Unsupervised Data Mining Algorithms Research Articles

Identifying roadway departure crash patterns on rural two-lane highways under different lighting conditions: Association knowledge using data mining approach

Introduction: More than half of all fatalities on U.S. highways occur due to roadway departure (RwD) each year. Previous research has explored various risk factors that contribute to RwD crashes, however, a comprehensive investigation considering the effect of lighting conditions has been insufficiently addressed. Data: Using the Louisiana Department of Transportation and Development crash database, fatal and injury RwD crashes occurring on rural two-lane (R2L) highways between 2008-2017 were analyzed based on daylight and dark (with and without streetlight). Method: This research employed a safe system approach to explore meaningful complex interactions among multidimensional crash risk factors. To accomplish this, an unsupervised data mining algorithm association rules mining (ARM) was utilized. Results and conclusions: Based on the generated rules, the findings reveal several interesting crash patterns in the daylight, dark-with-streetlight, and dark-no-streetlight, emphasizing the importance of investigating RwD crash patterns depending on the lighting conditions. In daylight condition, fatal RwD crashes are associated with cloudy weather conditions, distracted drivers, standing water on the roadway, no seat belt use, and construction zones. In dark lighting condition (with and without streetlight), the majority of the RwD crashes are associated with alcohol/drug involvement, young drivers (15–24 years), driver condition (e.g., inattentive, distracted, illness/fatigued/asleep), and colliding with animal(s). Practical Applications: The findings also reveal how certain driver behavior patterns are connected to RwD crashes, such as a strong association between alcohol/drug intoxication and no seat belt usage in the dark-no-streetlight condition. Based on the identified crash patterns and behavioral characteristics under different lighting conditions, the findings could aid researchers and safety specialists in developing the most effective RwD crash mitigation strategies.

Breast Cancer Detection using Decision Tree and K-Nearest Neighbour Classifiers

Data mining has the most important role in healthcare for discovering hidden relationships in big datasets, especially in breast cancer diagnostics, which is the most popular cause of death in the world. In this paper two algorithms are applied that are decision tree and K-Nearest Neighbour for diagnosing Breast Cancer Grad in order to reduce its risk on patients. In decision tree with feature selection, the Gini index gives an accuracy of %87.83, while with entropy, the feature selection gives an accuracy of %86.77. In both cases, Age appeared as the most effective parameter, particularly when Age<49.5. Whereas Ki67 appeared as a second effective parameter. Furthermore, K- Nearest Neighbor is based on the minimum error rate, and the test maximum accuracy for K_value selection with an accuracy of 86.24%. Where the distance metric has been assigned using the Euclidean approach. From previous models, it seems that Breast Cancer Grade2 is the most prevalent type. For the future perspective, a comparative study could be performed to compare the supervised and unsupervised data mining algorithms.

Unsupervised Data Mining and Effect of Fast Rehabilitation Nursing Intervention in Fracture Surgery.

At present, the most commonly used surgical treatment for fractures caused by external force injury is clinical, and unsupervised data mining is more advantageous in the face of the unknown format of perioperative network data. Therefore, this research aims to explore the application effect of unsupervised data mining in the concept of rapid rehabilitation nursing intervention after fracture surgery. 80 patients who underwent fracture surgery in the Department of Orthopedics of XXX Hospital were determined as the subjects, who were rolled into a research group (group R, 40 cases) and a control group (group C, 40 cases) by drawing lots. An unsupervised data mining algorithm based on unsupervised data mining for support vector machines (VDMSVMs) was proposed and applied to two groups of patients undergoing perioperative fracture surgery with the rapid rehabilitation nursing intervention and basic routine nursing. The results showed that the number of important features selected by the VDMSVM algorithm (5) was obviously more than that of the compressed edge fragment sampling (CEFS) algorithm (1) and the multicorrelation forward searching (MCFS) algorithm (2) (P < 0.05). The number of noise features screened by the VDMSVM algorithm (3) was much less in contrast to that of the CEFS algorithm and the MCFS algorithm, which was 8 and 10, respectively (P < 0.05). The Visual Analogue Scale (VAS) scores of the fracture site at the 4th, 8th, 12th, and 16th hour after surgery in group R were all lower than the scores in group C (P < 0.05). The length of hospital stay (LoHS) in group R was greatly shorter than that in group C (P < 0.05). After different nursing methods, the World Health Organization Quality of Life (WHOQOL-BREF) score of patients in group R (89.64 points) was greatly higher than the score in group C (61.45 points) (P < 0.05). The nursing satisfaction score of group R was 92.35 ± 3.65 points, and that in group C was 2.14 ± 1.25 points, respectively (P < 0.05). The test results verified the effectiveness of the feature selection of the VDMSVM algorithm. The rapid rehabilitation nursing intervention was conductive to reducing the postoperative pain of fracture patients, shortening the LoHS of patients, improving the quality of life (QOL) of fracture surgery patients, and increasing the patient's satisfaction with nursing.

Multi-element geochemical data mining: Implications for block boundaries and deposit distributions in South China

To explore the macroscopic characteristics of geological block boundaries, Mesozoic magmatic rocks, and various ore deposit distributions in South China, we processed large-scale stream sediment geochemical data covering the entire South China region. Two unsupervised data mining algorithms, cluster analysis and correlation analysis, were used to identify the geochemical distribution patterns. The combined geochemical patterns of nine major elements show two gradient lines that divide the South China region into three blocks. These gradient lines reveal the eastern and western boundaries of the intracontinental orogenic belts between the Yangtze and Cathaysia blocks. We suggest that the Nanning-Pingxiang segment is located on the southern end of the Yangtze-Cathaysia block boundary, and the Jishou-Kaili segment is a part of the boundary between the Yangtze block and the eastern orogenic belt. In the Mesozoic, the distribution of magmatic rocks migrated from the inland to the southeast coast. Meanwhile, the mantle-derived compatible elements were gradually depleted, whereas the crust-derived incompatible elements were gradually enriched. The migration and enrichment of geochemical elements provide material sources for the formation of various ore deposits. High-temperature metallogenic deposits related to Mesozoic magmatic activity are widely developed in eastern South China, while low-temperature metallogenic, sedimentary, and metamorphic deposits are more developed in inland South China. The regional geochemical patterns indicate the distributions of deposits to varying degrees.

Three-way unsupervised data mining for power system applications based on tensor decomposition

Sophisticated geospatial metering devices used in today's networks such as the advanced metering infrastructure (AMI), wide area measurement system (WAMS) and supervisory control and data acquisition (SCADA) open new opportunities to monitor the security of the system in real time. Consequently, these metering infrastructures have received significant attention in recent years from data mining communities because of the new challenges involved on managing this information. One of the main challenges is the analysis of multivariable data, which represents datasets containing variables of different nature, which are linked. In this document a data mining technique that allows the analysis of multivariate data is presented. Moreover, an innovative application of an unsupervised data mining algorithm for smart meters data, particularly to Electrical Load Profile using tensor decomposition is presented. Since the proposed tensor representation allows to assign a given dimension to a particular variable involved; data reduction, data compression, data visualization and data clustering is archived separately for every variable. To validate the effectiveness of the proposed methodology, a three-way tensor built with data from the Electrical Reliability Council of Texas (ERCOT) is presented. The results demonstrate that is possible to extract more information than using conventional approaches based on 2-way arrangements (matrices). Additionally, the proposed algorithm is solved using an iterative approach, which indirectly enable to estimate missing data.

Detecting medical prescriptions suspected of fraud using an unsupervised data mining algorithm.

Nowadays, health insurance companies face various types of fraud, like phantom billing, up-coding, and identity theft. Detecting such frauds is thus of vital importance to reduce and eliminate corresponding financial losses. We used an unsupervised data mining algorithm and implemented an outlier detection model to assist the experts in detecting medical prescriptions suspected of fraud. The implementation ran medicine code, patients’ sex, and patients’ age variables through three successive screening steps. The proposed model is capable of detecting 25% to 100% of cases violating the standards for some medicines that are not supposed to be prescribed at the same time in one single prescription. This model can also detect medical prescriptions suspected of fraud with a sensitivity of 62.16%, specificity of 55.11%, and accuracy of 57.2%. This paper shows that data mining can help detecting potential fraud cases in medical prescriptions more quickly and accurately than by the manual inspection as well as reducing the number of medical prescriptions to be checked which will result in reducing investigators heavy workload. The results of the proposed model can also help policymakers to plan for fighting against fraudulent activities. Graphical Detecting Medical Prescriptions Suspected of Fraud Using an Unsupervised Data Mining Algorithm

Mutual information-based correlation analysis of herbs against insomnia

This paper aims to analyze Professor Guo Rongjuan's medication experience on insomnia therapy based on the Traditional Chinese Medicine (TCM) Inheritance Support Plat. First, TCM formulae prescribed by Professor Guo for insomnia therapy were collected from the TCM Inheritance Support Plat. Next, unsupervised data mining algorithms, including apriori, modified mutual-information, and entropy clustering of complex system were applied to obtain the frequencies for different herbs and identify the association rules among the herbs. Accordingly, we can gain new insights into Professor Guo's medication experience on insomnia therapy. Based on analysis of 3 084 formulae, we determined the frequencies for herbs in the formulae and identified the association rules among these herbs. At last, 41 core combinations and 7 new formulae were obtained. The identified medication experience conform with Professor Guo's views on the etiology and pathogenesis of insomnia: "pathogenic fire derived from stagnation of liver-QI (Gan Yu Hua Huo)" is the core pathogenesis of insomnia; "liver stagnation and spleen deficiency" and "chronic illness transferred to kidney" are the main features for insomnia. The TCM Inheritance Support Plat is of great practical value for mining clinical experience of famous TCM doctors.

Monitoring Wind Turbine Vibration Based on SCADA Data

Three models for detecting abnormalities of wind turbine vibrations reflected in time domain are discussed. The models were derived from the supervisory control and data acquisition (SCADA) data collected at various wind turbines. The vibration of a wind turbine is characterized by two parameters, i.e., drivetrain and tower acceleration. An unsupervised data-mining algorithm, the k-means clustering algorithm, was applied to develop the first monitoring model. The other two monitoring models for detecting abnormal values of drivetrain and tower acceleration were developed by using the concept of a control chart. SCADA vibration data sampled at 10 s intervals reflects normal and faulty status of wind turbines. The performance of the three monitoring models for detecting abnormalities of wind turbines reflected in vibration data of time domain was validated with the SCADA industrial data.