A road accident pattern miner (RAP miner)

This study presents the distribution of road accidents in Bangkok, Thailand, during the COVID-19 outbreak (162 days) using spatial statistics. The findings show that the number of road accidents fell by 28.53% during the lockdown period (March 26 to June 14, 2020) compared to before the lockdown period (January 5 to March 25, 2020). There was also a considerable decrease in road accidents by approximately 4.96% compared to the same period in 2019 (January 4 to June 14, 2019). High accident incidence areas were located in central and southwestern Bangkok, and this pattern was also observed before and during the lockdown as well as in 2019. The findings revealed the numbers and patterns of road accidents that occurred during the COVID-19 outbreak. This information can be useful in minimizing and limiting the impact and damage caused by road accidents in Bangkok.

Identifying Similarities and Dissimilarities Among Road Accident Patterns

Case-Based Reasoning (CBR) is amply used as a method to solve problems in many domains. It involves retrieval and use of past cases to solve a new one. However, using past cases to solve a new one by this methodology is weighing a great deal. In this paper, we present our approach for reducing the search space solution through association rules and focus only interesting cases that meet only these rules. The reduced search space is then used by CBR to compute a solution for the new problem. Through this work, we aim to propose an approach that combines Association Rules and CBR to improve searching solution for similar cases. Thereafter, we test our approach by using real-life datasets.

One of the major challenges in the content-based information retrieval and machine learning techniques is to-build-the-so-called "semantic classifier" which is able to effectively and efficiently classify semantic concepts in a large database. This paper dealt with semantic image classification based on hierarchical Fuzzy Association Rules (FARs) mining in the image database. Intuitively, an association rule is a unique and significant combination of image features and a semantic concept, which determines the degree of correlation between features and concept. The main idea behind this approach is that any image visual concept has some associated features, so that, there are strong correlations between the concepts and their corresponding features. Regardless of the semantic gap, an image concept appears when the corresponding features emerge in an image and vice versa. Specially, this paper's contribution was to propose a novel Fuzzy Association Rule for improving traditional association rules. Moreover, it was concerned with establishing a hierarchical fuzzy rule base in the training phase and setup corresponding fuzzy inference engine in order to classify images in the testing phase. The presented approach was independent from image segmentation and can be applied on multi-label images. Experimental results on a database of 6000 general-purpose images demonstrated the superiority of the proposed algorithm.

A review on neural network techniques for the prediction of road traffic accident severity

Traditional basic oxygen furnace (BOF) prediction based on Case-based reasoning (CBR) is usually dependent on experts and experiences which will result in deviation. Aiming at attributes selection in BOF steelmaking and case base maintenance, this paper proposes using Ridge regression and Association rules to improve CBR and predicting the endpoint carbon content of BOF steelmaking. In CBR, case representation is the basic, the selected attributes in case representation play an important role but dependent on expert experiences so that this paper uses lasso regression algorithm to get the attributes. Through the simulation experiment, the results show that the improved CBR can obviously improve the accuracy of endpoint carbon content prediction.

A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance

Road accidents are still a prominent urban issue, worsened by a growing population and uncertain weather patterns. Conventional accident prediction models use static historical data, which does not enable them to be responsive to real-time traffic patterns. This research is responding to the demand for predictive models that are adaptive, smart, and can facilitate smart city infrastructure through real-time data integration. Machine learning models—Multilayer Perceptron, Gradient Boosting, Random Forest, Support Vector Machine, and K-Nearest Neighbors—were tested with both historical and real-time traffic data. The models were optimized and trained on varied datasets to improve prediction accuracy. Of these, Gradient Boosting recorded the highest accuracy at 88.1%, followed by Random Forest at 83.73%, showing the power of ensemble learning techniques in predicting accidents. This research emphasizes the significance of real-time data integration for accident prediction and prevention. Merging environmental elements like weather conditions and traffic congestion improves prediction quality, allowing proactive prevention of accidents. By leveraging these models, cities can shift towards data-based road management, infrastructure planning, and congestion control. The results show that real-time models of accident prediction have the potential to enhance urban safety, opening the door to smarter and more efficient traffic management systems.

The rapid development of AI shows its power and great development potential in practical engineering applications. Critical issues and potential solutions can reduce road traffic accidents and application of AI in road accident prediction. The published use of AI for road accident prediction is reviewed, presented, and represented as the main objective. The methods are collecting article data, quotations, presentation, and representation. The article data collection was obtained from 671 conference and journal articles in 2019-2023, but the suitability of articles that can be used is 69. Quotation produces a grouping of approaches, models, predictions, and benefits. The presentation showed that most approaches used were machine learning, the most used model was random forest, the prediction was mostly about severity, and the most benefit was about number reduction. Representation produces road accidents and related factors into factors in road accident predictions using artificial intelligence, so strategies and anticipation can be made to overcome them to improve road safety. AI in road accident prediction plays an important role in building predictive models with the hope that road accidents can be identified early, risk factors can be reduced, and effective preventive measures can be taken to improve road safety.

Predicting the development cost of TFT-LCD manufacturing equipment with artificial intelligence models

This paper proposes the design of Vehicular Cyber-Physical Systems (called VCPS) for smart road services in vehicular networks. Our VCPS realizes mobile cloud computing services where vehicles themselves or mobile devices (e.g., smartphones and tablets of drivers or passengers in vehicles) play a role of both cloud server and cloud client. First, this paper describes the architecture of vehicular networks for VCPS and the delay modeling for the interactive navigation and accident prediction, such as a mobile node's travel delay along its navigation path in vehicular networks. Second, the paper explains two VCPS applications as smart road services through the vehicular cloud, such as (i) interactive navigation service for the efficient driving and (ii) pedestrian protection service against road accidents.

Today, one of the top concerns for governments is road safety. There are many safety features built into cars, yet traffic accidents still happen frequently and are unavoidable. To lessen the harm caused by traffic accidents, predicting their causes has become the primary goal. In this situation, it will be beneficial to examine the frequency of accidents so that we can use this information to further aid us in developing strategies to lessen them. From this, we can deduce the connections between traffic accidents, road conditions, and the impact of environmental factors on accident occurrence. In order to construct an accident prediction model, I used machine learning techniques, including the Decision Tree, Random Forest, and Logistic Regression. The development of safety measures and accident prediction will both benefit from these classification systems. Several elements, including weather, vehicle condition, road surface condition, and light condition, can be used to predict road accidents. Three dataset files—accidents, casualties, and vehicles are loaded into this dataset. This allows us to forecast the severity of accidents.

Matching with the growth of the nations, the road surface transportation for each country has increased to it maximum capacity. The increased traffics have left a very little space for the maintenance of the roads and keeping the roads up to the mark for handling these higher volumes of traffic. Moreover, the traditional method for road maintenance is manual and it is highly time consuming. Due to this fact, many of the developed and underdeveloped nations are facing the problem of under maintained roads, which again leads to the road accidents. The accidents in the roads not only reduce the effectiveness of the country to match the growth of the industrial development but also cause the threat to the human life, which is highly unacceptable. Thus, the demand for the accident prediction automation is the need of the current research. Many of the parallel research outcomes have aimed to solve this problem by analysing the road traffic volume. However, many of the researchers, which again is cited further in this work, have proven that the accidents on the road surface are caused by the road conditions, rather by the traffic volume. Henceforth, this work proposes a novel framework for demonstrating the use of ICT enabled methods for predicting the accident-prone zones by analysing the road conditions. This work demonstrates nearly 90% accuracy for noise reduction, nearly 98% accuracy for road surface defect detection and nearly 98% accuracy for predicting the accident-prone zones for making the road surface transportation a much safer option.

Speed is one of the primary wellsprings of vehicle disasters. Many lives could have been saved on the off chance that emergency organizations had gotten the setback information and contacted them on time. This venture manages a mishap recognition framework. In case of a mishap, it involves different parts to call heroes for help. Effective programmed mishap identification with programmed warning of salvage administrations with data about the area of the mishap is a central prerequisite to saving significant living souls. The proposed framework manages mishap cautioning and recognition. Peruse the specific scope and longitude of the mishap vehicle and send this data to the closest crisis administrations. The motivation behind this undertaking is to perceive mishaps and ready salvage administrations on time. As of late the vast majority of the mishap happen because of laziness of drivers in vehicles and trucks. Yearly 1200 passings and 76000 harmed. This methodology incorporates examination of police detailed accident information, top to bottom nearby examinations promptly following an accident of the general driving populace. The present examination was intended to give additional data to traffic wellbeing and others could use in their endeavors to decrease the quantity of sleepy related accidents. than anywhere else in the world, including the more populous China. Calling road fatalities an "epidemic" that will become the world's fifth biggest killer by 2030, the report said while rich nations had been able to lower their death rates, these were sharply on the rise in the third world. It said 90% of deaths on the world's roads occur in low and middle-income countries (21.5 and 19.5 per lakh of population, respectively) though they have just 48% of all registered vehicles. The statistics for India are chilling. At least 13 people die every hour in road accidents in the country, the latest report of the National Crime Records Bureau reveals. However, road safety experts say the real numbers could be higher since many of these accident cases are not even reported. "There is no estimate of how many injured in road accidents die a few hours or days after the accident," points out RohitBaluja, member of the UN Road Safety Collaboration and Commission of Global Road Safety representing Asia. Based on the records, India will become the world number 1 in Road Deaths due to the poor record of average 13 die every hour, which is 1.14 lakh per year. This will make India to be the first place. This causative information about the accidents is the intent to develop the proposed technology as scientific traffic engineering wings to reduce the fatalities due to accidents. This proposed methodology is the automatic system which will provide the solution for identifying the accident location. Nowadays accidents are increasing at an alarming rate. Speed is the cause of most number of traffic accidents. In this project, we first applied Eclat algorithm Keywords— Eclat algorithm, clustering, classification,GPS to group the crime locations into 0 level, 1 level, 2 level accident tracking, Accident.

Case-based reasoning (CBR) is a method for solving new problem similar with it using the past solving problem experience. A case can be seen as a complex object that contains at least a problem description and a solution (i.e., a conditionally and a consequence). Between the conditionality and its consequence a strong association is existed. The focus of this paper is to describe a method discovering usable rules among case history by using the generalized association rule algorithm. Emphasis placed on approaching association rule mining for discovering rules existing in case history.