A self-learning iterative weighted possibilistic fuzzy c-means clustering via adaptive fusion

Wu, Chengmao; Zhang, Xialu

doi:10.1016/j.eswa.2022.118280

Cited by 19 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, to give the transmission power consumption closer to the real environment, we will replace the calculation method of power consumption based on the Friis model [57] with various losses L greater than 1, which can measure the actual power consumption in a non-ideal communication state more accurately, and can also well reflect the WBAN data transmission environment with mixed communication channels. Then, we consider using the adaptive weight approach [58] to fuse the related items in the Equation (15). The weight given by this adaptive weight method is not fixed and inconvenient.…”

Section: Discussionmentioning

confidence: 99%

Two-Tier Cooperation Based High-Reliable and Lightweight Forwarding Strategy in Heterogeneous WBAN

Xiao

Yuan

2023

Sustainability

View full text Add to dashboard Cite

Due to the limited and difficult access to sensor energy, energy conservation has always been an important issue in wireless body area network (WBAN). How to make full use of the limited energy of heterogeneous sensors in WBAN to achieve lightweight and high-reliable data transmission has also become key to the sustainable development of telemedicine services. This paper proposes a two-tier cooperation based high-reliable and lightweight forwarding (TTCF) mechanism via minimizing the amount of transmitted data and optimizing forwarding performance, so as to improve the efficiency and reliability of WBAN and reduce system energy consumption. In TTCF, an adaptive semi-tensor product compressed sensing evolution (STPCSE) model is first constructed to minimize the amount of data to be transmitted and extend the lifetime of sensors. Then, the important factors closely related to the energy consumption of human body sensors, including sampling frequency, residual energy and their importance in the network, are analyzed and redefined, and a high-reliable and lightweight forwarding model based on a multi-factor dynamic fusion is built. Finally, the performance and energy-saving effect of TTCF in a dynamic WBAN environment are compared and analyzed. Simulation results show that the system with our TTCF always performs the best in terms of data reconstruct accuracy, cumulative delivery rata, energy consumption and throughput. For example, its cumulative delivery rate is about 12% and 20.8% higher than that of UC-MPRP and CRPBA, and its residual energy and throughput are 1.22 times and 1.41 times, 1.35 times and 1.6 times of the latter two, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Two-Tier Cooperation Based High-Reliable and Lightweight Forwarding Strategy in Heterogeneous WBAN

Xiao

Yuan

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…The algorithm was based on the approximate accuracy of equivalence granularity. An enhanced self-adaptive weighted possibilistic fuzzy clustering algorithm was proposed in [19]. Experimentation results showed the proposed algorithm performed better than the other existing possibilistic fuzzy clustering-related algorithms.…”

Section: Review Of Literaturementioning

confidence: 99%

An FPGA Library Based Design of Variable CNN Weight Compression using Resizable K-Means Clustering

Yap¹,

Rosario²,

Munchua³

2022

IJETAE

View full text Add to dashboard Cite

Convolutional Neural Networks (CNN) is a popular tool used for image recognition. In CNN architecture, a set of weights undergo a series of updating while the training process for image recognition is ongoing. These weight values can be quite a lot in memory consumption. One way to reduce memory consumption is to use a form of weight compression through weight sharing. To do this, one can quantize the weights using K-Means clustering. To use the K means Clustering algorithm, one can manually try different values of K and then choose the best value that can save the CNN memory usage and at the same time will not deteriorate the recognition ability of the CNN. The method of trying different values of K to search for the best compression rate, can be time consuming for the user. In this paper, using XILINX Virtex FPGA library, a proposed hardware model design for a CNN integrated to a resizable Kmeans Clustering Model is presented. The hardware model design highlights the elimination of the manual search for best value of K. A synthesizable hardware model for the control and data path of the integration is proposed. A Hardware Model algorithm for an automated search for the best value of K in steps of 10, is presented. The proposed integration will allow the system to work by itself, to auto search for the best compression ratio after the CNN has finished training.

show abstract

“…In order to achieve the efficient identification of Mee tea quality, the discrimination model should be constructed by a non-destructive, rapid and accurate technology. Near-infrared (NIR) spectral analysis technology has such advantages in the detection of tea and other agricultural products [ [15] , [16] , [17] , [18] ]. NIR spectroscopy was combined with swarm intelligence methods for predicting the active constituents of green tea leaves [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

“…NIR spectroscopy was applied as a non-invasive technology to identify four kinds of green tea, and the classification accuracy of support vector machine (SVM) was higher than partial least squares discriminant analysis [ 17 ]. Fourier transform near-infrared spectroscopy (FTNIR) was combined with possibilistic fuzzy discriminant c-means clustering (PFDCM) for classification of four varieties of green tea [ 18 ]. It is difficult to accurately analyze some samples with overlapped spectra or numerous interference factors by simply analyzing the peak position and intensity of the atlas, as the fact that the NIR spectra have overlapped broadband absorption due to the absorption peaks in the NIR wavelength range [ 19 ].…”

Section: Introductionmentioning

confidence: 99%

Near-infrared spectroscopy combined with fuzzy fast pseudoinverse linear discriminant analysis to discriminate mee tea grades

Wu,

Tang,

Zhou

et al. 2024

Heliyon

View full text Add to dashboard Cite

A self-learning iterative weighted possibilistic fuzzy c-means clustering via adaptive fusion

Cited by 19 publications

References 50 publications

Two-Tier Cooperation Based High-Reliable and Lightweight Forwarding Strategy in Heterogeneous WBAN

Two-Tier Cooperation Based High-Reliable and Lightweight Forwarding Strategy in Heterogeneous WBAN

An FPGA Library Based Design of Variable CNN Weight Compression using Resizable K-Means Clustering

Near-infrared spectroscopy combined with fuzzy fast pseudoinverse linear discriminant analysis to discriminate mee tea grades

Contact Info

Product

Resources

About