KCA University Institutional Repository
Not a member yet
1075 research outputs found
Sort by
A Crypto-ransomware Detection Model For The Pre-encryption Stage Using Random Forest Algorithm
Get PDFCryptographic ransomware is a challenging cybersecurity threat that encrypts the victim's files and demands a ransom in exchange for the decryption key. Traditional signature-based protection methods, such as antivirus and anti-malware, have proven in-effective at preventing crypto-ransomware attacks, therefore the production of ransomware is on the rise. Additionally, crypto ransomware incorporates advanced encryption algorithms causing irreversible effects even if the victim chooses to pay the ransom. Given the magnitude and variety of threats we face today, it is critical to have solutions in place to effectively analyse and detect crypto-ransomware attacks during the pre-encryption stage before encryption happens. Only if these threats are identified during the pre-encryption phase can they be adequately mitigated. Existing methods for early detection of crypto ransomware rely on a timing thresholding methodology to set the border of the pre-encryption stage. However, the fixed time threshold strategy, suggests that the samples begin encryption at the exact moment. This is not always the case since timing varies between crypto-ransomware families as a result of the obfuscation techniques used to evade detection. Furthermore, scarcity of data during an attack's initial stages reduces the ability of feature extraction algorithms in early detection solutions to discover attack features lowering detection accuracy. This research, therefore, proposed development of a Dynamic Crypto-Ransomware Detection Model (DCRDM). DCRDM monitors the pre-encryption stage for every case separately relying on the initial appearance of any APIs related to cryptography to establish the pre-encryption stage boundary, whereby features are extracted and used in training a prediction model using the Random Forest machine learning algorithm. The sample data was obtained from widely used ransomware repositories. The model achieved a detection accuracy of 98.6% with False Positive Rate of 1.9%
Machine Learning Model For Classifying Fake News In Kenya
Get PDFThe revolution in the digital age to the information age to the growth of social
networks into go-to news sources and primary information pools has seen a
change in the conventional approach to political information dissemination. This,
unfortunately, also saw social media abuse through targeted mis- and dis-information to sway public opinion for political gain. Applied machine learning
was a solution that bears promise. This research proposal explored the next level
in Automated Machine learning to track and classify fake news in the Kenyan
environment targeted on the Facebook Platform by applying Natural Language
Processing at scale in renowned cloud computing frameworks.
This study would build multiple models and select the superior one for the final
deployment of inaccurate word scenarios
Digital Forensics Framework For Combating Cyber-crime
Get PDFOffenders use digital devices and networks to facilitate their crimes and hide their identities,
Information technology systems are attacked creating new challenges for digital investigators.
Malicious programs that exploit vulnerabilities also serve as threats to digital investigators. Since
digital devices such as computers and networks are used by organizations and digital investigators,
malicious programs and risky practices that may contaminate the integrity of digital evidence can
lead to the loss of critical evidence. For some reason, digital investigators face a major challenge
in preserving the integrity of digital evidence. Not only is there no definitive comprehensive digital
forensics investigation framework for ensuring digital evidence reliability but there has to date
been no intensive research into methods of doing so.
The aim of the study was to develop an efficient digital forensics framework for combating
cybercrime. Additionally, the study aimed to assess existing frameworks used for combating
cybercrime with a view to identifying existing gaps, develop an efficient framework for
investigating digital crimes based on the universal standard for digital forensic investigation
ISO/IEC 27043:2015 and finally validate the developed framework and evaluate its performance
compared to other existing frameworks. The study utilized a quasi-experimental and descriptive
research design and a target population of 105 participants which are officers drawn from the entire
communication Authority digital forensics and investigation department.
The study concluded that digital forensic investigations require an efficient framework digital
forensic examiners must adhere to a well-defined procedure that goes beyond technical
requirements. As a result, we must examine previous efforts and forensic frameworks in depth.
Therefore, a formal and methodical approach is required to provide a framework for analyzing and
reasoning the requirements of digital investigations. In addition, anti-forensics situations and
processes make the forensic investigation process challenging by contaminating any stage of the
investigation process, its requirements, or by destroying the evidence
The Effect Of Human Capital Management Practices On Employee Retention In Large Manufacturing Companies In Kenya
Get PDFEmployee retention is vital as it brings implications for organizational competitiveness in an
increasingly global landscape. “Retaining key employee is a vital source of competitive
advantage for any organization. The general objective of this study was to establish the effect of
human capital management practices on employee retention in manufacturing companies in
Kenya. The study research objectives was to determine the influence recruitment on employee
retention, training, job design and compensation on employee retention in manufacturing
companies in Kenya. The theories that inform the study are Resource-based theory, Job
characteristics theory and Expectancy theory. The population was 181 large manufacturing firms
and the sample size of 124. A Human resource manager was purposively selected from each of
the 124 manufacturing firms. The study adopted a descriptive research design. Primary data was
collected using questionnaire. The data was analyzed using descriptive and inferential statistics.
The study conducted normality test, multicollinearity and heteroscedasticity. A regression model
was used to test the effect of human capital management practices on employee retention
performance of manufacturing firms. The results indicated that recruitment and employee
retention is positively and significantly related. The results further indicated that training and
employee retention is positively and significantly related. The results further indicated that job
design and employee retention is positively and significantly related. Lastly, results showed that
compensation and employee retention is positively and significantly related. The study
concluded that human capital management practices on employee retention in large
manufacturing companies in Kenya. The study recommends that HR managers should endeavor
that their recruitment, selection and retention process always focuses businesses objectives. The
study recommends that HR managers should design specific training programmes that target this
group of employee with the aim of enhancing their readiness in taking up tasks and accepting
changes in the sector. Remuneration of employees who have upgraded should be reviewed
according to human resources policy
Effect Of Financial Innovation On Financial Performance Of Deposit Taking Savings And Credit Cooperative Societies In Kenya
Get PDFThe Savings and Credit Cooperative Societies (SACCO) in Kenya are today facing stiff
competition emanating from the mainstream banks, microcredit institutions, and recently,
digital credit, due to the modern-day technology, stringent regulatory requirements and the
dynamic customer demands. These have caused the declining membership in majority of
the cooperatives. Despite boasting of huge membership, their earnings cannot be compared
to those of commercial banks which post credible profits at the end on financial years.
Cooperative societies have therefore devised innovative ways in their operations to
enhance their competitiveness. The aim of this study was to investigate the effect of
financial innovation on the financial performance of cooperative societies in Kenya. The
specific objectives of the study were to examine the effect of product innovation on the
financial performance of cooperative societies in Kenya, assess the effect of service
innovation on the financial performance of cooperative societies in Kenya and to determine
the effect of process innovation on the financial performance of cooperatives in Kenya.
The study adopted a descriptive research design in which the population will be the 175
licensed deposit taking cooperatives by Sacco Society Regulatory Authority in Kenya. The
study samples 120 cooperative societies using simple random sampling and thereafter the
general managers from each of the selected cooperatives were selected purposively. The
study targeted the general managers of the cooperatives. Both primary and secondary data
were collected. Prior to actual data collection, the questionnaires were piloted for validity
and reliability. Data was analyzed using descriptive statistics namely percentages,
measures of central tendencies and frequency distribution. The researcher also used
multiple regression analysis to determine the relationship between the dependent and the
independent variables. The findings were presented in figures and tables. The study found
that all the contracts of financial innovation positively influenced the financial performance
of the SACCOs. The study found that the service innovation had the strongest influence
followed by process innovation. Among the innovations were the electronic funds transfer,
new deposit accounts, mobile banking, internet banking, automatic teller machines and the
front office service activity among others. The study therefore concludes that financial
innovation have positive effect on the financial performance of the cooperative societies.
The study recommended that the management of cooperatives should adopt more product
innovation, service innovation and process innovation to enhance the financial
performance of the societies. The study also recommended that the regulator should
formulate policies that will enhance use of financial innovation by the cooperative societies
such as use of incentives to encourage innovation or tax waiver on technology that
purchased by the societies for the purposes on enhancing their operations. Further, the
regulator should develop its surveillance structure to incorporate the adoption of financial
innovation by the societies particularly those struggling financially so as to boost their
efficiency and hence financial performance
Determinants Of Dividend Payout For Firms Listed At Nairobi Securities Exchange
Get PDFOver the years, dozens of theories have attempted to explain the dividends phenomenon with no
consensus reached. Many of the theories view agents as rational and dividends either serve as an
efficient way to resolve agency problems or as a signaling device to mitigate information
asymmetry problems. This study sought to establish the determinants of dividend payout ratio for
companies listed at the Nairobi Securities Exchange. The specific objectives of the study were to
determine the influence of profitability, liquidity, leverage and firm size on dividend payout ratio
for companies listed at the Nairobi Securities Exchange. The target population of the study were
all the 64 firms listed at the NSE as at 31st December 2021. However, one of the firms was listed
after 2017 while 5 were suspended remaining with 58 listed firms at NSE. Thus, a census of all
the 58 NSE listed firms was conducted. The study employed descriptive research design and
secondary data was collected for a period of 5 years, from 2017 to 2021. Data was analyzed
using descriptive statistics and panel data regression. Descriptive statistics involved determining
the mean, the standard deviation, skewness and kurtosis for each variable under study. Panel data
regression analysis established the nature and significance of the relationship between the study
variables. Stata version 16 was employed to analyze the data. The analyzed data was presented
using tables and charts. The findings of the study indicated that firm size, liquidity and
profitability of the companies listed at the Nairobi securities exchange had a positive and
statistically significant relationship with dividend payout. However, financial leverage was found
to have a positive but insignificant effect on the dividend payout of the listed firms under study.
The study recommended that the listed firms under study should focus on making their
operations cost efficient and effective to maximize profits and should invest some resources in
fixed assets but have more investments in liquid assets. The firms relying on loans to finance its
operations should not focus on paying dividends to its shareholders but the immediate focus of
these firms and finally the firms should focus on investing the profits accrued from the
operations of the company back to the company to grow the company and make it stable
Effect Of Digital Marketing Tools On Consumer Purchase Intention In The Motor Vehicle Industry In Nairobi
Get PDFGlobally, most industries have harnessed the potential of digital marketing tools in driving
consumer purchase intentions for their brands. Within the country we have seen various
industries incorporating digital marketing tools in their operations; however, within the motor
vehicle industry there has been limited investigation into this phenomenon. Industry reporting
has shown that there is volatility in vehicle sales in the country hence there is need to
examine whether digital marketing tools can determine the consumer purchase intention. The
study sought to establish the effect of social media marketing, website marketing and search
engine optimization on consumer purchase intention. The research was anchored on the
unified theory of acceptance and use of technology, theory of reasoned action and the
technology acceptance model. The study utilized a descriptive research design in determining
the relationship between the variables. The population for the study was drawn from the 197
registered motor dealers (new and second hand) that operate within Nairobi City County.
Using Yamane formula, the calculated sample size for this survey was 131 respondents. A
structured research questionnaire was used in data collection with Google forms used to
compliment the data collection procedures. The study instrument was pretested and checked
for validity and reliability. The collected data was analyzed using descriptive and inferential
statistical tests. Evidence from a mean analysis scores, show that firms in this sector have
embraced the use of digital marketing to a large extent. Factor analysis led to the extraction
of three factors that defined variations on consumer purchase intention to a great extent. The
study established a positive and significant relationship between digital marketing tools and
consumer purchase intention, while the third digital tool had a significant but negative effect
on the predicted variable. The study recommends the need for players in the auto mobile
industry to invest more on digital tools as the market place shifts grounds to the digital space
Changamoto Zinazowakumba Vijana katika Tamthilia ya Kitumbua Kimeingia Mchanga
No full textKatika ulimwengu wa sasa, kuna mabadiliko chungu nzima yanayoshuhudiwa duniani yanasababishwa na masuala anuwai kama vile maendeleo ya kiteknolojia pamoja na utandarithi yanayoathiri pakubwa maisha ya vijana. Nchini Kenya, vijana wana umuhimu wa kipekee kwani wanatekeleza majukumu muhimu sana katika kukuza uchumi wa nchi. Isitoshe, idadi ya vijana kote ulimwenguni imeendelea kuongezeka kila uchao na imepiku ile ya wazee. Kwa hivyo, ni nyema kujadili changamoto zinazowakabili na kupendekeza hatua za kukabiliana nazo. Lengo la utafiti huu lilikuwa ni kuchanganua changamoto zinazowakumba vijana pamoja na athari zake katika ya tamthilia ya Kitumbua Kimeingia Mchanga ya S.A Mohamed (2000). Mada hii ilichaguliwa kwa misingi kwamba vijana wanakumbwa na changamoto nyingi katika maisha yao zinazowaathiri kwa kiasi cha haja na kutinga juhudi za kuafikia jaala zao. Utafiti huu ulilenga kubainisha changamoto zinazowakumba vijana katika tamthilia hii na kutambua mbinu ambazo vijana hawa wanazua ili kukabiliana nazo. Nadharia ya Uhalisia ilitumika kwa sababu ilionekana kufaa zaidi kuchanganua changamoto zinazowakumba vijana. Hii ni kwa sababu changamoto hizi zina uhalisia mkubwa katika maisha yao. Madhumuni ya utafiti huu yalikuwa ni kuchunguza na kueleza namna changamoto za vijana zinavyojitokeza katika tamthilia ya Kitumbua Kimeingia Mchanga na kisha kubainisha hatua zinazochukuliwa kuzitatua changamoto hizo. Utafiti huu ni wa kimaelezo na kiudhamano kwani ulihusisha kuchanganua matini zinazohusiana na mada husika. Sampuli katika utafiti huu iliteuliwa kimakusudi kwani ndiyo ingempa mtafiti data aliyonuia kuipata. Ni bayana kuwa utafiti huu utaifaa jamii ya wasomi wanaoshughulikia maswala ibuka katika jamii
Weibull Distribution as the Choice Model for State-Specific Failure Rates in HIV/AIDS Progression
No full textThis study considered the problem of selecting the best single model for modeling state-specific failure rates in HIV/AIDS progression for patients on antiretroviral therapy with age and gender as risk factors using exponential, twoparameter, and three-parameter Weibull distributions. CD4 count changes in any two consecutive visits, the mean waiting time (μ), and transitional rates (λ) for remaining in the same state or transiting to a better or a worse state were analyzed. Various model selection criteria, namely, Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Log-Likelihood (LL), were used in each specific disease state. The Maximum Likelihood Estimation (MLE) method was applied to obtain the parameters of the distributions used. Plots of State-specific transition rates (λ) depicted constant, increasing, decreasing, and unimodal trends. Three-parameter Weibull distribution was the best for male patients and patients aged (40-69) years transiting in the states 1-2, 3-4, and 4-5, and 1-2, 3-4, and 5-6, respectively, and for male, female patients, and patients aged (40-69), remaining in the same state. Two-parameter Weibull distribution was the best for female patients and patients aged (20-39) years transiting in the states 1-2, 2-3, 4-5, and 1-2, 2-3, 3-4, respectively. Exponential distribution proved inferior to the other two distributions used
