Advances in Fuzzy Systems

Advances in Fuzzy Systems / 2011 / Article

Research Article | Open Access

Volume 2011 |Article ID 831261 | https://doi.org/10.1155/2011/831261

Santosh Kumar Nanda, Debi Prasad Tripathy, "Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines", Advances in Fuzzy Systems, vol. 2011, Article ID 831261, 11 pages, 2011. https://doi.org/10.1155/2011/831261

Application of Functional Link Artificial Neural Network for Prediction of Machinery Noise in Opencast Mines

Academic Editor: E. E. Kerre
Received16 Dec 2010
Accepted22 Apr 2011
Published27 Jun 2011

Abstract

Functional link-based neural network models were applied to predict opencast mining machineries noise. The paper analyzes the prediction capabilities of functional link neural network based noise prediction models vis-à-vis existing statistical models. In order to find the actual noise status in opencast mines, some of the popular noise prediction models, for example, ISO-9613-2, CONCAWE, VDI, and ENM, have been applied in mining and allied industries to predict the machineries noise by considering various attenuation factors. Functional link artificial neural network (FLANN), polynomial perceptron network (PPN), and Legendre neural network (LeNN) were used to predict the machinery noise in opencast mines. The case study is based on data collected from an opencast coal mine of Orissa, India. From the present investigations, it could be concluded that the FLANN model give better noise prediction than the PPN and LeNN model.

1. Introduction

At the present time, owing to the improvements in technology through superior energy competence, higher labor output, continuous production methods, and operating flexibility, automation has also advanced rapidly in open and underground pits together with mineral processing plants. In parallel to this improvement, sources of noise and ambient noise at work place in the mining industry have increased significantly. In general, noise is generated from all most all the opencast mining operations from different fixed, mobile, and impulsive sources, thereby becoming an integral part of the mining environment. With increased mechanization, the problem of noise has got accentuated in opencast mines. Prolonged exposure of miners to the high levels of noise can cause noise-induced hearing loss besides several nonauditory health effects [1]. The impact of noise in opencast mines depends upon the sound power level of the noise generators, prevailing geomining conditions and the meteorological parameters of the mines [24]. The noise levels need to be studied as an integrated effect of the above parameters. In mining conditions the equipment conditions and environment continuously change as the mining activity progresses. Depending on their placement, the overall mining noise emanating from the mines varies in quality and level. Thus, for environmental noise prediction models, the noise level at any receiver point needs to be the resultant sound pressure level of all the noise sources.

The need for accurately predicting the level of sound emitted in opencast mines is well established. Some of the noise forecasting models used extensively in Europe are those of the German draft standard VDI-2714 outdoor sound propagation and environmental noise model (ENM) of Australia [5]. These models are generally used to predict noise in petrochemical complexes, and mines. The algorithm used in these models rely for a greater part on interpolation of experimental data which is a valid and useful technique, but their applications are limited to sites which are more or less similar to those for which the experimental data were assimilated.

A number of models were developed and extensively used for the assessment of sound pressure level and their attenuation around industrial complexes. Generally, in Indian mining industry, environmental noise model developed by RTA group, Australia is mostly used to predict noise [4, 6]. ENM was used to predict sound pressure level in mining complexes at Moonidih Project in Jharia Coalfield, Dhanbad, India [6]. The applied model output was represented as noise contours. The application of different noise prediction models was studied for various mines and petrochemical complexes and it was reported that VDI2714 model was the simplest and least complex model vis-à-vis other models [5]. VDI2714 and ISO (1996) noise prediction models were used in Assiut cement plant, Assiut cement quarry and El-Gedida mine at El-Baharia oasis of Egypt to predict noise. From the study, it was concluded that the prediction models could be used to identify the safe zones with respect to the noise level in mining and industrial plants. It was also inferred that the VDI2714 model is the simplest model for prediction of noise in mining complexes and workplace [7]. Air attenuation model was developed for noise prediction in limestone quarry and mines of Ireland. The model was used to predict attenuation in air due to absorption [8].

All the noise prediction models treat noise as a function of distance, sound power level, different form of attenuations such as geometrical absorptions, barrier effects, ground topography. Generally, these parameters are measured in the mines and best fitting models are applied to predict noise. Mathematical models are generally complex and cannot be implemented in real time systems. Additionally, they fail to predict the future parameters from current and past measurements. It has been seen that noise prediction is a nonstationary process and soft-computing techniques like fuzzy system, adaptive neural network-based fuzzy inference system (ANFIS), neural network, and so forth, have been tested for nonstationary time-series prediction nearly for two decades. There is a scope of using different soft computing techniques:  fuzzy logic, artificial neural networks, radial basis function (RBF) and so forth, for noise prediction in mines. In comparison to other soft computing techniques, functional link artificial neural network (FLANN) and Legendre Neural Network (LeNN) has less computational cost and easily implemented in hardware applications. This is the motivation on which the present research work is based.

In this paper, an attempt has been made to develop three types of functional link artificial neural network models (FLANN, PPN, and LeNN) for noise prediction of machineries used in Balaram opencast coal mine of Talcher, Orissa, India. The data assembled through surveys, measurement or knowledge to predict sound pressure level in mines is often imprecise or speculative. Since neural network-based systems are good predictive tools for imprecise and uncertainty information; therefore, the proposed approach would be the most appropriate technique for modeling the prediction of sound pressure level in opencast coal mines.

2. VDI-2714 Noise Prediction Model

In 1976, the VDI draft code 2714 “outdoor sound propagation” was issued by the VDI committee on noise reduction [5]. The sound pressure level at an environmental point is calculated from the following equation (1) : source power level re 10−12 watts, : source directivity index, : geometric spreading term including infinite hard plane coinciding with the source, : source to receiver distance, : atmospheric attenuation = , : attenuation due to meteorological conditions = : ground effects = : barrier value (0–10) = : barrier path difference, : attenuation due to woodland areas, : attenuation due to built-up areas.

Neural network (NN) represents an important paradigm for classifying patterns or approximating complex nonlinear process dynamics. These properties clearly indicate that NN exhibit some intelligent behavior, and are good candidate models for nonlinear processes, for which no perfect mathematical model is available. Neural networks have been a powerful tool for their applications for more than last two decades [913]. Multilayer perceptron (MLP), radial basis function (RBF), Support vector machine (SVM) and so forth, are the types of Neural Network Model, where these models have better prediction competence with high computational cost. Generally, these models have high computational cost due to the availability of hidden layer. To minimize the computational cost, structures like, polynomial perceptron network (PPN) [14], functional link artificial neural network (FLANN) [1518], Legendre neural network (LeNN) [19, 20] were proposed. In this paper, three types of functional based artificial neural networks have been applied to predict mining machinery noise. These include polynomial perceptron network (PPN), functional link artificial neural network (FLANN), and Legendre neural network (LeNN).

In general, the functional link-based neural network models were single-layer ANN structure possessing higher rate of convergence and lesser computational load than those of an MLP structure. The behavior and mapping ability of a PPN and its application to channel equalization is reported by Xiang et al. (1994) [14]. The mathematical expression and computational calculation is evaluated as per MLP. Figure 1(a) represents the structure of PPN. Patra originally proposed functional link artificial neural network (FLANN), and it is a novel single-layer ANN structure capable of forming arbitrarily complex decision regions by generating nonlinear decision boundaries [1518]. In FLANN, the hidden layers are removed. Further, the FLANN structure offers less computational complexity and higher convergence speed than those of an MLP because of its single-layer structure. The FLANN structure is depicted in Figure 1(b). Here, the functional expansion block makes use of a functional model comprising a subset of orthogonal sin and cos basis functions and the original pattern along with its outer products. For example, considering a two-dimensional input pattern . The enhanced pattern is obtained by using the trigonometric functions as which is then used by the network for the equalization purpose. The BP algorithm, which is used to train the network, becomes very simple because of absence of any hidden layer. Justification for the use of the trigonometric functions in the FLANN model is provided in [1518].

Structure of the Legendre neural network [19, 20] (LeNN) (Figure 1(c)) is similar to FLANN. In contrast to FLANN, in which trigonometric functions are used in the functional expansion, LeNN uses Legendre orthogonal functions. LeNN offers faster training compared to FLANN. The performance of this model may vary from problem to problem. The Legendre polynomials are denoted by , where is the order and is the argument of the polynomial. The zero and the first-order Legendre polynomials are, respectively, given by and . The higher order polynomials are given by , and so forth. Polynomials are generated by using the following mathematical expression: Similar to FLANN, the two-dimensional input pattern is enhanced to a seven dimensional pattern by Legendre functional expansion. For Legendre neural network, the training is carried out in the same manner as FLANN and PPN. In all models, supervised learning is used. As in normal artificial neural network techniques, the presence of hidden layers increases the complexity in the real-time system, therefore, FLANN and LeNN is suitably used at here due to less computational cost.

The functional link artificial neural network-based noise prediction models consist of two input parameters: sound power level and distance . The inputs patterns are , , , , , and the desired output patterns are: , , . During training period, the desired network output was calculated with VDI-2714 noise prediction model. Since the procedures of these three models were similar; therefore, one algorithm is presented here to emphasize the development of functional-based neural network-based noise prediction models. Figure 2 graphically represent the algorithm of functional-based neural network-based noise prediction models.

Step 1. Initialize the inputs distance = , (), sound power level = (), where and are the number of input pattern and an error tolerance parameter . The dimension of and should be same.

Step 2. Randomly select the initial values of the weight vectors , for , where “” is the number of functional elements.

Step 3 (Initialization). All the weights were initialized to random number and given as

Step 4 (Produce functional blocks). For FLANN the functional block is made as follows:
For PPN the functional block is made as follows:
for LeNN the functional block is made as follows: where ,  , and so forth.

Step 5 (Calculation of the system outputs). For functional based neural network models, the output was calculated as follows:

Step 6 (Calculation of the output error). The error was calculated as . It may be seen that the network produces a scalar output.

Step 7 (Updating the weight vectors). The weight matrixes are updated next using the following relationship: where is the time index and is the momentum parameter.

Step 8. If error then go to Step 8 otherwise, go to Step 3.

Step 9. After the, learning is complete, the weights were fixed, and the network can be used for testing.

5. Simulation Result and Discussion

The proposed system models for noise prediction were validated using simulation studies. The studies were carried out by using MATLAB simulation environment. For validation of the models, the noise data was collected from Balaram opencast coal mine of Mahanadi Coalfields Limited (MCL), Talcher (Orissa, India). The test data was measured using Brüel and Kjaer 2239 (Denmark) precision sound level meter. From the measured parameter, VDI-2714 gives prediction by calculating all the sound attenuations in “dB(A)” not in octave frequency band. SPL of the different machineries from the above mine was collected. These machineries include Shovel (10 m3 bucket capacity), dozer (410 HP), tipper (10 T-160 HP), grader (220 HP), and dumper (85 T).

According to Figure 2, the stepwise procedures were required to design the model. In this problem, the system is a MISO (multi input and output system) system. The system architectures of these proposed functional link-based noise prediction models are the same, whereas only the input pattern or functional blocks are different. To design these models, total number of 3200 dataset were selected. Out of 3200, 3000 dataset were selected for training process and 200 data were selected for testing process. In this proposed systems, iteration based training methods were applied. The mean square error (MSE) plot of FLANN-based noise prediction model is represented in Figure 3, where Figures 4 and 5 are represented PPN and LeNN noise prediction models. Performance of these models for 200 testing samples or validation samples was represented from Figures 6, 7, and 8.The average percentage error (APE) was used as the performance index and was calculated as

Tables 1, 2, 3, 4, and 5 summarizes the results for noise prediction by proposed models and compares it with standard VDI-2714 noise prediction model for all selected opencast machineries. From these tables it can be seen that the proposed PPN, FLANN and LeNN models provided average percentage error of 7.03, 5.68, and 8.42, respectively, for shovel. For dumper, the average percentage errors were 7.27, 5.77, and 8.20; for Grader, the APE were 9.56, 6.15, and 9.76; for Tipper, APE for three systems were 13.59, 4.36, and 10.03, respectively. The average percentage errors of the dozer were found as 10.94, 6.32, and 9.53 respectively. From the simulation studies, it was observed that the average percentage error of FLANN model was lower than the other two models.


Distance from the source (meters)Measured field data (dBA)Prediction result (dBA)Average percentage error (dBA)
VDIPPNFLANNLeNNPPNFLANNLeNN

1102.300095.6919 74.1198 88.6731 81.48717.035.688.42
2102.100095.4828 74.1198 94.3428 81.4871
398.600091.9738 74.1198 94.5178 81.4871
498.200091.5648 74.1198 89.4572 81.4871
597.500090.8559 74.1198 87.9020 81.4871
697.500090.8469 85.8609 96.5394 94.5712
796.700090.0380 85.8609 90.3449 94.5712
895.200088.5291 85.8609 93.3190 94.5712
993.300086.6202 85.8609 94.0383 94.5712
1092.400085.7113 85.8609 94.0383 94.5712
1191.500084.8025 85.8609 87.6493 94.5712
1291.500084.7937 85.8609 88.3686 94.5712
1391.300084.5848 85.8609 85.2195 94.5712
1490.400083.6760 85.8609 91.4140 94.5712
1588.800082.0672 76.5756 85.3685 85.3813
1688.400081.6585 76.5756 85.3685 85.3813
1787.900081.1497 76.5756 88.5889 85.3813
1887.100080.3410 76.5756 88.4139 85.3813
1986.700079.9323 76.5756 87.6947 85.3813
2086.300079.5236 76.5756 87.6947 85.3813
2185.700078.9149 76.5756 85.1287 85.3813
2285.200078.4063 74.3142 84.4095 85.3813
2385.300078.4976 74.3142 84.4095 85.3813
2485.500078.6890 73.2126 81.1891 85.3813
2585.500078.6804 73.2126 80.1264 82.0894
2685.300078.4718 75.3380 81.6816 82.0894
2784.700077.8632 71.4890 81.4353 82.0894
2884.200077.3547 72.2342 81.6103 82.7253
2983.800076.9461 72.2342 82.3295 82.9287
3082.700075.8376 72.2342 82.3295 82.9287


Distance from the source (meters)Measured field data (dBA)Prediction result (dBA)Average percentage error (dBA)
VDIPPNFLANNLeNNPPNFLANNLeNN

1102.400095.791974.119888.6731 81.4871
2101.300094.6828 74.1198 93.0404 81.4871
398.200091.5738 74.1198 94.5178 81.4871
497.700091.0648 74.1198 89.4572 81.4871
597.200090.5559 74.1198 87.9020 81.4871
696.800090.1469 85.8609 96.5394 94.5712
794.200087.5380 74.1198 82.7701 81.4871
894.100087.4291 85.8609 93.3190 94.5712
993.600086.9202 85.8609 94.0383 94.5712
1093.200086.5113 85.8609 94.0383 94.5712
1193.200086.5025 85.8609 84.6752 94.5712
1292.500085.7937 85.8609 85.3944 94.5712
1392.200085.4848 85.8609 86.3534 94.5712
1490.600083.8760 85.8609 88.4398 94.5712
1589.700082.9672 76.5756 85.3685 85.38137.275.778.20
1688.300081.5585 76.5756 85.3685 85.3813
1788.200081.4497 76.5756 88.5889 85.3813
1887.600080.8410 76.5756 88.4139 85.3813
1987.100080.3323 76.5756 87.6947 85.3813
2086.800080.0236 76.5756 87.6947 85.3813
2186.500079.7149 76.5756 85.1287 85.3813
2286.200079.4063 74.3142 84.4095 85.3813
2385.800078.9976 74.3142 84.4095 85.3813
2485.600078.7890 73.2126 81.1891 85.3813
2584.800077.9804 73.2126 83.1006 82.0894
2684.200077.3718 75.3380 84.6557 82.0894
2784.200077.3632 71.4890 81.4353 82.0894
2883.700076.8547 72.0592 81.6103 82.7253
2983.400076.5461 72.2342 82.3295 82.9287
3082.800075.9376 72.2342 82.3295 82.9287


Distance from the source (meters)Measured field data (dBA)Prediction result (dBA)Average percentage error (dBA)
VDIPPNFLANNLeNNPPNFLANNLeNN

1105.300098.691974.1198 89.9755 81.4871
2103.400096.7828 74.1198 95.4768 81.4871
3101.200094.5738 74.1198 92.6776 81.4871
498.700092.0648 74.1198 89.4572 81.4871
597.200090.5559 74.1198 87.9020 81.4871
695.500088.8469 74.1198 85.9905 81.4871
794.300087.6380 74.1198 82.7701 81.4871
894.100087.4291 85.8609 93.3190 94.5712
993.700087.0202 85.8609 94.0383 94.5712
1093.200086.5113 85.8609 94.0383 94.5712
1192.600085.9025 85.8609 87.6493 94.5712
1291.800085.0937 85.8609 88.3686 94.5712
1390.400083.6848 85.8609 88.1936 94.5712
1488.600081.8760 85.8609 91.4140 94.5712
1588.500081.7672 76.5756 85.3685 85.38139.566.159.76
1688.200081.4585 76.5756 85.3685 85.3813
1787.900081.1497 76.5756 88.5889 85.3813
1887.300080.5410 76.5756 88.4139 85.3813
1986.500079.7323 76.5756 87.6947 85.3813
2085.800079.0236 76.5756 87.6947 85.3813
2185.400078.6149 76.5756 85.1287 85.3813
2285.100078.3063 74.3142 84.4095 85.3813
2384.600077.7976 74.3142 84.4095 85.3813
2484.200077.3890 73.2126 81.1891 85.3813
2583.800076.9804 73.2126 83.1006 82.0894
2683.200076.3718 63.5968 74.1068 66.3679
2782.900076.0632 71.4890 81.4353 82.0894
2882.500075.6547 60.3181 71.0614 67.0982
2982.100075.2461 60.3181 71.7806 67.3327
3081.800074.9376 60.3181 71.7806 67.3327


Distance from the source (meters)Measured field data (dBA)Prediction result (dBA)Average percentage error (dBA)
VDIPPNFLANNLeNNPPNFLANNLeNN

1100.900094.291974.1198 85.6989 81.4871
299.700093.0828 74.1198 93.0404 81.4871
398.600091.9738 74.1198 94.5178 81.4871
497.500090.8648 74.1198 92.4313 81.4871
596.500089.8559 74.1198 87.9020 81.4871
696.200089.5469 85.8609 96.5394 94.5712
795.800089.1380 85.8609 93.3190 94.5712
894.800088.1291 85.8609 93.3190 94.5712
994.300087.6202 85.8609 94.0383 94.5712
1093.700087.0113 85.8609 91.0641 94.5712
1192.800086.1025 85.8609 84.6752 94.5712
1290.600083.8937 85.8609 88.3686 94.5712
1389.500082.8848 85.8609 88.1936 94.5712
1488.400081.6760 74.1198 80.8651 81.4871
1586.800080.0672 64.8344 74.8196 70.193013.594.3610.03
1686.200079.4585 64.8344 74.8196 70.1930
1785.800079.0497 64.8344 78.0400 70.1930
1885.200078.4410 64.8344 77.8650 70.1930
1985.200078.4323 64.8344 77.1458 70.1930
2084.700077.9236 64.8344 77.1458 70.1930
2184.500077.7149 64.8344 74.5798 70.1930
2283.800077.0063 62.5730 73.8606 70.1930
2383.500076.6976 62.5730 73.8606 70.1930
2483.500076.6890 61.4715 70.6402 70.1930
2583.200076.3804 61.4715 72.5517 66.3679
2682.800075.9718 63.5968 74.1068 66.3679
2782.600075.7632 59.7479 70.8864 66.3679
2882.200075.3547 60.3181 71.0614 67.0982
2982.200075.3461 60.3181 71.7806 67.3327
3082.200075.3376 72.2342 82.3295 82.9287


Distance from the source (meters)Measured field data (dBA)Prediction result (dBA)Average percentage error (dBA)
VDIPPNFLANNLeNNPPNFLANNLeNN

1100.500093.8919 74.1198 85.6989 81.4871
2100.200093.5828 74.1198 93.0404 81.4871
398.200091.5738 74.1198 94.5178 81.4871
497.500090.8648 74.1198 92.4313 81.4871
596.700090.0559 74.1198 87.9020 81.4871
695.400088.7469 74.1198 85.9905 81.4871
794.800088.1380 85.8609 93.3190 94.5712
894.200087.5291 85.8609 93.3190 94.5712
993.600086.9202 85.8609 94.0383 94.5712
1092.500085.8113 85.8609 94.0383 94.5712
1191.800085.1025 85.8609 87.6493 94.5712
1289.600082.8937 74.1198 77.8197 81.4871
1389.300082.5848 85.8609 88.1936 94.5712
1488.800082.0760 85.8609 91.4140 94.5712
1588.200081.4672 76.5756 85.3685 85.381310.946.329.53
1687.900081.1585 76.5756 85.3685 85.3813
1787.400080.6497 76.5756 88.5889 85.3813
1886.600079.8410 76.5756 88.4139 85.3813
1985.500078.7323 64.8344 77.1458 70.1930
2085.500078.7236 76.5756 87.6947 85.3813
2184.800078.0149 64.8344 74.5798 70.1930
2284.300077.5063 62.5730 73.8606 70.1930
2384.200077.3976 62.5730 73.8606 70.1930
2483.800076.9890 61.4715 70.6402 70.1930
2583.500076.6804 61.4715 72.5517 66.3679
2683.500076.6718 75.3380 84.6557 82.0894
2782.800075.9632 59.7479 70.8864 66.3679
2882.500075.6547 60.3181 71.0614 67.0982
2982.400075.5461 72.0592 82.3295 82.9287
3082.400075.5376 72.2342 82.3295 82.9287

6. Conclusion

This paper introduced the idea of designing noise prediction model for opencast mining machineries using functional link artificial neural network systems. From the present study, it was observed that the average percentage error using FLANN lower than PPN and LeNN systems for all the machineries. These functional link artificial neural network based noise prediction models can be useful tools for mining engineers to estimate the actual noise condition of the machineries accurately.

Acknowledgments

The authors like to thank the anonymous referees for their valuable comments and words of encouragement. Their comments helped to improve the clarity of this paper.

References

  1. C. Sensogut, “Occupational noise in mines and its control—a case study,” Polish Journal of Environmental Studies, vol. 16, no. 6, pp. 939–942, 2007. View at: Google Scholar
  2. K. J. Marsh, “The CONCAWE model for calculating the propagation of noise from open-air industrial plants,” Applied Acoustics, vol. 15, no. 6, pp. 411–428, 1982. View at: Publisher Site | Google Scholar
  3. K. Pathak, S. Durucan, and S. Kunimatsu, “Activity accounting technique for environmental noise assessment in mechanized surface mining,” Environmental Monitoring and Assessment, vol. 56, no. 3, pp. 241–256, 1999. View at: Publisher Site | Google Scholar
  4. N. K. Mohalik and A. K. Pal, “Development of a noise model with respect to sound propagation and its application to a mining complex,” Noise and Vibration Worldwide, vol. 33, no. 2, pp. 8–16, 2003. View at: Publisher Site | Google Scholar
  5. R. Tonin, “Estimating noise level from petrochemical plants, mines and industrial complexes,” Acoustics Australia, vol. 13, pp. 59–67, 1985. View at: Google Scholar
  6. A. K. Pal, Y. Mishra, S. Mitra, and N. C. Saxena, “Noise model for mining complex—a case discussion,” in Proceedings of the 2nd World Mining Environment Congress, pp. 1–10, Katowice, Poland, 1997. View at: Google Scholar
  7. R. E. Rabeiy, M. Mohamed, and W. Gomma, “Study on the noise prediction in mining and industrial plants,” Assiut University Bulletin for Environmental Researches, vol. 7, no. 2, pp. 77–89, 2004. View at: Google Scholar
  8. K. Pathak, S. Durucan, and A. Korre, “Development of an air attenuation model for noise prediction in surface mines and quarries,” International Journal of Surface Mining, Reclamation and Environment, vol. 14, no. 3, pp. 223–234, 2000. View at: Google Scholar
  9. J.-S. R. Jang, C.-T. Sun, and E. Mizutan, Neuro-Fuzzy and Soft Computing, Prentice Hall of India Private Limited, New Delhi, India, 2005.
  10. S. Haykin, Adaptive Filter Theory, Pearson Education, Inc., New Delhi, India, 2002.
  11. S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, Reading, Mass, USA, 1994.
  12. M. Hagan, H. Demuth, and M. Beale, Neural Network Design, Thomson Learning, New Delhi, India, 2003.
  13. K. S. Narendra and K. Parthasarathy, “Identification and control of dynamical systems using neural networks,” IEEE Transactions on Neural Networks, vol. 1, no. 1, pp. 4–27, 1990. View at: Publisher Site | Google Scholar
  14. Z. Xiang, G. Bi, and T. Le-Ngoc, “Polynomial perceptrons and their applications to fading channel equalization and co-channel interference suppression,” IEEE Transactions on Signal Processing, vol. 42, no. 9, pp. 2470–2479, 1994. View at: Publisher Site | Google Scholar
  15. J. C. Patra and R. N. Pal, “Functional link artificial neural network-based adaptive channel equalization of nonlinear channels with QAM signal,” in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, vol. 3, pp. 2081–2086, 1995. View at: Google Scholar
  16. J. C. Patra and R. N. Pal, “A functional link artificial neural network for adaptive channel equalization,” Signal Processing, vol. 43, no. 2, pp. 181–195, 1995. View at: Google Scholar
  17. J. C. Patra, R. N. Pal, R. Baliarsingh, and G. Panda, “Nonlinear channel equalization for QAM signal constellation using artificial neural networks,” IEEE Transactions on Systems, Man, and Cybernetics, Part B, vol. 29, no. 2, pp. 262–271, 1999. View at: Publisher Site | Google Scholar
  18. C. H. Chen, C. J. Lin, and C. T. Lin, “A functional-link-based neurofuzzy network for nonlinear system control,” IEEE Transactions on Fuzzy Systems, vol. 16, no. 5, pp. 1362–1378, 2008. View at: Publisher Site | Google Scholar
  19. J. C. Patra, W. C. Chin, P. K. Meher, and G. Chakraborty, “Legendre-FLANN-based nonlinear channel equalization in wireless communication system,” in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, pp. 1826–1831, Singapore, October 2008. View at: Publisher Site | Google Scholar
  20. J. C. Patra, P. K. Meher, and G. Chakraborty, “Nonlinear channel equalization for wireless communication systems using Legendre neural networks,” Signal Processing, vol. 89, no. 11, pp. 2251–2262, 2009. View at: Publisher Site | Google Scholar

Copyright © 2011 Santosh Kumar Nanda and Debi Prasad Tripathy. This is an open access articel distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


More related articles

5247 Views | 1290 Downloads | 15 Citations
 PDF Download Citation Citation
 Download other formatsMore
 Order printed copiesOrder

Related articles

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.