering students. Specifically, we investigated whether general personality traits based on the Big Five model, vocational personality types, and students’ adjustment to college predicted academic achievement and engineering identity. College adjustment was measured using the Student Adaptation to College Questionnaire (SACQ). Engineering identity was measured using engineering identity measure (EIM).Academic achievement was measured by cumulative grade point average (CGPA). We recruited 115 college students from diverse ethnic and cultural backgrounds, all of whom were enrolled in the civil engineering program at a private university in a metropolitan area in the US. Participants were classified into either above-average or below-average groups based on their CGPA and EIM scores. Five machine learning models were trained and evaluated using nested 10-fold cross-validation. Feature importance was examined using Shapley Additive exPlanations (SHAP) to identify the variables that contributed most strongly to academic achievement and engineering identity. The findings suggest that personality characteristics and college adjustment play important roles in college engineering students’ academic performance and engineering identity. Academic adjustment emerged as the strongest positive predictor of both CGPA and engineering identity, whereas neuroticism and extraversion were associated with lower academic achievement. Future researchers should examine factors affecting academic achievement, engineering identity, and adjustment to college among students from diverse backgrounds.
- 1 January 2027
- Published by American Society of Civil Engineers (ASCE) in Journal of Civil Engineering Education
- Vol. 153 (1)
A Machine-Learning Approach to Examine Personality, Adjustment, and Engineering Identity among College Engineering Students
This study examined the relationship between personality, college adjustment, and student outcomes among undergraduate engineering students. Specifically, we investigated whether general personality traits based on the Big Five model, vocational personality types, and students’ adjustment to college predicted academic achievement and engineering identity. College adjustment was measured using the Student Adaptation to College Questionnaire (SACQ). Engineering identity was measured using engineering identity measure (EIM).Academic achievement was measured by cumulative grade point average (CGPA). We recruited 115 college students from diverse ethnic and cultural backgrounds, all of whom were enrolled in the civil engineering program at a private university in a metropolitan area in the US. Participants were classified into either above-average or below-average groups based on their CGPA and EIM scores. Five machine learning models were trained and evaluated using nested 10-fold cross-validation. Feature importance was examined using Shapley Additive exPlanations (SHAP) to identify the variables that contributed most strongly to academic achievement and engineering identity. The findings suggest that personality characteristics and college adjustment play important roles in college engineering students’ academic performance and engineering identity. Academic adjustment emerged as the strongest positive predictor of both CGPA and engineering identity, whereas neuroticism and extraversion were associated with lower academic achievement. Future researchers should examine factors affecting academic achievement, engineering identity, and adjustment to college among students from diverse backgrounds.
- Open Access
- 23 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 28 (3) , 1-28
Multi-Stage Enhanced Zero Trust Intrusion Detection System for Unknown Attack Detection in Internet of Things and Traditional Networks
Detecting unknown cyberattacks remains an open research problem and a significant challenge for the research community and the security industry. This article tackles the detection of unknown cybersecurity attacks in the Internet of Things (IoT) and traditional networks by categorizing them into two types: entirely new classes of unknown attacks (type-A) and unknown attacks within already known classes (type-B). To address this, we propose a novel multi-stage, multi-layer zero trust architecture for an intrusion detection system (IDS), uniquely designed to handle these attack types. The architecture employs a hybrid methodology that combines two supervised and one unsupervised learning stages in a funnel-like design, significantly advancing current detection capabilities. A key innovation is the layered filtering mechanism, leveraging type-A and type-B attack concepts to systematically classify traffic as malicious unless proven otherwise. Using four benchmark datasets, the proposed system demonstrates significant improvements in accuracy, recall, and error classification rates for unknown attacks, achieving an average accuracy and recall ranging between 88% and 95%. This work offers a robust, scalable framework for enhancing cybersecurity in diverse network environments.
- 23 August 2025
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Privacy and Security
- Vol. 28 (3) , 1-28
Open AccessMulti-Stage Enhanced Zero Trust Intrusion Detection System for Unknown Attack Detection in Internet of Things and Traditional Networks
Detecting unknown cyberattacks remains an open research problem and a significant challenge for the research community and the security industry. This article tackles the detection of unknown cybersecurity attacks in the Internet of Things (IoT) and traditional networks by categorizing them into two types: entirely new classes of unknown attacks (type-A) and unknown attacks within already known classes (type-B). To address this, we propose a novel multi-stage, multi-layer zero trust architecture for an intrusion detection system (IDS), uniquely designed to handle these attack types. The architecture employs a hybrid methodology that combines two supervised and one unsupervised learning stages in a funnel-like design, significantly advancing current detection capabilities. A key innovation is the layered filtering mechanism, leveraging type-A and type-B attack concepts to systematically classify traffic as malicious unless proven otherwise. Using four benchmark datasets, the proposed system demonstrates significant improvements in accuracy, recall, and error classification rates for unknown attacks, achieving an average accuracy and recall ranging between 88% and 95%. This work offers a robust, scalable framework for enhancing cybersecurity in diverse network environments.
- Open Access
- 18 March 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (3) , 308
Benchmarking Interpretability in Healthcare Using Pattern Discovery and Disentanglement
The healthcare industry seeks to integrate AI into clinical applications, yet understanding AI decision making remains a challenge for healthcare practitioners as these systems often function as black boxes. Our work benchmarks the Pattern Discovery and Disentanglement (PDD) system’s unsupervised learning algorithm, which provides interpretable outputs and clustering results from clinical notes to aid decision making. Using the MIMIC-IV dataset, we process free-text clinical notes and ICD-9 codes with Term Frequency-Inverse Document Frequency and Topic Modeling. The PDD algorithm discretizes numerical features into event-based features, discovers association patterns from a disentangled statistical feature value association space, and clusters clinical records. The output is an interpretable knowledge base linking knowledge, patterns, and data to support decision making. Despite being unsupervised, PDD demonstrated performance comparable to supervised deep learning models, validating its clustering ability and knowledge representation. We benchmark interpretability techniques—Feature Permutation, Gradient SHAP, and Integrated Gradients—on the best-performing models (in terms of F1, ROC AUC, balanced accuracy, etc.), evaluating these based on sufficiency, comprehensiveness, and sensitivity metrics. Our findings highlight the limitations of feature importance ranking and post hoc analysis for clinical diagnosis. Meanwhile, PDD’s global interpretability effectively compensates for these issues, helping healthcare practitioners understand the decision-making process and providing suggestive clusters of diseases to assist their diagnosis.
- 18 March 2025
- Published by MDPI AG in Bioengineering
- Vol. 12 (3) , 308
Open AccessBenchmarking Interpretability in Healthcare Using Pattern Discovery and Disentanglement
The healthcare industry seeks to integrate AI into clinical applications, yet understanding AI decision making remains a challenge for healthcare practitioners as these systems often function as black boxes. Our work benchmarks the Pattern Discovery and Disentanglement (PDD) system’s unsupervised learning algorithm, which provides interpretable outputs and clustering results from clinical notes to aid decision making. Using the MIMIC-IV dataset, we process free-text clinical notes and ICD-9 codes with Term Frequency-Inverse Document Frequency and Topic Modeling. The PDD algorithm discretizes numerical features into event-based features, discovers association patterns from a disentangled statistical feature value association space, and clusters clinical records. The output is an interpretable knowledge base linking knowledge, patterns, and data to support decision making. Despite being unsupervised, PDD demonstrated performance comparable to supervised deep learning models, validating its clustering ability and knowledge representation. We benchmark interpretability techniques—Feature Permutation, Gradient SHAP, and Integrated Gradients—on the best-performing models (in terms of F1, ROC AUC, balanced accuracy, etc.), evaluating these based on sufficiency, comprehensiveness, and sensitivity metrics. Our findings highlight the limitations of feature importance ranking and post hoc analysis for clinical diagnosis. Meanwhile, PDD’s global interpretability effectively compensates for these issues, helping healthcare practitioners understand the decision-making process and providing suggestive clusters of diseases to assist their diagnosis.
- Open Access
SPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics
Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.
Open AccessSPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics
Deep reinforcement learning agents often face challenges to effectively coordinate perception and decision-making components, particularly in environments with high-dimensional sensory inputs where feature relevance varies. This work introduces SPRIG (Stackelberg Perception-Reinforcement learning with Internal Game dynamics), a framework that models the internal perception-policy interaction within a single agent as a cooperative Stackelberg game. In SPRIG, the perception module acts as a leader, strategically processing raw sensory states, while the policy module follows, making decisions based on extracted features. SPRIG provides theoretical guarantees through a modified Bellman operator while preserving the benefits of modern policy optimization. Experimental results on the Atari BeamRider environment demonstrate SPRIG's effectiveness, achieving around 30% higher returns than standard PPO through its game-theoretical balance of feature extraction and decision-making.
- Open Access
- 28 December 2024
Learning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks
Network intrusion detection systems face significant challenges in identifying emerging attack patterns, especially when limited data samples are available. To address this, we propose a novel Multi-Space Prototypical Learning (MSPL) framework tailored for few-shot attack detection. The framework operates across multiple metric spaces-Euclidean, Cosine, Chebyshev, and Wasserstein distances-integrated through a constrained weighting scheme to enhance embedding robustness and improve pattern recognition. By leveraging Polyak-averaged prototype generation, the framework stabilizes the learning process and effectively adapts to rare and zero-day attacks. Additionally, an episodic training paradigm ensures balanced representation across diverse attack classes, enabling robust generalization. Experimental results on benchmark datasets demonstrate that MSPL outperforms traditional approaches in detecting low-profile and novel attack types, establishing it as a robust solution for zero-day attack detection.
- 28 December 2024
Open AccessLearning in Multiple Spaces: Few-Shot Network Attack Detection with Metric-Fused Prototypical Networks
Network intrusion detection systems face significant challenges in identifying emerging attack patterns, especially when limited data samples are available. To address this, we propose a novel Multi-Space Prototypical Learning (MSPL) framework tailored for few-shot attack detection. The framework operates across multiple metric spaces-Euclidean, Cosine, Chebyshev, and Wasserstein distances-integrated through a constrained weighting scheme to enhance embedding robustness and improve pattern recognition. By leveraging Polyak-averaged prototype generation, the framework stabilizes the learning process and effectively adapts to rare and zero-day attacks. Additionally, an episodic training paradigm ensures balanced representation across diverse attack classes, enabling robust generalization. Experimental results on benchmark datasets demonstrate that MSPL outperforms traditional approaches in detecting low-profile and novel attack types, establishing it as a robust solution for zero-day attack detection.
- Open Access
- 2 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-13
Admissions in the age of AI: detecting AI-generated application materials in higher education
Recent advances in Artificial Intelligence (AI), such as the development of large language models like ChatGPT, have blurred the boundaries between human and AI-generated text. This has led to a pressing need for tools that can determine whether text has been created or revised using AI. A general and universally effective detection model would be extremely useful, but appears to be beyond the reach of current technology and detection methods. The research described in this study adopts a domain and task specific approach and shows that specialized detection models can attain high accuracy. The study focuses on the higher education graduate admissions process, with the specific goal of identifying AI-generated and AI-revised Letters of Recommendation (LORs) and Statements of Intent (SOIs). Detecting such application materials is essential to ensure that applicants are evaluated on their true merits and abilities, and to foster an equitable and trustworthy admissions process. Our research is based on 3755 LORs and 1973 SOIs extracted from the application records of Fordham University’s Master’s programs in Computer Science and Data Science. To facilitate the construction and evaluation of detection models, we generated AI counterparts for each LOR and SOI using the GPT-3.5 Turbo API. The prompts for AI-generation text were derived from the admission data of the respective applicants, and the AI-revised LORs and SOIs were generated directly from the human-authored versions. We also utilize an open-access GPT-wiki-intro dataset to further validate our hypothesis regarding the feasibility of constructing domain-specific AI content detectors. Our experiments yield promising results in developing classifiers tailored to a specific domain when provided with sufficient training samples. Additionally, we present a comparative analysis of the word frequency and statistical characteristics of the text, which provides convincing evidence that ChatGPT employs distinctive vocabulary and paragraph structure compared to human-authored text. The code for this study is available on GitHub, and the models can be executed on user-provided data via an interactive web interface.
- 2 November 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-13
Open AccessAdmissions in the age of AI: detecting AI-generated application materials in higher education
Recent advances in Artificial Intelligence (AI), such as the development of large language models like ChatGPT, have blurred the boundaries between human and AI-generated text. This has led to a pressing need for tools that can determine whether text has been created or revised using AI. A general and universally effective detection model would be extremely useful, but appears to be beyond the reach of current technology and detection methods. The research described in this study adopts a domain and task specific approach and shows that specialized detection models can attain high accuracy. The study focuses on the higher education graduate admissions process, with the specific goal of identifying AI-generated and AI-revised Letters of Recommendation (LORs) and Statements of Intent (SOIs). Detecting such application materials is essential to ensure that applicants are evaluated on their true merits and abilities, and to foster an equitable and trustworthy admissions process. Our research is based on 3755 LORs and 1973 SOIs extracted from the application records of Fordham University’s Master’s programs in Computer Science and Data Science. To facilitate the construction and evaluation of detection models, we generated AI counterparts for each LOR and SOI using the GPT-3.5 Turbo API. The prompts for AI-generation text were derived from the admission data of the respective applicants, and the AI-revised LORs and SOIs were generated directly from the human-authored versions. We also utilize an open-access GPT-wiki-intro dataset to further validate our hypothesis regarding the feasibility of constructing domain-specific AI content detectors. Our experiments yield promising results in developing classifiers tailored to a specific domain when provided with sufficient training samples. Additionally, we present a comparative analysis of the word frequency and statistical characteristics of the text, which provides convincing evidence that ChatGPT employs distinctive vocabulary and paragraph structure compared to human-authored text. The code for this study is available on GitHub, and the models can be executed on user-provided data via an interactive web interface.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach
Distributed Denial of Service (DDoS) attacks pose an increasingly substantial cybersecurity threat to organizations across the globe. In this paper, we introduce a new deep learning-based technique for detecting DDoS attacks, a paramount cyber-security challenge with evolving complexity and scale. Specifically, we propose a new dual-space prototypical network that leverages a unique dual-space loss function to enhance detection accuracy for various attack patterns through geometric and angular similarity measures. This approach capitalizes on the strengths of representation learning within the latent space (a lower-dimensional representation of data that captures complex patterns for machine learning analysis), improving the model’s adaptability and sensitivity towards varying DDoS attack vectors. Our comprehensive evaluation spans multiple training environments, including offline training, simulated online training, and prototypical network scenarios, to validate the model’s robustness under diverse data abundance and scarcity conditions. The Multilayer Perceptron (MLP) with Attention, trained with our dual-space prototypical design over a reduced training set, achieves an average accuracy of 94.85% and an F1-Score of 94.71% across our tests, showcasing its effectiveness in dynamic and constrained real-world scenarios.
- 29 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach
Distributed Denial of Service (DDoS) attacks pose an increasingly substantial cybersecurity threat to organizations across the globe. In this paper, we introduce a new deep learning-based technique for detecting DDoS attacks, a paramount cyber-security challenge with evolving complexity and scale. Specifically, we propose a new dual-space prototypical network that leverages a unique dual-space loss function to enhance detection accuracy for various attack patterns through geometric and angular similarity measures. This approach capitalizes on the strengths of representation learning within the latent space (a lower-dimensional representation of data that captures complex patterns for machine learning analysis), improving the model’s adaptability and sensitivity towards varying DDoS attack vectors. Our comprehensive evaluation spans multiple training environments, including offline training, simulated online training, and prototypical network scenarios, to validate the model’s robustness under diverse data abundance and scarcity conditions. The Multilayer Perceptron (MLP) with Attention, trained with our dual-space prototypical design over a reduced training set, achieves an average accuracy of 94.85% and an F1-Score of 94.71% across our tests, showcasing its effectiveness in dynamic and constrained real-world scenarios.
- 29 November 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Education
- Vol. 100 (12) , 4933-4940
Rediscovering the Particle-in-a-Box: Machine Learning Regression Analysis for Hypothesis Generation in Physical Chemistry Lab
- 29 November 2023
- Published by American Chemical Society (ACS) in Journal of Chemical Education
- Vol. 100 (12) , 4933-4940
Rediscovering the Particle-in-a-Box: Machine Learning Regression Analysis for Hypothesis Generation in Physical Chemistry Lab
- Open Access
- 3 October 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Rediscovering the particle in a box: Machine learning regression analysis for hypothesis generation in physical chemistry lab
Given the growing prevalence of computational methods in chemistry, it is essential that undergraduate curricula introduce students to these approaches. One such area is the application of machine learning (ML) techniques to chemistry. Here we describe a new activity that applies ML regression analysis to the common physical chemistry laboratory experiment on the electronic absorption spectra of cyanine dyes. In the classic version of this experiment, students collect experimental spectra and interpret them using the Kuhn free electron model, based on the quantum mechanical particle-in-a-box (PIB). Our new computational activity has students train regression models of increasing complexity to predict the wavelength of maximum absorption for different cyanine dyes using a set of 13 molecular features. In addition, the activity introduces methods for evaluating and interpreting regression models. Ultimately, students are prompted to use their regression analysis results to generate hypotheses for what molecular properties underlie cyanine dye absorption, leading them naturally to the PIB model. In this report, we provide a dataset, reference code implementations in Mathematica and Python notebooks, and an example lab protocol with an introduction to cyanine dyes and the ML techniques. This activity can be completed in a single 3-hour lab period by upper-level undergraduate students with relatively little prior programming experience. Although intended to complement the experimental measurement of cyanine dye spectra, this activity can also be performed on its own; alternatively, it can form the basis of more involved projects in a computational chemistry or machine learning course.
- 3 October 2023
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessRediscovering the particle in a box: Machine learning regression analysis for hypothesis generation in physical chemistry lab
Given the growing prevalence of computational methods in chemistry, it is essential that undergraduate curricula introduce students to these approaches. One such area is the application of machine learning (ML) techniques to chemistry. Here we describe a new activity that applies ML regression analysis to the common physical chemistry laboratory experiment on the electronic absorption spectra of cyanine dyes. In the classic version of this experiment, students collect experimental spectra and interpret them using the Kuhn free electron model, based on the quantum mechanical particle-in-a-box (PIB). Our new computational activity has students train regression models of increasing complexity to predict the wavelength of maximum absorption for different cyanine dyes using a set of 13 molecular features. In addition, the activity introduces methods for evaluating and interpreting regression models. Ultimately, students are prompted to use their regression analysis results to generate hypotheses for what molecular properties underlie cyanine dye absorption, leading them naturally to the PIB model. In this report, we provide a dataset, reference code implementations in Mathematica and Python notebooks, and an example lab protocol with an introduction to cyanine dyes and the ML techniques. This activity can be completed in a single 3-hour lab period by upper-level undergraduate students with relatively little prior programming experience. Although intended to complement the experimental measurement of cyanine dye spectra, this activity can also be performed on its own; alternatively, it can form the basis of more involved projects in a computational chemistry or machine learning course.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1191-1196
Integrating Multiple Visual Attention Mechanisms in Deep Neural Networks
Inspired by the success of various visual attention techniques in computer vision, we introduce a novel method for integrating multiple attention mechanisms to boost model performance. Our approach involves augmenting a base model with a Parallel Visual Attention Encoder (PVAE) branch, which concurrently employs two different attention modules (modified large kernel attention and modified convolutional block attention) to capture essential visual features. To reduce the training cost incurred by these additional components, we apply an encoder for efficient feature extraction and dimensionality reduction before applying the attention modules. The proposed PVAE architecture can be combined with cutting-edge models (e.g., EfficientNet, ResNet, DenseNet, etc.) to create a Parallel Visual Attention Network (PVAN). We evaluate the efficacy of our approach by devising a PVAN with EfficientNet as the base model for the task of classifying dog breeds. Our experimental results demonstrate the effectiveness of the proposed hybrid visual attention architecture, which achieves superior performance compared to the base model and models with a single attention mechanism. We further present an interactive web application developed for the general public to identify dog breeds using their photographs to test our model’s performance in real-life scenarios.
- 1 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1191-1196
Integrating Multiple Visual Attention Mechanisms in Deep Neural Networks
Inspired by the success of various visual attention techniques in computer vision, we introduce a novel method for integrating multiple attention mechanisms to boost model performance. Our approach involves augmenting a base model with a Parallel Visual Attention Encoder (PVAE) branch, which concurrently employs two different attention modules (modified large kernel attention and modified convolutional block attention) to capture essential visual features. To reduce the training cost incurred by these additional components, we apply an encoder for efficient feature extraction and dimensionality reduction before applying the attention modules. The proposed PVAE architecture can be combined with cutting-edge models (e.g., EfficientNet, ResNet, DenseNet, etc.) to create a Parallel Visual Attention Network (PVAN). We evaluate the efficacy of our approach by devising a PVAN with EfficientNet as the base model for the task of classifying dog breeds. Our experimental results demonstrate the effectiveness of the proposed hybrid visual attention architecture, which achieves superior performance compared to the base model and models with a single attention mechanism. We further present an interactive web application developed for the general public to identify dog breeds using their photographs to test our model’s performance in real-life scenarios.