Efficient Computation of Multiple Density-Based Clustering Hierarchies

Neto, Antonio Cavalcante Araujo; Campello, Ricardo J. G. B.; Nascimento, Mário A.

doi:10.1109/icdm.2017.127

Cited by 18 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, this RNG has typically much fewer edges than the complete graph so its construction cost is more than outweighed by the reduction in edge weight computations. This paper is an extension of [29]. We add here all the proofs that guarantee the correctness of our proposed approach.…”

Section: Introductionmentioning

confidence: 94%

Efficient Computation and Visualization of Multiple Density-Based Clustering Hierarchies

Neto

Campello

Nascimento

2021

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

HDBSCAN*, a state-of-the-art density-based hierarchical clustering method, produces a hierarchical organization of clusters in a dataset w.r.t. a parameter mpts. While a small change in mpts typically leads to a small change in the clustering structure, choosing a "good" mpts value can be challenging: depending on the data distribution, a high or low mpts value may be more appropriate, and certain clusters may reveal themselves at different values. To explore results for a range of mpts values, one has to run HDBSCAN* for each value independently, which can be computationally impractical. In this paper, we propose an approach to efficiently compute all HDBSCAN* hierarchies for a range of mpts values by building upon results from computational geometry to replace HDBSCAN*'s complete graph with a smaller equivalent graph. An experimental evaluation shows that our approach can obtain over one hundred hierarchies for the computational cost equivalent to running HDBSCAN* about twice, which corresponds to a speedup of more than 60 times, compared to running HDBSCAN* independently that many times. We also propose a series of visualizations that allow users to analyze a collection of hierarchies for a range of mpts values, along with case studies that illustrate how these analyses are performed.

show abstract

Section: Introductionmentioning

confidence: 94%

Efficient Computation and Visualization of Multiple Density-Based Clustering Hierarchies

Neto

Campello

Nascimento

2021

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Beyond the minimum cluster size (MinPts), which is much easier to choose than Eps, the method requires no further setting of arbitrary or biasing parameters by a user [28]. Though HDBSCAN is claimed to be robust [29], the algorithm to build the hierarchy runs in quadratic time, in both the worst and the best case [30].…”

Section: Research Backgroundmentioning

confidence: 99%

The adaptive spatio-temporal clustering method in classifying direct labor costs for the manufacturing industry

Weichbroth¹,

Kalinowski²

2021

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Employee productivity is critical to the profitability of not only the manufacturing industry. By capturing employee locations using recent advanced tracking devices, one can analyze and evaluate the time spent during a workday of each individual. However, over time, the quantity of the collected data becomes a burden, and decreases the capabilities of efficient classification of direct labor costs. However, the results obtained from performed experiments show that the existing clustering methods have failed to deliver satisfactory results by taking advantage of spatial data. In contrast to this, the adaptive spatio-temporal clustering (ASTC) method introduced in this paper utilizes both spatial and time data, as well as prior data concerning the position and working status of deployed machines inside a factory. The results show that our method outperforms the bucket of three well-known methods, namely DBSCAN, HDBSCAN and OPTICS. Moreover, in a series of experiments, we also validate the underlying assumptions and design of the ASTC method, as well as its efficiency and scalability. The application of the method can help manufacturing companies analyze and evaluate employees, including the productive times of day and most productive locations.

show abstract

“…While traditional clustering techniques have provided many efficient schemes to detect irregularly shaped clusters (e.g., DBSCAN [52], OPTICS [10], spectral clustering [178], Chameleon [84], HDBSCAN [20,135], etc. ), these methods, as introduced earlier, do not incorporate statistical rigor required by domain applications of spatial hotspot detection (Sec.…”

Section: Enumerationmentioning

confidence: 99%

Statistically-Robust Clustering Techniques for Mapping Spatial Hotspots: A Survey

Xie,

Shekhar,

2021

Preprint

View full text Add to dashboard Cite

Mapping of spatial hotspots, i.e., regions with significantly higher rates or probability density of generating certain events (e.g., disease or crime cases), is a important task in diverse societal domains, including public health, public safety, transportation, agriculture, environmental science, etc. Clustering techniques required by these domains differ from traditional clustering methods due to the high economic and social costs of spurious results (e.g., false alarms of crime clusters). As a result, statistical rigor is needed explicitly to control the rate of spurious detections. To address this challenge, techniques for statistically-robust clustering have been extensively studied by the data mining and statistics communities. In this survey we present an up-to-date and detailed review of the models and algorithms developed by this field. We first present a general taxonomy of the clustering process with statistical rigor, covering key steps of data and statistical modeling, region enumeration and maximization, significance testing, and data update. We further discuss different paradigms and methods within each of key steps. Finally, we highlight research gaps and potential future directions, which may serve as a stepping stone in generating new ideas and thoughts in this growing field and beyond.

show abstract

Efficient Computation of Multiple Density-Based Clustering Hierarchies

Cited by 18 publications

References 17 publications

Efficient Computation and Visualization of Multiple Density-Based Clustering Hierarchies

Efficient Computation and Visualization of Multiple Density-Based Clustering Hierarchies

The adaptive spatio-temporal clustering method in classifying direct labor costs for the manufacturing industry

Statistically-Robust Clustering Techniques for Mapping Spatial Hotspots: A Survey

Contact Info

Product

Resources

About