Search

Project-based learning (PjBL) is one of the most predominantly practiced forms of active learning pedagogy in higher education. PjBL framework provides an authenticated platform/forum for 21st-century learners to acquire skills for solving real-life complex engineering problems through collaborative and iterative learning. The work presented in this paper describes a PjBL approach implemented as an instructional pedagogy and for a summative assessment of an undergraduate (UG) course on Digital Signal Processing (DSP). Students from Electronics and Telecommunication Department study this course in Third Year Engineering as a core course. The projects are chosen to make students identify and resolve real-life signal processing problems utilizing their subject knowledge and programming skills. PjBL implementation framework and rubrics-based evaluation devised for their summative assessment are discussed along with a study case. Student feedback analysis on the attainment of course outcomes and skills enhanced after completion of the course project is discussed. Through this analysis, it has been found that the effectiveness of the PjBL pedagogy employed has led to increasing students' engagement and interest in learning signal processing topics. It has also grown their self-learning ability and created awareness about the practical applications of the Digital Signal Processing course. [ABSTRACT FROM AUTHOR]

Outcome-based education (OBE) is the buzzword these days in the education field which boosts students' creativity through their active engagement in learning course contents. Their participatory learning in the OBE model is well supported by making them aware of learning goals and course outcomes. Due to this, the students develop themselves nicely in their working surroundings along with peers. This helps develop their interpersonal skills along with improving academic performance. This paper primarily outlines the implementation of a few key standards of OBE in teaching-learning of two fundamental courses in Electronics and Telecommunication Engineering. It then covers how OBE, and its consequences demand paradigm shifts in instructional design and evaluation practices. The discussion on OBE for courses on Digital Communication and Digital Signal Processing is explored with Program-Outcomes (POs), Program-Specific-Outcomes (PSOs), besides Course-Outcomes (COs). Analysis of POs along with COs attainment for these two courses reflects the importance of the OBE framework. The inclusion of engineering pedagogy and active learning strategies in this framework leads to enhancing students' creativity leading to their growth in their professional careers. [ABSTRACT FROM AUTHOR]

Outcome-based education (OBE) is the buzzword these days in the education field which boosts students’ creativity through their active engagement in learning course contents. Their participatory learning in the OBE model is well supported by making them aware of learning goals and course outcomes. Due to this, the students develop themselves nicely in their working surroundings along with peers. This helps develop their interpersonal skills along with improving academic performance. This paper primarily outlines the implementation of a few key standards of OBE in teaching-learning of two fundamental courses in Electronics and Telecommunication Engineering. It then covers how OBE, and its consequences demand paradigm shifts in instructional design and evaluation practices. The discussion on OBE for courses on Digital Communication and Digital Signal Processing is explored with Program Outcomes (POs), Program-Specific Outcomes (PSOs), and Course Outcomes (COs). Analysis of PO and CO attainment for these two courses reflects the importance of the OBE framework. The inclusion of engineering pedagogy and active learning strategies in this framework leads to enhancing students’ creativity leading to their growth in their professional careers. [ABSTRACT FROM AUTHOR]

Remote sensing imagery is generally prone to various radiometric distortions such as stripe noise, line loss, line or column drop out, banding, random bad pixels i.e. shot noise. These errors arrive due to on-board anomalies. These severely degrade the radiometric quality of the measured imagery and introduce a considerable level of incorrectness. Images with such a considerable level of radiometric incorrectness cannot be used directly for any image analysis application. It needs to be analyzed and pre-processed with Image Processing techniques before going to generate the data for the use of various applications. This paper presents a global residual learning method-based deep neural network (DNN) approach to automatically remove stripe noise of various types and shot noise as well, and hence improves the image quality of remote sensing imagery. The proposed method shows improved performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) quality measures when compared with the state-of-the-art methods. In addition, destriping by residual DNN is followed by a new post-processing step using multilevel wavelet decomposition and frequency domain filtering to remove the residual striping artefacts. A global residual learning method, batch normalization, mini batch selection and skip connection steps help speeding up the training process as well as boost the network performance. [ABSTRACT FROM AUTHOR]

Building extraction from aerial imagery facilitates many geospecialized tasks like Urban Planning, Map Generation and Disaster Management. Well planned cities ensure good sanitation, lesser pollution and hence, a better standard of living for its citizens. This is essential for developing countries which face a major crisis of urban migration and space crunch, and where planned cities would be a move towards smart living. The objective of this work is to segment building footprints from aerial images. Traditional pixel clustering algorithms like K-means, Color Quantization (CQ) and Gaussian Mixture Model (GMM) are implemented with inclusion of preprocessing steps for improved performance. These techniques are compared based on performance and time taken. The number of clusters/components are selected on the basis of Silhouette Score and Akaike Information Criterion/Bayesian Information Criterion (AIC/BIC). A commonly encountered problem in building segmentation is misclassification of pixels due to shadows. This challenge is dealt by masking shadows using morphological operations as a part of preprocessing. [ABSTRACT FROM AUTHOR]