Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.

Indexed Tree Sort: An Approach to Sort Huge Data with Improved Time Complexity

Abstract: Sorting has been found to be an integral part in many computer based systems and applications. Efficiency of sorting algorithms is a big issue to be considered. This paper presents the efficient use of Indexing with Binary Search Trees (BST) to model a new improved sorting technique, Indexed Tree (IT)-Sort, capable of working with huge data. Along with design and implementation details, major emphasis has been placed on complexity, to prove the effectiveness of new algorithm. Complexity comparison of IT-Sort with other available sorting algorithm has also been carried out to ascertain its competence in worst case also. In this paper, we describe the formatting guidelines for IJCA Journal Submission. Keywords Computing, Sorting Algorithm, Complexity, Huge Data Set, Binary Search Tree (BST), Indexing 1. INTRODUCTION There are number of traditional algorithms used to find ordering of unordered data sets. Each algorithm has its own pros and cons and a specific methodology to arrange the data like merging divide and conquer, partitioning, recursive methods etc [1, 2]. Different sorting algorithms are analyzed and compared according to their complexity [3, 6, and 7]. The analysis of algorithms is the area of computer science that provides tools for contrasting the efficiency of different methods of solution. Although the efficient use of both time and space is important, inexpensive memory has reduced the significance of space efficiency [4]. Thus, focus of researcher has been restricted to primarily on time efficiency only. Time complexity of an algorithm is a function of the size of the input to the problem and quantifies the amount of time taken by an algorithm to execute. Designing of suitable sorting algorithm as per application is a continuous process. Lots of work is being carried out in this field with single objective to reduce time complexity of proposed algorithm. Existences of large number of data values have significant impact on computational complexity of sorting. Since, sorting large datasets may slowdown the overall execution, schemes to speedup sorting operations are needed [8]. Sorting algorithms are classified according to computational complexity, number of swaps, stability, memory requirements, recursive nature, number of comparisons etc. Most of the times aalgorithms are analysed for best, worst and average cases according to size of input data. In most of the cases, all efforts are laid on improving the average case complexity. Present work is related, yet different from existing works on efficient practical algorithms for sorting. Proposed algorithm concentrate on reducing time complexity to a great extend if sorting is carried out with huge data sets even in worst case. In this paper, an attempt has been made to present improved approach for finding more efficient solution, requiring less execution time, of sorting using Indexing and BSTs. The rest of the paper is organized as follows. Next section describes the methodology followed in designing IT-Sort. Main emphasis in section 3 has been placed on presenting the design and implementation details of new algorithm. Section 4 supports the whole discussion with experimental results to prove the effectiveness of proposed algorithm and finally section 5 concludes the paper with future enhancements.

Sequential Regression Trees for Learning and Design

Abstract: Dynamic regression trees are an attractive option for automatic regression and classification with complicated response surfaces in on-line application settings. We create a sequential tree model whose state changes in time with the accumulation of new data, and provide particle learning algorithms that allow for the efficient on-line posterior filtering of tree-states. A major advantage of tree regression is that it allows for the use of very simple models within each partition. The model also facilitates a natural division of labor in our sequential particle-based inference: tree dynamics are defined through a few potential changes that are local to each newly arrived observation, while global uncertainty is captured by the ensemble of particles. We consider both constant and linear mean functions at the tree leaves, along with multinomial leaves for classification problems, and propose default prior specifications that allow for prediction to be integrated over all model parameters conditional on a given tree. Inference is illustrated in some standard nonparametric regression examples, as well as in the setting of sequential experiment design, including both active learning and optimization applications, and in on-line classification. We detail implementation guidelines and problem specific methodology for each of these motivating applications. Throughout, it is demonstrated that our practical approach is able to provide better results compared to commonly used methods at a fraction of the cost.

Mobile Intelligent Interruption Management: A New Context-Aware Fuzzy Mining Approach

Abstract: In recent days, phones recognized as more significant personal communication device for daily life. Usually, ringing notifications are utilized in notifying users on incoming calls. Notifications of inappropriate incoming calls occasionally cause interruptions for users and surrounding people. These unwanted interruptions have a disruptive effect on productivity, employee concentration, and error rate for tasks. A diversity of recommendation approaches for context-aware (e.g., data mining, decision tree, statistics, besides the soft computing) for limiting mobile phone interruptions was presented. However, a mutual problem for current techniques to minimize the interruptions of the mobile phone isn’t sufficiently coping with noisy or inconsistency instances that may minimize prediction accuracy. Hence, we are motivated to implement an integrated approach depends upon Bays classifier that classifies noisy cases from training the dataset, and fuzzy logic to manage the nebulizer in mobile phone context situations. The integration methodology implemented through feature-in-decision-out level fusion. In these regards, current work thong to extend a commonly utilized context-based data mining approaches that take out individuals unwavering temporal patterns to fuzzy data mining which might recognize social practices patterns, that might change after some time by supporting reinforcement learning. Simulation and evaluation results on real-life datasets cell phone reveal the efficiency of the suggested model. It achieves an improvement of 5%, 7% and 9% for precision, recall, and f-measure respectively contrasted with traditional systems which include decision tree model and Apriori model.

Comparing Preference Models in Recommender Systems

Abstract: How to represent the users' preference is one of the principle problems in widely used recommender systems. To address this problem, in this paper, the expressibility, space complexity and learning complexity of different kinds of preference models are investigated. The recommendation performances of these models are also compared on a real-life dataset. Considering both the expressibility and computational complexity, the quadric model is the most suited to recommender systems.

An Applied Research of Decision Tree Algorithm in Track and Field Equipment Training

Abstract: This paper has conducted a study on the applications of track and field equipment training based on ID3 algorithm of decision tree model. For the selection of the elements used by decision tree, this paper can be divided into track training equipment, field events training equipment and auxiliary training equipment ac- cording to the properties of track and field equipment. The decision tree that regards track training equipment as root nodes has been obtained under the conditions of lowering computation cost through the selection of data as well as the application and optimization of ID3 algorithm model.