Dr Renu Dhir | Dr BR Ambedkar National Institute of Technology Jalandhar India (original) (raw)

Papers by Dr Renu Dhir

Multimedia Systems, May 28, 2023

International journal of computational systems engineering, 2019

An object-oriented (OO) metrics has become crucial desideratum for software effort and fault pred... more An object-oriented (OO) metrics has become crucial desideratum for software effort and fault predictions. To strengthen the adequacy of object-oriented metrics, it becomes important to know relationship between OO metrics and fault proneness at different levels of severity. It is inconceivable to build model of accurate estimate due to the inherent uncertainty in development projects. Empirical validation of software metrics is essential issue to determine applicability of prediction model. In this study, empirical validation is done on OO metrics given by Chidamber and Kemerer (CK suite) for predicting faults at different severity levels. This paper also instanced on defect prediction using cross-projects (CP) because of the unpredictability in selection of software attributes by analogy-based approach that deliver imprecise and ambiguous solution. This paper depicts detection of fault-proneness by extracting the relevant OO metrics and such models helps to focus on fault-prone modules of new projects by allocating more resources to them with use of regression and other machine learning methods. Combination of CP data with regression techniques improves effectiveness of prediction by extracting similar features impacted by all datasets.

IOSR Journal of Computer Engineering, 2014

Human faces are major identity mark. Face recognition is the active research area in real time ap... more Human faces are major identity mark. Face recognition is the active research area in real time applications. Face detection has many applications in biometrics, video surveillance , robotics, control of manmachines, photography, and image indexing. Many face recognition techniques are developed to recognize human features. In this paper the study and methodology of PCA (Principal Component Analysis), CoC (Coefficient of Correlation) , SSIM (Structural SIMilarity Index Metrics), DWT (Discrete Wavelet Transform) face recognition techniques is provided.

In VANET, or Intelligent Vehicular Ad-Hoc Networking, defines an intelligent way of using Vehicul... more In VANET, or Intelligent Vehicular Ad-Hoc Networking, defines an intelligent way of using Vehicular Networking. InVANET integrates on multiple ad-hoc networking technologies such as WiFi IEEE 802.11, WAVE IEEE 1609, WiMAX IEEE 802.16, and Bluetooth for easy, accurate, effective and simple communication between vehicles on dynamic mobility. Effective measures such as media communication between vehicles can be enabled as well methods to track the automotive vehicles are also preferred. InVANET helps in defining safety measures in vehicles, streaming communication between vehicles, infotainment and telematics. The type of InVANET applications and inherent characteristics such as different network energy level and movement of vehicles from one network to other network makes this task (prior information about traffic) quite challenging. In this paper we focus on Inter Vehicle Communication (IVC) and Roadside to Vehicle Communication (RVC) network, one algorithm has been developed and proposed for implementation in real life IVC and RVC application. This paper's contribution is a reliable broadcasting method that is especially designed for an optimum performance of public-safety related applications.

Background: Economically Ethiopia remains one of the poorest countries in the world and malnutrit... more Background: Economically Ethiopia remains one of the poorest countries in the world and malnutrition is one of the major and most pressing health problems; especially among children. Objective: To assess the nutritional status of preschool children in a rural locality of Northwest Ethiopia Methods: A cross-sectional survey was conducted in a rural locality called Gumbrit. Weight and height of the study children were measured and the socio-demographic characteristics of the subjects were collected using a questionnaire. Results: The overall prevalence of malnutrition in the community was high with 28.5% of the children being underweight, 24% stunted and 17.7% wasted. Among the socioeconomic variables included in the study only family income was significantly associated with malnutrition. Conclusion: The nutritional status of children in rural communities is affected by low family income. To improve nutritional status of children the full implementation of the poverty alleviation programmes should be considered and appropriate measures need to be taken to support needy families with children.

2016 Symposium on Colossal Data Analysis and Networking (CDAN), 2016

Opinion Mining (also known as “Sentiment Analysis”) is an area of text classification which conti... more Opinion Mining (also known as “Sentiment Analysis”) is an area of text classification which continuously gives its contribution in research field. The main objective of Opinion mining is Sentiment Classification i.e. to classify the opinion into positive or negative classes. SentiWordNet is an opinion lexicon derived from the WordNet database where each term is associated with some numerical scores indicating positive and negative sentiment information. Up until recently most researchers presented opinion mining of online user generated data like reviews, blogs, comments, articles etc. Opinion mining for offline user generated data like newspaper is unconcerned so far despite the fact that it is also explored by many users. As a first step, this paper present opinion mining for newspaper headlines using SentiWordNet. Further, most of the researchers implement the opinion mining by separating out the adverb-adjective combination present in the statements or classifying the verbs of statements. On the other hand, in this paper we analyze each and every word in the News headline whether it is a noun, verb, adverb, adjective or any other part-of-speech. During experiment, python packages are used to classify words. Then SentiWordNet 3.0 is used to identify the positive and negative score of each word thus evaluating the total positive/negative impact in that news headline.

Genetic abnormalities constitute a considerable share of all the existing societal healthcare iss... more Genetic abnormalities constitute a considerable share of all the existing societal healthcare issues. There has been a dire need for the automation of chromosomal analysis, hence supporting laboratory workers in effective classification and identifying such abnormalities. Nevertheless, many modern image processing techniques, like karyotyping, have improved the life expectancy and quality of life of such cases. The standard image-based analysis procedures include pre-processing, segmentation, feature extraction, and classification of images. When explicitly considering karyotyping, the processes of segmentation and classification of chromosomes have been the most complex, with much existing literature focusing on the same. Various model-based machine learning models have proven to be highly effective in solving existing issues and building an artificial intelligence-based, autonomous-centric karyotyping system. An autonomous karyotyping system will connect the pre-processing, segmen...

The Asian Review of Civil Engineering

Himalayas has one of the largest resources of snow and ice, which act as a freshwater reservoir f... more Himalayas has one of the largest resources of snow and ice, which act as a freshwater reservoir for all the rivers originating from it. Monitoring of these resources is important for the assessment of availability of water in the Himalayan Rivers. The mapping of Glaciers is very difficult task because of the inaccessibility and remoteness of the terrain. Remote sensing techniques are often the only way to analyze glaciers in remote mountains and to monitor a large number of glaciers in multitemporal manner. This paper presents the results obtained from the analysis of a set of multitemporal Landsat MSS, TM and ETM+images for the monitoring and analysis of Burphu Glacier.

Maintainability is one of the important characteristics of quality of software. It is the measure... more Maintainability is one of the important characteristics of quality of software. It is the measure of efforts needed to modify the software. Large number of subjective techniques has been developed in industry to deal with assessment or prediction of this characteristic. But these techniques generally fail due to their inability to break down maintainability to a level of actual evaluation. They also lack homogeneity in the models thus developed and so fail to take into account the cost factor associated with maintainability. Activity based quality model is found to decompose maintainability to an actual analyzable level. It manages maintainability in terms of software maintenance efforts but it lacks quantitative evaluation of this characteristic. Bayesian approach to deal with this model added quantitative feature but also added crispness to the system developed. In this chapter, the authors propose the use of fuzzy approach to correct the existing Bayesian approach to deal with activity based quality model. A comprehensive comparative study is presented to show the effectiveness of proposed technique.

International Journal of Applied Metaheuristic Computing, Apr 1, 2017

Nature-inspired algorithms are becoming popular due to their ability to solve complex optimizatio... more Nature-inspired algorithms are becoming popular due to their ability to solve complex optimization and engineering problems. Grey Wolf algorithm is one of the recent nature-inspired algorithms that have obtained inspiration from leadership hierarchy and hunting mechanisms of grey wolves. In this paper, four formulations of multi-objective grey wolf algorithm have been developed by using combination of weighted objectives, use of secondary storage for managing possible solutions and use of Genetic Algorithm (GA). These formulations are applied for jobs scheduling on parallel machines while taking care of bi-criteria namely maximum tardiness and weighted flow time. It has been empirically verified that GA based multi-objective Grey Wolf algorithms leads to better results as compared to their counterparts. Also the use of combination of secondary storage and GA further improves the resulting schedule. The proposed algorithms are compared to some of the existing algorithms, and empirically found to be better. The results are validated by numerical illustrations and statistical tests.

International Journal of Applied Evolutionary Computation, 2016

Parallel machine scheduling problems are classified as NP-hard problems. The direct solutions for... more Parallel machine scheduling problems are classified as NP-hard problems. The direct solutions for these problems are not available and meta-heuristic algorithms are required to be used to find near-optimal solutions. In this paper, the formulations of multi-objective Artificial Bee Colony algorithm by using combination of weighted objectives, secondary storage for managing possible solutions and Genetic algorithm have been developed and applied to schedule jobs on parallel machines optimizing bi-criteria namely maximum tardiness and weighted flow time. The results obtained indicate that proposed algorithm outperforms other multi-objective algorithms in optimizing bi-criteria scheduling problems on parallel machines. Further, the sequential optimization of bi-criteria using Early Due Date (EDD) followed by Genetic Algorithm (GA) has also been investigated. The efficiencies of the proposed algorithms have been verified by numerical illustrations and statistical tests.

This paper mainly deals with the new method for line segmentation of Handwritten Hindi text. Line... more This paper mainly deals with the new method for line segmentation of Handwritten Hindi text. Line segmentation is the major task in segmentation process. If line segmentation fails word segmentation and character segmentation fails automatically. In this paper we have discussed an algorithm to detect header line and base lines accurately so that we can divide the lines correctly. The average line height is estimated, before calculating the header line and base lines. Performance of this method is checked on the 500 lines of different handwritten documents.

2021 2nd International Conference on Secure Cyber Computing and Communications (ICSCCC), 2021

In the broader area of machine learning, deep learning depicts a dramatic twist in enhancing the ... more In the broader area of machine learning, deep learning depicts a dramatic twist in enhancing the level of intelligence in the various machines. There is a plethora of parameters like weights, bias, number of hidden layers, activation function, and hyperparameters that are utilized for measuring the accuracy of a training model. The prominent form of hyperparameters that are essential for the training process and extracting information for taking decisions is known as Epochs. The enhancement of results is obtained by practicing on the pre-trained network architecture that includes GPU-based computation in the TPU chips. The paper uses the ResNet50 architecture network to train the ultra-deep neural networks for implementing multiclass image classification that is based on Transfer Learning uses a various number of hidden layers to classify handwritten digits and accuracies at different classes is judged by epochs. The tradition of the MNIST database dataset is that it classifies the image into 10 classes. As the image dataset in the NIST is of type bilevel and that was normalized in dimensions to fit in a 224x224 pixel box for better performance. The normalization algorithm uses the anti-aliasing technique to obtain the resultant grey images for the best recognition rate of 99%. As in Traditional machine learning approaches such as KNN, DNN, and many more that take a prolonged time for training the dataset while transfer learning provides the accuracy of 99%, and that was achieved in a few epochs.

2013 IEEE International Conference on Signal Processing, Computing and Control (ISPCC), 2013

ABSTRACT Digital watermarking has developed immensely for multimedia uses in the current decade. ... more ABSTRACT Digital watermarking has developed immensely for multimedia uses in the current decade. The requirement for protected digital content grows vital with the enhancement in exchange of digital images on internet. Watermarking is a technique to safeguard digital media by retaining the owner's possession. Fingerprinting extends the watermarking concept by embedding unique purchaser's information. This paper presents a joint digital watermarking and fingerprinting approach for colored digital images applied in double DCT domain. The approach aims at copyright protection and traitor identification of digital images. Altered mid-frequency coefficients are analyzed by applying forward DCT transform. Watermark and fingerprint are embedded in a non-overlying manner. Second DCT allows for the precise determination of the block, for embedding data. The double domain can enhance the embedding capacity of the host image by choosing more than one coefficients in a given block. Simulation outcomes reveal that the watermark is immune to JPEG compression, additive noise and median filtering. Quality of the image is retained, as the results reveal a Peak Signal to Noise Ratio (PSNR) in range of 58-73 dB.

International journal of computer applications, Jun 30, 2012

This paper presents an overview of Feature Extraction techniques for off-line recognition of isol... more This paper presents an overview of Feature Extraction techniques for off-line recognition of isolated Gurumukhi numerals/characters. Selection of Feature Extraction method is probably the single most important factor in achieving high performance in pattern recognition. Our paper presents Zone based hybrid approach which is the combination of image centroid zone and zone centroid zone of numeral/character image. In image centroid zone character is divided into n equal zone and then image centroid and the average distance from character centroid to each zones/grid/boxes present in image is calculated. Similarly, in zone centroid zone character image is divided into n equal zones and centroid of each zones/boxes/grid and average distance from zone centroid to each pixel present in block/zone/grid is calculated. SVM for subsequent classifier and recognition purpose. Obtaining 99.73% recognition accuracy.

CRC Press eBooks, Apr 5, 2022