Call Record Data Research Articles

Road coverage as demand metric for ambulance allocation.

Ambulances must be strategically placed to ensure timely patient care and save lives. The allocation problem considered in the current paper optimally distributes a fixed number of ambulances over predetermined bases with limited capacity. Ambulance allocation problems are usually solved through historical demand. In such cases, researchers process call record data that is shared by ambulance service providers. This paper proposes an alternative demand metric, namely the meters of covered road. Road network information is widely and publicly available, making it easily accessible. We demonstrate for a real ambulance region that the road coverage demand metric performs similarly to the historical call record metric in the case of static allocation, and that it outperforms when dynamic ambulance management is used.

Cell site analysis; testing understanding via internal consistency checks.

This paper is aimed at Cell Site Analysis Expert Witnesses. Ground Truth Data (GTD) are essential to validation exercises, but in the UK access to practitioner-generated Call Data Records (the traces considered by Cell Site Analysis experts) are restricted, reducing opportunities for practitioners to test their understanding against real-world data. This paper outlines methods by which casework material might be used to potentially detect issues within understanding of uncertainties (and therefore improve the reliability of analyses) by reviewing the properties of casework material in parallel with the casework assessment being conducted. Four case examples are given in which assessments of the reliability of understanding of uncertainties are tested (two examples for assessing Call Data Record GPRS time uncertainties, one for reliability of survey results and one for assessing the reliability of "geo" data from Encrochat examinations). The methods proposed are intended to provide a deeper layer of Quality Assurance; they are not intended to replace validation using GTD.

A Comparative result-based study on Criminal Call Data Record Analysis

All calls that travel through a phone exchange are recorded in detail in call detail records or CDRs. The telephone exchange maintains this CDR, which includes the time of the call, the length of the call, the source and destination numbers, the type of the call, etc. Call data logs are crucial for handling serious criminal cases. Processing of Call Detail Records is now moving towards real-time streaming data. It assists in real-time call detail record analysis, real-time criminal location tracking, and real-time network behaviour analysis. However, the number, diversity, and data rate of these Call Detail Records are enormous, and the current telecom systems were not developed with these challenges in mind. The largest source, which can be viewed as Call Detail Records, can be used (for storage, processing, and analysis). The issues that the telecom sector has with call detail records analysis are the subject of extensive research. In this paper we demonstrate how to use Excel, data mining & graph mining to analyse call detail records of criminal case.

Use of Graph Technology to Identify Criminal Activity Using Call Data Record

Use of Graph Technology to Identify Criminal Activity Using Call Data Record

Calls from Boston Schools for Police Psychiatric Emergency Response: A Study of 911 Call Record Data from 2014 to 2018.

This study examines patterns and trends in 911 calls from Boston public school addresses related to mental health and physical assaults/fights generated from 2014 to 2018. We analyzed 12,113 Boston Police Department (BPD) 911 call records from 102 Boston Public School addresses during the 2014-2018 school years. In addition, we separately analyzed calls coded by BPDas Emotionally Disturbed Person ("EDP"), indicating a psychiatric crisis was the primary reason for the call, as well as calls coded as "Fight," "Assault," or "Assault and battery." Call frequency ranged from 0 to 277 per school each year. Although the annual average number of calls increased each school year over the 4-year period, this was primarily due to an increase in hang-ups and abandoned calls. Overall, 7.4% calls were coded as EDP and 6.5% were coded as assault/fight. Call volume was highest in the middle of the school day, with a median time of 12pm. EDP calls were significantly earlier in the day than non-EDP calls, and the percentage of calls labeled as EDP decreased in frequency each day over the course of the week. There were more overall 911 calls, on average, per day in late spring than in other seasons. The frequency with which schools call upon police as emergency service providers for psychiatric crises indicates a need for additional school-based resources. Such resources may be most effective if they are allocated mid-day, responsive to changing student needs over the course of the week, and increased in spring.

A Privacy-Preserved Internet-of-Medical-Things Scheme for Eradication and Control of Dengue Using UAV.

Dengue is a mosquito-borne viral infection, found in tropical and sub-tropical climates worldwide, mostly in urban and semi-urban areas. Countries like Pakistan receive heavy rains annually resulting in floods in urban cities due to poor drainage systems. Currently, different cities of Pakistan are at high risk of dengue outbreaks, as multiple dengue cases have been reported due to poor flood control and drainage systems. After heavy rain in urban areas, mosquitoes are provided with a favorable environment for their breeding and transmission through stagnant water due to poor maintenance of the drainage system. The history of the dengue virus in Pakistan shows that there is a closed relationship between dengue outbreaks and a rainfall. There is no specific treatment for dengue; however, the outbreak can be controlled through internet of medical things (IoMT). In this paper, we propose a novel privacy-preserved IoMT model to control dengue virus outbreaks by tracking dengue virus-infected patients based on bedding location extracted using call data record analysis (CDRA). Once the bedding location of the patient is identified, then the actual infected spot can be easily located by using geographic information system mapping. Once the targeted spots are identified, then it is very easy to eliminate the dengue by spraying the affected areas with the help of unmanned aerial vehicles (UAVs). The proposed model identifies the targeted spots up to 100%, based on the bedding location of the patient using CDRA.

Exploring methods for mapping seasonal population changes using mobile phone data

Data accurately representing the population distribution at the subnational level within countries is critical to policy and decision makers for many applications. Call data records (CDRs) have shown great promise for this, providing much higher temporal and spatial resolutions compared to traditional data sources. For CDRs to be integrated with other data and in order to effectively inform and support policy and decision making, mobile phone user must be distributed from the cell tower level into administrative units. This can be done in different ways and it is often not considered which method produces the best representation of the underlying population distribution. Using anonymised CDRs in Namibia between 2011 and 2013, four distribution methods were assessed at multiple administrative unit levels. Estimates of user density per administrative unit were ranked for each method and compared against the corresponding census-derived population densities, using Kendall’s tau-b rank tests. Seasonal and trend decomposition using Loess (STL) and multivariate clustering was subsequently used to identify patterns of seasonal user variation and investigate how different distribution methods can impact these. Results show that the accuracy of the results of each distribution method is influenced by the considered administrative unit level. While marginal differences between methods are displayed at “coarser” level 1, the use of mobile phone tower ranges provided the most accurate results for Namibia at finer levels 2 and 3. The use of STL is helpful to recognise the impact of the underlying distribution methods on further analysis, with the degree of consensus between methods decreasing as spatial scale increases. Multivariate clustering delivers valuable insights into which units share a similar seasonal user behaviour. The higher the number of prescribed clusters, the more the results obtained using different distribution methods differ. However, two major seasonal patterns were identified across all distribution methods, levels and most cluster numbers: (a) units with a 15% user decrease in August and (b) units with a 20–30% user increase in December. Both patterns are likely to be partially linked to school holidays and people going on vacation and/or visiting relatives and friends. This study highlights the need and importance of investigating CDRs in detail before conducting subsequent analysis like seasonal and trend decomposition. In particular, CDRs need to be investigated both in terms of their area and population coverage, as well as in relation to the appropriate distribution method to use based on the spatial scale of the specific application. The use of inappropriate methods can change observed seasonal patterns and impact the derived conclusions.

Toward Decision Support for Telecom External Data Monetization: A Study of the Value of Network- and Personality-Based Metrics for Third-Party Businesses.

Abstract The big data revolution has led to unprecedented opportunities for data sharing between industries. Telephone companies offer specific data involving rich information not only about the customer's behavior but also regarding his/her relationship with other customers and with third-party businesses. This article addresses the following research question: Might telecom data help to improve the prospective selection of third-party businesses? By answering this question, we expect to offer support for two specific investment decisions: on the one hand, the decision of the telecom operator to invest in the new market of the external data monetization for third-party business; on the other hand, the decision of third-party businesses to buy such customer profiling extracted from telecom call data records (CDRs). Using complex data treatments and more than one million models, the article addresses the challenges and opportunities in collecting and analyzing telecom data from two European telephone companies for improving the prospective selection processes of 36 third-party businesses. This improvement relies on new features extracted from the CDR, among which behavioral variables are considered as Personality Proxy variables and network-based variables. The results highlight that Personality Proxy variables are useful to support smaller niche businesses. For these businesses these variables are predominant and they can be directly implemented. In addition, the study shows that network analysis-based variables have the potential to be more beneficial to large companies since the value of network analysis continuously increases with the number of third-party business clients identified.

A robust tracking system for COVID-19 like pandemic using advanced hybrid technologies

In order to track patients in coronavirus (COVID-19) like pandemic, this paper proposes a novel model based on hybrid advance technologies, which is capable to trace and track COVID-19 affectees with high accuracy. The hybrid technologies include, cellular, cyber and low range wireless technologies. This technique is capable to trace patients through call data record using cellular technology, voice over Internet protocol calls using cyber technology and physical contact without having a call history using low range wireless technologies. The proposed model is also capable to trace COVID-19 suspects. In addition to tracking, the proposed model is capable to provide surveillance capability as well by geo tagging the patients. In case of any violation by the patients an alert is sent to the concerned department. The proposed model is cost effective and privacy preserved as the entire process is carried out under the umbrella of a concerned government department. The potential outcomes of the proposed model are tracking of COVID-19 patients, monitoring of isolated patients, tracking of suspected ones and inform the mass about the safest path to use.

Understanding gender segregation through Call Data Records: An Estonian case study.

Understanding segregation plays a significant role in determining the development pathways of a country as it can help governmental and other concerned agencies to prepare better-targeted policies for the needed groups. However, inferring segregation through alternative data, apart from governmental surveys remains limited due to the non-availability of representative datasets. In this work, we utilize Call Data Records (CDR) provided by one of Estonia’s major telecom operators to research the complexities of social interaction and human behavior in order to explain gender segregation. We analyze the CDR with two objectives. First, we study gender segregation by exploring the social network interactions of the CDR. We find that the males are tightly linked which allows information to spread faster among males compared to females. Second, we perform the micro-analysis using various users’ characteristics such as age, language, and location. Our findings show that the prime working-age population (i.e., (24,54] years) is more segregated than others. We also find that the Estonian-speaking population (both males and females) are more likely to interact with other Estonian-speaking individuals of the same gender. Further to ensure the quality of this dataset, we compare the CDR data features with publicly available Estonian census datasets. We observe that the CDR dataset is indeed a good representative of the Estonian population, which indicates that the findings of this study reasonably reflect the reality of gender segregation in the Estonian Landscape.

Modeling mobile health service delivery to Syrian migrant farm workers using call record data

A significant number of Syrian refugees under temporary protection in Turkey work in agriculture seasonally in various rural areas during several months a year. These migrant farm workers and their families are deprived of access to the regular health care system and preventive services due to their remote locations. The government supports the delivery of different types of mobile health care services, such as vaccination for children, reproductive health and screening services. While planning the mobile health care service delivery, it is critical to know where the refugees will work during what time frame; hence the demand for the services. By analyzing the call record data of a major mobile network operator in Turkey, we quantify the increase in the volume of calls made by Syrian refugees in various agricultural areas during the harvesting season of local crops. This information helps us to forecast spatial and temporal distribution of demand for mobile health care services at a fine granularity. Taking demand over multiple periods as input into a mathematical programming model, we optimize the routing of mobile clinics that visit locations close to where refugees are concentrated over the given planning horizon. We consider three hierarchical objectives. Given the availability of a number of mobile clinics at community health centers in the districts, the first objective aims to maximize the percentage of refugees that can benefit from each service type within pre-defined close distances. The second objective minimizes the number of clinics needed while covering the maximum percentage of refugees. The third objective minimizes the total travel distance of the clinics, while keeping the maximum coverage level using a minimum number of clinics to achieve this level. We quantify the benefits of centralized planning (by the province directorate) over decentralized planning (by each district separately). We also show the trade-off between the required number of clinics and coverage of potential patients.

A Privacy-Preserved and Cost-Efficient Control Scheme for Coronavirus Outbreak Using Call Data Record and Contact Tracing

Coronavirus or COVID-19, which has been declared pandemic by the World Health Organization, has incurred huge losses to the lives of people throughout the world. Although the scientists, researchers, and doctors are working round the clock to develop a vaccine for COVID-19, it may take a year or two to make a safe and effective vaccine available for the world. In current circumstances, a solution must be developed to control or stop the spread of the virus. For this purpose, a novel technique based on call data record analysis (CDRA) and contact tracing is proposed, which can effectively control the coronavirus outbreak. A positive coronavirus patient can be traced through CDRA and contact tracing. The technique can track the path traversed by the patient and collect the cell numbers of all those people who have met with the patient. Keeping intact the privacy of this group of people, when a test result of a person comes positive among the group, then he/she must be isolated and same CDRA and contact tracing procedures are adopted for that person. A COVID-19 patient is geotagged and alerts are sent if any violation of isolation is done by the patient. Moreover, the general public is informed in advance to avoid the path followed by the patients. This privacy-preserved and cost-effective mechanism is not only capable to control the coronavirus outbreak but also helps in isolating the patient in his/her house.

USE OF THE STATISTICAL ANALYSIS METHODS TO DETECT VOIP NETWORK TRAFFIC ANOMALIES

The purpose of the study is to automate detection of signs of technical malfunction and deterioration in the quality of services in the VoIP network. Deterioration of quality leads to a decrease in the volume of services provided, and consequently a profit, a decrea se in customer loyalty and loss of market share. There are three levels of quality degradation in VoIP networks: lack of access at the data network layer, inability to establish a voice connection and lack of access at the level of application services, and degradation of service quality. The analysis of absolute and relative statistical quality indicators of IP-telephony in accordance with the requirements of the international ITU-T standards has been performed, and main indicators and formulas for their calculation are listed. The values of statistical quality indicators are periodically calculated for external channels, subscriber groups and tariff directions. The primary data is CDR (call data records). To detect anomalous changes in the values of the quality indicators it is proposed to use the exponential smoothing method – the Holt-Winters additive model. The deviation of the current value of the quality indicators from the forecasted one is calculated. The confidence range is calculated using the Brutlag method. If the deviation goes beyond the confidence range, the change in the value of the indicator is considered anomalous and the value of the anomaly coefficient of the indicator is set. The period is characterized by a vector of anomaly coefficients of all quality indicators. To classify the period as anomalous, the value of the module of the anomaly coefficients vector of the given period is used. The features of the method application are also considered, in particular the choice of the seasonal period and the calculation of anomaly coefficients during periods of minimum load. The proposed method allows to diagnose an abnormal change in the values of VoIP service quality indicators in automated mode. The prototype of an automated system for the quality of VoIP service monitoring was developed on the base of the method described.

A Comparative Study on Contract Recommendation Model: Using Macao Mobile Phone Datasets

Bordering on the Mainland of China, Macao is a city with diverse population and is also a world-famous gambling city. The residents living in Macao are not only localresidents, but a large-scale of residents are from the Mainland of China. There are diversified living habits among different resident groups. Some of them live and work in Macao most of the time, while others cross the border between Macao and the Mainland of China frequently. These diversities result in different demands for mobile phone contract services. Machine learning and data mining are powerful tools used by telecom companies to monitor the behavior of their customers. This paper aims to build a contract service recommendation model suitable for Macao telecom companies, which can accurately recommend the best fit contract services according to call data records (CDR). Based on data mining algorithm and large number of comparative experiments, this study conducts a study on variety of factors that have effect on the contract recommendation for obtaining a composition structure of factors that have the greatest impact on contract recommendation accuracy so as to improve the operation efficiency of the model. In addition, this study makes comparisons among five classification algorithms, including Bayesian, logistic, Random trees, Decision tree (C5.0), and KNN (k-nearest neighbor). The results are analyzed by different metrics such as Gain, Lift, ROI (region of interest), Response, and Profile. Experimental results demonstrate that the best classifier is decision trees (C5.0), and the contract service obtained by this method can achieve a recommendation accuracy close to 90%, which successfully reaches the expected goal.

Financial and Legal Obligations that appear from Internet Traffic - Technology of Information and Communication Kosovo Case

In this case study we have presented the comparison of the calls made by the clients to the telephone operator Y and the calls which have been transferred to the company responsible for the quiz through telephone calls. During this analysis we gathered calls from the Composite Call Data Record (CDR), the CDR partition is divided in two part, the CDR Originating part and the part of the CDR transit part.The part of the CDR Originating are as the showed following: Calling Party Number, Called Party Number, Date Fort Start Of Charge, Time For Start Of Charge, Time For Stop Of Charge and Chargeable Duration. The part of the CDR Transit part contains completely the same data that must be identical because it is the same call that additionally contains other information such as the name of the incoming route from which the call and outbound route or where the call came from is addressed by identifying its name. The data has been decoded by the hexadecimal system in the decade system to compare the numbers of calls, duration calls and time of calls. From the analysis that is done in this case study has come out there is a difference from the number of calls as well the duration of the calls that have been on the part of the customers to the operator Y and the calls directed by the operator Y in the contracting company X

Financial and Legal Obligations that appear from Internet Traffic - Technology of Information and Communication Kosovo Case

In this case study we have presented the comparison of the calls made by the clients to the telephone operator Y and the calls which have been transferred to the company responsible for the quiz through telephone calls. During this analysis we gathered calls from the Composite Call Data Record (CDR), the CDR partition is divided in two part, the CDR Originating part and the part of the CDR transit part.The part of the CDR Originating are as the showed following: Calling Party Number, Called Party Number, Date Fort Start Of Charge, Time For Start Of Charge, Time For Stop Of Charge and Chargeable Duration. The part of the CDR Transit part contains completely the same data that must be identical because it is the same call that additionally contains other information such as the name of the incoming route from which the call and outbound route or where the call came from is addressed by identifying its name. The data has been decoded by the hexadecimal system in the decade system to compare the numbers of calls, duration calls and time of calls. From the analysis that is done in this case study has come out there is a difference from the number of calls as well the duration of the calls that have been on the part of the customers to the operator Y and the calls directed by the operator Y in the contracting company X

CaseNote: Mobile phone call data obfuscation & techniques for call correlation

The use of call data records (CDRs) to establish links between suspects is well known and understood. In a number of major enquiries in the UK, however, it was found that CDRs contained apparently erroneous or nonsensical data which prevented the use of well-established techniques based on caller IDs contained within CDRs. Further analysis suggested that some form of number “spoofing” was being used and techniques were developed to associate calls made using one of the two mechanisms which appeared to be in operation. A working hypothesis about how the calls are being handled in order to implement obfuscation has been developed, based on additional data leaked by some of the mobile network providers.

The Potential Of Blockchain Technology To Change International Mobile Roaming Business Model

The key objectives of this paper is to propose a design implementation of blockchain based on smart contract which have potential to change international mobile roaming business model by eliminating third-party data clearing house (DCH). The analysis method used comparative analysis between current situation and target architecture of international mobile roaming business that commonly used by TOGAF Architecture Development Method. The purposed design of implementation has validated the business value by using Total Cost of Ownership (TCO) calculation. This paper applies the TOGAF approach in order to address architecture gap to evaluate by the enhancement capability that required from these three fundamental aspect which are Business, Technology and Information. With the blockchain smart contract solution able to eliminate the intermediaries Data Clearing House system, which impacted to the business model of international mobile roaming with no more intermediaries fee for call data record (CDR) processing and open up for online billing and settlement among parties. In conclusion the business value of blockchain implementation in the international mobile roaming has been measured using TCO comparison between current situation and target architecture that impacted cost reduction of operational platform is 19%. With this information and understanding the blockchain technology has significant benefit in the international mobile roaming business.

Profile based location update for cellular network using mobile phone data

In the wireless cellular network, location management is one of the intricate dynamic issues that expend the available limited wireless resources in order to guarantee for delivering a call to the mobile device. Towards enhancing the Quality of Service and reducing the dilemma of location management, an improved location update scheme has been proposed in this paper to capture the daily behavioral pattern of the mobile users. Here a profile based LU scheme has been developed according to the mobility pattern of the individual users in a cellular network. Especially, mobile phone data is recorded in a Call Data Record (CDR) data base containing the spatial–temporal information of the millions of anonymized users for consecutive 2 months. In this paper, the proposed profile based LU technique takes into consideration of the individual user movement to optimize the location update characteristics in order to minimize the signaling cost of mobile network. The proposed algorithm shows an improvement of 17% in terms of bandwidth compared to the conventional technique. The use of CDR data for profiling the users, the mathematical formulation which has not yet been used by the other researchers and validation of the algorithm based on actual user data rather than theoretically predicted data are the novelty of this work.

Mobility pattern of individual user in dynamic mobile phone network using call data record

The pervasiveness of cellular telephones, along with rapid advancement in cellular technology, wireless networks and mobile applications, has made them increasingly effective in our daily lives. Individual human activity with respect to travel behaviour is still in a less explored stage. In the past few decades, travel patterns and human activity have become more complex and exhibit a high degree of variations in space and time. In this study, how and in what extent Call Data Records (CDRs) from mobile phones provide the underlying activities of anonymised customers when a user initiates or receives a voice call or message is investigated in detail. Thus, this paper attempts to discover personal human mobility patterns where location, duration and days are the essential attributes in the interpretation of results. Profile-based paging algorithm has been proposed based on the individual human travel pattern. The finding suggests that the proposed algorithm is three times more efficient than conventional paging (blanket paging) and two times more effective than various other intelligent paging algorithms. Further, a substantial saving of about 35% in bandwidth is also obtained from the validation results.