The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Band selection, by choosing a set of representative bands in hyperspectral images (HSI), is concerned to be an effective method to eliminate the “Hughes phenomenon”. In this paper, we present a global optimal clustering-based band selection (GOC) algorithm based on the hypothesis that all the bands in a cluster are continuous at their wavelengths. After the clustering result is obtained, we propose...
A framework of automatic clustering and tracking algorithm is proposed for the multipath components (MPCs) in time-variant radio channels. The algorithm is based on the channel dynamics in time domain and is able to reflect the birth and death behaviors of MPCs naturally. The proposed algorithm is validated by a ray-tracer and the spatial channel model extension simulations. Compared with other existing...
Clustering is an unsupervised learning approach that explores data and seeks groups of similar objects. Many classical clustering models such as k-means and DBSCAN are based on heuristics algorithms and suffer from local optimal solutions and numerical instability. Recently convex clustering has received increasing attentions, which leverages the sparsity inducing norms and enjoys many attractive...
The analysis of communities and their evolution in dynamic networks is a challenging research with broad applications. The recent studies have found that the overlaps between communities are more densely connected than the non-overlapping parts in some real networks. The findings are different from the present concepts of the overlapping communities. Existing methods may fail to detect this kind of...
A novel method of calculating line loss in transformer district is presented and realized by programming, which is Back Propagation (BP) network model based on Levenberg-Marquardt (LM) algorithm. Establish the characteristic index system according to electric characteristics parameters of samples. The classification of samples by K-Means clustering algorithm solves the numerical dispersion of line...
This paper presents algorithm and digital hardware design, inspired by biological spiking neural networks, to perform unsupervised, online spike-clustering with high accuracy and low-power consumption in the context of deep-brain sensing and stimulation systems. The proposed hardware contains 1220 digital neurons and 4.86k latch-based synapses, and achieves the average sorting accuracy of 91% whereas...
Cluster formation and cluster head selection are important problems in Wireless Sensor Networks (WSNs) and can drastically affect the network's communication energy dissipation. Moreover, in WSNs, the bad usage of the energy shortens the operation time of sensors and consequently the network lifetime. In this work, we propose a fuzzy-based simulation system for WSNs, in order to calculate the lifetime...
In Wireless Sensor Networks (WSNs), cluster formation and cluster head selection are critical issues. They can drastically affect the network's performance in different environments with different characteristics. In order to deal with this problem, we have proposed a Fuzzy-based system for cluster-head selection and controlling sensor speed in Wireless Sensor Networks (WSNs). The proposed system...
Internet data is massive, heterogeneous, dynamic, and data is increasingly complex. Through data mining and analysis, we are able to obtain potentially valuable information, but traditional data mining system has bottleneck in data storage and computing power. To solve the problem, by using technology of cloud computing, we design a massive web log data mining and analysis platform based on cloud...
Mining closed frequent item set(CFI) plays a fundamental role in many real-world data mining applications. However, memory requirement and computational cost have become the bottleneck of CFI mining algorithms, particularly when confronting with large scale datasets, which herewith makes mining closed frequent item set from large scale datasets a significant and challenging issue. To address the above...
Cluster formation and cluster head selection are important problems in sensor network applications and can drastically affect the network's communication energy dissipation. However, selecting the cluster head is not easy in different environments which may have different characteristics. In order to deal with this problem, we have proposed a system for controlling sensor speed in Wireless Sensor...
Cluster formation and cluster head selection are important problems in sensor network applications and can drastically affect the network's communication energy dissipation. However, selecting the cluster head is not easy in different environments which may have different characteristics. In order to deal with this problem, we have proposed an algorithm for controlling sensor speed in wireless Sensor...
Cluster formation and cluster head selection are important problems in sensor network applications and can drastically affect the network's communication energy dissipation. However, selecting the cluster head is not easy in different environments which may have different characteristics. In order to deal with this problem, we have proposed a power reduction algorithm for sensor networks based on...
Cluster formation and cluster head selection are important problems in sensor network applications and can drastically affect the network's communication energy dissipation. However, selecting the cluster head is not easy in different environments which may have different characteristics. In order to deal with this problem, we have proposed a power reduction algorithm for sensor networks based on...
Cluster formation and cluster head selection are important problems in sensor network applications and can drastically affect the network's communication energy dissipation. However, selecting of the cluster head is not easy in different environments which may have different characteristics. In order to deal with this problem, we propose a power reduction algorithm for sensor networks based on fuzzy...
Wireless sensor networks have become one of the most tempting networking technologies since it can be deployed without the need of a communication infrastructure. In general, there are some major concerns with this technology. That is, sensor node should have a long lasting system lifetime. And the system should keep the livability of nodes in a received level during the using process. In such systems...
Researched on the characteristic of the traffic flow, a new method of abnormal data detection on traffic flow based on the curve-fitting is presented. First, the historical data on traffic flow are divided into the traffic flow with high speed and the traffic flow with low speed by the clustering analysis. Then, the algorithm on the determination safety zone scope is obtained by the curve-fitting...
Parallel and distributed algorithms constitute an advanced topic in theoretical and practical computer science that has gained much interest recently. It is generally known that studying and teaching the fundamentals of parallel algorithm's concepts present a constant challenge to both learners and educators. Due to the additional abstract concepts applied in the implementation of parallel algorithms,...
In most clustered topology control algorithms of sensor networks, all the sensor nodes are clustered and the network backbone is formed by cluster head nodes and gateway nodes, while cluster nodes keep sleeping to reduce energy cost. A fault- tolerant topology control algorithm based on clustered sensor nodes is proposed in this paper, which is termed as KCCTC (K- Connected cluster topology control...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.