Time to Critical Condition in Emergency Services

Providing uninterrupted response service is of paramount importance for emergency medical services, regardless of the operating scenario. Thus, reliable estimates of the time to the critical condition, under which there will be no available servers to respond to the next incoming call, become very useful measures of the system’s performance. In this contribution, we develop a key performance indicator by providing an explicit formula for the average time to the shortage condition. Our analytical expression for this average time is a function of the number of parallel servers and the inter-arrival and service times. We assume exponential distributions of times in our analytical expression, but for evaluating the mean first-passage time to the critical condition under more realistic scenarios, we validate our result through exhaustive simulations with lognormal service time distributions. For this task, we have implemented a simulator in R. Our results indicate that our analytical formula is an acceptable approximation under any situation of practical interest.

Telemedical emergency services: central or decentral coordination?

Background and objective Teleemergency doctors support ambulance cars at the emergency site by means of telemedicine. Currently, each district has its own teleemergency doctor office (decentralized solution). This paper analyses the advantages and disadvantages of a centralized solution where several teleemergency doctors work in parallel in one office to support the ambulances in more districts. Methods The service of incoming calls from ambulances to the teleemergency doctor office can be modelled as a queuing system. Based on the data of the district of Vorpommern-Greifswald in the Northeast of Germany, we assume that arrivals and services are Markov chains. The model has parallel channels proportionate to the number of teleemergency doctors working simultaneously and the number of calls which one doctor can handle in parallel. We develop a cost function with variable, fixed and step-fixed costs. Results For the district of Greifswald, the likelihood that an incoming call has to be put on hold because the teleemergency doctor is already fully occupied is negligible. Centralization of several districts with a higher number of ambulances in one teleemergency doctor office will increase the likelihood of overburdening and require more doctors working simultaneously. The cost of the teleemergency doctor office per ambulance serviced strongly declines with the number of districts cooperating. Discussion The calculations indicate that centralization is feasible and cost-effective. Other advantages (e.g. improved quality, higher flexibility) and disadvantages (lack of knowledge of the location and infrastructure) of centralization are discussed. Conclusions We recommend centralization of telemedical emergency services. However, the number of districts cooperating in one teleemergency doctor office should not be too high and the distance between the ambulance station and the telemedical station should not be too large.

Intelligent Speech Processing Technique for Suspicious Voice Call Identification Using Adaptive Machine Learning Approach

With recent advances in the field of data, there are many advantages of speedy growth of internet and mobile phones in the society, and people are taking full advantage of them. On the other hand, there are a lot of fraudulent happenings everyday by stealing the personal information/credentials through spam calls. Unknowingly, we provide such confidential information to the untrusted callers. Existing applications for detecting such calls give alert as spam to all the unsaved numbers. But all calls might not be spam. To detect and identify such spam calls and telecommunication frauds, the authors developed the application for suspicious call identification using intelligent speech processing. When an incoming call is answered, the application will dynamically analyze the contents of the call in order to identify frauds. This system alerts such suspicious calls to the user by detecting the keywords from the speech by comparing the words from the pre-defined data set provided to the software by using intelligent algorithms and natural language processing.

Two-way communication retrial queue with unreliable server and multiple types of outgoing calls

Retrial queue under consideration is the model of call center operator switching between input and outgoing calls. Incoming calls form a Poisson point process. Upon arrival, an incoming call occupies the server for an exponentially distributed service time if the server is idle. If the server if busy, an incoming call joins the orbit to make a delay before the next attempt to take the server. The probability distribution of the length of delay is an exponential distribution. Otherwise, the server makes outgoing calls in its idle time. There are multiple types of outgoing calls in the system. Outgoing call rates are different for each type of outgoing call. Durations of different types of outgoing calls follow distinct exponential distributions. Unsteadiness is that the server crashes after an exponentially distributed time and needs recovery. The rates of breakdowns and restorations are different and depend on server state. Our contribution is to obtain the probability distribution of the number of calls in the orbit under high rate of making outgoing calls limit condition. Based on the obtained asymptotics, we have built the approximations of the probability distribution of the number of calls in the orbit.

Two-way communication retrial queue with unreliable server and multiple types of outgoing calls

Retrial queue under consideration is the model of call center operator switching between input and outgoing calls. Incoming calls form a Poisson point process. Upon arrival, an incoming call occupies the server for an exponentially distributed service time if the server is idle. If the server if busy, an incoming call joins the orbit to make a delay before the next attempt to take the server. The probability distribution of the length of delay is an exponential distribution. Otherwise, the server makes outgoing calls in its idle time. There are multiple types of outgoing calls in the system. Outgoing call rates are different for each type of outgoing call. Durations of different types of outgoing calls follow distinct exponential distributions. Unsteadiness is that the server crashes after an exponentially distributed time and needs recovery. The rates of breakdowns and restorations are different and depend on server state. Our contribution is to obtain the probability distribution of the number of calls in the orbit under high rate of making outgoing calls limit condition. Based on the obtained asymptotics, we have built the approximations of the probability distribution of the number of calls in the orbit.

Two-way communication retrial queue with unreliable server and multiple types of outgoing calls

Retrial queue under consideration is the model of call center operator switching between input and outgoing calls. Incoming calls form a Poisson point process. Upon arrival, an incoming call occupies the server for an exponentially distributed service time if the server is idle. If the server if busy, an incoming call joins the orbit to make a delay before the next attempt to take the server. The probability distribution of the length of delay is an exponential distribution. Otherwise, the server makes outgoing calls in its idle time. There are multiple types of outgoing calls in the system. Outgoing call rates are different for each type of outgoing call. Durations of different types of outgoing calls follow distinct exponential distributions. Unsteadiness is that the server crashes after an exponentially distributed time and needs recovery. The rates of breakdowns and restorations are different and depend on server state. Our contribution is to obtain the probability distribution of the number of calls in the orbit under high rate of making outgoing calls limit condition. Based on the obtained asymptotics, we have built the approximations of the probability distribution of the number of calls in the orbit.

SmartCallerBot: A Multi-level Incoming Call Number Detection and Blocking using Context-award Technique and Artificial Intelligence

Recently, I have received many spam calls every day. My phone number is associated with many essential accounts due to this reason, so I could not change a new phone number. Sometimes the spam call wakes me up at 7 am on the weekend. This situation has sustained from March to June. It bothers my life. I have tried to put them in my phone blacklist, however every time the number call in is different, so my blacklist does not help so much. This paper proposes an application to automatically detect the call content and tell the user what kind of call it is. We applied our application to the call, especially from other states or countries. The results show that the app can detect if the call is a spam call or not.

National trends and state-level variation in the duration of incoming quitline calls to 1-800-QUIT-NOW during 2012–2015

IntroductionThe duration of incoming quitline calls may serve as a crude proxy for the potential amount of reactive counseling provided.AimsTo explore whether call duration may be useful for monitoring quitline capacity and service delivery.MethodsUsing data on the duration of incoming quitline calls to 1-800-QUIT-NOW from 2012 through 2015, we examined national trends and state-level variation in average call duration. We estimated a regression model of average call duration as a function of total incoming calls, nationally and by state, controlling for confounders.ResultsFrom 2012 through 2015, average call duration was 11.4 min, nationally, and was 10 min or longer in 33 states. Average call duration was significantly correlated with quitline service provider. Higher incoming call volume was significantly associated with lower average call duration in 32 states and higher average call duration in five states (P-value <0.05). The relationship between call volume and call duration was not correlated with quitline service provider.ConclusionsVariation in average call duration across states likely reflects different service delivery models. Average call duration was associated with call volume in many states. Significant changes in call duration may highlight potential quitline capacity issues that warrant further investigation.