Potential- $K$- Means for Load Balancing and Cost Minimization in Mobile Recycling Network

Cabria, I.; Gondra, Iker

doi:10.1109/jsyst.2014.2363156

Cited by 12 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relying on the proposed relay selection algorithm, the total capacity was increased by reusing the frequency in each low power cluster, which had the benefit of supporting high data rate services. Additionally, Cabria and Gondra [245] proposed a so-called potential-K-means scheme for partitioning data collection sensors into clusters and then for assigning each cluster to a storage center. The proposed K-means solution had the advantage of both balancing the storage center loads and minimizing the total network cost (optimizing the total number of sensors).…”

Section: A K-means Clustering and Its Applications 1)mentioning

confidence: 99%

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

Wang

Jiang

Zhang

et al. 2020

IEEE Commun. Surv. Tutorials

469

200

View full text Add to dashboard Cite

Future wireless networks have a substantial potential in terms of supporting a broad range of complex compelling applications both in military and civilian fields, where the users are able to enjoy high-rate, low-latency, low-cost and reliable information services. Achieving this ambitious goal requires new radio techniques for adaptive learning and intelligent decision making because of the complex heterogeneous nature of the network structures and wireless services. Machine learning (ML) algorithms have great success in supporting big data analytics, efficient parameter estimation and interactive decision making. Hence, in this article, we review the thirty-year history of ML by elaborating on supervised learning, unsupervised learning, reinforcement learning and deep learning. Furthermore, we investigate their employment in the compelling applications of wireless networks, including heterogeneous networks (Het-Nets), cognitive radios (CR), Internet of things (IoT), machine to machine networks (M2M), and so on. This article aims for assisting the readers in clarifying the motivation and methodology of the various ML algorithms, so as to invoke them for hitherto unexplored services as well as scenarios of future wireless networks.

show abstract

Section: A K-means Clustering and Its Applications 1)mentioning

confidence: 99%

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

Wang

Jiang

Zhang

et al. 2020

IEEE Commun. Surv. Tutorials

469

200

View full text Add to dashboard Cite

show abstract

“…It is possible for the SDN controller to use different clustering algorithms. In this paper, we use the K-means algorithm [17] which divides a set of N nodes in the network into K groups called clusters by minimizing the sum of the distances from the nodes belonging to a given group to the center of gravity of that group, called the centroid. Applied to our network architecture presented in Figure 4, the node that is closest to a centroid is designed as GO for the corresponding cluster.…”

Section: Clustering Algorithmmentioning

confidence: 99%

SDN-based Wi-Fi Direct clustering for cloud access in campus networks

et al. 2017

View full text Add to dashboard Cite

Mobile cloud is changing the way to enroll teaching activities in university campus. Lectures and lab sessions can be carried out directly from tablets in a class room by accessing a server in the cloud. In this paper, we address the problem of high density cloud access with wireless devices in campus networks. We propose to use Wi-Fi Direct clustering to solve the problem of Quality of Service (QoS) degradation when a high number of wireless devices want to access a content in the cloud at the same time. A centralized softwaredefined network controller is used in our proposed architecture to capture the network state and organize the Wi-Fi Direct groups. The optimized number of clusters can be calculated in function of the number of devices in the room. By simulations, we show that we can provide a better QoS in terms of download time and application's throughput by reducing the interference in this dense wireless network environment.

show abstract

“…The new version of K-means, potential-K-means, which we presented in [21], is based on the following analogy with Newton's law of universal gravitation. The gravitational potential at point…”

Section: Balanced Clusteringmentioning

confidence: 99%

“…, (c k , W K )} are initialized, where W i is the total intensity of the cluster, i.e, the sum of the intensities of the pixels of the cluster. Note that a number of methods can be employed for initializing cluster centers (an study of different methods was conducted in [21]). In order to have a fair comparison with Force clustering, we use the most common and default method, random initialization, where the initial centers are simply randomly generated (and the same initial values are used in Force clustering).…”

Section: Potential-k -Means For Tumor Localizationmentioning

confidence: 99%

“…In this paper we apply our new unsupervised learning algorithm potential-K-means [21] which, while following a Physics analogy different from that of the Force method [19,20], is also based on a balancing/equilibrium criteria. The focus is on localization (coarse detection) of the tumor region and its center which are typically requisite landmarks for the subsequent fine tumor detection process of identifying the precise boundaries of the tumor.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated Localization of Brain Tumors in MRI Using Potential-K-Means Clustering Algorithm

Cabria

Gondra

2015

2015 12th Conference on Computer and Robot Vision

Self Cite

View full text Add to dashboard Cite

The manual localization and precise segmentation of brain tumors from magnetic resonance images (MRI) is time-consuming and error-prone. In T2 and FLAIR MRI, tumors appear as bright areas of higher signal intensity than their surroundings. In this paper we view the intensity of a pixel as equal to its "workload" and employ an unsupervised learning algorithm called potential-K-means that generates a balanced distribution of the pixels into clusters of approximately equal total intensity. The algorithm is based on an analogy with the gravitational force exerted by masses. This balancing requirement introduces a search bias that tends to generate either small clusters of higher intensity pixels, which overlap with the tumor area, or large clusters of lower intensity pixels. We evaluate the proposed algorithm on the publicly available brain tumor image segmentation (BRATS) MRI benchmark by comparing the center of the cluster that overlaps with the tumor, with the center of the tumor in the corresponding ground truth segmentation. We compare the proposed algorithm with the well-known K-means and with the Force clustering algorithm by Kalantari et al. (2009), which follows a different Physics analogy, but it is also based on a balancing criteria. Experimental results show that K-means is not suitable for tumor localization and that potential-Kmeans and Kalantari's approach are comparable. However, the performance of Kalantari's approach is highly dependent on a parameter whose value needs to be set a priori, but without an informed way of doing so, which makes the present proposed method more practical.

show abstract

Potential- $K$- Means for Load Balancing and Cost Minimization in Mobile Recycling Network

Cited by 12 publications

References 17 publications

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks

SDN-based Wi-Fi Direct clustering for cloud access in campus networks

Automated Localization of Brain Tumors in MRI Using Potential-K-Means Clustering Algorithm

Contact Info

Product

Resources

About