Criminal activity continues to be a major concern in modern civilisations, with most nations facing unacceptable levels of crime and delinquency. The results show that African and Latin American countries suffer from the highest levels of various types of crime across the board, followed by countries in Asia. European, North American and Australian countries experience intermediate or relatively low levels of most types of crime. Levels of common crime have dropped or stabilized globally except in Africa where they went up. Homicides have fallen almost universally. Trends in organized crime are diverging. In today’s world of extensive crime, fighting crime is a major concern.
As with so many of the challenges we face as a society, the prevention of crime is better than cure. Stopping crime before it happens, and preventing the harm caused to victims, must be preferable to picking up the pieces afterwards. “Crime Prevention comprises strategies and measures that seek to reduce the risk of crimes occurring, and their potential harmful effects on individuals and society, including fear of crime, by intervening to influence their multiple causes.”
Increases in speciﬁc types of crime are often attributable to changes in opportunity. For instance, increases in online activity have led to signiﬁcant opportunities for cyber-enabled (made easier by the internet, such as fraud) or cyber-dependent (only possible because of the internet, such ransomware attacks) crime. However, technology has also been one of the driving forces that has enabled the improvement of approaches to crime prevention, and poling more generally.
Role of technologies in Crime Prevention
One of such technologies is Crime Mapping (CM), also known as hot-spot policing. CM refers to the process of conducting spatial analysis to map, visualise and analyse crime patterns. This allows for the identiﬁcation of crime hot spots in conjunction with other crime trends and patterns[60,61]. Such information can then be used to optimise the location of human or/and technological resources. As various works suggest, the identiﬁcation of hot spots is an effective software-based technology for optimising the use of resources and ultimately prevent crime.
Risk assessment is another key information-based technology for crime prevention. Risk assessment is used toassess the risk of recommitting crime by offenders under correctional control. According to the survey conducted in, a majority of serious crimes are committed by a small fraction of people during the ﬁrst months of probation parole. Risk assessment tools make use of predictive models to identify such a subgroup of people so that appropriate surveillance/supervision is granted to those cases.
Likewise, information technology is used to identify the likelihood of a terrorist attack or a serious violent event occurring at certain places, including schools, airports or train stations amongothers. Another application where information technology has been adopted to prevent crime is in the development of computer software to track individuals’ interactions on various social media sites. The monitoring of suchsuspect’s interactions is then used to identify abnormal behaviors which can potentially be related to crime intentions
Emerging technologies in Crime Prevention
Technological innovation has been one of the main driving forces leading to the continuous improvement of crime control and crime prevention strategies (e.g. GPS tracking and tagging, video surveillance, etc.).
City infrastructure is becoming smarter and more connected. This provides cities with sources of real-time information, ranging from traditional security cameras to smart lamps, which it can use to detect crimes as they happen. With the help of AI, the data collected can be used to detect gunfire and pinpoint where the gunshots came from.
Audio-based technologies have been used for many years to anticipate criminal actions. Common examples include the interception of calls by police ofﬁcers (wiretapping) or the use of recording devices as evidence collection mechanisms. With the current advances in audio processing and machine learning techniques, whereby several parameters andbio-metrics can be automatically computed from raw audio recordings, the scope of audio-based technologies have experienced a great expansion. For instance, gun shot detection audio-based technologies have been recently evaluated in the US.
With ShotSpotter and smart city infrastructure, law enforcement can triangulate the location of a gunshot alerting operators in less than 60 seconds and offering information about the type of gunfire and the site. accurate to within 3 meters (10 feet). The system is being used in over 90 U.S. cities with Denver one of the most recent to adopt the technology.
Besides, the presence of Intelligent Virtual Assistants (IVAs) or Chatbotssuch as Amazon Alexa or Google Assistant is becoming increasingly popular . Such IVAs incorporate speech recognition capabilities allowing users for asking questions and making requests to different interfaces. In addition to speech recognition, it is now possible to count the number of speakers in a conversation via speaker diarization, to infer the sentiment (mood) of individuals by analyzing their voice or yet recognize a speaker by his/her voice with considerably low error rates. These advances clearly provide opportunities for implementing audio-based crime prevention tools
Electronic Monitoring (EM) and Global Positioning System-based Technologies
EM is an effective tool towards preventing recidivism, specially for sex offenders.
First EM systems employed radio frequency identiﬁcation(RFID) technology. RFID technology is based on a tag with a unique identiﬁer that sends data to an electronic reader through wireless radiofrequency waves, enabling its identiﬁcation and tracking. The second generation of EM technologies incorporated the use of Global Positioning System or GPS. GPS is a satellite-based global navigation system that provides geo-location through the use of a network of satellites orbiting the Earth at an altitude of approximately 20,200 km. To estimate the geo-location, a GPS receiver intercepts the signals of at least three network satellites at regular intervals of time.
The use of GPS technology as a crime prevention tool has gained increasing attention. The ability to customise exclusion zones and provide instant alerts if these are violated has extended the use of electronic monitoring to sex offenders and post-work release offenders. Further applications, such as the tracking of terrorist suspects to gain insights into their spatial and temporal behavior, have recently been proposed.
Short-Range Wireless Communication Technologies
Short-range wireless communication transceivers such as Bluetooth and WIFI are widely incorporated into many portable and mobile devices, including laptops, mobile phones and smart-watches. During the manufacturing process, a wireless module is assigned a unique identiﬁcation (ID) in the form of a 48-bit Medium Access Control (MAC) address. This address is then used to identify and authenticate a device when communicating with other wireless devices.
For example, Bluetooth (BT) devices can interact with other nearby BT devices within their signal range (10mto100m, depending on the radio transceiver) by sending and receiving radio waves within a band of 79 different frequencies centred at 2.45 GHz. Using such radio waves, along with the identiﬁcation capabilities provided by the unique MACaddress assigned, a Bluetooth device can continuously monitor other Bluetooth devices nearby (within its signal range)and also identify the type of device associated with such MAC address (i.e. whether it is a smart-phone or a laptop for example). In addition, the Received Signal Strength Indicator (RSSI) provides an estimated measure of the power present in a received radio signal. As shown by previous RF-based research, RSSI can then be used to estimate the approximate distance a Bluetooth receiver is from a Bluetooth emitter
Exploiting the above characteristics of this technology, various researchers have employed Bluetooth technology to estimate the surrounding social context of a person, estimate pedestrian ﬂows at speciﬁc places or prevent or investigate the kidnapping of infants and elementary school children.
Short-range tagging technologies such as Near-ﬁeld communication (NFC) technology are gaining increasing attention and made available in most of the latest generations of smartphones. NFC technology is a set of communication protocols for short-distance communications (4cm or nearer) between two electronic devices, namely an NFC reader and an NFC tag. Such communication is achieved through the NFC reader sending a signal to a pre-programmed battery-free NFC tag which sends back its function or application to the reader. Common examples of the use of NFC technology include contact-less payment and door card readers. Given the reduced size of NFC tags, these could be potentially embedded in a wide range of everyday objects such as clothes, keyrings or furniture to be used as an alerting mechanism in cases of emergency. Likewise, tag tapping could be used to trigger evidence collection mechanisms such as microphones or video cameras in a quick, easy and efﬁcient way. NFC technology would be therefore a great complement to the current emergency reporting and evidence collection mobile apps, which will enable the triggering of the different apps’ built-in actions on the quiet.
In recent years, Closed Circuit Television (CCTV) surveillance has emerged globally as a mainstream crime prevention measure. CCTV technology is already present in many public places such as railway stations, airports, ofﬁcebuildings and on the street. While CCTV cameras were formerly employed as a means to report crime, support police ofﬁcers with prosecution processes or as a supporting evidence in court of justice, the increasing developments in computer vision and machine learning provide opportunities for investigating CCTV surveillance as a crime prevention mechanism.
CCTV technology has been investigated in different applications. These include the automatic detection of suspicious anomalies such us unattended bags in mass transit areas or crowded venues, iris recognition-based security systems which deny access to buildings to unauthorised personnel,intrusion detection systems (IDS) in unauthorized areas employing motion tracking techniques, automatic robbery detection in banks via object and human posture detection, and even as a means of crowd detection and congestion analysis for safety purposes.
Crime Prevention Mobile App
A wide array of applications have been proposed to help either with the prevention of crime or with the reporting of crime that has already occurred. Apps for crime prevention can be broadly divided into two categories, namely apps to be adopted by policing institutions and those directed to the general public. Numerous mobile apps have been developed in recent years to facilitate the communication of emergency and panic situations to close relatives and policing institutions.
Circle of 6 is a mobile app that enables its users to quickly contact a user-deﬁned list of six people and share their current location along with an emergency message. In a similar way, Noonlight provides a mechanism to alert emergency institutions by pushing and holding a button embedded in the app. Red PanicButton, which in addition to the above features, incorporates the automatic publication of emergency messages onTwitter.
BrightSky is a mobile app mainly directed towards victims or potential victims of domestic abuse, being the ﬁrst smartphone app to provide a UK-wide directory of specialist domestic abuse support services. BrightSky enables users to locate their nearest support centre by searching their area, postcode or current location.
When it comes to investigating crime, the details can make a difference. But what if you cannot separate the wheat from the chaff? That’s where AI can make an enormous difference, empowering law enforcement to speed up the processing of information and spot patterns that might remain hidden in the data.
CCTV surveillance systems are constantly being upgraded to incorporate the latest soft technology features. These include on-the-edge feature extraction and machine learning classiﬁcation algorithms. As a result, it is now possible to extract different patterns and personal bio-metrics from video sequences, which can be a posteriori used for person identiﬁcation.
Social network analysis of urban gangs, citywide alert systems, crime-spot prediction, and custody decision-making aids are all examples of predictive tools underpinned by AI that are already in use by law enforcement agencies. The development and use of AI in the financial services sector has been spurred by mandatory reporting of suspicious activity in financial transactions. Private-sector companies are also heavily involved in developing software and making datasets available for use by the public sector in the area of general law enforcement.
According to a recent study conducted by the University of California, crimes carried out in a location tend to follow a similar pattern and can be predicted in the same way seismologists predict earthquake aftershocks. One company using big data and machine learning to try to predict when and where crime will take place is Predpol. They claim that by analyzing existing data on past crimes they can predict when and where new crimes are most likely to occur.
Their algorithm is based around the observation that certain crime types tend to cluster in time and space. By using historical data and observing where recent crimes took place they claim they can predict where future crimes will likely happen. For example a rash of burglaries in one area could correlated with more burglaries in surrounding areas in the near future. They call this technique real-time epidemic-type aftershock sequence crime forecasting. Their system highlights possible hotspots on a map the police should consider patrolling more heavily.
One success the company highlights is Tacoma, Washington, which saw a 22 percent drop in residential burglaries soon after adopting the system. Tacoma started using Predpol in 2013 and saw the drop in burglaries in 2015.
With data analytics, we could see crime epidemics reduce to a large scale. It is proving to be a valuable tool in the arsenal of law enforcement officials in every jurisdiction. Companies and cities all over world are experimenting with using artificial intelligence to reduce and prevent crime, and to more quickly respond to crimes in progress.
The ideas behind many of these projects is that crimes are relatively predictable; it just requires being able to sort through a massive volume of data to find patterns that are useful to law enforcement. Data analytics can be used to identify vulnerable people, and to ensure potential victims are identified quickly and consistently.
UK’s Durham Constabulary has developed Modern Crime Prevention Strategy which calls for the use of data analytics and AI to help inform police decision making. The Strategy acknowledges that better use of data and technology is one of the key pillars of effective modern crime prevention in the digital age, and outlines the Government’s role in “stripping away barriers to the effective use of data and data analytics, and helping others exploit new and existing technology to prevent crime.”
According to Modern Crime Prevention Strategy data analytics can:
- Help police forces deploy officers to prevent crime in known hotspots (often called ‘predictive policing’)
- Use information shared by local agencies on, for example, arrests, convictions, hospital admissions, and calls on children’s services to identify individuals who are vulnerable to abuse or exploitation
- Spot suspicious patterns of activity that can provide new leads for investigators, such as large payments to multiple bank accounts registered at the same address
- Show which products, services, systems or people are vulnerable to particular types of crime – for example that young women are disproportionately likely to have their smartphone stolen. This means system flaws can be addressed, or crime prevention advice (e.g. on mobile phone security measures) can be targeted more effectively.
Advanced analytic capabilities can be integrated into CCTV systems to improve response times to public safety incidents. Analytics has the potential to enable police to achieve a truly preventative approach, as it can help to get new understandings from data and identify and recognize suspicious behavior and activities.
Hangzhou, China-based Hikvision, has developed a security camera that claims to achieve 99% accuracy with its advanced visual analytics applications. Its cameras can scan for license plates on cars, recognize faces to search for potential criminals or missing persons, and detect suspicious anomalies such as unattended bags in crowded places. Today its cameras are used in more than 150 countries and regions including the U.S. and U.K.
Data and data analytics, tools have become critical in successfully preventing crime. Many police forces are already trialling forms of ‘predictive policing’, largely to forecast where there is a high risk of ‘traditional’ crimes like burglary happening, and plan officers’ patrol patterns accordingly, says UK’s Modern Crime Prevention Strategy.
Edge Computing and on Device Processing
Traditionally, the majority of the processing for data-intensive applications was done on a central cloud to take advantage of fast and powerful computing infrastructure. However, major issues concerning latency, security and privacy can beidentiﬁed in the use of cloud-based systems for crime prevention. In this regard, a new trend of processing the data on the edge is emerging. The motivation behind edge computing is that of performing the data processing as near as possible to the point of data production. With this, the privacy and latency issues present in cloud-based systems can be signiﬁcantly mitigated. AI is gradually ﬁnding its way into embedding systems that are becoming smaller and less power demanding while offering fast processing power and low latency at an increasingly attractive cost.
A number of off-the-shelf edge computing devices suitable to carry out heavy signal processing and machine learning applications are already available. For instance, both Nvidia and Google have recently released their respective development boards, namely Jetson Nano and Google Edge TPU, with the aim of enabling users to develop and run AI applications on the edge. In addition to their portability and the privacy advantages they offer, such boards are supported by sophisticated development kits that consist of a SOM (System-on-Module) connected to a development board that incorporate numerous connectors like USB and Ethernet to share the data gathered when desired. Furthermore, the above devices also support major deep learning frameworks and tools such as TensorFlow.
Greater capacity of (private) 5G networks will enhance the development of Advanced analytic capabilities in perimeter security and defence. These include Machine Learning and deep learning algorithms to develop advanced video analytics solutions. 5G mmWave connectivity is also set to increase the intelligence of surveillance systems and enable Video Surveillance as a Service (VSaaS), where video is uploaded to a centralised cloud platform rather than being saved via local systems.
5G technologies will need to be capable of delivering fiber-like 10 Gb/s speeds will depend on ultra-wide bandwidth with sub-millisecond latencies. The scarcity of conventional microwave band has led to the exploration of mmWave realm. The multi-gigahertz bandwidth available in mmWave range has a strong potential in addressing the capacity demands of 5G and beyond wireless networks.
The spectrum for 5G services not only covers bands below 6 GHz, including bands currently used for 4G LTE networks, but also extends into much higher frequency bands not previously considered for mobile communications. It is the use of frequency bands in the 24 GHz to 100 GHz range, known as millimeter wave (mmWave), that provide new challenges and benefits for 5G networks.
Countries launch projects
China, a surveillance state where authorities have unchecked access to citizens’ histories, is developing artificial intelligence based tools that they say will help them identify and apprehend suspects before criminal acts are committed.
The South American police is tackling border protection issues with the help of analytics to better monitor federal highways and manage traffic. Africa is beginning to build crime prevention into their strategic approaches, through better crowd management and police dedicated to reducing road traffic accidents.
Indian Police Is Tapping Into Data Analytics To Prevent Crime
The Indian Police force has started taking an increasing interest in crime analytics using big data, which involves storing and analyzing huge volume and variety of data in real time, to predict and inference patterns and trends especially relating to human interactions and behavior.
To know which areas are most prone to crimes, the police force also uses predictive analytics to develop models using machine learning to know which areas are most prone to crime. It also helps them to keep a track on which criminals or individuals to keep a track on. Delhi police have partnered with ISRO to develop an analytical system called Crime Mapping, Analytics and Predictive System (CMAPS), which helps the Delhi police to ensure internal security, controlling crime, and maintaining law and order through analysis of data and patterns. Jharkhand police force is trying to implement an analytical system with the help of IIM Ranchi, to help evaluate criminal records, date and time of crime occurrences, and location to predict crime-prone zones.
China planning to use AI technology to predict and prevent crime
China’s crime-prediction technology relies on several AI techniques, including facial recognition and gait analysis, to identify people from surveillance footage, according to The Financial Times. In addition, “crowd analysis” can be used to detect “suspicious” patterns of behaviour in crowds, for example to single out thieves from normal passengers at a train stations.
Cloudwalk Technology, a Chinese early startup based in Beijing, has developed facial recognition technology that is currently being used in the financial, public security, and aviation sectors. It features facial recognition terminals, facial scanning door entry, and infrared binocular scanning machines. It can be used to detect changes in a person’s behavior through subtle facial changes and movements.
Facial recognition company Cloud Walk has been trialling a system that uses data on individuals’ movements and behaviour — for instance visits to shops where weapons are sold — to assess their chances of committing a crime. Its software warns police when a citizen’s crime risk becomes dangerously high, allowing the police to intervene.“If we use our smart systems and smart facilities well, we can know beforehand . . . who might be a terrorist, who might do something bad,” said Li Meng, vice-minister of science and technology.
Another example of AI use in Chinese crime prediction is “personal re-identification” — matching someone’s identity even if spotted in different places wearing different clothes, a relatively recent technological achievement. “We can use re-ID to find people who look suspicious by walking back and forth in the same area, or who are wearing masks,” said Leng Biao, professor of bodily recognition at the Beijing University of Aeronautics and Astronautics. “With re-ID, it’s also possible to reassemble someone’s trail across a large area.”
Durham Constabulary Deploy AI for Crime Prevention
Durham Constabulary is preparing to trial an artificially intelligent system to help officers decided whether or not to keep a suspect in custody.The Force, will use the Harm Assessment Risk Tool (Hart) to help officers decide if a suspect can be released from detention, based on the probability of offending once released. Hart has been trained on five years of the Force’s data (from 2008 – 2012), and will classify a suspect as either low, medium, or high risk of offending. The system was tested from 2013, with forecasts that a suspect was low risk accurate 98% of the time, while forecasts that suspects were high risk were accurate 88% of the time. The Hart system was developed in conjunction with the renowned Centre for Evidence-based Policing at the University of Cambridge.
Jurisdictions in the United States have been using more basic risk assessment algorithms for over a decade to make decisions about pretrial release and whether or not to give an individual parole. One of the most popular is Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) from Equivant, which is used throughout all Wisconsin and numerous other locations. A 2012 analysis by the New York Division of Criminal Justice Services found COMPAS’s, “ Recidivism Scale worked effectively and achieved satisfactory predictive accuracy.”
COMPAS has recently come under fire after a ProPublica investigation. The media organization’s analysis indicated the system might indirectly contain a strong racial bias. They found, “[T]hat black defendants who did not recidivate over a two-year period were nearly twice as likely to be misclassified as higher risk compared to their white counterparts (45 percent vs. 23 percent).”
SA Company to Use Artificial Intelligence to Predict Crime
Designed to predict and map potential crimes, Solution House Software has announced the launch of their new artificial intelligence (AI) module for Incident Desk. The Incident Desk Predictive Analysis module uses machine learning technology developed by Solution House together with aggregated data from multiple information sources to determine the likelihood of different types of criminal activity in the Incident Desk management area.
“With the module installed, Incident Desk generates 7 and 30-day forecasts as heat maps based on crime types and incident probabilities that managers can use to optimise their finite security resources,” says Janse van Rensburg. “Crime is notoriously difficult to predict, but given that Incident Desk can access so many different types of data – including weather patterns and forecasts and historical data – the results are based on fairly accurate and proven trending algorithms,” her says. One of the biggest problems currently plaguing public safety and security are the ‘islands of data’ that are not being shared or centralised, which makes it difficult to data mine and analyse.
References and Resources also include: