Papers by Dr. A. Charan Kumari
Investigating Transfer Learning Models for Lung Cancer Detection from CT Scans: A Comparative Evaluation
Algorithms for Intelligent Systems
Investigating Transfer Learning Models for Lung Cancer Detection from CT Scans: A Comparative Evaluation
Algorithms for Intelligent Systems
Inspecting Transfer Learning Models for Diabetic Retinopathy Detection
2023 3rd International Conference on Emerging Frontiers in Electrical and Electronic Technologies (ICEFEET)
Revitalizing Traditional Health Practices with HealingHands: An AI powered Chatbot
2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES)
Integrating software effort estimation with risk management
International Journal of System Assurance Engineering and Management

Service Discovery and Selection in Internet of Things - A Review
Recent Patents on Engineering, 2018
The Internet of Things (IoT) is a novel technology that has opened doors to the new level of inte... more The Internet of Things (IoT) is a novel technology that has opened doors to the new level of interaction between the things. This has resulted in an enhancement in the quality of life and optimized use of various resources. IoT uses various technologies related to networking, sensing, databases and artificial intelligence to enhance the lifestyle and makes business processes simpler. In the IoT based systems, the number of devices contributing to a particular application is very large, spreading to a large geographical area at various locations. The device can be considered as a resource used by a service in the application layer. IoT service is the most important entity. The real-world things generate data by perceiving the environment in large quantity and store it in the distributed databases or cloud databases. This manuscript analytically and statistically categorizes and analyze the current research techniques on the service discovery and selection in the IoT, published betwee...

Software module clustering using a hyper-heuristic based multi-objective genetic algorithm
2013 3rd IEEE International Advance Computing Conference (IACC), 2013
ABSTRACT This paper presents a Fast Multi-objective Hyper-heuristic Genetic Algorithm (MHypGA) fo... more ABSTRACT This paper presents a Fast Multi-objective Hyper-heuristic Genetic Algorithm (MHypGA) for the solution of Multi-objective Software Module Clustering Problem. Multi-objective Software Module Clustering Problem is an important and challenging problem in Software Engineering whose main goal is to obtain a good modular structure of the Software System. Software Engineers greatly emphasize on good modular structure as it is easier to comprehend, develop and maintain such software systems. In recent times, the problem has been converted into a Search-based Software Engineering Problem with multiple objectives. This problem is NP hard as it is an instance of Graph Partitioning and hence cannot be solved using traditional optimization techniques. The MHypGA is a fast and effective metaheuristic search technique for suggesting software module clusters in a software system while maximizing cohesion and minimizing the coupling of the software modules. It incorporates twelve low-level heuristics which are based on different methods of selection, crossover and mutation operations of Genetic Algorithms. The selection mechanism to select a low-level heuristic is based on reinforcement learning with adaptive weights. The efficacy of the algorithm has been studied on six real-world module clustering problems reported in the literature and the comparison of the results prove the superiority of the MHypGA in terms of quality of solutions and computational time.

Journal of Research in Engineering and Applied Sciences
Food waste is a serious global problem that has significant environmental, economical, and social... more Food waste is a serious global problem that has significant environmental, economical, and social consequences. Many measures to decrease food waste have been proposed in recent years, including the creation of leftover food management systems. This study presents a web application-based leftover food management system with three modules: donors, non-governmental organizations, and volunteers. The system intends to bridge the gap between food waste and hunger by offering a platform for donors to give their leftover food to non-profit organizations, who may then distribute it to the needy through their volunteer network. This article presents an overview of the proposed system, including its functions and advantages. It also covers the system's challenges and limits, as well as future research directions to increase the system's performance.
Optical Encryption of Images Using Partial Pivoting Lower Upper Decomposition Based on Two Structured Deterministic Phase Masks in the Hybrid Transform Domain
Chapman and Hall/CRC eBooks, May 2, 2022
Blockchain Technology: Architecture, Challenges, and Applications
Lecture Notes in Mechanical Engineering, 2021
Performance analysis of LED based indoor VLC system under receiver mobility
2017 International Conference on Computing, Communication and Automation (ICCCA), 2017
Existing indoor lighting systems consisting of incandescent bulbs and compact fluorescent lamps(C... more Existing indoor lighting systems consisting of incandescent bulbs and compact fluorescent lamps(CFLs) are being replaced by light emitting diodes(LEDs) at a much faster pace than envisaged. Such lighting systems are highly energy efficient, cost effective as well as environment-friendly. LEDs can also be used simultaneously for establishing indoor communication infrastructure known as visible light communication(VLC) system. In this paper, the performance of a VLC system is investigated for various communication parameters including the outage area ratio, root mean square (RMS) delay, signal to noise ratio(SNR) and minimum illumination requirement under spatial receiver mobility within the indoor environment.

Image encryption based on Walsh Hadamard and fractional fourier transform using Radial Hilbert Mask
2017 International Conference on Computing and Communication Technologies for Smart Nation (IC3TSN), 2017
In this letter an approach for double image encryption practicing Double Random Phase Encoding (D... more In this letter an approach for double image encryption practicing Double Random Phase Encoding (DRPE) technique that is based on Walsh Hadamard transform (WHT) and fractional Fourier transform (FRT) is proposed. The encryption scheme incorporates Radial Hilbert Mask (RHM), Random Phase Mask (RPM) and fractional order as the keys. Using the 4-f system of DRPE twice in both the WHT and FRT domain, each image is encoded independently with the presented scheme. Matlab simulation tests demonstrate the increase in security level of the classical DRPE technique by the designed optical cryptosystem, and it has a superior insusceptibility to noise also. The efficiency and sensitivity of the presented scheme is tested by calculating MSE and PSNR. The histogram shows that the energy is conserved by using Walsh Hadamard transform and shows that the encrypted image is much easy to transfer due to the compression property of WHT.

International Journal of Computer Applications, 2013
Software evolution is a natural phenomenon. As the software undergoes changes, it needs to be tes... more Software evolution is a natural phenomenon. As the software undergoes changes, it needs to be tested for the changes made along with the unchanged parts for consistency. This activity gradually increases the size of the test suite and becomes a challenging task for a software engineer to perform regression testing in a constrained environment of limited time. The activities of test case selection, test case prioritization or test suite minimization assists software engineers in regression testing by reducing the number of test cases. This paper presents a regression testing tool called ‘RegressAid’ to support software engineers in regression testing by minimizing the test suite while ensuring maximum code coverage and minimum execution time. This paper describes the tool along with its features. The efficacy of the tool is also demonstrated on two real world applications.

Procedia Computer Science, 2018
This paper presents an automated and efficient model of Public Distribution System (PDS) using bi... more This paper presents an automated and efficient model of Public Distribution System (PDS) using biometric based authentication and networking through a micro-controller. Public Distribution System, also termed as rationing distribution system, is one of the widely disputable area with a scope for many malpractices. The existing ration distribution system has high level of corruption such as inaccurate measurement of food grains, long waiting times in queues, material theft in ration shops and manual distribution of the food grains. As a solution to the problems involved in the existing ration card system, the present paper proposes a fully automated model to provide high transparency at all the stages of PDS. In this system, each customer is provided with a smart card, which is to be used along with fingerprint for their authentication. After successful authentication, the consumers can provide their requirements using a touchscreen interface. The dispensing of the food grains through vending machines will take place automatically with the operation of motors and valves controlled by a micro-controller, after verification of the requirements provided by the user. The same transaction will be reflected immediately in the database along with a message to the customer. All the payments are also handled in a digital mode. In addition, this model also strengthens the Di gital India initiative introduced by the government of India recently.
Security Augmented Symmetric Optical Image Cryptosystem Based on Hybrid Transform Employing Rear Mounted Technique Using Three Different Complex Masks
Lecture Notes on Data Engineering and Communications Technologies, 2021

Procedia Computer Science, 2020
Several software effort estimation techniques based on mathematical formulations have been propos... more Several software effort estimation techniques based on mathematical formulations have been proposed, however there is little consensus on the best technique for effort estimation, which can predict the estimated effort optimally for any given project. Much research has been carried out in finding out the most suitable parameter values for accurate effort estimation. This research investigates the efficacy of Differential Evolution algorithms in improving the parameter values for algorithmic models like CoCoMo and CoCoMo II. Parameter values were obtained by using the three successful mutation strategies in Differential Evolution. The proposed methodology was tested on two datasets from the Promise Repository. Test results were compared with the original CoCoMo and CoCoMo II models based on MMRE. The proposed differential evolution approach predicted the estimated effort more accurately than the original models for the two datasets under consideration.

Procedia Computer Science, 2020
This research work proposes a lens less secure symmetric image encryption system using a novel ch... more This research work proposes a lens less secure symmetric image encryption system using a novel chaotic deterministic phase mask (CDPM) in the light of Fresnel transform (FrT) deploying singular value decomposition (SVD). Here, two CDPM's are used instead of random phase masks (RPM) in Fresnel transform based double random phase encoding (DRPE) scheme with the addition of SVD. The variation of CDPM and SVD amplifies the security of the Fresnel transform based DRPE in comparison to the traditional one. The key space of the proposed cryptosystem is large constituting the complex phase masks (CDPM), the order of SVD, the distance between the significant planes and the wavelength of the Fresnel transform. The system is simple, fast and tough to break. The encrypted image can be sent over an unsecured channel since the security lies in the secrecy of the keys. The enhanced framework resists the possible attacks on traditional DRPE and therefore reinforces DRPE security. The utilization of a novel complex mask that gives advantages of both chaotic map and deterministic phase mask improves the quality of the cryptosystem. The performance analysis and the result outcomes exhibit the efficacy of the designed cryptosystem.

Transactions on Emerging Telecommunications Technologies, 2018
In this paper, we study a mobile indoor visible light communication system that can be used for t... more In this paper, we study a mobile indoor visible light communication system that can be used for the creation of the indoor network infrastructure for sending information besides serving its main purpose of illumination. It uses visible light communication technology where the light-emitting diodes (LEDs) are deployed on the ceiling of the room and the receiver is kept mobile at a certain height from the ground level. This paper focuses on the optimal deployment of the LEDs with an objective to achieve the requisite level of communication performance without any transmission error while maintaining ubiquitous receiver mobility. The hyperheuristic evolutionary algorithm (HypEA) has been implemented to analyze and optimize the energy consumption through optimal placement of LEDs under variation of semiangle values. Furthermore, the implemented optimization algorithm investigates the other system related parameters including average outage area ratio, signal-to-noise ratio, and root mean square delay for a given threshold average bit error ratio. Finally, The obtained results are illustrated through numerical plots, which reveal that the HypEA is efficient in optimizing the system to minimize the overall power consumption under maximum receiver mobility.

Journal of Optical Communications, 2019
There is now an increasing awareness about the possibility of health hazards due to excessive ele... more There is now an increasing awareness about the possibility of health hazards due to excessive electromagnetic radiations around us within the indoor environment. Hence, the alternative communication technologies such as indoor mobile communication system based on LED lighting are gaining more attention in the present scenario. The dual use of LEDs i. e. for illumination as well as for setting up of an indoor communication network infrastructure simultaneously makes it an attractive preposition. The LED lighting based communication system is qualified to be part of green technology networks. This paper investigates the optimal LED placement strategy for such a system to optimize the overall communication system parameters including the transmit power optimization. It is observed that the overall optimization of LEDs improve the signal to noise ratio and also a significant reduction in root mean square delay at lower semi-angle values besides improving the mobile coverage area.

International Journal of Social Computing and Cyber-Physical Systems, 2019
As the amount of data is growing day by day, there is a need to convert it into some effective ma... more As the amount of data is growing day by day, there is a need to convert it into some effective manner so as to extract some useful information from huge data. Text mining is used to perform this task. In this paper, text clustering is used to convert the large data into different cluster forms to extract the meaningful information for the purpose of analysis so as to get the summarised data. Three partitioning-based clustering techniques, i.e., k-means, k-means fast and k-medoids are compared, and a new algorithm named shift k-medoid is proposed, which is hybrid of k-medoid and mean shift clustering algorithms. Cosine similarity, correlation coefficient and Jaccard similarity measures are used to check the performance of the algorithms and two measures, i.e., randomised feature and normalised mutual information (NMI) feature are used to test the accuracy of the algorithms. The outcomes demonstrate that the best performance is accomplished by using the proposed algorithm.
Uploads
Papers by Dr. A. Charan Kumari