TITLE: Crime Pattern Recognition based on High-Performance Computing
SPEAKER: Ahmed Eissa (Middlesex University)

ABSTRACT:
This paper reported research results on capturing the semantic similarity of two crimes categories based on the crime description. This study is based on the police data, collected from different sources. The proposed solution can capture the semantic similarity distance between the crimes from the crime database in order to put the selected crime in the right category. We focussed on the crime features and the description of each crime. We will also implement one of Deep Learning algorithms the Recurrent Neural Networks (RNN) algorithm, on top of a labelled crime data that is captured from online police data source. The crime data are labelled using a previous solution presented in a previous work in order to prepare the data to be introduced to RNN algorithm. The proposed solution can capture the semantic similarity distance between the crimes from the crime database in order to put the selected crime in the right category. We focussed on the crime features and the description of each crime. In elaborated experiments, the researchers built tools based on RNN as well as proposed algorithm from previous research, which implements RNN on a top layer and Natural Language Processing based Text Mining on the lower layer. The experiment results so that there is a speed up in RNN training time with an increasing number of threads and CPU cores used. In an elaborated experiments, the researchers built tools based on a proposed algorithm in this research, which implements Natural Language Processing based Text Mining techniques. 


TITLE:  Apply K-Means Clustering Algorithm for Crime Data Analysis
SPEAKER: Karthika Sivapathasundaram (Middlesex University)

ABSTRACT:
This paper reports part of our efforts to apply latest computing technology to support law enforcement officers. This study analyses terrorist attack crime datasets, which include cases of murder, suicide bombing, vehicular attack, car bombing, hijacking, hostage taking and armed assaults. The data are collected from different sources, such as: web sites, blogs, social media, and news sites. The crime reports data are managed in an electronic format, which include type of crime, date, time, location, suspect information, victim, and crime description. This study aims to help the police to fight crime and to reduce future occurrences of high impact crimes. The objective of crime analysis is to find the meaningful information from the crime data, such as characteristics of high impact crimes, to investigate how to prevent similar crimes in the future.  Hadoop Distributed File System (HDFS) is used for storing large datasets, supports to store, manage and process data in a distributed environment across a cluster of computers, with multiple tasks running in parallel. This paper shows the results of analysing two cluster categories from the collected crime datasets about terrorist attack from year 2008 to 2016.

TITLE: Using Smart Crime Reporting Apps to Prevent Crimes?
SPEAKER: Ahmed Hassan (Middlesex University)

ABSTRACT:
Information sharing on the Internet is a key driver in the evolution of human forms of communication. From emails to video conferencing applications, developers are finding new ways of enabling communication amongst Internet users. Social media platforms support text, voice, video, and imagery type of messaging data. Specific messages can be extracted from Twitter, Facebook, WhatsApp as well as similar social media platform, and analyzed in volumes to provide meaningful patterns that could provide predictive pointers to crime events. The police and other arms of government are particularly interested in mechanisms that would allow a proactive approach to crime. Other works in this area have focused on analyzing user data from Twitter and demonstrating the correlation between social content and crime trends. Some studies have shown that social media context could provide socio-behaviour signals for crime prediction. 
What we aim to demonstrate is that in addition to the impact of social data in providing predictive crime indicators, we can also combine other datasets from different sources to provide more comprehensive crime indicators. Datasets from historical police crime data, Crime reporting apps, and more are combined with Twitter sentiments and integrated into our Hybrid Infographic Visual Intelligent Crime Reporting Analysis app (HIVICRA). We sampled some historical police crime data, Twitter sentiments, and data from our crime-reporting app, and projected our results into visual info-graphic crime heat maps and crime clusters. The app also provides navigation to the crime hotspots, by plotting navigation routes utilizing Google maps. The versatility of the app means it is customizable and can be used in any city around the world and integrated into larger databases, such as ‘Interpol’, ‘human trafficking’, ‘missing persons’ and more. The community and the police could particularly benefit in the form of ‘community policing’ by deploying this form of hybrid app amongst community members and officers.