Anale. Seria Informatica

 Conference

 SIMULATION OF AN INTELLIGENT TRAFFIC LIGHT SYSTEM EMBEDDED TECHNIQUE

 Owolafe Otasowie, Olanrewaju Olufemi Sunday

 2018

The level of urbanization in developing nations indicates that more people live in cities than before. This increase heaviness on traffic flow and makes living in urban area complex. Traffic control at road junction which was done purely by human effort and expansion of roads remain inefficient owing to the increasing rate of both motorists as well as the complexity of road networks. This paper proposes that an intelligent traffic light in addition to existing traffic management techniques should be put in place to monitor traffic congestions. The traffic light system is designed using arduino uno microcontroller, ultrasonic sensor, liquid crystal display and light emitting diode (LED). For effective traffic control, the controller was programmed using C language. The designed traffic light control system was simulated on cardboard and using toy cars as model of the real vehicle. 

 International Journal Of Computer Applications

 Journal

 Towards Detecting Deception Using K-Nearest Neighbour Model

 Owolafe Otasowie , Alese Bonifacem K. Adewale Olumide S

 2018

Security over the years remains a major concern of all especially the law enforcement agencies. One way of arresting this concern is to be able to reliably detecting deception. Detecting deception remains a difficult task as no perfect method has been found for the detection. Past researches made use of a single cue (verbal or nonverbal), it was found that examining combinations of cues will detect deception better than examining a single cue. Since no single verbal or nonverbal cue is able to successfully detect deception the research proposes to use both the verbal and nonverbal cues to detect deception. Therefore, this research aims to develop a KNN model for classifying the extracted verbal, nonverbal and VerbNon features as deceptive or truthful. The system extracted desired features from the dataset of Perez-Rosas. The verbal cues capture the speech of the suspect while the nonverbal cues capture the facial expressions of the suspect. The verbal cues include the voice pitch (in terms of variations), frequency perturbation also known as jitters, pauses (voice or silent), and speechrate (is defined as the rate at which the suspect is speaking). The Praat (a tool for speech analysis) was used in extracting all the verbal cues. The nonverbal features were extracted using the Active Shape Model (ASM). The work was implemented in 2015a MatLab. The classification was done using KNN model. KNN performed well with VerbNon dataset with a percentage score of 96.2% 

 IJCA

 Journal

 Towards Detecting Deception Using K-Nearest Neighbour Model

 Otasowie Owolafe, Oluwaseun Bosede Ogunrinde, And Aderonke Favour-Bethy Thompson

 2018

Security over the years remains a major concern of all especially the law enforcement agencies. One way of arresting this concern is to be able to reliably detecting deception. Detecting deception remains a difficult task as no perfect method has been found for the detection. Past researches made use of a single cue (verbal or nonverbal), it was found that examining combinations of cues will detect deception better than examining a single cue. Since no single verbal or nonverbal cue is able to successfully detect deception the research proposes to use both the verbal and nonverbal cues to detect deception. Therefore, this research aims to develop a KNN model for classifying the extracted verbal, nonverbal and VerbNon features as deceptive or truthful. The system extracted desired features from the dataset of Perez-Rosas. The verbal cues capture the speech of the suspect while the nonverbal cues capture the facial expressions of the suspect. The verbal cues include the voice pitch (in terms of variations), frequency perturbation also known as jitters, pauses (voice or silent), and speechrate (is defined as the rate at which the suspect is speaking). The Praat (a tool for speech analysis) was used in extracting all the verbal cues. The nonverbal features were extracted using the Active Shape Model (ASM). The work was implemented in 2015a MatLab. The classification was done using KNN model. KNN performed well with VerbNon dataset with a percentage score of 96.2%. 

 Informing Science & IT Education

 Conference

 Contributory Indices To Cybercrime Activities In Nigeria.

 Akinyokun, O. K., Alese, B. K., Oluwadare, S. A., Iyare, O., & Iwasokun, G. B.

 2015

The arrival of Internet has turned the world into a global village where geographical location ordistance has to some extent ceased to be a major obstacle to communication and movement ofgoods and services. This development has also brought with it cybercrime and its level of sophistication.A lot of measures and institutions are being put in place to minimize the incidence ofcybercrime in different countries; also, efforts are being made to identify the contributing factorsto cybercrime. This research however, adopts a factor analytic approach to formulate the indicesthat may contribute to the perpetration of cybercrime. A total of seventy three (73) indices wereformulated and used to design a structured questionnaire which was administered on five classesof respondents, using purposive and simple random sampling techniques. The data obtained wereanalyzed by means of factor analysis by principal component using Statistical Package for SocialSciences (SPSS). Ten factors were extracted and subjected to orthogonal rotation using promax.The contributing factors identified in this study could assist stakeholders to combat the menace ofcybercrime. 

 Infonomics Society

 Journal

 A Web Based Information Security Risks Assessment Model

 B.K. Alese, O. Oyebade, O. Iyare, Osuolale A. Festus, A. F. Thompson

 2015

A risk is the possibility that an undesirable event could happen. Different methodologies have been proposed to assess and manage IT risks each of which is divided into processes and steps. Two specific methods of interest in this work are: “Risk Matrices” and “Risk Registers”. A generic Risk Register application module and an updatable Risk Matrix module were designed. This work studies risk management techniques and employs a custom model for the automated assessment of IS risks. This model was implemented in phases corresponding to its aspects. The “Assessment methods” of interest to this work are Risk Registers, Risk Matrices and the Scenario Geek”. What-if analysis is a data-intensive simulation whose goal is to inspect the behavior of a complex system under some given hypotheses called scenarios. What-ifs are used to generate qualitative descriptions of potential problems in the form of questions and responses lists of recommendations for preventing problems. The Risk Assessor was developed using Microsoft’s Visual Basic.Net with Active Server Pages (ASP.Net) Technologies on .Net Framework 4.0. The solution propounded in this work is a good risk management application that provides upward assurance from information technology security issues, business activities and administrative functions and ultimately to anyone that chooses to adopt it.

 

 Proceedings Of Informing Science & IT Education Conference (InSITE)

 Conferenceproceeding

 On Information Integrity Measurement With Secure Hash Algorithm (SHA)

 S. A. Ojo, A. F. Thompson, O. Iyare, And B. K. Alese

 2015

The “information age” as often referred to the modern society, has become heavily dependent on information systems. As this dependency increases, the threat to information security has also gained ground. Societies need to cater for the security of information, and this has led to the development of different information security techniques most notable of which is cryptography. Cryptographic Hash functions are used to achieve a number of security goals like authenticity, digital signatures, pseudo-random number generation, digital steganography, digital time stamping. The strength of a cryptographic hash function can be summarized into its vulnerability to attack and computational time. This work therefore, reviews existing standard cryptographic hash functions, their construction and their application areas. The secured hash function (SHA) was selected and implemented based on its comparative worth over others. The implemented cryptographic hash function is evaluated for performance using a cryptographic evaluation standard 

 International Journal Of Computer Applications

 Journal

 An Analytical Framework For Vision Testing In Driving License Allocation In Nigeria

 Adewale Olumide S., Ogundele Oloruntoba S., Iyare Otasowie

 2014

Allocation of Driving Licensing in Nigeria in the past was done haphazardly and as a result drivers with poor driving culture were usually allocated driving license. This probably was followed by unprecedented wave of road traffic accidents with attendant human and material losses. In other to reduce these losses, the federal road safety commission at its inception introduced some measures to curb the issue of licensing. This work, in line with the technological trend proposed an automated licensing scheme to improve on the efficiency of the previous system. The system was tested with 50 applicants and the result presented.

 

 WCE

 Conference

 Game-based Analysis Of The Network Attack-Defense Interaction

 Boniface K. Alese, Emmanuel O. Ibidunmoye, D.I. Haruna, Aderonke F. Thompson, Iyare Otasowie

 2014

The interactive behavior between the attacker and thedefender in a network environment is similar to informationwarfare where both attacker and defender may have severalavailable strategies to achieve maximum gratification. Theprocess of positioning security within a network environment issynonymous to a decision-making process. Security decisionmakinginvolves the allocation of scarce network securityresources to counter or mitigate security attacks. To ensureeffective security, security decision-makers must ensure that theresources are allocated and deployed in the most optimummanner. Game theory provides a quantitative framework for theanalysis and modeling of such network security cases. Gametheoreticmodels view network security scenarios as anoptimization game comprising of multiple players notably theattackers (malicious users) and the defenders (systemadministrators) and has become a major source of attraction insecurity research. These types of games are referred to assecurity games. Security games and their solutions are potentialtools for security decision making and algorithm development aswell as for predicting attacker behavior. In this paper, we firstexplore the fundamentals of game-theory with respect to security,and then presents a two-player zero-sum game model of theinteraction between malicious users and network administrators.A description of the major components of such game is presentedand a solution technique for solving such game scenario isproposed. We then describe how expected results can be analyzedto show the optimality of resulting strategies and how they maybe employed by system administrators to better protect thenetwork. 

 WCE

 Conference

 A Telepathology Model Using JPEG Algorithm For Histological Image Compression

 Boniface K. Alese, Adebowale J. Adelakun, Otasowie Iyare, Oloruntoba S. Ogundele

 2014

The specific objectives of the research were toexamine the efficacy of Discrete Cosine Transform (DCT) asan image compression algorithm using the Joint PhotographicExpert Group (JPEG) standard; and determine the suitabilityor otherwise of application of DCT on images required forCollaborative Pathological diagnosis. Seven histological imagesacquired with the use of Digital microscope from theUniversity of Alberta, Canada were sent by e-mail by the LeadPathologist to the researcher in Nigeria. These werecompressed using GNU Image Processing software (GIMP, athird party freeware) at 25% and 50% factor and presentedrandomly to researchers. The result showed that JPEG isefficient in compression of medical images because the imagescompressed at 25% factor were reduced from between 22% -32%. The ones compressed at 50% factor were reducedbetween 15% - 20% which revealed that though the JPEGalgorithm does not reduce images literarily based on the factorof reduction, size reduction is still significant. The conclusiontherefore is that the DCT is an efficient image compressionalgorithm and that using JPEG for telepathology systems isnot only suitable but desirable because of the various practicalusefulness to providing cost effective pathology services to therural areas of the developing world. 

 IAENG

 Conference

 On Forensics Investigation Models

 Eso Dieko, Alese Boniface K., Thompson Aderonke F. And Iyare Otasowie

 2014

In any court case, the technical expert’s evidence isopen to legal challenge and such challenges, irrespective of theoutcome, might delay the process of litigation. Hence, it ispertinent that the investigator and expert pre-empt any delayby making the report as comprehensive and complete aspossible. The investigator can thus follow a digital forensicprocess model to aid the digital investigation. The challengetherefore in digital forensics is to find and discover forensicallyinteresting, suspicious or useful patterns within often verylarge data sets. Consequently, this paper presents a dynamic,adaptive clustering model to arrange unstructured documentsinto content-based homogeneous groups. The documentclustering framework, based on kernel k-means which relies onRadial Basis Function (RBF) has demonstrated can profitablysupport intelligence and security activities in identifying,tracking, extracting, classifying and discovering patterns, sothat the outcomes can generate alert notifications accordingly.Also, the method can generate consistent structures forinformation access and retrieval.