K.B. Anusha

@vnrvjiet.ac.in

Assistant Professor
Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering &Technology

K.B. Anusha


                     Download Compact PDF  
https://researchid.co/anushakb91

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Engineering, Computer Science, Computer Engineering
14

Scopus Publications

22

Scholar Citations

3

Scholar h-index

Scopus Publications

  • TriXNet-21: An Explainable Multi-Modal Deep Learning Framework for Radical Improvement in Prenatal Down Syndrome Screening
    International Journal of Intelligent Engineering and Systems, 2026
    Prenatal diagnosis of Down syndrome requires accurate, reliable, and interpretable screening methods to support clinical decision-making.TriXNet-21 is an advanced multimodal deep learning architecture designed to integrate ultrasound imaging, clinical parameters, and genetic data using a hybrid CNN-Transformer backbone with an attention-based cross-modal fusion mechanism.The model extracts high-level features from ultrasound images via EfficientNet-B3 and transformer encoders, dynamically combines them with clinical and genetic information, and employs explicit interpretability methods (Grad-CAM visualizations, SHAP values, attention-weight analysis).Clinical and genetic features are simulated, and external testing evaluates generalization of the imaging branch under a distinct site.Experimental evaluation on a comprehensive dataset demonstrates that TriXNet-21 achieves a ROC-AUC of 0.983, surpassing contemporary models BCNN (ROC-AUC: 0.951) and VNL-Net (ROC-AUC: 0.912), with consistently higher sensitivity (98.1%) and specificity (98.3%).These results, validated through rigorous 5-fold cross-validation and independent external testing, underline TriXNet-21's potential as an effective, clinically interpretable, and robust solution for prenatal screening, explicitly addressing critical limitations such as data imbalance and interpretability gaps prevalent in existing frameworks.
  • Seeing, Reading, Hearing Abuse: A Unified Deep Learning Model for DV Detection
    P. Sai Sreenidhi, K. Anusha, D. Sreekala, K. Poojitha, P. Tejaswini, I.V. Shashikala
    2026 International Conference on Communication Computing and Emerging Technologies Ic3et 2026, 2026
  • Multimodal Deep Learning Framework for Prenatal Down Syndrome Diagnosis Using Key Imaging Markers
    K. B. Anusha, Bhukya Krishna, Ch. Ramesh
    2025 IEEE 4th International Conference for Advancement in Technology Iconat 2025, 2025
    Ultrasound scans are commonly used to check Down syndrome in babies before birth. But results can change depending on how skilled the person scanning is and the quality of these images. This study introduces PDL-Marker, a simple deep learning model for detecting Down syndrome using features like nuchal translucency, nasal bone size, femur length, and heart shape. To detect these parts, the model uses YOLOv8 and Faster R-CNN, and to separate them clearly, it uses U-Net. A weighted score system gives higher value to some markers that are more important. Tools like SHAP and Gra-dCAM help to show more clearly which features the model focuses on. From 2D, 3D, and 4D scans taken at different stages and baby positions, the images come. The images go through steps like contrast fixing, noise removal using Gaussian filters, and small detail improvement using super-resolution methods before giving them to the model. Using 4-fold cross-validation, the system was trained. It was compared with two other models called MM-IDS and AG-CNN afterward. A sensitivity of 96.1 % and specificity of 95.8% was achieved by PDL-Marker. AUC score was 0.97, which usually shows the model gives correct results and reduces wrong negatives and positives. Also checked were time and storage. Compared to the other models, PDL-Marker generally needed both less. In hospital systems where resources are low, this may be useful. Yet the study does not include real hospital data. Future plans include testing this model in those real-world setups. Optimizing the model for faster and lighter use and increasing the dataset are also being considered.
  • Analysis on a New Machine Learning-Based Artificial Neural Network Technique for Natural Gas Price Prediction
    K.B. Anusha, Modalavalasa Divya, Mule Ramakrishna Reddy, P. Santhi
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    People use natural gas widely since it is the cleanest energy source. As the world's population grows, natural gas is becoming one of the most important energy sources. It is suggested as one of the ways to increase global environmental pollution reduction and energy production protection. Not only is it the most fuel for civilian employ, but it is moreover an essential component for many mechanical applications and the production of electricity. Because of its important natural advantages, natural gas is becoming more and more important to the future of global vitality, making research and price forecasting imperative. In competitive normal gas marketplaces, the ability to estimate characteristic gas costs has proven to be a highly valuable tool for all showcase members due to its various benefits. Machine learning algorithms have led to the development of widely used tools for estimating common gas costs. The purpose of this project is to investigate data-driven predictive models based on popular ML methods, such as ANN, for common gas cost estimation.
  • A Unique and Effective Deep Learning Approach for Alzheimer’s Disease Prediction
    Sireesha Moturi, M. Mounika Naga Bhavani, K. B. Anusha, Modalavalasa Divya
    Lecture Notes in Networks and Systems, 2025
  • Evaluating and Comparing Deep Learning Methods with Vision Transformers for Musical Key Assessment
    Modalavalasa Divya, K.B. Anusha, D. Venkata Reddy, Mohammed Jany Shaik
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    A composition's major key is an essential component that helps with transposition and arrangement, providing information about the work's harmonic structure, tonal center, and chord progressions. Furthermore, precise key estimate finds use in both academic and industrial contexts, such as in computerized music recommendation systems and computerized music reproduction. By utilizing their successes in various domains, the current publication provides a thorough comparison between the conventional deep learning structures and the upcoming visualization converters. They estimate the outcomes by analyzing six distinct deep learning methods on a specific subset of gathered GTZAN dataset. Our findings show that Dense-Net, a traditional deep neural network architecture, outperforms visual transformers with an impressive 93.64 % accuracy; yet, we examine each deep learning method in more detail to clarify its temporal characteristics. In particular, the SWIN and vision transformers perform better in temporal metrics than the Dense-Net design, but they show a slight decrease in overall effectiveness (1.82 % and 2.39 %, respectively). Our results are noteworthy because they offer a practical instrument for musical key valuation, an area where precise and effective computational methods are essential. Through analyzing the advantages and disadvantages of image transformers and artificial neural networks, we might potentially obtain important data for real-world applications like automatic music transcription and product recommendation systems. Our research opens up new avenues for future advances and motivates further study in this field
  • A Comparative Study of Inception Models for Bone X-Ray Classification and Pathology Detection
    K. Anusha, Karanam Sai Surya, Jadhav Prashanth, Chaluvadi Kartheekeya
    Springer Proceedings in Mathematics and Statistics, 2025
  • Novel and Efficient Classification of Cardiovascular Abnormalities by Machine Learning
    K.B. Anusha, Sudha Rajesh, B. Syed Moinuddin Bokhari, Yangibayev Jonibek Saparbayevich, T Chandra Sekhar Rao, Padmaja Kadiri, B. Venkataramanaiah
    Proceedings of the 9th International Conference on Inventive Systems and Control Icisc 2025, 2025
    Abnormality detection of ECG signal is useful for classifying cardiovascular problems. The most popular techniques for identifying abnormalities in ECG signal is Arrhythmic beat classification. Wavelet transform and Principal component analysis (PCA) and Wavelet transform are applied to ECG signal to extract morphological, spectral features and wavelet features. ECG signal processing and Machine learning classifier based arrhythmic beat classification are implemented to classify into abnormal and normal subjects in proposed research. Discrete wavelet transform and PCA are used to extract feature points in ECG signal and we used Random Forest (RF) classifier and Multinomial Logistic Regression (MLR) classifier for training and testing by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{5}$</tex>-fold cross validation to asset performance and to classify abnormality of ECG signal obtained from patient heart. This proposed work is tested on MIT-BIH arrhythmia public database and overall Accuracy of multinomial logistic regression classifier is (99.6 %) high compared to RF classifier but true positive rate for <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{R F}$</tex> is higher than Multinomial logistic regression. We also conducted experiment and our methodology showed improved results while compared with other machine learning algorithms
  • Leveraging Deep Learning for Accident Detection and Immediate Response System
    K.B. Anusha, Modalavalasa Divya, Modalavalasa Varalakshmi, Ponnana Seshagiri, Kola Geetha, Biddika Sunil Kumar, Arisetty Ganesh, Pidugu pavan Kalyan
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    The increasing rate of road accidents, especially on highways as a result of rash driving, emerged as a major issue. The biggest problem is that of the delay in calling emergency services there by leading to delayed medical care and avoidable deaths. Prompt action can make a big difference in survival chances. This new system takes advantage of sophisticated machine learning algorithms and deep learning architectures image capture, preprocessing, Convolutional Neural Networks (CNN), TensorFlow, PyTorch and OpenCV in order to identify accidents in real time. Once identified, the system immediately sends an alert to the surrounding police stations and hospitals, allowing for a quicker emergency response. Moreover with the integration of Internet of Things (IoT) technology, including vibration sensors, accelerometers, and GPS modules, the system becomes more capable of detecting accidents accurately and sending out alerts. This method increases the accuracy of accident detection, decreases emergency response time, maximizes medical service deployment, reduces financial burdens on the government, and facilitates improved traffic management.
  • Effective Strategies for Mitigating the Gas Leakages Using IoT
    Modalavalasa Divya, Koppara Madhuri, K.B. Anusha, Katta Jathin Kumar, Sistu Lokesh, Palli Kishore Naidu, Paidi Jeeven Sai, Silla Ravi Srinivas
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
    This paper presents a comprehensive strategy for mitigating gas leaks using Internet of Things (IoT) technologies, focusing on enhancing safety in residential and industrial environments. By integrating MQ4, MQ6, and MQ135 gas sensors with an ESP32 microcontroller, the system effectively monitors LPG, methane, and benzene gas levels in real-time. The collected data is uploaded to a Python-based machine learning model hosted on ThingSpeak, where a random forest algorithm analyzes sensor readings to predict gas presence. Upon detection of any gas leak, the system activates alerts by displaying messages on an LCD, illuminating a red LED, and sounding a buzzer. Additionally, the system sends SMS alerts to users via GSM, ensuring immediate notification for potential hazards. This multifaceted approach not only improves responsiveness to gas leaks but also provides users with mobile access to real-time monitoring data. By combining advanced sensor technology with machine learning and IoT capabilities, this solution effectively mitigates risks associated with gas leaks and underscores the transformative potential of IoT in promoting public safety.
  • Missing Person Tracking System Using AI
    Koppara Madhuri, Modalavalasa Varalashmi, K.B Anusha, Kotni Supritha, Ippili Jaswanth, Borige Adarsh Kumar, Kandapu Abhi Ram, Muddapu Naveen
    4th Wireless Antenna and Microwave Symposium Wams 2025, 2025
  • A Scrutiny of Machine Learning Methods for the Detection and Identification of Cyber Intrusion
    Rama Krishna Eluri, Karunakumar Valicharla, Modalavalasa Divya, K.B. Anusha
    2024 International Conference on Advances in Modern Age Technologies for Health and Engineering Science Amathe 2024, 2024
  • Intelligent Fault Detection and Shading Analysis in Photovoltaic Arrays: A Fuzzy Logic Approach for Enhanced Performance and Reliability
    S. Vijaya Madhavi, K. Ramalingeswara Prasad, Bankaru Sonia, Madhavi Mallam, Jami Venkata Suman, K.B. Anusha
    2024 International Conference on Computational Intelligence for Green and Sustainable Technologies Iccigst 2024 Proceedings, 2024
  • Machine learning models and neural network techniques for predicting uddanam ckd
    , K. B. Anusha, Dr. T. Pandu Ranga Vital, , K. Sangeeta, and
    International Journal of Recent Technology and Engineering, 2019

RECENT SCHOLAR PUBLICATIONS

  • A Tri-Modal Deep Learning Framework for Prenatal Trisomy 21 Risk Assessment Using Proxy Multimodal Data
    DCR K.B.Anusha,Dr Bhukya Krishna
    Mathematical Modelling of Engineering Problems 13 (No. 3, March, 2026, pp … , 2026
    2026
  • Efficient prediction of Ocular disease using deep learning model
    KB Anusha
    2025 2nd International Conference on Artificial Intelligence for Innovations … , 2026
    2026
  • TriXNet-21: An Explainable Multi-Modal Deep Learning Framework for Radical Improvement in Prenatal Down Syndrome Screening.
    A KB, K Bhukya
    International Journal of Intelligent Engineering & Systems 19 (2) , 2026
    2026
  • Novel and Efficient Classification of Cardiovascular Abnormalities by Machine Learning
    KB Anusha
    ICISC 2025 , 2025
    2025
  • Multimodal Deep Learning Framework for Prenatal Down Syndrome Diagnosis Using Key Imaging Markers
    KB Anusha, B Krishna, C Ramesh
    2025 IEEE 4th International Conference for Advancement in Technology (ICONAT … , 2025
    2025
  • DeepViT-Detect: A Vision Transformer-Based Framework for Robust Deepfake Video Detection
    KB Anusha
    Techniques - Sciences - Methodes 9 (9), 81-89 , 2025
    2025
  • A Unique and Effective Deep Learning Approach for Alzheimer’s Disease Prediction
    KBAMD Sireesha Moturi, M. Mounika Naga Bhavani
    Included in the following conference series: International Conference on … , 2025
    2025
  • Missing Person Tracking System Using AI
    K Madhuri, M Varalashmi, KB Anusha, K Supritha, I Jaswanth, BA Kumar, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
    Citations: 1
  • Leveraging Deep Learning for Accident Detection and Immediate Response System
    KB Anusha, M Divya, M Varalakshmi, P Seshagiri, K Geetha, BS Kumar, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
  • Evaluating and Comparing Deep Learning Methods with Vision Transformers for Musical Key Assessment
    M Divya, KB Anusha, DV Reddy, MJ Shaik
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Effective Strategies for Mitigating the Gas Leakages Using IoT
    M Divya, K Madhuri, KB Anusha, KJ Kumar, S Lokesh, PK Naidu, PJ Sai, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Analysis on a New Machine Learning-Based Artificial Neural Network Technique for Natural Gas Price Prediction
    KB Anusha, M Divya, MR Reddy, P Santhi
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Energy Harvesting from Ambient Vibrations Using Piezoelectric Materials: A Sustainable Approach To Powering Iot Devices
    KB Anusha
    IJES 2025 11 (ISSN: 2229-7359), 10-18 , 2025
    2025
  • Fraud face detection at atm using yolov5
    M Divya¹, KB Anusha, C KrishnaVeni, TS Sriya, K Jagadeesh
    Proceedings of the International Conference on Computational Innovations and … , 2024
    2024
    Citations: 1
  • Molecule Generation of Drugs Using VAE
    K Anusha, M Rani, B Satvika, P Tarun, G Vaishnavi, SL Raju
    Proceedings of the International Conference on Computational Innovations and … , 2024
    2024
    Citations: 4
  • Intelligent Fault Detection and Shading Analysis in Photovoltaic Arrays: A Fuzzy Logic Approach for Enhanced Performance and Reliability
    SV Madhavi, KR Prasad, B Sonia, M Mallam, JV Suman, KB Anusha
    2024 International Conference on Computational Intelligence for Green and … , 2024
    2024
    Citations: 1
  • A Survey on Disease Detection Using Machine Learning Algorithms
    MVL K.B. Anusha, Modalavalasa Divya, Koppara Madhuri
    Strad Research 11 (ISSUE 6,), ISSN: 0039-2049 , 2024
    2024
  • A scrutiny of machine learning methods for the detection and identification of cyber Intrusion
    RK Eluri, K Valicharla, M Divya, KB Anusha
    2024 International Conference on Advances in Modern Age Technologies for … , 2024
    2024
    Citations: 5
  • AN ARTIFICIAL INTELLIGENCE (AI)-BASED MONITORING SYSTEM AND METHOD FOR A FOOD PROCESSING SYSTEM
    KB Anusha
    2023
  • UTILIZING BLOCK CHAIN & IOT TECHNOLOGY FOR MANAGING BATTERIES IN SMART ELECTRIC VEHICLES
    KB Anusha
    2023

MOST CITED SCHOLAR PUBLICATIONS

  • Machine learning models and neural network techniques for predicting Uddanam CKD
    KB Anusha, TPR Vital, K Sangeeta
    International Journal of Recent Technology and Engineering (IJRTE) 8 (2) , 2019
    2019
    Citations: 9
  • A scrutiny of machine learning methods for the detection and identification of cyber Intrusion
    RK Eluri, K Valicharla, M Divya, KB Anusha
    2024 International Conference on Advances in Modern Age Technologies for … , 2024
    2024
    Citations: 5
  • Molecule Generation of Drugs Using VAE
    K Anusha, M Rani, B Satvika, P Tarun, G Vaishnavi, SL Raju
    Proceedings of the International Conference on Computational Innovations and … , 2024
    2024
    Citations: 4
  • Missing Person Tracking System Using AI
    K Madhuri, M Varalashmi, KB Anusha, K Supritha, I Jaswanth, BA Kumar, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
    Citations: 1
  • Fraud face detection at atm using yolov5
    M Divya¹, KB Anusha, C KrishnaVeni, TS Sriya, K Jagadeesh
    Proceedings of the International Conference on Computational Innovations and … , 2024
    2024
    Citations: 1
  • Intelligent Fault Detection and Shading Analysis in Photovoltaic Arrays: A Fuzzy Logic Approach for Enhanced Performance and Reliability
    SV Madhavi, KR Prasad, B Sonia, M Mallam, JV Suman, KB Anusha
    2024 International Conference on Computational Intelligence for Green and … , 2024
    2024
    Citations: 1
  • A Privacy Policy for Continuous Query Processing through Location Based Services
    MSH K.B.Anusha
    International Journal of Computer Science and Information technologies 6 (6 … , 2015
    2015
    Citations: 1
  • A Tri-Modal Deep Learning Framework for Prenatal Trisomy 21 Risk Assessment Using Proxy Multimodal Data
    DCR K.B.Anusha,Dr Bhukya Krishna
    Mathematical Modelling of Engineering Problems 13 (No. 3, March, 2026, pp … , 2026
    2026
  • Efficient prediction of Ocular disease using deep learning model
    KB Anusha
    2025 2nd International Conference on Artificial Intelligence for Innovations … , 2026
    2026
  • TriXNet-21: An Explainable Multi-Modal Deep Learning Framework for Radical Improvement in Prenatal Down Syndrome Screening.
    A KB, K Bhukya
    International Journal of Intelligent Engineering & Systems 19 (2) , 2026
    2026
  • Novel and Efficient Classification of Cardiovascular Abnormalities by Machine Learning
    KB Anusha
    ICISC 2025 , 2025
    2025
  • Multimodal Deep Learning Framework for Prenatal Down Syndrome Diagnosis Using Key Imaging Markers
    KB Anusha, B Krishna, C Ramesh
    2025 IEEE 4th International Conference for Advancement in Technology (ICONAT … , 2025
    2025
  • DeepViT-Detect: A Vision Transformer-Based Framework for Robust Deepfake Video Detection
    KB Anusha
    Techniques - Sciences - Methodes 9 (9), 81-89 , 2025
    2025
  • A Unique and Effective Deep Learning Approach for Alzheimer’s Disease Prediction
    KBAMD Sireesha Moturi, M. Mounika Naga Bhavani
    Included in the following conference series: International Conference on … , 2025
    2025
  • Leveraging Deep Learning for Accident Detection and Immediate Response System
    KB Anusha, M Divya, M Varalakshmi, P Seshagiri, K Geetha, BS Kumar, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-5 , 2025
    2025
  • Evaluating and Comparing Deep Learning Methods with Vision Transformers for Musical Key Assessment
    M Divya, KB Anusha, DV Reddy, MJ Shaik
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Effective Strategies for Mitigating the Gas Leakages Using IoT
    M Divya, K Madhuri, KB Anusha, KJ Kumar, S Lokesh, PK Naidu, PJ Sai, ...
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Analysis on a New Machine Learning-Based Artificial Neural Network Technique for Natural Gas Price Prediction
    KB Anusha, M Divya, MR Reddy, P Santhi
    2025 IEEE Wireless Antenna and Microwave Symposium (WAMS), 1-6 , 2025
    2025
  • Energy Harvesting from Ambient Vibrations Using Piezoelectric Materials: A Sustainable Approach To Powering Iot Devices
    KB Anusha
    IJES 2025 11 (ISSN: 2229-7359), 10-18 , 2025
    2025
  • A Survey on Disease Detection Using Machine Learning Algorithms
    MVL K.B. Anusha, Modalavalasa Divya, Koppara Madhuri
    Strad Research 11 (ISSUE 6,), ISSN: 0039-2049 , 2024
    2024