Browse
Recent Submissions
Now showing 1 - 5 of 1934
- ItemPrivacy Preservation in Data Mining through Geometric Transformation(KNUST, 2018-04) Atua Lawson AyaabilaThere are a number of benefits that data mining provides. However, because data mining deals with massive data stored in databases or other electronic formats, there have been issues of ethics and privacy violations. The purpose of privacy preserving data mining (PPDM) algorithms is to mine significant information from huge amounts of data while protecting sensitive information against unauthorized use. This work was undertaken to test and experiment two main PPDM algorithms. The focus of this work is on numerical attributes which are considered to be confidential. The dilation algorithm adopted multiplicative data perturbation and the translation implemented additive data perturbation. After conducting series of experiments, the results were validated using statistics, tree structure, Receiver Operating Characteristics (ROC) curve and confusion matrix. Also the levels of privacy provided by the two PPDM algorithms were quantified. It was realised that the algorithms can be described as restrictive and so Privacy Enhancement Procedure (PEP) was instituted to improve the levels of privacy provided by the two algorithms. After the implementation of Privacy Enhancement Procedure (PEP), it was discovered that the level of privacy can be improved but is highly dependent on values given to the lower bound and upper bound. The knowledge discovery is done using the University of Waikato open source data mining software – Waikato Environment Knowledge Analysis (WEKA). It can be concluded that the PPDM algorithms used in this work can provide a good level of privacy when adopted to protect the privacy of data mining participants. Typically the dilation changed the lowest age and income values in the original dataset from 69 and 2100 to 15 and 728 respectively.
- ItemModeling Water Consumption Using Time Series Analysis. Case Study: Tamale Metropolis, Ghana(KNUST, 2018-05) Eric KojoWater supply system is the base of a city development, the protection of people’s daily lives and the indispensable material conditions of social development, production and construction. The rapid growth of the Tamale Metropolis has for years back caused severe strains on water supply to the metropolis. Population growth in the metropolis has led to gradual increase in water consume and subsequent water shortage in the metropolis, which may be apparent over a span of several years. To curtail this continuous shortage of water and to develop a rational urban growth plan for the metropolis, it is imperative to estimate the future need of water consumption of the people in the Metropolis. Water consumption of certain future period usually is associated with the past, the present and future water supply system operating conditions. The purpose of this research is to identify the best fit time series model to water consumption data in the Tamale Metropolis and to use it to forecast water consumption in the fourth coming years in the Metropolis. Time series models including ARIMA and SARIMA were fitted to the data collected from Ghana Water Company Limited in the Tamale Metropolis of the Northern Region of Ghana spanning 13 years (2002-2014) on monthly basis. The empirical study suggests that the most adequate model for the data is SARIMA(4,1,1) × (0,1,1)12. The model is used to forecast monthly water consumption by residents and businesses for sixty months from 20152019 in the metropolis.
- ItemThe Impact Of Subnetting And Supernetting On Tcp/Ip Network(KNUST, 2018-06) Asare ErasmusThe purpose of this study is to identify the impact of subnetting and supernetting on TCP/IP Networks. Subnetting was introduced with RFC 950 for more efficient usage of IP addresses. Subnetting creates supplementary network IDs at the expense of host IDs. The inverse of subnetting is supernetting which creates more host IDs at the expense of network IDs. This study used network simulations in GNS3 and Wireshark application to capture packets on the simulated networks for exploration. The following parameters were measured: jitter, latency, broadcast, efficient use of Internet Protocol (IP) addresses and size of routing tables. The study was carried out with 410 computers placed on a single Class B network. The network was later subnetted into four subnets. Again, two Class C networks were supernetted with the same number of computers. The idea was to find out the network latency, jitter and speed by pinging. The results were used to determine the efficacy of each of the networks. The subnetted network was further configured with Variable Length Subnet Masks and routing protocols to verify limitations set on routing protocols. Based on the findings, subnetting showed up to have very high jitter and latency during cross-subnets transmissions and very less jitter and latency during packets transmission within a single subnet. Moreover, the subnetted network conserved IP addresses and had a reduced broadcast size as compared to that of the non-subnetted and supernet which were very high. However, subnetting caused bloated routing tables and no support for classful routing protocols using Variable Length Subnet Masks. Supernetting on the other hand, reduced the size of routing tables and conserved IP addresses as well.
- ItemAssessing Dietary Pattern And Its Association With Hypertension Among The Elderly In The Tano North District In The Brong Ahafo Region, Ghana(KNUST, 2018-06) Helina GyameaHypertension has become a major contributor to the burden of cardiovascular related morbidity and mortality in the world. Diet has been identified as one of the key modifiable risk factors in the development of hypertension especially among the elderly in low and middle income countries due to changes in dietary patterns. This study investigated dietary patterns and determined their correlation with hypertension among the aged in Ghana. A cross-sectional survey was conducted among six communities (three urban and three rural) in the Tano North district in Brong Ahafo Region of Ghana. Anthropometric measurements including height, weight, Waist-to- height ratio, Body Mass Index, together with clinical assessments (systolic and diastolic blood pressure) were also taken. Habitual pattern of dietary intake was measured using the Food Consumption Score. The FCS was measured based on eight classified major food groups. In all, 198 individuals were enrolled from 205 households visited. Participants were 55 years and above. Analysis revealed 12.6%, 27.3% and 60.1% of food consumption being the prevalence for poor, mild and acceptable dietary patterns respectively. The results also revealed 10.1% and 46.0% prevalence of mild and high blood pressure levels, respectively, among the respondents. A chi square test revealed an association between dietary pattern and high blood pressure level (X22=12.777, p=0.012). Multinomial regression analysis was conducted and associations were measured using crude and adjusted ratios at the 0.05 level of significance. The odds of elderly with poor dietary pattern (food insecure) having mild hypertension was 5.989 (CI, 1.661, 21.598; P=0.006) with association persisting even after controlling for cofounders. No association was however found between acceptable dietary pattern and high blood pressure level after controlling for other potential factors in the regression model. Family History of BP, poor dietary pattern and locality predictedblood pressure status among the study population. Higher diet score (representing healthy diet or food secured) remains a significant protective factor for hypertension (60.1%), attempts should therefore be made to improve upon the living standards of the aged for an improved life. In conclusion, dietary pattern, when modelled with appropriate control is associated with an increased risk of hypertension among the aged.
- ItemAssessing The Effect Of Monitoring Equipment On Patient Health In A Standard Hospital(KNUST, 2018-06) Anakwa RuthA hospital based cross sectional study was used to assess impacts of monitoring equipment on patients’ health in a standard hospital. The main objective of the study was to determine the impact of monitoring equipment on patients’ health in a standard hospital. A cross-sectional study was used to determine the impact of monitoring equipment on patients’ health in a standard hospital in which a purposive sampling technique was used to select 180 patients who were put on 6 monitoring equipment in groups of 30 at the Komfo Anokye Teaching Hospital. Other secondary information was gathered from documentary source in the form of reports, records and review of literature from the various sources. Patients who went through dialysis, 66.6% of them had their temperature increased and this difference is statistically significant (p=0.004). However, 63.3 % of the respondents recorded no change in their temperature after going through computer topography (CT) and ultrasound scans. The results also indicate that 76.6% had their weight reduced after going through dialysis and the difference is statistically significant p=0.003. The study further found out that most of the respondents (80.0%) recorded an increase in their blood pressure after going through dialysis procedure the difference is statistically significant with systolic(p=0.011) and diastolic(0.005). However, majority of the respondents recorded no change in their blood pressure after ultrasound and CT scan. However, more than 70% recorded no change in their pulse after going through CT and ultrasound scan. In conclusion, findings from this study show that there may be negative impacts of monitoring equipment on patients’ health as temperature and others rise as one goes through some of these procedures. It is recommended that further research should include effect of monitoring equipment on body temperature, pule rate, weight and blood pressure as little research has been done in this area.