Ramesh Babu Pittala

Prof. Ramesh Babu Pittala

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
23 February 2022
Verified
Conference Paper
Closed access
RPRamesh Babu Pittala
Ramesh Babu Pittala
BTB.R Tejopriya
B.R Tejopriya
EPEsha Pala
Esha Pala
Artificial Neural Networks is one of the most preferable topics in Machine Learning. Various applications like Google Assistant, Google Translator, Apple Siri, etc are implemented on these Artificial Neural Networks. All these applications are based on Speech Recognition. Nowadays Speech Recognition plays a prominent role in many fields, the machine can recognize words and sentences in spoken language and translate them into machine-readable formats. Different methods of speech recognition include Hidden Markov Model (HMM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), etc. The main objective of this paper is to know how MFCC is helpful in the recognition of speech commands spoken by the speakers using Convolutional Neural Networks. Convolutional neural networks help train the machine to recognize the spoken words by using Speech Recognition.

1 December 2016
Verified
Conference Paper
Closed access
RPRamesh Babu Pittala
Ramesh Babu Pittala
MRM. Nagabhushana Rao
M. Nagabhushana Rao
MKM. Shiva Kumar
M. Shiva Kumar
Correctness and completeness are the two major factors in the medical field to take the accurate decision for the treatment in a span of time. Automated Patient Records (APR) will help to the Health Management Organization (HMO) to take the decision on any specific disease. Among the huge APR's Retrieving the data is very important to HMOs. Proposed Collocation Rules in the spatial data mining will optimize the information on every level and able produce the efficient results to take the decision in every aspect. In this paper, we proposed collocation rules to find the dengue disease affected areas in a specified region and displayed in a map. HMOs will identify the areas along with the severity of the symptoms and will identify the preventive methodology for the disease.

11 February 2026 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
RPRamesh Babu Pittala
Ramesh Babu Pittala
MKMedikonda Asha Kiran
Medikonda Asha Kiran
NSNiteesha Sharma
Niteesha Sharma
MTManyam Thaile
Manyam Thaile
KSKranthi Kumar Singamaneni
Kranthi Kumar Singamaneni
PNPeddada Nagamani
Peddada Nagamani
In text classification tasks with complex models and high-stakes domains the alignment between predictions and explanations tends to be weak because post-hoc explainability methods operate independent of model training. In this paper, we suggest ATM-AM - an approach based on the Gated Recurrent Unit (GRU) that combines Bahdanau attention with a training-time SHAP-backed alignment objective to offer real-time, context-aware interpretability without trade-off in predictive performance. The model is tested over three frequently-used sentiment analysis datasets (IMDbhttps://huggingface.co/datasets/imdb, Amazon Reviews https://www.kaggle.com/datasets/bittlingmayer/amazonreviews, and SST-2. https://huggingface.co/datasets/glue/viewer/sst2) yielding accuracy scores of 91.8%, 89.5%, and 90.0% with respective F1-scores of 0.899, 0.877, and 0.889 respectively, on each dataset. We also average our measurements over three runs for statistical soundness. The additional training latency added by ATM-AM is quite modest (13–18%), and the inference time remains short (3–4 ms per sample), rendering it feasible to be deployed in real-time. A user-centered interpretability study with 30 participants obtained an average rating of 4.6/5 showing that users trust the explanations produced by our proposed model. These observations posit ATM-AM as a feasible and interpretable solution Text Classification in contexts where model behavior needs to be accountable and reliable.

7 November 2024 in The Bioscan
Verified
Journal Article
Open access
PDF file
PGP. Gunasekaran
P. Gunasekaran
VSV Sudha
V Sudha
NMNarendra B Mustare
Narendra B Mustare
RPRamesh Babu Pittala
Ramesh Babu Pittala
AJAZHAGU JAISUDHAN JAISUDHAN
AZHAGU JAISUDHAN JAISUDHAN
GBG. Charles Babu
G. Charles Babu
Medical guidance systems make extensive use of machine learning methods. A medical diagnostic aids in obtaining several characteristics that correspond to the various illness variants. It is probable to have redundant, irrelevant, and relevant aspects that reflect a disease with the use of various diagnostic techniques. The illness may be incorrectly classified due to redundant characteristics. Consequently, the amount of the data & computational complexity is decreased by eliminating the superfluous characteristics. Finding a suitable feature subset for efficient classification is a challenging problem. This calls for a thorough search over the dataset's sample space. This paper's primary goal is to identify the best feature subset with higher classification accuracy for the diagnosis of cardiovascular diseases using a metaheuristic algorithm. The best traits for illness detection are found using the Artificial Bee Colony (ABC) method, which is based on swarm intelligence. Support Vector Machine (SVM) categorisation is employed to assess ABC's capability. Dataset of Indian Heart Disease is used to verify the suggested algorithm's performance. According to the experimental findings, ABC-SVM performs well when compared with feature selection via reverse ranking. In addition, the results show that with only eight characteristics, the proposed approach accomplished maximum classification precision.

2 May 2026
Verified
Book Chapter
Closed access
RMRampelli Manojkumar
Rampelli Manojkumar
GVGundu Venu
Gundu Venu
SASuresh Kumar Annam
Suresh Kumar Annam
RPRamesh Babu Pittala
Ramesh Babu Pittala
APAnji Reddy Polu
Anji Reddy Polu
Yuvaraj ThangarajYuvaraj Thangaraj
Yuvaraj Thangaraj
This chapter explores the integration of Artificial Intelligence (AI) and Digital Twin (DT) technologies for intelligent condition monitoring and fault detection in wind energy systems. It highlights the limitations of traditional approaches and presents AI-based models for fault prediction, anomaly detection, and remaining useful life estimation. The layered architecture of DTs, their real-time synchronization, and hybrid AI-DT frameworks for predictive maintenance are discussed. The chapter also examines challenges such as data integrity, scalability, and cybersecurity while outlining emerging trends like federated learning and quantum digital twins for resilient and sustainable wind farm operations.

7 November 2024 in The Bioscan
Verified
Journal Article
Open access
PDF file
RPRamesh Babu Pittala
Ramesh Babu Pittala
NMNarendra B Mustare
Narendra B Mustare
KLKavitha G L
Kavitha G L
AJAZHAGU JAISUDHAN JAISUDHAN
AZHAGU JAISUDHAN JAISUDHAN
DPDr SUBBA RAO POLAMURI
Dr SUBBA RAO POLAMURI
Predicting cardiovascular illness via the integration of datasets and deep neural networks using an asynchronous learning methodology. Healthcare experts see the prediction of cardiac disease as a critical endeavour, while deep learning has shown considerable potential in accomplishing this objective. This research study presents a unique methodology termed the Asynchronous Federated Deep Learning Approach aimed at Cardiac Predictions (AFLCP), which integrates a heart disease dataset along with DNN through an asynchronous learning strategy. Suggested method utilises an asynchronous parameter update mechanism for deep neural networks and integrates a temporally weighted aggregate strategy to improve the convergence and accuracy of core model. The efficacy of the proposed AFLCP technique is assessed using two datasets across several DNN architectures, revealing that proposed AFLCP method surpasses baseline technique for communication expenses and model correctness.