A review of clustering techniques and developments

Saxena, Amit; Prasad, Mukesh; Gupta, Akanksha; Bharill, Neha; Patel, Om Prakash; Tiwari, Aruna; Er, Meng Joo; Ding, Weiping; Lin, Chin‐Teng

doi:10.1016/j.neucom.2017.06.053

Cited by 939 publications

(549 citation statements)

References 136 publications

Supporting

Mentioning

477

Contrasting

Unclassified

Order By: Relevance

“…We also adopted a data driven approach (correlation-based hierarchical clustering) to define our region of interest. In this method, we used average linkage clustering on Spearman correlation between the temporal responses recorded by each pair of electrodes to cluster the channels into groups [32].…”

Section: Eegmentioning

confidence: 99%

The correspondence between EMG and EEG measures of changes in cortical excitability following transcranial magnetic stimulation

Biabani

Fornito

Coxon

et al. 2019

Preprint

View full text Add to dashboard Cite

Introduction: Transcranial magnetic stimulation (TMS) is a powerful tool to investigate local cortical circuits and broader neural networks. Paired-pulse TMS (ppTMS) paradigms are commonly employed to study excitatory/inhibitory neurotransmissions in motor circuits across time by assessing changes in motor-evoked potentials (MEPs) using electromyography (EMG).The combination of TMS with electroencephalography (EEG) has the capacity to extend this work outside the motor system by focusing on TMS-evoked potentials (TEPs) across both space and time as the measurable output of brain stimulation. However, the relationship between these two putative outputs of TMS effects -MEPs and TEPs -remains unclear. Aim: To investigate whether the same neural populations are responsible for fluctuations in MEPs with ppTMS as the TEP waveform following single pulse TMS (spTMS). Methods: Twenty-four healthy participants received intra-hemispheric and interhemispheric (dual-coil) ppTMS, with different inter-pulse intervals, conditioning intensities, and TMS pulse waveforms over the motor cortex, while EMG was recorded from first dorsal interosseous muscles. EEG was also recorded in response to spTMS with the same intensity and location as the conditioning pulses in ppTMS-EMG. Additionally, TMS was applied to the shoulder as a multisensory control condition. The relationship between ppTMS-EMG and spTMS-EEG were evaluated using metrics sensitive to both the shape and amplitude of the signals. Results: The fluctuations in cortical excitability following suprathreshold TMS were correlated in shape, but not amplitude, when measured with ppTMS-EMG and TMS-EEG. This relationship was observable only after reversing the 2 polarity of short latency TEPs (<~60 ms). For interhemispheric measures, supressing sensory potentials in TEPs was required to discern the relationship between the two signals. Conclusion:The relationship between MEP and TEP measures suggests both signals reflect activity from overlapping neural populations. This finding establishes a fundamental link between TEP peaks and periods of net excitation/inhibition observed with ppTMS-EMG in both the stimulated motor cortex and connected cortical regions.

show abstract

Section: Eegmentioning

confidence: 99%

The correspondence between EMG and EEG measures of changes in cortical excitability following transcranial magnetic stimulation

Biabani

Fornito

Coxon

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…We choose three widespread partitioning clustering methods [31,39,42] for our purpose: -means, PAM (Partitioning Around Medoids), and CLARA (Clustering LARge Application). In the following paragraphs, we introduce the main ideas behind these well-known methods.…”

Section: Clustering Methodsmentioning

confidence: 99%

Network Intrusion Detection with Threat Agent Profiling

Bajtoš

Gajdoš

Kleinova

et al. 2018

Security and Communication Networks

View full text Add to dashboard Cite

With the increase in usage of computer systems and computer networks, the problem of intrusion detection in network security has become an important issue. In this paper, we discuss approaches that simplify network administrator's work. We applied clustering methods for security incident profiling. We consider -means, PAM, and CLARA clustering algorithms. For this purpose, we used data collected in Warden system from various security tools. We do not aim to differentiate between normal and abnormal network traffic, but we focus on grouping similar threat agents based on attributes of security events. We suggest a case of a fine classification and a case of a coarse classification and discuss advantages of both cases.

show abstract

“…To show the advantage of using our proposed clustering method, different clustering techniques such as K‐mean, partitioning around medoids, clustering for large applications, and clustering large applications based on randomized search, which were proposed by Saxena et al (), are run along with SOM. Table compares these clustering techniques considering Davies–Bouldin index (see Kapoor, Zeya, Singhal, & Nanda, ) that is based on dispersion measure within each cluster i (i.e., S i ) and cluster dissimilarity between two clusters i and j (i.e., D ij ).…”

Section: Case Studymentioning

confidence: 99%

A robust hybrid artificial neural network double frontier data envelopment analysis approach for assessing sustainability of power plants under uncertainty

et al. 2019

View full text Add to dashboard Cite

To assess sustainability of power plants, this paper presents a novel hybrid method. To this end, self‐organizing map method of artificial neural networks is employed. Then, a double frontier data envelopment analysis is developed to rank power plants in each cluster of decision‐making units. Because outputs of power plants might be uncertain, a robust optimization approach is incorporated into proposed double frontier data envelopment analysis model to present ranks that are robust against different uncertainties. A case study is given to validate the proposed model. The case study shows that the proposed model can present improvement solutions that guide power plants towards efficient frontier and far from inefficient frontier. Given the results, decision makers can decide on which power plants should be closed and which power plants should be expanded.

show abstract

A review of clustering techniques and developments

Cited by 939 publications

References 136 publications

The correspondence between EMG and EEG measures of changes in cortical excitability following transcranial magnetic stimulation

The correspondence between EMG and EEG measures of changes in cortical excitability following transcranial magnetic stimulation

Network Intrusion Detection with Threat Agent Profiling

A robust hybrid artificial neural network double frontier data envelopment analysis approach for assessing sustainability of power plants under uncertainty

Contact Info

Product

Resources

About