Showing 5 results for Clustering
A. H. Hadjahmadi, M. M. Homayounpour, S. M. Ahadi,
Volume 8, Issue 2 (6-2012)
Abstract
Nowadays, the Fuzzy C-Means method has become one of the most popular
clustering methods based on minimization of a criterion function. However, the
performance of this clustering algorithm may be significantly degraded in the presence of
noise. This paper presents a robust clustering algorithm called Bilateral Weighted Fuzzy CMeans
(BWFCM). We used a new objective function that uses some kinds of weights for
reducing the effect of noises in clustering. Experimental results using, two artificial
datasets, five real datasets, viz., Iris, Cancer, Wine, Glass and a speech corpus used in a
GMM-based speaker identification task show that compared to three well-known clustering
algorithms, namely, the Fuzzy Possibilistic C-Means, Credibilistic Fuzzy C-Means and
Density Weighted Fuzzy C-Means, our approach is less sensitive to outliers and noises and
has an acceptable computational complexity.
H. Kiani Rad, Z. Moravej,
Volume 15, Issue 3 (9-2019)
Abstract
In this paper, a new method is conducted for incorporating the forecasted load uncertainty into the Substation Expansion Planning (SEP) problem. This method is based on the fuzzy clustering, where the location and value of each forecasted load center is modeled by employing the probability density function according to the percentage of uncertainty. After discretization of these functions, the location and value of each of the new load centers are determined based on the presented fuzzy clustering based algorithm. A Genetic Algorithm (GA) is used to solve the presented optimization problem in which the allocations and capacities of new substations as well as the expansion requirements for the existing ones are determined. With the innovative presented method, the impact of uncertainty of the power and location of the predicted loads on the results of SEP is measured, and finally, it is possible to make a proper decision for the SEP. The significant features of this method can be outlined as its applicability to large-scale networks, robustness to load changes, the comprehensiveness and also, the simplicity of applying this method to various problems. The effectiveness of proposed method is demonstrated by application on a real sub-transmission system.
A. Pathak,
Volume 16, Issue 4 (12-2020)
Abstract
It is very difficult and expensive to replace sensor node battery in wireless sensor network in many critical conditions such as bridge supervising, resource exploration in hostile locations, and wildlife safety, etc. The natural choice in such situations is to maximize network lifetime. One such approach is to divide the sensing area of wireless sensor network into clusters to achieve high energy efficiency and to prolong network lifetime. In this paper, an Artificial Bee Colony Inspired Clustering Solution (ABCICS) is introduced. The proposed protocol selects the head of the cluster with optimal fitness function. The fitness function comprises the residual energy of node, node degree, node centrality, and distance from base station to node. When cluster-head with high energy node transmits the data to the base station, it further minimizes the energy consumption of the sensor network. The presented protocol is compared with LEACH, HSA-PSO, and MHACO-UC. Simulation experiments show the effectiveness of our approach to enhance the network lifetime.
Humairah Mansor, Shazmin Aniza Abdul Shukor, Razak Wong Chen Keng, Nurul Syahirah Khalid,
Volume 21, Issue 2 (6-2025)
Abstract
Building fixtures like lighting are very important to be modelled, especially when a higher level of modelling details is required for planning indoor renovation. LIDAR is often used to capture these details due to its capability to produce dense information. However, this led to the high amount of data that needs to be processed and requires a specific method, especially to detect lighting fixtures. This work proposed a method named Size Density-Based Spatial Clustering of Applications with Noise (SDBSCAN) to detect the lighting fixtures by calculating the size of the clusters and classifying them by extracting the clusters that belong to lighting fixtures. It works based on Density-Based Spatial Clustering of Applications with Noise (DBSCAN), where geometrical features like size are incorporated to detect and classify these lighting fixtures. The final results of the detected lighting fixtures to the raw point cloud data are validated by using F1-score and IoU to determine the accuracy of the predicted object classification and the positions of the detected fixtures. The results show that the proposed method has successfully detected the lighting fixtures with scores of over 0.9. It is expected that the developed algorithm can be used to detect and classify fixtures from any 3D point cloud data representing buildings.
Zahra Memarian, Mahdi Majidi,
Volume 21, Issue 3 (8-2025)
Abstract
This paper presents a two-dimensional (2D) direction of arrival (DOA) estimation method based on the popular correlative interferometer (CI) approach, incorporating practical considerations. Leveraging the flexibility of software-defined radio (SDR) platforms, the proposed array antenna model is designed according to the specifications of a dual-channel synchronous USRP B210 receiver and an appropriate RF switch. To enhance the speed and accuracy of 2D DOA estimation for narrowband, wideband (WB), and frequency hopping (FH) signals, this study introduces a method that integrates power spectrum density (PSD) and spectrogram analysis of the receiver’s instantaneous bandwidth with an optimized filter bank, to precisely detect active frequencies and their intervals. Additionally, a fast, modified K-means clustering algorithm is developed to refine DOA estimation for FH and WB signals across multiple active subchannels. Simulation results demonstrate improved DOA estimation accuracy in multipath conditions, particularly at longer distances, with further enhancements achieved through the proposed clustering method.
