Moumita Roy

A novel approach for change detection of remotely sensed images using semi-supervised multiple classifier system

In this article, a novel approach using ensemble of semi-supervised classifiers is proposed for change detection in remotely sensed images. Unlike the other traditional methodologies for detection of changes in land-cover, the present work uses a multiple classifier system in semi-supervised (leaning) framework instead of using a single weak classifier. Iterative learning of base classifiers is continued using the selected unlabeled patterns along with a few labeled patterns. Ensemble agreement is utilized for choosing the unlabeled patterns for the next training step. Finally, each of the unlabeled patterns is assigned to a specific class by fusing the outcome of base classifiers using some combination rule. For the present investigation, multilayer perceptron (MLP), elliptical basis function neural network (EBFNN) and fuzzy k-nearest neighbor (k-nn) techniques are used as base classifiers. Experiments are carried out on multi-temporal and multi-spectral images and the results are compared with the change detection techniques using MLP, EBFNN, fuzzy k-nn, unsupervised modified self-organizing feature map and semi-supervised MLP. Results show that the proposed work has an edge over the other state-of-the-art techniques for change detection.

Semi-supervised change detection using modified self-organizing feature map neural network

In the present article, semi-supervised learning is integrated with an unsupervised context-sensitive change detection technique based on modified self-organizing feature map (MSOFM) network. In the proposed methodology, training of the MSOFM network is initially performed using only a few labeled patterns. Thereafter, the membership values, in both the classes, for each unlabeled pattern are determined using the concept of fuzzy set theory. The soft class label for each of the unlabeled patterns is then estimated using the membership values of its K nearest neighbors. Here, training of the network using the unlabeled patterns along with a few labeled patterns is carried out iteratively. A heuristic method has been suggested to select some patterns from the unlabeled ones for training. To check the effectiveness of the proposed methodology, experiments are conducted on three multi-temporal and multi-spectral data sets. Performance of the proposed work is compared with that of two unsupervised techniques, a supervised technique and two semi-supervised techniques. Results are also statistically validated using paired t-test. The proposed method produced promising results.

Land-Cover Classification of Remotely Sensed Images Using Compressive Sensing Having Severe Scarcity of Labeled Patterns

The aim of this letter is twofold. First, we assess the compressive sensing (CS) approach as a classification tool for multispectral remote sensing images, assuming severe scarcity of training samples (at most, ten for each class). Then, we propose a new strategy to perform domain adaptation using a CS approach for classifying images at large spatial scales (continental mapping). In particular, the “most confusing” training samples in the target domain are collected by exploiting plenty of training samples available in the source domain under the transfer learning framework. For assessing the proposed method, experiments are performed on three remotely sensed images captured by the Landsat 8 satellite in different regions of India. Results obtained using the proposed approach are found to be promising.

A Neural Approach Under Active Learning Mode for Change Detection in Remotely Sensed Images

In this paper, a change detection technique using neural networks in active learning framework is proposed under the scarcity of labeled patterns. In the present investigation, two variants of radial basis function neural networks and a multilayer perceptron are used as learners. Instead of training the network (or ensemble of networks) with randomly collected labeled patterns, in the proposed work, the network (or ensemble of networks) is iteratively trained with label patterns, collected using the query functions. Here, two query selection strategies are used: uncertainty sampling and query-by-committee. In this way, the most informative set of labeled patterns can be iteratively generated by querying. To evaluate the effectiveness of the proposed approach, the experiments are conducted on multi-temporal remotely sensed images. The results obtained using the proposed active learning framework are found to be encouraging.

Ensemble of Multilayer Perceptrons for Change Detection in Remotely Sensed Images

In this letter, a change detection technique using a multiple classifier system is proposed. Here, different architectures of multilayer perceptron (MLP) are used as base classifiers. An ensemble of different MLPs is utilized to increase the robustness of the system. This also avoids the problem of choosing an optimum architecture for MLP. First, the support values for each of the unlabeled patterns are estimated using different MLPs (trained with the labeled patterns). Then, each of the unlabeled patterns is assigned to a specific class by fusing the outcome of the base classifiers using different combination rules. Experiments are carried out on multitemporal and multispectral images. Results show that the proposed ensemble technique has an edge over individual base classifiers for change detection in remotely sensed images.

Search-based semi-supervised clustering algorithms for change detection in remotely sensed images

In real life change detection for remotely sensed images suffers due to the problem of inadequate labeled patterns. When a few labeled patterns can be collected by experts, semi-supervised (learning) clustering can be opted for change detection instead of the unsupervised approach to make full utilization of both labeled and unlabeled patterns. In the present work, a study has been carried out by applying some of the semi-supervised clustering techniques for changed detection. A comparative analysis between K-Means, COP-KMeans, Seeded-KMeans and Constrained-KMeans algorithms is being performed based on the results obtained using two multi-temporal remotely sensed images. It can be concluded from the experiments that the Constrained-KMeans is well suited for changed detection of remotely sensed images under semi-supervised framework.

Modified self-organizing feature map neural network with semi-supervision for change detection in remotely sensed images

Problem of change detection of remotely sensed images using insufficient labeled patterns is the main topic of present work. Here, semisupervised learning is integrated with an unsupervised context-sensitive change detection technique based on modified self-organizing feature map (MSOFM) network. In this method, training of theMSOFMis performed iteratively using unlabeled patterns along with a few labeled patterns. A method has been suggested to select unlabeled patterns for training. To check the effectiveness of the proposed methodology, experiments are carried out on two multitemporal remotely sensed images. Results are found to be encouraging.

Semi-supervised Hopfield-Type Neural Network for change detection in remotely sensed images

In this article, we propose a change detection technique using semi-supervised Hopfield-Type Neural Network (HTNN). The purpose of the work is to show the usefulness of semi-supervision over existing unsupervised/fully supervised methods when we have only a few labeled samples. Here, training of HTNN is performed iteratively using a few labeled patterns along with a number of unlabeled patterns. A method has been suggested to propagate the label information using a kind of K-nearest neighbor approach. To check the effectiveness of the proposed method, experiments are carried out on multi-temporal remotely sensed images. Results are compared with other state of the art techniques and found to be significantly better.

Designing an energy efficient WBAN routing protocol

Advancement of medical science brings together new trend of proactive health care which gives rise to the era of Wireless Body Area Networks (WBAN). A number of issues including energy efficiency, reliability, optimal use of network bandwidth need to be considered for designing any multi-hop communication protocol for WBANs. Energy consumption depends on many factors like amount and frequency of forwarding traffic, node activity, distance from sink etc. Energy consumption gives rise to other issues like heated nodes. Existing routing protocols are mostly single hop or multi-hop, and generally focus on one issue ignoring the others. In this paper, we first identify the sources of energy drain, and then propose a 2-hop cost based energy efficient routing protocol for WBAN that formulates the energy drain of a node due to various reasons and incorporates it in the routing decision. Relative node mobility due to posture change is also considered here. The protocol is simulated in Castalia simulator and compared with state of the art protocols. It is found to outperform state of the art protocols in terms of packet delivery ratio for a given transmission power level. Moreover, only a small number of relays are found to be sufficient to stabilize packet delivery ratio.

Developing Secured MANET Using Trust

Distributed nature of Mobile Adhoc NETwork (MANET) and dynamically varying topology lead to a number of security threats in MANET. Malicious behavior of the participating entity disrupts normal functioning of the network. Moreover one major problem with continuous participation of nodes in MANET is energy consumption which often leads to selfish behavior of participating entity. Here we propose a distributed trust based framework to ensure secure packet delivery in a hostile MANET. In this regard Bayesian network based trust management scheme is used to infer trust of a node using prior interaction history. Besides, we introduce an energy factor which is the ratio of remaining energy of a node to the initial energy of the same. These are merged towards aggregate trust of a node so that future behavior of a node can be anticipated more precisely. Performance is evaluated in discrete event simulation environment. Results show that the proposed scheme not only detects the malicious nodes but also improves performance of routing protocol.