Developing a Natural Language Understanding System for Dealing with

the Sequencing Problem in Simulating Brain Damage

IOANNIS GIACHOS1, ELENI BATZAKI1, EVANGELOS C. PAPAKITSOS1,*,

MICHAIL PAPOUTSIDAKIS1, NIKOLAOS LASKARIS1

1Department of Industrial Design & Production Engineering,

University of West Attica,

Egaleo, Athens 12241,

GREECE

*Corresponding Author

Abstract: - This paper is an attempt to show how a Human-Robot Interface (HRI) system in the Greek language

can help people with brain damage in speech and its related perception issues. This proposal is not the product

of research conducted on how to treat brain injuries. It is a conclusion stemming from research on intelligent

Human-Robot interfaces, as a part of Artificial Intelligence and Natural Language Processing, which

approaches the processing and understanding of natural language with specific methods. For the same reason,

experiments on real patients have not been conducted. Thus, this paper does not propose a competing method,

but a method for further study. Since it is referring to a very general and quite complex issue, an approach is

presented here for the Sequencing problem. A person with such a problem cannot hierarchically organize the

tasks needed to be performed. This Hierarchy has to do with both time and practicality. The particular problem

here, as much as the innovation of our approach, lies not when there are explicit temporally defined

instructions, but in the ability to derive these temporal values through the person’s perception from more vague

temporal references. The present approach is developed based on our related previous works for deploying a

robotic system that relies on Hole Semantics and the OMAS-III computational model as a grammatical

formalism for its communication with humans.

Key-Words: NLP, NLG, NLU, dialog system, OMAS-III, HRI, Virtual Assistant, Hole Semantics, Sequencing.

Received: November 30, 2023. Revised: December 19, 2023. Accepted: January 26, 2024. Published: March 28, 2024.

1 Introduction

In the research paper, [1] and its related work, the

authors attempted to structure a Natural Language

Processing (NLP) system based on a computational

model called OMAS-III, [2]. OMAS-III is the third

improved version of the original OMAS method,

belonging to the family of SADT and IDEFx

techniques, [3], [4], representing their design

evolution. Here, OMAS-III is adapted to function as

a grammatical formalism. This adaptation allows the

detection of the grammatical position and value of

words in a sentence, their correctness, and potential

gaps in their grammatical structure, which, however,

do not invalidate the sentence’s correctness. The

human brain can correctly fill in the gaps in

elliptical structures. If this cannot be done due to

ambiguities or non-grammatical expressions, it

generates questions for the source (the interlocutor).

Therefore, when this formalism detects gaps in the

sentence to be processed, it generates basic

questions for their completion. The entire endeavor

is based on both OMAS-III and the Hole Semantics

Theory, [5]. The study results demonstrated the

algorithm’s exceptional capabilities in processing

incoming sentences, providing additional

information due to OMAS-III that may be implicit

or considered obvious in a dialogue. This

information includes time and location as highly

significant, while subject and object are considered

less crucial.

The action is sufficient to be declared so that the

algorithm begins to extract all the remaining

information. If, for example, the verb was “come”,

then the algorithm understood that it was an

imperative of the second person, so someone is

calling you to go somewhere. As a grammatical

sentence, it is correct, but because it’s a machine,

there are no obvious conclusions. So, what did the

system want to know?

 Who is calling it to go?

 Where is it called to go?

 When should it go?

 How should it go (in what way)?

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

138

Volume 21, 2024

Fig. 1: Basic algorithm (from: [1], after adaptation)

Some of this information could be extracted by

the algorithm from its database, as long as there was

continuity in the dialogue, hence evolving

knowledge and understanding. If the desired

information was not in its database, then it posed all

these questions to its interlocutor. Thus, in the

“brain” of the system, a sentence was eventually

formed: “The A person calls me to go to his/her

point in a defined time.” Through this algorithmic

process, the system showed high “awareness”,

providing additional usability.

The algorithm, depicted in Figure 1, initially

covers a broad spectrum. In continuation of the

referenced work, a survey on Humanoid systems

and their capabilities compared to humans was

conducted, [6]. The conclusions highlighted the lack

of implicit and obvious information reception, such

as time and place perception. All systems were

categorized based on the functions they cover. From

there, a robotic system began to develop, aiming to

cover all basic functions of a Humanoid from the

outset, communicating and processing data in the

Greek language. The initial algorithm allowed us to

grab implied information such as time and place. In

subsequent work, autonomous modules were added

for additional functions, discovering that adding

capabilities to the initial system is possible. The

emerging idea is that, just as we can add

capabilities, we can also remove them.

In recent work focused on the Natural Language

Generation (NLG) module, [7], it was observed that

the system could simulate certain brain impairments

related to speech problems by removing modules

and, conversely, complement brain functions related

to speech by adding modules.

This paper does not constitute a survey on brain

disorders related to speech. Therefore, some cases

are briefly mentioned in a corresponding chapter.

Through these cases, the impairment chosen to be

approached has been identified and supported

through this system.

The structure of the paper consists of six

chapters. The first chapter is an introduction. The

second chapter briefly discusses the grammatical

formalism as designed with OMAS-III, the Hole

semantic theory, and their combination. The third

chapter discusses brain disorders related to speech

and the specific case chosen herein to address

through this system. The fourth chapter develops the

method algorithm for the approach discussed in

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

139

Volume 21, 2024

Chapter 2. The fifth chapter discusses this

developing system and how it provides possibilities

for expanding its capabilities. The final, sixth,

chapter presents conclusions and suggestions for

future research.

2 OMAS-III & Hole Semantic Theory

in Combination

In a few words, it will be described how OMAS-III

contributes to the implementation of a grammatical

formalism. In general, the algorithm based on

OMAS-III seeks answers to the seven basic

questions, known as “journalist questions”.

 The question “Why” will return the rationale

(why). If there is an explanation of the action in

the incoming sentence, it will be attributed to

this question.

 The question “What” seeks the action referred

to in the sentence, i.e., the verb itself.

 The question “How much” contains all the

quantitative indicators, and the answer here is

the objects of the sentence but not the adverbs.

 The question “How” seeks the method,

indicating the action that will be used in the

verb, and is done with the help of tropic adverbs

and any determiners that can indicate manner.

 The question “Who” looks for the subject of the

sentence.

 The question “Where” asks for the place where

the verb will exert its action.

 The question “When” seeks the chronological

moment when the action of the verb in the

sentence will take place.

By answering these seven questions, this system

gathers all the information provided. In cases where

one or more of these questions are not answered, the

algorithm turns to grammatical rules and the

system’s database. If there are still gaps, the

questions are externalized. These abilities are

exhibited in the following examples.

Suppose our system is person A and is located

at point 1. There is also a person B who is located at

point 2. Another person submits the following

sentence addressing the system: "A, go from point 1

to point 2, to meet B, now". The sentence enters the

system and after being analyzed, it makes the

following correspondences:

Who = "A";

What = "go";

How = with default moving way;

How Much = "B" (the object of the formalism);

Why = "to meet";

Where From = "point 1";

Where To = "point 2";

When = "now".

The above sentence is complete and answers all the

formalism’s questions. Attention should be paid to

the fact that the verb "go" indicates movement. So,

since no way is stated, this movement will be done

in the default way of the system, e.g., by its wheels.

Also, the justification of the action (Why) is not

mandatory, but since it is here we use it.

Now suppose that instead of the above sentence, the

following sentence is submitted to the system

(person A): "go to B".

The system now proceeds with the analysis as

follows:

 Is there a verb? Yes! So: What = "go".

 Which tense? Present imperative. So: When =

"now".

 Is there a subject? No! Who is it addressed to?

Me! So: Who = "A".

 What action does the verb ask for? Movement!

Does it indicate a way? No! So: How = moving

by its default way.

 Has a movement been requested? Yes! Then,

(a) Is the start point given? No! So: Where From

= "A’s current position";

(b) Is the end point given? No! Where To =

(SEMANTIC) HOLE (required to be filled in).

 Is there an object? Yes! So: How Much = "B".

 Is a reason given? No. Not required! So: Why =

"–".

At the end of the process we notice that all but

one question has been completed! So, firstly the

system tries to retrieve from its knowledge if the

current position of "B" (Where To) is known. If it is

not, then it submits a query to its originator to get

this piece of information. Once it retrieves this piece

of information as well, all queries will have been

completed, as shown below:

Who = "A";

What = "go";

How = moving by default way;

How Much = "B";

Why = "-" (not required);

Where From = "A current position";

Where To = "B current position";

When = "now".

With the above example, we show how the used

method can fill in incomplete grammatical

structures, just like a human brain does. The

answers to all these seven queries are the fillings in

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

140

Volume 21, 2024

several holes that make up the grammatical

formalism.

Given that Hole Semantics, [8], [9] is an

approach in linguistics where holes represent the

phonetic, morphological, syntactic and semantic

levels of language, it can be said that it helps

understand language as a complex system with

various interacting levels while maintaining their

autonomy. It is a framework that defines

underspecified representations in arbitrary object

languages such as FOL or DRT, [10], [11], [12],

[13]. Specifically, it constructs an object language

with holes to which other types can be attached.

The Hole Semantic Theory is applied to

grammatical formalisms, as in this case, and as

mentioned earlier. This theory also uses semantic

grammar, [14], as it was done herein. More

specifically, these grammars introduce artificial

intelligence that makes the robot/machine capable of

asking questions, and they are also constraint-based

grammars, [15].

3 Encephalopathies Associated with

Speech Disorders

In a research study from several years ago, the

following statement was found: “Many problems

related to the functions of the nervous system can be

effectively studied through research on animals,

which allows controlled and repeatable experiments

on large groups of individuals. However, when we

come to examine the relationship of the brain with

language, we must recognize that our knowledge is

entirely based on findings in humans”, [16]. At this

very point, there could be an artificial brain that can

replace the human brain for research purposes,

offering what experimental animals provide for

other functions. Let’s first look at some brain

disorders related to speech disorders, some of which

are included in the aforementioned research. We

have the following cases: Dysphasia, Aphasia, and

Alexia.

3.1 Dysphasia

In Dysphasia, patients are unable to articulate words

correctly and, at the same time, comprehend the

meanings of words. This language disorder is

caused by damage to the part of the brain where

language functions are concentrated. This damage

can result from interrupted blood flow to the brain,

infection, and swelling, head injury, or a tumor in

the brain. Dysphasia leads a patient to difficulties in

comprehension, as they are unable to recognize

sounds, fail to understand and lose the meanings of

words, cannot recall useful and non-useful

information, and ultimately cannot recognize

sentence structures during speech.

Other limitations include the ability to recognize

what a word or sentence is but still unable to

pronounce them, or substituting words or sounds

while speaking. There may be cases where the

patient can articulate basic words but cannot

connect them into a grammatically correct sentence.

Often, the patient gets stuck on a word or a sound

and cannot clearly explain it in reading, as they

struggle to recognize and understand letters and

words. Additionally, due to the inability to

remember information, results in problems with

memories, recalling details from long narratives,

and difficulties in understanding large sentences or

forming letters. Furthermore, there is a problem

even in organizing ideas into logical stories.

3.2 Aphasia

Aphasia is characterized by the inability to

comprehend or produce written or spoken language.

This term is used for severe language disorders,

while Dysphasia is used for milder cases. It’s

important to clarify that Aphasia is a symptom and

not a disease, stemming from damage to the

Wernicke and Broca areas of the brain. Aphasia has

four forms of manifestation: non-fluent, fluent,

global, and anomic, with conditions distinguished as

acute, slowly worsening, and transient. Mixed forms

often occur. Causes for the onset of Aphasia can

include ischemic strokes, traumatic brain injuries,

intracranial hemorrhages, intracranial tumors,

neurodegenerative diseases, infections of the central

nervous system, migraines with aura, or epileptic

seizures. Explanatorily, the forms of aphasia are

characterized by the following.

3.2.1 Non-Fluent Aphasia

In this form, speech is slow, and the “flow of

speech” is disrupted, resulting in numerous syntactic

errors. However, the comprehension of speech,

whether oral or written, remains surprisingly good,

as patients are aware of the problem and give the

impression that they know what they want to say,

but struggle to find the appropriate words to express

it. Therefore, they can articulate better than a patient

with dysarthria, as, in this case, they struggle to

formulate sentences but do not make syntactic

errors.

3.2.2 Fluent Aphasia

In this form, the main characteristic is the difficulty

in understanding speech, where the patient has

incomprehensible and fluent speech. In this case, the

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

141

Volume 21, 2024

patient is unaware that others cannot understand

them and presents an image of a person who

constantly speaks with unintelligible words. This

condition is located in the left temporal lobe in the

Wernicke’s area.

3.2.3 Global Aphasia

This specific form of aphasia is the most severe,

characterized by deficits in both comprehension and

speech production. Patients with Global Aphasia are

mute and cannot even understand simple commands

or sentences. These deficits are located in the left

hemisphere of the brain, and in some cases, coexist

with weakness in the right half of the body.

3.2.4 Anomic Aphasia

Defined as the mildest of the previous forms,

individuals with Anomic Aphasia have difficulty

finding appropriate words and use circumlocutory or

explanatory speech to make their conversation

partner understand which word they mean. A

characteristic example is the claims of such patients,

stating that they are imprisoned inside their heads or

“I knew what I wanted to say, but I couldn’t find the

words to express it,” or “Really, I understood

everything, but I couldn’t articulate my thoughts

into words.”

3.3 Alexia

The Alexia syndrome, otherwise known as

Agraphia, is defined as a pathological entity in

which the patient, without difficulties in oral or

written speech, experiences difficulties in reading

and comprehending written language. The patient

communicates and understands oral speech

encouragingly, although there are some deficiencies

in words and pathological changes. They can write,

but with some distortions in letters and spelling,

without, however, depriving them of the ability to

express in writing what they have thought to say or

what has been asked of them. The area where the

patient presents difficulty is in reading something

suggested to them or in understanding a written text

or phrase. Something quite common is the

difficulties faced in understanding oral speech.

The damage in this syndrome is located in the

posterior and upper regions of the occipital lobe.

The occipital lobe is a crucial node, connected to the

parietal and temporal lobes. Initially, its location led

to the belief that it consisted of sensory types of

Aphasia, as Wernicke stated until it was explained

as a syndrome by Dejerine. Any damage in the

upper region of the angular gyrus causes difficulties

in information exchange between the two cerebral

hemispheres, that is, the exchange between the

symbolic image of a word and the spatial image of it

at the reading level on paper.

A significant piece of information for a patient

with Alexia syndrome is whether they are literate or

illiterate. In literate individuals, the symptoms are

very noticeable, and in the initial stages, there is

difficulty in orally expressing certain words, giving

the impression that they do not remember the word.

In such cases, it is possible to be perceived as

Amnesic Aphasia, something that, according to the

above explanation, does not exist. Such cases reveal

that it is not Amnesic Aphasia, as the phenomenon

where the patient does not remember the word

gradually recedes, until it is eliminated, resulting in

no recurrence of such a phenomenon.

3.4 Hierarchical Task Structure

(Sequencing)

In another research paper, it can be read, among

other things: “This finding further supports the

hypothesis that Broca’s area could play a key role in

encoding the hierarchical structure or, in other

words, the motor syntax, of human actions”, [17].

We encountered problems in Broca’s area in

subsection 3.2, which refers to Aphasia. This

specific issue, where persons struggle to structure

tasks that they are called to perform hierarchically,

is referred to as a sequencing problem. We will

delve into this particular issue because it is believed

that we can propose a functional approach to

support individuals with this problem. The role

aimed to be played in this medical section is not an

attempt to cure with artificial intelligence. It is

simply wanted to create a mechanism in the form of

an assistant to complement the individual, with this

mechanism taking on the task of hierarchy. The

sequence of tasks that someone needs to execute is

related not only to time but also to another factor.

This factor depends on both the importance of a task

compared to another and a practical sequential

connection between them. For example, if we have

three tasks where:

1. Something needs to be done in Area A.

2. Something needs to be done in Area B.

3. Something else needs to be done in Area A.

It is logical for tasks in Area A to be done

together. If the task in Area B is more important,

then it should be done first. A healthy brain

categorizes tasks by calculating these parameters,

ultimately providing a chronological placement for

task execution. Therefore, task sequencing

ultimately involves the temporal arrangement of

tasks. This developing system has the capability, as

presented, to receive temporal parameters from

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

142

Volume 21, 2024

incoming sentences, because it is a gap that needs to

be filled. One of the basic functions of the core

algorithm is the temporal placement of sentences

after processing. Such a system, in the form of a

smart virtual assistant, could receive incoming

sentences, hierarchically organize them temporally,

and suggest the order for the individual to follow in

task execution. Current virtual assistants do not

provide such capabilities.

3.5 A Hierarchy Example

Let's look at an example where a healthy brain

prioritizes tasks it has to perform. In a multinational

company, one of the employees is assigned a series

of tasks where they need to:

Draft a report on the new product before taking

a break. Upon returning from the break, go to the

marketing office. Collect new documents from the

director’s office and bring the presentations

recorded by the marketing office. Before leaving for

the day, ensure that the financial amounts calculated

by the accountants in the morning are correct.

The prioritization is as follows:

 First, they must draft the report on the new

product and finish it before the break.

 When they return from the break, they need to

pass by the marketing office.Collect the

presentations.

 Then go to the director’s office.

 Knock on the door.

 Hand over the new documents.

 Then present the marketing office’s

presentations.

 As they leave, close the door.

 Their last obligation is to visit the accounting

department.

 Count the money.

 Ensure it is the correct result.

 After that, they can leave for the day.

4 Method / Algorithm

The method being developed here is an algorithm

that will examine sentences already prioritized to

submit them to the person who needs assistance. It

is important to note again here that the

chronological arrangement of all sentences based on

qualitative and temporal characteristics is a default

process performed by this developing system.

Additionally, for the submission of sentences to

humans, the natural language generation algorithm

is activated, designed as an additional module for

this system, [7].

Before proceeding with the algorithm

development, we need to establish some basic

characteristics regarding the grammar being used.

4.1 Grammatical Specifications

We will examine and determine how sentences

regarding human tasks will reach the assistant robot,

so that the assistant, in turn, can transfer them

hierarchically to the user.

4.1.1 The Assistant Receives Sentences from

the Command Giver

In this case, the sentences are formulated in the third

person, since the command giver addresses the

recipient through the assistant. Besides performing

the required prioritization, the assistant must also

change the sentence from the third to the second

person. Thus, if the command from the giver is: “He

needs to complete this Task,” the transfer from the

assistant to the recipient will be: “You need to

complete this Task.” In the Greek language, verbs

change when the person changes, and this is

something we must consider in the algorithm

design.

4.1.2 The Assistant Simply Listens to Sentences

from the Command Giver to the Recipient

Fig. 2: the algorithm to support people who have sequencing problems in task hierarchy

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

143

Volume 21, 2024

Fig. 3: The block of new algorithm as placed in the basic algorithm, with red color

In this case, the assistant receives sentences in

the second person since the command giver

addresses the recipient directly. Here, the assistant

does not have to do anything beyond prioritizing the

sentences. Additionally, we infer that in this case,

the imperative is used.

4.1.3 The Assistant Receives Sentences from the

Human Recipient

Here, the human recipient in need of support

monologues with the assistant as the listener. The

assistant ultimately receives the sentences in the

first person. Again, it must convert these sentences

into the second person to address the recipient

correctly. Thus, if the recipient’s statement is: “I

need to complete this Task,” the transfer from the

assistant to the recipient will be: “You need to

complete this Task,” as in the first case. Here, too,

the verb must change because, in the Greek

language, verbs have different endings for each

person.

4.2 Algorithm Development

According to the specifications above, the algorithm

can be designed to support humans with brains in

sequencing problems.

In the algorithm design, presented in Figure 2,

we will start with an “IF-THEN” statement,

regarding the existence of the imperative. If the

imperative is detected, then we have the second

person, so it remains as it is. If the answer is

negative, then we may have the first or third person.

This case is covered with two consecutive “IF-

THEN” statements, where the negative response

leads from one to the other and ultimately results in

maintaining the grammatical person, unless one of

the two becomes positive, in which case the process

of changing the person proceeds. The output of this

process reaches the final formation of the proposal,

where the process of maintaining the grammatical

person also takes place. Once all proposals have

turned into the second person, the chronological

arrangement is done, as in the referenced work, [1].

The system can now address the user and provide

tasks in the correct chronological order. The

algorithm is placed at the end of its initial Figure 1,

as shown in Figure 3.

Support algorithm for

Sequencing Problem

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

144

Volume 21, 2024

5 Discussion

As mentioned earlier, an initial NLP algorithm

allowed us to develop a robotic system that evolves

step by step and module by module. In this work so

far, in addition to the basic algorithm in Figure 1, a

dynamic algorithm has been developed for learning

new words and a natural language generation

algorithm.

It is also noteworthy that in its initial form, the

algorithm operated with a constructed-language

dictionary, which, among other things, had simpler

grammatical rules. This would make this system

more flexible with simpler processes, but would be

more challenging in communication because it

would require human conversationalists with it to

know the constructed language.

Therefore, another limited dictionary of the

Greek natural language with its corresponding

grammar was integrated into this system. These new

data brought us closer to considering the system as

an assistant in solving speech-related problems. An

example of such use was developed in this paper,

aiming for future exploration in more cases.

Considering the relation of this study to other

similar ones, regarding the computerized simulation

of brain condition and function, these can be

roughly classified into four categories:

 Those that focus on the physical aspects of

damages to facilitate brain surgery, [18], [19],

[20], [21], [22].

 Those that focus on single-cell sequencing

technologies (DNA, RNA), [23], [24], [25].

 Those that focus on robotic task sequencing in

predefined industrial production lines, [26],

[27], [28], which are not of general purpose, do

not refer to brain functions, and do not include

natural language processing.

 Finally, those that focus on the task-sequencing

learning method, [29], [30], [31] refer to the

didactic method of ordering a set of tasks from

the simpler to the more complex ones.

This study of ours is not competitive or even

relevant to them, since it solely and uniquely, to the

best of our knowledge, focuses on the general

purpose of processing time and space through

natural language, potentially extended to the

functional aspects of speech disorders.

6 Conclusion

This paper, has explored how a developing robotic

system, based on the computational model of

OMAS-III and the Hole Semantic Theory, can be

proved useful as an assistant in supporting people

who struggle with task prioritization. For the study,

an algorithm was designed and implemented to

organize tasks chronologically, capturing their

correct hierarchical positions. The results in a

computational setting are quite encouraging, paving

the way for further brain problems in speech-related

issues. Therefore, it is suggested that further

research should be extended to more brain injury-

related problems with speech disorders. However,

the scope of the initial research is to develop a

robotic system with an intelligent and innovative

HRI. The integration of this system will give us

additional modules in speech, thinking, and

comprehension functions. So, the aim is that

research into brain diseases should be timed after

the completion of this system, so that the maximum

potential for simulating diseases on it is available.

Therefore, the immediate next priority step is the

development of environmental perception and

mobility. This will provide new modules that can be

integrated into the initial algorithm.

References:

[1] Giachos I., Papakitsos C.E. and Chorozoglou

G., Exploring natural language understanding

in robotic interfaces, International Journal of

Advances in Intelligent Informatics, Vol. 3,

No. 1, 2017, pp. 10-19.

[2] Papakitsos E., The Systemic Modeling via

Military Practice at the Service of any

Operational Planning, International Journal

of Academic Research in Business and Social

Science, Vol. 3, No. 9, 2013, pp. 176-190.

[3] Ross D.T., Structured Analysis (SA): A

Language for Communicating Ideas, IEEE

Transactions on Software Engineering, Vol.

SE-3, No. 1, 1977, pp. 16-34.

[4] Grover V. and Kettinger W.J., Process Think:

Winning Perspectives for Business Change in

the Information Age, IDEA Group Publishing

Inc, 2000.

[5] Koller A., Niehren J. and Thater, S., Bridging

the gap between underspecification

formalisms: hole semantics as dominance

constraints, Proceedings of the tenth

conference on European chapter of the

Association for Computational Linguistics

(EACL '03), Vol. 1, Budapest, Hungary, 2003,

pp. 195–202.

[6] Giachos I., Piromalis D., Papoutsidakis M.,

Kaminaris S. and Papakitsos E.C., A

Contemporary Survey on Intelligent Human-

Robot Interfaces Focused on Natural

Language Processing, International Journal

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

145

Volume 21, 2024

of Research in Computer Applications and

Robotics, Vol. 8, No. 7, 2020, pp. 1-20.

[7] Giachos I., Batzaki E., Papakitsos C.E.,

Kaminaris S. and Laskaris N., A Natural

Language Generation Algorithm for Greek by

using Hole Semantics and a systemic

Grammatical Formalism, Journal of

Computer Science Research, Vol. 5, No. 4,

2023, pp. 27-37.

https://doi.org/10.30564/jcsr.v5i4.6067.

[8] Bos J., Predicate logic unplugged,

Proceedings of the 10th Amsterdam

Colloquium, Amsterdam, The Netherlands,

1996.

[9] Bos J., Underspecification and resolution in

discourse semantics, Ph.D. thesis, Saarland

University, 2002.

[10] Jumanto J., Rizal S.S., Asmarani R. and

Sulistyorini H., The Discrepancies of Online

Translation-Machine Performances: A Mini-

Test on Object Language and Metalanguage,

International Seminar on Application for

Technology of Information and

Communication (iSemantic), 2022, pp. 27-35.

https://doi.org/10.1109/iSemantic55962.2022.

[11] Georgi G., Demonstratives in First-Order

Logic, The Architecture of Context and

Context-Sensitivity, Studies in Linguistics and

Philosophy, Springer, Cham, Vol. 103, 2020,

pp. 125–148.

[12] Michalczenia P., First-Order Modal Semantics

and Existence Predicate, Bulletin of the

Section of Logic, Vol. 51, No. 3, 2022, pp.

317-327.

[13] Bos, J., Variable-free discourse representation

structures, Semantics Archive, 2021.

[14] Pereira J., Franco N. and Fidalgo R., A

Semantic Grammar for Augmentative and

Alternative Communication Systems, 23rd

International Conference on Text, Speech, and

Dialogue (TSD 2020), Brno, Czech Republic,

2020, pp. 257–264.

[15] Bîlbîie G., A constraint-based approach to

linguistic interfaces, Lingvisticæ

Investigationes, Vol. 43, No. 1, 2020, pp. 1-

22.

[16] Geschwind N., The Organization of Language

and the Brain: Language disorders after brain

damage help in elucidating the neural basis of

verbal behavior, Vol. 170, No. 3961, 1970,

pp. 940-944.

[17] Clerget E., Winderickx A., Fadiga L., and

Olivier E., Role of Broca's area in encoding

sequential human actions: a virtual lesion

study, Neuroreport, Vol. 20, No. 16, 2009, pp.

1496-1499.

[18] Goriely A., Weickenmeier J. and Kuhl E.,

Stress Singularities in Swelling Soft Solids,

Physical Review Letters, Vol. 117, 2016,

138001.

[19] Linka K., St. Pierre S. R. and Kuhl E.,

Automated model discovery for human brain

using Constitutive Artificial Neural Networks,

Acta Biomaterialia, Vol. 160, 2023, pp. 134-

151.

[20] Daphalapurkar N. P., Biofidelic Digital Head

Model Software, U.S. Department of Energy,

Office of Scientific and Technical

Information, Technical Report LA-UR-20-

30334 (TRN: US2214783), 2020.

[21] Moss W. and Heller A., Computer Modeling

Provides New Insights into Traumatic Brain

Injury, Science & Technology Review, Vol.

2018-09, 2018, pp. 21-23.

https://doi.org/10.2172/1489455.

[22] Schroder A., Lawrence T., Voets N., Garcia-

Gonzalez D., Jones M., Peña J.-M. and

Jerusalem A., A Machine Learning Enhanced

Mechanistic Simulation Framework for

Functional Deficit Prediction in TBI,

Frontiers in Bioengineering and

Biotechnology, Vol. 9, 2021, pp. 1-19.

https://doi.org/10.3389/fbioe.2021.587082.

[23] Armand E. J., Li J., Xie F., Luo C. and

Mukamel E. A., Single-Cell Sequencing of

Brain Cell Transcriptomes and Epigenomes,

Neuron, Vol. 109, No. 1, 2021, pp. 11-26.

[24] Wang S., Sun S.-T., Zhang X.-Y., Ding H.-R.,

Yuan. Y., He J.-J., Wang M.-S., Yang B. and

Li Y.-B., The Evolution of Single-Cell RNA

Sequencing Technology and Application:

Progress and Perspectives, International

Journal of Molecular Sciences, Vol. 24, No. 3,

2023, 2943.

[25] Naydenov D.D., Vashukova E.S., Barbitoff

Y.A., Nasykhova Y.A., Glotov A.S., Current

Status and Prospects of the Single-Cell

Sequencing Technologies for Revealing the

Pathogenesis of Pregnancy-Associated

Disorders, Genes, Vol. 14, No. 3, 2023, 756.

[26] Alatartsev S., Stellmacher S. and Ortmeier F.,

Robotic Task Sequencing Problem: A Survey,

Journal of Intelligent & Robotic Systems, Vol.

80, 2015, pp. 279–298.

[27] Touzani H., Séguy N., Hadj-Abdelkader H.,

Suárez R., Rosell J., Palomo-Avellaneda L.

and Bouchafa S., Efficient Industrial Solution

for Robotic Task Sequencing Problem With

Mutual Collision Avoidance & Cycle Time

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

146

Volume 21, 2024

Optimization, IEEE Robotics and Automation

Letters, Vol. 7, No. 2, 2022, pp. 2597-2604.

[28] Donghui Li, Qingbin Wang, Wei Zou, Hu Su,

Xingang Wang, Xinyi Xu, An Efficient

Approach for Solving Robotic Task

Sequencing Problems Considering Spatial

Constraint, 2022 IEEE 18th International

Conference on Automation Science and

Engineering (CASE), Mexico City, Mexico,

2022, pp. 60-66.

[29] Malicka A., The role of task sequencing in

fluency, accuracy, and complexity:

Investigating the SSARC model of pedagogic

task sequencing, Language Teaching

Research, Vol. 24, No. 5, 2020, pp. 642-665.

[30] Janacsek K., Shattuck K. F., Tagarelli K. M.,

Lum J.A.G., Turkeltaub P.E. and Ullman M.

T., Sequence learning in the human brain: A

functional neuroanatomical meta-analysis of

serial reaction time studies, NeuroImage, Vol.

207, 2020, 116387.

[31] Yidan Hu, Ruonan Liu, Xianling Li, Dongyue

Chen, Qinghua Hu, Task-Sequencing Meta

Learning for Intelligent Few-Shot Fault

Diagnosis With Limited Data, IEEE

Transactions on Industrial Informatics, Vol.

18, No. 6, 2022, pp. 3894-3904.

Contribution of Individual Authors to the

Creation of a Scientific Article (Ghostwriting

Policy)

The authors equally contributed to the present

research, at all stages from the formulation of the

problem to the final findings and solution.

Sources of Funding for Research Presented in a

Scientific Article or Scientific Article Itself

No funding was received for conducting this study.

Conflict of Interest

The authors have no conflicts of interest to declare.

Creative Commons Attribution License 4.0

(Attribution 4.0 International, CC BY 4.0)

This article is published under the terms of the

Creative Commons Attribution License 4.0

https://creativecommons.org/licenses/by/4.0/deed.en

_US

WSEAS TRANSACTIONS on BIOLOGY and BIOMEDICINE

DOI: 10.37394/23208.2024.21.14

Ioannis Giachos, Eleni Batzaki,

Evangelos C. Papakitsos,

Michail Papoutsidakis, Nikolaos Laskaris

E-ISSN: 2224-2902

147

Volume 21, 2024