Navigation safety control system development through navigator action prediction by data mining means

Taking into account current trends in the development of ergatic maritime transport systems, the factors of the navigator’s influence on vessel control processes were determined. Within the framework of the research hypothesis, to improve navigation safety, it is necessary to apply predictive data mining models and automated vessel control. The paper proposes a diagram of the ergatic vessel control system and a model for identifying the influence of the navigator “human factor” during navigation. Within the framework of the model based on the principles of navigator decision trees, prediction by data mining means is applied, taking into account the identifiers of the occurrence of a critical situation. Based on the prediction results, a method for optimal vessel control in critical situations was developed, which is triggered at the nodes of the navigator decision tree, which reduces the likelihood of a critical impact on vessel control. The proposed approaches were tested in the research laboratory “Development of decision support systems, ergatic and automated vessel control systems”. The use of the Navi Trainer 5,000 navigation simulator (Wärtsilä Corporation, Finland) and simulation of the navigation safety control system for critical situations have confirmed its effectiveness. As a result of testing, it was determined that the activation of the system allowed reducing the likelihood of critical situations by 18–54 %. In 11 % of cases, the system switched the vessel control processes to automatic mode and, as a result, reduced the risk of emergencies. The use of automated data mining tools made it possible to neutralize the negative influence of the “human factor” of the navigator and to reduce the average maneuvering time during vessel navigation to 23 %

Decision Support System for Diabetes Classification Using Data Mining Techniques

The use of data mining algorithms in health information systems has played a significant role in developing applications that help to diagnose different diseases. The type of the disease determines the selection of the algorithm, parameters to be used, and dataset pre-processing steps, etc. In this chapter, diagnosing diabetes mellitus is the target since it has gained significant attention in the last few decades due to the increased severity of the disease. Four predictive data mining approaches are being used in diagnosing diabetes. Four models were implemented to diagnose diabetes from PIMA dataset: k-nearest neighbor, support vector machine, multilayer perceptron neural network, and naive Bayesian network. Giving the highest classification accuracy, support vector machine technique outperformed the others with a value of 78.83%.

Predictive Data Mining Model for Electronic Customer Relationship Management Intelligence

The rising adoption of e-CRM strategies in marketing and customer relationship management has necessitated to more needs especially where a specific customer segment is targeted and the services are personalized. This paper presents a distributed data mining model using access-control architecture in a bid to realize the needs for an online CRM that intends to deliver web content to a specific group of customers. This hybrid model utilizes the integration of the mobile agent and client server technologies that could easily be updated from the already existing web platforms. The model allows the management team to derive insights from the operations of the system since it focuses on e-personalization and web intelligence hence presenting a better approach for decision support among organizations. To achieve this, a software approach made of access-control functions, data mining algorithms, customer-profiling capability, dynamic web page creation, and a rule-based system is utilized.

The Use of Machine Learning Approaches for the Diagnosis of Acute Appendicitis

Acute appendicitis is one of the most common emergency diseases in general surgery clinics. It is more common, especially between the ages of 10 and 30 years. Additionally, approximately 7% of the entire population is diagnosed with acute appendicitis at some time in their lives and requires surgery. The study aims to develop an easy, fast, and accurate estimation method for early acute appendicitis diagnosis using machine learning algorithms. Retrospective clinical records were analyzed with predictive data mining models. The predictive success of the models obtained by various machine learning algorithms was compared. A total of 595 clinical records were used in the study, including 348 males (58.49%) and 247 females (41.51%). It was found that the gradient boosted trees algorithm achieves the best success with an accurate prediction success of 95.31%. In this study, an estimation method based on machine learning was developed to identify individuals with acute appendicitis. It is thought that this method will benefit patients with signs of appendicitis, especially in emergency departments in hospitals.

Educational Data Mining in Practice Literature Review

Educational Data Mining (EDM) is an evolving field with a suite of computational and psychological methods for understanding how students learn. Applying Data Mining methods to education data help us to resolve educational investigation issues. The growth of education data offers some unique advantages as well as some new challenges for education study. Some of the challenges are an improvement of student models, identify domain structure model, pedagogical support and extend educational theories. The main objective of this paper is to present the capabilities of data mining in the context of the higher educational system and their applications and progress, through a survey of literature and the classification of articles. We observed the works on investigational situation studies showed in the EDM during the recent past, in addition, we have introduced three data models based on descriptive and predictive data mining techniques. This is oriented towards students in order to recommend learners’ activities, resources, suggest path pruning and shortening or simply links that would favor and improve their learning or to educators in order to get more objective feedback for instruction.

Predictive Data Mining Techniques for Fault Diagnosis of Electric Equipment: A Review

Data mining is a technological and scientific field that, over the years, has been gaining more importance in many areas, attracting scientists, developers, and researchers around the world. The reason for this enthusiasm derives from the remarkable benefits of its usefulness, such as the exploitation of large databases and the use of the information extracted from them in an intelligent way through the analysis and discovery of knowledge. This document provides a review of the predictive data mining techniques used for the diagnosis and detection of faults in electric equipment, which constitutes the pillar of any industrialized country. Starting from the year 2000 to the present, a revision of the methods used in the tasks of classification and regression for the diagnosis of electric equipment is carried out. Current research on data mining techniques is also listed and discussed according to the results obtained by different authors.

Integrative discovery of treatments for high-risk neuroblastoma

Despite advances in the molecular exploration of paediatric cancers, approximately 50% of children with high-risk neuroblastoma lack effective treatment. To identify therapeutic options for this group of high-risk patients, we combine predictive data mining with experimental evaluation in patient-derived xenograft cells. Our proposed algorithm, TargetTranslator, integrates data from tumour biobanks, pharmacological databases, and cellular networks to predict how targeted interventions affect mRNA signatures associated with high patient risk or disease processes. We find more than 80 targets to be associated with neuroblastoma risk and differentiation signatures. Selected targets are evaluated in cell lines derived from high-risk patients to demonstrate reversal of risk signatures and malignant phenotypes. Using neuroblastoma xenograft models, we establish CNR2 and MAPK8 as promising candidates for the treatment of high-risk neuroblastoma. We expect that our method, available as a public tool (targettranslator.org), will enhance and expedite the discovery of risk-associated targets for paediatric and adult cancers.