Crime investigation and criminal network analysis using archive call detail records

Kumar, Manish; Hanumanthappa, M.; Kumar, T. V. Suresh

doi:10.1109/icoac.2017.7951743

Cited by 19 publications

(12 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of CDRs in criminal investigations has been described in technical literature, but mostly from a social networking perspective [42,43]. Despite CDR based geolocation evidence appearing more frequently in US courts, there seems to be nothing published on the topic by the scientific community.…”

Section: Call Detail Recordsmentioning

confidence: 99%

Analysis of Mobile Phone Geolocation Methods Used in US Courts

Jovanovic¹,

Cummings

2022

IEEE Access

View full text Add to dashboard Cite

Call Detail Records (CDR) are files that collect information about every call made on every cellular wireless network in the USA. Network operators capture and archive these files in the regular course of daily operations for internal use by their technical departments, but CDR files are also used as evidence in criminal cases to estimate the locations of mobile phones and infer the locations of individuals. Courts are tasked with determining the admissibility of evidence and are sometimes presented with CDR interpretations that are not based on legitimate radio-frequency (RF) engineering science. This paper discusses CDR-based geolocation methods that are well founded in the science of RF engineering as well as methods that have no basis in RF theory nor any engineering practices.

show abstract

Section: Call Detail Recordsmentioning

confidence: 99%

Analysis of Mobile Phone Geolocation Methods Used in US Courts

Jovanovic¹,

Cummings

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…This structure can be used to find associations between criminals and anti-social people. Several studies proposed to identify patterns of calls, people most often called by the suspects, and their communication with convicted criminals, see for instance [9,23].…”

Section: Related Workmentioning

confidence: 99%

Graph embeddings in criminal investigation: towards combining precision, generalization and transparency

et al. 2022

View full text Add to dashboard Cite

Criminal investigation adopts Artificial Intelligence to enhance the volume of the facts that can be investigated and documented in trials. However, the abstract reasoning implied in legal justification and argumentation requests to adopt solutions providing high precision, low generalization error, and retrospective transparency. Three requirements that hardly coexist in today’s Artificial Intelligence solutions. In a controlled experiment, we then investigated the use of graph embeddings procedures to retrieve potential criminal actions based on patterns defined in enquiry protocols. We observed that a significant level of accuracy can be achieved but different graph reformation procedures imply different levels of precision, generalization, and transparency.

show abstract

“…A user-centric grid-based approach that utilizes location information retrieved from subscriber CDRs as a basis for cell parameter optimization is presented in [29]. In a different area, a CDR database which contains the CDR related to old cases and convicted criminals is used in a crime investigation in [30]. In [31], suspect tracking based on call log analysis and visualization is proposed.…”

Section: Call Detail Records Approachesmentioning

confidence: 99%

“…This first example describes a call made the day 1 by the caller #349 to the receiver #23 at a time between 00:00 and 00:59 with a duration of 1634 milliseconds. [38], communication network anomaly detection [39], tracking based on call log analysis [30,31], interactive visual analytics [40], and so on. In this research, the VAST data set has been chosen because it has been used widely in this field and, in our case, the extraction of calling patterns is proposed solely from CDR data.…”

Section: Original Datasetmentioning

confidence: 99%

Real-Time Recognition of Calling Pattern and Behaviour of Mobile Phone Users through Anomaly Detection and Dynamically-Evolving Clustering

et al. 2017

View full text Add to dashboard Cite

Abstract:In the competitive telecommunications market, the information that the mobile telecom operators can obtain by regularly analysing their massive stored call logs, is of great interest. Although the data that can be extracted nowadays from mobile phones have been enriched with much information, the data solely from the call logs can give us vital information about the customers. This information is usually related with the calling behaviour of their customers and it can be used to manage them. However, the analysis of these data is normally very complex because of the vast data stream to analyse. Thus, efficient data mining techniques need to be used for this purpose. In this paper, a novel approach to analyse call detail records (CDR) is proposed, with the main goal to extract and cluster different calling patterns or behaviours, and to detect outliers. The main novelty of this approach is that it works in real-time using an evolving and recursive framework.

show abstract

Crime investigation and criminal network analysis using archive call detail records

Cited by 19 publications

References 4 publications

Analysis of Mobile Phone Geolocation Methods Used in US Courts

Analysis of Mobile Phone Geolocation Methods Used in US Courts

Graph embeddings in criminal investigation: towards combining precision, generalization and transparency

Real-Time Recognition of Calling Pattern and Behaviour of Mobile Phone Users through Anomaly Detection and Dynamically-Evolving Clustering

Contact Info

Product

Resources

About