6229 research outputs found
Sort by
Speech by Prof. Dickson Nyariki, Vice Chancellor, Murang'a University of Technology, on the occasion of the 6th graduation ceremony held on Tuesday, 29th November 2022 at the graduation ground.
No full textDeveloping Hybrid-Based Recommender System with Naïve Bayes Optimization to Increase Prediction Efficiency
No full textCommerce and entertainment world today have shifted to the digital platforms where customer preferences are suggested by recommender systems. Recommendations have been made using a variety of methods such as content-based, collaborative filtering-based or their hybrids. Collaborative systems are common recommenders, which use similar users’ preferences. They however have issues such as data sparsity, cold start problem and lack of scalability. When a small percentage of users express their preferences, data becomes highly sparse, thus affecting quality of recommendations. New users or items with no preferences, forms cold start issues affecting recommendations. High amount of sparse data affects how the user-item matrices are formed thus affecting the overall recommendation results. How to handle data input in the recommender engine while reducing data sparsity and increase its potential to scale up is proposed. This paper proposed development of hybrid model with data optimization using a Naïve Bayes classifier, with an aim of reducing data sparsity problem and a blend of collaborative filtering model and association rule mining-based ensembles, for recommending items with an aim of improving their predictions. Machine learning using python on Jupyter notebook was used to develop the hybrid. The models were tested using MovieLens 100k and 1M datasets. We demonstrate the final recommendations of the hybrid having new top ten highly rated movies with 68% approved recommendations. We confirm new items suggested to the active user(s) while less sparse data was input and an improved scaling up of collaborative filtering model, thus improving model efficacy and better predictions
The effect of habitat type on population distribution and abundance of Rothschilds Giraffe (Giraffa camelopardalis rothschildi) in Ruma National Park and Mwea National Reserve in Kenya
No full textThe Rothschilds giraffe is currently listed as vulnerable by the International Union for Conservation of Nature (IUCN). This is attributed to the loss of habitat due to human activities. This study examined the effect of habitat type on population structure and distribution of Rothschilds giraffe in Ruma National Park (RNP) and Mwea National Reserve (MNR) in Kenya. The study employed road transects to collect data on the number, age class and sex distribution in three habitat types, open, medium and closed. Data was collected along three road transects of equal lengths measuring 14.2 km in each site (RNP and MNR) for comparison. A driving speed of 20 km per hour was maintained along each transect for standardization of survey effort and a maximum giraffe detection rate. Photographic capture of the coat patterns of the right side of all the giraffes sighted within 500 m from the transect was done for identification of age classes. The field visits were replicated 12 times for each transect giving 36 replications for each site spread equally through wet and dry seasons from March 2017 to November 2018. The effect of habitat type on population structure and distribution was analysed using ANOVA and Tukey HSD to test for significant differences. T-test was used to compare the mean population size of giraffe across the wet and dry seasons. Coat pattern analysis for age class identification was done using WildID software. The findings indicated that MNR had more males to females compared to RNP that registered more females and calves. Habitat type had a significant effect on the distribution of giraffes. The giraffe population showed a preference for medium habitat types. The findings are key for the management of habitat quality for giraffe populations at the interface where conservation areas overlap with human land use
Sports Tourism Events and Socio-economic Well-being of the Host Communities: Motivations and Benefits from an Emerging Destination
No full textTravel and tourism industry has been considered as a major catalyst for local community development. As an alternative way of involving the host community in tourism activities directly, sports tourism aims to enable the hosts to earn income. Host community is an important stakeholder in tourism, their wellbeing is directly proportional to sustainable tourism. Nairobi city has hosted several sports tourism events for decades, but little has been documented on how such events promote the socio-economic wellbeing of the host community. This research sought to put sports tourism events into limelight by looking at the perceived motivational factors behind hosting of sports tourism events and to assess the socio-economic benefits of hosting sports tourism events. A cross-sectional research design was used in the study with a total of 404 respondents. Questionnaires and interviews were used to collect data from informants in three stadia. Descriptive, thematic analysis and inferential statistics were used for data analysis. The major motivating factors for hosting sports tourism event were good infrastructure, expected benefits and availability of accommodation facilities. The main benefits of hosting sports tourism events were identified as employment opportunities and increased trade for local businesses. A number of recommendations were made
Epidemiological patterns of Rift Valley Fever from diverse habitats during an extreme unprecedented flooding of Lake Baringo basin, Kenya, 2012-2013
No full textMosquitoes’ ecology and associated arboviruses are heavily influenced by precipitation and retention of
water in the environment. In 2011 and 2014, unprecedented floods occurred in Lake Baringo basin
inundating approximate 88 km2 of the shoreline land. This caused abrupt environmental changes raising
fears of an outbreak of Rift Valley Fever (RVF) disease. This study was carried out to determine the situation
of RVF disease in livestock from diverse habitats during the extreme unprecedented flooding phenomenon
that occurred in Lake Baringo basin, in 2012-2013. Blood was drawn from ear vein of livestock selected
randomly from the three study areas (lakeshore land, swamp marshy and dry rangeland habitats).
Mosquitoes were trapped using CDC light traps and identified morphologically. From a total of 77 blood
samples, eight were positive for RVF virus (RVFV) representing an overall infection of 12%. RVF prevalence
from livestock resident in flooded lakeshore land habitat was 2.6% (N=77) compared to the swamp marshy
habitat at 7.8% (N=77). No infections were recorded from dry rangeland (0%). Mosquitoes of genus
Mansonia dominated the catches in flooded lakeshore (98%). Highest individual catches of mosquitoes of
genus Aedes was from swamp marshy area whose abundance was 96.8% and below 2% in other habitats.
The Simpson’s Diversity Index for mosquitoes from swamp marshy habitat was 0.56, dry rangeland 0.57
and lakeshore land 0.13. The flooded lakeshore land was the most affected by the unprecedented floods
resulting in uneven mosquito diversity and subsequently low prevalence of RVF in this habitat. This could
be attributed to prolonged disruption of biotic and abiotic factors creating unfavourable breeding sites of
multiple species of primary vectors of RVF in flooded lakeshore land unlike in other habitats
Perceived Destination Image and Post-Visit Behaviour: An International MICE Visitors’ Perspective
No full textAfrica including Kenya has continued to suffer negative images due to stereotypes, prejudice, and negative
reporting by international media. This has continued to negatively affect the continents' share of the global
leisure tourism market despite the rich and unique natural touristic resources. The continents’ MICE tourism,
however, has been on the growth path before COVID 19 pandemic. This study, therefore, investigated the
influence of perceived destination image by international MICE visitors on their post-visit behaviour. The study
was carried out in the Kenyan capital city, Nairobi. The study followed a convenience sampling method with a
total sample of 335 respondents. A model on destination image and post-visit behaviour was developed and
tested. A blindfolding procedure in PLS showed the model had predictive relevance. Findings indicated that the
cognitive image dimension had a positive and significant influence on affective image, overall image, and postvisit behaviour. Affective image positively influences overall image but not post-visit behaviour. Overall
destination image had the greatest effect on post-visit behaviour. Destination Marketers in Kenya should pay
particular attention to the destination’s cognitive image. The study provides valuable information for
policymakers and destination marketers in developing actionable positioning strategies to enhance the
destination’s image and competitiveness
