Vedula Sitharamulu

Vedula Sitharamulu

Auto-generated profile, based on publicly available information

Vedula Sitharamulu

Computer Science and Engineering, GITAM School of Technology, GITAM (Deemed to be University), Hyderabad, India

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
6 September 2023 in IEEE Access
Verified
Journal Article
Open access
GSG. Sucharitha
G. Sucharitha
VSVedula Sitharamulu
Vedula Sitharamulu
Sachi Nandan MohantySachi Nandan Mohanty
Sachi Nandan Mohanty
Anjanna MattaAnjanna Matta
Anjanna Matta
DJDeepa Jose
Deepa Jose
The use of encryption is essential to protect sensitive data, but it often poses challenges when it comes to locating and retrieving information without decryption. Searchable encryption provides an effective mechanism that achieves secure search over encrypted data. In this paper a new approach to address the fine-grained search and to protect sensitive data, Blockchain Assisted ciphertext policy decentralized attribute-based encryption (BA-CP-DABE) in cloud has been developed. The CP-DABE is employed to manage data access, secure key generation, while the immutability of blockchain ensures the confidentiality of ciphertext. By leveraging searchable encryption, it becomes possible to securely search encrypted data stored on the blockchain. Keywords are encrypted using attribute-based encryption and stored on a remote server, along with the corresponding ciphertext in the blockchain. One of the significant challenges in this approach is the assumptions-based technique i.e., bilinear mapping, which involves keyword ciphertext and trapdoor security. However, through extensive numerical experiments, the system has demonstrated its ability to generate key and trapdoor structures, as well as effectively find keywords within the encrypted data.

1 October 2024 in Egyptian Informatics Journal
Verified
Journal Article
Open access
VSV. Sitharamulu
V. Sitharamulu
GSG. Sucharitha
G. Sucharitha
SMSachi Nandan Mohanty
Sachi Nandan Mohanty
SJShaik Janbhasha
Shaik Janbhasha
DKD. Kothandaraman
D. Kothandaraman

2 August 2025 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
SJShaik Janbhasha
Shaik Janbhasha
CKC. H. N. Santhosh Kumar
C. H. N. Santhosh Kumar
VSVedula Sitharamulu
Vedula Sitharamulu
BBB. N. V. Madhu Babu
B. N. V. Madhu Babu
HBHanumantha Rao Battu
Hanumantha Rao Battu
KVK. Venkataramana
K. Venkataramana
Digital payment systems are increasingly used to complete everyday transactions; however, their digital nature exposes users to the risk of fraudulent activity, necessitating advanced detection techniques to ensure security. This study proposes a hybrid fraud detection model for digital wallet transactions by integrating Adversarial Autoencoders (AAE) and Gated Recurrent Units (GRU), combining AAE's ability to learns robust latent representations, and GRU's ability to capture temporal dependencies within transaction sequences. The proposed method outperforms existing approaches, achieving 99% accuracy, 99% recall, 98% F1-score, 99% precision, and 99.4% Area Under the Curve (AUC). By effectively reducing both false positives and false negatives, the model improves fraud detection and mitigates financial risks in digital transactions.

6 October 2025 in Engineering, Technology & Applied Science Research
Verified
Journal Article
Open access
PDF file
VSV. Sitharamulu
V. Sitharamulu
SMSreerama Murty Maturi
Sreerama Murty Maturi
MMM. Murugesan
M. Murugesan
DRDudekula Mahammad Rafi
Dudekula Mahammad Rafi
HBHanumantha Rao Battu
Hanumantha Rao Battu
Cardiovascular Disease (CVD) is a critical global health concern requiring efficient early prediction. This study evaluates Machine Learning (ML) algorithms—Logistic Regression (LR), Light Gradient Boosting Machine (LGBM), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbors (K-NN)—for forecasting the cardiovascular risk. By analyzing key patient features, such as cholesterol, blood pressure, and lifestyle, these models classify individuals into low or high-risk categories. The findings demonstrate that LGBM and RF achieve superior performance, both reaching 99% accuracy, precision, recall, and F1-score, alongside high ROC-Area Under the Curve (AUC) values. This research provides robust, data-driven tools to enhance the timely diagnosis and support preventative medical strategies, ultimately improving the patient outcomes.

2 December 2025 in Discover Computing
Verified
Journal Article
Open access
PDF file
VSV. Sitharamulu
V. Sitharamulu
SGSucharitha Gowni
Sucharitha Gowni
SGSrihari Babu Gole
Srihari Babu Gole
HBHanumantha Rao Battu
Hanumantha Rao Battu
OOOnur Osman
Onur Osman
Jawad RasheedJawad Rasheed
Jawad Rasheed
Web 3.0 represents an advanced internet framework that combines technologies such as blockchain and semantic communication to enable decentralized, transparent data exchange. While semantic communication reduces redundancy by transmitting contextual meaning rather than raw data and existing systems lack a cohesive integration strategy, further, the centralized models struggle with efficient semantic sharing and valuation. The work proposed integration framework of semantic web communication with blockchain to enhance reliable web 3.0 data sharing. A novel “Proof of Semantic” mechanism tackles data integrity issues, ensuring only high-quality semantic inputs. The approach also elucidates the implementation of the bottleneck method and state channels. The computational load is optimized using a semantic shared protocol across the web. Further, a hierarchical Stackelberg game model optimizes semantic pricing, balancing stakeholder incentives. Evaluations confirm the framework’s efficacy, achieving reduction in network load without compromising accuracy compared to conventional approaches.

30 May 2016 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
VRV. Sitha Ramulu
V. Sitha Ramulu
BBB. Raveendra Babu
B. Raveendra Babu
Background and Objectives: Relational Databases have got such a great importance in the current global enterprises, such that they are widely and extensively used for storing and managing data. The objective includes the comparison techniques with older approaches and present approach depicts best accessibility to read/write access to the data. The data semantics are not directly imposed on the relational schema. In fact, they are direct towards the application level. Methods/Statistical Analysis: There are several mapping techniques involved by many semantic web technologies and several ontologies that enhance data utilization among many applications. The techniques also embed data reusability for many number of times across community boundaries, large enterprises etc. The current strategies depend on the Read only access either through Linked data or SPARQL. The implemented approach underwent the test cases with various instances using interfaces. The interfaces falling under semantic web frameworks for accessing of data by these approaches include RDF2GO: ChangeSet, Sesame and Jena. Findings: The feasibility factors for conversion of relational data schema to the RDF do not give satisfactory remarks. Hence, to increase the feasibility scope for conversions, we used and adopted an approach called "Mediation Approach" for converting RDF's to RDB's. In the current context we present an extensible platform called RDB-to-RDF Ingression (R2RI) that supports Read/write access to the data residing in the relational schema. The entitled platform uses the technique of "encapsulation" as the translation logic during translation process in the core layer. This translation logic proves itself to be the foundation for the rest of the interfaces existing in the interface layer. At later stages, we exposed the general concepts about the architectural patterns, mappings of RDB-to-RDF and emphasizing special focus on our mediation platform "R2RI" duly enhancing a protocol to provide parsing feedback protocol to the client. We also present the prototype implementation process followed by its performance calculations.