Usef Faghihi

Usef Faghihi
Sul Ross State University · Computer Science

Ph.D.

About

50
Publications
13,630
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
676
Citations
Citations since 2017
7 Research Items
434 Citations
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
2017201820192020202120222023020406080
Introduction
Skills and Expertise
Additional affiliations
January 2011 - present
The University of Memphis
Position
  • Professor (Assistant)
July 2006 - July 2011
Université du Québec à Montréal
Position
  • Researcher

Publications

Publications (50)
Preprint
Full-text available
In this paper, we introduce a new causal framework capable of dealing with probabilistic and non-probabilistic problems. Indeed, we provide a formula called Probabilistic vAriational Causal Effect (PACE). Our formula of causal effect uses the idea of total variation of a function integrated with probability theory. PACE has a parameter $d$ determin...
Chapter
Researchers and engineers may use inferential logic and/or fuzzy logic to solve real-world causal problems. Inferential logic uses probability theories, while fuzzy logic uses its membership functions and set theories to process uncertainty and fuzziness of the events. To benefit from both logics, some researchers in the past tried to create probab...
Chapter
In causal reasoning, one uses previous information about an event or situation to attempt to predict its future state. To create explainable AI tools, first, we need to integrate reasoning into the machine. Recently, many researchers in artificial intelligence (AI) have been interested in implementing causality in the machine. Some researchers sugg...
Chapter
Today, deep learning (DL) algorithms are intertwined with our daily life. This subdomain of artificial intelligence (AI) technology is used to unlock your phone by only detecting your face, find the best path from work to your home or vice versa, or detect anomalies in the human cells taken for lab tests. Yet, although AI technology is helping in m...
Article
When a health practitioner is at the bedside of a patient suffering from chronic pain and a psychiatric comorbid condition, he is facing a true clinical conundrum. The comorbidity is frequent yet poorly understood, the diagnosis is difficult and the treatment that follows is less than appropriate. Pain conditions and psychiatric disorders have cust...
Article
Full-text available
Natural selection has imbued biological agents with motivations moving them to act for survival and reproduction, as well as to learn so as to support both. Artificial agents also require motivations to act in a goal-directed manner and to learn appropriately into various memories. Here we present a biologically inspired motivation system, based on...
Chapter
Full-text available
Applying game-like mechanics in non-game software is a technique known as gamification. Gaming environments have been used to teach mathematical topics such as addition and division in a fun manner. However, given the difficulty of mathematical concepts, especially at the college level, it is very difficult to make software that can be considered b...
Conference Paper
Full-text available
Mining high-utility itemsets (HUIs) is a key data mining task. It consists of discovering groups of items that yield a high profit in transaction databases. A major drawback of traditional high-utility itemset mining algorithms is that they can return a large number of HUIs. Analyzing a large result set can be very time-consuming for users. To addr...
Article
Full-text available
Over a decade in the making and described in some seventy-five published papers, the LIDA cognitive model is comprehensive, complex, and hard to "wrap one's head around". Here we offer, in tutorial fashion, a current, relatively complete and somewhat detailed, description of the conceptual LIDA model, with pointers to more complete accounts of indi...
Chapter
Modern tools and methods of cognitive science, such as brain imaging or computational modeling, can provide new insights for age-old philosophical questions regarding the nature of temporal experience. This chapter aims to provide an overview of functional consciousness and time perception in brains and minds (Section 8.2), and to describe a comput...
Article
Spinal cord injury (SCI) leads to increased anxiety and depression in as many as 60% of patients. Yet, despite extensive clinical research focused on understanding the variables influencing psychological well-being following SCI, risk factors that decrease it remain unclear. We hypothesized that excitation of the immune system, inherent to SCI, may...
Article
Full-text available
Gaming environments have been used to teach mathematical topics such as addition and division in a fun manner*. However, when it comes to college level mathematical concepts such as the use of the quadratic formula, there are very few software that explain these concepts in a fun way. In this paper, we present a first step towards using video game...
Article
Daniel Kahneman (2011) posits two main processes that characterize thinking: “System 1” is a fast decision making system responsible for intuitive decision making based on emotions, vivid imagery, and associative memory. “System 2” is a slow system that observes System 1’s outputs, and intervenes when “intuition” is insufficient. Such an interventi...
Conference Paper
Full-text available
The Itemset Tree is an efficient data structure for performing targeted queries for itemset mining and association rule mining. It is incrementally up-datable by inserting new transactions and it provides efficient querying and up-dating algorithms. However, an important limitation of the IT structure, con-cerning scalability, is that it consumes a...
Article
Full-text available
To assist learners during problem-solving activities, an intelligent tutoring system (ITS) has to be equipped with domain knowledge that can support appropriate tutoring services. Providing domain knowledge is usually done by adopting one of the following paradigms: building a cognitive model, specifying constraints, integrating an expert system, a...
Chapter
To provide a rich learning experience, an intelligent tutoring agent should be able to take into account past and present events, and to learn from its interactions with learners to continuously improve the assistance it provides. Until now, the learning capabilities of tutoring agents in educational technologies have been generally very limited. I...
Article
Biologically inspired cognitive architectures should faithfully model the high-level modules and processes of cognitive neuroscience. Also, they are expected to contribute to the BICA “challenge of creating a real-life computational equivalent of the human mind”. One important component of the mind is attention and attentional learning. In this pap...
Article
A biologically inspired cognitive architecture must draw its insights from what is known from animal (including human) cognition. Such architectures should faithfully model the high-level modules and processes of cognitive neuroscience. Also, biologically inspired cognitive architectures are expected to contribute to the BICA ‘‘challenge of creatin...
Conference Paper
Full-text available
Building an intelligent tutoring system requires to define an expertise model that can support appropriate tutoring services. This is usually done by adopting one of the following paradigms: building a cognitive model, specifying constraints, integrating an expert system and using data mining algorithms to learn domain knowledge. However, for some...
Article
Full-text available
Sequential rule mining is an important data mining task used in a wide range of applications. However, current algorithms for discovering sequential rules common to several sequences use very restrictive definitions of sequential rules, which make them unable to recognize that similar rules can describe a same phenomenon. This can have many undesir...
Chapter
Artificial intelligence (AI) initially aimed at creating “thinking machines,” that is, computer systems having human level general intelligence. However, AI research has until recently focused on creating intelligent, but highly domain-specific, systems. Currently, researchers are again undertaking the original challenge of creating AI systems (age...
Article
Full-text available
In this article, we propose the Conscious-Emotional Learning Tutoring System technology, a biologically plausible cognitive agent based on human brain functions. This agent is capable of learning and remembering events and any related information such as corresponding procedures, stimuli and their emotional valences. In our model, emotions play a r...
Conference Paper
Full-text available
To build an intelligent tutoring system, a key task is to define an expertise model that can support appropriate tutoring services. However, for some ill-defined domains, classical approaches for representing expertise do not work well. To address this issue, we illustrate in this paper a novel approach which is to combine several approaches into a...
Conference Paper
An important research problem for developing complex cognitive agents is to provide them with human-like learning mechanisms. One important type of learning among episodic, emotional, and procedural learning is causal learning. In current cognitive agents, causal learning has up to now been implemented with techniques such as Bayesian networks that...
Conference Paper
Full-text available
To mimic human tutor and provide optimal training, an intelligent tutoring agent should be able to continuously learn from its interactions with learners. Up to now, the learning capabilities of tutoring agents in educational systems have been generally very limited. In this paper, we address this issue with CELTS, a cognitive tutoring agent, whose...
Conference Paper
In this document, we propose a health care system which could allow physicians to monitor their patients' leg muscle activity in real time while the patient is at home. Patients receive prompt advice and necessary information from a tutoring agent (a computer program on a home computer or mobile device) that is in direct communication with a physic...
Conference Paper
This paper describes a Conscious Tutoring System (CTS) capable of dynamic fine-tuned assistance to users. We put forth the combination of a Causal Learning and Emotional learning mechanism within CTS that will allow it to first establish, through data mining algorithms, gross user group models. CTS then uses these models to find the cause of mistak...
Article
Full-text available
This paper describes a computational model for the implementation of causal learning in cognitive agents. The Conscious Emotional Learning Tutoring System (CELTS) is able to provide dynamic fine-tuned assistance to users. The integration of a Causal Learning mechanism within CELTS allows CELTS to first establish, through a mix of data mining algori...
Conference Paper
Full-text available
In this paper, we show how to make a cognitive tutoring agent capable of precise causal reasoning by integrating constraints with data mining algorithms. Putting constraints on recorded interactions between the agent and learners during learning activities allows data mining algorithms to extract the causes of the learners' problems. Subsequently,...
Conference Paper
We investigate the value of bringing emotional components into cognitive architectures. We start by presenting CELTS, an emotional cognitive architecture, with an aim at showing that the emotional component of the architecture is an essential element of CELTS value as a cognitive architecture. We do so by analyzing the role that the emotional mecha...
Article
To mimic human tutors and provide optimal training, a cognitive tutoring agent should be able to continuously learn from its interactions with learners. An important element that helps a tutor better understand learner’s mistake is finding the causes of the learners’ mistakes. In this paper, we explain how we have designed and integrated a causal l...
Article
Full-text available
Les tuteurs professionnels humains sont capables de prendre en considération des événements du passé et du présent et ont une capacité d'adaptation en fonction d'événements sociaux. Afin d'être considéré comme une technologie valable pour l'amélioration de l'apprentissage humain, un agent cognitif artificiel devrait pouvoir faire de même. Puisque l...
Article
Full-text available
We propose to mine temporal patterns in Intelligent Tutoring Systems (ITSs) to uncover useful knowledge that can enhance their ability to provide assistance. To discover patterns, we suggest using a custom, sequential pattern-mining algorithm. Two ways of applying the algorithm to enhance an ITS's capabilities are addressed. The first is to extract...
Conference Paper
This paper describes a Conscious Tutoring System (CTS) capable of dynamic fine-tuned assistance to users. We put forth the combination of a Causal Learning and Emotional learning mechanism within CTS that will allow it to first establish, through data mining algorithms, gross user group models. CTS then uses these models to find the cause of mistak...
Conference Paper
This paper describes a Conscious Tutoring System (CTS) capable of dynamic fine-tuned assistance to users. We put forth the integration of an Episodic Learning mechanism within CTS that allows it to first establish, through data mining algorithms, gross user group models. CTS then uses these models to classify incoming users, evaluate their performa...
Chapter
Full-text available
In this paper, we propose to build agents that learn by observing other agents performing a task by extracting frequent temporal patterns from their behavior. We propose a learning mechanism consisting of three phases: (1) recording other agents’ behavior, (2) mining temporal patterns from this data and (3) utilizing the resulting knowledge. We ill...
Conference Paper
Full-text available
In this paper we propose the CTS (concious tutoring system) technology, a biologically plausible cognitive agent based on human brain functions.This agent is capable of learning and remembering events and any related information such as corresponding procedures, stimuli and their emotional valences. Our proposed episodic memory and episodic learnin...
Chapter
Full-text available
We propose two mechanisms for agent learning based on the idea of mining temporal patterns from agent behavior. The first one consists of extracting temporal patterns from the perceived behavior of other agents accomplishing a task, to learn the task. The second learning mechanism consists in extracting temporal patterns from an agent’s own behavio...
Conference Paper
Research in human neurobiology sustains the idea that emotions play a role, sometimes crucial, in most decisions and actions taken. Every input from perceptual mechanism passes through the amygdala before affecting action selection, sometimes temporarily bypassing detailed cortical interpretation. We describe our reproduction of these emotional mec...
Conference Paper
Full-text available
We here describe some essential and fundamental learning mechanisms, both "conscious and unconscious". The proposed architecture is based on functional "consciousness" mechanisms. In this paper, we suggest an emotional learning mechanism (ELM) model, which can both learn new events and influence different types of "conscious" and "unconscious" lear...
Conference Paper
Full-text available
In most contexts, learning is essential for the long-term autonomy of an agent. We describes here some essential and fundamental learning mechanisms implemented in a cognitive autonomous agent, CTS (Conscious Tutoring System), we suggest a model that maintains “conscious-” and at the same time "unconscious-" learning as means to increase the agent’...
Conference Paper
We describe two fundamental learning mechanisms implemented in a cognitive autonomous agent, CTS (conscious tutoring system). They are meant to allow the ITS discover regularities (frequent situations and contexts), and improve its reaction time.
Article
Les systèmes tuteurs intelligents sont considérés comme un remarquable concentré de technologies qui permettent un processus d'apprentissage. Ces systèmes sont capables de jouer le rôle d'assistants voire même de tuteur humain. Afin d'y arriver, ces systèmes ont besoin de maintenir et d'utiliser une représentation interne de l'environnement. Ainsi,...

Network

Cited By

Projects

Project (1)
Project
Hi David et al, I'm delighted that others are interested. When I got started thinking about the scientific evidence wrt consciousness, it was (a) taboo, and (b) interpreted in very specific ways. For example, a common euphemism was "perception" _ because that was safe. But when you compare cs vs. ucs perception (as in backward masking) you get visual cortex activation with lower amplitude and spread, as shown by Dehaene and colleagues. That tell us something new, and I believe it replicates for audition. (Systematic replications should be much more common). Another problem was circular explanation. "Conscious access" was called "awareness" or "attention to" something. But that explains nothing UNLESS you have an independent source of evidence to break the circularity. Other confusions were rife. The conscious (waking) STATE was confused with consciousness OF something. Visual imagery was not fully recognized until Steve Kosslyn, and so on. Attention was used interchangeably with consciousness. All that has cleared up now, either explicitly, or implicitly, by usage. For example, my impression is that attention is used for voluntary control of access to some conscious content. As in voluntary head movements, but not for spontaneous, unconsciously directed eye movements (most fast eye movements are that). As long as these practical usages are clear, they are good enough to avoid confusion. Recent work coming from animal and human electrophysiogy is fabulous. Buszaki's book is important reading. Invasive e-physiology has 1000x the S/N ratio as scalp recording. Both deep sleep and waking look strikingly different at that resolution. Animal researchers have known that for years, but human e-phys researchers were held back by the ethical constraints of working with humans. Penfield was right. Other methodologies are reaching that kind of spatiotemporal resolution, and have their own pros and cons, of course. Our 2013 Frontiers overview still holds water, mostly. My Scholarpedia article is still mostly up to date. But the frontier is moving fast. It's very exciting. Theorists need to integrate the wealth of evidence, clarify ambiguous usages and confusions, and so on. There are still many of them. I believe our theory writing needs much improvement, with the emphasis on INDUCTIVE thinking. (Some writers seem to think this is a form of math, but that's indefensible empirically). A recent article confused the brainstem nuclei involved with the STATE of consciousness with the mostly cortical regions that support CONTENTS of consciousness, like the ventral visual stream. There is appropriate debate about the region of visual integration (MTL or PFC? or both?). I guess I'm a "corticocentrist," but that does NOT rule out other regions, especially given the long evolutionary history of csns -- at least 200 million years for neocortex. Walter Freeman, our late friend, convinced me that paleocortex (incl hippocampus) has to be involved with gustatory-olfactory consciousness. The work on the anterior insula strongly implicates interoceptive consciousness, as in feelings of nausea. Generalization between species is now much more convincing because we have the human and macaque, plus rodent genome. The avian pallium is now considered to be much like cortex in mammals. So there is a TON of work to do. Each question deserves discussion and debate, based on the best evidence available. I HOPE YOU JOIN !!!!