On the Time Series $K$-Nearest Neighbor Classification of Abnormal Brain Activity

Chaovalitwongse, Wanpracha Art; Fan, Ya-Ju; Sachdeo, Rǎjesh C.

doi:10.1109/tsmca.2007.897589

Cited by 169 publications

(69 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The last element of the warping path is the distance between two time series [15]. This matrix has complexity of O(M N ), thus in our implementation we decreased the complexity by limiting the warping window size.…”

Section: Dynamic Time Warpingmentioning

confidence: 99%

Real time degradation identification of UAV using machine learning techniques

Manukyan

Olivares-Méndez

Voos

et al. 2017

2017 International Conference on Unmanned Aircraft Systems (ICUAS)

View full text Add to dashboard Cite

Abstract-The usages and functionalities of Unmanned Aerial Vehicles (UAV) have grown rapidly during the last years. They are being engaged in many types of missions, ranging from military to agriculture passing by entertainment and rescue or even delivery. Nonetheless, for being able to perform such tasks, UAVs have to navigate safely in an often dynamic and partly unknown environment. This brings many challenges to overcome, some of which can lead to damages or degradations of different body parts. Thus, new tools and methods are required to allow the successful analysis and identification of the different threats that UAVs have to manage during their missions or flights. Various approaches, addressing this domain, have been proposed. However, most of them typically identify the changes in the UAVs behavior rather than the issue. This work presents an approach, which focuses not only on identifying degradations of UAVs during flights, but estimate the source of the failure as well.

show abstract

Section: Dynamic Time Warpingmentioning

confidence: 99%

Real time degradation identification of UAV using machine learning techniques

Manukyan

Olivares-Méndez

Voos

et al. 2017

2017 International Conference on Unmanned Aircraft Systems (ICUAS)

View full text Add to dashboard Cite

show abstract

“…O parâmetro k pode ser obtido através de validação cruzada na porção de treino, maximizando-se indicadores de performance de classificação como sensibilidade e especificidade, entre outros. Maiores detalhes sobre KNN podem ser obtidos em Duda et al [17], enquanto que exemplos de aplicações são encontrados em Golub et al [18], Weiss et al [19] e Chaovalitwongse et al [20].…”

Section: Referencial Teóricounclassified

“…Três componentes PLS foram retidos em cada banco de dados, com base no percentual de variância explicada em Y (Vinho tinto=81%, Vinho branco=77%, QSAR=70%). O parâmetro k da ferramenta KNN foi determinado por intermédio de 15 repetições de validação cruzada, sendo que cada banco de dados foi dividido em 5 porções em cada procedimento [20]. Definiu-se k=3 para os três bancos de dados ao maximizar-se sensibilidade e especificidade simultaneamente.…”

Section: Métodounclassified

See 1 more Smart Citation

Seleção De Variáveis Para Categorização De Amostras Químicas

Anzanello

2017

Eclet. Quim. J.

View full text Add to dashboard Cite

This paper presents a method to select the best variables to categorize chemical samples into two classes, say conforming or non-conforming. For that matter, PLS regression is combined with a data mining tool, the k-Nearest Neighbor classification technique, through an iterative variable selection process. The recommended subset of variables is chosen based on several criteria: sensitivity, specificity and percent of retained variables. When applied to two datasets related to wine analysis and one associated to QSAR, the proposed method significantly reduced the number of variables required for classification, while yielding superior categorization performance when compared to using all original variables.

show abstract

“…In general, for a given unlabeled time series X, the KNN rule finds the K "closest" (neighborhood) labeled time series in the training data set and assigns X to the class that appears most frequently in the neighborhood of k time series. There are two main schemes or decision rules in KNN algorithm, the similarity voting scheme and majority voting scheme (Chaovalitwongse et al 2007). …”

Section: K Nearest Neighbour (Knn)mentioning

confidence: 99%