Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
264
result(s) for
"Srivastava Rajeev"
Sort by:
Green information and communication systems for a sustainable future
\"This book includes the fundamental concepts, applications, algorithms, protocols, new trends, challenges, and research results in the area of Green Information and Communication Systems. It is a resource that offers knowledge on core and specialized issues, making it highly suitable for both the new and the experienced researcher in the field. The book covers network design theoretical and practical perspectives. It includes how Green ICT initiatives and applications can play a major role in reducing CO2 emissions, and focuses on industry and how it can promote awareness and implementation of Green ICT. The book discusses scholarship and research in green and sustainable IT for business and organizations and uses the power of IT to usher sustainable in other parts of an organization. The book is for business and management educators, management researchers, doctoral scholars, university teaching personnel, policy makers as well as higher academic research organizations. It is also a good resource for Industrial and Management training organizations all over the world\"-- Provided by publisher.
Book
A technique for image splicing detection using hybrid feature set
Image manipulation has no longer been rocket science for non-professionals. Tampering of images has become so popular due to the accessibility of free editing application in smart phone’s store, these applications work without any agreement or license from the user which makes the condition more vulnerable. The image alteration is not limited to the smart phone’s applications, they can be done online without downloading and signing in the application making the scenario even worst. These forged images are so tricky that they are not predictable with bare human eyes. So, in order to tackle with this delinquent act, one must develop such system which can instantly discriminate between the unique and altered image. One of the best technologies that can tackle the problem and helps to develop such a scheme is Machine learning. There are several classification techniques based on the requirement of the system that can be applied to the data set, resulting in the classification of images under the groups forged and unforged images. In this work, we have discussed the images which are being forged using Image splicing Technique, in which the region of an original image is cropped and pasted onto the other original image. In this paper, a machine learning classification technique logistic regression has been used to classify images into two classes, spliced and non-spliced images. For this, a combination of four handcrafted features has been extracted from images for feature vector. Then these feature vectors are trained using logistic regression classification model. 10-fold cross-validation test evaluation procedure has been used to evaluate the result. Finally, the comparative analysis of the proposed method with other state-of-the-art methods on three online available datasets is presented in the paper. It is observed that the obtained results perform better than state-of-the-art methods.
Journal Article
Detection of Copy-Move Forgery in Digital Image Using Multi-scale, Multi-stage Deep Learning Model
Images are an important source of information and copy-move forgery (CMF) is one of the vicious forgery attacks. Its objective is to conceal sensitive information from the image. Hence, authentication of an image from human eyes become arduous. Reported techniques in literature for detection of CMF are suffering from the limitations of geometric transformations of forged region and computation cost. In this paper, a deep learning CNN model is developed using multi-scale input with multiple stages of convolutional layers. These layers are divided into two blocks i.e. encode and decoder. In encoder block, extracted feature maps from convolutional layers of multiple stages are combined and down sampled. Similarly, in decoder block extracted feature maps are combined and up sampled. A sigmoid activation function is used to classify pixels into forged or non-forged using the final feature map. To validate the model two different publicly available datasets are used. The performance of the proposed model is compared with state-of-the-art methods which show that the presented data-driven approach is better.
Graphic Abstract
Journal Article
A robust salient object detection using edge enhanced global topographical saliency
Complex salient object detection is the most challenging task in clutter background images. In this prevailing problem, global contrast-based methods are comprehensively preferred. But these methods fail in preserving the structure, shape and broader related geometrical information. Aiming at these limitations, the proposed method uses global contrast and iterative Laplacian of Gaussian to generate initial global topographical saliency. In this topographical saliency, iterative Laplacian of Gaussian is used to preserve the structural, shape and broader related geometrical information. This global topographical saliency is used as a reference plane for integrating regional saliencies. The color, spatial and distance based regional saliencies are integrated into the boundary enhanced global topographical saliency to improve the substantial information of the object. Boundary-based Gaussian weighted, background suppression model, is used to remove the background and edge-effects. Finally, central saliency addition is used to enhance the final saliency. The proposed method is compared with recent six global contrasts based state-of-art methods, two deep learning based methods and four publicly available datasets. The experimental result presented here shows that the proposed method performs better in comparison to the state-of-the-art methods.
Journal Article
Time-efficient spliced image analysis using higher-order statistics
Image forgery is gaining huge momentum as changing the content is no longer arduous. One of the leading techniques of this category is image splicing. This technique generates a composite image formed by combining regions of images. Once the image is forged, it becomes nearly impossible for the human expert to substantiate. Hence, for detecting and localizing the spliced region in the forged image, a tool is to be developed which has become the need of the hour. Articles have been reported that one of the key ingredients for such a tool is noise inconsistency, among others. The spliced region contains the non-homogeneous distribution of noise which acts as a feature to localize it. State-of-the-art techniques based on inconsistent noise are suffering from challenges like the requirement of prior knowledge about the image, localization of spliced region and estimation of inconsistent non-gaussian noise. In this paper, a blind local noise estimation technique has been introduced using a fourth-order central moment to localize the spliced region. This paper tries to overcome the challenges of state-of-the-art techniques. Experimental analysis has been done on images of three publicly available datasets. The results are evaluated on pixel level using confusion matrix and some other performance measures. The result of the given approach is compared with previously reported techniques and found better than them.
Journal Article
A Hybrid Dragonfly Algorithm for Efficiency Optimization of Induction Motors
Induction motors tend to have better efficiency on rated conditions, but at partial load conditions, when these motors operate on rated flux, they exhibit lower efficiency. In such conditions, when these motors operate for a long duration, a lot of electricity gets consumed by the motors, due to which the computational cost as well as the total running cost of industrial plant increases. Squirrel-cage induction motors are widely used in industries due to their low cost, robustness, easy maintenance, and good power/mass relation all through their life cycle. A significant amount of electrical energy is consumed due to the large count of operational units worldwide; hence, even an enhancement in minute efficiency can direct considerable contributions within revenue saving, global electricity consumption, and other environmental facts. In order to improve the efficiency of induction motors, this research paper presents a novel contribution to maximizing the efficiency of induction motors. As such, a model of induction motor drive is taken, in which the proportional integral (PI) controller is tuned. The optimal tuning of gains of a PI controller such as proportional gain and integral gain is conducted. The tuning procedure in the controller is performed in such a condition that the efficiency of the induction motor should be maximum. Moreover, the optimization concept relies on the development of a new hybrid algorithm, the so-called Scrounger Strikes Levy-based dragonfly algorithm (SL-DA), that hybridizes the concept of dragonfly algorithm (DA) and group search optimization (GSO). The proposed algorithm is compared with particle swarm optimization (PSO) for verification. The analysis of efficiency, speed, torque, energy savings, and output power is validated, which confirms the superior performance of the suggested method over the comparative algorithms employed.
Journal Article
User-interactive salient object detection using YOLOv2, lazy snapping, and gabor filters
Salient object detection is the process of locating prominent objects in an image. In this field, deep learning methods are providing outstanding results. One way of finding salient objects is to first obtain a bounding box for the prominent object in the image and then use the bounding box to form the actual shape of the salient object. In this work, we find an object bounding box using YOLOv2 network. Next, we apply boundary correction to the bounding box predicted by the deep network. In the third step, we segment the image using a set of Gabor filters. Then, we select the matching segment from the first-level boundary correction. On the matching segment, we apply second-level boundary correction. Usually, in salient object detection, the end-user plays no role in selecting the salient object. In this work, we provide the user with a choice to improvise on the salient object detected at the first level. If the user is not satisfied with first-level boundary correction, he/she can choose for second-level boundary correction. The method provides a benefit over the existing methods as most of the saliency map results are static, and pure deep learning methods have blurred edges. By using this procedure, neat object edges are obtained. The algorithm is tested on three datasets against four state-of-the-art methods. The algorithm is evaluated based on F-measure. The proposed model achieves 0.86, 0.7904, and 0.745 F-measure for ASD, ECSSD, and PASCAL-S dataset, respectively.
Journal Article
Development of short questionnaire to measure an extended set of role expectation conflict, coworker support and work-life balance: The new job stress scale
This study aimed to investigate the reliability and validity of a new version of job stress scale, which measures the extended set of psychosocial stressors by adding new scales to the current version of the job stress scale. Additional scales were extensively collected from theoretical job stress models and similar questionnaire from different countries. Items were tested in workplace and refined through a pilot survey (n = 400) to examine the reliability and construct validity. Most scales showed acceptable levels of internal consistency, intra-class reliability, and test–retest reliability. Factor analysis and correlation analysis showed that these scales fit the theoretical expectations. These findings provided enough evidences that the new job stress scale is reliable and valid. Although confirmatory analysis should be examined in future studies. The new job stress scale is a useful instrument for organization and academicians to evaluate job stress in modern Indian workplace.
Journal Article
An efficient modification of generalized gradient vector flow using directional contrast for salient object detection and intelligent scene analysis
In the field of computer vision, scene analysis is a very important area of study. To analyze the scene present in an image, in this paper, the attempt is to enhance salient object information with background information. For this, the Generalized Gradient Vector Flow model is modified by adding contrast information. The contrast information of an image is obtained by computing the Minimum Directional Contrast of the image. Using Minimum Directional Contrast as a determinant of the salient object arises from the fact that the salient objects have higher Minimum Directional Contrast than the non-salient objects. The Minimum Directional Contrast information is added to the data term of Generalized Gradient Vector Flow so that for producing contours, not only edge information is utilized, but saliency information is also used. The result gives us the salient object and added relevant background information. The algorithm is tested on three public datasets. The evaluation is done based on precision, recall, accuracy, and F1-score after comparing with six state-of-the-art methods.
Journal Article
Depth based enlarged temporal dimension of 3D deep convolutional network for activity recognition
An activity takes many seconds to complete which makes it a spatiotemporal structure. Many contemporary techniques tried to learn activity representation using convolutional neural network from such structures to recognize activities from videos. Nevertheless, these representation failed to learn complete activity because they utilized very few video frames for learning. In this work we use raw depth sequences considering its capabilities to record geometric information of objects and apply proposed enlarged time dimension convolution to learn features. Due to these properties, depth sequences are more discriminatory and insensitive to lighting changes as compared to RGB video. As we use raw depth data, time to do preprocessing are also saved. The 3 dimensional space-time filters have been used over increased time dimension for feature learning. Experimental results demonstrated that by lengthening the temporal resolution over raw depth data, accuracy of activity recognition has been improved significantly. We also studied the impact of different spatial resolution and conclude that accuracy stabilizes at larger spatial sizes. We shows the state-of-the-art results on three human activity recognition depth datasets: NTU-RGB + D, MSRAction3D and MSRDailyActivity3D.
Journal Article