N Silpa

Mrs. N Silpa


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
23 June 2023
Verified
Conference Paper
Closed access
NSN Silpa
N Silpa
MRMaheswara Rao V V R
Maheswara Rao V V R
MSM. Venkata Subbarao
M. Venkata Subbarao
PMPradeep Mullangi
Pradeep Mullangi
CGChalla Ram Grandhi
Challa Ram Grandhi
AKAdina Karunasri
Adina Karunasri
Effective teamwork is essential to the success of organizations, necessitating that executives implement efficient strategies for fostering collaboration. This paper proposes a novel approach to team development by analyzing employees' tweets with the Myers-Briggs Type Indicator (MBTI). We accurately determine the personality traits of employees based on their processed tweets by employing deep learning techniques, specifically the RNN-LSTM. In addition, we create a recommendation engine that employs the MBTI personality types to generate optimal team compositions. Using the designated dataset, our empirical analysis demonstrates that the RNN-LSTM model outperforms alternative RNN models and baseline machine learning algorithms for accurately predicting personality. The performance of the proposed model is evaluated based on its accuracy, precision, recall, and F1 score, providing a thorough and evidence-based methodology for team building recommendations. This study contributes to the field by presenting a data-driven strategy for fostering collaboration and boosting organizational morale. By utilizing the proposed study, leaders can gain valuable insights into employee personalities, allowing them to form cohesive teams that contribute to increased productivity and employee retention.

1 March 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
Shiva Shankar ReddyShiva Shankar Reddy
Shiva Shankar Reddy
VRVenkata Rama Maheswara Rao
Venkata Rama Maheswara Rao
PVPriyadarshini Voosala
Priyadarshini Voosala
NSN Silpa
N Silpa
You only look once version 4 (YOLOv4) is a deep-learning object detection algorithm. It is used to decrease parameters and simplify network structures, making it suited for mobile and embedded device development. The YOLO detector can foresee an object's Class, bounding box, and probability of that Object's Class being found inside that bounding box. A probability value for each bounding box represents the likelihood of a given item class in that bounding box. Global features, channel attention, and special attention are also applied to extract more compelling information. Finally, the model combines the auxiliary and backbone networks to create the YOLOv4's entire network topology. Using custom functions developed upon YOLOv4, we get the count of the objects and a crop around the objects detected with a confidence score that specifies the probability of the thing seen being the same Class as predicted by YOLOv4. A confidence threshold is implemented to eliminate the detections with low confidence.

1 April 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
Shiva Shankar ReddyShiva Shankar Reddy
Shiva Shankar Reddy
VRVeeranki V. R. Maheswara Rao
Veeranki V. R. Maheswara Rao
KSKalidindi Sravani
Kalidindi Sravani
NSN Silpa
N Silpa
Evaluating image features is a significant step in image processing in applications like number plate detection, vehicle tracking and many image processing-based applications. Image processing-based applications need accurate parts to get the best outcomes. Feature detection is done based on various feature detection techniques. The proposed system aims to get the best feature detector based on the input images by evaluating the image features. For assessing the image features, the proposed system worked on various descriptors like oriented FAST and rotated brief (ORB), learned arrangements of three patch codes (LATCH), binary robust independent elementary features (BRIEF), and binary robust invariant scalable keypoints (BRISK) to extract and evaluate the features using K-nearest neighbor (KNN)-matching and retrieve the inliers of the matching. Each descriptor produces different matching features and inliers; with the matchings and inliers, the inlier ratio calculates to show the analysis. To increase performance, we also examine adding depth information to descriptors.


5 April 2024 in Journal of Machine and Computing
Verified
Journal Article
Open access
KMKarrar S. Mohsin
Karrar S. Mohsin
JMJhansilakshmi Mettu
Jhansilakshmi Mettu
CMChinnam Madhuri
Chinnam Madhuri
GUGude Usharani
Gude Usharani
NSN Silpa
N Silpa
Pachipala YellammaPachipala Yellamma
Pachipala Yellamma
Traffic congestion has made city planning and citizen well-being difficult due to fast city growth and the increasing number of vehicles. Traditional traffic management fails to solve urban transportation's ever-changing issues. Traffic prediction and control systems are vital for enhancing Traffic Flow (TF) and minimizing congestion. Smart cities need advanced prediction models to regulate urban TF as traffic management becomes more complex. This paper introduces a hybrid Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) model for better real-time traffic management. The hybrid model combines CNNs' spatial feature extraction with GNNs' structural and relational data processing to analyze and predict traffic conditions. Traffic camera images are pre-processed to extract spatial characteristics. Traffic network graph construction is used for structural research. The model accurately captures traffic topology and space. The proposed method sequentially processes spatial data with CNNs and integrates them with GNNs. The final hybrid model is trained on one year of traffic data from diverse circumstances and events. The hybrid model is compared to CNN, GNN, and traditional Traffic Prediction Models (TPM) like ARIMA and SVM utilizing MAE, RMSE, and MAPE. The hybrid GNN+CNN model outperforms benchmark models with lower MAE, RMSE, and MAPE across several prediction intervals.

12 July 2024
Verified
Conference Paper
Closed access
NSN Silpa
N Silpa
RRR Suneetha Rani
R Suneetha Rani
MRMaheswara Rao V V R
Maheswara Rao V V R
ANAmrutha N
Amrutha N
SRShiva Shankar Reddy
Shiva Shankar Reddy
RKRamachandra Rao Kurada
Ramachandra Rao Kurada
Web page categorization plays a crucial role in organizing the ever-growing repository of online content, facilitating improved search functionality, enabling personalized content delivery, enhancing recommendation systems, optimizing targeted advertising, and spotlighting user interests. Utilizing the predictive capabilities of Ensemble Machine Learning (EML) models is essential for automating the web page classification process, ensuring a more efficient identification of user preferences in the dynamic landscape of online content. Towards this objective, the present research study introduces the Ensemble Machine Learning-based Webpage Categorization System (EML-WCS), concentrating on all essential stages of the classification process. The EML-WCS gathers a large and open-source dataset, ensuring a representative sample of web content across various key domains. The pre-processing phase entails a series of text processing steps, including replacing separators, removing URLs, punctuation, and numbers, eliminating stop words, and performing lemmatization to enhance the quality of the provided text data. The EML-WCS leverages the ensemble capabilities of Random Forest and XGBoost techniques for multi-class classification of webpages based on content, achieving an impressive accuracy of 99.69% and 96.04%, respectively. The outcomes of this study have implications for industries spanning from e-commerce to content recommendation systems, highlighting the pivotal role of understanding and responding to user interests for achieving optimal user satisfaction and engagement.