750 Hits in 4.1 sec

Nearest neighbor regression in the presence of bad hubs

Krisztian Buza, Alexandros Nanopoulos, Gábor Nagy
2015 Knowledge-Based Systems  
This paper is the first to study bad hubs in context of regression. We propose hubness-aware nearest neighbor regression schemes.  ...  However, k nearest neighbor approaches are affected by the presence of bad hubs, a recently observed phenomenon according to which some of the instances are similar to surprisingly many other instances  ...  Acknowledgment We thank to the Anonymous Reviewers' for their insightful comments and suggestions. Discussions about hubness-aware regression with Dr. Nenad Tomašev are highly appreciated.  ... 
doi:10.1016/j.knosys.2015.06.010 fatcat:xwhqshy3kbao5hq57ie67awjaa

A New Proposal for Person Identification Based on the Dynamics of Typing: Preliminary Results

Krisztian Buza, Dora Neubrandt
2017 Theoretical and Applied Informatics  
The presence of hubs, i.e., few instances that appear as nearest neighbours of surprisingly many other instances, have been observed in various domains recently and hubness-aware machine learning approaches  ...  In this paper, we examine hubness in typing data and propose to use ECkNN, a recent hubness-aware regression technique together with dynamic time warping for person identification.  ...  This research was performed within the framework of the grant of the Hungarian Scientific Research Fund -OTKA PD 111710.  ... 
doi:10.20904/281-2001 fatcat:hbowdxjoqjcatdsmf6eddssvui

ParkinsoNET: Estimation of UPDRS Score Using Hubness-Aware Feedforward Neural Networks

Krisztian Buza, Noémi Ágnes Varga
2016 Applied Artificial Intelligence  
In this paper, we study the hubness phenomenon in context of the UPDRS score estimation and propose hubness-aware error correction for feed-forward neural networks in order to increase the accuracy of  ...  Speech disturbance appears during the progression of the disease. UPDRS is a gold standard tool for diagnostic and follow up of the disease.  ...  Note that, some of the high error instances appear as nearest neighbors of many other instances, i.e., there are bad hubs in the data.  ... 
doi:10.1080/08839514.2016.1193716 fatcat:5lr6cxxdh5eu5g47n4t6fsq2py

ALADIN: A New Approach for Drug–Target Interaction Prediction [chapter]

Krisztian Buza, Ladislav Peska
2017 Lecture Notes in Computer Science  
In this paper, we extend BLM by the incorporation of a hubness-aware regression technique coupled with an enhanced representation of drugs and targets in a multi-modal similarity space.  ...  Due to its pharmaceutical applications, one of the most prominent machine learning challenges in bioinformatics is the prediction of drug-target interactions.  ...  Acknowledgment Ladislav Peska was supported by the Charles University grant P46.  ... 
doi:10.1007/978-3-319-71246-8_20 fatcat:rgoiorcnlresvgcwgyohiq6day

Hubness-Aware Classification, Instance Selection and Feature Construction: Survey and Extensions to Time-Series [chapter]

Nenad Tomašev, Krisztian Buza, Kristóf Marussy, Piroska B. Kis
2014 Studies in Computational Intelligence  
In the last decade, the simple nearest neighbor classifier, in combination with dynamic time warping (DTW) as distance measure, has been shown to achieve surprisingly good overall results on time-series  ...  On the other hand, the presence of hubs, i.e., instances that are similar to exceptionally large number of other instances, has been shown to be one of the crucial properties of time-series data sets.  ...  In the presence of class labels, we distinguish between good hubness and bad hubness: we say that the time series x ′ is a good k-nearest neighbor of the time series x, if (i) x ′ is one of the k-nearest  ... 
doi:10.1007/978-3-662-45620-0_11 fatcat:q7dmxcs34jgf3hero47yjvp4kq

Drug–target interaction prediction with Bipartite Local Models and hubness-aware regression

Krisztian Buza, Ladislav Peška
2017 Neurocomputing  
In this paper, we extend the Bipartite Local Model (BLM), one of the most prominent interaction prediction methods. In particular, we use BLM with a hubness-aware regression technique, ECkNN.  ...  The results show that our approach outperforms state-of-the-art drug-target prediction techniques. Additionally, we demonstrate the feasibility of predictions from the point of view of applications.  ...  Despite all of the aforementioned advantages of k-nearest neighbor regression, one of its recently explored shortcomings has to be mentioned, namely, the suboptimal performance in the presence of bad hubs  ... 
doi:10.1016/j.neucom.2017.04.055 fatcat:dbvyr4mejrbd7krvcmg263fllq

Ridge Regression, Hubness, and Zero-Shot Learning [article]

Yutaro Shigeto, Ikumi Suzuki, Kazuo Hara, Masashi Shimbo, Yuji Matsumoto
2015 arXiv   pre-print
of hubs in the subsequent nearest neighbor search step.  ...  This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space.  ...  The presence of hubs are not necessarily disadvantageous in standard classification settings; there may be "good" hubs as well as "bad" hubs [23] .  ... 
arXiv:1507.00825v1 fatcat:xzhuaboonzazlgemlpk6p6nwu4

Choosing ℓp norms in high-dimensional spaces based on hub analysis

Arthur Flexer, Dominik Schnitzer
2015 Neurocomputing  
We propose an unsupervised approach for choosing an ℓ p norm which minimizes hubs while simultaneously maximizing nearest neighbor classification.  ...  A closely related problem is the concentration of distances in high-dimensional spaces.  ...  Acknowledgements This research was supported by the Austrian Science Fund (FWF, Project P27082).  ... 
doi:10.1016/j.neucom.2014.11.084 pmid:26640321 pmcid:PMC4567076 fatcat:g5oxavf7svgm5jv6zkyq6sv2da

TPR, PPV and ROC based Performance Measurement and Optimization of Human Face Recognition of IoT Enabled Physical Location Monitoring

2019 International journal of recent technology and engineering  
Performance measurement of face recognition is done with the help of Decision Tree (DT), K-Nearest Neighbors (KNN), Naïve Bayes (NB) and Logistic Regression (LR).  ...  The dataset used in order to apply supervised machine learning algorithms is the combination of automatically captured live sensor data along with name of the human face recognized or unknown and additional  ...  K Nearest Neighbors (KNN) KNN recognizes the order of unclear information point based on its nearest neighbor whose class is as of now known.  ... 
doi:10.35940/ijrte.b3186.078219 fatcat:wlyr7rp7hjcyhk2xzxl4q2efq4

Building Trust On-Line: The Design of Reliable Reputation Reporting : Mechanisms for Online Trading Communities

Chrysanthos N. Dellarocas
2001 Social Science Research Network  
The objective of this paper is to contribute to the construction of online reputation reporting systems that are robust in the presence of unfair and deceitful raters.  ...  The paper sets the stage by providing a critical overview of the current state of the art in this area.  ...  mean of the fair ratings distribution in the nearest neighbor set.  ... 
doi:10.2139/ssrn.289967 fatcat:jz3iyr7qezdsdljqd3ycnjoibu

Improved Small Molecule Identification through Learning Combinations of Kernel Regression Models

Céline Brouard, Antoine Bassé, Florence d'Alché-Buc, Juho Rousu
2019 Metabolites  
In small molecule identification from tandem mass (MS/MS) spectra, input–output kernel regression (IOKR) currently provides the state-of-the-art combination of fast training and prediction and high identification  ...  Our experiments show a consistent improvement of top-k accuracy both in positive and negative ionization mode data.  ...  Acknowledgments: We acknowledge the computational resources provided by the Aalto Science-IT project. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/metabo9080160 pmid:31374904 pmcid:PMC6724104 fatcat:4rwswo6vq5h2phklyfpmrer6n4

Predicting missing links via local information

Tao Zhou, Linyuan Lü, Yi-Cheng Zhang
2009 European Physical Journal B : Condensed Matter Physics  
It is found that many links are assigned same scores if only the information of the nearest neighbors is used.  ...  We therefore design another new measure exploited information of the next nearest neighbors, which can remarkably enhance the prediction accuracy.  ...  [51] , who have already demonstrated the presence of rich-club phenomenon in the air transportation network).  ... 
doi:10.1140/epjb/e2009-00335-8 fatcat:ohwji4gw2jbxbnr7bc3gzadxkq

Topology and weights in a protein domain interaction network--a novel way to predict protein interactions

Stefan Wuchty
2006 BMC Genomics  
In fact, we expect that the heterogeneity in the utilization of connections has a major impact on the organization of cellular activities as well.  ...  protein interactions in the underlying interactions of yeast and fly.  ...  Acknowledgements This project was entirely funded by the Northwestern Institute on Complexity (NICO).  ... 
doi:10.1186/1471-2164-7-122 pmid:16716232 pmcid:PMC1523346 fatcat:tb5t23oe4rbevlsqehj3hrt35i

How Complex is your classification problem? A survey on measuring classification complexity [article]

Ana C. Lorena, Luís P. F. Garcia, Jens Lehmann, Marcilio C. P. Souto, Tin K. Ho
2020 arXiv   pre-print
Characteristics extracted from the training datasets of classification problems have proven to be effective predictors in a number of meta-analyses.  ...  Among them, measures of classification complexity can be used to estimate the difficulty in separating the data points into their expected classes.  ...  Acknowledgements The first author would like to thank the financial support of the foundations FAPESP (grant 2012/22608-8) and CNPq (grant 308858/2014-0).  ... 
arXiv:1808.03591v3 fatcat:5g7uqvcd5fatphqa3zgylepgl4

Perception Exploration on Robustness Syndromes With Pre-processing Entities Using Machine Learning Algorithm

Pravin R. Kshirsagar, Hariprasath Manoharan, Shitharth Selvarajan, Hassan A. Alterazi, Dilbag Singh, Heung-No Lee
2022 Frontiers in Public Health  
The CNN also detects early-stage problems since it accepts input in the form of writing and sketching, both of which are turned to images.  ...  As a result, the primary goal of the proposed research is to create a unique model that can detect a variety of diseases in humans, thereby averting a high level of depression.  ...  All authors contributed to the article and approved the submitted version.  ... 
doi:10.3389/fpubh.2022.893989 pmid:35784247 pmcid:PMC9243559 fatcat:iud4mgewm5bzxepqqkpuiu4h6m
« Previous Showing results 1 — 15 out of 750 results