A Quantitative Site-Specific Classification Approach Based on Affinity Propagation Clustering

Moustafa, Sayed S. R.; Abdalzaher, Mohamed S.; Khan, Farhan Hassan; Metwaly, Mohamed; Elawadi, Eslam; Al‐Arifi, Nassir

doi:10.1109/access.2021.3128284

Cited by 31 publications

(5 citation statements)

References 55 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fourth aim is to compare the two developed algorithms to affinity propagation clustering [34] algorithms, e.g., for studying the seismic consequences caused by earthquakes [35]. In addition, the influence of the method about point distributions in the hypersphere [36] on our described clustering deserves particular attention.…”

Section: Discussionmentioning

confidence: 99%

Improving Clustering Accuracy of K-Means and Random Swap by an Evolutionary Technique Based on Careful Seeding

Nigro,

Cicirelli

2023

Algorithms

View full text Add to dashboard Cite

K-Means is a “de facto” standard clustering algorithm due to its simplicity and efficiency. K-Means, though, strongly depends on the initialization of the centroids (seeding method) and often gets stuck in a local sub-optimal solution. K-Means, in fact, mainly acts as a local refiner of the centroids, and it is unable to move centroids all over the data space. Random Swap was defined to go beyond K-Means, and its modus operandi integrates K-Means in a global strategy of centroids management, which can often generate a clustering solution close to the global optimum. This paper proposes an approach which extends both K-Means and Random Swap and improves the clustering accuracy through an evolutionary technique and careful seeding. Two new algorithms are proposed: the Population-Based K-Means (PB-KM) and the Population-Based Random Swap (PB-RS). Both algorithms consist of two steps: first, a population of J candidate solutions is built, and then the candidate centroids are repeatedly recombined toward a final accurate solution. The paper motivates the design of PB-KM and PB-RS, outlines their current implementation in Java based on parallel streams, and demonstrates the achievable clustering accuracy using both synthetic and real-world datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving Clustering Accuracy of K-Means and Random Swap by an Evolutionary Technique Based on Careful Seeding

Nigro,

Cicirelli

2023

Algorithms

View full text Add to dashboard Cite

show abstract

“…In the seismology field, the presented efforts in seismic hazard assessment, risk mitigation, site specification parameter determination, etc. would assist in this regard [8], [9], [10], [11]. Therefore, intelligent integration between these classical and modern technologies has become inevitable to mitigate such vulnerable systems.…”

Section: Introductionmentioning

confidence: 99%

Toward Secured IoT-Based Smart Systems Using Machine Learning

et al. 2023

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) and the internet of things (IoT) are among the most booming research directions. Smart cities, smart campuses (SCs), smart homes, smart cars, early warning systems (EWSs), etc.; or it could be called ''Smart x'' systems are implemented using ML and IoT. Those systems will alter how various world entities communicate with one another. This paper spots light on the significant roles of the IoT in SS. Also, it focuses on the importance of ML in IoT-based SS. Besides, an overview of smartness and IoT is presented. Then, this paper offers ML benchmarking along with a taxonomy that categorizes the ML models into linear and non-linear ones depending on the problem type (classification or regression). Afterward, the commonly utilized evaluation metrics are provided. In addition, this paper considers the trust techniques used for mitigating different security aspects in IoT networks, which play a crucial part in regulating the new era of communication. Moreover, two case studies devoting ML for IoT-based SS, namely IoT-based SC and IoT-based EWS, are considered for data collection and manipulation with guided research directions. Finally, the paper presents effective recommendations of ML's significant roles in SC and earthquake EWS for interested scholars.INDEX TERMS Machine learning, Internet of Things, smart systems, security.

show abstract

“…As a result, a procedure for shortlisting sites is needed to pick the most ideal places for applying site-specific micro zonation methods [10]- [12] nature-based seismic hazard reduction measures. To guarantee sustainable land management and the protection of human life in urban environments, decision-makers, engineers, planners, and managers must consider the physical elements of the urban region, as well as natural risks, while planning and growing an urban environment [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Seismic Hazard and Site Suitability Evaluation Based on Multicriteria Decision Analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

Effective management and planning for sustainable urban regions' development require up-todate information. Natural hazard maps (NHMs) creation is critical for urban development. Urban areas along the western coast of Saudi Arabia are susceptible to natural disasters due to their hazard sources' proximity, especially, with the lack of preparation. Yanbu' Al-Bahr, a major Red Sea port, provides an excellent example. This research aims to combine NHMs into a single multi-hazard map, allowing acceptable site identification for urban development. To create a seismic hazard model of the rapidly growing Yanbu' Al-Bahr region, spatial distributions of different hazard entities were assessed using the analytical hierarchy process (AHP). To create a multi-hazard map, six seismic hazard assessment maps were independently developed. Hazard attributes were assimilated into a geographic information system (GIS) platform to delineate seismic hazard zones and build a suitability map for urban development. Weight and rank values were determined during AHP and assigned to each layer and its corresponding classes. By overlaying all the weighted maps, a suitability map was created. This map depicts the research area's prospective appropriateness for urban growth. Accordingly, the study area was classified into five hazard categories, namely, very-low (VL), low (L), moderate (M), high (H), and very high (VH). Therefore, the limited regions, most appropriate locations, and least suitable areas were identified. Accordingly, stakeholders can use the produced seismic hazard map as a platform for future land-use planning and environmental hazard management. Furthermore, the AHP-GIS model would deliver more precise findings in urban development site selection studies.

show abstract

A Quantitative Site-Specific Classification Approach Based on Affinity Propagation Clustering

Cited by 31 publications

References 55 publications

Improving Clustering Accuracy of K-Means and Random Swap by an Evolutionary Technique Based on Careful Seeding

Improving Clustering Accuracy of K-Means and Random Swap by an Evolutionary Technique Based on Careful Seeding

Toward Secured IoT-Based Smart Systems Using Machine Learning

Seismic Hazard and Site Suitability Evaluation Based on Multicriteria Decision Analysis

Contact Info

Product

Resources

About