Using data mining to improve traffic safety programs

Solomon, Scott; Nguyen, Hang; Liebowìtz, Jay; Agresti, William W.

doi:10.1108/02635570610666412

Cited by 27 publications

(25 citation statements)

References 21 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the average of specificity of the same trial recorded better results (99.4%) than case (2) which indicates that the proposed model performance improved by MDD. And an ROC value result is (0.996) which indicates that the classifier with MDD is performed well with sharp increase of CCR (97.597%).…”

Section: Resultsmentioning

confidence: 82%

“…(2) All narrators in Isnad were renowned for their accuracy (3)There is no interrupting in the Isnad (4)There is no irregular statement in the Hadith Maten (5)There is no defective in the Hadith Maten. Therefore, the experiment corpus consistes of five basic features (link, defective, irregular, grade of reliability, grade of preservation).…”

Section: A Hadith Databasementioning

confidence: 99%

“…In addition, data mining techniques enable knowledge to be extracted from data in statistical models to see how variables relate to each other and to better understand the underlying phenomena among them. Data mining methods include neural networks [2], decision trees (DT) [3], cluster analysis, market basket analysis, and regression analysis, among others.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving knowledge extraction of Hadith classifier using decision tree algorithm

Aldhaln

Zeki

Alreshidi

2012

2012 International Conference on Information Retrieval &Amp; Knowledge Management

View full text Add to dashboard Cite

Abstract-Decision tree algorithms have the ability to dealwith missing values. While this ability is considered to be advantage, the extreme effort which is required to achieve it is considered a drawback. With the missing values the correct branch could be missed. Therefore, enhanced mechanisms must be employed to handle these values. Moreover, ignoring these null values may cause critical decision to user. Especially for the cases that belong to religion. The present study proposed Hadith classifier which is a method to classify such Hadith into four major classes Sahih, Hasan, Da'ef and Maudo' according to the status of its Isnad ( narrators chain ). This research provided a novel mechanism to deal with missing data in Hadith database. The experiment applied C4.5 algorithm to extract the rules of classification. The findings showed that the accurate rate of the naï vebyes classifier has been improved by the proposed approach with 46.54%. Meanwhile, DT classifier had achieved 0.9% better than naï vebyes classifier.

show abstract

Section: Resultsmentioning

confidence: 82%

Section: A Hadith Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving knowledge extraction of Hadith classifier using decision tree algorithm

Aldhaln

Zeki

Alreshidi

2012

2012 International Conference on Information Retrieval &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…DM has become a widely used tool in a number of fields, including business, finance [2], security [3], medicine [4] and human science. DM methods include neural networks [5], decision trees (DT) [6], cluster analysis, market basket analysis, and regression analysis, among others.…”

Section: Introductionmentioning

confidence: 99%

Novel Mechanism to Improve Hadith Classifier Performance

Al‐Dhlan

Zeki

et al. 2012

2012 International Conference on Advanced Computer Science Applications and Technologies (ACSAT)

View full text Add to dashboard Cite

Abstract-Muslims believe that the Sunnah of the ProphetMuhammad (SAAW) is the second of the two revealed fundamental sources of Islam, after the Holy Qur'an. Hadith provides a Gold Standard "ground truth" for Artificial Intelligent (AI) knowledge extraction and knowledge representation experiments. In the present study, the extracted Islamic knowledge represented the focal point of the research; three famous books in Hadith science framed the corpus of the study. This study attempted to explore new approach to classify Hadith using a combination of the expert system and data mining techniques to classify Hadith according to its validity degree (Sahih, Hasan, Da'eef and Maudo'), the proposed Hadith Classifier model was built through learning process, Decision Tree (DT) classifier modeling had been represented by the tree structure model, and the attributes of the instances originally were obtained from the source books. Whilst some attributes were indicated as null values, or missing values. A novel mechanism called missing data detector (MDD) was employed to handle these missing data. This mechanism simulated the Isnad verification methods in Hadith science. The results of the research were compared with the resource books, concurrently with the point of view of the experts in the Hadith science. The findings of the research showed that the performance of DT Hadith classifier had significant effect with MDD, the CCR was sharply increased from (50.1502 %) to (97.597%) Furthermore, the favorable obtained results indicated that the DT Modeling is a viable approach to classify Hadith due to the ease of rules induction and results interpretation.

show abstract

“…There are a few studies where data mining has been used for local municipalities [15,16]. This study addresses this lack by applying a novel approach to large datasets collected by a local municipality to investigate citizens' tax payment behaviors.…”

Section: Introductionmentioning

confidence: 99%

DTreeSim: A new approach to compute decision tree similarity using re-mining

Bakırlı¹,

Birant²

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

A number of recent studies have used a decision tree approach as a data mining technique; some of them needed to evaluate the similarity of decision trees to compare the knowledge reflected in different trees or datasets. There have been multiple perspectives and multiple calculation techniques to measure the similarity of two decision trees, such as using a simple formula or an entropy measure. The main objective of this study is to compute the similarity of decision trees using data mining techniques. This study proposes DTreeSim, a new approach that applies multiple data mining techniques (classification, sequential pattern mining, and k-nearest neighbors) sequentially to identify similarities among decision trees. After the construction of decision trees from different data marts using a classification algorithm, sequential pattern mining was applied to the decision trees to obtain rules, and then the k-nearest neighbor algorithm was performed on these rules to compute similarities using two novel measures: general similarity and pieced similarity.Our experimental studies compared the results of these novel similarity measures and also compared our approach with existing approaches. Our comparisons indicate that our proposed approach performs better than existing approaches, because it takes into account the values of the branches in the trees through sequential pattern mining.

show abstract

Using data mining to improve traffic safety programs

Cited by 27 publications

References 21 publications

Improving knowledge extraction of Hadith classifier using decision tree algorithm

Improving knowledge extraction of Hadith classifier using decision tree algorithm

Novel Mechanism to Improve Hadith Classifier Performance

DTreeSim: A new approach to compute decision tree similarity using re-mining

Contact Info

Product

Resources

About