Ratna Babu Chinnam | Searcharxiv

arXiv2026

Automated Generation of Complexity-Validated Decision Scenarios Using Large Language Models

Cognitive decision-making research depends on diverse scenarios with carefully controlled complexity, yet manual production is slow, inconsistent, and biased. We developed an automated pipeline that uses LLms to generate structured decision scenarios and validates their complexity through a composite framework rooted in established task-complexity theory. We evaluated 4,238 scenarios across multiple domains and complexity tiers. Measurement validation met rigorous psychometric standards. Agreement among five independent model families was nearly perfect, with an intraclass correlation coefficient of 0.997 and a kappa of 0.971. Known-groups validity demonstrated large separation between tiers, with an eta-squared of 0.587 and all pairwise comparisons significant at p less than .001. Factor analysis revealed a dominant complexity construct, with loadings between 0.87 and 0.96 across three frameworks, while interactivity formed a weaker secondary dimension at 0.34. Discriminant validity was limited by a strong relationship between complexity and text length that persisted after controlling for tier, yielding a partial correlation of 0.86. This constrains construct purity but does not undermine the instrument's tier-grading function. Model analyses showed a negative association between throughput and schema pass rate (r = -0.967, p = .007, n = 5), suggesting a speed-quality trade-off, though largely driven by one high-throughput model. Llama 4 Maverick generated scenarios fastest at 134 per minute versus 25 for DeepSeek Chat V3.2, but underproduced complex-tier scenarios, whereas DeepSeek Chat V3.2 balanced domain coverage with high schema compliance. The system demonstrated strong psychometric properties, enabling reliable classification into Simple, Moderate, and Complex tiers and providing the measurement infrastructure needed for downstream cognitive assessment of AI systems

cs.AI↗

arXiv2026

Multi-Dimensional Assessment for AI Cognition (MAAC): A Theoretical Framework for Process-Oriented Cognitive Evaluation of Text-Based AI Systems

Evaluating artificial intelligence systems has historically relied on outcome-based benchmarks that measure task accuracy, robustness, or fairness. While indispensable, these benchmarks provide limited diagnostic insight into the underlying cognitive processes that generate performance-leaving critical questions unanswered about how AI systems reason, integrate memory, manage complexity, or avoid generating false information. This paper introduces the Multi-Dimensional Assessment for AI Cognition (MAAC), a theoretically grounded framework for shifting evaluation from what text-based AI systems produce to how they think. MAAC defines nine cognitively motivated dimensions: Cognitive Load, Tool Execution, Content Quality, Memory Integration, Complexity Handling, Hallucination Control, Knowledge Transfer, Processing Efficiency, and Process-Outcome Alignment. Each dimension is grounded in established cognitive science theory-drawing on Marr's tri-level hypothesis, Baddeley's working memory model, Sweller's cognitive load theory, and unified theories of cognition. Five theoretical analyses provide initial support for the framework's coherence and empirical testability: dimension-to-theory mapping; a coverage matrix assessing breadth and non-redundancy; a formal gap analysis relative to current evaluation practice; a worked diagnostic illustration; and a set of a priori interdependency predictions for future empirical testing. MAAC provides a theoretical and operational framework for principled process-level cognitive assessment of text-based AI systems, complementing existing outcome-based benchmarks with cognitively grounded, multi-dimensional evaluation.

cs.AI↗

arXiv2020

SPA-GAN: Spatial Attention GAN for Image-to-Image Translation

Image-to-image translation is to learn a mapping between images from a source domain and images from a target domain. In this paper, we introduce the attention mechanism directly to the generative adversarial network (GAN) architecture and propose a novel spatial attention GAN model (SPA-GAN) for image-to-image translation tasks. SPA-GAN computes the attention in its discriminator and use it to help the generator focus more on the most discriminative regions between the source and target domains, leading to more realistic output images. We also find it helpful to introduce an additional feature map loss in SPA-GAN training to preserve domain specific features during translation. Compared with existing attention-guided GAN models, SPA-GAN is a lightweight model that does not need additional attention networks or supervision. Qualitative and quantitative comparison against state-of-the-art methods on benchmark datasets demonstrates the superior performance of SPA-GAN.

cs.CV↗

arXiv2020

Two-Stage Stochastic Choice Modeling Approach for Electric Vehicle Charging Station Network Design in Urban Communities

Electric vehicles (EVs) provide a cleaner alternative that not only reduces greenhouse gas emissions but also improves air quality and reduces noise pollution. The consumer market for electrical vehicles is growing very rapidly. Designing a network with adequate capacity and types of public charging stations is a challenge that needs to be addressed to support the current trend in the EV market. In this research, we propose a choice modeling approach embedded in a two-stage stochastic programming model to determine the optimal layout and types of EV supply equipment for a community while considering randomness in demand and drivers' behaviors. Some of the key random data parameters considered in this study are: EV's dwell time at parking {\sv location}, battery's state of charge, distance from home, willingness to walk, drivers' arrival patterns, and traffic on weekdays and weekends. The two-stage model uses the sample average approximation method, which asymptotically converges to an optimal solution. To address the computational challenges for large-scale instances, we propose an outer approximation decomposition algorithm. We conduct extensive computational experiments to quantify the efficacy of the proposed approach. In addition, we present the results and a sensitivity analysis for a case study based on publicly available data sources.

eess.SP↗

arXiv2019

Managing access to primary care clinics using robust scheduling templates

An important challenge confronting healthcare is the effective management of access to primary care. Robust appointment scheduling policies/templates can help strike an effective balance between the lead-time to an appointment (a.k.a. indirect waiting time, measuring the difference between a patient's desired and actual appointment dates) and waiting times at the clinic on the day of the appointment (a.k.a. direct waiting time). We propose methods for identifying effective appointment scheduling templates using a two-stage stochastic mixed-integer linear program model. The model embeds simulation for accurate evaluation of direct waiting times and uses sample average approximation method for computational efficiency. The model accounts for patients' no-show behaviors, provider availability, overbooking, demand uncertainty, and overtime constraints. The model allows the scheduling templates to be potentially updated at regular intervals while minimizing the patient expected waiting times and balancing provider utilization. Proposed methods are validated using data from the U.S. Department of Veterans Affairs (VA) primary care clinics.

math.OC↗

arXiv2019

Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study

Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predictive modeling approach based on deep learning based feature representations and word embedding techniques. Our method uses different deep architectures (stacked sparse autoencoders, deep belief network, adversarial autoencoders and variational autoencoders) for feature representation in higher-level abstraction to obtain effective and robust features from EHRs, and then build prediction models on top of them. Our approach is particularly useful when the unlabeled data is abundant whereas labeled data is scarce. We investigate the performance of representation learning through a supervised learning approach. Our focus is to present a comparative study to evaluate the performance of different deep architectures through supervised learning and provide insights in the choice of deep feature representation techniques. Our experiments demonstrate that for small data sets, stacked sparse autoencoder demonstrates a superior generality performance in prediction due to sparsity regularization whereas variational autoencoders outperform the competing approaches for large data sets due to its capability of learning the representation distribution.

cs.LG↗

arXiv2019

Representation Learning with Autoencoders for Electronic Health Records: A Comparative Study

Increasing volume of Electronic Health Records (EHR) in recent years provides great opportunities for data scientists to collaborate on different aspects of healthcare research by applying advanced analytics to these EHR clinical data. A key requirement however is obtaining meaningful insights from high dimensional, sparse and complex clinical data. Data science approaches typically address this challenge by performing feature learning in order to build more reliable and informative feature representations from clinical data followed by supervised learning. In this paper, we propose a predictive modeling approach based on deep learning based feature representations and word embedding techniques. Our method uses different deep architectures (stacked sparse autoencoders, deep belief network, adversarial autoencoders and variational autoencoders) for feature representation in higher-level abstraction to obtain effective and robust features from EHRs, and then build prediction models on top of them. Our approach is particularly useful when the unlabeled data is abundant whereas labeled data is scarce. We investigate the performance of representation learning through a supervised learning approach. Our focus is to present a comparative study to evaluate the performance of different deep architectures through supervised learning and provide insights in the choice of deep feature representation techniques. Our experiments demonstrate that for small data sets, stacked sparse autoencoder demonstrates a superior generality performance in prediction due to sparsity regularization whereas variational autoencoders outperform the competing approaches for large data sets due to its capability of learning the representation distribution

cs.LG↗

arXiv2018

Grouped Mixture of Regressions

Finite Mixture of Regressions (FMR) models are among the most widely used approaches in dealing with the heterogeneity among the observations in regression problems. One of the limitations of current approaches is their inability to incorporate group structure in data when available. In some applications, it is desired to cluster groups of observations together rather than the individual ones. In this work, we extend the FMR framework to allow for group structure among observations, and call the resulting model the Grouped Mixture of Regressions (GMR). We derive a fast fitting algorithm based on the Expectation-Maximization (EM) idea. We also show how the group structure can improve prediction by sharing information among members of each group, as reflected in the posterior predictive density under GMR. %that they don't consider clustering the data when there is group structure. In other words, sometimes it is desired to force the algorithm to cluster groups/blocks of observations, instead of individual observations. %In this work, we propose a maximum likelihood approach to cluster groups of observations. We call this algorithm Group Mixture of Regressions (GMR). Expectation Maximization (EM) is employed to maximize the likelihood. Posterior prediction density for predicting new observations is also derived and presented. The performance of the approach is assessed using both synthetic data as well as a real-world example.

stat.AP↗

arXiv2018

Data-Driven Analytics for Benchmarking and Optimizing Retail Store Performance

Growing competitiveness and increasing availability of data is generating tremendous interest in data-driven analytics across industries. In the retail sector, stores need targeted guidance to improve both the efficiency and effectiveness of individual stores based on their specific locations, demographics, and environment. We propose an effective data-driven framework for internal benchmarking that can lead to targeted guidance for individual stores. In particular, we propose an objective method for segmenting stores using a model-based clustering technique that accounts for similarity in store performance dynamics. The proposed method relies on an effective Finite Mixture of Regressions technique based on competitive learning for carrying out the model-based clustering with `must-link' constraints and modeling store performance. We also propose an optimization framework to derive tailored recommendations for individual stores within store clusters that jointly improves profitability for the store while also improving sales to satisfy franchiser requirements. We validate the methods using synthetic experiments as well as a real-world automotive dealership network study for a leading global automotive manufacturer.

stat.AP↗

arXiv2017

Observational Data-Driven Modeling and Optimization of Manufacturing Processes

The dramatic increase of observational data across industries provides unparalleled opportunities for data-driven decision making and management, including the manufacturing industry. In the context of production, data-driven approaches can exploit observational data to model, control and improve the process performance. When supplied by observational data with adequate coverage to inform the true process performance dynamics, they can overcome the cost associated with intrusive controlled designed experiments and can be applied for both monitoring and improving process quality. We propose a novel integrated approach that uses observational data for process parameter design while simultaneously identifying the significant control variables. We evaluate our method using simulated experiments and also apply it to a real-world case setting from a tire manufacturing company.

math.OC↗

arXiv2017

A Stochastic Programming Approach for Electric Vehicle Charging Network Design

Advantages of electric vehicles (EV) include reduction of greenhouse gas and other emissions, energy security, and fuel economy. The societal benefits of large-scale adoption of EVs cannot be realized without adequate deployment of publicly accessible charging stations. We propose a two-stage stochastic programming model to determine the optimal network of charging stations for a community considering uncertainties in arrival and dwell time of vehicles, battery state of charge of arriving vehicles, walkable range and charging preferences of drivers, demand during weekdays and weekends, and rate of adoption of EVs within a community. We conducted studies using sample average approximation (SAA) method which asymptotically converges to an optimal solution for a two-stage stochastic problem, however it is computationally expensive for large-scale instances. Therefore, we developed a heuristic to produce near to optimal solutions quickly for our data instances. We conducted computational experiments using various publicly available data sources, and benefits of the solutions are evaluated both quantitatively and qualitatively for a given community.

math.OC↗