1. COMPUTER AIDED CRIME INVESTIGATION IN DEVELOPING
COUNTRIES
BY
OLUWOLE CHARLES AKINYOKUN
PROFESSOR OF SOFTWARE ENGINEERING; FNCS, MCPN, MISPON, MBCS, MACM
Department of Software Engineering
Federal University of Technology, Akure
Ondo State, Nigeria
August 2018
2. The conventional method for crime investigation and trial of cases in the law courts in
developing countries are usually slow. Consequently, the society is characterized by
prolonged periods of detention of the suspects awaiting trial and congestion in the
prisons and law courts. This paper attempts to describe the application of Artificial
Intelligence (AI) in the investigation of crime. An Expert System (ES) is proposed
which supports the storage and intelligent interactive processing of the knowledge
acquired by study and experience of the human expert in the domain of crime
investigation, law and justice. One of the objectives of the study is to provide an
intelligent computer system which will enhance the efficient performance of the human
expert in the domain of crime investigation. The other objective is to provide a system
for computer aided learning of crime investigation.
ABSTRACT
3. • The general design of the existing four generations of computers is based on the
Von Neuman machine architecture. The architecture is composed of a central
processor, a memory, arithmetic and logic unit and input-output devices. The
computers operate in a largely serial fashion, step by step and widely applied in
routine data processing, mathematical and statistical calculations in science and
engineering. Only a small segment of the activities of the professionals in
business, science and engineering has as its kernel mathematical algorithmic
procedures.
• Artificial Intelligence (AI) is a subfield of computer science concerned with the
concepts and methods of symbolic inference by computer and the symbolic
representation of the knowledge to be used in making inferences typical of
human reasoning. The earliest work in AI focused on the construction of
general-purpose intelligent systems. General-purpose deductive schemes do not
emulate human experts and therefore lack the efficiency and flexibility necessary
for solving complex practical problems [Feigenbaum 1984]. The recent
developments emphasize Expert System (ES) which is concerned with the role
and use of the knowledge of a specific problem domain.
INTRODUCTION
3
4. • Every nation has a department within its Police Force which is charged with the
responsibility of crime investigation. The department relies primarily on the
information collected from complainants, witnesses and existing records of
criminal cases in an attempt to investigate a case on hand. The existing records
have to be searched in order to find out whether a crime just committed and
under investigation can be related to some cases in the past. The existing
records are often kept piecemeal in file cabinets. The manual file system lacks
standard procedures for data formatting, storage, retrieval, maintenance and
documentation. Furthermore, there is no central control, thus, data security and
privacy cannot be guaranteed. The processing of the manual file is usually slow
and tedious, particularly when the population of records to be searched is
large. The time lag between the time a crime is committed and that by which
the investigation is completed may be too long. The society has therefore been
characterized by prolonged detention of suspects, congestion in the prisons and
law courts. Furthermore, the normal process of prosecution may be
jeopardized. There is even the likelihood of justice being switched unduly in the
long process, after all, justice delayed is justice denied.
INTRODUCTION CONTD.
4
5. • The research attempts to apply certain principles in AI to the investigation of crime
with emphasis on bank robbery. An ES is proposed which supports the storage and
intelligent interactive processing of the knowledge acquired by study and
experience of the human experts in the domain of crime investigation. One of the
objectives of the study is to provide an intelligent computer based system which
will enhance the efficient performance of the human expert in the domain of crimel
investigation. The other goal is to provide a system for computer aided learning of
crime investigation. The paper presents the architecture and functionality of the
system and some conclusions are drawn.
5
INTRODUCTION CONTD.
6. •Knowledge is the key factor in the performance of an ES. There are two types of
knowledge; the first type is concerned with the facts of the problem domain which is the
widely shared knowledge commonly agreed upon by the human experts in a particular
problem domain. This is the knowledge acquired from textbooks, technical reports,
journals, conference proceedings and lectures. The second type of knowledge is called
heuristic knowledge which is the knowledge of good practice and good judgment in a
field.
•The knowledge acquired by study is composed of the rules and thumb binding together
the events, activities and objects associated with bank robbery. This knowledge has
semantic contents but is void of pragmatic. The semantic network exhibits a number of
navigational paths whose straightforward method of enumeration leads to explosive
number of possibilities.
•The semantic network describes four different points against which the bank robbery
can be targeted, namely: customer (CUST), cashier (CASH), courier (COUR) and strong
room (STRM). The categories of persons that may be connected with a bank robbery and
subject to interrogation are: bank manager (BKMG), bank accountant (BKAT), ledger
clerk (LGCK), police (POLI), courier driver (CRDV), gateman (GTMN), robber(s)
caught in the scene (BKRB) and others (OTHR).
6
KNOWLEDGE BASE
7. • The second type of knowledge is concerned with that which is acquired by
experience. In this research, it is assumed that this knowledge is exhibited in the
history of the existing bank robbery. A case history is described by the bank robbed,
robbery target, mode of attack, personal data of suspects, witnesses and culprits,
investigation procedure and decision extract, court procedure and judgement. The
conceptual model of the case history is formulated using the concepts of data
abstraction, namely: classification, generalization, aggregation and association
[Trayner 1984]. The graphical representation of the conceptual model is shown in
Appendix C. A node in the graph describes an object type and an arc describes the
semantic relationships between two object types. The attributes of the object types
have been suppressed in the conceptual graph for clarity.
7
KNOWLEDGE BASE CONTD.
8. Knowledge serves as the basis for reasoning by a knowledge information
processing system but it is not sufficient in itself to discover and use lines of
reasoning [Feigenbaum and McCorduck 1984]. The inference engine is concerned
with piecing together an appropriate line of reasoning which leads to the solution
of a problem or the formulation of a body of consultative advice. In this research,
the inference engine coded in modules using IF THEN clause of Fortran 77 is
proposed. The modules are hierarchically structured and the details of the
information contents increased downward. Thus, a module in the hierarchy can
call another module at lower level thereby supporting the forward chaining
strategy of inference engine. The upward chaining of modules in the hierarchy is
allowable and this supports the backward chaining strategy of inference engine.
8
INFERENCE ENGINE
9. The textual description of some of the modules are:
If target of bank robbery is courier
and the robbers went away with the money
and nobody is killed in the robbery
then the crew of the courier and police escort are suspects
If target of bank robbery is courier
and the robbery takes place in the bank premises
and the robbers did away with a car in the premises
and there exist a case such that
the robbers did away with a car in the bank premises
then the culprits involved in that case are suspects
A deduction based on the navigation of the semantic network may be valid but the truth
value may be false. A deduction in this context will be true only when the history of the
existing cases has been processed and the findings favour the deduction.
9
INFERENCE ENGINE CONTD.
10. • Consider for example, the modules given above. The deduction that members of a
group of robbers which are involved in a case of bank robbery in the past whereby a
car is stolen are suspects in a case under investigation may be valid. The information
deduced from the existing records may show that every member of the group has been
executed by firing squad five years ago. Therefore, the truth value of the earlier
assertion is false. Then another course of action has to be taken and this may lead to
some chains of investigation procedures.
• Thus, there are many alternative paths which can be navigated in the semantic
network thereby leading to many alternative decisions. A weighing function based on
the principle of probability distribution of the decision extracts from the case history is
built into the inference engine. A navigational path which is favoured by a decision
extract with the highest weight is considered valid and true.
10
INFERENCE ENGINE CONTD.
11. • The user interface acts primarily as the communication medium between the user
and the ES. It provides the resources for the user to ask questions and offer
information, in principle, at any time and without binding the user to respond
narrowly to the system’s initiatives [Bramer 1984]. In this research, a user interface
which is based on pseudo-natural language coupled with menu driven facility is
proposed.
• A user view of the system is hierarchically structured. A user gains access to the
system by supplying valid user name and password. Following this, the system
prompts the user for the category of crime which is of interest. It is remarked that
the system will incorporate other types of crime such as murder, rape, highway
robbery and warehouse robbery. The system presents to the user the scenario of the
modules which compose the inference engine concerning the crime requested. The
user then calls the modules one at a time. The system guides the user but always
leaving the ultimate decisions to the user.
11
USER INTERFACE
12. •This paper has addressed the design of an intelligent computer based system for
crime investigation with emphasis on bank robbery. The architecture of the system
has been presented and its functionality described. It has been shown that there are
many alternative paths that can be taken in the investigation of a crime. The
alternative paths have been modeled using the concept of semantic network.
•Given the events, activities and objects associated with a reported criminal
offence and their inter-relationships, the framework proposed provides the
mechanism for the interactive processing of the corresponding semantic network
of the crime and the history of existing cases. The interactive processing considers
a number of key factors which can be related, evidence weighed and alternative
deductive reasoning evaluated with the intention of identifying the set of culprits
involved in the given case.
•It has been argued that the application of ESs to legal process is extraordinarily
complex in [Laudon 1985]. The research reported in this paper is a good starting
point to what may be very useful system for legal processes in practice.
12
CONCLUSIONS
13. 13
ARCHITECTURE OF ES
Knowledge base
Knowledge acquired
by study
Knowledge acquired
by experience
Inference Engine
User Interface
16. • Akinyokun O. C., 1987. The Feature Analysis of Information and Knowledge
Management Systems. Proceedings of the 2nd Nigerian National Conference on
Computer Applications (in Press), Lagos, Nigeria.
• Akinyokun O. C. and Stocker P. M, 1985. A Framework for the Implementation of
Distributed Databases. Proceedings of the 1st Nigerian National Conference on
Computer Applications, Lagos, Nigeria, pp 198 – 204.
• Barman C., 1986. Courts up for High Tech. Computing. A Publication of the British
Computer Society, April 10, pp 10.
• Bramer M. A. (ed.), 1984. Research and Development in Expert System. Cambridge
University Press.
• Cookson M. J., et al.1984. Knowledge Acquisition for Medical Expert Systems: A
System for Eliciting Diagnostic Decision Making Histories. Research and
Development in Expert System. Cambridge University Press., pp 113 – 116.
• Craig I. D., 1986. The Ariadine-I Blackboard System. The British Computer
Journal, Vol. 29, No.3, pp 235 – 240.
• Crehange M. et al., 1984. EXPRIM: An Expert System to Aid in Progressive
Retrieval from a Pictorial and Descriptive Database. Private Communication.
16
REFERENCES
17. • Dodson D. C. and Rector A. L., 1984. Importance Driven Distributed Control of
Diagnostic Inference. Research and Development in Expert System. Cambridge
University Press., pp 51 – 60.
• Feigenbaum E. A. and McCorduck P., 1984. The 5th Generation: Artificial Intelligence
and Japan’s Computer Challenge to the World. Pan Books Ltd.
• Feigenbaum E. A. and Feldman J. (eds.), 1963. Computers and Thought. McGraw
Hill Book Co.
• Fikes R. and Kehler J., 1985. The Role of Frame Based Representation in Reasoning.
Communications of the ACM, Vol. 28, No. 9, pp 904 – 920.
• Genasereth M. R. and Ginsberg M. L., 1985. Logic Programming. Communications of
the ACM. Vol. 28, No. 9, pp 933 – 941.
• Giles D. A. et al., 1984. Representing Knowledge as Triples. Technical Report, IBM,
UK Laboratory Ltd., Winchester.
• Hamilton S., 1986. Police Use `Second Best’ in Major Murder Hunt. Computing: A
Publication of the British Computer Society, October 16.
• Hayes-Roth F., 1985. Rule-based Systems. Communications of the ACM, Vol. 28, No.
9, pp 921 – 932.
• Hofstadler D. R., 1982. Godel, Escher, Bach: An Eternal Golden Brand – A
Metaphoric Fugue on Minds and Machines in the Spirit of Lewis Caroll. Penguin
Books Ltd. 17
REFERENCES CONTD.
18. • Jones K.S. 1984. Natural Language Interfaces for Expert Systems. Research and
Development in Expert System. Cambridge University Press., pp 85 – 94.
• Jones M. J. and Crates D. T., 1984. Expert Systems and Vediotex: An Application in
the Marketing of Agrochemical. Research and Development in Expert System.
Cambridge University Press., pp 141 – 150.
• Laudon K. C., 1985. Environmental Models of System Development: A National
Criminal History System. Communications of ACM, Vol. 28, No. 7, pp 728 – 740.
• Moto-Oka T. and Kitsuregawa M., 1985. The Fifth Generation Computer: The
Japanese Challenge. John Wiley and Sons.
• Mylopoulos J., 1980. An Overview of Knowledge Representation. Proceedings of
the Workshop in Data Abstraction and Conceptual Modeling, pp 5 – 18.
• Roycraft A. E. and Loucopoulos P., 1984.
• ACCI – An Expert System for the Apportionment of Close Companies’ Income.
Research and Development in Expert System. Cambridge University Press., pp 127
– 140.
• Sanda A. O., 1986. Basic Ingredients of Crime Prevention in the Traditional Yoruba
Society. Private Communication.
• Sergot et al. M. J., 1986. The British Nationality Act as a Logic Program.
Communications of the ACM, Vol. 29, No. 5, pp 370 – 386. 18
REFERENCES CONTD.
19. • Sharpe W. P., 1984. Logic Programming for the Law. Research and Development in
Expert System. Cambridge University Press., pp 217 – 228.
• Shortliffe E. H., 1976. Computer-based Medical Consultations: MYCIN. Elsevier,
North-Holland.
• Sowa J. F., 1984. Conceptual Structures: Information Processing in Mind and Machine.
Addison-Wiley Pub. Co.
• Trayner C., 1984. Expert Systems in Clinical Decision Support. Current Perspectives in
Health Computing. Kostrewski, B. (ed.), Cambridge University Press, pp 115 – 124.
• Wong H. R. T. and Mylopoulos J., 1977. Two Views of Data Semantics: A Survey of
Data Models in Artificial Intelligence and Database Management. International Journal
of Information System, Vol. 15, No. 3.
19
REFERENCES CONTD.
