RRRamakrishnan Raman

Ramakrishnan Raman

*This is an algorithmically generated author record based on publicly available information.

Ramakrishnan Raman has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Towards a SMARTer Requirements: An AI-based Approach for Requirements Quality

    by Sharmila K.A., Ramakrishnan Raman

    It is well recognized that the quality of textual requirements plays a critical role in engineering of complex systems. When textual requirements suffer from issues such as ambiguity, inconsistency, and lack of verifiability, it causes significant issues in the systems engineering lifecycle of complex systems. This paper presents the design, development and fine-tuning of an AI-based system for evaluating and improving the quality of textual requirements. The system classifies requirements as either SMART or non-SMART based on established guidelines, such as the INCOSE Requirements Working Group rules. Using Natural Language Processing (NLP) techniques and a BERT based model, the system recognizes NON-SMART requirements and suggests improvements towards making the requirements more Specific, Measurable, Achievable, Relevant, and Time-bound (SMART). The AI workflow includes several stages: first, the requirements are preprocessed and tokenized using a BERT tokenizer. The model is then fine-tuned on a labeled dataset of SMART and NON-SMART requirements using binary classification. To ensure robustness and avoid overfitting, cross-validation is used, along with model evaluation through performance metrics like accuracy, precision, recall, and F1-score. Additionally, a rule-based system is integrated to detect violations of specific INCOSE rules, and specific suggestions are provided for converting NON-SMART requirements into SMART ones. Designed with modularity and integration in mind, the system supports interoperability with MBSE workflows by facilitating traceability, consistency checking, and the generation of structured artifacts from unstructured inputs. This capability enables a more seamless transition from textual requirements to formal models within MBSE environments. The system’s performance is evaluated using confusion matrices and tested on an independent dataset to validate its performance and generalizability. Preliminary results of the AI-based system demonstrate good accuracy, showing immense potential for adoption towards improving requirements quality across various domains and seamlessly transitioning to MBSE workflows.

  • Towards a SMARTer Requirements: An AI-based Approach for Requirements Quality

    by Sharmila K.A., Ramakrishnan Raman

    It is well recognized that the quality of textual requirements plays a critical role in engineering of complex systems. When textual requirements suffer from issues such as ambiguity, inconsistency, and lack of verifiability, it causes significant issues in the systems engineering lifecycle of complex systems. This paper presents the design, development and fine-tuning of an AI-based system for evaluating and improving the quality of textual requirements. The system classifies requirements as either SMART or non-SMART based on established guidelines, such as the INCOSE Requirements Working Group rules. Using Natural Language Processing (NLP) techniques and a BERT based model, the system recognizes NON-SMART requirements and suggests improvements towards making the requirements more Specific, Measurable, Achievable, Relevant, and Time-bound (SMART). The AI workflow includes several stages: first, the requirements are preprocessed and tokenized using a BERT tokenizer. The model is then fine-tuned on a labeled dataset of SMART and NON-SMART requirements using binary classification. To ensure robustness and avoid overfitting, cross-validation is used, along with model evaluation through performance metrics like accuracy, precision, recall, and F1-score. Additionally, a rule-based system is integrated to detect violations of specific INCOSE rules, and specific suggestions are provided for converting NON-SMART requirements into SMART ones. Designed with modularity and integration in mind, the system supports interoperability with MBSE workflows by facilitating traceability, consistency checking, and the generation of structured artifacts from unstructured inputs. This capability enables a more seamless transition from textual requirements to formal models within MBSE environments. The system’s performance is evaluated using confusion matrices and tested on an independent dataset to validate its performance and generalizability. Preliminary results of the AI-based system demonstrate good accuracy, showing immense potential for adoption towards improving requirements quality across various domains and seamlessly transitioning to MBSE workflows.

  • Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems

    by Ramakrishnan Raman, Nikhil Gupta, Yogananda Jeppu

    A complex system is characterized by emergence of global properties which are very difficult, if not impossible, to anticipate just from complete knowledge of component behaviors. Emergence, hierarchical organization, and numerosity are some of the characteristics of complex systems. Recently, there has been an exponential increase on the adoption of various neural network‐based machine learning models to govern the functionality and behavior of systems. With this increasing system complexity, achieving confidence in systems becomes even more difficult. Further, ease of interconnectivity among systems is permeating numerous system‐of‐systems, wherein multiple independent systems are expected to interact and collaborate to achieve unparalleled levels of functionality. Traditional verification and validation approaches are often inadequate to bring in the nuances of potential emergent behavior in a system‐of‐systems, which may be positive or negative. This paper describes a novel approach towards application of machine learning based classifiers and formal methods for analyzing and evaluating emergent behavior of complex system‐of‐systems that comprise a hybrid of constituent systems governed by conventional models and machine learning models. The proposed approach involves developing a machine learning classifier model that learns on potential negative and positive emergent behaviors, and predicts the behavior exhibited. A formal verification model is then developed to assert negative emergent behavior. The approach is illustrated through the case of a swarm of autonomous UAVs flying in a formation, and dynamically changing the shape of the formation, to support varying mission scenarios. The effectiveness and performance of the approach are quantified.

  • Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems

    by Ramakrishnan Raman, Nikhil Gupta, Yogananda Jeppu

    A complex system is characterized by emergence of global properties which are very difficult, if not impossible, to anticipate just from complete knowledge of component behaviors. Emergence, hierarchical organization, and numerosity are some of the characteristics of complex systems. Recently, there has been an exponential increase on the adoption of various neural network‐based machine learning models to govern the functionality and behavior of systems. With this increasing system complexity, achieving confidence in systems becomes even more difficult. Further, ease of interconnectivity among systems is permeating numerous system‐of‐systems, wherein multiple independent systems are expected to interact and collaborate to achieve unparalleled levels of functionality. Traditional verification and validation approaches are often inadequate to bring in the nuances of potential emergent behavior in a system‐of‐systems, which may be positive or negative. This paper describes a novel approach towards application of machine learning based classifiers and formal methods for analyzing and evaluating emergent behavior of complex system‐of‐systems that comprise a hybrid of constituent systems governed by conventional models and machine learning models. The proposed approach involves developing a machine learning classifier model that learns on potential negative and positive emergent behaviors, and predicts the behavior exhibited. A formal verification model is then developed to assert negative emergent behavior. The approach is illustrated through the case of a swarm of autonomous UAVs flying in a formation, and dynamically changing the shape of the formation, to support varying mission scenarios. The effectiveness and performance of the approach are quantified.


  • Experiences in Machine Learning Models for Aircraft Fuel Flow and Drag Polar Predictions

    by Ramakrishnan Raman, Rajesh Chaubey, Surendra Goswami, Radhakrishna Jella


  • Decision learning framework for architecture design decisions of complex systems and system‐of‐systems

    by Ramakrishnan Raman, Meenakshi D'SOuza

    Architecting complex systems and complex system‐of‐systems (SoS) have evinced keen interest recently. Architectural design decisions have a significant bearing on the operational measures of success, referred to as Measures of Effectiveness (MOEs), of the systems and SoS. Architecting complex systems and SoS involves making architecture design decisions despite uncertainty (due to knowledge gaps) on the implications associated with the decisions. The learning of whether the decision is optimal or not, and the impact on the MOEs and the emergent behavior of the SoS, often occur later, resulting in Learning Cycles. This paper proposes an integrated decision learning framework for architecture design decisions for complex systems and SoS. The proposed framework adopts a decision oriented view that factors the uncertainty associated with architectural decisions and the learning cycles and feedback loops experienced. The framework enables leverage of machine learning approaches to learn from the decision learning cycles experienced and factor it into the uncertainty assessments of the decisions. By inculcating various aspects such as knowledge gaps and learning cycles, by building models such as Learning Cycle Model and Uncertainty Model, and by incorporating deployment approaches such as codification of decision attributes and decision uncertainty assessments, the proposed framework enables progressive maturity of the architectural knowledge base and aids robustness in architecture design decisions.


  • An Approach for Formal Verification of Machine Learning based Complex Systems

    by Ramakrishnan Raman, Yogananda Jeppu

    A complex system is characterized by emergence of global properties which are very difficult, if not impossible, to anticipate just from complete knowledge of component behaviors. Emergence, hierarchical organization and numerosity are some of the characteristics of complex systems. With increasing system complexity, achieving confidence in systems becomes increasingly difficult. With the recent trend towards significant footprint of complex system's functionality being governed by machine learning based models and algorithms, there is a need to ensure that emergent behavior associated with such systems are well analyzed and understood. Traditional verification and validation approaches are often inadequate to bring in the nuances of potential emergent behavior, which may be positive or negative. This paper describes a novel approach towards application of formal methods for analyzing and evaluating emergent behavior of complex systems that are governed by machine learning models. The proposed approach involves developing a machine learning classifier model that learns on potential negative and positive emergent behaviors, and leveraging the classifier in a formal verification model checking environment to assert negative emergent behavior. The approach is illustrated through an example of a pitch control system of an aircraft. The effectiveness and performance of the approach are quantified.


  • Learning Framework For Maturing Architecture Design Decisions For Evolving Complex SoS

    by Ramakrishnan Raman, Meenakshi D’SOuza

    Architecting a complex System-of-Systems (SoS) poses significant challenges due to the uncertainty and perceptions associated with understanding the implications of constituent system's architecture design decisions at SoS level. Due to significant knowledge gaps, architects may find it difficult to uncover the ramifications of a specific decision on various Measures-of-Effectiveness (MOEs) and emergent behavior of the SoS. Subsequently, for complex SoS, learning cycles maybe experienced on the architecture design decisions. As the SoS evolves, these experiential learnings need to be factored into the uncertainty assessments of decisions and the impacted SoS MOEs, while evaluating and deciding on a specific decision. This paper proposes a knowledge based decision learning framework that factors the learning cycles experienced into the uncertainty associated with the decisions and impacted SoS MOEs. The framework takes into consideration, through an architectural knowledge base, multiple knowledge dimensions such as the attributes of the architecture design decision and the feedback loops experienced, in tandem with the complexity attributes and the knowledge gaps associated with the decision.