scholarly journals Ensemble probability distribution for novelty detection

2018 ◽  
Vol 189 ◽  
pp. 03008
Author(s):  
Xiaoshuang Qiao ◽  
Hui Wang ◽  
Gongde Guo ◽  
Yuanyuan Liu
Keyword(s):  
Probability Distribution ◽  
Real World ◽  
Mixed Models ◽  
Novelty Detection ◽  
The Other ◽  
Support Vector ◽  
Ensemble Approach ◽  
Overall Performance ◽  
Real World Datasets ◽  
Domain Description

This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches - Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.

scholarly journals Dimension Reduction for Objects Composed of Vector Sets

2017 ◽  
Vol 27 (1) ◽  
pp. 169-180 ◽  
Author(s):  
Marton Szemenyei ◽  
Ferenc Vajda
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Feature Selection ◽  
Discriminant Analysis ◽  
Probability Distribution ◽  
Dimension Reduction ◽  
Pose Estimation ◽  
Real World ◽  
Single Object ◽  
Real World Datasets

Abstract Dimension reduction and feature selection are fundamental tools for machine learning and data mining. Most existing methods, however, assume that objects are represented by a single vectorial descriptor. In reality, some description methods assign unordered sets or graphs of vectors to a single object, where each vector is assumed to have the same number of dimensions, but is drawn from a different probability distribution. Moreover, some applications (such as pose estimation) may require the recognition of individual vectors (nodes) of an object. In such cases it is essential that the nodes within a single object remain distinguishable after dimension reduction. In this paper we propose new discriminant analysis methods that are able to satisfy two criteria at the same time: separating between classes and between the nodes of an object instance. We analyze and evaluate our methods on several different synthetic and real-world datasets.

scholarly journals Extracting Entity Synonymous Relations via Context-Aware Permutation Invariance

2022 ◽  
Vol 17 (1) ◽  
pp. 1-17
Author(s):  
Nan Yan ◽  
Subin Huang ◽  
Chao Kong
Keyword(s):  
Real World ◽  
Relation Extraction ◽  
The Other ◽  
Context Aware ◽  
Important Work ◽  
Relational Context ◽  
Permutation Invariance ◽  
Level Statistics ◽  
Real World Datasets ◽  
Better Than

Discovering entity synonymous relations is an important work for many entity-based applications. Existing entity synonymous relation extraction approaches are mainly based on lexical patterns or distributional corpus-level statistics, ignoring the context semantics between entities. For example, the contexts around ''apple'' determine whether ''apple'' is a kind of fruit or Apple Inc. In this paper, an entity synonymous relation extraction approach is proposed using context-aware permutation invariance. Specifically, a triplet network is used to obtain the permutation invariance between the entities to learn whether two given entities possess synonymous relation. To track more synonymous features, the relational context semantics and entity representations are integrated into the triplet network, which can improve the performance of extracting entity synonymous relations. The proposed approach is implemented on three real-world datasets. Experimental results demonstrate that the approach performs better than the other compared approaches on entity synonymous relation extraction task.

Default Probability Prediction of Credit Applicants Using a New Fuzzy KNN Method with Optimal Weights

2015 ◽  
pp. 429-465
Author(s):  
Abbas Keramati ◽  
Niloofar Yousefi ◽  
Amin Omidvar
Keyword(s):  
Real World ◽  
Nearest Neighbor ◽  
Predictive Accuracy ◽  
Credit Scoring ◽  
Default Probability ◽  
The Other ◽  
K Nearest Neighbor ◽  
Optimal Weights ◽  
Probability Prediction ◽  
Real World Datasets

Credit scoring has become a very important issue due to the recent growth of the credit industry. As the first objective, this chapter provides an academic database of literature between and proposes a classification scheme to classify the articles. The second objective of this chapter is to suggest the employing of the Optimally Weighted Fuzzy K-Nearest Neighbor (OWFKNN) algorithm for credit scoring. To show the performance of this method, two real world datasets from UCI database are used. In classification task, the empirical results demonstrate that the OWFKNN outperforms the conventional KNN and fuzzy KNN methods and also other methods. In the predictive accuracy of probability of default, the OWFKNN also show the best performance among the other methods. The results in this chapter suggest that the OWFKNN approach is mostly effective in estimating default probabilities and is a promising method to the fields of classification.

Analyzing mixed-type data by using word embedding for handling categorical features

2021 ◽  
Vol 25 (6) ◽  
pp. 1349-1368
Author(s):  
Chung-Chian Hsu ◽  
Wei-Cyun Tsao ◽  
Arthur Chang ◽  
Chuan-Yu Chang
Keyword(s):  
Real World ◽  
Mixed Type ◽  
Transformation Method ◽  
The Other ◽  
Data Analyses ◽  
Categorical Attributes ◽  
Real World Datasets ◽  
Type Data ◽  
Numeric Representation ◽  
Degree Of Similarity

Most of real-world datasets are of mixed type including both numeric and categorical attributes. Unlike numbers, operations on categorical values are limited, and the degree of similarity between distinct values cannot be measured directly. In order to properly analyze mixed-type data, dedicated methods to handle categorical values in the datasets are needed. The limitation of most existing methods is lack of appropriate numeric representations of categorical values. Consequently, some of analysis algorithms cannot be applied. In this paper, we address this deficiency by transforming categorical values to their numeric representation so as to facilitate various analyses of mixed-type data. In particular, the proposed transformation method preserves semantics of categorical values with respect to the other values in the dataset, resulting in better performance on data analyses including classification and clustering. The proposed method is verified and compared with other methods on extensive real-world datasets.

scholarly journals Simandro-plus: On computing similarity of android applications

2021 ◽  
pp. 36-36
Author(s):  
Masoud Hamedani ◽  
Sang-Wook Kim
Keyword(s):  
Real World ◽  
State Of The Art ◽  
Similarity Score ◽  
The State ◽  
The Other ◽  
Android Applications ◽  
Similarity Computation ◽  
Real World Datasets

In this paper, we propose SimAndro-Plus as an improved variant of the state-of-the-art method, SimAndro, to compute the similarity of Android applications (apps) regarding their functionalities. SimAndro-Plus has two major differences with SimAndro: 1) it exploits two beneficial features to similarity computation, which are totally disregarded by SimAndro; 2) to compute the similarity score of an app-pair based on strings and package name features, SimAndro-Plus considers not only those terms co-appearing in both apps but also considers those terms appearing in one app while missing in the other one. The results of our extensive ex periments with three real-world datasets and a dataset constructed by human experts demonstrate that 1) each of the two aforementioned differences is really effective to achieve better accuracy and 2) SimAndro-Plus outperforms SimAndro in similarity computation by 14% in average.

scholarly journals Modeling Contemporaneous Basket Sequences with Twin Networks for Next-Item Recommendation

2018 ◽  
Author(s):  
Duc-Trong Le ◽  
Hady W. Lauw ◽  
Yuan Fang
Keyword(s):  
Real World ◽  
Sequence Type ◽  
The Other ◽  
Target Sequence ◽  
Network Structures ◽  
Time Step ◽  
Real World Datasets ◽  
Siamese Networks ◽  
Sequence Types

Our interactions with an application frequently leave a heterogeneous and contemporaneous trail of actions and adoptions (e.g., clicks, bookmarks, purchases). Given a sequence of a particular type (e.g., purchases)-- referred to as the target sequence, we seek to predict the next item expected to appear beyond this sequence. This task is known as next-item recommendation. We hypothesize two means for improvement. First, within each time step, a user may interact with multiple items (a basket), with potential latent associations among them. Second, predicting the next item in the target sequence may be helped by also learning from another supporting sequence (e.g., clicks). We develop three twin network structures modeling the generation of both target and support basket sequences. One based on "Siamese networks" facilitates full sharing of parameters between the two sequence types. The other two based on "fraternal networks" facilitate partial sharing of parameters. Experiments on real-world datasets show significant improvements upon baselines relying on one sequence type.

Default Probability Prediction of Credit Applicants Using a New Fuzzy KNN Method With Optimal Weights

2018 ◽  
pp. 1838-1874
Author(s):  
Abbas Keramati ◽  
Niloofar Yousefi ◽  
Amin Omidvar
Keyword(s):  
Real World ◽  
Nearest Neighbor ◽  
Predictive Accuracy ◽  
Credit Scoring ◽  
Default Probability ◽  
The Other ◽  
K Nearest Neighbor ◽  
Optimal Weights ◽  
Probability Prediction ◽  
Real World Datasets

Credit scoring has become a very important issue due to the recent growth of the credit industry. As the first objective, this chapter provides an academic database of literature between and proposes a classification scheme to classify the articles. The second objective of this chapter is to suggest the employing of the Optimally Weighted Fuzzy K-Nearest Neighbor (OWFKNN) algorithm for credit scoring. To show the performance of this method, two real world datasets from UCI database are used. In classification task, the empirical results demonstrate that the OWFKNN outperforms the conventional KNN and fuzzy KNN methods and also other methods. In the predictive accuracy of probability of default, the OWFKNN also show the best performance among the other methods. The results in this chapter suggest that the OWFKNN approach is mostly effective in estimating default probabilities and is a promising method to the fields of classification.

scholarly journals The Application of Pattern Recognition in Electrofacies Analysis

2014 ◽  
Vol 2014 ◽  
pp. 1-8 ◽  
Author(s):  
Huan Li ◽  
Xiao Yang ◽  
Wenhong Wei
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machine ◽  
Real World ◽  
Analytical Tool ◽  
Support Vector ◽  
Classification Algorithms ◽  
Number Of Clusters ◽  
Advantages And Disadvantages ◽  
Clustering And Classification ◽  
Real World Datasets

Pattern recognition is an important analytical tool in electrofacies analysis. In this paper, we study several commonly used clustering and classification algorithms. On the basis of advantages and disadvantages of existing algorithms, we introduce the KMRIC algorithm, which improves initial centers ofK-means. Also, we propose the AKM algorithm which automatically determines the number of clusters and apply support vector machine to classification. Finally, we apply these algorithms to electrofacies analysis, where the experiments on the real-world datasets are carried out to compare the merits of various algorithms.

scholarly journals SpHMC: Spectral Hamiltonian Monte Carlo

2019 ◽  
Vol 33 ◽  
pp. 5516-5524
Author(s):  
Haoyi Xiong ◽  
Kafeng Wang ◽  
Jiang Bian ◽  
Zhanxing Zhu ◽  
Cheng-Zhong Xu ◽  
...  
Keyword(s):  
Monte Carlo ◽  
Probability Distribution ◽  
Real World ◽  
Dimensional Space ◽  
Probability Distributions ◽  
Superior Performance ◽  
High Dimensional ◽  
Hamiltonian Monte Carlo ◽  
Real World Datasets ◽  
Low Dimensional

Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) methods have been widely used to sample from certain probability distributions, incorporating (kernel) density derivatives and/or given datasets. Instead of exploring new samples from kernel spaces, this piece of work proposed a novel SGHMC sampler, namely Spectral Hamiltonian Monte Carlo (SpHMC), that produces the high dimensional sparse representations of given datasets through sparse sensing and SGHMC. Inspired by compressed sensing, we assume all given samples are low-dimensional measurements of certain high-dimensional sparse vectors, while a continuous probability distribution exists in such high-dimensional space. Specifically, given a dictionary for sparse coding, SpHMC first derives a novel likelihood evaluator of the probability distribution from the loss function of LASSO, then samples from the high-dimensional distribution using stochastic Langevin dynamics with derivatives of the logarithm likelihood and Metropolis–Hastings sampling. In addition, new samples in low-dimensional measuring spaces can be regenerated using the sampled high-dimensional vectors and the dictionary. Extensive experiments have been conducted to evaluate the proposed algorithm using real-world datasets. The performance comparisons on three real-world applications demonstrate the superior performance of SpHMC beyond baseline methods.

Sign in / Sign up

Export Citation Format

Share Document