Article | 01-December-2014
, wavelet packet and kernel principal component analysis are used to extract the data features. Then cascaded decision is presented to improve the recognition rate of artificial neural network, by which the film thickness can be estimated accurately. With a set of tests, the results demonstrate that the method is effective. It can be widely used to take measurement of the film thickness in industrial field.
Erqing Zhang,
Pan Fu,
Kesi LI,
Xiaohui Li,
Zhongrong Zhou
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 4, 1870–1889
Article | 11-April-2018
Financial market dynamics forecasting has long been a focus of economic research. A hybridizing functional link artificial neural network (FLANN) and improved particle warm optimization (PSO) based on wavelet mutation (WM), named as IWM-PSO-FLANN, for forecasting the CSI 300 index is proposed in this paper. In the training model, it expands a wider mutation range while apply wavelet theory to the PSO, in order to exploring the solution space more effectively for better parameter solution. In
Tian Lu,
Zhongyan Li
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 173–178
Article | 01-June-2016
This paper details about the noninvasive estimation of Urea concentration in blood using near infrared spectroscopy (NIRS) and Artificial neural network based prediction model. The absorption spectrum of the urea has been studied experimentally in order to choose the wavelengths of peak absorption. For this purpose, IR absorption spectrum of 0.1M aqueous urea solution has been collected and analyzed in second overtone region of the near-infra red spectra using the Bruker tensor 27 FTIR
Swathi Ramasahayam,
Shubhajit Roy Chowdhury
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 2, 449–467
Research paper | 31-October-2017
compared with ANN (Artificial Neural Network) methodology. The results showed that ANN performed better than the ARIMA models in forecasting the prices.
Abhishek Singh,
G. C. Mishra
Statistics in Transition New Series, Volume 16 , ISSUE 1, 83–96
Article | 01-June-2015
levels. Effects of pressure, temperature and humidity have been considered. Artificial Neural Network (ANN) has been used to extract features from the output waveform of the sensors. The system has been trained and tested with patient data in the blood glucose ranges from 80 mg/dl to 180 mg/dl. Using the proposed system, the blood glucose concentration has been estimated within an error limit of ±7.5 mg/dl.
Anand Thati,
Arunangshu Biswas,
Shubhajit Roy Chowdhury,
Tapan Kumar Sau
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 2, 1244–1260
Research Article | 11-January-2018
analog array (FPAA) (Anadigm AN231E04) based hardware implementation of artificial neural network (ANN) model with minimized error in frequency drift in the range of 3.68% to about 0.64% as compared to ANN simulated results in the range of 23.07% to 0.99%. Single neuron consumes power of 206.62 mW with minimum block wise resource utilization. The proposed hardware uses all analog blocks removing the requirement of analog to digital converter and digital to analog converter, reducing significant power
Ramesh Pawase,
Dr. N.P. Futane
International Journal on Smart Sensing and Intelligent Systems, Volume 11 , ISSUE 1, 1–6
Article | 01-December-2016
Sunita Sinha,
Nirupama Mandal
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 4, 2204–2218
Research paper | 13-December-2017
This paper proposes system identification on application of nonlinear AR (NAR) based on Artificial Neural Network (ANN) for monitor of dengue infections. In building the model, three selection criteria, i.e. the final prediction error (FPE), Akaike’s Information Criteria (AIC), and Lipschitz number were used. Each of the models is divided into two approaches, which are unregularized approach and regularized approach. The findings indicate that NARMAX model with regularized approach yields
H. Abdul Rahim,
F. Ibrahim,
M. N. Taib
International Journal on Smart Sensing and Intelligent Systems, Volume 3 , ISSUE 4, 783–806
Research Article | 02-November-2017
The detection, location and sizing of transverse cracks in a composite beam, by combining damage features of Lamb wave and vibration based techniques in artificial neural network (ANN) environment, using numerical finite element model, is discussed. Four damage features, time of flight (TOF) and amplitude ratio, which are Lamb wave based features and first and second natural frequencies, which are vibration based features were used as input to ANN. The output of ANN was crack location and depth
Ramadas C.,
Krishnan Balasubramaniam,
M. Joshi,
C.V. Krishnamurthy
International Journal on Smart Sensing and Intelligent Systems, Volume 1 , ISSUE 4, 970–984
Research paper | 31-October-2017
Germanas Budnikas
Statistics in Transition New Series, Volume 16 , ISSUE 2, 309–322
Research Article | 27-December-2017
A. Che Soh,
K. K.Chow,
U. K. Mohammad Yusuf,
A. J. Ishak,
M. K. Hassan,
S. Khamis
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 2, 584–609
Research paper | 12-December-2017
relative humidity and ambient temperature by an appropriately trained Artificial Neural Network (ANN). The performance of the arrangement has been evaluated by numerical simulation studies using thermistor data from manufacturer’s table. Significantly good results have been obtained.
Debangshu Dey,
Sugata Munshi
International Journal on Smart Sensing and Intelligent Systems, Volume 3 , ISSUE 2, 217–229
Article | 01-June-2015
In this paper, we proposed to use the Efficient Indoor Thermal Time Constant (EITTC) to characterize the indoor thermal response in old buildings. Accordingly, a low cost, energy-efficient, wide-applicable indoor thermal modeling solution is developed by combining Wireless Sensor Network (WSN) and Artificial Neural Network (ANN). Experiments on both prototype and building room showed consistent results that the combination of WSN and ANN can provide accurate indoor thermal models. A linear
Yi Zhao,
Valentin Gies,
Jean-Marc Ginoux
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 2, 869–895
Research Article | 12-December-2017
Aman Tyagi,
Arrabothu Apoorv Reddy,
Jasmeet Singh,
Shubhajit Roy Chowdhury
International Journal on Smart Sensing and Intelligent Systems, Volume 4 , ISSUE 1, 94–111
research-article | 08-October-2021
Piotr OWERKO,
Jerzy KAŁUŻA,
Marek WAZOWSKI
Architecture, Civil Engineering, Environment, Volume 14 , ISSUE 3, 69–78
Research Article | 23-May-2019
models, transfer models, Artificial Neural Network, interactions between species, and single cell models. The process of creating a mathematical model requires coordination of work and the knowledge of: microbiology, statistics, mathematics, chemistry, process engineering and computer and web science. It also requires appropriate hardware and software. There are four stages in the construction of a mathematical model: planning; data collection and analysis; mathematical description; validation and
Elżbieta Rosiak,
Katarzyna Kajak-Siemaszko,
Monika Trząskowska,
Danuta Kołożyn-Krajewska
Postępy Mikrobiologii - Advancements of Microbiology, Volume 57 , ISSUE 3, 229–243
Article | 07-May-2018
algorithm is low. In allusion to the problem of poor accuracy of email classification based on naive bayes algorithm, scholars have proposed some new email classification algorithms. The email classification algorithm based on deep neural network is one kind of them. The deep neural network is an artificial neural network with full connection between layer and layer. The algorithm extracted the email feature from the training email samples and constructed a DNN with multiple hidden layers, the DNN
Wang Yawen,
Yu Fan,
Wei Yanxi
International Journal of Advanced Network, Monitoring and Controls, Volume 3 , ISSUE 2, 17–21