• International Journal of Contents
• /
• v.10 no.1
• /
• pp.18-22
• /
• 2014

Hidden nodes have a key role in the information processing of feed-forward neural networks in which inputs are processed through a series of weighted sums and nonlinear activation functions. In order to understand the role of hidden nodes, we must analyze the effect of the nonlinear activation functions on the weighted sums to hidden nodes. In this paper, we focus on the effect of nonlinear functions in a viewpoint of information theory. Under the assumption that the nonlinear activation function can be approximated piece-wise linearly, we prove that the entropy of weighted sums to hidden nodes decreases after piece-wise linear functions. Therefore, we argue that the nonlinear activation function decreases the uncertainty among hidden nodes. Furthermore, the more the hidden nodes are saturated, the more the entropy of hidden nodes decreases. Based on this result, we can say that, after successful training of feed-forward neural networks, hidden nodes tend not to be in linear regions but to be in saturated regions of activation function with the effect of uncertainty reduction.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9B
• /
• pp.1775-1784
• /
• 1999

This paper proposes a method of removing unnecessary hidden nodes by a new cost function that evaluates the variance and the mean of hidden node outputs during training. The proposed cost function makes necessary hidden nodes be activated and unnecessary hidden nodes be constants. We can remove the constant hidden nodes without performance degradation. Using the CEDAR handwritten digit recognition, we have shown that the proposed method can remove the number of hidden nodes up to 37.2%, with higher recognition rate and shorter learning time.

• Journal of Communications and Networks
• /
• v.16 no.1
• /
• pp.81-91
• /
• 2014

This paper proposes hidden-node aware grouping (HAG) algorithm to enhance the performance of institute of electrical and electronics engineers (IEEE) 802.15.4 networks when they undergo either severe collisions or frequent interferences by hidden nodes. According to the degree of measured collisions and interferences, HAG algorithm dynamically transforms IEEE 802.15.4 protocol between a contention algorithm and a contention-limited one. As a way to reduce the degree of contentions, it organizes nodes into some number of groups and assigns each group an exclusive per-group time slot during which only its member nodes compete to grab the channel. To eliminate harmful disruptions by hidden nodes, especially, it identifies hidden nodes by analyzing the received signal powers that each node reports and then places them into distinct groups. For load balancing, finally it flexibly adapts each per-group time according to the periodic average collision rate of each group. This paper also extends a conventional Markov chain model of IEEE 802.15.4 by including the deferment technique and a traffic source to more accurately evaluate the throughput of HAG algorithm under both saturated and unsaturated environments. This mathematical model and corresponding simulations predict with 6%discrepancy that HAG algorithm can improve the performance of the legacy IEEE 802.15.4 protocol, for example, even by 95% in a network that contains two hidden nodes, resulting in creation of three groups.

• The KIPS Transactions:PartC
• /
• v.16C no.1
• /
• pp.133-142
• /
• 2009

This paper proposes an analytical performance model of IEEE 802.15.4 in the presence of hidden nodes. Conventional 802.15.4 mathematical models assume ideal situations where every node can detect the transmission signal of every other nodes different from the realistic environments. Since nodes can be randomly located in real environments so that some nodes' presence is hidden from other ones, this assumption leads to wrong performance evaluation of 802.15.4. For solving this problem, we develop an extended performance model which combines the traditional 802.15.4 performance model with one for accounting the presence of hidden nodes. The extended model predicts the rapid performance degradation of 802.15.4 due to the small number of hidden nodes. The performance, for example, degrades by 62% at maximum when 5% of the total nodes are hidden. These predictions are confirmed to be equal to those of ns-2 simulations by less than 6% difference.

• The KIPS Transactions:PartC
• /
• v.16C no.3
• /
• pp.393-406
• /
• 2009

This paper introduces two functions added to the current version of ns-2 simulator for better accuracy of IEEE 802.15.4 network simulations. The first one is to automatically place hidden nodes over the ring topology in which the coordinator is centered, when the number of hidden nodes and total number of nodes is given. Collisions of signals can be distinguished into the trace file according to the ways of participation of hidden nodes. The second one is the CCA deferment algorithm described in IEEE 802.15.4-2006 standard which is not implemented in the current version of ns-2. Owing to these additional functions, we can carry out the precise analysis of the performance effects of hidden nodes and CCA deferment algorithm on 802.15.4 networks. Simulation results present at least 66% of performance degradation in throughput and drastic increase of collision probability up to 90% from 65% by just a single hidden node. Besides, 2006 standard for CCA deferment algorithm gives 19% lower collision probability and 38% higher performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.8A
• /
• pp.702-711
• /
• 2011

This paper proposes a HAG(Hidden-Node-Aware Grouping) algorithm for IEEE 802.15.4 networks to enhance the performance by eliminating collisions resulted from the hidden node problem without adopting the RTS/CTS packet exchanges. To solve the hidden node problem, the HAG algorithm organizes nodes into disjoint transmission groups by dynamically allocating hidden nodes into separate groups which take turns in a round robin way for their transmission. For dynamic group adjustment, it periodically evaluates the presence of hidden nodes based on subordinate nodes' receipt reports. To accurately measure its behavior, this paper also builds an analytical model to estimate its throughput fluctuation over various network topologies. The mathematical model along with simulation results confirmed that the HAG technique gracefully degraded the throughput of IEEE 802.15.4 networks whereas the standard IEEE 802.15.4 networks suffer severe throughput fallout as hidden nodes become populated.

• KIPS Transactions on Computer and Communication Systems
• /
• v.4 no.7
• /
• pp.235-238
• /
• 2015

IEEE 802.15.4 is the well-established standard enabling wireless connectivities among wireless sensor nodes. However, the wireless sensor networks based on IEEE 802.15.4 are inherently vulnerable to hidden nodes collision because the wireless sensor nodes have very limited communication range and battery life time. In this paper, we propose the advanced method of mitigating hidden nodes collision in IEEE 802.15.4 base wireless sensor networks by clustering sensor nodes according to channel quality information. Moreover, we deal with the problem of resource allocation for each cluster.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.125-130
• /
• 2016

The proposal of this study is a fast version of the conventional extreme learning machine (ELM), called pseudoinverse matrix decomposition based incremental ELM (PDI-ELM). One of the main problems in ELM is to determine the number of hidden nodes. In this study, the number of hidden nodes is automatically determined. The proposed model is an incremental version of ELM which adds neurons with the goal of minimization the error of the ELM network. To speed up the model the information of pseudoinverse from previous step is taken into account in the current iteration. To show the ability of the PDI-ELM, it is applied to few benchmark classification datasets in the University of California Irvine (UCI) repository. Compared to ELM learner and two other versions of incremental ELM, the proposed PDI-ELM is faster.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.26 no.1
• /
• pp.152-159
• /
• 2002

Neural networks are used to predict the sense of touch of polyurethane coated fabrics. In this study, we used the multi layer perceptron (MLP) neural networks in Neural Connection. The learning algorithm for neural networks is back-propagation algorithm. We used 29 polyurethane coated fabrics to train the neural networks and 4 samples to test the neural networks. Input variables are 17 mechanical properties measured with KES-FB system, and output variable is the sense of touch of polyurethane coated fabrics. The influence of MLF function, the number of hidden layers, and the number of hidden nodes on the prediction accuracy is investigated. The results were as follows: MLP function, the number of hidden layer and the number of hidden nodes have some influence on the prediction accuracy. In this work, tangent function, the architecture of the double hidden layers and the 24-12-hidden nodes has the best prediction accuracy with the lowest RMS error. Using the neural networks to predict the sense of touch of polyurethane coated fabrics has hotter prediction accuracy than regression approach used in our previous study.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.2
• /
• pp.246-254
• /
• 2008

In this paper, a new efficient hidden node detection method is proposed to decide whether the RTS/CTS mechanism is necessary to resolve the hidden node problem for the data transmission of each node in infrastructure mode IEEE 802.11 wireless LANs. The nodes, for which the RTS/CTS mechanism is found to be not necessary by the hidden node detection method, can transmit their data frames without performing the RTS/CTS exchange. Only the nodes, for which the RTS/CTS mechanism is found to be necessary by the hidden node detection method, perform the RTS/CTS exchange before their data frame transmissions.