Projects

A sampling of my AI-centric projects are below. I have provided one sample project for each year, in descending order, for the time period 2025 through 2017:
(1) Enhancing the Involved Multi-Attribute Decision-Making (MADM)/Multi-Objective Decision-Making (MODM) Subjective Measure (SM)/Objective Measure Counterpoisings (OM),
(2) A Reduction of AI Energy Consumption (AEC) at the Metaheuristic Algorithm (MA) Level and Certain Other Areas That Are Amenable to Such Optimizations,
(3) Enhancing the Bound Tightening for Successive Neural Network Layers to Facilitate Global Optimization, via a Bespoke Numerical Stability Implementation,
(4) An Optimal Convex Relaxation (OCR)-Centric Approach for a More Robust Implementation of the Wavelet Covariance Transform (WCT) for Boundary Detection,
(5) Numerical Stability Adaptive Inertial Weighting for Particle Swarm Optimization (PSO) Implementation on a Deep Convolutional Generative Adversarial Network (DCGAN),
(6) Auto-tuning of an Artificial Intelligence (AI)-centric Steady State Genetic Algorithm (SSGA) Compression Factor on a Modified Numerical Computing Platform,
(7) Stochastic Gradient Descent (SGD) Algorithm for Ascertaining Apropos Weights in the Fast Training of Support Vector Machines (SVMs),
(8) Bi-Normal Separation (BNS) and a Modified Association Matrix (MAM) for an Accelerated Inference Engine, and
(9) Higher Tolerance for Uncertainty amidst Compressed Decision Cycles (CDCs) on an Stacked Generative Adversarial Network (SGAN).

2025

Enhancing the Involved Multi-Attribute Decision-Making (MADM)/Multi-Objective Decision-Making (MODM) Subjective Measure (SM)/Objective Measure Counterpoisings (OM)

Excerpt from my publication: [Mitigation Approach for Certain Biases in Survey Scale Input Within AI Control and Decision Systems]

For the realm of Artificial Intelligence (AI), Transparency, Explainability, and Accountability (TEA) have become a critical triumvirate. Central to TEA are reliability and validity. However, classical assessment instruments may fall short in this regard. The purpose of this paper was to formulate a prospective TEA-centric AI-facilitated assessment instrument that better contends with quantitative fallacy and human bias issues that are often not addressed. Various hybridizations of Semantic Difference Scales and Object Measures (OMs) were experimented with for the purposes of enhancing the involved Multi-Attribute Decision-Making/Multi-Objective Decision-Making Subjective Measure/OM counterpoisings, particularly on the Human-Informed Repertoire of Experience side of the AI Control and Decision System - which impacts the machine-centric Decision Engineering/Decision-Making side - thereby effectuating a more robust System TEA (STEA) paradigm.

2024

A Reduction of AI Energy Consumption (AEC) at the Metaheuristic Algorithm (MA) Level and Certain Other Areas That Are Amenable to Such Optimizations

Excerpt from my publication: [Inference-Optimized Metaheuristic Approach for a Prospective AI Training/Inference Inversion Paradigm in Optimized Energy-Aware Computing], which received a Best Presenter Award.

Energy consumption at the various steps of the Machine Learning (ML) model life cycle, as a constituent application of Artificial Intelligence (AI), is infrequently reported. While the Explainable AI (XAI) or Explainable ML (XML) movement has focused upon more explainable ML models, the AI Energy Consumption (AEC) facet has not progressed as rapidly and still remains quite translucent. For example, even the AEC ratios of the key AI stages (e.g., pre-training, fine-tuning, and inferencing) have not always accompanied the releases of new ML models. This lack of data has, perhaps, contributed to the dearth of analyses on effective compute (e.g., algorithmic efficiency versus hardware efficiency) for the newer models, and in modern times, AEC may be skewing to the inferencing side. This may necessitate revised architectures, particularly amidst the findings that generalized ML models for specific tasks have a much higher AEC when contrasted against task-specific ML models. It has also been reported that, within those same models, a higher number of parameters segues to a higher AEC. Higher accuracies also beget higher AECs, and “advanced anomaly detection” necessitates tasks that have an even higher AEC. Moreover, as it is now customary to run numerous instances of a pre-trained model over various instances in an ensemble fashion, the AEC is multiplied accordingly. Yet, there are opportunities to reduce AEC at the Metaheuristic Algorithm (MA) level (e.g., at the convolutional layer), and certain versatile constructs (that scale well across the AI stages) are amenable to such optimizations; furthermore, performance metric comparisons in the literature have, traditionally, been artificially constrained to a “fixed number of allowed function calls,” and this might have led to misinterpretations of MA performance in Real World Scenario (RWS) paradigms. These misinterpretations can skew research directions, particularly for RWS Multiple Objective Large Scale Nonlinear Programming Problems (MOLSNLP) and may also lead to an underestimation of the involved AEC. This paper presents a promising RWS-oriented Particle Swarm Optimization (PSO)-based MA with concomitant Rough Order of Magnitude (ROM) AECs.

2023

Enhancing the Bound Tightening for Successive Neural Network Layers to Facilitate Global Optimization, via a Bespoke Numerical Stability Implementation

Excerpt from my publication: [AI-Facilitated Ambient Factor-Based Annealment and Resiliency Sufficiency in Austere Locales]

For the involved experiment, explorations were conducted regarding a particular class of Convolutional Neural Networks (CNNs), namely Deep Convolutional Generative Adversarial Network (DCGANs), to solve not only certain convex optimization problems, but also to leverage the same mechanism for tuning its own hyperparameters. This gives rise to other interesting technical challenges. For example, Particle Swarm Optimization (PSO) is an approach for hyperparameter reduction/tuning, but the algorithmic challenge of implementing a PSO on a DCGAN centers upon the conversion of continuous or discontinuous hyperparameters to discrete values, which may result in premature stagnation of particles at local optima. The involved implementation mechanics, such as increasing the inertial weighting (so as to assist in mitigating the stagnation issue), may spawn yet other convex optimization problems. The involved experiments capitalized upon the feed-forward structure of a “You Only Look Once” (YOLO)-based DCGAN. Specifically, a squeezed Deep Convolutional-YOLO-Generative Adversarial Network (DC-YOLO-GAN), referred to as a Modified Squeezed YOLO v3 Implementation (MSY3I), combined with convex relaxation adversarial training, was utilized to improve the bound tightening for each successive neural network layer and better facilitate the global optimization, via a specific numerical stability implementation within the MSY3I.

2022

An Optimal Convex Relaxation (OCR)-Centric Approach for a More Robust Implementation of the Wavelet Covariance Transform (WCT) for Boundary Detection

Excerpt from my publication: [Optimal Convex Relaxation-based Wavelet Covariance Transform for More Robust AOD-PM Characterization and Tracer Tracking of Biomass Burning Over Land/Sea Boundary Regions], which received a Best Paper Award.

Satellite-Based (SB) Remote Sensing (R/S) column values, such as Aerosol Optical Depth (AOD), and surface values, such as Particulate Matter (PM), can be leveraged for better monitoring and tracking of the pattern of life for peatland fire-induced smoke, smog, and precipitation-generating cloud cover (a Potentially Toxic Triumvirate or PTT), which might initially move out over coastal waters, but subsequently return to coastal lands, peninsulas, as well as nearby islands with ensuing effects. In many cases, as noted by interviews with those involved with firefighting task forces, the tracking of the PTT stops at the border between land/sea. Traditionally, the amalgam of SB R/S and land surface values have been more readily available. However, the availability of Version 3 Maritime Aerosol Network (MAN) data and ship-based measurements of opportunity, such as via the Amazon procurable Microtops II Sunphotometer (MIIS), have made sea surface values more prevalent. Available Moderate Resolution Imaging Spectroradiometer (MODIS) and other SB R/S data can be combined with MIIS data for enhanced contextualization. Conjoined with the fact that aerosols from the peatland fires have been characterized, the Biomass Burning (BB) (e.g., peatland fire) tracer tracking of, among others, Levoglucosan (LG) in PM2.5 and PM1 presents an opportunity for both Post-fire Evaluation and Pre-fire Planning. Yet, a core challenge centers upon the issue that while SB R/S estimation of PM2.5 has become quite pervasive, the estimation of PM1 requires more care, such as by way of a more robust AOD-PM characterization. Contributory to this goal is AOD normalization, such as by considering Planet Boundary Layer Height (PBLH). Traditionally, this can be derived using a Wavelet Covariance Transform (WCT) (e.g., Haar) for boundary detection in the scattering ratio, and the main contribution of this paper is that of a more robust implementation of the WCT by way of an Optimal Convex Relaxation (OCR)-based approach. The ensuing enhanced AOD-PM characterization, improved AOD normalization, enhanced tracking, and more reliable contextualization might be of value-added proposition for better understanding the impact of peatland fires and improving Postfire Evaluation and Pre-fire Planning.

2021

Numerical Stability Adaptive Inertial Weighting for Particle Swarm Optimization (PSO) Implementation on a Deep Convolutional Generative Adversarial Network (DCGAN)

Excerpt from my publication: [AI-based Robust Convex Relaxations for Supporting Diverse QoS in Next-Generation Wireless Systems]

For the involved experiment, explorations were conducted regarding a particular class of Convolutional Neural Networks (CNNs), namely Deep Convolutional Generative Adversarial Network (DCGANs), to solve not only certain convex optimization problems, but also to leverage the same mechanism for tuning its own hyperparameters. This gives rise to other interesting technical challenges. For example, Particle Swarm Optimization (PSO) is an approach for hyperparameter reduction/tuning, but the algorithmic challenge of implementing a PSO on a DCGAN centers upon the conversion of continuous or discontinuous hyperparameters to discrete values, which may result in premature stagnation of particles at local optima. The involved implementation mechanics, such as increasing the inertial weighting (so as to assist in mitigating the stagnation issue), may spawn yet other convex optimization problems. The involved experiments capitalized upon the feed-forward structure of a “You Only Look Once” (YOLO)-based DCGAN. Specifically, a squeezed Deep Convolutional-YOLO-Generative Adversarial Network (DC-YOLO-GAN), referred to as a Modified Squeezed YOLO v3 Implementation (MSY3I), combined with convex relaxation adversarial training, was utilized to improve the bound tightening for each successive neural network layer and better facilitate the global optimization, via a specific numerical stability implementation within the MSY3I.

2020

Auto-tuning of an Artificial Intelligence (AI)-centric Steady State Genetic Algorithm (SSGA) Compression Factor on a Modified Numerical Computing Platform

Excerpt from my publication: [Mitigation Factors for Multi-domain Resilient Networked Distributed Tessellation Communications], which received a Best Paper Award.

Simulations run atop a Modified GNU Octave (M-GNU-O) platform have indicated that statistical consistency tests are not reliable for discerning an optimal filter (which still necessitates parameter tuning). Rather, the tests yield an infinite set of consistent filters within which the optimal filter is a unique member. Preliminary experimental results indicate promise for the auto-tuning of the Steady State Genetic Algorithm (SSGA) compression factor ζ for more optimal convergence of an optimally tuned filter (or a set of near optimally tuned filters). Indeed, auto-tuning is central to this capability, and the compression factor ζ is instrumental in dictating the rate of the steady state towards convergence. Large ζ values may be indicative of earlier (i.e., premature) convergence, thereby segueing to specious solutions that have keyed in on local minima and/or noise, thereby precluding a more optimal convergence. Accordingly, one observation centers around the fact that the ability to re-tune the compression factor ζ to a lower value (i.e., <1) seems to be critical. Another observation centers around the Principal Tuning Result (PTR) for an exponentially bounded fitness, given the characteristic time λ for an overall time dependent population fitness F, which satisfies the convergence condition where PTR = [F_(t+1)-F_t ] < F_t(e^(- λt)-1). In essence, the PTR allows for an SSGA optimization estimate for the convergent approach of the time dependent population fitness F in a quasi-analytical fashion prior to a given numerical iteration, and this finding seems to be consistent with other research in the field.

2019

Stochastic Gradient Descent (SGD) Algorithm for Ascertaining Apropos Weights in the Fast Training of Support Vector Machines (SVMs)

Excerpt from my publication: [Fast Training of Support Vector Machine for Forest Fire Prediction]

The Support Vector Machine (SVM) is a binary classification model, which aims to find the optimal separating hyperplane with the maximum margin so as to classify the data. The maximum margin SVM is obtained by solving a convex Quadratic Programming Problem (QPP) and is termed the hard-margin linear SVM, whose training process is often time-consuming. Several decomposition methods have been experimented with, which split the problem into a sequence of smaller sub-problems. The Sequential Minimal Optimization (SMO) algorithm is a widely utilized decomposition method for SVM. The SMO decomposition method can lead to faster training, whereby the problem is decomposed more quickly into sub-problems. SMO avoids the resolving of numerical Quadratic Programming (QP) problems and takes the alternative pathway of solving the smallest optimization problem at each iteration (by repeatedly selecting a subset of the free variables and optimizing over these variables). Another method for solving optimization problems, which has also been widely utilized for machine learning is that of the Stochastic Gradient Descent (SGD), which is an iterative method. A SGD algorithm was utilized on the discussed experimental testbed to ascertain apropos weights (w_0, w) by iteratively updating the values of w_0 and w, via the utilization of the value of gradient V. The value of the gradient V depends upon the inputs (S), the current values of the model parameter (λ,η,σ), and the cost function f; η is the learning rate, which determines the size of the steps to reach a minimum, λ is the regularization parameter to reduces overfitting, and σ is standard deviation of sigma with loss function l (y ̂(x|Θ,y) that measures the cost of prediction ŷ when the actual answer is y.

2018

Bi-Normal Separation (BNS) and a Modified Association Matrix (MAM) for an Accelerated Inference Engine

Excerpt from my publication: [Countering an Anti-Natural Language Processing Mechanism in the Computer-Mediated Communication of “Trusted” Cyberspace Operations: Bi-Normal Separation Feature Scaling for Informing a Modified Association Matrix]

A prototypical Deep Learning Engine (Training Engine and Inference Engine) with the specified exemplar layers for the discussed Training Engine experiment are as follows: N-Grams (NG) (i.e. recurrent word combinations), Part-of-Speech (POS) N-Grams (POSNG) (i.e. recurrent POS combinations), words with semantic characteristics of relationships (using values from WordNet), Positive and Negative Values (PNV) of words (using values from the Macquarie Semantic Orientation Lexicon [MSOL] ), Pleasantness Value (PV) of words (using values from Whissel’s Dictionary of Affect in Language (WDAL), and Affective words Demonstrating Subjectivity (ADS). These same exemplar layers are utilized for both the Forward Propagation “Rough-Tuning” for the Training Model and well as the Continuous Back Propagation “Fine-Tuning” for the Pre-Trained Model. Bi-Normal Separation (BNS) and a Modified Association Matrix (MAM) were leveraged as accelerants for the inference engine. When combined with specifically chosen datasets to assist in the pre-training, the Transfer Learning was enhanced. By way of explanation, the Untrained Model eventually becomes a “Rough-Tuned” Trained Model (upon ingestion of the initial Training Dataset and Forward Propagation). Further “Rough Tuning” can be achieved by training specific layers, such as PNV and PV (e.g. via MSOL and WDAL, respectively). Eventually, the Trained Model becomes a Pre-Trained Model, and “Fine-Tuning” can be achieved by Continuous Back Propagation and optimizing at certain training layers, such as PNV (e.g., via the Yelp Restaurant Sentiment Lexicon [YRSL] and Amazon Laptop Sentiment Lexicon [ALSL]) and PV (e.g., via the Canadian National Research Council (NRC) Hashtag Emotion Lexicon [HEL] and NRC Word-Emotion Association Lexicon [WEAL]). The Pre-Trained Model is then further optimized when a new dataset is ingested. To avoid over-fitting, the Pre-Trained Model of the CNN also served as a feature extractor for which the features can be fed into a Support Vector Machine (SVM). Collectively, the described constituent components comprised an experimental framework for an enhanced inference system.

2017

Higher Tolerance for Uncertainty Amidst Compressed Decision Cycles on an Stacked Generative Adversarial Network (SGAN)

Excerpt from my publication: [Prototype Orchestration Framework as a High Exposure Dimension Cyber Defense Accelerant Amidst Ever-Increasing Cycles of Adaptation by Attackers: A Modified Deep Belief Network Accelerated by a Stacked Generative Adversarial Network for Enhanced Event Correlation], which received a Best Paper Award.

The prototype orchestration framework involved a modified Stacked Generative Adversarial Network (SGAN) for Uncompressed Decision Cycles (UDC) and a modified Deep Belief Network (DBN) for Compressed Decision Cycles (CDC). A particular focus was given to the Artificial Intelligence (AI) accelerant methodology utilized to compress the involved decision-making cycles. Data was ingested by two disparate pathways: (1) UDC, and (2) CDC. For UDC, the data was passed along for Deep Learning (DL) as well as a paradigm of “higher ambiguity and lower uncertainty” (HALU) (i.e. more data is desired). In contrast, for CDC, data was passed along to a DBN as well as a paradigm of “lower ambiguity and higher uncertainty” (LAHU) module. For the UDC pathway, DL and HALU passed their votes to a modified N-Input Voting Algorithm (NIVA) 1 module, whose output was then passed along to a Voting Algorithm for Fault Tolerant Systems (VAFTs) variant for further processing prior to a decision being reached. For the CDC pathway, DBN and LAHU passed their votes down a fast track pathway that had its own NIVA 2 module, an additional “Lower Ambiguity Accelerant (LAA),” and a resultant decision output. In essence, the prototype orchestration framework was predicated upon the hybridization of a modified DBN conjoined with a particular cognitive computing precept (the acceptance of higher uncertainty amidst lower ambiguity for CDC); for UDC, it utilized a modified SGAN, which served as a feeder to an LAA.