Search In this Thesis
   Search In this Thesis  
العنوان
Developing A GIS-BASED Crime Mining System in Kuwait /
المؤلف
Alomar, Kholoud Ali H.
هيئة الاعداد
باحث / خلود على حسن العمر
مشرف / يوسف بسيونى مهدى
مناقش / إبراھيم محمود محمد الحناوي
مناقش / عبد المجيد أمين علي
الموضوع
Information System.
تاريخ النشر
2016.
عدد الصفحات
115 p. ;
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
Information Systems
الناشر
تاريخ الإجازة
28/3/2016
مكان الإجازة
جامعة أسيوط - كلية الحاسبات والمعلومات - Information Systems
الفهرس
Only 14 pages are availabe for public view

from 32

from 32

Abstract

Crime hotspot identification is an important aspect for law enforcement authorities in an attempt to tackle national security. Identification of crime hot spot data is thus essential for tackling crime. As crime rates are increasing worldwide,crime mining requires more efficient algorithms that can handle current situations.Spatial-temporal data mining techniques are used for crime identification becauseof their capability to detect crime patterns.Therefore, identifying crime hot spot areas via clustering spatio-temporal data is an emerging research area. Thisstudy aims to identify unique ways of crime data categorization in the state of Kuwait. To accomplish this objective, the study presents a new technique todetect hot crime spots in Kuwait. More specifically, two efficient dynamic clustering algorithms are proposed- namely,DynamicA and DynamicB.
Expensive experimental studies are conducted using real data set to evaluate the effectiveness of the proposed algorithms.Kuwait governorates are taken as a case study including the capital, Hawalli, Al-Ahmady, Al-Jahra, Al-Farawaniya, and Mubarak Al-kebeer. In addition, different crime types are considered including act of discharge and humiliation, adultery, aggravated assault, bribery, counter fitting, drugs, embezzlement, fight or resist employee on job, forging of official documents, weapon, robbery and attempted robbery, suicide and attempted suicide, and bank theft. The effectiveness of the proposed dynamic clustering algorithms is compared with that of the existing clustering algorithms, especially K-means algorithm.. The experimental results showthe superiority of the proposed algorithms over
K-mean algorithm. Furthermore, results show that after applying random subspace classification to those clustered data, 98% accuracy and 99.4% ROC are obtained, having precision (98.7%), recall (98.4%), and F1 (98.28%). . The results reveal that crime is highly distributed in the capital governorate region of Kuwait. Moreover, handling of illegal weapons and robbery are the most committed crimes in Kuwait. This information is important for the adoption of crime fighting policies in Kuwait.