Anita Raja

• PhD
• Professor at City University of New York - Hunter College

Understanding and managing uncertainty is crucial in machine learning, especially in high-stakes domains like healthcare, where class imbalance can impact predictions. This paper introduces RIGA, a novel pipeline that mitigates class imbalance using generative AI. By converting tabular healthcare data into images, RIGA leverages models like cGAN, V...

Preeclampsia is one of the leading causes of maternal morbidity, with consequences during and after pregnancy. Because of its diverse clinical presentation, preeclampsia is an adverse pregnancy outcome that is uniquely challenging to predict and manage. In this paper, we developed racial bias-free machine learning models that predict the onset of p...

Adverse pregnancy outcomes (APOs) affect a large proportion of pregnancies and represent an important cause of morbidity and mortality worldwide. Yet the pathophysiology of APOs is poorly understood, limiting our ability to prevent and treat these conditions. To search for genetic markers of maternal risk for four APOs, we performed multi-ancestry...

Objective Preterm birth (PTB) is a major determinant of neonatal mortality, morbidity, and childhood disability. In this article, we present a longitudinal analysis of the risk factors associated with PTB and how they have varied over the years: starting from 1968 when the CDC first started, reporting the natality data, up until 2021. Along with th...

Autonomous agents require the ability to identify and adapt to unexpected conditions. Real-world environments are rarely stationary, making it problematic for agents operating in such environments to learn efficient policies. There is therefore a need for a general framework capable of detecting when an agent has encountered novel conditions, and d...

Preterm birth is a major cause of neonatal morbidity and mortality, but its etiology and risk factors are poorly understood. We undertook a scoping review to illustrate the breadth of risk factors for preterm birth that have been reported in the literature. We conducted a search in the PubMed database for articles published in the previous 5 years....

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code -- supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce code that is error-prone, n...

Adverse pregnancy outcomes (APOs) are major risk factors for women's health during pregnancy and even in the years after pregnancy. Due to the heterogeneity of APOs, only few genetic associations have been identified. In this report, we conducted genome-wide association studies (GWAS) of 479 traits that are possibly related to APOs using a large an...

Adverse pregnancy outcomes (APOs) are major risk factors for women's health during pregnancy and even in the years after pregnancy. Due to the heterogeneity of APOs, only few genetic associations have been identified. In this report, we conducted genome-wide association studies (GWAS) of 479 traits that are possibly related to APOs using a large an...

Objective Preeclampsia is one of the leading causes of maternal morbidity, with consequences during and after pregnancy. Because of its diverse clinical presentation, preeclampsia is an adverse pregnancy outcome that is uniquely challenging to predict and manage. In this paper, we developed machine learning models that predict the onset of preeclam...

Preeclampsia is a type of hypertension that develops during pregnancy. It is one of the leading causes for maternal morbidity with consequences during and after pregnancy. Because of its diverse clinical presentation, preeclampsia is a uniquely challenging adverse pregnancy outcome to predict and manage. In this paper, we explore preeclampsia in a...

Traffic congestion is ubiquitous in cities across the globe resulting in great economic and environmental costs. Although real-time traffic updates are now available, the tendency of drivers to make uncoordinated routing decisions exacerbates the known problems of selfish routing including traffic congestion and flow oscillation. Existing solutions...

As cities across the globe continue to grow, traffic congestion has become globally ubiquitous with great economic and environmental costs associated with it. The increasing prevalence of self-driving vehicles creates an opportunity to build smart, responsive traffic infrastructure of the future. Such an infrastructure consisting of connected and a...

Background Adverse pregnancy outcomes (APOs) affect a large proportion of pregnancies and represent an important cause of morbidity and mortality worldwide. Yet, the pathophysiology of APOs is poorly understood, limiting our ability to prevent and treat these conditions. Objective To search for genetic risk markers for four APOs, we performed geno...

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code that supports symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development tends to produce DL code that is error-prone...

In 2010, the Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) started the Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-be (nuMoM2b), a prospective cohort study of a racially/ethnically/geographically diverse population of nulliparous women with singleton gestation. The nuMoM2b is a very large da...

In this article, we present a decentralized convention formation framework for creating social conventions within large multiagent convention spaces. We study the role of the topological characteristics of the network in forming conventions with an emphasis on scale-free topologies. We hypothesize that contextual knowledge encapsulated in the topol...

It is well-known that selfish routing, where individual agents make uncoordinated greedy routing decisions, does not produce a socially desirable outcome in transport and communication networks. In this paper, we address this general problem of the loss of social welfare that occurs due to uncoordinated behavior in networks and model it as a multia...

We describe an application of machine learning to the problem of predicting preterm birth. We conduct a secondary analysis on a clinical trial dataset collected by the National In- stitute of Child Health and Human Development (NICHD) while focusing our attention on predicting different classes of preterm birth. We compare three approaches for deri...

In this paper, we design a distributed mechanism that is able to create a social convention within a large convention space for multiagent systems (MAS) operating on various topologies. Specifically, we investigate a language coordination problem in which agents in a dynamic MAS construct a common lexicon in a decentralized fashion. Agent interacti...

Resource management is a key challenge in multiagent systems. It is especially important in dynamic environments where decisions need to be made quickly and when decisions can get obsolete quickly. In wireless local area networks WLANs, resource management includes dynamic channel assignment, dynamic transmit power control and load balancing of WLA...

Preterm birth is a major public health problem with profound implications on society, there would be extreme value in being able to identify women at risk of preterm birth during the course of their pregnancy. Previous research has largely focused on individual risk factors correlated with preterm birth and less on combining these factors in a way...

Single convention convergence across different types of networks is a challenging multi-agent task. Our central hypothesis in this paper is that no simple distributed mechanism (such as the state-of-the-art Generalized Simple Majority (GSM) rule) can achieve this. We augment the agents with "network thinking" capability to solve this single convent...

In this paper, our goal is to achieve the emergence of cooperation in self-interested agent societies operating on highly connected scale-free networks. The novelty of this work is that agents are able to control topological features during the network formation phase. We propose a commitment-based dynamic coalition formation approach that result i...

Emergence of a single coalition among self-interested agents operating on large scale-free networks is a challenging task. Many existing approaches assume a given static network platform and do not use the network dynamics to facilitate the dynamics of agent interactions. In this paper, we present a decentralized game-theoretic approach to this sin...

Learning consistent policies in decentralized settings is often problematic. The agents have a myopic view of their neighboring states that could lead to inconsistent action choices. The fundamental question addressed in this work is how to determine and obtain the minimal overlapping context among decentralized decision makers required to make the...

It is crucial for embedded systems to adapt to the dynamics of open environments. This adaptation process becomes especially challenging in the context of multiagent systems. In this paper, we argue that multiagent meta-level control is an effective way to determine when this adaptation process should be done and how much effort should be invested...

This introductory chapter begins with a brief discussion of the concept of metareasoning. It then provides manifesto in an attempt to present in plain language and simple diagrams a description of a model of metareasoning that mirrors the action-selection and perception cycle in first-order reasoning. Many theories and implementations are covered b...

Experts report on the latest artificial intelligence research concerning reasoning about reasoning itself. The capacity to think about our own thinking may lie at the heart of what it means to be both human and intelligent. Philosophers and cognitive scientists have investigated these matters for many years. Researchers in artificial intelligence h...

Experts report on the latest artificial intelligence research concerning reasoning about reasoning itself. The capacity to think about our own thinking may lie at the heart of what it means to be both human and intelligent. Philosophers and cognitive scientists have investigated these matters for many years. Researchers in artificial intelligence h...

Experts report on the latest artificial intelligence research concerning reasoning about reasoning itself. The capacity to think about our own thinking may lie at the heart of what it means to be both human and intelligent. Philosophers and cognitive scientists have investigated these matters for many years. Researchers in artificial intelligence h...

The AAAI-10 Workshop program was held Sunday and Monday, July 11–12, 2010 at the Westin Peachtree Plaza in Atlanta, Georgia. The AAAI-10 workshop program included 13 workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were AI and Fun, Bridging the Gap between Task and Motion Planning, Collaboratively-Bu...

Significant increase in collected data for investigative tasks and the increased complexity of the reasoning process itself have made investigative analytical tasks more challenging. These tasks are time critical and typically involve identifying and tracking multiple hypotheses; gathering evidence to validate the correct hypotheses and eliminating...

It is crucial for embedded systems to adapt to the dynamics of open environments. This adaptation process becomes especially challenging in the context of multiagent systems. In this paper, we argue that multiagent meta-level control is an effective way to determine when this adaptation process should be done and how much effort should be invested...

The traffic load of wireless local area networks (WLANs) is often distributed unevenly among access points. In addition, interference from collocated wireless devices operating in the same unlicensed frequency band may cause WLANs to become unstable, leading to temporary failures of access points. This paper addresses the questions of how to dynami...

Embedded systems consisting of collaborating agents capable of interacting with their environment are becoming ubiquitous. It is crucial for these systems to be able to adapt to the dynamic and uncertain characteristics of an open environment. In this paper, we argue that multiagent meta-level control (MMLC) is an effective way to determine when th...

Embedded systems consisting of collaborating agents capable of interacting with their environment are becoming ubiquitous. It is crucial for these systems to be able to adapt to the dynamic and uncertain characteristics of an open environment. In this paper, we argue that multiagent meta-level control (MMLC) is an effective way to determine when th...

It is crucial for social systems to adapt to the dynamics of open environments. This adaptation process becomes espe-cially challenging in the context of multiagent systems. In this paper, we argue that multiagent meta-level control is an effective way to determine when this adaptation process should be done and how much effort should be invested i...

Mathematical models of complex processes provide precise definitions of the processes and facilitate the prediction of process behavior for varying contexts. In this paper, we present a numerical method for modeling the propagation of uncertainty in a multi-agent system (MAS) and a qualitative justification for this model. We discuss how this model...

Conservative design is the ability of an individual agent to ensure predictability of its overall performance even if some of its actions and interactions may be inherently less predictable or even completely unpredictable. In this paper, we describe the importance of conservative design in cooperative multi-agent systems and briefly characterize t...

Significant increase in collected data for analysis and the increased complexity of the reasoning process itself have made investigative analytical tasks more challenging. These tasks are time critical and typically involve identifying and tracking multiple hypotheses; gathering evidence to validate the correct hypotheses and to eliminate the incor...

Knowledge gathering and investigative tasks in open environments can be very complex because the problem-solving context is constantly evolving, and the data may be incomplete, unreliable and/or conflicting. This paper significantly extends our previous work on a mixed-initiative agent by making it capable of assisting humans in foraging task analy...

Knowledge gathering and investigative tasks in open environments can be very complex because the problem- solving context is constantly evolving, and the data may be incomplete, unreliable and/or conflicting. This paper significantly extends our previous work on a mixed- initiative agent by making it capable of assisting humans in foraging task ana...

There is a critical and urgent need for automated analytical agents operating in complex domains to provide meta-level explanations of their reasoning and conclusions. In this paper, we identify the princi-ples for designing analytical agents that can explain their reasoning and justify their conclusions at different levels of abstractions to poten...

Meta-level control manages the allocation of limited resources to deliberative actions. This paper discusses eorts in adding meta-level control capabilities to a Markov Decision Process (MDP)-based scheduling agent. The agent's reasoning pro- cess involves continuous partial unrolling of the MDP state space and periodic reprioritization of the stat...

This manifesto proposes a simple model of metareasoning that constitutes a general framework to organize research on this topic. The claim is that metareasoning, like the action-perception cycle of reasoning, is composed of the introspective monitoring of reasoning and the subsequent meta-level control of reasoning. This model holds for single agen...

Embedded systems consisting of collaborating agents capable of interacting with their environment are be- coming ubiquitous. It is crucial for these systems to be able to adapt to the dynamic and uncertain characteris- tics of an open environment. The question of when this adaptation process should be done and how much effort should be invested in...

Visual Analytics is the science of applying reasoning and analysis techniques to large, complex real-world data for problem solving using visualizations. Real world knowledge gathering and investigative tasks are very complex because the problem-solving context is constantly evolving, and the data may be incomplete, unreliable and/or conflicting. W...

Sophisticated agents operating in open environments must make decisions that efficiently trade off the use of their limited resources between dynamic deliberative actions and domain actions. This is the meta-level control problem for agents operating in resource-bounded multi-agent environments. Con- trol activities involve decisions on when to inv...

In this paper, we attempt to dene a generalized framework for meta-level control in multiagent systems. We generalize and extend previous work in single-agent meta-control. We discuss the issues which system designers must consider when designing an agent's meta-control component and conclude with areas for future research.

This paper investigates cooperative radio resource management for multiple cognitive radio networks in interference environments. The objective of this research is to manage shared radio resources fairly among multiple non- cooperative cognitive radio networks to optimize the overall performance. We emphasize the underlying predictability of networ...

Open environments are characterized by their uncertainty and non-determinism. Agents need to adapt their task processing to available resources, deadlines, the goal criteria specified by the clients as well their current problem solving context in order to survive in these environments. If there were no resource constraints, then an optimal Markov...

Abstract Agents operating in open environments must be able to adapt their processing to available resources, deadlines, their goal criteria, and their current problem solving con- texts. This paper describes the role of meta-cognition in this process; in particular, we dene a meta-cognition frame- work that uses Naive Bayesian classication of the...

Open environments are characterized by their uncer- tainty and non-determinism. This poses an inevitable challenge to the construction of agents operating in such environments. The agents need to adapt their process- ing to available resources, deadlines, the goal criteria specified by the clients as well as their current problem solving context in...

An essential task in critical infrastructure protection is the assessment of critical infrastructure vulnerabilities. The use of scenario sets is widely regarded as the best form for such assessments. Unfortunately, the construction of scenario sets is hindered by a lack in the public domain of critical infrastructure information as such informatio...

An essential task in critical infrastructure protection is the assessment of critical infrastructure vulnerabilities. The use of scenario sets is widely regarded as the best form for such assessments. Unfortunately, the construction of scenario sets is hindered by a lack in the public domain of critical infrastructure information as such informatio...

Wireless sensor networks (WSN) are a subset of wireless networking applications focused on enabling sensor and actuator connectivity without the use of wires. Energy consumption among the wireless devices participating in these networks is a major constraint on the deployment for a broad range of applications enabled by WSNs. This paper introduces,...

Deliberative agents operating in open environments must make complex real-time decisions on scheduling and coordination of domain activities. These decisions are made in the context of limited resources and uncertainty about the outcomes of activities. We describe a reinforcement learning based approach for efficient meta-level reasoning. Empirical...

The GPGP/TMS domain-independent coordination framework for small agent groups was first described in 1992 and then more fully detailed in an ICMAS'95 paper. In this paper, we discuss the evolution of this framework which has been motivated by its use in a number of applications, including: information gathering and management, intelligent home auto...

The protection of critical infrastructures, such as electrical power grids, has become a primary concern of many nation states in recent years. Critical infrastructures involve multi-dimensional, highly complex collections of technologies, processes, and people, and as such, are vulnerable to potentially catastrophic failures on many levels. Moreov...

An important issue for complex agents operating in open real-time environments is how to sequence execution and computation actions without consuming too many resources. An empirical approach to this meta-level control problem is presented. We show that explicit meta-level control leads to significant improvement in agent performance.

Complex agents operating in open environments must make real-time control decisions on schedul-ing and planning of domain actions. These deci-sions are made in the context of limited resources and uncertainty about outcomes of actions. The question of how to sequence domain and con-trol actions without consuming too many resources in the process is...

The World Wide Web has become an invaluable information resource but the explosion of available information has made Web search a time consuming and complex process. The large number of information sources and their different levels of accessibility, reliability and associated costs present a complex information gathering control problem. This pape...

Sophisticated agents operating in open environments must make complex real-time control decisions on scheduling and coordination of domain actions. These decisions are made in the context of limited resources and uncertainty about outcomes of actions. The question of how to sequence domain and control actions without consuming too many resources in...

The GPGP/TÆMS domain-independent coordination framework for small agent groups was first described almost ten years ago and then more fully detailed in an ICMAS95 paper. In this paper, we discuss the evolution of this framework over the last six years motivated by its use in a number of applications, including: information gathering and management,...

Sophisticated agents operating in open environments must make complex real-time control decisions on scheduling and coordination of domain activities. These decisions are made in the context of limited resources and uncertainty about outcomes of activities.

It is paramount for agent-based systems to adapt to the dynamics

. Open environments are characterized by their uncertainty and non-determinism. Sophisticated agents operating in these environments must reason about their local problem solving activities, interact with other agents, plan a course of action and carry out actions in the face of limited resources and uncertainty about action outcomes and the action...

Open environments are characterized by their uncertainty and nondeterminism. This poses an inevitable challenge to construction of agents which need to operate in such environments. The agents need to adapt their processing to available resources, deadlines, the goal criteria speci ed by the clients as well their current problem solving context in...

The World Wide Web has become an invaluable information resource but the explosion of available information has made Web search a time consuming and complex process. The large number of information sources and their different levels of accessibility, reliability and associated costs present a complex information gathering control problem. This pape...

Open environments are characterized by their uncertainty and non-determinism. Agents need to adapt their task processing to available resources, deadlines, the goal criteria specified by the clients as well their current problem solving context in order to survive in these environments. If there were no resource constraints, then an optimal Markov...

Coordination, which is the process that an agent reasons about its local actions and the (anticipated) actions of others to try to ensure the community acts in a coherent fashion, is an important issue in multi-agent systems. Coordination is a complicated process that typically consists of several operations: exchanging local information; detecting...

Multi-agent coordination is an important and complicated process. This paper proposes a layered approach to coordination in which lowlevel domain independent coordination and scheduling modules deal with detailed temporal and resource constraints and high-level controllers focus on domain issues and domain state. A general agent architecture is des...

BIG is a sophisticated, web-based, information gathering agent that recommends software packages. BIG plans, locates and processes free-format WWW documents via natural language processing and other text extraction techniques. BIG uses the processed information to create models of software products and then compares the models to the client's crite...

Multi-agent coordination is an important and complicated process. This paper proposes a layered approach to coordination in which lowlevel domain independent coordination and scheduling modules deal with detailed temporal and resource constraints and high-level controllers focus on domain issues and domain state. A general agent architecture is des...

Agent control involves reasoning about local problem solving activities, interacting with other agents, planning for a course of action and contingencies in the event of failure of the action and finally carrying out the actions with limited resources and uncertainty about agent outcomes and the actions of other agents. The growing complexity and d...

Intelligent environments are an interesting development and research application problem for multi-agent systems. The functional and spatial distribution of tasks naturally lends itself to a multi-agent model and the existence of shared resources creates interactions over which the agents must coordinate. In the UMASS Intelligent Home project we ha...

BIG (resource-Bounded Information Gathering) is a next generation information gathering agent which integrates several areas of Artificial Intelligence research under a single umbrella. To date, reported work has presented the rationale, architecture, and implementation of the system. This has included planning, reasoning about resource trade-offs...

Intelligent environments are an interesting development and research application problem for multi-agent systems. The functional and spatial distribution of tasks naturally lends itself to a multi-agent model and the existence of shared resources creates interactions over which the agents must coordinate. In the UMASS Intelligent Home project we ha...

The World Wide Web has become an invaluable information resource but the explosion of available information has made web search a time consuming and complex process. The large number of informa-tion sources and their different levels of accessibility, reliability and associated costs present a complex information gathering coordination problem. Thi...

Intelligent environments are an interesting development and research application problem for multiagent systems. The functional and spatial distribution of tasks naturally lends itself to a multi-agent model and the existence of shared resources creates interactions over which the agents must coordinate. In the UMASS Intelligent Home project we hav...

The Design-to-Criteria scheduler is a domain independent system that schedules complex AI problem solving tasks to meet real-time performance goals. In this paper, we further extend the scheduler to more effectively deal with uncertainty present in a schedule which can be critical in hard deadline or hard cost situations. This is based on an analys...

The World Wide Web has become an invaluable information resource but the explosion of information available via the web has made web search a time consuming and complex process. Index-based search engines, such as AltaVista or Infoseek help, but they are not enough. This paper describes the rationale, architecture, and implementation of a next gene...

Introduction The vast amount of information available today on the World Wide Web (WWW) has great potential to improve the quality of decisions and the productivity of consumers. However, the WWW's large number of information sources and their different levels of accessibility, reliability and associated costs present human decision makers with a c...