Devadatta Sinha

Bio: Devadatta Sinha is an academic researcher from University of Calcutta. The author has contributed to research in topics: Concept map & Keystroke dynamics. The author has an hindex of 6, co-authored 27 publications receiving 147 citations.

Early Prediction of Students Performance using Machine Learning Techniques

Abstract: Anal Acharya, Department of Computer Science, St Xavier’s College, Kolkata, India. Devadatta Sinha, Department of Computer Science and Engineering, University of Calcutta, Kolkata, India. ABSTRACT In recent years Educational Data Mining (EDM) has emerged as a new field of research due to the development of several statistical approaches to explore data in educational context. One such application of EDM is early prediction of student results. This is necessary in higher education for identifying the “weak” students so that some form of remediation may be organized for them. In this paper a set of attributes are first defined for a group of students majoring in Computer Science in some undergraduate colleges in Kolkata. Since the numbers of attributes are reasonably high, feature selection algorithms are applied on the data set to reduce the number of features. Five classes of Machine Learning Algorithm (MLA) are then applied on this data set and it was found that the best results were obtained with the decision tree class of algorithms. It was also found that the prediction results obtained with this model are comparable with other previously developed models.

Application of Feature Selection Methods in Educational Data Mining

Abstract: recent years, web based learning has emerged as a new field of research due to growth of network and communication technology. These learning systems generate a large volume of student data. Data mining algorithms may be applied on this data set to study interesting patterns. As an example, student enrollment data and his past examination records could be used to predict his grades in the term end examination. However this prediction could mean examining a lot of features of the student data resulting in creation of a model with high computational complexity. In this context this work first defines a student data set with 309 records and 14 features collected by a survey from various graduation level students majoring in Computer Science under University of Calcutta. Different feature selection algorithms are applied on this data set. The best results are obtained by Correlation Based Feature Selection algorithm with 8 features. Subsequently classification algorithms may be applied on this feature subset for predicting student grades.

A “Mixed” Strategy for Collaborative Group Formation and Its Learning Outcomes:

Abstract: This study uses homogeneity in personal learning styles and heterogeneity in subject knowledge for collaborative learning group decomposition indicating that groups are “mixed” in nature. Homogenei...

User Authentication: Keystroke Dynamics with Soft Biometric Features

Abstract: This chapter investigates the integration of the soft biometric features, gender and age group, with the existing keystroke dynamics user authentication systems. It also investigates the probability of predicting gender and age group based on typing pattern. The main objective of this chapter is to develop a model that can identify the gender and age group of users through the way of typing on a computer keyboard and touching a computer screen for a predefined text, and it increases the accuracy by recognizing this soft biometric information as additional features in keystroke dynamics user authentication systems. The chapter further fuses the two soft biometric scores with the timing features to enhance the performance of keystroke dynamics user authentication systems. It is also observed that gender and age group information as extra features increase the user authentication performance instead of using only gender information.

An Intelligent Web-Based System for Diagnosing Student Learning Problems Using Concept Maps:

Abstract: The aim of this article is to propose a method for development of concept map in web-based environment for identifying concepts a student is deficient in after learning using traditional methods. D...

DAEN: Deep Autoencoder Networks for Hyperspectral Unmixing

Abstract: Spectral unmixing is a technique for remotely sensed image interpretation that expresses each (possibly mixed) pixel as a combination of pure spectral signatures (endmembers) and their fractional abundances. In this paper, we develop a new technique for unsupervised unmixing which is based on a deep autoencoder network (DAEN). Our newly developed DAEN consists of two parts. The first part of the network adopts stacked autoencoders (SAEs) to learn spectral signatures, so as to generate a good initialization for the unmixing process. In the second part of the network, a variational autoencoder (VAE) is employed to perform blind source separation, aimed at obtaining the endmember signatures and abundance fractions simultaneously. By taking advantage from the SAEs, the robustness of the proposed approach is remarkable as it can unmix data sets with outliers and low signal-to-noise ratio. Moreover, the multihidden layers of the VAE ensure the required constraints (nonnegativity and sum-to-one) when estimating the abundances. The effectiveness of the proposed method is evaluated using both synthetic and real hyperspectral data. When compared with other unmixing methods, the proposed approach demonstrates very competitive performance.

Object-Based Mangrove Species Classification Using Unmanned Aerial Vehicle Hyperspectral Images and Digital Surface Models

Abstract: Mangroves are one of the most important coastal wetland ecosystems, and the compositions and distributions of mangrove species are essential for conservation and restoration efforts. Many studies have explored this topic using remote sensing images that were obtained by satellite-borne and airborne sensors, which are known to be efficient for monitoring the mangrove ecosystem. With improvements in carrier platforms and sensor technology, unmanned aerial vehicles (UAVs) with high-resolution hyperspectral images in both spectral and spatial domains have been used to monitor crops, forests, and other landscapes of interest. This study aims to classify mangrove species on Qi’ao Island using object-based image analysis techniques based on UAV hyperspectral images obtained from a commercial hyperspectral imaging sensor (UHD 185) onboard a UAV platform. First, the image objects were obtained by segmenting the UAV hyperspectral image and the UAV-derived digital surface model (DSM) data. Second, spectral features, textural features, and vegetation indices (VIs) were extracted from the UAV hyperspectral image, and the UAV-derived DSM data were used to extract height information. Third, the classification and regression tree (CART) method was used to selection bands, and the correlation-based feature selection (CFS) algorithm was employed for feature reduction. Finally, the objects were classified into different mangrove species and other land covers based on their spectral and spatial characteristic differences. The classification results showed that when considering the three features (spectral features, textural features, and hyperspectral VIs), the overall classification accuracies of the two classifiers used in this paper, i.e., k-nearest neighbor (KNN) and support vector machine (SVM), were 76.12% (Kappa = 0.73) and 82.39% (Kappa = 0.801), respectively. After incorporating tree height into the classification features, the accuracy of species classification increased, and the overall classification accuracies of KNN and SVM reached 82.09% (Kappa = 0.797) and 88.66% (Kappa = 0.871), respectively. It is clear that SVM outperformed KNN for mangrove species classification. These results also suggest that height information is effective for discriminating mangrove species with similar spectral signatures, but different heights. In addition, the classification accuracy and performance of SVM can be further improved by feature reduction. The overall results provided evidence for the effectiveness and potential of UAV hyperspectral data for mangrove species identification.

Remote sensing approaches for monitoring mangrove species, structure, and biomass: Opportunities and challenges

Abstract: The mangrove ecosystem plays a vital role in the global carbon cycle, by reducing greenhouse gas emissions and mitigating the impacts of climate change. However, mangroves have been lost worldwide, resulting in substantial carbon stock losses. Additionally, some aspects of the mangrove ecosystem remain poorly characterized compared to other forest ecosystems due to practical difficulties in measuring and monitoring mangrove biomass and their carbon stocks. Without a quantitative method for effectively monitoring biophysical parameters and carbon stocks in mangroves, robust policies and actions for sustainably conserving mangroves in the context of climate change mitigation and adaptation are more difficult. In this context, remote sensing provides an important tool for monitoring mangroves and identifying attributes such as species, biomass, and carbon stocks. A wide range of studies is based on optical imagery (aerial photography, multispectral, and hyperspectral) and synthetic aperture radar (SAR) data. Remote sensing approaches have been proven effective for mapping mangrove species, estimating their biomass, and assessing changes in their extent. This review provides an overview of the techniques that are currently being used to map various attributes of mangroves, summarizes the studies that have been undertaken since 2010 on a variety of remote sensing applications for monitoring mangroves, and addresses the limitations of these studies. We see several key future directions for the potential use of remote sensing techniques combined with machine learning techniques for mapping mangrove areas and species, and evaluating their biomass and carbon stocks.