AbstractThispaper will focus on the distribution of hotels and attractions in MuscatGovernorate and point pattern analysis.
Different tools and analysis will beused and different examples of point pattern analysis will be mentioned.Finally, an integration between the distribution ofhotels and attractions in Muscat Governorate and point pattern analysis will beconducted.!!IntroductionPoint pattern analysis is the assessment ofthe pattern or distribution of a certain or set of points. It can indicate the actualspatial or temporarily location. It’s one of the most important models in GISand spatial analysis since its important in population.
Different methods ofpoint pattern will be discussed. Also, it will be integrated with the hotelsand attraction is Muscat. It is not integration, it is analysisLiteraturereview Theanalysis of point patterns shows up in numerous diverse ranges of research.
Forinstance, you have ecology where the concentration is on defining the spatial distributionand its causes of a tree species for which the areas have been gotten from forthe research study for example the location of it. Additionally, in case two ormore species have been recorded, it would be better to asses and evaluate whetherthese species are similarly dispersed or if there is a competition existsbetween them. There are other causes that dynamism each species to extent in certainareas of the study. Also, in spatial epidemiology, the study of diseasetransmission there is a common issue which is to decide whether the cases of acertain illness are clustered. This can be evaluated by comparing the spatialdistribution of the cases to the areas of a set of controls taken at subjectivefrom the population.
Ingeneral, a point process is a stochastic process in which locations of aredetected the significant locations within a restricted region. According to (Bivand., 2008) defines a pointprocess as a ‘stochastic mechanism which generates a countable set of events’. Also,he provided us with an appropriate definitions and classification of the differenttypes of a point process and their core properties.
The locations of the eventsgenerated by a point process in the area of study will be called a pointpattern. Occasionally, supplementary covariates might need to be documented andit will be support the locations by attaching the document in it of the perceivedevents. Theanalysis of point patterns is concentrates on the spatial distribution of theperceived procedures and create readings of the fundamental process that iscreated by them. There are two primary issues of interest is particular: thedistribution of events in space and the presence of potential collaborationsbetween them. For only a descriptive analysis, we would represent the locationsof the point pattern in the study area.
This will give us an idea of the distributionof the points, which can lead to probable theory about the spatial distributionof the events. Also, statistical analyses can be described and be competed. Whenexamining a point process, the most fundamental test that can be performed isthat of Complete Spatial Randomness also knows and CSR. Naturally, by CSR meansthat the occasions are dispersed autonomously at irregular and consistentlyover the study area This infers that there are no districts where the occasionsare more likely to happen and that the presence of a given occasion does notalter the likelihood of other occasions showing up nearby.Thiscan be examined by plotting the point pattern and seeing if the points manageto appear in clusters or if it respects a regular pattern.
Anyway, the pointsare not allocated homogeneously because they must be distributed filling allthe space in the study area. Usually, clustered patterns happen when there isan attraction in the area or between points, whilst regular patterns happenwhen there is a competition for example. Thereare more special analysis techniques and examples including Ripleys K Function,the G function, The F function and Morans I point pattern analysis which areused in the different fields of study. MethodologyTwotools had been used: Average nearestpoint: TheAverage Nearest Neighbor tool measures the distance between each featurecentroid and its nearest neighbor’s centroid location. Then the averages of allthe nearest neighbors distance gets conducted. Depending on the averagedistance and the average for a hypothetical random distribution it defineswhether it’s considered as cluster or discrete. The average nearest neighborratio is calculated as the observed average distance divided by the expectedaverage distance.Thistool is used to:Evaluatecompetition of the region for example it compares a variety of pant specieswithin a fixed study area.
It monitorschange over time since it evaluates changed in a single type of study with afixed study.It compares anobserved distribution to a control distribution. The directionaldistribution it generates standard deviational leapsto summarize the spatial characteristics of geographic features: centralmovement, distribution, and indicator trends. Its uses are: The StandardDeviational Ellipse tool makes a new Output Feature Class that has ellipticalpolygons with a coordinate for mean center, two standard distances androtation. Measuring distancesusing Calculations based on Euclidean or Manhattan. Used to analyze whena field is specified.
For the line andpolygon features, feature centroids are used in distance calculations. Map layers can beused to define the Input Feature Class. Result: After creating the map, it was decided that the two tools that willbe used are the directional distribution and average nearest point. Thedirectional distribution map shows 2 outputs of an ellipses shape.
The blueellipse represents the hotels and light yellow represent the attraction. Themap shows the that the attractions are spread more than the hotels and thehotels are gathered in a small ellipse in the middle of the attractions. Thismeans hotels exist when there are attractions. Thisgraph shows that the attractions in Muscat are clustered since the z score is-9.58 and there is less than 1% that the clustered pattern could be the resultof a random chance.
thegraph show that hotels in Muscat and clustered since the z score is -10.06 andthere is less than 1% and that the clustered pattern is random.