Article | 23-April-2018
This paper proposes a single image dehazing based on deep neural network that is to deal with haze image. In this paper, we build up a deep neural network to restore the hazy image.We test our method both objective and subjective and compare with classical method for dehazing. Our test shows that our method works better than the others in reducing Halo effect and also our method does well in restore colorful of input image. Finally, our method process faster.
Dewei Huang,
Kexin Chen,
Jianqiang Lu,
Weixing Wang
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 4, 10–14
Article | 09-April-2018
In this paper, the neural network theory is used to establish the BP neural network prediction system for the occurrence of haze. The corresponding parameters are determined by MATLAB language, and the effect of the model is tested by the prediction of Shijiazhuang area. The result shows the feasibility of the predictive model. So it’s valuable and has a bright future.
Ma Limei,
Wang Fangwei
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 2, 107–119
Research Article | 10-April-2013
A fault diagnosis method based on adaptive dynamic clone selection neural network (ADCSNN) is proposed in this paper. In this method the weights of neural network is encoded as the antibody, and the network error is considered as the antigen. The algorithm is then applied to fault detection of motor equipment. The experiments results show that the fault diagnosis method based on ADCS neural network has the capability in escaping local minimum and improving the algorithm speed, this gives better
Wu Hongbing,
Lou Peihuang,
Tang Dunbing
International Journal on Smart Sensing and Intelligent Systems, Volume 6 , ISSUE 2, 482–504
Research Article | 01-September-2014
A methodology based on multi-weights neural network (MWNN) is presented to identify faults of rolling bearing. With considerations of difficulties in analyzing rolling bearing vibration data, we analyzed how to extract time domain feature parameters of faults. Further, the time domain feature parameters extracted from fault signals are utilized to train multi-weights neural network for achieving an optimal coverage of fault feature space. Thus, faults of rolling bearing can
Yujian Qiang,
Ling Chen,
Liang Hua,
Juping Gu,
Lijun Ding,
Yuqing Liu
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 3, 1004–1023
Article | 14-October-2020
many assumptions in the training process to achieve prediction, and finally achieves air quality the accuracy of the prediction needs to be further improved. The neural network has a good approximation effect in air quality prediction. It can continuously update the newly acquired air pollutant information to the neural network, update the prediction model in time, and improve the prediction accuracy. The neural network has a strong performance in air quality prediction. Dynamic adaptability and
Wenjing Wang,
Shengquan Yang
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 3, 57–64
Article | 01-June-2015
A novel intelligent neural network control scheme which integrates the merits of fuzzy inference, neural network adaptivity and simple PID method is presented in this paper. This control method overcomes the defects existed in the traditional variable frequency induction motor driven hydraulic source, such as slow response, poor control precision, easy to overshoot. Permanent magnet synchronous motor driven constant pump hydraulic system is designed instead of common motor, energy saving, fast
Ma Yu
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 2, 1406–1423
Research Article | 27-December-2017
The ability to classify distinctive odor pattern for aromatic plants species provides significant impact in food industry especially for herbs. Each herbs species has a unique physicochemical and a distinctive odors. This project emphasizes on the techniques of artificial intelligence (AI) to distinguish distinctive odor pattern for herbs. Neural Network method has been exploited for the classification and optimization of various odor patterns. Based on AI techniques, Neural Network-based
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
Article | 30-November-2018
lime rotary kiln is the main technology workers. Through the process system on-line monitoring state parameters to predict the current product quality, and it is as the basis for the adjustment of control parameters. The quality of products is greatly influenced by artificial judgment or off-line detection.
In this paper, the ability of the neural network is used to deal with the nonlinear mapping problem, and the quality of the product is predicted based on the on-line monitoring state parameters
Lingli Zhu,
Tingzhong Wang
International Journal of Advanced Network, Monitoring and Controls, Volume 3 , ISSUE 4, 83–86
research-article | 31-August-2021
the network to understand complex ideas by building upon simpler ones. For example, a deep network can build the concept of an image of a car by combining simpler concepts, such as edges, corners, contour, and object parts [1].
Convolutional Neural Network (CNN) is one such type of deep networks. Yann LeCan carried out one of the first exercises on CNN. He taught a computer system how to recognize the differences between handwritten digits [2]. When the system chose incorrectly, he would correct
Ashray Bhandare,
Devinder Kaur
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 26–35
research-article | 06-November-2020
through a filter that lets the larvae, but not the adults, though.
To further improve Caenorhabditis fitness analysis, here we present (i) a fitness assay protocol involving separation of parental and offspring generations and (ii) an open-source model for image analysis based on a convolutional neural network (CNN). Machine learning models are very convenient for image analysis because they can be trained on a sample of pictures to analyze images of interest with a high output rate. The concept of
Joanna K. Palka,
Krzysztof Fiok,
Weronika Antoł,
Zofia M. Prokop
Journal of Nematology, Volume 52 , 1–15
Article | 01-September-2015
To identify the important attributes of complex system, which is high-dimensional and contain both discrete and continuous variables, this paper proposes a sensitivity analysis method of hierarchical hybrid fuzzy - neural network. We derive the sensitivity indexes of discrete and continuous variables through the differential method. To verify the effectiveness of our method, this study employed a man-made example and a remote sensing image classification example to test the performance of our
Xing Haihua,
Yu Xianchuan,
Hu Dan,
Dai Sha
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 3, 1837–1854
research-article | 25-August-2020
self-driving library written in Python for the implementation of the neural network. To analyze the AI aspect of the research, the paper by NVIDIA DAVE-2 (Bojarski et al., 2016) and ALVINN (Pomerleau, 1989) were the first attempts to build an operational CNN-based model.
Analyzing different research work done, this research paper uses different heterogeneous and open-source material to build the autonomous vehicle (Blaga et al., 2018; Zhang and Mahale, 2018; Tian et al., 2018). It also reports the
Avishkar Seth,
Alice James*,
Subhas C. Mukhopadhyay
International Journal on Smart Sensing and Intelligent Systems, Volume 13 , ISSUE 1, 1–17
research-article | 30-November-2020
strategy has been extensively studied and many viable solutions have been developed and proposed, for example model predictive control (MPC) (Cristea et al., 2011; Han et al., 2012; Holenda et al., 2008; Martín et al., 2012; Yang et al., 2013), PID (Du et al., 2018; Husin et al., 2020b; Samsudin et al., 2013), fuzzy and neural network (NN) control (Han et al., 2020).
However, even with the DO control strategy, the aeration cost issues persist as DO control requires aerators and turbines which are
M. H. Husin,
M. F. Rahmat,
N. A. Wahab,
M. F. M. Sabri
International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–16
Article | 16-December-2013
Usability of QR Code in Augmented Reality system has been used for digital content accessible publicly. However, QR Code in AR system still has imprecision tracking. In this article we propose merging QR Code within conventional marker and backpropagation neural network (BPNN) algorithm to recognizing QR Code Finder Pattern. The method which our chosen to approaching conventional marker. The result of BPNN testing, QRFP detected in perspective distortion with ID-encoded character length 78, 53
Gia M. Agusta,
Khodijah Hulliyah,
Arini,
Rizal Broer Bahaweres
International Journal on Smart Sensing and Intelligent Systems, Volume 6 , ISSUE 5, 1918–1948
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
research-article | 30-November-2018
Nomenclatures
SE
state estimation
PS
power system
PSN
power system networks
PSO–NN
particle swarm optimization–neural network
DPN
distribution power network
RDPSNs
radial distribution power system networks
DMS
distribution management system
GTP
graph theoretic procedure algorithm
DSSE
distribution system state estimation model
WLS
weighted least square
WLAV
weighted least absolute value
PMUs
phasor measurement units
ANN
artificial neural network
Husham Idan Hussein,
Ghassan Abdullah Salman,
Ahmed Majeed Ghadban
International Journal on Smart Sensing and Intelligent Systems
, Volume 12 , ISSUE 1, 1–10
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 | 30-November-2018
control the oil pump accurately and stably, and is easy to cause system shock. With the development of intelligent control technology, such as fuzzy control, neural network control, and sensor technology, more and more control methods and control technology become more and more mature. This paper synthesizes the advantages of simple PID control, fuzzy control does not depend on model, and neural network control is adaptive. Fuzzy neural network PID control is used to control oil pump accurately, after
Chen Gong,
Shengquan Yang
International Journal of Advanced Network, Monitoring and Controls, Volume 3 , ISSUE 4, 63–68
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
Article | 02-April-2020
;;
So far, all values of the attribute have been expressed as One-Hot form.
D.
Data Fusion
This section analyzes the problem of data fusion, that is, how to merge Large_Attributes, Small_Attributes, Interval_Attributes, and Enumerated_Attributes together. This thesis will propose a pixel-based data fusion method: first establish a pixel matrix; then use a fully connected neural network model to process the pixel matrix.
1)
Create a pixel matrix
This section aims to transform multiple attributes
Yonghui Yang
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 1, 1–8
Research Article | 27-December-2017
Aiming at the problem that changes of nonlinear dynamic resistance of stator affect the performance of speed sensorless vector control system, a hybrid computing intelligence approach is used in the identification of stator resistance of motorized spindle. The partial least squares (PLS) regression is combined with neural network to solve the problem of few samples and multi-correlation of variables in complicated data modeling. The PLS method is used to extract variable components from sample
Lixiu Zhang,
Yuhou Wu,
Ke Zhang
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 2, 781–797
Article | 01-June-2016
In order to effectively differentiate all kinds of defects inside the composites, this paper carries out testing on the internal defects of three-dimensional (3d) braided composites by use of acoustic emission nondestructive detecting technology. It puts forward the processing method for acoustic emission signals for the internal defects of three-dimensional braided composites based on wavelet neural network (WNN). This method does wavelet transformation on real-time collected acoustic emission
Su Hua,
Zhang Tianyuan,
Zhang Ning
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 2, 780–798
research-article | 22-June-2021
-based sentiment analysis (ABSA) has gained much attention in the last decade, and it continues a thrust area of research. Various studies have shown the effectiveness of recurrent neural network-based models for the sentiment classification task in the recent past. Different hybrid models are proposed, which use convolution neural network (CNN) and LSTM for the classification task.
Now the research question/direction that comes out is to propose an efficient deep neural network model for the
Nikhlesh Pathik,
Pragya Shukla
International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–12
Article | 01-September-2015
This paper focuses on the problem of lateral stability of four hub-motor-in-wheels drive electric vehicle, 7 DOF (degrees of freedom) vehicle simulation model which is verified by field test is established based on Matlab/Simulink software. On basis of simulated model, BP neural network PID torque distribution controller of lateral stability is proposed. The sideslip angle at mass center and yaw rate are selected as the control variables, and the BP neural network PID torque distribution
Biao Jin,
Chuanyang Sun,
Xin Zhang
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 3, 1855–1875
Article | 10-April-2018
Aiming at the problem that the micro drills is easy to be broken in the process of drilling; it is difficult to detect the drill bit. The drilling torque signal is taken as the monitoring object. A new method for the on-line monitoring the micro-drill breakage based on BP neural network is proposed. After the three layer wavelet decomposition of the drilling torque signal, the energy feature vector is used as the input layer of the BP network, and the mapping model of the working state and the
Yanhong Sun,
Mei Tian
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 4, 142–146
Article | 11-April-2018
This paper focuses on the effective analysis of the mine gas emission monitoring data, so as to realize the accurate and reliable mine gas emission prediction. Firstly, a weighted multiple computing models based on parametric t– norm is constructed. And a new mine gas emission combination forecasting method is proposed. The BP neural network model and the support vector machine were used as the single prediction models. Finally, genetic algorithm and least square method were used to
Liang Rong,
Chang Xintan,
Jia Pengtao,
Dong Dingwen
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 194–198
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
Research Article | 24-February-2017
prediction models in the package of Statistics are Exponential, ARIMA and Neural Network approaches. The primary target for a predictive scenario in the data mining workspace is to provide modelling data faster and with more versatility than the other management techniques.
Anastasiia KUPTCOVA,
Petr PRŮŠA,
Gabriel FEDORKO,
Vieroslav MOLNÁR
Transport Problems, Volume 11 , ISSUE 3, 21–31
Article | 08-April-2018
Aiming at the issues of random delay and delay uncertainty in both the before channel and feedback channel for network control system, the root causes of random delay influence closed-loop control system by case is analysis, and the predictive control method based on neural network to solve the feasibility of existence network random delay in control system closed-loop control has provided. Simulation results show that the method can reflect and predict the delay characteristics of between
Xu Shuping,
Chen Yiwei,
Cheng Xinhua,
Su Xiaohui
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 1, 38–48
Article | 30-November-2020
blind deblurring. Blind defuzzification is the current mainstream technology. The principle is not to rely on fuzzy kernel estimation, and to adjust the weight parameters and loss function by constructing a neural network to achieve the effect of the convergence of the objective function. In the process of non-blind deblurring, false contours will appear due to the inaccurate estimation of the blur kernel, and a large amount of noise will be present in the image, which will bring great difficulties
Xu Hexin,
Zhao Li,
Jiao Yan
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 57–67
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
Article | 01-September-2015
Capacitive differential pressure sensor (CPS), which converts an input differential pressure to an output current, is extremely used in different industries. Since the accuracy of CPS is limited due to ambient temperature variations and nonlinear dependency of input and output, compensation is necessary in industries that are sensitive to pressure measurement. This paper proposes a framework for designing of CPS compensation system based on Multi Layer Perceptron (MLP) neural network. Firstly
Payman Moallem,
Mohammad Ali Abdollahi,
S. Mehdi Hashemi
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 3, 1443–1463
Article | 30-November-2018
control systems that are experiencing another problem. This paper based on the method of modify the control parameters of PID values to improve the stability of the remote control system, and propose intelligent remote control system design methods with adaptive function under a random delay based on neural network theory.
III.
QUESTION ANALYSIS
Remote control single-link manipulator, set the sampling period in figure 1 is 0.05s, and take the delay value of 0.05s, the control information in time k
Xu Shuping,
Wang Shuang,
Guo yu,
Su Xiaohui
International Journal of Advanced Network, Monitoring and Controls, Volume 4 , ISSUE 4, 30–37
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
Article | 30-November-2018
designed manually (such as SIFT, SURF, HOG, etc.), and the features of the artificial design are well interpreted. However, in the face of complex backgrounds, changing fonts and various deformations, it is rather troublesome and difficult to extract more general features[7].
The Convolutional Neural Network (CNN) is a multi-layered supervised learning neural network. Although the training process requires a large amount of data compared with the traditional method, the convolutional neural network can
Haoqi Yang,
Hongge Yao
International Journal of Advanced Network, Monitoring and Controls, Volume 4 , ISSUE 3, 47–52
Research Article | 01-June-2017
The literature indicates that exchange rates are largely unforecastable from the fact that the overwhelming majority of studies have employed linear models in forecasting exchange rates. In this paper, we applied Radial Basis Function Neural Network (RBFNN) to predict exchange rate, motived by the fact that RBFNN have the ability to implicitly detect complex nonlinear relationships between dependent and independent variables as it “learns” the relationship inherent in the exchange rate data
AI SUN,
JUI-FANG CHANG
International Journal on Smart Sensing and Intelligent Systems, Volume 10 , ISSUE 2, 308–326
Research Article | 13-December-2017
tracking system using multiple mobile sensors. For the purposes of surveillance and security, trackers use an Extended Kohonen neural network to track the moving targets in their environments. The proposed tracking algorithm can be used for single and multiple target tracking. A clustering algorithm is used in order to minimize the number of active trackers over time and hence save energy. An auction based algorithm is used for the purpose of optimizing the cooperation between trackers. Quantitative
Ahmed M. Elmogy,
Fakhreddine O. Karray
International Journal on Smart Sensing and Intelligent Systems, Volume 1 , ISSUE 3, 716–734
Research paper | 31-October-2017
suggested in the paper uses the following techniques: Business Process Modelling for formalisation of user online activity; Google Analytics tracking code function for gathering statistical data about user online activities; Naïve Bayes classifier and a feedforward neural network for a classification of online patterns of user behaviour as well as for an estimation of a website component that has the highest impact on a fulfilment of business objective by a user and which will be advised to be looked at
Germanas Budnikas
Statistics in Transition New Series, Volume 16 , ISSUE 2, 309–322
Research Article | 20-February-2013
Based on the analysis for the present research on controlling urban trunk road, a intelligent control method for urban trunk road based on wireless sensor and fuzzy neural network was proposed. In this method, we took two layers of WSN structure. The first one was data collecting layer, which consisted of traffic information collecting nodes and sink nodes. Data collecting layer was responsible for collecting vehicle information at single crossing, transmitted to the second layer after data
Peng Xiaohong,
Mo Zhi,
Liao Riyao
International Journal on Smart Sensing and Intelligent Systems, Volume 6 , ISSUE 1, 352–367
Research Article | 01-March-2017
This paper proposes a soft sensor to estimate phase flow rates utilizing common measurements in oil and gas production wells. The developed system addresses the limited production monitoring due to using common metering facilities. It offers a cost-effective solution to meet real-time monitoring demands, reduces operational and maintenance costs, and acts as a back-up to multiphase flow meters. The soft sensor is developed using feed-forward neural network, and generalization and network
Tareq Aziz AL-Qutami,
Rosdiazli Ibrahim,
Idris Ismail,
Mohd Azmin Ishak
International Journal on Smart Sensing and Intelligent Systems, Volume 10 , ISSUE 1, 199–222
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
research-article | 31-August-2021
and visual cues in form of features to be used with Convolutional Neural Network for attaining good performance in the fine-grained classification [1, 28] of soft drinks. To the best of our knowledge, it is a unique application of a classification technique in the domain of fine-grained image classification of soft drink datasets.
The second section of this paper discusses the proposed classification technique, the third section involves results and discussion and conclusions are drawn in the last
Zaryab Shaker,
Xiao Feng,
Muhammad Adeel Ahmed Tahir
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 42–49
Article | 01-December-2016
Sunita Sinha,
Nirupama Mandal
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 4, 2204–2218
Research Article | 27-December-2017
In order to improve the measurement accuracy of three-dimensional (3D) scanning robot, a method of 3D scanning robot system error modeling and compensation based on particle swarm optimization radial basis function neural network (PSO-RBFNN) is proposed to achieve intelligent compensation of measurement error. The structure, calibration and error modeling process of 3D scanning robot system are mainly described. Cleverly using the iterative closest point (ICP) algorithm to construct
Jianhong Qi,
Jinda Cai
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 2, 837–855
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
Article | 01-September-2015
into a sensor chamber; a water bath module for preparing rice sample, said water bath module including a heater attachment to facilitate cooking; a computing module to quantify the aroma data acquired by sensors; data acquisition module etc. Principal Component Analysis (PCA) implemented for clustering the data sets acquired from sensor array. Also data generated from sensor array was fed to Probabilistic Neural Network (PNN), Back-propagation Multilayer Perceptron (BPMLP) and Linear Discriminant
Arun Jana,
Nabarun Bhattacharyya,
Rajib Bandyopadhyay,
Bipan Tudu,
Subhankar Mukherjee,
Devdulal Ghosh,
Jayanta Kumar Roy
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 3, 1730–1747
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
Article | 09-April-2018
This paper presents a new method of recognition of lidar cloud point images based on convolutional neural network. This experiment uses 3D CAD ModelNet, and generates 3D point cloud data by simulating the scanning process of lidar. The data is divided into cells, and the distance is represented by gray values. Finally, the data is stored as grayscale images. Changing the number of cells dividing point cloud results in different experimental results. Experiments show that the proposed method has
Yang Wenhui,
Yu Fan
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 158–162
Article | 07-May-2018
Ma Xing,
Yu Fan,
Yu Haige,
Wei Yanxi,
Yang Wenhui
International Journal of Advanced Network, Monitoring and Controls, Volume 3 , ISSUE 1, 19–22
Research Article | 15-February-2020
gas sensors with different chemical affinity towards VOC molecules. The sensitivity of the elaborated QCMbased sensors was evaluated by monitoring the frequency shifts of the quartz exposed to different concentrations of volatile organic compounds, such as; ethanol, benzene and chloroform. The sensors responses data have been used for the identification and quantification of VOCs. The principal component analysis (PCA) and the neural-network (NNs) pattern recognition analysis were used for the
Omar C. Lezzar,
A. Bellel,
M. Boutamine,
S. Sahli,
Y. Segui,
P. Raynaud
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 5, 1–6
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 Article | 27-December-2017
B. Mulliez,
E. Moutaye,
H. Tap,
L Gatet,
F. Gizard
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 1, 400–420
Article | 30-November-2020
and statistics, namely deep convolutional neural networks (CNNs), was proposed by Proenca and was also used to build periocular recognition systems. At the same time, Canadian professor Hugo. Proenca [5] also proposed to use neural network to process the human eye areas outside the eye, and to take the features extracted from these areas as a mode of identity recognition and attribute recognition.
In order to solve the problem of angular rotation of eyes in practical application, this paper
Bo Liu,
Songze Lei,
Yonggang Li,
Aokui Shan,
Baihua Dong
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 11–17
Article | 11-April-2018
In this paper, Self-adaptive Differential Evolutionary Extreme Learning Machine (SaDE-ELM) was proposed as a new class of learning algorithm for single-hidden layer feed forward neural network (SLFN). In order to achieve good generalization performance, SaDE-ELM calculates the error on a subset of testing data for parameter optimization. Since SaDE-ELM employs extra data for validation to avoid the over fitting problem, more samples are needed for model training. In this paper, the cross
Junhua Ku,
Kongduo Xing
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 3, 72–77
Article | 01-December-2012
Zheng LI
International Journal on Smart Sensing and Intelligent Systems, Volume 5 , ISSUE 4, 911–927
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
Research Article | 13-December-2017
Mohd Fuaad Rahmat,
Herman Wahid,
Norhaliza Abdul Wahab
International Journal on Smart Sensing and Intelligent Systems, Volume 3 , ISSUE 1, 45–60
Article | 02-April-2020
, the traditional survey situation is that the site construction surveyors scan the survey images generated by radar equipment one by one according to their expert knowledge. This traditional method has a large workload, a large human factor, and a certain rate of omission and error.
In recent years, with the continuous improvement of GPU, the field of deep learning is booming. In 2006, Hinton[4] and other researcher proposed the concept of deep learning, using convolutional neural network (CNN) to
He Li,
Yubian Wang
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 1, 44–53
Article | 14-October-2020
that can obtain high reward values in the environment, and find the best strategy to solve the problem in such constant interaction. Based on this idea, this paper use reinforcement learning technology to simulate the human visual attention mechanism. The agent is taught to change the shape of the bounding box and focus only on a significant part of the image at a time, and then extract its features through the convolutional neural network. Finally, the object of image positioning and
Wei Zhang,
Hongge Yao,
Yuxing Tan
International Journal of Advanced Network, Monitoring and Controls, Volume 5 , ISSUE 3, 65–72
Article | 30-November-2020
architecture of the network control system continues to change, the current method is largely concentrated in the condition of network delay is no more than one sampling period, and other cases have yet to be depth.
Self-learning and adaptive capacity of neural network made the neural network model predictive control applications and research gaining increasing attention in the control system, and the prediction control based on neural network has strong robustness can adapt to the changing of system
Xu Shuping,
Wu Jinfe,
Su Xiaohui,
Xiong Xiaodun
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 1, 1–10
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
obtained with the use of the 7-9-1 neural network, which turned out to be effective in both analyzed aspects. Studying Fig. 6a and 6b, it can be seen that the broken line representing the results of the 7-9-1 network is very similar in shape to the in-situ results. However, models with a greater number of hidden layers should not be disqualified, especially in the planned, future analyzes based on a significantly larger set of data and training parameters.
6.
CONCLUSIONS
A few decades ago, hardly
Piotr OWERKO,
Jerzy KAŁUŻA,
Marek WAZOWSKI
Architecture, Civil Engineering, Environment, Volume 14 , ISSUE 3, 69–78
Article | 03-November-2017
Dr.R HariKumar,
T. Vijayakumar
International Journal on Smart Sensing and Intelligent Systems, Volume 2 , ISSUE 4, 612–635
Article | 01-September-2016
components of the localization information, and then regarding the nonlinear principal components extracted from distance vectors as the input samples, and meanwhile taking the coordinates of vertices in addition to the region boundary as the output samples, the PSO-BP neural network is trained to achieve the localization model. Finally the localization of unknown nodes can be estimated. The simulation experiment result showed that the method has high ability of stability and precision, and meets the
Wang Jun,
Zhang Fu,
Ren Tiansi,
Chen Xun,
Liu Gang
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 3, 1323–1340
Research Article | 12-September-2018
Abstract
The success of an Electrocardiogram (ECG) Decision Support System (DSS) requires the use of an optimum machine learning approach. For this purpose, this paper investigates the use of three feedforward neural networks; the Multilayer Perceptron (MLP), the Radial Basic Function Network (RBF), and the Probabilistic Neural Network (PNN) for recognition of normal and abnormal heartbeats. Feature sets were based on ECG morphology and Discrete Wavelet Transformer (DWT) coefficients. Then, a
Hela Lassoued,
Raouf Ketata,
Slim Yacoub
International Journal on Smart Sensing and Intelligent Systems, Volume 11 , ISSUE 1, 1–15
Research Article | 30-April-2018
Abstract
This research aims at develop an MTB detection model from the FLVQ neural network to HGA-FLVQ model. In this research, the FLVQ method was developed through strengthening its initiation, in which the first cluster centers used as FLVQ input were optimized first by HGA. The results show that sensitivity and specificity of the HGA-FLVQ model reach 96.30 and 95.65%, whereas the sensitivity of an FLVQ method is 70.83%, and the sensitivity of an LVQ method is 87.50%. The specificity of an
N. Charibaldi,
A. Harjoko,
B. Hisyam
International Journal on Smart Sensing and Intelligent Systems, Volume 11 , ISSUE 1, 1–13
Article | 09-April-2018
This paper presented the research on heat load prediction method of central heating system. The combined simulation data at Xi'an in January was used as the samples for training and predicting. This paper selected the daily average outdoor wind speed, the daily average outdoor temperature, date type, sunshine duration as input variables and the heating load value as output variable. After preprocessing of the historical data, the BP neural network algorithm and the GA-BP algorithm were
Bingqing Guo,
Jin Xu,
Ling Cheng,
Lei Chen
International Journal of Advanced Network, Monitoring and Controls, Volume 2 , ISSUE 4, 137–141
research-article | 30-November-2020
achieve information transfer. For the general neural network structure at this stage, the output of each layer of neurons is a scalar result, and the scalar data contains limited information. Correspondingly, if the output is a vector, the output generated can more accurately represent the posture, etc. Related Information. The capsule network implements this theory, and the capsule is equivariant. Different inputs of the capsule network will have different outputs. When the same object changes, such
Yan Jiao,
Li Zhao,
Hexin Xu
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 2, 1–8
Research Article | 15-February-2020
Goutam Chakraborty,
Tetsuhiro Dendou
International Journal on Smart Sensing and Intelligent Systems, Volume 7 , ISSUE 5, 1–6
research-article | 25-October-2021
inspection (Nakhaeinia et al., 2016), license plate recognition (Bennet et al., 2017). All these works presented here, only focused on pre and post-operative diagnosis using magnetic resonance imaging, computer tomography scans, ultrasound images. None of the papers consider real-time surgical images to identify tumors. This paper will address this issue and propose using convolutional neural network (YOLOv4 at first, then optimized VGG-16) for giving the surgeons a second opinion during real time tumor
Rohan Ibn Azad,
Subhas Mukhopadhyay,
Mohsen Asadnia
International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–16
Article | 01-March-2015
Shweta Sinha,
Aruna Jain,
S. S. Agrawal
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 1, 235–254
Article | 02-November-2017
different normalization techniques were applied on electronic nose data. Finally the comparison of classification accuracy is presented with different normalization techniques using back-propagation multilayer perceptron (BP-MLP) neural network.
Bipan Tudu,
Bikram Kow,
Nabarun Bhattacharyya,
Rajib Bandyopadhyay
International Journal on Smart Sensing and Intelligent Systems, Volume 2 , ISSUE 1, 176–189
Article | 01-September-2015
through the modeling of the physical auditory system and the biological neural network of the primary auditory cortex using artificial neural networks. The behavior of artificial neural networks both during and after the training process has also been found to mimic that of biological neural networks and this method will be shown to have certain advantages over previous methods in the modeling of auditory perception. This work will describe the nature of artificial neural networks and investigate
D. Riordan,
P. Doody,
J. Walsh
International Journal on Smart Sensing and Intelligent Systems, Volume 8 , ISSUE 3, 1806–1836
research-article | 31-August-2021
Davy [1] et al. converts lane processing into an end-to-end instance segmentation problem, using a lightweight ENet network as the main structure and adding instance segmentation branches to classify different lanes into different categories. XingGang Pan[2] et al. proposed a spatially based deep neural network SCNN (Spacial CNN), which was trained to classify the network for the poorly conditioned dataset CULane, and the network performance was substantially improved in lane detection compared to
Jiaqi Shi,
Li Zhao
International Journal of Advanced Network, Monitoring and Controls, Volume 6 , ISSUE 3, 1–8
Article | 01-December-2012
and evaluated against existing solutions in the literature. A novel adaptive algorithm then chooses the best weighting scheme based on a similarity error to ensure the best performance of the attention model in a given context. Finally, a neural network is trained to predict the set of weights provided by the best weighting scheme for the context of the image in which buildings are to be detected. The solution provides encouraging results on a set of 50 satellite images.
A.-M. Cretu,
P. Payeur
International Journal on Smart Sensing and Intelligent Systems, Volume 5 , ISSUE 4, 742–766
Research paper | 10-April-2013
, Least Squares Support Vector Machines (LS-SVM) is introduced. In order to estimate the effectiveness of feature selection algorithm, the comparative analysis among Fisher Score (FS) Information Gain (IG) and SVM-RFE is exploited to real milling datasets. The identification result proves that: The selected feature set based on SVM-RFE is more effective to recognize tool wear state; LS-SVM wear identification method is superior to BP neural network, and it has higher identification accuracy; the
Weilin Li,
Pan Fu,
Weiqing Cao
International Journal on Smart Sensing and Intelligent Systems, Volume 6 , ISSUE 2, 448–465
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
Research paper | 25-July-2017
The brain as a system with gradually declining resources by age maximizes its performance by neural network reorganization for greater efficiency of neuronal processes which is reflected in changes of event-related band responses (ERBRs) for sensory stimuli. Whether changes of high-frequency components of event-related responses are related to plasticity in neural recruitment during stabilization of sensory/cognitive mechanisms accompanying aging or are underlying pathological changes remains
Mario Christov,
Juliana Dushanova
Acta Neurobiologiae Experimentalis, Volume 76 , ISSUE 2, 98–109
research-article | 30-November-2020
scheme was proposed (Naeem et al., 2019) and the architecture consists of an access router (AR), roadside unit (RSU), and vehicles. This work defines two HO schemes as inter-AR HO and intra-AR HO. The key goal of this scheme was to minimize latency and improve the packet delivery ratio. A fuzzy logic model and Elman Neural Network (ANN) was designed to decide along with the assurance of QoS (Naeem et al., 2019). For HO decisions, the parameters that are taken into account as cost, transmission range
Shaik Mazhar Hussain,
Kamaludin Mohamad Yusof,
Shaik Ashfaq Hussain,
Rolito Asuncion
International Journal on Smart Sensing and Intelligent Systems, Volume 14 , ISSUE 1, 1–16
Article | 01-June-2016
Amitava Akuli,
Abhra Pal,
Gopinath Bej,
Tamal Dey,
Arunangshu Ghosh,
Bipan Tudu,
Nabarun Bhattacharyya,
Rajib Bandyopadhyay
International Journal on Smart Sensing and Intelligent Systems, Volume 9 , ISSUE 2, 709–731