Salakapuri Rakesh

Salakapuri Rakesh

Auto-generated profile, based on publicly available information

Salakapuri Rakesh

Symbiosis Institute of Technology, Hyderabad Campus, Symbiosis International (Deemed University), Pune, India

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
25 January 2024 in IEEE Access
Verified
Journal Article
Open access
KRKuncham Sreenivasa Rao
Kuncham Sreenivasa Rao
PTPANDURANGA VITAL TERLAPU
PANDURANGA VITAL TERLAPU
DJD. Jayaram
D. Jayaram
KRKalidindi Kishore Raju
Kalidindi Kishore Raju
GKG. Kiran Kumar
G. Kiran Kumar
SRS. Rakesh
S. Rakesh
According to WHO statistics for 2018, there are 1.2 million cases and 700,000 deaths from breast cancer (BC) each year, making it the second-highest cause of mortality for women globally. In recent years, advances in artificial (AI) intelligence and machine (ML) learning have shown incredible potential in increasing the accuracy and efficiency of BC diagnosis. This research describes an intelligent BC image analysis system that leverages the capabilities of transfer learning (TLs) with ensemble stacking ML models. As part of this research, we created a model for analyzing ultrasound BC images using cutting-edge TL models such as Inception V3, VGG-19, and VGG-16. We have implemented stacking of ensemble ML models, including MLP (Multi-Layer Perceptron) with different architectures (10 10, 20 20, and 30 30) and Support Vector Machines (SVM) with RBF and Polynomial kernels. We analyzed the effectiveness of the proposed system in performance parameters (accuracy (CA), sensitivity, specificity, and AUC). Compared to the results with existing BC diagnostic systems, the proposed method (Inception V3 + Staking) is superior, with performance parameters 0.947 of AUC and 0.858 of CA values. The proposed BCUI analysis system consists of data collection, pre-processing, transfer learning, ensemble stacking of ML models, and performance evaluation, with comparative analysis demonstrating its superiority over existing methods.

11 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RSRakesh Salakapuri
Rakesh Salakapuri
NNNaveen Kumar Navuri
Naveen Kumar Navuri
TVThrimurthulu Vobbilineni
Thrimurthulu Vobbilineni
GRG. Ravi
G. Ravi
KKKarthik Karmakonda
Karthik Karmakonda
KVK. Asish Vardhan
K. Asish Vardhan
Most accidents are a result of distractions while driving and road user’s safety is a global concern. The proposed approach integrates advanced deep learning for driver distraction detection with real-time road object recognition to jointly address this problem. The behaviour of a driver is categorized into physical and visual distraction and cognitive distraction using Convolutional Neural Networks (CNN’s) and transfer learning in order to achieve greater accuracy while also consuming lesser computational resources. The YOLO (You Only Look Once) detects vehicles, pedestrians, lane markers, and traffic signals, in real-time. This system has (1) distraction detection and (2) output (or scenario) recognition, which combine other systems and codes to evaluate driving scenarios. A decision-making module evaluates the combined data to assess danger levels and prompt either timely warnings or corrective actions. Our integrated solution will enable a fully-context capable Advanced Driver Assistance System (ADAS) to warn drivers of distractions and hazards, and increases overall situational awareness and reduces accidents. The methodology is supplemented by annotated pictures and videos of driver behavior and road situations in the rain, fog, and low-light scenarios. System reliability under a range of driving scenarios is achieved through data augmentation, model optimization, and transfer learning. State Farm Distracted Driver Dataset, KITTI and MS COCO benchmarks demonstrated better accuracy and efficiency. Integrating existing systems that monitor drivers with systems that are aware of the road would create a multi-target, comprehensive solution that makes both driving safer and helps build upon existing ADAS technology for the better. A real-time and scalable road safety system is established through the integration of CNNs and YOLO deep learning advances. The system’s practicality was further validated through real-time embedded deployment on an NVIDIA Jetson Xavier NX platform, achieving 25 frames per second (FPS) with reduced latency and memory footprint, demonstrating feasibility for resource-constrained Advanced Driver Assistance Systems (ADAS). This paper presents a domain-specific driver monitoring module and a knowledge-based road hazard recognition model that better connect autonomous driving to the human side.

18 March 2024 in MATEC Web of Conferences
Verified
Journal Article
Open access
PDF file
SRS. Rakesh
S. Rakesh
PRP. Kushal Reddy
P. Kushal Reddy
VPV. Prashanth
V. Prashanth
KRK. Srinath Reddy
K. Srinath Reddy
HTR (Handwritten Text Recognition) is the automated process of converting handwritten text into digital text, holding immense value in digitizing historical records and facilitating data entry. Through a combination of image processing and HTR systems decode handwritten characters and words. Pre-processing techniques increases image quality by reducing noise and correcting orientation, while models, like “convolutional neural networks” and “recurrent neural networks”, extract features and capture sequence patterns. Effective HTR models demand diverse training datasets and involve supervised learning to align predicted text with actual transcriptions. Post processing tools, including language models and spell-checkers, refine recognition outcomes. HTR's significance spans historical archive digitization, automated form processing, and aiding individuals with disabilities. Challenges persist in deciphering complex handwriting and handling degraded documents. The integration of deep learning advances HTR, enhancing its accuracy and efficiency, thereby expanding access to handwritten texts and enabling their digital search ability and edit ability. The outcome of this endeavor is a robust and user-friendly tool capable of converting handwritten notes, letters, manuscripts, and other textual materials into editable digital text. This project contributes significantly to bridging the gap between analog and digital information, offering immense potential for archival preservation, data accessibility improved productivity across domains.

4 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RSRakesh Salakapuri
Rakesh Salakapuri
PTPANDURANGA VITAL TERLAPU
PANDURANGA VITAL TERLAPU
KKKishore Raju Kalidindi
Kishore Raju Kalidindi
RBRamesh Naidu Balaka
Ramesh Naidu Balaka
DJD. Jayaram
D. Jayaram
TRT. Ravikumar
T. Ravikumar
Brain tumours (BTs) are severe neurological disorders. They affect more than 308,000 people each year worldwide. The mortality rate is over 251,000 deaths annually (IARC, 2020 reports). Detecting BTs is complex because they vary in nature. Early diagnosis is essential for better survival rates. The study presents a new system for detecting BTs. It combines deep (DL) learning and machine (ML) learning techniques. The system uses advanced models like Inception-V3, ResNet-50, and VGG-16 for feature extraction, and for dimensional reduction, it uses the PCA model. It also employs ensemble methods such as Stacking, k-NN, Gradient Boosting, AdaBoost, Multi-Layer Perceptron (MLP), and Support Vector Machines for classification and predicts the BTs using MRI scans. The MRI scans were resized to 224 × 224 pixels, and pixel intensities were normalized to a [0,1] scale. We apply the Gaussian filter for stability. We use the Keras Image Data Generator for image augmentation. It applied methods like zooming and ± 10% brightness adjustments. The dataset has 5,712 MRI scans. These scans are classified into four groups: Meningioma, No-Tumor, Glioma, and Pituitary. A tenfold cross-validation method helps check if the model is reliable. Deep transfer (TL) learning and ensemble ML models work well together. They showed excellent results in detecting BTs. The stacking ensemble model achieved the highest accuracy across all feature extraction methods, with ResNet-50 features reduced by PCA (500), producing an accuracy of 0.957, 95% CI: 0.948–0.966; AUC: 0.996, 95% CI: 0.989–0.998, significantly outperforming baselines (p < 0.01). Neural networks and gradient-boosting models also show strong performance. The stacking model is robust and reliable. This method is useful for medical applications. Future studies will focus on using multi-modal imaging. This will help improve diagnostic accuracy. The research improves early detection of brain tumors.

1 January 2023 in Journal of Intelligent Systems
Verified
Journal Article
Open access
PDF file
MGMukkamula Venu Gopalachari
Mukkamula Venu Gopalachari
SGSangeeta Gupta
Sangeeta Gupta
SRSalakapuri Rakesh
Salakapuri Rakesh
DJDharmana Jayaram
Dharmana Jayaram
PRPulipati Venkateswara Rao
Pulipati Venkateswara Rao
The finest resource for consumers to evaluate products is online product reviews, and finding such reviews that are accurate and helpful can be difficult. These reviews may sometimes be corrupted, biased, contradictory, or lacking in detail. This opens the door for customer-focused review analysis methods. A method called “Multi-Domain Keyword Extraction using Word Vectors” aims to streamline the customer experience by giving them reviews from several websites together with in-depth assessments of the evaluations. Using the specific model number of the product, inputs are continuously grabbed from different e-commerce websites. Aspects and key phrases in the reviews are properly identified using machine learning, and the average sentiment for each keyword is calculated using context-based sentiment analysis. To precisely discover the keywords in massive texts, word embedding data will be analyzed by machine learning techniques. A unique methodology developed to locate trustworthy reviews considers several criteria that determine what makes a review credible. The experiments on real-time data sets showed better results compared to the existing traditional models.

28 August 2025 in Energy Informatics
Verified
Journal Article
Open access
PDF file
RSRakesh Salakapuri
Rakesh Salakapuri
TPThirukkavalluru Pavankumar
Thirukkavalluru Pavankumar
Accurate electricity load forecasting is essential for the stability, efficiency, and sustainability of modern power systems. However, individual forecasting models often lack generalization across temporal and regional variations and offer limited interpretability. This study proposes a comprehensive meta-learning-based forecast combination framework to enhance both prediction accuracy and model transparency. Using hourly load data from 20 European countries spanning 2018 to 2024, the framework incorporates time-aware features such as hour of the day, day of the week, month, and public holidays. Ten diverse base models—including XGBoost, LightGBM, Random Forest, and LSTM—are trained globally, from which the top five performers are selected (based on R², MAE, and MAPE) and fed into five meta-learners: Ridge Regression, Lasso, Random Forest, Gradient Boosting, and MLP. These meta-models are trained using both model predictions and engineered time features. Experimental results demonstrate superior performance, with the best-performing meta-learner (Random Forest Regressor) achieving a coefficient of determination (R²) of 0.9998 and a Mean Absolute Percentage Error (MAPE) of 0.79%, significantly outperforming traditional ensemble methods. Furthermore, the inclusion of lag features and 5-fold cross-validation led to substantial improvements across all models, including dramatic reductions in MAE (up to 87%), MAPE (up to 88%), and MSE (up to 97%), along with near-perfect R² scores (~ 1.000). Additionally, SHAP-based explainability reveals the contribution of individual time-based features and the influence of each base model within the ensemble, thereby enhancing transparency and supporting practical decision-making.