Kenneth MBale | Bowie State University (original) (raw)

Papers by Kenneth MBale

Abstract—Agents situated in dynamic environments have limited time to deliberate before performin... more Abstract—Agents situated in dynamic environments have limited time to deliberate before performing their actions. Cautious agents that deliberate for too long may miss deadlines to accomplish tasks whereas bold agents that deliberate for too little time may behave rashly or miss opportunities. There are several approaches discussed in the literature that rely on meta-level mechanisms to monitor and control the deliberation time. These approaches seem to follow the view that the meta-level mechanism is an external component not constrained by the same resource limitations as the underlying agent’s deliberation mechanism. In this paper, we present an approach to resource bounded metacognition wherein an agent monitors and controls its deliberation and metacognition within the uniform framework of Active Logic. Keywords-metacognition; deliberation; reasoning; active logic I.

2017 International Conference on Computational Science and Computational Intelligence (CSCI), 2017

The Kasai is an algorithm for processing data series. It organizes the incoming data series as a ... more The Kasai is an algorithm for processing data series. It organizes the incoming data series as a set of rules and these rules are used to predict the next item in the data series. In this paper, we analyze the ability of Kasai to make reliable predictions. We apply Kasai to predict weather using Weather Underground data and compare Kasai’s performance with standard Weka machine learning algorithms on the same dataset.

The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the ... more The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the patterns found in the data series. The rules represent a sound and compact abstraction of the data series that can be used for analysis, for reproduction of the original data series or for prediction. The Kasai Algorithm is an attempt to unify the symbolic and connectionist paradigm into a unified model.

Artificial agents need to adapt in order to perform effectively in situations outside of their no... more Artificial agents need to adapt in order to perform effectively in situations outside of their normal operation specifications. Agents that do not have the capability to adapt to unanticipated situations cannot recover from unforeseen failures and hence are brittle systems. One approach to deal with the brittleness problem is to have a metacognitive component that watches the performance of a host agent and suggests corrective actions to recover from failures. This paper presents the architecture of a metacognitive agent that can be integrated with any host cognitive agent so that the resulting system can dynamically create expectations about observations from a host agent’s sensors, and make use of these expectations to notice expectation violations, assess the cause of a violation and guide a correction if required to deal with the violation. The agent makes use of the metacognitive loop (MCL) and three generic ontologies -- indications of failures, causes of failures and response...

2018 International Conference on Computational Science and Computational Intelligence (CSCI), 2018

Electronic medical records and patient data sharing are critical and considered as core issues in... more Electronic medical records and patient data sharing are critical and considered as core issues in health care. How to store patient's information securely, how to access the information and how to ensure the privacy of patients when sharing medical data among several health service providers or agents are critical considerations. To handle those crucial considerations, a blockchain-based technology called Hyperledger Fabric will be useful. Hyperledger Fabric is a permissioned blockchain technology that provides a way to secure the interactions among a group of identified participants. In this paper, we will show how the implementation of Hyperledger Fabric to store, manage and maintain electronic medical records can ensure the security and the privacy of patient data.

Biologically Inspired Cognitive Architectures, 2018

Behavior adaptation is an integral aspect for autonomous agents to survive in a world where chang... more Behavior adaptation is an integral aspect for autonomous agents to survive in a world where change is normal. Animals change their foraging routines and socializing habits based on predator risks in their environment. Humans adapt their behavior based on current interests, social norms, stress level, health conditions, upcoming deadlines and various other factors. Artificial agents need to effectively adapt to changes in their environment such that they can quickly adjust their behavior to maintain performance in the changed environment. In this paper, we present a multi-level metacognitive model that allows agents to adapt their behavior in various ways based on the resources available for metacognitive processing. As the agent operates at higher levels of this model, the agent is better equipped to adapt to a wider range of changes. The model has been tested on 2 different applications: (i) a reinforcement learner-based agent trying to navigate and collect rewards in a seasonal grid-world environment and (ii) a convolutional neural network-based agent trying to classify the signals in a radio frequency spectrum world and separate them into known modulations and unknown modulations.

Procedia Computer Science, 2016

GPME enhances the function of host agents by enabling them to develop and apply advanced behavior... more GPME enhances the function of host agents by enabling them to develop and apply advanced behaviors. In this paper, we demonstrate the subset of GPME algorithms that are used to identify host behaviors from a time-series of perceptions about host observations and host actions.

This paper summarizes a work in progress in the area of the metacognitive loop (MCL). The objecti... more This paper summarizes a work in progress in the area of the metacognitive loop (MCL). The objective of MCL is to provide a design approach supported by software to extend an intelligent system’s ability to cope with perturbations. A perturbation is any deviation from optimal performance for the system. Many MCL implementations exist, each increasing in sophistication. This paper describes an approach to produce the next implementation of MCL, which we call the General Purpose Metacognition Engine (GPME). The GPME evolves the functionality of the current implementation developed at the University of Maryland, MCL2, in particular, to handle seasonality. Seasonality is a periodic or cyclic variation in conditions that causes agents to re-learn when the length of the seasonal cycle exceeds their ability to detect the cycle. Keywords-Metacognition;Learning;Reasoning;Situated Agents;Autonomous Agents.

Behavior adaptation is an integral aspect for autonomous agents to survive in a world where chang... more Behavior adaptation is an integral aspect for autonomous agents to survive in a world where change is normal. Animals change their foraging routines and socializing habits based on predator risks in their environment. Humans adapt their behavior based on current interests, social norms, stress level, health conditions, upcoming deadlines and various other factors. Artificial agents need to effectively adapt to changes in their environment such that they can quickly adjust their behavior to maintain performance in the changed environment. In this paper, we present a multi-level metacognitive model that allows agents to adapt their behavior in various ways based on the resources available for metacognitive processing. As the agent operates at higher levels of this model, the agent is better equipped to adapt to a wider range of changes. The model has been tested on 2 different applications: (i) a reinforcement learner-based agent trying to navigate and collect rewards in a seasonal grid-world environment and (ii) a convolutional neural network-based agent trying to classify the signals in a radio frequency spectrum world and separate them into known modulations and unknown modulations.

IEEE CSCI 2017, 2017

The Kasai is an algorithm for processing data series. It organizes the incoming data series as a ... more The Kasai is an algorithm for processing data series. It organizes the incoming data series as a set of rules and these rules are used to predict the next item in the data series. In this paper, we analyze the ability of Kasai to make reliable predictions. We apply Kasai to predict weather using Weather Underground data and compare Kasai's performance with standard Weka machine learning algorithms on the same dataset.

From our experience performing systems modernization projects, we identify three broad approaches... more From our experience performing systems modernization projects, we identify three broad approaches to modernization: process-driven, data-driven, and code base reconditioning.

The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the ... more The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the patterns found in the data series. The rules represent a sound and compact abstraction of the data series that can be used for analysis, for reproduction of the original data series or for prediction. The Kasai Algorithm is an attempt to unify the symbolic and connectionist paradigm into a unified model.

The three leading frameworks, SAFe, DAD, and LeSS, seek to scale one of the most popular Agile me... more The three leading frameworks, SAFe, DAD, and LeSS, seek to scale one of the most popular Agile methodologies, Scrum, to enable it for large projects. Scrum and Agile methodologies have increased the effectiveness of software development teams. However, Agile methodologies often have to be augmented by other measures to scale up properly to large projects, where an organization has up to 100 or more software developers, analysts, and testers. Team size increases communication and organizational risks on Agile delivery teams. All of the Agile frameworks require high maturity processes to control the complexities of working with a large program.

Agile Transformations require organizational commitment and a high level of process maturity. SCi... more Agile Transformations require organizational commitment and a high level of process maturity. SCi has undertaken the same change internally and within projects we execute for our customers. We are highly qualified to guide organizations through this cultural transformation. SCi incorporates Agile principles within our vision and mission. All corporate and commercial functions employ the same Agile approach for managing the work. The key lesson learned from our decade-long adoption of Agile principles is that Agile requires a sound structure to operate within, and a robust management foundation. The management foundation we employ, and recommend for our customers, is the Capability Maturity Model Integrated (CMMI). Our Agile approach has been independently appraised at CMMI maturity level 4. CMMI can be used to guide process improvement across a project, a division, or an entire organization.

GPME enhances the function of host agents by enabling them to develop and apply advanced behavior... more GPME enhances the function of host agents by enabling them to develop and apply advanced behaviors. In this paper, we demonstrate the subset of GPME algorithms that are used to identify host behaviors from a time-series of perceptions about host observations and host actions.

The paper presents the architecture of a general-purpose metacognition engine. It is a software a... more The paper presents the architecture of a general-purpose metacognition engine. It is a software agent that collaborates with a host to provide it with metacognitive capabilities. The objective is for the combined system to exhibit adaptive intelligent behavior.

At higher levels of abstraction, there are finite and limited ways in which agents can fail. Ther... more At higher levels of abstraction, there are finite and limited ways in which agents can fail. Therefore, it is possible to create a general purpose agent that notes anomalies, assesses them and guides responses. The metacognitive loop (MCL) agent aims to achieve this objective using three ontologies; indications, failures and responses. Continued applications of the MCL agent to increasingly more complex situations requires that the MCL agent be equipped with a flexible interface that enables integration with a variety of cognitive agents without programming, and, with a persistence capability that independently and actively monitors expectations over time as well as generate expectations dynamically. This paper describes the work undertaken to produce MCL3, a general purpose metacognitive agent that builds upon the existing MCL2 implementation.

Cognitive 2013, May 27, 2013

Agents situated in dynamic environments have limited time to deliberate before performing their a... more Agents situated in dynamic environments have
limited time to deliberate before performing their actions.
Cautious agents that deliberate for too long may miss deadlines
to accomplish tasks whereas bold agents that deliberate for
too little time may behave rashly or miss opportunities. There
are several approaches discussed in the literature that rely on
meta-level mechanisms to monitor and control the deliberation
time. These approaches seem to follow the view that the metalevel
mechanism is an external component not constrained
by the same resource limitations as the underlying agents
deliberation mechanism. In this paper, we present an approach
to time-bounded metacognition wherein an agent monitors and
controls its deliberation and metacognition within the uniform
framework of Active Logic.

Abstract—Agents situated in dynamic environments have limited time to deliberate before performin... more Abstract—Agents situated in dynamic environments have limited time to deliberate before performing their actions. Cautious agents that deliberate for too long may miss deadlines to accomplish tasks whereas bold agents that deliberate for too little time may behave rashly or miss opportunities. There are several approaches discussed in the literature that rely on meta-level mechanisms to monitor and control the deliberation time. These approaches seem to follow the view that the meta-level mechanism is an external component not constrained by the same resource limitations as the underlying agent’s deliberation mechanism. In this paper, we present an approach to resource bounded metacognition wherein an agent monitors and controls its deliberation and metacognition within the uniform framework of Active Logic. Keywords-metacognition; deliberation; reasoning; active logic I.

2017 International Conference on Computational Science and Computational Intelligence (CSCI), 2017

The Kasai is an algorithm for processing data series. It organizes the incoming data series as a ... more The Kasai is an algorithm for processing data series. It organizes the incoming data series as a set of rules and these rules are used to predict the next item in the data series. In this paper, we analyze the ability of Kasai to make reliable predictions. We apply Kasai to predict weather using Weather Underground data and compare Kasai’s performance with standard Weka machine learning algorithms on the same dataset.

The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the ... more The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the patterns found in the data series. The rules represent a sound and compact abstraction of the data series that can be used for analysis, for reproduction of the original data series or for prediction. The Kasai Algorithm is an attempt to unify the symbolic and connectionist paradigm into a unified model.

Artificial agents need to adapt in order to perform effectively in situations outside of their no... more Artificial agents need to adapt in order to perform effectively in situations outside of their normal operation specifications. Agents that do not have the capability to adapt to unanticipated situations cannot recover from unforeseen failures and hence are brittle systems. One approach to deal with the brittleness problem is to have a metacognitive component that watches the performance of a host agent and suggests corrective actions to recover from failures. This paper presents the architecture of a metacognitive agent that can be integrated with any host cognitive agent so that the resulting system can dynamically create expectations about observations from a host agent’s sensors, and make use of these expectations to notice expectation violations, assess the cause of a violation and guide a correction if required to deal with the violation. The agent makes use of the metacognitive loop (MCL) and three generic ontologies -- indications of failures, causes of failures and response...

2018 International Conference on Computational Science and Computational Intelligence (CSCI), 2018

Electronic medical records and patient data sharing are critical and considered as core issues in... more Electronic medical records and patient data sharing are critical and considered as core issues in health care. How to store patient's information securely, how to access the information and how to ensure the privacy of patients when sharing medical data among several health service providers or agents are critical considerations. To handle those crucial considerations, a blockchain-based technology called Hyperledger Fabric will be useful. Hyperledger Fabric is a permissioned blockchain technology that provides a way to secure the interactions among a group of identified participants. In this paper, we will show how the implementation of Hyperledger Fabric to store, manage and maintain electronic medical records can ensure the security and the privacy of patient data.

Biologically Inspired Cognitive Architectures, 2018

Behavior adaptation is an integral aspect for autonomous agents to survive in a world where chang... more Behavior adaptation is an integral aspect for autonomous agents to survive in a world where change is normal. Animals change their foraging routines and socializing habits based on predator risks in their environment. Humans adapt their behavior based on current interests, social norms, stress level, health conditions, upcoming deadlines and various other factors. Artificial agents need to effectively adapt to changes in their environment such that they can quickly adjust their behavior to maintain performance in the changed environment. In this paper, we present a multi-level metacognitive model that allows agents to adapt their behavior in various ways based on the resources available for metacognitive processing. As the agent operates at higher levels of this model, the agent is better equipped to adapt to a wider range of changes. The model has been tested on 2 different applications: (i) a reinforcement learner-based agent trying to navigate and collect rewards in a seasonal grid-world environment and (ii) a convolutional neural network-based agent trying to classify the signals in a radio frequency spectrum world and separate them into known modulations and unknown modulations.

Procedia Computer Science, 2016

GPME enhances the function of host agents by enabling them to develop and apply advanced behavior... more GPME enhances the function of host agents by enabling them to develop and apply advanced behaviors. In this paper, we demonstrate the subset of GPME algorithms that are used to identify host behaviors from a time-series of perceptions about host observations and host actions.

This paper summarizes a work in progress in the area of the metacognitive loop (MCL). The objecti... more This paper summarizes a work in progress in the area of the metacognitive loop (MCL). The objective of MCL is to provide a design approach supported by software to extend an intelligent system’s ability to cope with perturbations. A perturbation is any deviation from optimal performance for the system. Many MCL implementations exist, each increasing in sophistication. This paper describes an approach to produce the next implementation of MCL, which we call the General Purpose Metacognition Engine (GPME). The GPME evolves the functionality of the current implementation developed at the University of Maryland, MCL2, in particular, to handle seasonality. Seasonality is a periodic or cyclic variation in conditions that causes agents to re-learn when the length of the seasonal cycle exceeds their ability to detect the cycle. Keywords-Metacognition;Learning;Reasoning;Situated Agents;Autonomous Agents.

Behavior adaptation is an integral aspect for autonomous agents to survive in a world where chang... more Behavior adaptation is an integral aspect for autonomous agents to survive in a world where change is normal. Animals change their foraging routines and socializing habits based on predator risks in their environment. Humans adapt their behavior based on current interests, social norms, stress level, health conditions, upcoming deadlines and various other factors. Artificial agents need to effectively adapt to changes in their environment such that they can quickly adjust their behavior to maintain performance in the changed environment. In this paper, we present a multi-level metacognitive model that allows agents to adapt their behavior in various ways based on the resources available for metacognitive processing. As the agent operates at higher levels of this model, the agent is better equipped to adapt to a wider range of changes. The model has been tested on 2 different applications: (i) a reinforcement learner-based agent trying to navigate and collect rewards in a seasonal grid-world environment and (ii) a convolutional neural network-based agent trying to classify the signals in a radio frequency spectrum world and separate them into known modulations and unknown modulations.

IEEE CSCI 2017, 2017

The Kasai is an algorithm for processing data series. It organizes the incoming data series as a ... more The Kasai is an algorithm for processing data series. It organizes the incoming data series as a set of rules and these rules are used to predict the next item in the data series. In this paper, we analyze the ability of Kasai to make reliable predictions. We apply Kasai to predict weather using Weather Underground data and compare Kasai's performance with standard Weka machine learning algorithms on the same dataset.

From our experience performing systems modernization projects, we identify three broad approaches... more From our experience performing systems modernization projects, we identify three broad approaches to modernization: process-driven, data-driven, and code base reconditioning.

The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the ... more The Kasai Algorithm analyzes non-random data series to derive a set of rules that represents the patterns found in the data series. The rules represent a sound and compact abstraction of the data series that can be used for analysis, for reproduction of the original data series or for prediction. The Kasai Algorithm is an attempt to unify the symbolic and connectionist paradigm into a unified model.

The three leading frameworks, SAFe, DAD, and LeSS, seek to scale one of the most popular Agile me... more The three leading frameworks, SAFe, DAD, and LeSS, seek to scale one of the most popular Agile methodologies, Scrum, to enable it for large projects. Scrum and Agile methodologies have increased the effectiveness of software development teams. However, Agile methodologies often have to be augmented by other measures to scale up properly to large projects, where an organization has up to 100 or more software developers, analysts, and testers. Team size increases communication and organizational risks on Agile delivery teams. All of the Agile frameworks require high maturity processes to control the complexities of working with a large program.

Agile Transformations require organizational commitment and a high level of process maturity. SCi... more Agile Transformations require organizational commitment and a high level of process maturity. SCi has undertaken the same change internally and within projects we execute for our customers. We are highly qualified to guide organizations through this cultural transformation. SCi incorporates Agile principles within our vision and mission. All corporate and commercial functions employ the same Agile approach for managing the work. The key lesson learned from our decade-long adoption of Agile principles is that Agile requires a sound structure to operate within, and a robust management foundation. The management foundation we employ, and recommend for our customers, is the Capability Maturity Model Integrated (CMMI). Our Agile approach has been independently appraised at CMMI maturity level 4. CMMI can be used to guide process improvement across a project, a division, or an entire organization.

GPME enhances the function of host agents by enabling them to develop and apply advanced behavior... more GPME enhances the function of host agents by enabling them to develop and apply advanced behaviors. In this paper, we demonstrate the subset of GPME algorithms that are used to identify host behaviors from a time-series of perceptions about host observations and host actions.

The paper presents the architecture of a general-purpose metacognition engine. It is a software a... more The paper presents the architecture of a general-purpose metacognition engine. It is a software agent that collaborates with a host to provide it with metacognitive capabilities. The objective is for the combined system to exhibit adaptive intelligent behavior.

At higher levels of abstraction, there are finite and limited ways in which agents can fail. Ther... more At higher levels of abstraction, there are finite and limited ways in which agents can fail. Therefore, it is possible to create a general purpose agent that notes anomalies, assesses them and guides responses. The metacognitive loop (MCL) agent aims to achieve this objective using three ontologies; indications, failures and responses. Continued applications of the MCL agent to increasingly more complex situations requires that the MCL agent be equipped with a flexible interface that enables integration with a variety of cognitive agents without programming, and, with a persistence capability that independently and actively monitors expectations over time as well as generate expectations dynamically. This paper describes the work undertaken to produce MCL3, a general purpose metacognitive agent that builds upon the existing MCL2 implementation.

Cognitive 2013, May 27, 2013

Agents situated in dynamic environments have limited time to deliberate before performing their a... more Agents situated in dynamic environments have
limited time to deliberate before performing their actions.
Cautious agents that deliberate for too long may miss deadlines
to accomplish tasks whereas bold agents that deliberate for
too little time may behave rashly or miss opportunities. There
are several approaches discussed in the literature that rely on
meta-level mechanisms to monitor and control the deliberation
time. These approaches seem to follow the view that the metalevel
mechanism is an external component not constrained
by the same resource limitations as the underlying agents
deliberation mechanism. In this paper, we present an approach
to time-bounded metacognition wherein an agent monitors and
controls its deliberation and metacognition within the uniform
framework of Active Logic.

Intelligence is the ability to acquire behavior through observation of the environment, including... more Intelligence is the ability to acquire behavior through observation of the environment, including other individuals, and to select the correct behavior in response to stimuli emanating from the environment. In this dissertation, we describe the Behavior Oriented Intelligence framework, with a focus on the abstract data type that supports the knowledge base of a behavior oriented artificial intelligence.