PRABHA SELVARAJ

Dr. PRABHA SELVARAJ

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 February 2023 in Electronics
Verified
Journal Article
Open access
PDF file
ANAnupama Namburu
Anupama Namburu
PSPRABHA SELVARAJ
PRABHA SELVARAJ
SMsenthilkumar mohan
senthilkumar mohan
SRSumathi Ragavanantham
Sumathi Ragavanantham
EEElsayed Tag Eldin
Elsayed Tag Eldin
Forest fires are caused naturally by lightning, high atmospheric temperatures, and dryness. Forest fires have ramifications for both climatic conditions and anthropogenic ecosystems. According to various research studies, there has been a noticeable increase in the frequency of forest fires in India. Between 1 January and 31 March 2022, the country had 136,604 fire points. They activated an alerting system that indicates the location of a forest fire detected using MODIS sensor data from NASA Aqua and Terra satellite images. However, the satellite passes the country only twice and sends the information to the state forest departments. The early detection of forest fires is crucial, as once they reach a certain level, it is hard to control them. Compared with the satellite monitoring and detection of fire incidents, video-based fire detection on the ground identifies the fire at a faster rate. Hence, an unmanned aerial vehicle equipped with a GPS and a high-resolution camera can acquire quality images referencing the fire location. Further, deep learning frameworks can be applied to efficiently classify forest fires. In this paper, a cheaper UAV with extended MobileNet deep learning capability is proposed to classify forest fires (97.26%) and share the detection of forest fires and the GPS location with the state forest departments for timely action.

16 December 2022 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
ABAfiya Parveen Begum
Afiya Parveen Begum
PSPRABHA SELVARAJ
PRABHA SELVARAJ
Deep learning techniques had achieved notability in the healthcare domain and are more specialized in medical imaging. Alzheimer’s disease (AD) enduring nervous system disorder affects elderly senior people with loss of cognitive processes and loss of memory. Early and précised detection of AD is essential for patient medical assistance and potential treatment. Since deep learning algorithms are adequate to analyze the enormous dataset and extract higher-level features from it, unlike traditional machine learning algorithms. This work presents a system-based deep convolutional neural network (DCNN) algorithm to detect AD and its stages. A DCNN and 3D densely connected convolutional neural networks (3D-DCNN) are used to perform the feature analysis and classification task. Finally, the features learned from the DCNN and 3D-DCNN are concatenated to classify disease. Alzheimer's disease neuroimaging initiative (ADNI) dataset is used for experimental analysis. The proposed AD-3DCNN model is compared to existing pre-trained models like Xception, inception V3, mobile Net, and dense Net and has recorded a highest accuracy for predicting different stages of AD. Apart from accuracy, various performance measures are used for evaluating system performance as precision, recall, and F1 score accuracy.

7 January 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
PSPRABHA SELVARAJ
PRABHA SELVARAJ
VBVIJAY KUMAR BURUGARI
VIJAY KUMAR BURUGARI
Gopikrishnan SundaramGopikrishnan Sundaram
Gopikrishnan Sundaram
AAAbdullah Alourani
Abdullah Alourani
Gautam SrivastavaGautam Srivastava
Gautam Srivastava
Mohamed BazaMohamed Baza
Mohamed Baza
Wireless sensors and actuator networks (WSNs) are the physical layer implementation used for many smart applications in this decade in the form of the Internet of Things (IoT) and cyber-physical systems (CPS). Even though many research concerns in WSNs have been answered, the evolution of the WSN into an IoT network has exposed it to many new technical issues, including data security, multi-sensory multi-communication capabilities, energy utilization, and the age of information. Cluster-based data collecting in the Internet of Things has the potential to address concerns with data freshness and energy efficiency. However, it may not offer reliable network data security. This research presents an improved method for data sharing and cluster head (CH) selection using the hybrid Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method in conjunction with glowworm swarm optimization (GSO) strategies based on the energy, trust value, bandwidth, and memory to address this security-enabled, cluster-based data aggregation in the IoT. Next, we aggregate the data after the cluster has been built using a genetic algorithm (GA). After aggregation, the data are encrypted and delivered securely using the TIGSO-EDS architecture. Cuckoo search is used to analyze the data and choose the best route for sending them. The proposed model’s analysis of the results is analyzed, and its uniqueness has been demonstrated via comparison with existing models. TIGSO-EDS reduces energy consumption each round by 12.71–19.96% and increases the percentage of successfully delivered data packets from 2.50% to 5.66%.

25 July 2022 in Innovations in Systems and Software Engineering
Verified
Journal Article
Closed access
PDF file
ANAnupama Namburu
Anupama Namburu
PSPRABHA SELVARAJ
PRABHA SELVARAJ
MVM. Varsha
M. Varsha

1 January 2021
Verified
Book Chapter
Closed access
VBVIJAY KUMAR BURUGARI
VIJAY KUMAR BURUGARI
PSPRABHA SELVARAJ
PRABHA SELVARAJ
KPKanmani Palaniappan
Kanmani Palaniappan
In India, the agriculture sector has an adverse effect and day by day the crop production is getting reduced. So, it is important to identify and implement a solution for the problem in order to increase the production. Smart technologies are introduced in this domain to improve the agriculture industry. The technologies like IoT, big data, cloud-based services, and GPS are gaining its importance in the field of agriculture. There is a rising need due to the requirement of higher precision in crop analysis, transformation of live data from the field and automated farming techniques for further improvement. The expected result of this is to have smart agriculture industry with the implementation of these smart techniques. In this chapter, the authors have discussed the challenges and benefits of IoT and various types of sensor for data acquisition.

1 January 2020
Verified
Book Chapter
Closed access
PSPRABHA SELVARAJ
PRABHA SELVARAJ
SDSumathi Doraikannan
Sumathi Doraikannan
VBVIJAY KUMAR BURUGARI
VIJAY KUMAR BURUGARI
Big data and IoT has its impact on various areas like science, health, engineering, medicine, finance, business, and mainly, the society. Due to the growth in security intelligence, there is a requirement for new techniques which need big data and big data analytics. IoT security does not alone deal with the security of the device, but it also has to care about the web interfaces, cloud services, and other devices that interact with it. There are many techniques used for addressing challenges like privacy of individuals, inference, and aggregation, which makes it possible to re-identify individuals' even though they are removed from a dataset. It is understood that a few security vulnerabilities could lead to insecure web interface. This chapter discusses the challenges in security and how big data can be used for it. It also analyzes the various attacks and threat modeling in detail. Two case studies in two different areas are also discussed.