RURajyalakshmi Uppada

Rajyalakshmi Uppada

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rajyalakshmi Uppada has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Detection of stages in diabetic retinopathy using computer aided ensemble network

    by Rayudu Prasanti, Rajyalakshmi Uppada, Leela Kumari Balivada

    Diabetic retinopathy (DR) is one of the progressive micro vascular disorders of diabetes and a major cause of preventable blindness in the world. Manual ophthalmologist evaluation is costly in terms of time and more likely to have inter-observer error, whereas current automated methods tend to fail to differentiate between intermediate stages of DR; yet, proper assessment of DR severity is critical to its successful intervention. This paper suggests a framework of hybrid ensemble deep learning (DL) model that incorporates VGG16, InceptionV3 and ResNet50 based on a weighted feature fusion model and a feature-scaled parametric activation (FSPA) model to maximize inter-classes separability. The Kaggle EyePACS dataset containing 35,126 retinal fundus images was used. Image normalization, contrast enhancement, and data augmentation improved robustness to class imbalance. The overall accuracy of the proposed ensemble was 95.0% and the sensitivity and specificity were 92.0 and 94.0 respectively and the quadratic weighted Kappa (QWK) was 0.91, with up to +5% improvements in accuracy over individual convolutional neural network (CNN) baselines. Although there are still limitations to differentiating moderate versus severe DR, the findings demonstrate that the proposed framework enables consistent and reliable DR grading for large-scale clinical screening.

  • Open Access

    Machine learning-enabled joint antenna selection and precoding

    by Monica Nilesh Kalbande, Kanala Sai Madhuri, M. Venkateswara Rao, Saradha Rani Sabbavarapu, Rajyalakshmi Uppada, Lakshmi Durga Rajamahendravarapu

    Joint antenna selection (AS) and precoding design is essential for improving spectral efficiency and energy efficiency in multi-antenna wireless communication systems. However, conventional optimization-based solutions rely on exhaustive search and iterative processing, leading to high computational complexity that limits real-time applicability. This work proposes a machine learning-enabled framework that shifts the computational burden from online operation to offline training. Optimal AS and precoding decisions are first generated offline using model-based optimization under diverse channel conditions. A supervised machine learning model is then trained to learn the relationship between channel state information (CSI) and optimal transmission configurations. During online operation, the trained model enables fast and efficient AS with significantly reduced processing time. Numerical results demonstrate that the proposed approach achieves near-optimal system performance while substantially lowering computational complexity, making it well suited for real-time and next-generation wireless communication systems.

  • Parkinson’s Disease Recognition from EEG Using Memory-Efficient Hexagonal Vision Convolutional Neural Network with Snake Optimizer

    by B. H. Baba Fakruddin Ali, Gagana Putchala, Elangovan Muniyandy, Rajyalakshmi Uppada

    Early detection can help slow down Parkinson’s Disease (PD), which is a progressive neurological condition characterized by immense impairment of motor and cognitive functions. EEG is useful as a non-invasive diagnostic approach because PD alters brain activity. However, the methodologies developed so far using EEG suffer from such issues as interference due to noise, high computational cost, and poor accuracy. This paper presents an efficient Memory-Efficient Hexagonal Vision Convolutional Neural Network optimized with the Snake Optimizer, known as MEHVCNNet[ ]SO, for accurate recognition of PD. This framework first removes noise from the raw EEG signals using a Wavelet Decomposition Threshold Anisotropic Filter (WDTAF), followed by DenseNet-201 that extracts robust features. The classified features obtained are then fed into MEHVCNNet, which is optimized by the use of the Snake Optimizer. This optimization in the proposed MEHVCNNet[ ]SO framework enhances accuracy while reducing computational complexity. The experimental results on three benchmark EEG datasets, San Diego, UNM, and Iowa, indicated an outstanding performance that outperformed current state-of-the-art techniques, with 99.2% accuracy, 98.4% recall, and 0.1% error rate. Offering great potential in clinical applications, these findings demonstrated the proposed MEHVCNNet[ ]SO framework as a reliable and efficient means of early identification of PD.

  • Four-Element MIMO Diversity Antenna for 5G Sub-6 GHz N79 Band Applications and Verified with TCM Analysis

    by Tathababu Addepalli, Sivasubramanyam Medasani, Ch Jyotsna Rani, Chandrasekhar Rao Jetti, Bandi Kiran Kumar, Ch Manohar Kumar, Rajyalakshmi Uppada, Prasanthi Badugu


  • Four‐element equilateral triangular‐shaped MIMO antenna with connected ground for 5G sub:6 GHz N79 and WiFi‐6E band applications

    by Tathababu Addepalli, V. Siva Nagaraju, Sivasubramanyam Medasani, Jetti Chandrasekhar Rao, Prasanthi Badugu, Ch. Manohar Kumar, Rajyalakshmi Uppada, Bandi Kiran Kumar

    Summary: The present communication presents a novel compact microstrip line feed dual‐band four‐element MIMO (multiple input multiple output) antenna for 5G sub‐6GHz N79 and WiFi‐6E bands with a defined size of 48 × 48 × 1.6 mm3. The FR4 substrate used in the construction of the designated antenna has a thickness of 1.6 mm, a relative permittivity of 4.4, and loss tangent values of 0.02. The proposed MIMO architecture consists of four equilateral triangle‐shaped antenna elements on top and ground with inverted L‐shaped stubs on the substrate's bottom layer. The ground structure of the antenna is a connected ground and is formed by defected ground parts which are connected with inverted L‐shaped stubs. The orthogonal structure of the MIMO antenna elements, with four armed square stubs among them, enhanced the isolation between surrounding antennas. The proposed four‐port MIMO antenna is built and tested in to validate design, scattering, and radiation performance, as well as MIMO diversity features. The designed antenna has more than 15 dB isolation and operates at 4.75 GHz from 4.45 to 5.2 GHz (5G sub‐6 GHz N79 band) and 6.3 GHz from 5.95 to 7.15 GHz (WiFi‐6E band). Furthermore, the design provides omnidirectional patterns, high gain (6.5dBi) and efficiency (>95%), a low envelope correlation coefficient (<0.00001) and acceptable diversity gain (10 dB), a good total active refraction coefficient (−10 dB) and low channel capacity loss (0.03 bit/s/Hz), and a considerable mean effective gain (MEG = −3 dB) and MEG ratio (0 dB). Because the simulated and tested results match so well, the antenna is a good candidate for 5G sub‐6 GHz N79 band operations.


  • Automated Computer Aided Diagnosis Using Altered Multi-Phase Level Sets in Application to Categorize the Breast Cancer Biopsy Images

    by Rajyalakshmi Uppada, Satya Prasad Kodati, Sanagapallela Koteswara Rao

    As macroscopic Breast Cancer (BC) imaging diagnostics do not provide satisfied data, microscopic image analysis is used to get optimum cell-nuclei segmentation for image categorization. The paper presents a Novel Hybrid Segmentation Method which uses the energy detail coefficients attained from Non-Subsampled Contourlet Transform for cell-nuclei segmentation of BC histopathological images. NHSM solves the local inhomogeneities problem while preserving all necessary details. The system evaluation is done using training dataset of 98 BC histopathological images and testing dataset of 26 images. Total of 25 segmented features was extracted for classification using Decision Trees, k-Nearest Neighbor, multilayer perceptron, Multiclass-Support Vector Machine (M-SVM). The proposed NHSM segmentation results were undergone through both subjective and objective performance evaluation. Result evaluation proved that NHSM along with Multi Class-Support Vector Machine classifier provides highly precise and accurate classified result for BC tissue images compared to state-of-the-art segmentation methods. Also, the edge detection model initialization is highly robust and insensitive.


  • Image processing based Smart Weed Removal and Organic Fertilizer Sprinkling Bot – A Systematic Review

    by Rajyalakshmi Uppada, Vanaja Kandubothula, Uppalapati Padma

    Most of our country’s economy depends on agriculture production. The production of the crop decreases due to unwanted plants (weeds) and the pests’ infection around the crop. Weeds are removed manually and also controlled by spraying herbicides. To eradicate the pests, fertilizers are used. Due to the fertilizers and herbicides, the fert ility of the soil decreases and also causes pollution. Manually, these processes are time-taking and need more money to complete both the tasks. In this paper, the weed and diseased plant control using machine learning algorithms based on image processing is discussed. Dataset consists of samples of some healthy and diseased crops. The images in the real field are captured through a vision sensor and pre-processed. The resultant image is compared with the threshold value of the trained dataset. Feature Extraction is done through color, size, and shape. Based on the error rate, the system classifies the plant either as a weed or a diseased plant. If the error rate is high, the plant is classified as a weed and the signal is sent to the robotic arm to pluck the plant through serial communication. If the error rate is less, then it is detected as a diseased plant, and the signal is sent to the sprinkler to spray the organic fertilizer to the infected area. If there is no error, then the plant is treated as a healthy plant. Thus, the machine controls the weeds and the diseased plants around the field autonomously.