Leena Ragha

Leena Ragha

Auto-generated profile, based on publicly available information

Leena Ragha

Department of Computer Engineering, Ramrao Adik Institute of Technology, Nerul Navi Mumbai, Maharashtra, India

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
9 August 2023
Verified
Book Chapter
Closed access
PDF file
SPSnehal Paddalwar
Snehal Paddalwar
LRLeena Ragha
Leena Ragha
VMVanita Mane
Vanita Mane
In today’s era, tasks that were meant to be impossible have now become possible with advanced technologies. It is now easy for every one of us to store, manage and share information within seconds. The world has chosen to be digital in every aspect and at a fast pace. Digitalization has made everything work at lightning speed. With all these easy access services, a huge amount of data is generated and shared in an environment in which communication occurs and this environment is nothing but cyber space. Cyber criminals perform illegal activities in this cyber space and we need technologies to prevent them from carrying out such activities. Advancements in technology have also resulted in an increase in cybercrimes. Human interventions and other devices are not sufficient for protection against cyber threats. There is a need for some advanced technology that can be used to defend against them. This chapter focuses on technologies that can play an important role in cyber threat detection, prevention and by using blockchain information, make a real-time decision to counter cyber-attacks. Cyber datasets typically contain several collections of information from various sources generated by the users’ cyber activities. This information can be analyzed to build an intelligent security model using various technologies such as machine learning, deep learning, artificial intelligence, and so on. Additionally, blockchain's capability to provide data confidentiality, integrity and availability can help in mitigating various cyber threats by providing essential secured information. Thus, we can create a cyberinfrastructure using all these technologies to build an automated system capable of mitigating cyber threats and attacks. The proposed solution has four parts. The first part is to aggregate the data from various nodes in the network regarding cyber-criminal activities using artificial intelligence techniques, namely information agents. The second part is to mine the aggregated data further to extract the meaningful data highlighting possible criminal activities using machine learning techniques. The third part is to build the knowledge for classification using deep learning techniques that identify the threats and the system vulnerabilities intelligently and futuristically so that the cyber threats and attacks can be mitigated. The last part is to secure all collected insights so that attackers cannot tamper with it. <!----> <!----> <!----> <!---->

1 January 2023 in International Journal of Medical Engineering and Informatics
Verified
Journal Article
Closed access
HDHimani S. Deshpande
Himani S. Deshpande
LRLeena Ragha
Leena Ragha
Every woman's body is unique and will have some features playing a vital role contributing towards a healthy pregnancy and manually it is difficult to decide the important features to be observed t...

19 December 2024 in International Journal of Image and Graphics
Verified
Journal Article
Closed access
SBSumedha Bhagwat
Sumedha Bhagwat
LRLeena Ragha
Leena Ragha

1 December 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
HDHimani Deshpande
Himani Deshpande
LRLeena Ragha
Leena Ragha
Preterm birth (PTB) is a major cause of child and mother mortality, a PTB classification model can assist in assessing the health condition ahead of time and help avoid complications during childbirth. Mother’s significant feature (MSF) dataset created for this study has features derived from mother’s physical, lifestyle, social and stress attributes. MSF dataset consists of 119 features of 1,000 mothers with 172 preterm and 828 full-term deliveries, resulting in issues of dataset imbalance namely class inseparability and classification bias. To overcome the imbalance issue, a novel algorithm named majority penalizing minority upsampling (MPMU) is proposed. MPMU forms clusters looking into the degree of dataset imbalance, it analyses the composition of each cluster individually and computes the varied penalty for majority class instances. It further balances dataset composition by oversampling minority class instances. MPMU processed dataset is further used to train the proposed 6L-ANN network which finds the probability of occurrence of PTB. The proposed model has shown efficient results on MSF sub-datasets with precision values ranging from 0.90 to 0.97, area under the curve (AUC) between 0.86 to 0.99, and prediction accuracy ranging from 93.04% to 99.47%. Experiment results show that a mother’s lifestyle and stress features have a strong influence on the childbirth outcome.

1 May 2020
Verified
Book Chapter
Closed access
PDF file
BJBharti Joshi
Bharti Joshi
SAShivangi Agarwal
Shivangi Agarwal
LRLeena Ragha
Leena Ragha
NYNavdeep Yadav
Navdeep Yadav