Evaluation & Development of Road Traffic Accident prediction model by Using Artificial Neural Network

Significant effort and money have been expended in recent years to improve road and highway safety. A continuing problem for transportation engineers is to build and operate the transportation system in such a way that it serves a variety of social goals such as shortening travel time and increasing safety. There has been an increase in due to an exceptional surge in road transportation and automotive traffic in India as a result of and the economy's and consumers' consumption habits have grown at an exponential rate, resulting in dangerous conditions. Circumstances on our Indian roads, including highways and expressways The number of people killed or injured in traffic accidents on these roads is increasing year after year. The path Accidents, deaths, and injuries are global events, but the issue is more severe in mixed communities. The traffic situation on Indian multi-lane motorways; the true situation is likely to be far worse due to underreporting of incidents to make the road worse Furthermore, there is a culture of poor car upkeep, poor driving practice, and a lack of enforcing the law, and the casual attitude of road users Road safety has become a major concern for the general population, and highway safety in particular. Professionals in particular, because road accidents are a major cause of death; Furthermore, the economic losses as a result of property damage or lost working days as a result of injuries the annual cost of fatalities is estimated to exceed billions of dollars. Road safety is both a health and a safety concern and development issue of significance given its magnitude and gravity, as well as the as a result, negative effects on the economy, public

There have been numerous types of vehicles on the road in India due to the development of road networks, such as cars, buses, motorcycles, trucks, vans, and others that have been used as a base to move from one place to another. According to the statistics from the Road Transportation Department website in 2019, as shown in Figure, the registered public vehicles in India are increasing every year, indicating that road safety is an important aspect because it involves the majority of the people in this country who are primarily transported by road.

It is quite concerned based on the development of the complete situation about motor vehicles for that period. This is due to the fact that, as the diversity of motor vehicles on the road has increased, so has the number of accidents that have happened in India. This scenario must be investigated, and study must be conducted to determine the root reasons of the accident. It is also critical to ensure that India's present transportation infrastructure is in perfect working order in serving all types of vehicle users in this country.

The availability of transportation is directly and strongly tied to the economic development of any country, and the objective of transportation systems is to facilitate the efficient and safe movement of freight and passengers from one location to another. The increasing number of automobiles on the road had produced a serious social problem in the form of traffic accidents, which resulted in the loss of lives and property. According to several accident studies, road accidents are not caused by natural causes, but rather have a significant part in the causes of road accidents. As a result, road/highway safety is a modern-day necessity.

The Highway Police, Maharashtra State project "Highway MrityunjayDoot" was launched on March 1,

2021.

Following a thorough investigation into the causes of mortality in road accidents, it was discovered that the lack of rapid Medical Aid was the biggest source of worry. In many cases, the injured were not properly evacuated and transported, which compounded the injuries and medical condition. Employees from nearby Malls, Petrol Pumps, Local Dhabas or Hotels, and neighboring villages establish groups of up to 4-5 persons as part of this project. These groups are known as "MrityunjayDevdoot" (Angels of God) and are trained in First Aid (including CPR, precautionary procedures for lifting and transporting injured people, and so on) with the assistance of Government/Semi-Government or Social Organizations. The Maharashtra State Highway Police has developed the "Highway MrityunjayDoot "Project to avoid any such scenarios and to enable timely and effective evacuation of people injured in accidents within the "Golden Hour," which is critical.

Statistics and accident prediction models are commonly employed in highway safety research. For example, they may be utilised for establishing correlations between collisions and explanatory factors like traffic flow, kind of control, and highway geometrical features, among others. It has been found that neural network models may be used successfully in a variety of transportation study domains, including traffic safety studies, with outstanding results.. networked brains. Traditional statistical models can't match the versatility, accuracy, generalisation, and forecasting capabilities of ANNs. When it comes to predicting traffic accidents, ANN outperforms all other AI algorithms since it is capable of representing non- linear functions without the use of statistical simulations.

With this paper, members of the construction project team will learn about the aspects they must constantly monitor to ensure that the project meets its deadline and expectations. The study's goal was to create an ANN model that could predict the success of building projects based on the aforementioned variables.

In order to analyse one-dimensional, two-dimensional, and time-series data, these studies utilised MLPNN, CNN, and RNN architectures (multi-layer perceptron neural networks). CNN-based pavement health inspection and monitoring has received the greatest scholarly attention because of its potential to replace human labour. Data collecting, parameter optimization, model transferability, and low-cost data annotation are some of the primary problems that ANN meets in pavement material design, cost analysis, and fault

Here, we provide an approach to assessing the impact of rail network interruptions on the city's tram and bus systems. Models for optimising train scheduling and simulating dynamic public transit assignment are coupled in this framework in an iterative process. By iteratively constructing train schedules, passengers' flow re-distribution and delays may be taken into account. By conducting research, we've developed a framework that can be used to improve public transportation contingency plans at the strategic and tactical levels in response to short- and medium term disruptions, taking into account the impact on passengers of train network disruptions on the urban network. This technique allows for the retrospective quantification of interruption costs, including spillover effects.

Methods for building driving cycles, variables impacting performance and driving modes, and the car's fuel consumption are examined in this article. Standard driving cycles for urban settings are developed by synthesising several city-driving modes for passenger cars. This approach of synthesising driving modes for vehicles has been shown to allow for distinct identification of vehicle driving cycles while also taking into account the individual conditions of their

Using a time-space diagram, we compare the molecular model to the classical optimum velocity model to examine the rule of evolution for traffic flow stoppage. Molecular car-following models better replicate micro-level behaviour, according to the study's findings. Because of this, it's possible to build a more accurate model of the driver's behaviour as he or

We propose a new method for predicting risky driving behaviours based on vehicle motion state estimates and passenger subjective sensation ratings, utilising a hybrid model comprised of a cloud model and an Elman neural network (CM-ENN). We've built a data collection system for driving motion states to test the recommended technique in China's Shenzhen metropolis. Tests show that the novel method outperforms traditional neural network-based approaches in terms of precision and

During an official competition, a video tracking system (MEDIACOACH) and a GPS device were used to compare the number and distance travelled in various acceleration and deceleration stages. During the course of a season, data was gathered from a Spanish professional football team. Wimu Pro recorded higher accelerations and decelerations than MEDIACOACH, but both systems recorded the same number of total distances travelled.

We measured the filtering methods utilised to compute acceleration and the minimal effort time for these occurrences in this review.... Accurate evaluation of athlete acceleration and deceleration datasets has been hampered by the variance in GPS/GNSS device reporting on horizontal dilution of accuracy and satellite number information. Acceleration and deceleration loads may be influenced by technology-related differences across tracking manufacturers and devices, according to our research. As a result, applied team sport research must devise and implement an accelerated filtering method and reporting structure that are both consistent and possibly sport-specific.

An artificial intelligence-based computer model capable of predicting the execution costs of construction projects for Brazilian educational public buildings is being studied and presented. In order to train and test the neural network, the Ministry of Education's web portal was utilised to get the database. To optimise the gradient descent approach, a multilayer perceptron back propagation algorithm was applied. Using Pearson correlation coefficients and the mean absolute percentage errors, the findings were analysed.

their efficacy in producing realistic and accurate forecasts of building projects. The various Non- Traditional Methods employed in the study are Regression analysis, Artificial Neural Networks and Fuzzy Inference System. The result of the survey and literature review shows that many factors are affecting construction out of which 15 significant factors were identified by conducting t-test using SPSS Software. Data from 116 real executed construction projects in Kerala were collected for the most significant factors to build up models. The Models using ANN and FIS was done in Matlab whereas regression Analysis was carried out in SPSS Software

It has been suggested that ANNs can be used to forecast the decision-making process of construction professionals when selecting PCCTs in different stages of construction project delivery by evaluating survey data. How the questionnaire data may be used for ANN analysis is demonstrated by the standardised scaling of operationalized variables for pseudo-probability.

This study intends to fill up the knowledge gap that currently exists in the field. We wanted to use artificial neural networks (ANNs) to analyse and anticipate the influence of factors like communication on project rework costs. Twelve communication-influencing variables were discovered and tested throughout the data gathering phase. 18 construction projects were examined to determine the average amount of rework required. The hidden layer of our network had a sigmoid transfer function, whereas the output layer had a linear transfer function. To reduce the amount of rework and energy and resource consumption in building projects, project management can utilise the suggested model as an integrated decision support tool.

A six-story building is being used as a test case for the use of artificial neural networks (ANNs) in this research. In order to train the algorithm, 30 reinforced concrete buildings with a system of structural walls were manually created using the ETABS application. MATLAB was used to create and train the neural networks. An extra studied building was used for validation, where the actual savings were estimated and existing rules were confirmed.

Article, 07 June 2021 Project efficacy is determined using a benefit-cost analysis (BCA) that compares expected averted flood loss to project expenditures. However, it is occasionally necessary to make decisions concerning mitigation measures based only on generic construction features, even when conventional construction cost estimates are quite detailed. The average floor area of an existing single-family home, the number of stories, and the foundation type are used in this paper to estimate the costs associated with re-elevation using data modelling and mining methods like multiple regression, random forest, generalised additive model (GAM), model

Here, we're talking about everything that goes into creating a new home, from land acquisition and development through completion and decommissioning. Even during the maintenance phase, budgetary restrictions, environmental circumstances, a lack of communication, and the availability of qualified workers have an impact on costs and timeliness. These characteristics can also have a substantial impact on the efficiency and cost- effectiveness of the design management and construction phase of the process. This means that the design and construction phases are closely intertwined.

productivity. Project managers can benefit from the use of artificial neural networks (ANNs) in modelling the complex interconnections that are typical of building operations and in estimating productivity. A bricklaying productivity ANN model's network settings are delineated in this study.

Analytical, statistical and analogue models are grouped into three categories, and their features are examined. As a result, articles have been extensively examined in terms of their application area, method used, techniques utilised, journals published in, and the year of publication.. etc. Predicting construction costs and other associated projects using analytics and machine learning algorithms is a key finding of this research, which will help researchers discover the best practises for actual building projects.

The application of artificial intelligence for the assessment of concrete and reinforcement consumption and the selection of the best models for estimation; the estimation model was constructed by employing artificial neural networks. As measured by a mean absolute percentage error (MAPE), the best artificial neural network model had an accuracy of 8.56 percent for concrete consumption and 17.31 percent for reinforcement

The application field, method used, techniques employed, journals published in, and the year of publication of papers have all been extensively examined. Predicting construction costs and other associated projects using analytics and machine learning algorithms is a key finding of this research,

CSFs (critical success factors) for selecting construction contractors in Qatar to assist investors develop their homes more effectively and efficiently are the goal of this article. To begin, a comprehensive analysis of prior studies was conducted to identify the twenty most common CSFs used in the construction of dwellings. Afterwards, 280 investors were surveyed to see out how important CSFs were to them. CSFs that are important to investors while developing houses were analysed using Pareto analysis and the Analytic Hierarchy Process (AHP). Building contractor selection may be improved by researching the investor's behaviour in terms of frequency, cost and time in order to identify the most important Critical Success Factors

Cost estimating is an experience-based process that requires assessments of unknown conditions and intricate interactions between cost-influencing elements.. factors.. factors.. ANNs are analogy-based processes that are best suited to the forecasting of costs.. They can generalise solutions for future applications because of ANNs' capacity to learn from examples (previous projects) (future projects). Everyone, especially in the construction industry, is concerned about the cost of their project. Any project must have an accurate cost estimate in order to motivate a choice on whether or not to proceed with it.

The cost drivers have been divided into two groups based on historical research: qualitative and quantitative methods, which are the subjects of this study. This study also discusses computational intelligence (CI) approaches and ensemble methods for developing credible cost prediction models. There are limits and suggestions in this study's hybridization of (FL) models, neural networks, regression models, case-based reasoning, and hybrid models are all investigated in this study.

In order to better anticipate project cost indices, this research aims to reduce the drawbacks of the Earned Value Management (EVM) technique by employing an Artificial Neural Network (ANN) and multiple regression. This study focused on 50 different road development projects in Iran's Fars Province. Cost performance indices were forecasted using an ANN model, which allowed for a more accurate comparison between anticipated and actual costs by taking into account elements that impact project success. MATLAB was used to examine the ANN model's input data. In addition to the ANN, a multiple regression model was employed to verify the results.

Accurate project estimates are critical for businesses. Because there is so little information available about the scope and details of the project, traditional methods of cost estimation tend to be slow and inaccurate. Machine Learning (ML)-based technologies like Artificial Neural Networks (ANNs), may now be utilised for more accurate cost prediction even in the face of limited information during the bidding process because of the increased computing power available in today's world. While ANNs have been widely investigated by contractors, there has been little study on the development and deployment of ML-based techniques for engineering consulting firms. Because the products and services provided by consultants are distinct from those provided by contractors.

Cost analysis at an early stage may be enhanced by applying neural networks, which can give more accurate results and reduce estimation errors. The Republic of Croatia has a tendency to overspend on road construction projects. In order to avoid mistakes and raise the possibilities of success in future road projects, the contractor's prior work on comparable projects is a crucial factor. Artificial neural networks may be used to predict construction costs at various phases of the project life cycle using data from previous projects.

The purpose of this research is to estimate the costs through the use of an Artificial Neural Network (ANN) (ANN). Finally, a reasonable assessment of the model's accuracy is provided. Microsoft Excel Solver and MATLAB software were used to create a neural network model analysis. Papers on the building of artificial neural networks (ANNs) are the focus of these efforts. Research papers, articles, and studies on this topic are discussed in this document. Artificial neural networks (ANNs) have the potential to transform the way building costs are estimated in the future..

Artificial Neural Networks (ANNs) can be used to generate a more accurate method for estimating building highway projects. The back propagation approach was used to train and evaluate several network designs with 10, 15, and 20 neurons. Data from fourteen Brazilian highway projects was gathered and examined as a result of this. After a lot of trial and error, eleven criteria were identified that had the greatest impact on the final building cost. Cost estimates had an average accuracy of 99 percent in the best-case scenario. Public agencies may employ this preliminary study's findings if the tool is shown to be feasible for use on Brazilian projects in the future..

The Daerah Istimewa Yogyakarta I-girder Bridge's detailed engineering design yielded a cost estimation model based on thirteen data points (DIY). I-girder Bridge superstructure costs were influenced by a number of variables. It is important to consider factors such as bridge span and breadth, sidewalk size, and kind of railing when determining the cost of a construction. Multiple linear regression (MLR) and artificial neural network (ANN) are used to generate the best estimation model using these variables. The study revealed that the length and breadth of the bridge were the most significant determinants of price.

When it comes to building reinforced concrete duplex houses, this study aims to illustrate how design parameters and unit prices fluctuate over time. An efficient design can be created in this manner. It's also a goal to create an estimating model for costs based on a small number of design characteristics. The early design process will save time and money by using a model with a low error

Using neural networks and multilayer perceptrons, we want to build a model for estimating construction costs. We create NN and MLP models with varying numbers of hidden nodes and layers. In this study, four synthetic neural networks and twelve multilayer perceptron models are put side by side for comparison and contrast. MLP and NN outperform statistical regression when it comes to predicting outcomes. On training datasets, MLP outperforms NN; but, on testing datasets, it fails.

Predicting the energy consumption and costs of CLT office buildings in cold climates at an early stage of for input variables containing building form and construction variables were determined using local building standards and surveys. To train ANNs using simulation data, researchers employed LHS, a Latin hypercube sampling (LHS) strategy for selecting training datasets.

Forecasting the severity of traffic accidents is an important step in the intelligent transportation and traffic management system because it allows drivers at higher risk of catastrophic accidents to be identified and avoided colliding. The multilayer perceptron neural network (MPNN) is by far the most popular, fundamental, and widely utilised form of neural network (NN) for forecasting road accidents.

To compare the two models, a graph was created showing the difference between the predicted crashes and those that really occurred. The ANN was found to be more effective. It has an R2 score of 88.79 percent for the ANN model There were several discrepancies between the ANN model and the MLR model. In terms of forecasting traffic accidents, the ANN model outperforms the Multiple Linear Regression model.

The study concluded that the ANN model's superiority is demonstrated by its low error value and r2 value. As a result, artificial neural networks can be used to forecast the number of accidents on two-lane undivided roadways. This also serves as a platform for connecting ANN to other planning models in order to achieve the best results in the field of transportation planning.

evaluate and compare all traffic accident features. The model's superiority is indicated by low mean squared error values. The findings showed that, based on appropriate data, forecasted traffic accidents are near enough to real traffic accidents to be reliable in predicting future traffic accidents in Khulna Metropolitan City.

The study concluded that the ANN model's performance varied based on the type of accident. When evaluating predictions utilizing data from 2010 to 2012, it was discovered that the ANN and BN models performed similarly for minor and severe injury events.

―By studying different examinations like Highway survey and traffic analysis that the problem at city by pass Highway is due to insufficiency of Highway space for the vehicles to pass through the junction at different instants of time in a day which is effecting the free flow of traffic, and improper movement of traffic also results in occurrence of accident in different instants of time.‖ As previously said, the number of incidents is increasing year after year and has become a major source of safety concern. As a result, doing this research is vital in order to grasp the scale of the problem, as well as to understand what causes accidents and injuries and what steps can be taken to prevent them. Furthermore, an effective solution for ensuring the safety of road users must be offered.

This study focuses on accident investigations along the Mumbai-Pune Expressway, which runs through the Pune District. The goal of this study is to identify the primary elements that influence the occurrence of accidents and to construct an accident prediction model utilizing Artificial Neural Networks (ANN)

This study focuses on accident investigations along the Mumbai-Pune Expressway, which runs through the Pune District. The goal of this study is to identify the primary elements that influence the occurrence of accidents and to construct an accident prediction model utilizing Artificial Neural Networks (ANN)

This image depicts the construction of a computer- generated neural network model for predicting traffic accidents. Data collection, decision-making, and data analysis or error-minimization are the fundamental activities of all neural networks, regardless of the kind of neural network used. These procedures ultimately have an impact on the trial's final results. In the relation by iterating on the wn.xn results in order to limit the chance of a mistake.

EXPERIMENTATION

The Mumbai–Pune Expressway (MPEW) is India's first 6-lane wide concrete toll road. It connects Mumbai, Maharashtra's capital, and Pune, the state's capital, across a distance of 94.5 kilometers. Pune, Maharashtra's cultural and educational hub, is India's financial capital. In the year 200, it was fully operationalized. There have been a lot of road accidents in MPEW because of human error and the high volume of traffic. The Highway Patrol has reported 872 collisions in the past three years. Out of which 232 were recorded as fatal accidents and 268 users were killed, 392 were seriously injured and 67 suffered minor injuries.

The expressway travels from Kalamboli in Navi Mumbai to Kiwale in Pune. In the Sahyadri mountain ranges, it meanders through a series of tunnels and overpasses. The five interchanges are Kon (Shedung), Chowk, Khalapur, Kusgaon, and Talegaon. A central median divides the two carriageways, each of which has three concrete lanes and a tarmac or concrete shoulder on each side of the divider.

Three-hour time intervals were plotted against the accident instances included in the contributing factors research (Figure 5). Nearly three-quarters of all accidents and nearly half of fatal accidents occur between the hours of zero to five o'clock.

Accidents that occur between the hours of 6:00 a.m. and 11:59 p.m. account for 31% of all accidents and 34% of fatal and severe ones. Between the hours of 00:00 and 09:00, 56 percent of all accidents occurred, including 54 percent of fatal ones. Figure 5 depicts the breakdown of the total number of accidents (including fatalities) according to the kind of accident. Listed below are the 10 accident categories that are utilised to categorise these incidents.

• Collision with another vehicle that is moving, stopping, or standing still..

• Collision with a vehicle approaching or waiting.

• Collision with another car travelling in the same direction from the side..

• Collision with another oncoming vehicle.

• Collision with a vehicle that enters or crosses a road..

• A car collides with a pedestrian..

• Collision with a carriageway obstruction.

• Leaving the carriageway to the right.

• Leaving the carriageway to the left.

4 percent of all accidents and 58 percent of fatal accidents are caused by collisions with another vehicle that is travelling ahead or waiting, and collisions with another vehicle that begins, stops, or is stationary at the same moment (Figure 6). The second most common form of collision is "run-off- road," which accounts for 28% of all collisions and 20% of deaths. Accidents between vehicles and pedestrians account for 7% of all fatalities and 14% of fatal collisions. Rear-end crashes, exiting the highway to the left or right, and pedestrian accidents are all examples of collisions with another vehicle that is driving forward, waiting, or halted. Alcohol is responsible for 90% of all accidents and 94% of fatal accidents.

Most road traffic accidents and fatalities are caused by a combination of circumstances. The injuries that resulted were thoroughly investigated and are detailed. Accidents and injuries are influenced by a variety of factors. The properties of contributing components are used to create a distribution. The Venn diagram depicts (Human/Vehicle/Infrastructure) for road traffic accidents. The combination of human and vehicle components (56%) resulted in this diagram. The influence of all variables (24 percent) on the occurrence of accidents and the subsequent injury

Human error, vehicle characteristics, and infrastructure/ environmental factors are the three key contributing factors in traditional accident analysis. It should be noted that when investigating an accident, it is important to try to identify all possible contributing variables (human, vehicle, and infrastructure) that may have contributed to the accident's occurrence, as any of these aspects might have an independent or combined effect. Despite human flaws, this type of study provides a broader viewpoint and can aid in the identification of vehicle and infrastructure-related solutions.

injuries might be caused by more than one factor, therefore the sum of percentage impacts will not match the number of human variables.

The following are the car variables that have been found to be responsible for causing accidents and injuries in the first place. One may see how many incidents occurred by looking at table 2. Each of the variables has an effect.

Factors that may have contributed to the accident are outlined below. The percentage of accidents impacted by each component is shown in the table below.

(2020)

8. CONCLUSION

The following are the important results based on the above discussions on road traffic accidents for the Mumbai-Pune Expressway:

• 56% of all accidents and 54% of fatal accidents occur between the hours of 00:00 and 09:00.

• More over 90% of all accidents and 94% of all deaths are caused by collisions with another vehicle that is either moving ahead of, waiting, or halted (rear-end collisions).

• All road users involved in crashes and 98% of those with at least one death are either trucks or other vehicles, including pedestrians.

• Car occupants were outside the vehicle in 4.58 percent of pedestrian accidents while the vehicle was parked, broken down, or being pushed to the side of the road.

• Factors that cause accidents, together with their severity in percentages

1. Develop an artificial neural network (ANN) model to predict construction projects performance in Syria Rana Maya, Bassam Hassan, Ammar Hassan, Journal of King Saud University – Engineering Sciences, 2 May 2021 2. Research and applications of artificial neural network in pavement engineering: A state-of- the-art review Xu Yang a, Jinchao Guan a, Ling Ding c, Zhanping You, Science Direct, 23 March 2021 3. Quantification and control of disruption propagation in multi-level public transport networks Menno Yap a, Oded Cats, Johanna TörnquistKrasemann, Niels van Oort, International Journal of Transportation Science and Technology, Elsevier 21st Feb

2021

4. AkmalMukhitdinov* , KamoliddinZiyaev, JanserikOmarov, and ShokhsanamIsmoilova ―Methodology of constructing driving cycles by the synthesis‖ Web of Conferences 264, 01033 (2021) 5. Research on car-following model based on molecular dynamics YanfengJia , Dayi Qu, Lewei Han, Lu Lin and Jiale Hong, 8 January 2021 6. Huaikun Xiang, Jiafeng Zhu, Guoyuan Liang and YingjunShen ―Prediction of Dangerous Driving Behavior Based on Vehicle Motion State and Passenger Feeling Using Cloud Model and Elman Neural Network‖, : Research Article, 29 April 2021 7. Eduard Pons, TomásGarcía-Calvo, Francesc Cos, Ricardo RestaEt.Al. ―Integrating video tracking and GPS to quantify accelerations and decelerations in elite soccer‖ Scientific Report 17 August

2021

8. Robert I. M. Delves, Robert J. Aughey, ―The Quantification of Acceleration Events in Elite Team Sport: a Systematic Review‖ Open Access2021 9. Cost Forecasting of Public Construction Projects Using Multilayer Perceptron Artificial Neural Networks: A Case Study, Alcineide Pessoa, Gean Sousa, Research Article, and DECEMBER - 2021 10. Determination of Efficacy of Traffic accidents Models for Projects using Artificial

International Research Journal of Engineering and Technology (IRJET), Oct 2021 11. An Artificial Neural Network Approach to Predicting Most Applicable Post-Contract Cost Controlling Techniques in Construction Projects TemitopeOmotayo, AwuzieBankole, Research Gate, 28 July 2020 12. Using ANN to Predict the Impact of Communication Factors on the Rework Cost in Construction Projects, Roman Trach, Yuliia Trach, Research Article, 20 July 2021 13. Optimization of structural elements in highly seismic areas using neural networks, V. Arana, M. Sanchez and P. Vidal2IOP Conference Series: Materials Science and Engineering2021 14. Predictive Statistical Cost Estimation Model for Existing Single Family Home Elevation Projects ArashTaghinezhad, Carol J. Friedland, Research Article, 07 June 2021 15. The Implementation Factors of Information and Communication Technology in the Life Cycle Costs of Buildings Peter Mésároš , TomášMandicák , Marcela Spišáková, Research Article, 25 March 2021 16. Using artificial neural networks to model bricklaying productivity OrsolyaBokor, Laura Florez-Perez, Giovanni Pesce, 2021 European Conference on Computing in Construction

2021

17. Estimation and prediction in construction projects: a systematic review on machine learning techniques Sanaz Tayefeh Hashemi, Omid Mahdi Ebadati, · Harleen Kaur, Springer Article 15 September 2020 18. Application of Artificial Intelligence for the Estimation of Concrete and Reinforcement Consumption in the Construction of Integral Bridges ZeljkaBeljkas, Milos Knezevic, SnezanaRutes and Nenad Ivanisevic, Research Article, 8th June 2020 19. Cost estimation and prediction in construction projects: a systematic review on machine learning techniques Sanaz Tayefeh Hashemi, · Omid Mahdi Ebadati, Springer Article, 6 September 2020 20. Evaluation of the Critical Success Factors (CSFs) in Selecting Building Contractors Using Pareto Analysis and the Analytical Hierarchy Process Khalid F. Al-Salahi, Khalid K. Naji and Murat Gunduz, Journal of Engg Research 25th June 2020 Sarode, Shubham E. Chandgude, International Journal of Innovative Research in Science, Engineering and Technology (IJIRSET), April

2020

22. Artificial Intelligence and Parametric Construction Cost Estimate Modeling: State-of- the-Art Review Haytham H. Elmousalam,

ASCE 2020

23. Improving the Results of the Earned Value Management Technique Using Artificial Neural Networks in Construction Projects AmirhosseinBalali, AlirezaValipour, Research Article, 21 October 2020 24. An artificial neural network approach for cost estimation of engineering services, Erik Matel, FaridaddinVahdatikhaki, SiavashHosseinyalamdary, This Evers & Hans Voordijk, International Journal of Construction Management, 29 Nov 2019 25. Cost estimation in road construction using artificial neural network KsenijaTijanic Diana Car-Pusic, MarijaSperac, Springer, 8 August

2019

26. Evaluation of Constructions using Artificial Neural Network (ANN), Sandhya W T, International Journal for Modern Trends in Science and Technology, 09-November-

2019

27. Construction Cost Estimation of Brazilian Highways Using Artificial Neural Networks Laís B. Barros, Marília Marcy and Michele T. M. Carvalho, International Journal of Structural and Civil Engineering Research Vol. 7, No. 3, August 2018 28. Estimation Model for I-Girder Bridge Superstructure Using Multiple Linear Regression and Artificial Neural Network, InasWinalytra, AriefSetiawan Budi Nugroho, Applied Mechanics and Materials2018 29. An artificial neural network (ANN) model proposal for cost minimization and cost estimation based on building dimensions for reinforced concrete duplex villa in preliminary design, Latif Onur UĞUR, 2017 30. Construction cost prediction using neural networks Smita K. Magdum and Amol C. Adamuthe, ICTACT Journal on soft computing, October 2017, 31. Artificial Neural Network for Assessment of Energy Consumption and Cost for Cross Laminated Timber Office Building in Severe Cold Regions Qi Dong, Kai Xing and 32. Md. Ebrahim Shaik, Md. Milon Islam, QuaziSazzad Hossain (2021) ―A review on neural network techniques for the prediction of road traffic accident severity‖ 33. Aanal Desai, Dr. L. B. Zala, Amit A. Amin (2021) ―Comparison of crash prediction models using MLR and ANN‖ RT&A volume 16. 34. Nivea John, Archana S (2019) ―Crash Prediction Modeling of Two Lane Undivided Highways Using Artificial Neural Network‖ International Journal of Scientific & Engineering Research, Volume 10 35. Ebrahim and Hossain Q. (2018) ―An Artificial Neural Network model for road accident prediction: A case study of Khulna metropolotan city‖ 4th International Conference on Civil Engineering for Sustainable Development (ISBN-978-984-34-3502-6). 36. Borja García de Soto, Markus Deublein, Andreas Bumbacher, Bryan T. Adey (2018) ―Predicting road traffic accidents using artificial neural network models‖ Infrastructure Asset Management Volume 5.

PG Student, Department of Civil Engineering, TSSM‘S Padmabhooshan Vasantdada Patil Institute Technology, Pune