Soft ComputDOI 10.1007/s00500-014-1230-z

FOCUS

Towards cognitive economy

Lidia Ogiela

© Springer-Verlag Berlin Heidelberg 2014

Abstract This publication discusses new developmentdirections of cognitive economics charted based on cogni-tive processes of financial data analysis. Semantic analy-sis tasks will be dedicated to cognitive economics systems.Such systems, which semantically analyse the economic sit-uation of enterprises/organisations/business structures, exe-cute their tasks using semantic information available to them(contained in data sets). The foundation for the operationof economic cognitive systems consists in both the seman-tic analysis of the situation of an enterprise described byvarious economic/financial ratios and the assessment of thefuture situation of this enterprise. Hence cognitive eco-nomics is geared towards the semantic analysis of the eco-nomic/financial situation of enterprises carried out by meansof an in-depth description, an analysis, a reasoning and aprojection of the future condition of enterprises. The subjectof cognitive economics discussed for the purpose of indicat-ing and elaborating on the directions of this discipline andof semantic analysis of economic/financial data goes handin hand with the currently growing trend of soft computing.Methods of semantic analysis, just like e.g. neural networks,were developed by researchers inspired by the operation ofthe human mind. The cognitive, decision-making, reason-ing, understanding and prediction processes running in thismind have become the basis for attempts to create informa-tion systems analysing various data. This type of analysis,based on extracting semantic aspects and information fromthe analysed data sets has been aimed at using computa-tional methods to help solve various problems. Since such

Communicated by A. Castiglione.

L. Ogiela (B)AGH University of Science and Technology, al. Mickiewicza 30,30-059 Krakow, Polande-mail: logiela@agh.edu.pl

solutions are dedicated to bioinformatics, cognitive infor-matics and artificial intelligence, it appeared likely that theycould also be used in economics. It is in this regard that thedevelopment of semantic data analysis methods (dedicatedto economic/financial problems) puts cognitive economics inthe same group with all other scientific disciplines makinguse of soft computing techniques.

Keywords Cognitive economy · Semantic information ·Semantic analysis · Cognitive systems

1 Introduction

Cognitive economics, as a new field of cognitive science(Branquinho 2001; Ogiela 2012a), straddles the border ofeconomics, management theory and cognitive science. Animportant change in the perception of economics is theprocess of understanding phenomena taking place in theeconomy. It is therefore necessary to understand cognitiveeconomics not only as the combination of sociology witheconomics, but also combining these with the informationtheory (both in the mathematical and technical areas), whosefoundations significantly enhance the operation of cogni-tive economics. These types of processes are moving in thedirection of the correct analysis of economic processes, con-ducted in the same way as humans reason. It is, therefore,an element of neural and behavioural economics (Grossberg2012). Currently, the human cognitive, interpretational anddecision-making analysis processes very significantly deter-mine the development of cognitive economics. A questionarises whether human models of cognitive processes can betransferred into economic/cognitive/technical sciences. Thereason is that the very essence of cognitive economics isto enhance economic/cognitive sciences with the machine

123

L. Ogiela

execution of decision-making solutions. Consequently, thefundamental question is how this enhancement occurs andwhether it is necessary in the analysis of economic processes.

The processes of cognitive economics, understood as thecombination of psychology with economics, allow us tounderstand (in relation to human perception processes) theeconomic processes taking place in the economy. This com-bination does not, however, enable improving this type ofanalysis by adding automatic (computer) data analysis. It is,therefore, a strictly individual interpretation (personal, andconsequently fully dependent on the person conducting theanalysis processes). If computer-based, semantic data analy-sis is combined with the aspects of cognitive economics, theprocesses of economic data interpretation will not dependonly and exclusively on a single person, but on a whole groupof experts building broad knowledge bases of systems, andit will be possible for information systems to analyse largeinformation sets for various situations in real time.

Cognitive economics must, therefore, be a combination ofdifferent sciences in whose domains the economic and com-mercial situation of a given entity will be analysed (Cohenand Lefebvre 2005; Ogiela 2013a). This situation is presentedin Fig. 1.

Computer applications for the automatic acquisition,interpreting and description of data can be employed fortasks oriented at the semantic perception analysis of data(Albus and Meystel 2001; Duda et al. 2001; Ogiela 2009;Ogiela 2013c). The purpose of this paper will be present

concepts and solutions for new classes of systems support-ing the interpretation, description and analysis of data includ-ing its semantic classification, which can be used to help intasks consisting in the complete interpretation and semanticreasoning about selected types of data and information tosupport strategic information management. Such solutionswill be based on the semantic analysis of interpreted datacollected in the form of databases as well as isolated (single)data type. The purpose of the semantic analysis presentedwill be to indicate the factors and features of the analysedinformation which can be used to unambiguously conductthe analysis, interpretation and reasoning processes based onfeatures characteristic for selected information classes. Thisis due to the importance of excluding and eliminating fac-tors and features which turn out to be immaterial during theanalysis conducted, because of the type of the data examinedor because of the characterisation of features of the analysedpattern in the form of a data vector representing economicand financial indicators of key importance for enterprise man-agement.

The purpose of this paper will be to propose algorithmsexecuted by a broad class of automatic data interpretationand understanding systems designed for the in-depth seman-tic analysis and interpretation of the results obtained. Thiswill be done by defining new system classes as applicationssupporting decision-making processes useful in various areasof knowledge. CFAIS—Cognitive Financial Analysis Infor-mation Systems will be developed, as will be sub-classes of

Fig. 1 Cognitive economyscience

123

Towards cognitive economy

these systems representing new classes of cognitive analysissystems for economic and financial data.

CFAIS are systems for the semantic analysis of economicdata. This data consists in values of economic and financialratios which can be used to determine the current situationof companies, organisations, farms etc. What is more, theirfuture situation can also be projected. Thus the modellingprocess enables analyses of the current situation, but if it isalso supported with projecting and simulation mechanisms,it enables forecasting the future condition. This is how tradi-tional data analysis systems work.

On the other hand, semantic interpretation systems usesemantic information contained in the analysed datasets tointerpret and understand the present and future condition(Ogiela 2012a). Systems for the semantic analysis of dataare built on the foundation of linguistic formalisms whichunambiguously interpret the analysed data. This method ofanalysis allows not only the current status to be describedcorrectly, but also makes understanding its reasons possible(the semantic aspect of the analysis).

The class of semantic data analysis systems is dividedinto their various types. The first systems of semantic dataanalysis were dedicated to medicine: to analysing and under-standing medical images (Bodzioch and Ogiela 2009; Hachajand Ogiela 2011). The next type of semantic data analysissystems has been targeted at economic subjects: analysingand understanding the values of economic/financial ratios.

As a result of operating these CFAIS systems, it’s pos-sible to take the right strategic decision for the enterpriseand to reason about the future on the basis of an analysis ofeconomic ratios characteristic for the enterprise, and in par-ticular the financial or macroeconomic indicators portrayingits current standing.

Automatic data interpretation and understanding sys-tems designed for the purposes of the semantic analysis ofeconomic and financial data are develop by applying theprinciples of linguistic analysis and semantic interpretation.Linguistic analysis is a part of the processes of inference-reasoning. Reasoning applies to determine the meaning ofthe analyzed data.

Linguistic formalisms make it possible to describe andperform a semantic analysis oriented at determining the sig-nificant features of the examined figures (ratios), and also toanticipate and project the directions of their future changes.The construction and structure of the presented class ofIT systems with the identification of their subclasses is ofextreme importance due to the increasingly robust develop-ment of IT systems serving not just technical science, but allother fields of science and knowledge.

Cognitive data analysis systems are built by adaptingmathematical linguistic methods to the tasks of semantic dataanalysis (Ogiela 2012a,b). Grammatical formalisms wereused to build cognitive systems. Strategic data of enterprises

were analysed using specific economic/financial indicators,and during the interpretation process, it’s undergo an analysisand a determination of its significance for the further growthof the enterprise (based on determining the semantics of thedata interpreted).

2 Cognitive processes in cognitive economy

In the course of research work and the development ofconcepts and ideas of cognitive data analysis systems, thedevelopment started on class of cognitive systems—CFAIS(Cognitive Financial Analysis Information Systems)—usedto analyse data strategic for enterprises, i.e. to analyse eco-nomic and financial ratios. These systems were developedas two main subclasses of economic systems, i.e. those foranalysing liquidity ratios and rates of return. The formalismsproposed for the linguistic description (Kornai 2008; Ogiela2012a) and analysis of data, in the form of sequential gram-mars, were designed for simple single-factor analysis, two-factor analysis and the more complex multi-factor analysis.The results of analyses conducted were to show whether thedecision taken is right and whether it is weighed with risk,and if so, whether this risk is high. For an entrepreneur, theanswer to these questions is fundamental for the correct oper-ation of the company (Ning et al. 2012), and it was thereforeappropriate to establish that the set of economic and financialdata had been absolutely correctly selected for its semanticanalysis by cognitive systems.

Scientific research work focused on characterising newclasses of information systems used for interpreting, analysingand reasoning based on the cognitive categorisation conceptfor economical data.

The operation of cognitive economical systems is foundedon adapting the specific course of thought, cognitive andreasoning processes taking place in the human mind, whichultimately allow the meaning of patterns presented to beunderstood (Fig. 2).

The most important element in the presented analysis andreasoning process is that processes based on cognitive cate-gorisation which leads to semantic reasoning occur in boththe human cognitive/thinking process and the system’s infor-mation/reasoning process that conducts the interpretation andanalysis of data.

This process is based on the cognitive resonance phenom-enon which occurs during the thought process, and whichbecomes the starting point for the process of data understand-ing which consists in extracting the semantic information andthe meaning contained in the analysed type of data, whichenables reasoning.

Cognitive resonance is an attempt to compare and distin-guish certain similarities and differences between the set offeatures of analysed data and the set of features represented

123

L. Ogiela

Fig. 2 CFAIS systems—example of cognitive processes in cognitive economy

by a knowledge base. The set of analysed data is used forits broadly-understood analysis (the analysis of the form, thecontents, the meanings, the shape etc.), as a result of which itbecomes possible to extract certain significant features (val-ues) of the analysed data. At the same time, the collected(possessed) set of information (knowledge about the specificobjects) is used to generate expectations about the analyseddata by referring to the knowledge resource held by the sys-tem (Fig. 3).

The data stored in expert knowledge bases is used to gen-erate certain expectations concerning the analysed datasets.Expectations are generated by the system based on definedpatterns (an identification of characteristic features) whichconstitute the baseline (a kind of a reference point) to whichthe analysed data is compared. Each feature of it is confrontedwith the feature of a pattern defined in every data class. Defin-ing patterns characteristic for each data class makes it possi-ble to compare the features of the analysed data with the fea-tures of the pattern. Datasets contained in knowledge basesand patterns make it possible to generate expectations aboutthe occurrence of significant features of the analysed data(Ogiela 2008, 2010, 2013b).

Those expectations are compared to the features of theanalysed data extracted during the analysis process. Then, asa result of comparing the features and expectations, cognitiveresonance occurs, which consists in indicating the similari-ties that appear between the analysed dataset and the gener-ated set of expectations as to the possible consequences ofthe knowledge acquired by the system. The similarities arerevealed during the comparative analysis conducted by thesystem, in the course of which the analysed data is subjectedto the phenomenon of understanding. The reasoning processwhich forms the result of the understanding process is anindispensable factor for the correct data analysis, because ifit did not occur, it would become impossible to forecast and

reason as to the future of the phenomenon being studied. Soconducting the analysis without the reasoning process couldactually lead to impoverishing the entire analysis process,as it would be limited only to understanding the reasons forthe occurrence of the analysed phenomenon, but without achance of determining its further development.

The ability to conduct a complete analysis of data aroseas a result of transferring cognitive and thought processesoccurring in biological structures (e.g. in the human brain) toinformation systems, as a consequence of which informationsystems can analyse data using the foundations of cognitivecategorisation.

The description of cognitive categorisation processescomes from psychology and philosophy. Their advantage istheir indisputable universality and interdisciplinary nature inthe application and the correct implementation (courses) ofthe above cognitive processes.

Cognitive categorisation originates from cognitive sci-ence, in which the notions of thought, cognitive or analysisprocesses have been unambiguously defined. These knownnotions of cognitive processes to present and discuss infor-mation systems analysing image data and at the same timeusing processes referred to in psychology and philosophy ascognitive processes.

The cognitive analysis and the semantic interpretation ofthe analysed data aimed at the process of data understandingand cognitive categorisation was made possible by the useof formalisms of linguistic analysis and semantic reasoningbased on graph and sequential formalisms.

3 Cognitive economical systems

Cognitive analysis processes dedicated to interpreting andunderstanding economic data, including economic/financial

123

Towards cognitive economy

Fig. 3 Data analysis process in cognitive economy

ratios, are executed by CFAIS systems—Cognitive Finan-cial Analysis Information Systems. Cognitive financial ratioanalysis systems can conduct analyses in four main areas.The division of systems into classes is strictly determined bytypes of financial analysis ratios.

The main sub-classes of systems making up the CFAISsystem class consist of the following systems (Ogiela 2013a):

• UBMLRSS (Understanding Based Management Liq-uidity Ratios Support Systems)—cognitive systems for

analysing enterprise liquidity ratios which will reasonabout the resources and the solvency of the working cap-ital of the company as well as about its current operationsbased on a semantic analysis of a set of ratios. UBMLRSSsystems are used to analyse:

• short-term liquidity:• the current ratio,• the quick ratio,• the cash ratio,

123

L. Ogiela

• the mature payables ratio,• long-term liquidity:

• cash flow indicator ratios:• operating cash flow/sales,• operating cash flow/operating profit,• operating cash flow/assets,• operating cash flow/fixed assets,• operating cash flow/working capital,

• cash flow coverage ratios:• operating cash for paying total liabilities,• operating cash for paying current liabilities,• operating cash for paying long-term liabilities,• operating cash flow for fixed asset purchases,• general operating cash flow coverage.

• UBMFLRSS (Understanding Based Management Finan-cial Leverage Ratios Support Systems)—cognitive sys-tems for analysing financial leverage ratios (financial debtratios) which will reason about the sources financing thecompany’s assets and the proportion of external capi-tal by analysing short-term and long-term liabilities, aswell as the effectiveness of outlays and the interest paid.UBMFLRSS systems are used to analyse:

• ratios describing the debt level:• total debt,• long-term debt,• liability structure,• debt to equity,• long-term debt to equity,• long-term liability coverage with net fixed assets,

• ratios describing the company’s capacity to serviceits debt:• debt service coverage,• interest coverage,• debt service coverage with the cash surplus.

• UBMPRSS (Understanding Based Management Prof-itability Ratios Support Systems)—cognitive systems foranalysing profitability ratios which will reason about thefinancial efficiency of business operations of a given unitbased on the relationship between financial results andthe sales of goods and services as well as the cost ofsales. UBMPRSS systems are used to analyse:

• return on sales:• return on sales,• operating profitability of sales,• profitability of business operations,• return on gross sales,• return on net sales,• net profitability,• cost level,

• return on assets:• return on net assets,

• return on gross assets,• return on gross assets including interest,• return on fixed assets,• return on working assets,• return on clear assets,

• return on equity:• return on equity,• return on core capital,

• capital market ratios:• profit per share,• unit dividend,• dividend pay-out rate,• share market price,• dividend rate.

• UBMARSS (Understanding Based Management Activ-ity Ratios Support Systems)—cognitive systems foranalysing turnover ratios which will reason about howfast assets rotate and how productive they are. UBMARSSsystems are used to analyse:

• asset turnover:• total asset turnover,• fixed asset turnover,• working asset turnover,• liquid asset turnover,

• inventory turnover:• inventory turnover,• inventory days on hand,• finished product inventory turnover,• material inventory turnover,• production in progress turnover,

• receivables turnover:• receivables turnover,• receivables days on hand,

• liability repayment period,• cash turnover.

All classes of cognitive financial analysis systems use thesemantic analysis of selected economic/financial ratios todetermine the condition of the enterprise, its future and tointerpret the significance of individual ratio values for theenterprise’s current and future situation. The selection ofratios depends on the class of the cognitive system whichis analysing various financial ratios.

4 Semantic analysis in cognitive economical systems

Economics enhanced with cognitive processes dedicated tothe cognitive analysis of economic data is oriented towardsinterpreting selected financial ratios presented in the previoussection.

123

Towards cognitive economy

This section of the publication will present a selected classof cognitive systems as an example of cognitive economicsystems.

Below, the author will present an example of a CFAIS-UBMLRSS system used to assess the current financial situa-tion of an enterprise in the debt service area. The evaluation ofan enterprise’s debt service is usually performed by assessingthe values of the current ratio, the quick ratio, assessing cashand mature payables. The UBMLRSS system was developedto assess the current financial situation of an enterprise usingthree selected ratios, namely:

• current liquidity ratio,• quick liquidity ratio,• cash ratio.

The three selected liquidity ratios were assigned symbolsconsistent with the order in which the values of individualratios are analysed, namely:

• the value of the current ratio is represented by v1,• the value of the quick ratio is represented by v2,• the value of the cash ratio is represented by v3.

A grammatical formalism (Kornai 2008; Ogiela 2012a) inthe form of a quadruple constituting a sequential grammarwas defined for the above ratios describing the short-termliquidity of an enterprise.

The way in which a formal grammar for describing theanalysed phenomenon is built is described below. A gram-mar is defined manually. One of the three basic types of lin-guistic formalisms known currently is selected: a sequential,tree or graph grammar. The choice of the formal grammartype depends on the type of data analysed (Ogiela 2010). Inthe case of systems analysing indicator data—economic orfinancial ratios (i.e. numerical ones)—the best choice is asequential grammar. Then the components of the grammarare defined. For a sequential grammar, these consist in: a setof non-terminal symbols, a set of terminal symbols, a startsymbol of the grammar and a set of productions. All these setsare defined manually, taking into account the characteristicfeatures of the analysed data.

The proposed mathematical formalism has the followingform (Ogiela 2013a):

GL = (VN L , VT L , PL , SL)

where:VN L , the set of non-terminal symbols:VN L = {LIQUIDITY, EXCESS_LIQUIDITY,OPTIMAL_LIQUIDITY, SOLVENCY_PROBLEMS},VT L , the set of terminal symbols:VT L = {a, b, c, d, e, where: a ε [0; 1), b ε [1; 1,2], c ε (1,2;1,5), d ε [1,5; 2], e ε (2; +∞)

SL ε VN L , SL = LIQUIDITYPL , set of productions:

1. LIQUIDITY → EXCESS_LIQUIDITY |OPTIMAL_LIQUIDITY | SOLVENCY_PROBLEMS

2. EXCESS_LIQUIDITY → EEE | EDE | EED3. OPTIMAL_LIQUIDITY → DCA | DCB | DBB | DBC

| DBA | CBA | CCA | CBD4. SOLVENCY_PROBLEMS → DEE | AAA | ABA |

AAB | ABB | BAB | BBA | ABC | BAC | ACB | BCA |AAC | ACA | CAA | AAD | ADA | DAA | AAE | AEA| EAA | ACD | ADC | ABD | ADB | DAB | ABE | AEB| BAA | BAD | BAE | BEA | EAB | EBA | CAB | ACC| CAC | BCC | CAD | CDA | CAE | CEA | ACE | ADE| AED | DAE | DEA | EAD | EDA | BBB | CCC | DDD| BBC | CBB | BDA | BCB | BBD | BDB | BBE | BEB| EBB | CCD | CDC | DCC | CCE | CEC | ECC | DDE| DED | EDD | BCD | BDC | CDB | BCE | BEC | ECB| EBC | CBE | CEB | CDE | CED | EDC | ECD | DEC| DCE | EEA | EAE | AEE | EEB | EBE | BEE | CEE |ECE | EEC | DDA | DAD | ADD | BDD | DBD | DDB |DDC | CDD | DCD | BDE | BED | CBC | CCB | DAC |DBE | EAC | EBD | ECA | EDB | AEC | DEB

5. A → a6. B → b7. C → c8. D → d9. E → e.

The linguistic formalism proposed for semantically analysingratios used for assessing the current financial situation of anenterprise allows the following to be identified:

• The current situation of the organisation/enterprise, byanalysing the value of the short-term liquidity ratio;

• The semantic analysis is used to determine the signifi-cance of the analysed ratios for the current and futuresituation of the given organisation;

• In addition, this type of analysis becomes similar to theprocess of projecting the future situation of the enterprise.

The results of the operation of a CFAIS-UBMLRSS systemare presented in Fig. 4.

The above examples of the operation of a UBMLRSSeconomic system demonstrate how this system assesses thefinancial situation of an enterprise with regard to debt ser-vice. The important information is whether the enterprisehas payment problems or not and what consequences thiscauses. The system can also assess whether current liquid-ity is maintained and whether the inventory of stocks andready products is right or not. Another issue which needs tobe correctly identified is whether there are problems withcollecting amounts receivable and with their timely pay-ment by debtors. All these elements influence the assess-ment of a company’s operations as part of the analysis ofits current financial situation and form the basis for the cor-

123

L. Ogiela

Fig. 4 UBMLRSS systems—example of cognitive economy

rect analysis of its situation in the aspect of their semanticinterpretation.

5 Conclusions

The methodology, presented in this publication, for seman-tically interpreting financial ratios in the economic area pro-vides the foundation for developing aspects of cognitive eco-nomics. Thus cognitive economics becomes the starting pointfor modern financial data analysis systems. An assessmentof the financial condition, a financial analysis of the eco-nomic situation, a cost analysis of a project, a profit andloss assessment etc. can be enhanced with new elements: ofunderstanding the situation. The processes of understandingsituations of this type do not pose a problem for expert teams,but are something novel in the area of computer data analy-sis. The semantics of the analysed information allows theanalysis to be conducted in a deeper and more detailed way.This analysis uncovers the meaning of this information andits impact on the development of the situation. Hence cog-nitive economics becomes a new challenge for researchersdealing with complex economic situations, particularly in theaspect of their machine understanding with the use of neuralprocesses.

The essence of the presented solution is the semantic inter-pretation of strategic data of enterprises achieved by conduct-ing a cognitive analysis of the interpreted data which illustratecertain economic phenomena occurring within these enter-

prises. Such situations are usually a component of the fluctu-ations of the selected financial indicators. Building systemsfor the semantic analysis of data strategic for enterprises will,to a significant extent, help to manage these organisations bet-ter, more efficiently and more rationally. Hence the researchresults can contribute to scientific development in the fieldof further detailing subjects of cognitive data analysis andmachine data interpretation.

Acknowledgments This work has been supported by the NationalScience Centre, Republic of Poland, under project number DEC-2012/05/B/HS4/03625.

References

Albus JS, Meystel AM (2001) Engineering of mind: an introduction tothe science of intelligent systems. Willey, New York

Bodzioch S, Ogiela MR (2009) New approach to gallbladder ultrasonicimages analysis and lesions recognition. Comput Med Imag Graphics33(2):154–170

Branquinho J (ed) (2001) The foundations of cognitive science. Claren-don Press, Oxford

Cohen H, Lefebvre C (eds) (2005) Handbook of categorization in cog-nitive science. Elsevier, The Netherlands

Duda RO, Hart PE, Stork DG (2001) Pattern Classification. SecondEdition, A Wiley-Interscience Publication John Wiley & Sons Inc.

Grossberg S (2012) Adaptive resonance theory: how a brain learns toconsciously attend, learn, and recognize a changing world. NeuralNetw 37:1–47

Hachaj T, Ogiela MR (2011) A system for detecting and describingpathological changes using dynamic perfusion computer tomogra-phy brain maps. Comput Biol Med 41(6):402–410

123

Towards cognitive economy

Kornai A (2008) Mathematical linguistics. Springer, Berlin, HeidelbergNing Y, Liu J, Yan L (2012) Uncertain aggregate production planning.

Soft Comput 17:617–624Ogiela L (2008) Syntactic approach to cognitive interpretation of med-

ical patterns. In: Xiong Caihua, Liu Honghai, Huang Yongan, XiongYoulun (eds) Intelligent robotics and applications, first internationalconference, ICIRA 2008, Wuhan, China, 15–17 October 2008, LNAI5314. Springer, Berlin, Heidelberg, pp 456–462

Ogiela L (2009) UBIAS systems for cognitive interpretation and analy-sis of medical images. OptoElectron Rev Springer Verlag Heidelberg17(2):166–179

Ogiela L (2010) Cognitive informatics in automatic pattern understand-ing and cognitive information systems. In: Yingxu Wang Du, ZhangWitold Kinsner (eds) Advances in cognitive informatics and cogni-tive computing, studies in computational intelligence 323. Springer,Berlin, Heidelberg, pp 209–226

Ogiela L (2013a) Data management in cognitive financial systems. IntJ Inf Manag 33:263–270

Ogiela L (2013b) Semantic analysis and biological modeling in selectedclasses of cognitive information systems. Math Comput Modell58:1405–1414

Ogiela L (2013c) Cognitive informatics in image semantics description,identification and automatic pattern understanding. Neurocomputing122:58–69

Ogiela L, Ogiela MR (2012a) Advances in cognitive information sys-tems. COSMOS 17, Springer, Berlin, Heidelberg

Ogiela MR, Ogiela U (2012b) DNA-like linguistic secret sharing forstrategic information systems. Int J Inf Manag 32(2):175–181

Ogiela MR, Ogiela U (2010) The use of mathematical linguistic meth-ods in creating secret sharing threshold algorithms. Comput MathAppl Elsevier 60(2):267–271

123