A semi supervised image classification method for satellite images is proposed in this paper.The satellite images contain enormous data that can be used in various applications.The analysis of the data is a tedious ta...A semi supervised image classification method for satellite images is proposed in this paper.The satellite images contain enormous data that can be used in various applications.The analysis of the data is a tedious task due to the amount of data and the heterogeneity of the data.Thus,in this paper,a Radial Basis Function Neural Network(RBFNN)trained using Manta Ray Foraging Optimization algorithm(MRFO)is proposed.RBFNN is a three-layer network comprising of input,output,and hidden layers that can process large amounts.The trained network can discover hidden data patterns in unseen data.The learning algorithm and seed selection play a vital role in the performance of the network.The seed selection is done using the spectral indices to further improve the performance of the network.The manta ray foraging optimization algorithm is inspired by the intelligent behaviour of manta rays.It emulates three unique foraging behaviours namelys chain,cyclone,and somersault foraging.The satellite images contain enormous amount of data and thus require exploration in large search space.The spiral movement of the MRFO algorithm enables it to explore large search spaces effectively.The proposed method is applied on pre and post flooding Landsat 8 Operational Land Imager(OLI)images of New Brunswick area.The method was applied to identify and classify the land cover changes in the area induced by flooding.The images are classified using the proposed method and a change map is developed using post classification comparison.The change map shows that a large amount of agricultural area was washed away due to flooding.The measurement of the affected area in square kilometres is also performed for mitigation activities.The results show that post flooding the area covered by water is increased whereas the vegetated area is decreased.The performance of the proposed method is done with existing state-of-the-art methods.展开更多
Space images play an important role in the Earth study as they bring the main information received from the Space Flyer Units (SFU) to help researchers. Space images’ deciphering gives the opportunity to study the te...Space images play an important role in the Earth study as they bring the main information received from the Space Flyer Units (SFU) to help researchers. Space images’ deciphering gives the opportunity to study the territory and to plot different maps. On the basis of the space image obtained from Landsat 5TM (30 m resolution, 01.09.2012 year), we managed to get a picture of the modern relief of the northern part of Inder lake. When comparing the space image with topographic maps of 1985, we succeeded to identify the dynamics of landforms change on the studied area, what has been shown on the drawn map of the relief of the Inder salt dome uplift. 14 classes, corresponding to a particular type of terrain or to a landscape complex, have been distinguished on the studied area. Inder salt dome uplift is a paradynamic conjugation, consisting of highly karsted Inder Mountains corresponding to large diapir uplift, and of the Inder Lake having a large ellipsoidal shape. Geomorphologically, the investigated territory is located on the left bank of Zhaiyk River, and presents a salt dome uplift in the form of a plateau-like hill raised above the surrounding surface from 12 to 40 m. The maximum height reaches 42.5 m (g. Suatbaytau). The crest of the Inder salt dome is composed of Low Permian sediments (rock salt with anhydrite, potassiummagnesium salts), and has an area of about 210 km2. Inder lake’s basin is represented by a tectonic depression, which is the local basis of erosion and is a drainage place of the Inder uplift karstic water. The lake area is 150 km2. Depending on the climatic conditions, the water level can vary.展开更多
The aim of this article is to develop an automatic algorithm for the classification of non stationary signals. The application context is to classify uterine electromyogram (EMG) events to prevent the onset of preterm...The aim of this article is to develop an automatic algorithm for the classification of non stationary signals. The application context is to classify uterine electromyogram (EMG) events to prevent the onset of preterm birth. The idea is to discriminate between the events by allocating them to the physiological classes: contractions, foetus motions, Alvarez or Long Duration Low Frequency waves. Our method is based on the Wavelet Packet (WP) decomposition and the choice of a best basis for classification purpose. Before classification, there is a need to detect events in the recorded signals. The discrimination criterion is based on the calculation of the ratio between intra-class variance and total variance (sum of the intra-class and inter-class variances), calculated directly from the coefficients of the selected WP. We evaluated the performance of the algorithm on real signals by using the classification methods Neural Networks (NN) and Support Vector Machines (SVM). Subband energies of the best selected WP are used as effective features. The determined best basis is applicable to a wide range of uterine EMG signals from large range of patients. In most cases, more than 85% of events are well classified whatever the term of gestation.展开更多
The remote sensing image classification has stimulated considerable interest as an effective method for better retrieving information from the rapidly increasing large volume, complex and distributed satellite remote ...The remote sensing image classification has stimulated considerable interest as an effective method for better retrieving information from the rapidly increasing large volume, complex and distributed satellite remote imaging data of large scale and cross-time, due to the increase of remote image quantities and image resolutions. In the paper, the genetic algorithms were employed to solve the weighting of the radial basis faction networks in order to improve the precision of remote sensing image classification. The remote sensing image classification was also introduced for the GIS spatial analysis and the spatial online analytical processing (OLAP), and the resulted effectiveness was demonstrated in the analysis of land utilization variation of Daqing city.展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
文摘A semi supervised image classification method for satellite images is proposed in this paper.The satellite images contain enormous data that can be used in various applications.The analysis of the data is a tedious task due to the amount of data and the heterogeneity of the data.Thus,in this paper,a Radial Basis Function Neural Network(RBFNN)trained using Manta Ray Foraging Optimization algorithm(MRFO)is proposed.RBFNN is a three-layer network comprising of input,output,and hidden layers that can process large amounts.The trained network can discover hidden data patterns in unseen data.The learning algorithm and seed selection play a vital role in the performance of the network.The seed selection is done using the spectral indices to further improve the performance of the network.The manta ray foraging optimization algorithm is inspired by the intelligent behaviour of manta rays.It emulates three unique foraging behaviours namelys chain,cyclone,and somersault foraging.The satellite images contain enormous amount of data and thus require exploration in large search space.The spiral movement of the MRFO algorithm enables it to explore large search spaces effectively.The proposed method is applied on pre and post flooding Landsat 8 Operational Land Imager(OLI)images of New Brunswick area.The method was applied to identify and classify the land cover changes in the area induced by flooding.The images are classified using the proposed method and a change map is developed using post classification comparison.The change map shows that a large amount of agricultural area was washed away due to flooding.The measurement of the affected area in square kilometres is also performed for mitigation activities.The results show that post flooding the area covered by water is increased whereas the vegetated area is decreased.The performance of the proposed method is done with existing state-of-the-art methods.
文摘Space images play an important role in the Earth study as they bring the main information received from the Space Flyer Units (SFU) to help researchers. Space images’ deciphering gives the opportunity to study the territory and to plot different maps. On the basis of the space image obtained from Landsat 5TM (30 m resolution, 01.09.2012 year), we managed to get a picture of the modern relief of the northern part of Inder lake. When comparing the space image with topographic maps of 1985, we succeeded to identify the dynamics of landforms change on the studied area, what has been shown on the drawn map of the relief of the Inder salt dome uplift. 14 classes, corresponding to a particular type of terrain or to a landscape complex, have been distinguished on the studied area. Inder salt dome uplift is a paradynamic conjugation, consisting of highly karsted Inder Mountains corresponding to large diapir uplift, and of the Inder Lake having a large ellipsoidal shape. Geomorphologically, the investigated territory is located on the left bank of Zhaiyk River, and presents a salt dome uplift in the form of a plateau-like hill raised above the surrounding surface from 12 to 40 m. The maximum height reaches 42.5 m (g. Suatbaytau). The crest of the Inder salt dome is composed of Low Permian sediments (rock salt with anhydrite, potassiummagnesium salts), and has an area of about 210 km2. Inder lake’s basin is represented by a tectonic depression, which is the local basis of erosion and is a drainage place of the Inder uplift karstic water. The lake area is 150 km2. Depending on the climatic conditions, the water level can vary.
文摘The aim of this article is to develop an automatic algorithm for the classification of non stationary signals. The application context is to classify uterine electromyogram (EMG) events to prevent the onset of preterm birth. The idea is to discriminate between the events by allocating them to the physiological classes: contractions, foetus motions, Alvarez or Long Duration Low Frequency waves. Our method is based on the Wavelet Packet (WP) decomposition and the choice of a best basis for classification purpose. Before classification, there is a need to detect events in the recorded signals. The discrimination criterion is based on the calculation of the ratio between intra-class variance and total variance (sum of the intra-class and inter-class variances), calculated directly from the coefficients of the selected WP. We evaluated the performance of the algorithm on real signals by using the classification methods Neural Networks (NN) and Support Vector Machines (SVM). Subband energies of the best selected WP are used as effective features. The determined best basis is applicable to a wide range of uterine EMG signals from large range of patients. In most cases, more than 85% of events are well classified whatever the term of gestation.
基金Sponsored by the National Natural Science Foundation of China (Grant No.40271044), Natural Science Foundation(Grant No.TK2005 -17) and Projectof Science Backbone of Heilongjiang Province(Grant No.1151G021).
文摘The remote sensing image classification has stimulated considerable interest as an effective method for better retrieving information from the rapidly increasing large volume, complex and distributed satellite remote imaging data of large scale and cross-time, due to the increase of remote image quantities and image resolutions. In the paper, the genetic algorithms were employed to solve the weighting of the radial basis faction networks in order to improve the precision of remote sensing image classification. The remote sensing image classification was also introduced for the GIS spatial analysis and the spatial online analytical processing (OLAP), and the resulted effectiveness was demonstrated in the analysis of land utilization variation of Daqing city.
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.