Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

The selection of elective courses, which best fits the student's personal choice, becomes a challenge, considering the variety of courses available at the higher education level. The traditional recommendation approach often uses collaborative filtering along with sequential pattern mining. Existing recommender systems also use ontology. However, these approaches have several limitations, including lack of availability of ratings at higher education level and lack of personalization based on student attributes. The proposed system intends to overcome these limitations by firstly extracting student personality and profile attributes and thereby generating a set of similar users by utilizing the versatile ontology. Secondly, it predicts courses based on a well-performing sequence prediction algorithm, the compact prediction tree (CPT). The results show that the proposed approach increases the accuracy in terms of precision to a tune of 0.97 and F1 measure to a tune of 0.58 when compared with existing systems which makes the proposed method more suitable for recommending courses. © 2021 IGI Global. All rights reserved.

World University root node

Department of Information Security

School of Computer Science and Engineering

Vellore Campus

International Journal on Semantic Web and Information Systems

A personalized approach to course recommendation in higher education

Diabetes Mellitus disease is said to occur when there is not proper generation of insulin in the body which is needed for proper regulation of glucose in the body. This health disorder leads to whole degradation of several organs including the heart, kidneys, eyes, nerves. Hence diabetes disease diagnosis by means of accurate prediction is vital. When such disease related data is given as input to several machine learning techniques it becomes an important classification problem. The purpose of the work done in this paper is to compare several classic machine learning algorithms including decision tree, logistic regression and ensemble methods to identify the more accurate classification algorithm for better prediction of the diabetes mellitus disease. This in turn would help for better and effective treatment.

Department of Database Systems

Journal of Computational and Theoretical Nanoscience

Comparative Study of Machine Learning Algorithms on Prediction of Diabetes Mellitus Disease

In recent years there has been an enormous increase in learning resources available online through massive open online courses and learning management systems. In this context, personalized resource recommendation has become an even more significant challenge, thereby increasing research in that direction. Recommender systems use ontology, artificial intelligence, among other techniques to provide personalized recommendations. Ontology is a way to model learners and learning resources, among others, which helps to retrieve details. This, in turn, generates more relevant materials to learners. Ontologies have benefits of reusability, reasoning ability, and supports inference mechanisms, which helps to provide enhanced recommendations. The comprehensive survey in this paper gives an overview of the research in progress using ontology to achieve personalization in recommender systems in the e-learning domain.

Computers & Education

Review of ontology-based recommender systems in e-learning

This article proposes a novel method for recognizing objects in synthetic aperture radar images. The target is initially detected using a proposed morphology-based segmentation process and is further confirmed by classifying the objects. The identified target after the proposed segmentation process is subjected to feature extraction using Zernike moments, which efficiently downsamples the features and makes them rotationally invariant. The features are classified using a tree-based method called gradient boosting. Gradient boosting, by far, has shown very promising results on various kinds of data sets. The main focus is to bring to light this kind of tree-based architecture for target recognition in satellite imagery as well as to propose a framework that reduces the overall time and improves the efficiency of the process. It outperforms the previous state-of-the-art methods for this data size. The proposed method is compared with existing techniques to measure and evaluate its performance.

VIT Unitversity

Journal of Testing and Evaluation

Morphology-Combined Gradient Boosting for Recognizing Targets in SAR Images

As big data hits the maximum number of companies in all domains, secured data transfer can be done by cryptography. With increasing threats to big data, the security must focus on to avoid the attackers from the formation of any pattern to gain access to the information. Big data deals with the linguistic data which consists of low secured data and high secured data as well. Hence, the system should focus on providing multi-fold security and should avoid high-security common to all data categories. This paper presents a hybrid model for big data that ensures data confidentiality, data integrity, access control and sequential freshness by combining three symmetric key algorithms AES, DES and blowfish for the encryption and decryption process in any desired order. Based on the level of security the combination of the algorithms can vary. This method of encryption and decryption process ensures safe data transformation between source and destination.

International Journal of Cloud Computing

A hybrid encryption method handling big data vulnerabilities

The paper focuses on the analysis of methane (CH4) and nitrous oxide (N2O) emission from paddy rice using IoT and fuzzy logic. The study of rice paddy fields brings out the fact that they are the substantial sources of greenhouse gases such as methane (CH4) and nitrous oxide (N2O). Internet of thing provides an integrated solution for data acquisition, monitoring and measuring methane (CH4) and nitrous oxide (N2O) concentration in air. The combination of IoT and fuzzy logic can be used in the development of intelligent system for pattern recognition, event prediction and decision making. Sensors deployed will provide real time data which will be pushed on centralized server where analysis is done for decision making using fuzzy logic. The researcher proposes a model which takes benefit of these technologies to monitor and analyze emission level of methane (CH4) and nitrous oxide (N2O) from the rice paddy fields.

Analysis of methane (CH4) and nitrous oxide (N2O) emission from paddy rice using IoT and fuzzy logic

Change detection is the amount of changes that can guide to more concrete understandings into essential method concerning land cover, land usage and ecological variations. This paper deals with an intelligent methodology to optimize the solution out of the solution space that improves the efficiency of the change detection process. To support the theme, an integrated semi-supervised method is designed with a focus on image fusion, semi supervised clustering and binary swarm based optimization. A new approach of handling fusion using sparse coding is referred to expand the amount of information. Using the extracted information, change detection process is carried out by a constrained <a href="https://www.sciencedirect.com/topics/computer-science/clustering-technique">clustering technique</a> to provide a solution reflecting the level of changes occurred in the region of investigation. To improve the accuracy by proposing a global optimum solution, still the result is refined through binary swarm based <a href="https://www.sciencedirect.com/topics/computer-science/process-optimization">optimization process</a> and hence the results are accelerated towards the increased level of accuracy followed by which the change map is reconstructed to show case changes prominently. To determine the accurateness of the proposed methodology quantitative and qualitative analysis has been done with different datasets. The proposed method has been evaluated with existing techniques such as k-means, AKM, FCM, ECKM and ASCC to show the efficiency and proved to be the preeminent change detection methodology compared to the state-of-art methods.

Fulltext

Journal of King Saud University - Computer and Information Sciences

Modernizing the multi-temporal multispectral remotely sensed image change detection for global maxima through binary particle swarm optimization

Image restoration is the process of cleaning of distorted image and rein- state to its original form. In remote sensing images, usually the degradation of images happens during the acquisition process of images mostly affected by blur. This paper proposes a novel remote sensing image restoration technique. The technique mainly concentrates on the parameter estimation which is used to estimate the PSF (Point Spread Function). First, the image is transformed to the frequency using Fourier transform. Then, Gaussian Low-pass filter is used to remove or eliminate some noises present in the corrupted image. Next, the PSF or degradation function is estimated using parameters estimation based on blur angle and blur length. For effectiveness and simplicity, Radon transforma- tion was used to estimate these parameters, which later were used to estimate the PSF of image. From the estimated PSF the image is restored using Wiener filter. In order to improve the quality of restored image, a post-processing process is added to enhance the image. The evaluation results shows that the proposed technique is effective and better compared to the existing techniques such as Lucy-Richardson and RSL Adaptive filters.

Remote Sensing Image Restoration for Environmental Applications Using Estimated Parameters

Skin recognition is the process of finding flesh-coloured pixels and regions in an image. It is generally used as a preliminary step to look for specific areas in the image that could possibly have human faces and limbs. There have been numerous computer vision approaches that have been developed for skin recognition. Skin segmentation assumes an important role in several applications like medical X Ray imaging (MXRI) and magnetic resonance imaging(MRI). Other applications of skin segmentation include surveillance, human computer interaction, face recognition, etc. There is no certainty that the regions detected correspond to only skin. Hence, to say that the colour of the detected region and that of the skin is the same, is a definitive. For detecting the face in the image, the regions which are not the same colour as skin can be eliminated reliably as they are not necessary for our process. A thresholding process should be used to segment the skin regions from the rest of the image as usually the skin regions would be brighter than the other regions. Among all the supervised learning algorithms, back propagation (BP) is probably the most widely used. We have used back propagation for carrying the skin segmentation of the input image. The dataset source is taken from the UCI Repository. The dataset is collected by randomly sampling R, G, B values from the images. These RGB values are then mapped to the HSV colour model for a more adaptive and effective detection. The success rate of the implementation is 94.317568%. © IAEME Publication.

International Journal of Mechanical Engineering and Technology

Skin segmentation of rgb images and adaptive recognition using hsv color model

International Journal of Engineering & Technology for Automobile Security

Crack Detection using Image Processing for Automobiles and Aircrafts

Change detection is defined as the process that helps in determining the changes associated with land use and land cover properties with reference to georegistered multitemporal remote sensing data. A unique idea of integrating sparse fusion with constrained clustering has been attempted to detect changes in multitemporal and multispectral remote sensing images in a framework called ASCC (to be pronounced as “ask”). Unlike the other traditional methods of change detection, this approach focuses on the fusion of difference images followed by a semisupervised clustering to construct a change detection map in binary form. An enhanced sparse representation is adopted to improve the performance of the fusion process by creating a locally adaptive dictionary that extracts patches from the two difference images. The reconstruction of the fused image is performed using maximum absolute coefficients of the learned dictionary. The resultant fused image is subjected to the change detection process through constrained clustering to discern the changed pixels from the unchanged pixels. To evaluate the designed solution, the method is quantified through percentage correct classification and the process is compared with the existing methods of clustering such as k-means, adaptive k-means, fuzzy C-means, and enhanced constrained k-means. The simulation results demonstrated that the designed approach performed better when compared with state-of-art change detection methods for detecting changes in multitemporal images.

Department of Software Systems

Journal of Applied Remote Sensing

Adapted sparse fusion with constrained clustering for semisupervised change detection in remotely sensed images

In remote sensing, image fusion is the process of blending two images to obtain finer details of the fused image. In this paper, an enhanced dictionary-based sparse representation (EDSR) is proposed for multitemporal image fusion. Multitemporal remote satellite images acquired on the same geographical area at different acquisition dates are merged to obtain a fused image for further analysis. Sparse representation of the image is employed in the approximation and representation of the target image. In order to improve the performance of the fusion process, a locally adaptive dictionary is created such that the dictionary contains patches extracted from both source images. The reconstruction of the image is performed using maximum absolute coefficients through the learned dictionary. The proposed EDSR technique has been compared quantitatively and qualitatively with the existing techniques, such as PCA, DWT, SWT, Ehlers, and sparse representation (SR), to evaluate its performance. The EDSR performs well in mutual information (MI) with 3.4742 and feature mutual information (FMI) with 0.4790 and provides better results in the case of degree of distortion, UIQI, and ERGAS for dataset 1 than the existing fusion methods. Experimental results on LANDSAT images revealed that the proposed technique is more effective in terms of preservation of spectral information, errors, color, and visual quality of the fused product.Keywords:<a href="https://www.tandfonline.com/keyword/Sparse+Representation">Sparse representation</a><a href="https://www.tandfonline.com/keyword/Multitemporal">multitemporal</a><a href="https://www.tandfonline.com/keyword/Image+Fusion">image fusion</a><a href="https://www.tandfonline.com/keyword/Remote+Sensing">remote sensing</a>

European Journal of Remote Sensing

Enhanced Dictionary based Sparse Representation Fusion for Multi-temporal Remote Sensing Images

Change detection is the measure of the thematic change information that can guide to more tangible insights into an underlying process involving land cover, land usage and environmental changes. This paper deals with a semi-supervised change detection approach combining sparse fusion and constrained k means clustering on multi-temporal remote sensing images taken at different timings T1 and T2. Initially a remote sensing fusion method with sparse representation over learned dictionaries is applied to the difference images. The dictionaries are learned from the difference images adaptively. The fused image is calculated by combining the sparse coefficients and the dictionary. Finally the fused image is subjected to constrained k means (CKM) clustering combining few known labelled patterns and unlabelled patterns which have been collected from experts. The enhanced (CKM) approach (ECKM) is compared with k means, adaptive k means (AKM) and fuzzy c means (FCM). Experimental results were carried out on multi-temporal remote sensing images. Results obtained using PCC and F1 measure confirms the effectiveness of the proposed approach. It is also noticed that the ECKM provides better results with less misclassification of errors as compared to k means, adaptive k means and fuzzy c means.

The Egyptian Journal of Remote Sensing and Space Science

Semi-supervised change detection approach combining sparse fusion and constrained k means for multi-temporal remote sensing images

Background/Objectives: Image fusion in remote sensing is a challenging task for fusing minute differences in multispectral images for further analysis. The objective of this paper is to propose a hybrid approach for image fusion in remotely sensed images. Methods/Statistical Analysis: The objective of this paper is accomplished by a hybrid approach combining Stationary Wavelet Transform (SWT) and sparse representation. SWT is used for pre-processing and sparse is used for fusing the multitemporal LANDSAT image. Results: Various fusion metrics like RMSE, PSNR and FMI are evaluated and the obtained results show that the proposed hybrid approach outperforms well than the existing methods. The proposed approach gives better results in terms of all the features has been fused correctly, less mean square error and high signal to noise ratio compared to the existing methods such as DWT, SWT and Ehlers. Conclusion/Application: The application of this work is mainly on multispectral multitemporal images. It can be used for change detection also can be used to fuse low resolution image with high resolution remote sensing image. Finally this approach provides an efficient fusion result compared to the traditional methods.

Indian Journal of Science and Technology

A Hybrid Approach for Fusion Combining SWT and Sparse Representation in Multispectral Images

Image fusion is a process of blending the complementary as well as the common features of a set of images, to generate a resultant image with superior information content in terms of subjective as well as objective analysis point of view. Especially in the case of remotely sensed panchromatic and multispectral images its play a vital role to help subjective and objective analysis. Many algorithms and software tools have been developed for fusing panchromatic and multispectral datasets. Also, a number of methods have been proposed and developed for the comparative evaluation of fusion results. So most of the attempts focused on the change detection which had a few limitations. Thus a trail is made to detect, discover and reveal the boundary of satellite images (Raster and spatial vector data) using a novel approach for easy detection of boundary for classifying environmental changes in this paper. In this study, methods that evaluate fusion quality are tested for different images and test sites and the analysis shows that in most cases the tested methods performs well. © 2015 IJED (CESER Publications).