Can We Group Similar Amazon Reviews: A Case Study with Different Clustering Algorithms

2016 ◽  
Author(s):  
Chantal Fry ◽  
Sukanya Manna
Keyword(s):  
Clustering Algorithms

scholarly journals Spatial analysis of urban material stock with clustering algorithms: A Northern European case study

2019 ◽  
Vol 23 (6) ◽  
pp. 1328-1343
Author(s):  
Paul Gontia ◽  
Liane Thuvander ◽  
Babak Ebrahimi ◽  
Victor Vinas ◽  
Leonardo Rosado ◽  
...  
Keyword(s):  
Spatial Analysis ◽  
Clustering Algorithms ◽  
Northern European

Innovation Problem Identification and Decision-Making for Product Platform

2009 ◽  
Vol 628-629 ◽  
pp. 131-136 ◽  
Author(s):  
Yu Yi Liu ◽  
Liang Hou ◽  
Hong Lian Wang
Keyword(s):  
Decision Making ◽  
Clustering Algorithms ◽  
Value Engineering ◽  
Product Platform ◽  
Problem Identification ◽  
Existing Problems ◽  
Correlation Degree ◽  
Production Capacities ◽  
Platform Evolution

During product platform life cycle, innovation problem identification and decision-making are regarded as vital issues in product platform evolution process. The Comprehensive Disturbance Degree is proposed and analyzed considering customer demand, technology status and production capacities, then existing problems of product platform are identified. According to Innovation Problem Selecting Principles, the innovation problem set Q is defined. The value of modules in product platform is calculated using Value Engineering, the module set M needed to be improved is determined. Then based upon the correlation degree analysis of the innovation problem set and the module set, Fuzzy Clustering Algorithms is advanced to classify innovation problems. Finally, a case study is given to illustrate the validity of the methodology.

scholarly journals Space–time series clustering: Algorithms, taxonomy, and case study on urban smart cities

2020 ◽  
Vol 95 ◽  
pp. 103857
Author(s):  
Asma Belhadi ◽  
Youcef Djenouri ◽  
Kjetil Nørvåg ◽  
Heri Ramampiaro ◽  
Florent Masseglia ◽  
...  
Keyword(s):  
Time Series ◽  
Smart Cities ◽  
Clustering Algorithms ◽  
Space Time ◽  
Time Series Clustering

scholarly journals Evolutionary dataset optimisation: learning algorithm quality through evolution

2019 ◽  
Vol 50 (4) ◽  
pp. 1172-1191 ◽  
Author(s):  
Henry Wilde ◽  
Vincent Knight ◽  
Jonathan Gillard
Keyword(s):  
Finite Number ◽  
Open Source ◽  
Learning Algorithm ◽  
Clustering Algorithms ◽  
Genetic Evolution ◽  
Artificial Data ◽  
New Approach ◽  
Benchmark Datasets ◽  
Novel Method

AbstractIn this paper we propose a novel method for learning how algorithms perform. Classically, algorithms are compared on a finite number of existing (or newly simulated) benchmark datasets based on some fixed metrics. The algorithm(s) with the smallest value of this metric are chosen to be the ‘best performing’. We offer a new approach to flip this paradigm. We instead aim to gain a richer picture of the performance of an algorithm by generating artificial data through genetic evolution, the purpose of which is to create populations of datasets for which a particular algorithm performs well on a given metric. These datasets can be studied so as to learn what attributes lead to a particular progression of a given algorithm. Following a detailed description of the algorithm as well as a brief description of an open source implementation, a case study in clustering is presented. This case study demonstrates the performance and nuances of the method which we call Evolutionary Dataset Optimisation. In this study, a number of known properties about preferable datasets for the clustering algorithms known as k-means and DBSCAN are realised in the generated datasets.

Incorporating Field Effects Into Modular Architecture Methods

2010 ◽  
Author(s):  
Kevin Otto ◽  
Katja Ho¨ltta¨-Otto
Keyword(s):  
Clustering Algorithms ◽  
High Heat ◽  
High Magnetic Fields ◽  
Modular Architecture ◽  
Creative Solutions ◽  
Modular Architectures ◽  
Architectural Synthesis ◽  
Field Boundaries ◽  
Definition Of

Prior research on methods and algorithms to create modules and modular architectures deal with minimizing interactions between modules and increasing the commonality between products. While these approaches are a good start and provide good suggestions for preliminary architecture, these algorithms ignore the fact that some design solutions cannot be placed in regions of high heat, high pressure, high magnetic fields, etc. The exclusion of such field effect constraints often results in architecture clustering algorithms forming impractical solutions. In this paper, we introduce a field based definition of modularity constraints that incorporate these practical embodiment considerations. We demonstrate the method via examples and a detailed case study in medical device industry. We find that the field based module definitions not only bring the constraints of fields to the attention of the designer, but it also enables new creative solutions through movement of the field boundaries over different functions or components. Generally, only the two endpoint set-of-functions need be at different field values, and the intermediary parts or functions connecting them can be in either field. We conclude with a set of architectural guidelines to bridge the gap between current work and practical architectural synthesis considerations.

scholarly journals Siting MSW landfills via the integration of DEMATEL-ANP and clustering algorithm in a fuzzy logic environment (Case Study: Lanzhou, China)

2021 ◽  
Author(s):  
Jiamin Liu ◽  
Yueshi Li ◽  
Bin Xiao ◽  
Jizong Jiao
Keyword(s):  
Fuzzy Logic ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Decision Makers ◽  
Spatial Distribution Characteristics ◽  
Criteria Weights ◽  
Spatial Decision Making ◽  
Complex Decision ◽  
Selection Of

Abstract The siting of Municipal Solid Waste (MSW) landfills is a complex decision based process that involves multiple hydrogeological, morphological, environmental, climatic, and socio-economic criteria. In a fuzzy logic environment, DEMATEL and ANP methods were employed to comprehensively consider uncertainty, fuzziness of data and the subjective scoring and stability of results to enhance the spatial decision-making process. Primarily, 21 criteria were identified in five groups through the Delphi method at 30m resolution, criteria weights were determined via the integration of DEMATEL and ANP, and seven sets of membership functions were simulated to obtain the best fuzzy logic environment. Combining GIS spatial analysis and the three clustering algorithms (DBSCAN, HDBSCAN, and OPTICS), candidate sites that satisfied the landfill conditions were identified, and the spatial distribution characteristics and reachability were analyzed. These sites were subsequently ranked utilizing the MOORA, WASPAS, COPRAS, and TOPSIS methods to verify the reliability of the results by conducting sensitivity analysis. This paper focuses on a flexible and novel framework for the selection of MSW landfill sites for Lanzhou, which is a semi-arid valley basin city in China. In contrast to common techniques, this model not only made the best recommendation scientifically and efficiently but could also provide accurate assessment data for decision makers in landfill construction and high-quality urban development.

Sign in / Sign up

Export Citation Format

Share Document