An Improved Automatic Traffic Incident Detection Technique Using a Vehicle to Infrastructure Communication

Trac incident detection is one of the major research areas of intelligent transportation systems (ITSs). In recent years, many megacities suer from heavy trac ow and congestion. erefore, monitoring trac scenarios is a challenging issue due to the nature and the characteristics of a trac incident. Reliable detection of trac incidents and congestions provide useful information for enhancing trac safety and indicate the characteristics of trac incidents, trac violation, driving pattern, etc. is paper investigates the estimation of trac incident from a hybrid observer (HO) method, and detects a trac incident by using an improved automatic incident detection (AID) technique based on the lane-changing speed mechanism in the highway trac environment. First, we developed the connection between vehicles and roadside units (RSUs) by using a beacon mechanism. en, they will exchange information once the vehicles get access to a wireless medium. Second, we utilized the probabilistic approach to collect the trac information data, by using a vehicle to infrastructure (V2I) communication. ird, we estimated the trac incident by using an HO method which can provide an accurate estimation of an event occurring. Finally, in order to detect trac incident accurately, we applied the probabilistic data collected through V2I communication based on lane-changing speed mechanism. e experimental results and analysis obtained from simulations show that the proposed method outperforms other methods in terms of obtaining a better estimation of trac incident which agrees well with the theoretical incident, around 30% faster detection of trac incidents and 25% faster dissipation of trac congestion. With regard to duration of an incident, the proposed system obtained a better Kaplan– Meier (KM) curve, inuenced by the shortest duration of time to clear the trac incident, in comparison with the other methods.


Introduction
In recent years, intelligent transportation systems (ITSs) draw a great deal of attention for the researcher of wireless and communication technology background. is raises concern to the transportation authorities because of the large number of vehicles on the road causing tra c incidents, congestions, road bottlenecks, etc. ITS integrates wireless communication technology with the transport networks in order to provide tra c safety, reduce tra c congestion, and improve tra c management [1,2]. In addition to the tra c safety, ITS also provides entertainment services on vehicles such as climate information, internet access, etc. In many global cities, people are using private cars, taxi and bus to commute to their destination.
Because tra c conditions on the road can rapidly become severe, it can a ect the transport operations. Speci cally, many metropolitan cities are su ering from severe tra c congestions in the urban and highway tra c environments, which are caused by the tra c incident [3]. As a consequence, the loss and disturbance caused by the tra c incident, is directly associated with the duration of the tra c incident which, may further deteriorate the tra c ow. In this context, early detection of incidents is necessary to investigate and to implement the tra c strategy for an ITS. ese early incident detections can alleviate tra c congestion and hence improve the tra c ow for real-time tra c monitoring system in ITS [4]. e tra c incident is referred to as an abrupt change in tra c ow, which reduces the road capacity and increases tra c congestion. In the past, a tra c accident was very dicult to analyze due to the nature of an incident which is always changing and this makes the detection more complex for transportation authorities. Such complexity can cause the failure of the transportation management system. erefore, there is a great need of designing a sophisticated algorithm, which is able to estimate and detect tra c incident. e challenging issue in ITS is to estimate and detect an incident from tra c congestion scenarios [5]. Generally speaking, an incident is referred to as an occurrence of an event that creates disturbance to the normal tra c ow [6]. Surveillance cameras are placed on the road to detect the tra c incident. An incident detection and the classi cation are a very important aspect in tra c management system. e tra c management system has the ability to conduct automatic incident classi cation (AIC) to evaluate di erent types of incidents [7].
As mentioned, in the past, many methods have been proposed which are used to collect data from the detectors such as loop detector, radar detector, video detector, etc. In this context, V2I communication system is used to collect data from vehicles to detect tra c incidents. V2I communication is a robust system, which is considered as a highly contributive in ITS [8,9]. e collected data are processed by AID algorithms, which can generate incident alerts in case of any tra c incident and violations. Tra c incidents can be detected by using global positioning system (GPS) detector. Asakura et al. [10] presented the properties of tra c ow dynamics under incident by using oating data gathered from GPS. In this scheme, a proposed method is able to predict the time and location of tra c congestion in uenced by a tra c incident. Surveillance cameras are placed on the road to detect the tra c incident. Incident detection and classi cation are a very important aspect of the tra c management system. e tra c management system has the ability to conduct automatic incident classi cation (AIC) to evaluate di erent types of incidents [7]. Ren et al. [11] presented a video-based technique to monitor and detect the tra c incident by evaluating the distribution characteristics of the tra c states on the road section. An incident detection system (IDS) play an important role in ITS which gains a lot of attention from the research community in recent years. e IDSs are designed to detect incident or unpleasant situation such as tra c incident, tra c violation and tra c congestion by using communication technology [5,6]. e main challenging issue for an ITS is to obtain an early and accurate detection of tra c incident [12].
In past decades, machine learning techniques have been widely utilized to detect tra c incident. Many arti cial neural network (ANN) were discussed [7]. Ritchie and Cheu [13] introduced an ANN technique which is able to detect the trafc incident with a better performance. However, the collection of ANN parameters is very complex and di cult to obtain. A hybrid approach is introduced by combing time series analysis and machine learning schemes to detect incidents [14]. is approach may detect tra c incidents accurately. Jin et al. [15] introduced the constructive probabilistic neural network (CPNN) in a highway tra c environment.
is model is tested on I-880 and evaluated by considering online and o ine tra c situations. However, this approach is able to detect only small tra c incidents.
To enhance the performance of AID, support vector machine (SVM) was introduced to detect tra c incident [4,16,17]. In [4], two SVMs were trained and simulated on the tra c incident data. is method did not produce a robust result because the selection criteria of SVM parameters and kernels are always very complex during the training process in order to construct a sample. Xiao [18] introduced SVM and -Nearest Neighbor (KNN) ensemble learning method to detect tra c incident. is model trains SVM and KNN learning, and combine them to obtain better results. Wang et al. [7] introduced an incident classi cation of tra c data by using SVM method. However, this method cannot support small tra c data and require a much longer time to process the tra c data due to the characteristics of the ST signals. In social media such as Twitter, it has become the most famous tool used to gather information and have a large user's account database, which can share a portion of data to the public using APIs [19]. In recent years, many works have been proposed to detect the tra c incident by analyzing the location and time of an incident from tweets. In Ref. [19], Gu et al. introduced a real-time tra c detection from Twitter using the REST API. e proposed method utilizes Semi-Naive Bayes (SNB) method to detect ve di erent incidents and obtain better performance. However, the processing of tweets from di erent incident situations o en required large computational time. Schulz et al. [20] introduced a method to detect small incident by analyzing microblog. is method obtains a better detection of an incident, but only applicable for the low-level applications.
Dabiri and Heaslip [21] proposed a framework which is able to monitor and detect tra c incidents based on Tweeter, by using deep learning method. e proposed method utilized the numerous amount of Tweets to evaluate the tra c event condition and required a large computational time to process these tweets. Zhang et al. [22] introduced a new method to detect tra c incidents from Tweets using a deep learning method. e proposed method utilized millions of Tweets and was applied in two megacities. It also achieved better tra c incident detection, while consuming a large amount of time to process millions of Tweets. Paule et al. [23] proposed a method for geo-localization tweet, by utilizing a weight-voting algorithm where the weight of tweets votes depend on the user's reliability. e proposed method obtains a better detection of real-time tra c incident. However, due to an increase in the voting users, the proposed method is limited to the lower coverage and also limited users.
AID algorithm is used to calculate new parameters values from collected data and then compare these values to the threshold values to identify the incident detection. Several famous methods falls in this category such as McMaster Algorithm [24] and California Algorithm [25]. Recently, many approaches have been used to enhance the performance of existing AID schemes, such as integration of V2I communications with Bayesian-based scheme [26], which is focused on less tra c ow to detect an incident. He et al. [27] proposed a hybrid tree-based quantile regression method to predict and evaluate the incident duration. e presented method produced better results as compared to other predictive models. Peeta et al. [28] also proposed a variable message sign (VMS) scheme that only focused on the prediction of incident clearance time because of the delay caused by an accident.
Lu et al. [29] proposed a method to detect traffic incident based on nFoil. is method was implemented on the real traffic data and simulated traffic data generated from Singapore highway. e proposed method produced a better detection of a traffic incident. However, it required a longer time to process traffic data. Wang et al. [30] introduced an efficient multiple model particle filter (EMMPF) to estimate and detect traffic incident. e main idea is to implement an EMMPF to reduce the large computational time, which occurred in traditional AID techniques during the training of datasets. e proposed system is able to reduce the large computational time and the proposed method is only limited to the hybrid system which contains a large model. Based on GPS analysis, D' Andrea and Marcelloni [5] proposed a method to detect traffic incident and congestions to obtain a better incident detection rate. However, the proposed system was unable to differentiate between the traffic incident and congestion event due to the correlation of GPS data gathered from the moving or slow vehicles. Fogu et al. [31] introduced e-Notify system, which is able to detect traffic accident rapidly and also reduce the incident duration time, by implementing efficient communication through the combination of V2I and V2V, respectively. In the past, improved nonparametric regression based model was proposed to detect traffic incidents [32]. Popescu et al. [33] introduced an AID scheme, in which the lane changing distance and lane changing speed mechanisms were utilized to detect the traffic incident based on the collection of traffic-information data by using V2I communication. However, this method required a longer time to process the traffic data in terms of vehicle lane changing distance and also this scheme cannot distinguish the road bottleneck caused by a traffic incident.
e estimation and detection of traffic incident are one of the main challenging issues in the ITS. In the past, previous studies revealed that AID is a well-known and robust technique to detect traffic incident. Also, an AID technique can overcome the traffic congestion at the location where the occurrence of an incident caused the traffic difficulties such as road bottleneck, accident, and disabled vehicles, electronics equipment malfunctioning and other issues which can disrupt the traffic flow. Significant monitoring, estimation, and detection of traffic incident provide relevant traffic-related information to enhance the traffic safety and driving experiences, by providing a driver with real-time traffic information to assist decision. In particular, traffic monitoring, traffic incident management and traffic safety management are the main pillar for enhancing the ITS. is inspired us to further investigate the estimation and detection of the traffic incident. Specifically, the estimation of traffic incident and detection is somehow related to the pattern recognition problem, in which the incident and nonincident must be evaluated and classified. A sophisticated learning method can be applied to AID a er training the data. So far, the support vector machine, neural network and deep learning techniques have been utilized to deal with this issue. ese techniques depend on the propositional learning systems, which indicates that the data learned from these systems are propositional and not reliable. Also, a few AID algorithms such a McMaster algorithm [24] and California algorithm [25] are used to calculate the new parameter values from the collected data and compare these values to the threshold values to identify the incident detection. e estimation of traffic incident may not be accurate because of the hybrid modeling, in which the traffic incident can occur at any location with different traffic conditions. Estimation of traffic incident with HO method and incident detection with an improved AID technique are not covered well in the above studies. Also, the traffic data were not utilized to analyze the incident conditions.
In this paper, we presented an efficient ITS system, which is able to estimate and detect the traffic incident from the hybrid observer and an improved AID technique, respectively.
e proposed system significantly utilized the PWSL observation to estimate the traffic incident and probabilistic collection of traffic data to detect the traffic incident. First, we developed the connection between vehicles and RSUs by using beacon mechanism. Once the connection is developed, they will exchange traffic-related information. Second, we employ the HO method to estimate the traffic incident, these estimations can provide an accurate estimation of an event occurring.
ird, in order to detect traffic incident accurately, the proposed method exploits the probabilistic approach to collect the traffic information data by using V2I communication based on the lane changing speed mechanism. e rest of this paper is structured as follows. Section 2 presents the system modeling in which vehicle signing and beacon signal mechanism have been discussed. Section 3 presents the probabilistic approach to obtain the traffic information data. Section 4 presents the proposed estimation of traffic incident and detection method. Section 5 discussed the comparison of the proposed model with different competent methods. Simulation results are presented in Section 6. Finally, Section 7 concludes this paper.

System Model
In this work, we assumed that the vehicles are equipped with a wireless module, which is used to communicate with the RSUs that are placed on the road to exchange traffic-related information with any passing vehicles. In addition, vehicles are also assumed equipped with the event data recorder (EDR) [34], which is used to monitor fast acceleration, speed, and lane information of the vehicles. Figure 1 shows the system model of highway traffic flow on the road with the movement of vehicles in the forward direction. e RSUs are placed on the road apart from each other with a distance of nearly 1.5 km. ese RSUs are able to provide equal coverage in its vicinity. Also, the RSUs situated in the adjacent and on the opposite side of the road, are used to construct infrastructure. Each RSU contains a GPS device to obtain the exact location of vehicles, a radio transceiver for developing a connection between passing vehicles and a computing device that processed traffic information data gathered from vehicles, such as lane changing speed and distance.
As shown in Figure 2, Figure 2(a) illustrates the vehicles are moving in the forward direction with the constant speed, Both the vehicle and TA must initialize the counter to the value of and increment it by at every message received by the vehicle .

Beacon Signal Mechanism.
In this section, we discuss the beaconing signal process. A er sign-in, each vehicle sends a beacon signal, periodic message, at every time second to share the detail information such as recent location, pseudoidentity and type of vehicle to the RSU.
Lets assume a vehicle establishs a beacon and transmits, the established beacon is expressed as below.
where PID is the pseudo-identity of the vehicle , is used to protect from replay attack, ( ) is the sign-in process of the vehicle.
and Figure 2(b) illustrates an aberrant change in the speed of a vehicle 1 during lane changing caused the tra c incident.

Vehicle Signing.
In the proposed method each vehicle needs to sign up and register their details with the transport authority (TA). TA is responsible for managing database of the vehicles such as, vehicle ID, personal information of the drivers, and also providing certi cates to the vehicles. It is important that all the vehicles must be connected with the TA. A time-dependent secret ( ) act on behalf of the TA for verifying the identity of the vehicle and when it issued a message last time. e secret can be computed and encrypted as below.
Lets assume the vehicle sent a request for sign-up, to the TA at time . First, TA will check the identity, of , and then generate a reply which contains three parameters , , , where is a symmetric key, and are two integer values.
Tra c incident caused by V 1 due to aberrant overtaking for successful aggregation. Let be the random variable which traces the number of vehicles that provided tra c data information among the passing vehicles. So that the equation can be written as follows.

Equation (4) observed as a binomial function, where
Equation (4) can be expressed as below.
Lets assume Φ is the incident target caused by . In order to detect the event which must satisfy the below condition.
e transpositions can be yields as below.
A er applying natural logarithm to the Equation (9) and then divide by ln 1 − 1 − , so the nal equation can be expressed as below.
Equation (3) is used to calculate the beacon signal, lets assume when a witness vehicle received a message, it immediately checks the time-stamp function of the received beacon, and then verify the beacon signal . If both values match, then the beacon content is correct. erefeore, the beacon is considered valid within the vicinity of the incident vehicle. As shown in Figure 3, the total time required to exchange the tra c information between vehicle and RSU is , 1 is the time when the vehicle are waiting to receive beacon, and at the time 2 vehicle and RSU start to develop connection. Once the vehicle gets access to the wireless medium, it will exchange information such as ID, speed, acceleration, with RSU at time /2 , and exchange the information from RSU to vehicle at time /2 , respectively.

Collection of Traffic Information Data
Due to an enormous amount of tra c ow in the urban tra c environment, data from externalities on the road are o en interlinked with other vehicles. Consequently, it is very dicult to collect and manage data from each vehicle passing through RSU. In order to obtain the accurate detection of trafc incident. Firstly, we applied the probabilistic approach to collect the data from the passing vehicles [36].
We assumed that the RSUs are active and able to collect the tra c-related information from the vehicles passing through the RSU with the probability of . In particular, the vehicles are capable of maintaining a database of reliable tra c information to identify the tra c conditions that shows the sign of tra c incidents. e data collected from number of vehicles with the probability of 1 − can lead to provide optimum aggregation. For some application ranges from 0 < < 1 [36].
Lets assume is an event caused by incident vehicle, i.e. vehicle (see Figure 4) Figure 4 illustrates the estimation of the tra c incident, which rely on the tra c-related data and continuous observer. By using the continuous observer mechanism, we can obtain the accurate estimation of tra c incidents.

Tra c State Estimation.
In most of the estimation approaches, the utilization of Lyapunov function ensures the asymptotic convergence of the estimated error [38]. A multiple Lyapunov function introduced a piecewise Lyapunov function due to the nature of the piecewise hybrid system to ensure the guarantee of error reduction [39].
To solve the HO problem which relies on determining the observer gain , the estimated tra c incident ̀ ( ) could converge with the theoretical incident ( ). erefore, the di erence of possible error between theoretical and estimated incident can be expressed as below.
e convergence of the tra c incident estimation error is required to obtain the gain of the hybrid observer of (11), which ensure that − is a Hurwitz matrix.

Detection of Tra c Incident.
To detect tra c incident based on lane changing speed, RSUs rst collect the tra c information related to speed changing between the vehicles and then analyze and evaluate the vehicle speed in the incident and nonincident conditions. In other words, at the nonincident conditions, the average change in speed in shorter average time during changing lane as compared with the incident conditions. In this method, we used the collected tra c information from the RSU related to vehicle speed changing, to evaluate whether or not the incident has occurred when the vehicle changing lane speed falls in the critical region of the de ned threshold values. Figure 5 shows the vehicle lane-changing process which identi ed that the three vehicles , , and vehicles are travelling along the road. Vehicle is switching from lane 2 at "point a" to lane 1 at "point b" to pass and cross the vehicle . e aberrant change in speed from "a" to "b" caused by the driver behavior which creates disturbance to Equation (10) is used to determine the number of vehicles which is necessary for meaningful aggregation at the event caused by the incident vehicle in the highway tra c environment.

Designing of PWSL Hybrid Observer.
A designing observer is used to estimate and reconstruct the tra c states of the dedicated system by using measurable variables. As the nature and characteristics of tra c systems are complex, a hybrid observer is able to estimate the possibility of occurring an event that detects the tra c incident. In order to obtain the accurate estimation of tra c incident, a PWSL model and hybrid observer are combined together to produce a better estimation [37].
To estimate the tra c incident, we have developed the structure of the hybrid observer with PWSL, which is written as.
where is the observer gain with tra c incident mode ̀ . is linked with the PWSL to ensure the accurate estimation of tra c incident ̀ ( ) with the theoretical incident ( ) under any tra c condition. erefore, the observed gains ensure the convergence of estimated error and stablize the matrices − .
Estimated tra c incident ̀ ( ) of the continuous state converge with the theoretical incident ( ) using the continuous tra c ow ( ), and the continuous output ̀ ( ) can be expressed as below.
where is the matrix with structures that depends on tra c conditions or state. e estimation of tra c incident depends on several factors such as tra c scenarios, road conditions, tra c ow, etc. collected tra c-related data from the RSU related to vehicle speed changing to evaluate whether or not the incident has occurred when the changing lane speed falls in the critical region of the de ned threshold values. Figure 7 shows the comparison of the theoretical incident with the estimated incident. In the simulation, we have considered three cases such as low, moderate and high tra c densities. Figure 7(a) illustrate the comparison of the theoretical and estimated tra c incident with low tra c density. From Figure 7(a), it can be seen that the detection of tra c incident takes a longer time to detect and clear an incident. However, the estimation of tra c incident is close to the theoretical incident, which indicated that the proposed method is able to estimate the tra c incidents in case of low tra c density. When the tra c density is moderate, the performance of the proposed method in terms of estimation of tra c incidents shown in Figure 7(b). Clearly improved estimation of tra c incident has been obtained. Also, it has the fastest clearance the other vehicles on the road, which may subsequently cause tra c incident. We assumed that the aberrant change in speed while changing lane by the vehicle also causes variation and disturbance of the vehicle speed. e RSU calculates the average speed variation which occurred during the lane-changing and the associated average time . Based on these parameters, we have de ned the threshold level, if the speed variation falls under the incident threshold region, then it clearly indicates that an incident has occurred, which is caused by the aberrant overspeeding during lane change.

Model Comparison
In ITS, model validation is considered as an important parameter because it is able to evaluate the e ectiveness of the presented method. ough, the study and empirical investigation revealed that the detection of tra c incidents is more complicated and challenging than the other traditional incidents due to the nature and characteristics of the tra c incident. ese characteristics depend on the tra c structure, pattern, and collection of tra c information data from infrastructure. In the past, many traditional AID techniques have been proposed which investigates the tra c incidents in di erent tra c scenarios [24,25]. In order to evaluate the performance of the proposed method, we have compared the results with traditional AID techniques. Also, the presented method is further validated by KM estimate [40], which is used to evaluate the duration and clearance of tra c incidents with other competent methods.

Incident
reshold Region. Figure 6 illustrates the average change in speed with the average time for lane changing mechanism in incident detection threshold region, i.e., incident and nonincident scenarios. It can be seen that, when a lane is congested due to road bottleneck, the average vehicle speed changes in much shorter average time under nonincident conditions as compared with the incident conditions. In this method, the proposed method uses the Journal of Advanced Transportation 8 the tra c incident. More speci cally, the tra c congestion depends on the number of vehicles which take alternative routes when the incident has occurred. From Figure 8, it can be observed that the proposed system achieved the fastest detection of the tra c incident. Also, when the incident is cleared by the police, the proposed method obtains the fastest dissipation of tra c congestion. Figure 8(a) shows the comparison of the proposed method with the heavy tra c congestion of 25% of tra c diverts. It can be seen that the improved AID technique is able to detect the fastest tra c incident as compared with the other methods. Figure 8(b) shows the comparison of the proposed method with 35% of tra c diverts. At the time, when the incident has occurred, 35% of the vehicles take other routes. By means of simulation, it can be observed that the proposed method obtains better incident detection and the fastest dissipation of tra c congestion. Figure 8(c) shows the comparison of the proposed method with 45% of tra c diverts. e proposed of incident detection. More speci cally, the proposed method obtained a better estimation of tra c incident than the low tra c density, and the estimation of tra c incident has somehow agreed with the theoretical tra c incident. Figure 7(c) illustrates the comparison of the theoretical incident with the estimated incident when the tra c density is very high. e proposed method obtained the most robust estimation of the tra c incident in comparison with the low tra c and moderated tra c densities. And, the estimated trafc incident is also very close to the theoretical incident. is indicates that the proposed method agrees well with the theoretical incident. Figure 8 shows the comparison of the proposed method with other methods. In our simulation, we assumed that when the incident occurred, it introduces tra c congestion. e simulation results demonstrated in Figure 8 shows that the tra c congestion is in uenced by vehicles.

Tra c Incident Detection.
e validation results reveal that the proposed method has the capability to estimate and detect the tra c incident with the fastest detection rate. With regard to duration of an incident, it can be seen from Figure 9 that the proposed model obtained a better KM curve by achieving the shortest duration of time to clear an incident among all other schemes.

Exchange Communication between Vehicle and RSU.
In our simulations, we assumed that the average speed of the vehicles passing from the RSU was varying from 20 mph to 80 mph in the highway tra c environment. e probability of exchange tra c information between vehicle and RSU was determined using the low data rates such as 512 kbps and improved AID technique is able to give the fastest incident detection and obtains the fastest dissipation of tra c congestion.
From Figure 9, we can evaluate the performance of the KM curves between the proposed method and other AID techniques. It can be seen that the duration of the incident of California algorithm and integrated method are similar to each other. e characteristics of these algorithms required a longer time to notify the police for the incident situation and also need more time to tow and clear an incident. e KM curve for the incident duration with the AID (CLD/CLS) technique obtained better performance than the Integrated and California methods. A er receiving complaint, the police arrived at the incident location in the shortest time to towing the incident vehicles and subsequently clear the incident. By using the proposed method, the police were able to clear the incident in the shortest time by towing away the incident  Figure 11, it can be seen that the probability of tra c information increases as the vehicles are heading towards the next RSU location. erefore, the strong connection between the vehicle and RSU is developed, which successfully lead to exchange of the tra c information between the passing vehicles and each RSU locations.

Probabilistic Comparison of Tra c Information
Data. Figure 12 shows the e ects of the number of vehicles on the probability of data collection. In order to accurately detect tra c incidents, we have assumed several parameters, the incident target Φ = 0.9, application parameter which is able to detect an incident accurately = 0.90, and the probability of 1 Mbps, and the high data rates such as 2 Mbps. As shown in Figure 10, the results obtained from the simulation revealed that the probability of exchange tra c information decreases with the increase of the average speed of the vehicles passing by the RSU. As the vehicle travels at low speed 50 mph and below, it will remain in the coverage area of the RSU for a longer time and be able to exchange the accurate tra c information at lower data rates such as 512 kbps. When the average vehicle speed exceeds 55 mph, the probability of successful exchange tra c information takes place between the passing vehicles and RSU at higher data rate such as 2 Mbps, which lead to provide the higher probability of exchange tra c information.

Vehicle Communication with Each RSU Location.
e simulation test is carried out to examine the in uence of vehicles traveling to each RSU on the probability of successful exchange information as illustrated in Figure 11. We have placed four RSUs with a distance of 1.5 km apart from each other that is where DR is the incident detection rate, is the number of incident cases detected and is the total number of incident cases reported.
where CR is the classi cation rate, which is used to determine the incident detection, is the number of events correctly classi ed and is the total number of events.
We further evaluate the performance of the proposed method by using performance index (PI), which can be written as below.
where , , and are the weight of the DR, FAR, and CR, respectively. We assumed that the values of the weight of DR, a vehicle to communicate with the RSU is = 0.7. Substitute all these values in equation (10), a er solving we obtained that 32 vehicles can communicate with RSU, with the probability of 90%. erefore, it indicates that RSU is able to acquire the tra c information data of 32 vehicles including incident vehicle, and it is also used to detect the tra c incidents caused by vehicle with the higher accuracy of = 0.90.

Performance Test Criteria.
In this section, we evaluate the performance of the proposed method with other well-known techniques such as Naive Bayes, SVM, and KNN using three criteria i.e. false alarm rate (FAR), detection rate (DR) and classi cation rate (CR) [41].
where FAR is the false alarm rate, is the number of false alarm cases, and is the total number of nonincident cases.  6.5. CPU Timing. Figure 14 shows the CPU comparison of the proposed method with KNN and SVM methods. When the tra c ow is 10, the CPU time of the proposed method and other methods were very low. As the tra c ow increases, the CPU required a longer time to process input dataset. From Figure 14, it can be observed that the KNN and SVM methods required a longer CPU time due to exploiting more input data, which subsequently required a longer time to process dataset. e proposed method obtains the less CPU time to process input dataset as compared with other competent methods.

Conclusion
e incident estimation and detection are the important parameters in the ITS for reducing the tra c congestion, improving tra c and road safety. However, the tra c incident may cause road bottlenecks, tra c congestion and disrupt the normal tra c ow. In this paper, we proposed an ITS model which is able to estimate the tra c incident from HO method, and then detect the tra c incident from an improved AID technique in the highway tra c environment. First, we present a hybrid observer method to estimate the tra c incident based on the combination of the PWSL model and a model estimation technique. Second, we designed a probabilistic approach to collect tra c information data by using a V2I communication based on lane-changing speed mechanism capable of detecting tra c incident accurately. e analysis shows that the proposed method can estimate the tra c incident more precisely and has the potential to estimate the tra c incident with three di erent tra c densities. By mean of the simulation, the proposed method has obtained a better estimation of the tra c incident, which agrees well with the theoretical incident. Furthermore, by comparing the e ectiveness of the proposed method for detecting tra c incident, the proposed method outperforms other methods by obtaining the fastest incident detection rate, and the fastest dissipation of tra c congestion. e comparison with the other methods in terms of duration of an incident, the proposed method obtains the shortest duration of time to clear an incident. Moreover, we have further evaluated the performance of the proposed method with well-known techniques such as Naive Bayes, KNN, and SVM using I-880 tra c data. Experimental results show that the proposed method obtained a better performance compared with other methods.
In the future, we will enhance the proposed model by using joint learning and support vector machine (SVM) techniques which can produce the robust detection of tra c incidents. Also, we will utilize the 5G wireless network to obtain the robust accuracy of tra c information data which will be successfully applied to estimate the tra c incident.
FAR, and CR are all 1/2. e larger value of PI indicates that the proposed method has obtained a better detection of tra c incidents. More speci cally, the smaller the FAR values, the higher the possibility of detecting tra c incident accurately. e performance of DR indicates that, when the DR values approaching 100%. It clearly indicates that the algorithm is able to detect the tra c incident well. However, the higher DR values may generate some false alarm.
To evaluate the e ectiveness of the proposed method, we further demonstrate the performance of the proposed method on I-880 datasets for evaluating FAR, DR, CR, and PI values, and compare these values with the other methods. Figure 13 shows the comparison of the proposed method with other competent methods in terms of FAR, DR, CR, and PI values. From Figure 13(a) it can be observed that the proposed method has obtained less FAR values as compared with the SVM method. Also, we can observe that the Naive Bayes and KNN methods produce worst FAR values as compared with the SVM method.
As shown in Figure 13(b), the proposed method has obtained the highest DR values which indicate that the accurate detection of tra c incident. Also, it can be seen that the KNN method has obtained better DR values to accurately detect the tra c incident as compared with the Naives Bayes and SVM methods. Due to the nature and characteristics of incident, the Naive Bayes and SVM methods are unable to detect tra c incident.
It can be noted from Figure 13(b) and Figure 13(c), the results of KNN method in DR and CR is very close to the proposed method. Also, from Figure 13(a) the FAR values of SVM are very close to the proposed method. Also from Figure  13(d), it can be observed that the proposed method has obtained better PI values as compared with other competent methods. erefore, it clearly demonstrates that the improved values of FAR, DR, CR, and PI enhanced the performance of the proposed method, thus, the proposed method has an ability to detect tra c incident on I-880 datasets.
More speci cally, from Figure 13, the observation values minimized FAR values when DR value was greater than 0.90. Data Availability e performance test data used to support the finding of this study are available from the corresponding author upon request.

Conflicts of Interest
e authors declare no conflict of interest.