Blended Models for Nearest Neighbour Algorithms for High Dimensional Smart Medical Data

2020 ◽  
pp. 48-75
Author(s):  
Sandhya Harikumar
Keyword(s):  
Nearest Neighbor ◽  
Window Size ◽  
High Dimensional ◽  
Massive Datasets ◽  
Parzen Window ◽  
Classification Of Diseases ◽  
Diagnosis And Classification ◽  
Generative Algorithms ◽  
Neighbor Classifier

Nearest neighbor algorithms like kNN and Parzen Window are generative algorithms that are used extensively for medical diagnosis and classification of diseases. The data generated or collected in healthcare is high dimensional and cannot be assumed to follow a particular distribution. The conventional approaches fail due to computational complexity, curse of dimensionality, and varying distributions. Hence, this chapter deals with a blending technique for evaluation of nearest neighbor algorithms based on various parameters such as the size of data, dimensions of data, window size, and number of nearest neighbors to make it suitable for massive datasets. Dimensionality reduction and clustering are combined with nearest neighbor classifier such as kNN and Parzen Window to observe the performance of the blended models on various types of datasets. Experimental results on 15 real datasets with various models reveal the efficacy of the proposed blends.

Depression

2017 ◽  
Author(s):  
Philip Cowen
Keyword(s):  
International Classification Of Diseases ◽  
Behavioural Therapy ◽  
Historical Background ◽  
Cognitive Behavioural ◽  
Classification Of Diseases ◽  
Icd 10 ◽  
Diagnosis And Classification ◽  
Modern Experience ◽  
Symptoms And Signs

This chapter discusses the symptomatology, diagnosis, and classification of depression. It begins with a brief historical background on depression, tracing its origins to the classical term ‘melancholia’ that describes symptoms and signs now associated with modern concepts of the condition. It then considers the phenomenology of the modern experience of depression, its diagnosis in the operational scheme of ICD-10 (International Classification of Diseases, tenth edition), and current classificatory schemes. It looks at the symptoms needed to meet the criteria for ‘depressive episode’ in ICD-10, as well as clinical features of depression with ‘melancholic’ features or ‘somatic depression’ in ICD-10. It also presents an outline of the clinical assessment of an episode of depression before concluding with an overview of issues that need to be taken into account when addressing approaches to treatment, including cognitive behavioural therapy and the administration of antidepressants.

Gait Recognition Based on Locality Preserving Projections

2015 ◽  
Vol 738-739 ◽  
pp. 625-630
Author(s):  
Chao Li ◽  
Jin Ye Peng ◽  
Jing Guo ◽  
Xian Feng Wang ◽  
Xu Qi Wang
Keyword(s):  
Nearest Neighbor ◽  
Wavelet Packet ◽  
Gait Recognition ◽  
Recognition Method ◽  
The Public ◽  
Nearest Neighbor Classifier ◽  
Locality Preserving Projections ◽  
Locality Preserving ◽  
Neighbor Classifier

A gait recognition method based on wavelet packet decomposition (WPD) and Locality preserving projections (LPP) is proposed in this paper. The method includes the following steps, pretreatment, feature extraction by WPD and dimensionality reduction by LPP and classification of the test samples to a corresponding class according to the nearest neighbor classifier. The experiment results on the public gait database show the effectiveness of the proposed method.

scholarly journals On Improving the Classification of Imbalanced Data

2017 ◽  
Vol 17 (1) ◽  
pp. 45-62 ◽  
Author(s):  
Lincy Meera Mathews ◽  
Hari Seetha
Keyword(s):  
Nearest Neighbor ◽  
Imbalanced Data ◽  
Experimental Results ◽  
Minority Class ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

Abstract Mining of imbalanced data isachallenging task due to its complex inherent characteristics. The conventional classifiers such as the nearest neighbor severely bias towards the majority class, as minority class data are under-represented and outnumbered. This paper focuses on building an improved Nearest Neighbor Classifier foratwo class imbalanced data. Three oversampling techniques are presented, for generation of artificial instances for the minority class for balancing the distribution among the classes. Experimental results showed that the proposed methods outperformed the conventional classifier.

scholarly journals Nearest-neighbor classifier as a tool for classification of protein families

2010 ◽  
Vol 4 (9) ◽  
pp. 396-398 ◽  
Author(s):  
Mona Chaurasiya ◽  
Gohel Bakul Chandulal ◽  
Krishna Misra ◽  
Vivek Kumar Chaurasiya
Keyword(s):  
Nearest Neighbor ◽  
Protein Families ◽  
Nearest Neighbor Classifier ◽  
Neighbor Classifier

scholarly journals K Nearest Neighbor Based Model for Intrusion Detection System

2019 ◽  
Vol 8 (2) ◽  
pp. 2258-2262 ◽  
Keyword(s):  
Intrusion Detection System ◽  
Nearest Neighbor ◽  
Detection System ◽  
Information And Communications Technology ◽  
K Nearest Neighbor ◽  
Digital Era ◽  
Learning Classifier ◽  
Improved Accuracy ◽  
Neighbor Classifier

Network security has become more important in this digital era due to the usage of information and communications technology (ICT). Data security is also one of the major issues in today’s world. Due to the usage of this ICT technologies threat to network is also increasing. So in order to solve these problems the researchers has developed IDS that deals with network traffic to identify the harmful users and hackers in the computer. In this paper, we designed a model for IDS for classification of attacks using K-Nearest Neighbor classifier algorithm. KNN is a supervised and lazy machine learning classifier, it shows its best performance in terms of accuracy and classifications. Experimental analysis was conducted on ISCX dataset to judge the implementation of model. The Experimental outcome shows that our suggested model recorded an improved accuracy of 99.96%.

Sign in / Sign up

Export Citation Format

Share Document