IJCSIS Papers by ASHIMA SINGH
Image processing is the technique to fetch the valuable data from the given images for different ... more Image processing is the technique to fetch the valuable data from the given images for different purposes like improvement in visualization of an image and to measure structure or features from the extracted data. High-quality images and videos are easy to predict, and classify, whereas detecting hazy or foggy image is a cumbersome issue. This paper has proposed an efficient methodology integrating various techniques of image processing like Discrete Wavelet Transform (DWT) and Convolutional Neural Network (CNN) for defogging images with prior pre-processing using guided filter. The proposed technique has improved the related standard performance metrics like PSNR, MSE and IIE significantly.
Papers by ASHIMA SINGH
2013 International Conference on Information Systems and Computer Networks
ABSTRACT Software Quality is the very popular and a very important topic for researchers within t... more ABSTRACT Software Quality is the very popular and a very important topic for researchers within the software engineering communities, most probably everyone has an opinion about the meaning of quality. However, many disagreements and conflicts are very often leaded between peoples whose involve in software development, when they implement to it in the real world. This has been highly notable in the case of customer's complaints about faults in the software products. It is well known that many organizations or individuals are relishing many challenges to preserve software product quality, whenever they develop any types of software product. Appearance of defects is the very much contributor to reduce the product quality and prominently increases in development costs and completion time due to amendment and rework time. The success and demand of a software system is not only pivot on cost and proceedings, but also on software quality. In between many software quality features, to identify the vestigial defects in the product has become the actual industry standard. This paper is a study about software quality, software defect and how both are relate to each other and also discuss defect prediction is batter approach in compare defect correction to assure software product quality. We also discuss some data mining methodologies in brief; they are used to build defect prediction models to ensure the level of defect density of target program modules of software product.
2013 International Conference on Information Systems and Computer Networks
ABSTRACT Software Quality is the very popular and a very important topic for researchers within t... more ABSTRACT Software Quality is the very popular and a very important topic for researchers within the software engineering communities, most probably everyone has an opinion about the meaning of quality. However, many disagreements and conflicts are very often leaded between peoples whose involve in software development, when they implement to it in the real world. This has been highly notable in the case of customer's complaints about faults in the software products. It is well known that many organizations or individuals are relishing many challenges to preserve software product quality, whenever they develop any types of software product. Appearance of defects is the very much contributor to reduce the product quality and prominently increases in development costs and completion time due to amendment and rework time. The success and demand of a software system is not only pivot on cost and proceedings, but also on software quality. In between many software quality features, to identify the vestigial defects in the product has become the actual industry standard. This paper is a study about software quality, software defect and how both are relate to each other and also discuss defect prediction is batter approach in compare defect correction to assure software product quality. We also discuss some data mining methodologies in brief; they are used to build defect prediction models to ensure the level of defect density of target program modules of software product.
Neural Computing and Applications, 2021
Unfortunately, the reference no. 52 contains a typo in the original publication of the article. T... more Unfortunately, the reference no. 52 contains a typo in the original publication of the article. The corrected reference should read as below: ''52. Ç içek, E., Gören, S. Smartphone power management based on ConvLSTM model. Neural Comput &
2017 8th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON), 2017
The increasing use of social networking websites has given a platform for people to share their o... more The increasing use of social networking websites has given a platform for people to share their opinion to a wider audience. Corporations now recognise these sites as amongst primary modes of advertisement as well as the foremost source of feedback. Several companies now focus their core marketing operations and generate insights using such websites. In this paper, we propose a tool, GLOPP, for monitoring geolocation specific public perception and brand sentiment on such social media platforms, and use it to create different visualizations highlighting various aspects of the customer response for a brand in a particular region, or in a broader sense, public perception for any entity, regionally. This can help enterprises in formulating new marketing strategies, while enabling them to understand and improve customer experience.
Communications in Computer and Information Science, 2018
Image processing methods are widely used to improvise the quality of an image to extract the hidd... more Image processing methods are widely used to improvise the quality of an image to extract the hidden information in it. Phenomena of scattering and atmosphere absorption results inhaze smoke and fog. Weather conditions majorly influence the visual system as well as detection and identification of the targets and degrade the picture quality. In the previous year, researchers have been focused on the high-quality images or videos for enhancement as well as to detect objects. In this paper, we have reviewed previous papers and compare based on used techniques and performance parameters.
Information and Communication Technology for Intelligent Systems, 2020
179 Abstract—The Component Based Software Development (CBSD) approach is becoming the trend for s... more 179 Abstract—The Component Based Software Development (CBSD) approach is becoming the trend for software development which is based on developing the software from existing components instead of developing software from scratch everytime. Measuring software complexity is an important aspect during software development. Because software complexity is an important determinant of software development effort, testing effort , cost, maintainability etc. Researchers have proposed a wide range of complexity metrics for software systems . But the traditional software product and process metrics are neither suitable nor sufficient in measuring the Component and Component Based Software (CBS) complexity. So CBSD provides one of the central problems in measuring component and CBS complexity. Measuring component complexity plays an important role in determining the complexity of CBS system. Because component complexity affects the complexity of whole CBS . Component complexity affects integrati...
Journal of Biology and Today`s World, 2019
In recent years, healthcare data analysis is becoming one of the most promising research areas. H... more In recent years, healthcare data analysis is becoming one of the most promising research areas. Healthcare includes data in various types such as clinical data, Omics data, and Sensor data. Clinical data includes electronic health records which store patient records collected during ongoing treatment. Omics data is one of the high dimensional data comprising genome, transcriptome and proteome data types. Sensor data is collected from various wearable and wireless sensor devices. To handle this raw data manually is very difficult. For analysis of data, machine learning is emerged as a significant tool. Machine learning uses various statistical techniques and advanced algorithms to predict the results of healthcare data more precisely. In machine learning different types of algorithms like supervised, unsupervised and reinforcement are used for analysis. In this paper, different types of machine learning algorithms are described. Then use of machine learning algorithms for analyzing v...
Agile software development is finding a new dimension in software development process models. As ... more Agile software development is finding a new dimension in software development process models. As tools and techniques used to develop software has been changed drastically. Software development processes need to keep pace with changing technologies and new demands from clients. Today’s changing business needs have given rise to adaption of structures, strategies, and policies to suit the new environment by the organizations. These organizations need to upgrade their information systems to meet their changing requirements but the traditional and plan-driven software development methodologies lack the flexibility to adjust the development process as the process runs in the defined or standardized manner. Agile development method has the ability of overcoming the limitations of traditional approach. A number of software development methods such as extreme programming (XP), feature-driven development, scrum and adaptive software development are part of agile development method [3,7]. We...
Communications in Computer and Information Science, 2018
A healthcare system using modern computing techniques is the highest explored area in healthcare ... more A healthcare system using modern computing techniques is the highest explored area in healthcare research. Researchers in the field of computing and healthcare are persistently working together to make such systems more technology ready. Recent studies by World Health Organization have shown an increment in the number of diabetic patients and their deaths. Diabetes is one of the basic sicknesses which has long-haul complexities related to it. A high volume of medical information is produced. It is important to gather, store, learn and predict the health of such patients using continuous monitoring and technological innovations. An alarming increase in the number of diabetic patients in India has become an important area of concern. With the assistance of innovation, it is important to construct a framework that store and examine the diabetic information and further see conceivable dangers. Its early detection and analysis remain a challenge among researchers. This review gives present status of research in determining diabetes and proposed frameworks.
Enterprise Information Systems, 2020
This paper proposes IoT-based an enterprise health information system called IoTPulse to predict ... more This paper proposes IoT-based an enterprise health information system called IoTPulse to predict alcohol addiction providing real-time data using machine-learning in fog computing environment. We used data from 300 alcohol addicts from Punjab (India) as a case study to train machine-learning models. The performance of IoTPulse is compared against existing work using various parameters including accuracy, sensitivity, specificity and precision which shows improvement of 7%, 4%, 12% and 12% respectively. Finally, IoTPulse is validated in FogBus-based real fog environment using QoS parameters including latency, network bandwidth, energy and response time which improves performance by 19.56%, 18.36%, 19.53% and 21.56% respectively.
Software Processes are the lifeline of any Software Development Model. Software Processes decide ... more Software Processes are the lifeline of any Software Development Model. Software Processes decide the survival of a particular software development model in the market as well as in software organization. The set of processes those proved to be effective and efficient for software development in one organization may or may not be followed in another organization. That is other organization finds another approach for software development more convenient to work with. This paper explains the progression and remarkable change in Software Processes and their respective models. It also summarizes a contrast of classical software processes with Agility and CBSE.
In software industry, there is progressive increase in reusability of software components. To inc... more In software industry, there is progressive increase in reusability of software components. To increase productivity and to reduce time-to-market organizations are adapting for-reuse and with-reuse approach. In order to make reusable component available in future projects there must be a system to store software components so that they can be efficiently retrieved as per user requirements. So this work is toward, construction of component repository with efficient retrieval of software component that best fits user’s requirements, while retrieving software component. Besides, it enhances reusability; reduces efforts of software development from scratch and increases productivity.
Journal of Software: Evolution and Process, 2020
Establishing the maturity levels of-Small and Medium Enterprises (SMEs) without Capability Maturi... more Establishing the maturity levels of-Small and Medium Enterprises (SMEs) without Capability Maturity Model Integration (CMMI) certification has always been regarded as an extremely challenging task. Software process improvement (SPI) has targeted to monitor and improve software processes, thereby improving the software business. Although there is scientific interest in SPI, little attention has been specifically given to the exploration of maturity levels for non-CMMI SMEs. The goal is to explore the effect of time on process maturity and maturity levels achieved informally or unofficially by SMEs that are not otherwise CMMI certified. To find out the maturity levels achieved informally, a CMMI-DEV v1.3 based survey questionnaire is administered to Indian software SMEs. Time of establishment of SMEs and follow-up of CMMI-based processes and practices unofficially are used as two important parameters to decide upon process maturity and achievement of specific CMMI level informally. This paper has been successful in ascertaining the effect of time of establishment of SMEs and follow-up of CMMI-based processes on process maturity using proposed RuleML that advocates adoption of more than 70% of CMMI-DEV v1.3 process area-specific practices for an SME to be unofficially ready for CMMI-based SPI initiatives. The findings manifest multidimensional aspects of unofficial readiness of SMEs for CMMI-based SPI that can be used by relevant authorities to select SMEs for funding for SPI initiatives. Finally, the proposed work has been validated statistically using t-test for CMMI Level II and Level III.
Internet Technology Letters, 2020
Road related accidents have always been a nuisance to drivers and pedestrians alike. Every year c... more Road related accidents have always been a nuisance to drivers and pedestrians alike. Every year countless accidents and deaths occur due to potholes which could have been preventable if there had been a prior warning or if the civic authorities were able to repair these potholes in time. This paper proposes a machine learning based pothole detection system called DeepBus for real time identification of surface irregularities on roads using Internet of Things (IoT). DeepBus uses IoT sensors to detect potholes in real time while an end user is driving vehicles on the road. The location of these potholes would be available on a centrally hosted map which can be accessed by both end users and civic authorities. Thus, it would serve as a warning system to all users as well as a database of potholes with thier locations to the authorities for quick repair and action. We have compared the performance of various machine learning models (Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, Decision Tree, Random Forest and Ensemble Voting) based on different parameters (Accuracy, F-score, Precision and Recall) and identified that Random Forest is the best model for pothole detection.
The Computer Journal, 2020
Flying ad hoc networks (FANETs) are a collection of unmanned aerial vehicles that communicate wit... more Flying ad hoc networks (FANETs) are a collection of unmanned aerial vehicles that communicate without any predefined infrastructure. FANET, being one of the most researched topics nowadays, finds its scope in many complex applications like drones used for military applications, border surveillance systems and other systems like civil applications in traffic monitoring and disaster management. Quality of service (QoS) performance parameters for routing e.g. delay, packet delivery ratio, jitter and throughput in FANETs are quite difficult to improve. Mobility models play an important role in evaluating the performance of the routing protocols. In this paper, the integration of two selected mobility models, i.e. random waypoint and Gauss–Markov model, is implemented. As a result, the random Gauss integrated model is proposed for evaluating the performance of AODV (ad hoc on-demand distance vector), DSR (dynamic source routing) and DSDV (destination-Sequenced distance vector) routing pr...
International Journal of Process Management and Benchmarking
It has been of utmost significance for the software industry to find a way for the successful imp... more It has been of utmost significance for the software industry to find a way for the successful implementation of software process improvement (SPI). It assumes greater importance when we talk about small and medium enterprises (SMEs). Majority of the researchers have explored limited resources in terms of cost, time and expertise for the low adoption rate of software process reengineering (SPR) in Indian SMEs. Last decade evidenced evolvement of software SMEs; and the rate of adoption of SPI initiatives realised some appreciation. In order to explore the reasons attributing towards the success or failure of SPI, researchers need to focus on the underlying multi-dimensional issues. Sufficient literature is available regarding SPI initiatives of triumphant organisations, but not much has been said about Indian SMEs. This paper aims to point out the facilitating factors in SPI that can really boost the quality of software processes to provide a competitive edge to the Indian SMEs.
Uploads
IJCSIS Papers by ASHIMA SINGH
Papers by ASHIMA SINGH