Search

Video shreds of evidence are usually admissible in the court of law all over the world. However, individuals manipulate these videos to either defame or incriminate innocent people. Others indulge in video tampering to falsely escape the wrath of the law against misconducts. One way impostors can forge these videos is through inter-frame video forgery. Thus, the integrity of such videos is under threat. This is because these digital forgeries seriously debase the credibility of video contents as being definite records of events. This leads to an increasing concern about the trustworthiness of video contents. Hence, it continues to affect the social and legal system, forensic investigations, intelligence services, and security and surveillance systems as the case may be. The problem of inter-frame video forgery is increasingly spontaneous as more video-editing software continues to emerge. These video editing tools can easily manipulate videos without leaving obvious traces and these tampered videos become viral. Alarmingly, even the beginner users of these editing tools can alter the contents of digital videos in a manner that renders them practically indistinguishable from the original content by mere observations. This paper, however, leveraged on the concept of correlation coefficients to produce a more elaborate and reliable inter-frame video detection to aid forensic investigations, especially in Nigeria. The model employed the use of the idea of a threshold to efficiently distinguish forged videos from authentic videos. A benchmark and locally manipulated video datasets were used to evaluate the proposed model. Experimentally, our approach performed better than the existing methods. The overall accuracy for all the evaluation metrics such as accuracy, recall, precision and F1-score was 100%. The proposed method implemented in the MATLAB programming language has proven to effectively detect inter-frame forgeries.

The ability of machine learning techniques to make accurate predications is increasing. The aim of this work is to apply machine learning techniques such as Support Vector Machine, Na&#239ve Bayes, Decision Tree, Logistic Regression, and K-Nearest Neighbour algorithms to predict the shelf life of Okra. Predicting the shelf life of Okra is important because Okra becomes harmful for human consumption if consumed after its shelf life. Okra parameters such as weight loss, firmness, Titrable Acid, Total Soluble Solids, Vitamin C/Ascorbic acid content, and PH were used as inputs into these machine learning techniques. Support Vector Machine, Na&#239ve Bayes and Decision Tree each accurately predicted the shelf life of Okra with accuracies of 100%. However, the Logistic Regression and K-Nearest Neighbour achieved 88.89% and 88.33% accuracies, respectively. These results showed that machine learning techniques especially Support Vector Machine, Na&#239ve Bayes and Decision Tree can be effectively applied for the prediction of Okra shelf life.

Investigations towards studying terrorist activities have recently attracted a great amount of research interest. In this paper, we investigate the use of the Apriori algorithm on the Global Terrorism Database (GTD) for forensic investigation purposes. Recently, the Apriori algorithm, which could be considered a forensic tool, has been used to study terrorist activities and patterns across the world. As such, our motivation is to utilise the Apriori algorithm approach on the GTD to study terrorist activities and the areas/states in Nigeria with high frequencies of terrorist activities. We observe that the most preferred method of terrorist attacks in Nigeria is through armed assault. Again, our experiment shows that attacks in Nigeria are mostly successful. Also, we observe from our investigations that most terrorists in Nigeria are not suicidal. The main application of this work can be used by forensic experts to assist law enforcement agencies in decision making when handling terrorist attacks in Nigeria.

Recently, there has been a tremendous increase of failure rate in higher institutions. Often times, students of tertiary institutions drop-out of school or end up with certain classes of degrees that are far lesser than their ideal intellectual capabilities. As fresh students enroll into higher institutions, some may not even know what a class of degree is, and the level of work that is likely to place them in a particular class of degree. Predicting their academic performance in this wise becomes necessary to ascertain the future of their performances in order to make informed decisions. Traditionally, we find out “who failed in an examination” or who “passed in an examination”. However, predictions usually finds out who is likely to fail and who is likely to pass an examination and to what extent the failure or pass could be. Hence, predictions serve as counseling tool for the students to either improve their work rate or maintain their rate to achieve higher performance in subsequent examinations. In this paper, we predicted the academic performance of Benue State University students using linear regression. Linear regression assumes a linear relationship between the dependent variables (x) and an independent variable (y) such that the slope (predicted) can be specifically calculated from a computational linear combination of the variables x and y. Our proposed system correctly predicted the performance of mathematics/computer science students of the Benue State University with an accuracy of up to 100%.

Severe outbreaks of infectious disease occur throughout the world with some reaching the level of international pandemic: Coronavirus (COVID-19) is the most recent to do so In this paper, a mechanism is set out using Zipf’s law to establish the accuracy of international reporting of COVID-19 cases via a determination of whether an individual country’s COVID-19 reporting follows a power-law for confirmed, recovered, and death cases of COVID-19 The probability of Zipf’s law (P-values) for COVID-19 confirmed cases show that Uzbekistan has the highest P-value of 0 940, followed by Belize (0 929), and Qatar (0 897) For COVID-19 recovered cases, Iraq had the highest P-value of 0 901, followed by New Zealand (0 888), and Austria (0 884) Furthermore, for COVID-19 death cases, Bosnia and Herzegovina had the highest P-value of 0 874, followed by Lithuania (0 843), and Morocco (0 825) China, where the COVID-19 pandemic began, is a significant outlier in recording P-values lower than 0 1 for the confirmed, recovered, and death cases This raises important questions, not only for China, but also any country whose data exhibits P-values below this threshold The main application of this work is to serve as an early warning for World HealthOrganization (WHO) and other health regulatory bodies to perform more investigations in countries where COVID-19 datasets deviate significantly from Zipf’s law To this end, this paper provide a tool for illustrating Zipf’s law P-values on a global map in order to convey the geographic distribution of reporting anomalies © 2021, International Journal of Advanced Computer Science and Applications All Rights Reserved

Severe outbreaks of infectious disease occur throughout the world with some reaching the level of an international pandemic: Coronavirus (COVID-19) is the most recent to do so. As such pandemics cause extensive loss of lives, hamper industrial operations, and cause economic losses in both developing and developed countries, it is critical to establish common standards of accuracy in the determination and reporting of cases. In particular, there are current concerns that countries are hiding or incorrectly reporting cases of COVID-19. In this paper, we set out a mechanism for using Zipf's law to establish the accuracy of international reporting of COVID-19 cases via a determination of whether an individual country's COVID-19 reporting follows a power-law for confirmed, recovered, and death cases. We observe that the probability of Zipf's law (P-values) for COVID-19 confirmed cases show that Uzbekistan has the highest P-value of 0.940, followed by Belize (0.929), and Qatar (0.897). For COVID-19 recovered cases, Iraq had the highest P-value of 0.901, followed by New Zealand (0.888), and Austria (0.884). Furthermore, for COVID-19 death cases, Bosnia and Herzegovina had the highest P-value of 0.874, followed by Lithuania (0.843), and Morocco (0.825). China, where the COVID-19 pandemic began, is a significant outlier in recording P-values lower than 0.1 for the confirmed, recovered, and death cases. This raises important questions, not only for China but also any country whose data exhibits P-values below this threshold. The main application of this work is to serve as an early warning for the World Health Organization (WHO) and other health regulatory bodies to perform more investigations in countries where COVID-19 datasets deviate significantly from Zipf's law. To this end, we also provide a tool for illustrating Zipf's law P-values on a global map in order to report anomalies.

Recently, Benford’s law and Zipf’s law, which are both statistical laws, have been effectively used to distinguish between authentic data and fake data. Some similarities that exist between Benford’s law and Zipf’s law are that both of these laws are classified as natural laws. Also, both laws are Power laws and it is expected that distributions that follow Benford’s law should also follow Zipf’s law. Even though both laws have similarities, there exist some differences between these two laws. Benford’s law establishes a relationship between digit and frequency. In contrast, Zipf’s law shows a relationship between rank and frequency. Another difference that exists between these two laws is that Benford’s law applies to numeric attributes, whereas Zipf’s law applies to both numeric and string attributes. In this chapter, we perform a comparative analysis of these two laws on network traffic data and to determine whether they follow these laws and discriminate between non-malicious and malicious network traffic flows. We observe that both the laws effectively detected whether a particular network was non-malicious or malicious by investigating its data using these laws. Furthermore, we observe that the initial Benford’s law chi-square divergence values obtained seem to be inversely proportional to Zipf’s law P-values, which can be potentially exploited for intrusion detection system applications. These passive forensic detection methods when properly deployed to analyse network traffic data in Nigeria will save the Nigerian cyber space from malware and related attacks.

The number of Nigeria’s mobile subscribers reached 150 million users in 2017 [1]. For forensic experts and security experts, this is a great concern in terms of using the right security tools to investigate these devices when they are used for crime purposes. More strangely, most of the crimes that occur in Nigeria are performed on these digital devices and there is lack of evidence from these devices for admissibility in the court of law. Due to this challenge, a digital surveillance software (A-BOT) is proposed to secure Nigeria’s cyber space and mobile devices from being used for cyber crimes and related crimes. Proper usage of A-BOT will serve as digital surveillance and prevent digital crimes in Nigeria.

With the increase in the number of character assassination and fake news recently happening in Nigeria, we combine Zipf’s law and Benford’s law to analyse and detect fake news. The problem of fake news has become one of the most prominent issues in Nigeria recently. In this chapter, the challenges fake news poses to Nigeria is briefly presented. Due to these challenges, we propose the combination of Benford’s law and Zipf’s law in news analysis such that the hybrid of the two laws will obey the Power law for real news and deviate for fake news. We carried out various tests on different real news sources and the result shows that real news obeys the Power law. We, therefore, propose that fake news should not obey the Power law even though we could not test on fake news sources because of the lack of verified fake news dataset.

Issues relating to cybersecurity and its challenges in Nigeria can be traced as far back as the provision of Internet services to Nigerians in 1996. Nigerians are known for the huge frauds they commit using the Internet. This chapter treats cybersecurity challenges/conflicts history in Nigeria. Furthermore, it looks at the relevant laws guiding against cyber crimes in Nigeria. Lastly, the need for embracing cybersecurity and mobile device forensics is encouraged.

Generally speaking, forensic science is targeted towards crime investigation. A crime is defined as “ an offensive act against society that violates a law and its punishable by the government (Volonino et al. Computer Forensics: Principles and Practices. Prentice-Hall Inc., 2006, [1]).” For an act to be considered a crime, it must violate a criminal law. Criminal laws are defined by statutes and they are in place to safeguard the public, human life, or private property (Volonino et al. Computer Forensics: Principles and Practices. Prentice-Hall Inc., 2006, [1]). Again, it’s the government’s obligation to punish offensive acts committed by individuals. This means that crimes committed to individuals are punished by the government and not by the individual the crime is committed to. In this chapter, we will explore the different subdivisions of forensic science and how they are applied to tackle crimes.

This chapter aims at giving the reader an insight into how forensic science will positively impact the lives of Nigerians and how bodies/institutions formed by the Nigerian government could positively benefit from this discipline if properly implemented. Furthermore, it analyses the legal aspect that Nigeria needs to adopt to make the application of forensic science a reality.

For several years, forensics and biometrics domain have benefited from one another. This chapter explains the importance of forensics and biometrics. It further looks at how the Power laws (Benford’s law and Zipf’s law) have been effectively used for crime investigations in different areas.

The History of forensic science is a key to understanding where we were, and where we are now in issues relating to crime investigations. Forensics originates from the latin word ‘forensis’ which means ‘a forum’. Generally, Forensic is an adjective which refers to “of or used in courts of law or forensic science.” In recent times, forensics (used interchangeably with forensic science) is closely related to legal issues, the court, and different disciplines. In academic literature, forensic science could be traced as far back as the end of the 19th century. Forensic science is of great importance when we need to present evidence to the court of law to either convict or acquit a suspect of a particular crime. Unfortunately, Nigeria and other African countries have not utilised the advantages of forensic science in solving the numerous crimes that happen in this continent. With the proper usage of forensic science, the evidence acquired could be used in the court of law to fight crimes. In this chapter, the history of forensic science is carefully covered and some lessons learnt from reviewing this history is presented.

The different domains of forensic science and their applications are discussed in 3. This chapter reviews the forensic tools used in different domains and how they are used to tackle crimes. The Tables below shows the domain, tool, description and the platforms each of the forensic tool operates. This is not a full list of all the forensic tools. They are only chosen for illustrative purposes.

It is obvious that tampering of raw biometric samples is becoming an important security and privacy concern. The Benford's law, which is also called the first digit law, has been reported in the forensic literature to be very effective in detecting forged or tampered data. In this chapter, besides an introduction to the concept and state-ofthe-art reviews, the divergence values of Benford's law are used as input features for a neural network for the classification of biometric images. Experimental analysis shows that the classification of the biometric images can achieve good accuracies between the range of 90.02% and 100%.

Alzheimer's disease (AD) is a neurodegenerative disease caused by the progressive death of brain cells over time. It represents the most frequent cause of dementia in the western world, and affects an individual's cognitive ability and psychological capacity. While clinical diagnoses of AD are made primarily on the basis of clinical evaluation and mental health tests, diagnostic certainty is only possible through necropsy. One non-invasive approach to investigating AD is to use electroencephalograms (eEGs), which reflect brain electrical activity and so can be used to detect electrical abnormalities in brain signals with non-invasive cranial surface electrodes. Generally EEGs in AD patients show a shift to lower frequencies in spectral analysis and display less complexity and contain more regular patterns compared to those of control subjects. Here we present a method for differentiating AD patients from healthy ones based on their EEG signals using Benford's law and support vector machines (SVMs) with a radial basis function (RBF) kernel. EEG signals from eleven AD and eleven age-matched controls were divided into artefact-free 5-sec epochs and used to train an SVM. 10 fold cross validation was performed at both the epoch- and subject-level to evaluate the importance of each electrode in discriminating between AD and healthy subjects. Substantive variability was seen across the different electrodes, with electrodes O1, O2 and C4 particularly being important. Performance across the electrodes was reduced when subject-level cross validation was performed, but relative performance across the electrodes was consistent with that found using epoch-level cross validation.

It is obvious that tampering of raw biometric samples is becoming an important security concern. The Benford’s law, which is also called the first digit law has been reported in the forensic literature to be very effective in detecting forged or tampered data. In this paper, the divergence values of Benford’s law are used as input features for a Neural Network for the classification and source identification of biometric images. Experimental analysis shows that the classification and identification of the source of the biometric images can achieve good accuracies between the range of 90.02% and 100%.

© 2015 IEEE.Rendering a face recognition system robust is vital in order to safeguard it against spoof attacks carried out using printed pictures of a victim (also known as print attack) or a replayed video of the person (replay attack). A key property in distinguishing a live, valid access from printed media or replayed videos is by exploiting the information dynamics of the video content, such as blinking eyes, moving lips, and facial dynamics. We advance the state of the art in facial antispoofing by applying a recently developed algorithm called dynamic mode decomposition (DMD) as a general purpose, entirely data-driven approach to capture the above liveness cues. We propose a classification pipeline consisting of DMD, local binary patterns (LBPs), and support vector machines (SVMs) with a histogram intersection kernel. A unique property of DMD is its ability to conveniently represent the temporal information of the entire video as a single image with the same dimensions as those images contained in the video. The pipeline of DMD + LBP + SVM proves to be efficient, convenient to use, and effective. In fact only the spatial configuration for LBP needs to be tuned. The effectiveness of the methodology was demonstrated using three publicly available databases: 1) print-attack; 2) replay-attack; and 3) CASIA-FASD, attaining comparable results with the state of the art, following the respective published experimental protocols.

The selection and application of biometrics traits for authentication and identification have recently attracted a significant amount of research interest. In this paper we investigate the use of keystroke data to distinguish between humans using keystroke biometric systems and non-humans for auditing application. Recently, Benford’s Law and Zipf’s Law, which are both discrete Power law probability distributions, have been effectively used to detect fraud and discriminate between genuine data and fake/tampered data. As such, our motivation is to apply the Benford’s Law and Zipf’s Law on keystroke data and to determine whether they follow these laws and discriminate between humans using keystroke biometric systems from non-humans. From the results, we observe that, the latency values of the keystroke data from humans actually follow the Benford’s law and Zipf’s law, but not the duration values. This implies that, latency values from humans would follow the two laws, whereas the latency values from non-humans would deviate from the Benford’s law and Zipf’s law. Even though, the duration values from humans deviates from the Benford’s law, they do follow a pattern that we can develop an accurate model for the duration values. We perform experiments using the benchmark data set developed by Killourhy and Maxion, CMU [1] and obtain divergences of 0.0008, 0.029 and 0.05 for the keyup-keydown (latency), keydown-keydown, and duration of the keystroke data, respectively. Moreover, P-value’s of 0.7770, 0.6230 and 0.0160 are obtained for the keyup-keydown (latency), keydown-keydown, and duration of the keystroke data, respectively. We observe that the latency (which is the time elapsed between release of the first key and pressing down of the next key) is one of the most important features used by administrators for auditing purposes to detect anomalies during their employees logging into their company system.

Tampering of biometric samples is becoming an important security concern. Tampering can take place at the sensor level (spoofing), and through the backend, e.g., replacing the template with another sample. One example of backend attack is manipulating the original biometric image, i.e. contaminating the template. We study one particular aspect of tampering: image manipulation. In the forensics literature, Benford's law has been reported to be very effective in detecting tampering of natural images. In this paper, our motivation is to examine whether biometric images will follow the Benford's law and whether or not they can be used to detect potential malicious tampering of biometric images. We find that, the biometric samples do indeed follow the Benford's law; and the method can detect tampering effectively, with Equal Error Rate (EER) of 0.55% for single compressed face images, 2.7% for single compressed fingerprint images, 4.3% for double compressed face images and 3.7% for double compressed fingerprint images.