B. Raja Koti

B. Raja Koti

Auto-generated profile, based on publicly available information

B. Raja Koti

Department of CSE, GITAM School of technology, GITAM University, Visakhapatnam, Andhra Pradesh, India

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
20 August 2017 in International Journal of Advanced Research in Computer Science
Verified
Journal Article
Open access
BKB. Raja Koti
B. Raja Koti
International Journal of Advanced Research in Computer Science (IJARCS) is a scholarly online, open access, peer-reviewed, interdisciplinary, bimonthly, and fully refereed journal focusing on theories, methods and applications in computer science and relevant fields.The journal covers all areas of computer science, like computer engineering, computer security, biometrics and bioinformatics, database management system Artificial Intelligence, Software Engineering and more. We publish original research articles, review articles and technical notes.

5 December 2024 in International Journal of Online and Biomedical Engineering (iJOE)
Verified
Journal Article
Open access
PDF file
AKArchana Kalidindi
Archana Kalidindi
RBRaja Koti B.
Raja Koti B.
SCSrilakshmi Ch.
Srilakshmi Ch.
KBKrishna Mohan Buddaraju
Krishna Mohan Buddaraju
AKAkash Reddy Kandi
Akash Reddy Kandi
GMGopi Sai Srinivas Makutam
Gopi Sai Srinivas Makutam
The increase of illegal endeavors and malware traffic inside the Darknet presents a detracting challenge to cybersecurity. This study deals with the problems by applying leading machine learning (ML) techniques to reduce the use of the Darknet misuse while still preserving the aura of mystery, anonymity, and privacy. Leveraging the Darknet CIC2020 dataset, the research performs binary and multiclass classification, which are based on modern algorithms, with autoencoder being one of them. Convolutional neural networks (CNN), long short-term memory (LSTM), and XGBoost were used to discriminate the complicated systems. Results indicate XGBoost performed better in cases of both binary and multi-class classifications showing tremendous reliability, accuracy, recall, and F1-score. Furthermore, the study extends its scope by introducing ensemble techniques such as voting classifier and stacking classifier, aiming to enhance predictive accuracy by joining diverse base estimators. Combining autoencoder and XGBoost, alongside investigating the CNN+LSTM architecture, enhances the model’s effectiveness. These hybrid approaches are implemented so that they can affect the components of various algorithms, creating more finely grained acting metrics on a per-order basis. This approach is to analyze Darknet traffic patterns that enable us to understand the importance of Internet security measures.

5 February 2018 in International Journal of Engineering & Technology
Verified
Journal Article
Closed access
PDF file
BKB. Raja Koti
B. Raja Koti
GKG.V.S. Raj Kumar
G.V.S. Raj Kumar
The Digital world is advancing in terms of technological development day by day, resulting in an instantaneous rise in Data. This massive amount of Data has introduced the thought of Big Data, which has attracted both the business and IT sectors leaving the scope for huge opportunities. In turn, securing this massive data has become a challenging issue in the field of Information and Communication Technology. In this paper, we have carried out the work on business information sharing data which contains some sensitive information to investigate the security challenges of data in the field of business communication. The article an attempt is also made to identify the user’s intention or behavior during the navigation of data. The greatest challenge that is associated here is to prevent the integrity of the data while sharing the data from organization to the third party, where there exist huge chances of data loss, leakages or alteration. This paper highlights the concepts of data leakage, the techniques to detect the data leakage and the process of protecting the leaked data based on encrypted form.

1 January 2018 in International Journal of Advanced Computer Science and Applications
Verified
Journal Article
Open access
PDF file
BKB. Raja Koti
B. Raja Koti
G.G.
G.
Y.Y.
Y.
K.K.
K.
GKG. V. S. Raj Kumar
G. V. S. Raj Kumar
YSY. Srinivas
Y. Srinivas
Enormous increase in data in the current world presents a major threat to the organization. Most of the organization maintains some sort of data that is sensitive and must be protected against the loss and leakage. In the IT field, the large amount of data will be exchanged between the multiple points at every moment. During this allocation of the data from the organization to the third party, there are enormous probabilities of data loss, leakages or alteration. Mostly an email is being utilized for correspondence in the working environment and from web-based like logins to ledgers; thereby an email is turning into a standard business application. An email can be abused to leave organization's elusive information open to trade off. Along these lines, it might be of little surprise that muggings on messages are normal and these issues need to be addressed. This paper completely focuses on the concept of data leakage, the technique to detect the data leakage and prevention.

30 November 2024 in INTERNATIONAL JOURNAL OF EXPERIMENTAL RESEARCH AND REVIEW
Verified
Journal Article
Open access
PDF file
SDS. Sarojini Devi
S. Sarojini Devi
BPBora Pavani
Bora Pavani
MVM. Pavan Kalyan Varma
M. Pavan Kalyan Varma
RBRaja Koti. B
Raja Koti. B
KSKrishna Rupendra Singh
Krishna Rupendra Singh
BSBadugu Samatha
Badugu Samatha
The present online application employs a contemporary artificial intelligence (AI)-driven solution to transform the process of diagnosing skin disorders. This research uses DenseNet201 and VGG19, two of the most advanced DNN architectures, to build a Convolutional Neural Network (CNN). The enhanced predictive models, built with a dataset of 930 photos divided into ten groups and strengthened by data augmentation, produce remarkably accurate predictions for a range of skin conditions. The website's intelligent chatbot is a standout feature; it was built to answer questions about skin diagnoses, treatment options, and more. This chatbot is designed to help users understand their diagnostic results and find their way on the health journey. In addition, it keeps track of users' prediction histories, so they may learn a lot about their skin's health over time and make educated choices about their medical treatments. In addition, by giving people a place to talk about their struggles and get advice from others, the website fosters a supportive community. The emphasis here is on real human connections, which are great for learning from one another and helping one another out. Firebase facilitates efficient data administration for monitoring forecasts and engaging with the community, while Replit and Voice flow support the CNN model, chatbot, and forum, guaranteeing optimal performance. By integrating cutting-edge AI with a user-centric approach, this web application empowers users with the tools, insights, and support necessary for proactive skin health management.

30 November 2019 in International Journal of Innovative Technology and Exploring Engineering
Verified
Journal Article
Closed access
BKB. Raja Koti
B. Raja Koti
GKG. V. S. Raj Kumar
G. V. S. Raj Kumar
KKK. Naveen Kumar
K. Naveen Kumar
In this modern era, all organizations depend on internet and data so, maintaining of all data is done by the third party in large organizations. But in this present on-developing world, one have to share the data inside or outside the organization which incorporates the sensitive data of the venture moreover. Data of the organization have sensitive data which should not share with any others but unfortunately, that data was there in the third party hands so; we need to protect the data and also have to identify the guilt agent. For this, we propose a model that would evaluate and correctly identifies guilt agents, for which a recursive partitioning has been created which is a decision tree that spills data in to the sub partitions and does the easiest way to get alert and at least one specialist or it can autonomously accumulate by some different means. The main intention of the model is to secure sensitive information by recognizing the leakage and distinguish the guilt agent.