Harish Reddy Gantla

Prof. Harish Reddy Gantla

orcid

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
9 May 2025
Verified
Book Chapter
Closed access
IKIndra Kishor
Indra Kishor
PGPriya Goyal
Priya Goyal
Harish Reddy GantlaHarish Reddy Gantla
Harish Reddy Gantla
PGParul Goyal
Parul Goyal
UMUdit Mamodiya
Udit Mamodiya
Motor disabilities resulting from stroke affect millions of people worldwide and necessitate long-term rehabilitation. . This research develops an AI-driven haptic rehabilitation system (HAIRL-Stroke) with deep reinforcement learning (DRL) and real-time biomechanical sensing for enhancing stroke patient motor recovery. The system adapts to learn to dynamically optimize adaptive haptic force feedback, adjusting therapy in relation to patient progress and delivering personalized rehabilitation exercises. The conceptualized system makes use of wearable haptic gloves and exoskeletons along with biomechanical sensors to sense muscle activation, joint mobility, and movement response. results demonstrate that HAIRL-Stroke boosts muscle activation by 42%, reduces rehabilitation time by 35%, and improves neuromotor coordination by 47% when compared to traditional physiotherapy. The AI-based system has an 18 ms average response latency, providing real-time adaptivity. Patients have enhanced grip strength, motor ability, and therapy participation with shorter recovery times for functions.

30 June 2023
Verified
Book Chapter
Closed access
PRPankaj Rahi
Pankaj Rahi
MDMonika Dandotiya
Monika Dandotiya
Harish Reddy GantlaHarish Reddy Gantla
Harish Reddy Gantla
RNRegonda Nagaraju
Regonda Nagaraju
GSGandla Shivakanth
Gandla Shivakanth
VAVandana Ahuja
Vandana Ahuja
Cognitive business processing must be gradually implemented in the modern world. Cognitive computing software uses machine learning and pattern analysis to simulate reasoning, deduction, learning, and perception. Cognitive computing simulates human intelligence with AI and signal processing. It aids human-computer interaction, natural language processing, speech and image recognition, and HCI machine learning. Hospital and healthcare management systems can track pandemics and diseases using social media data. Cognitive computing in healthcare improves disease management and patient outcomes. The healthcare applications of cognitive computing for the benefit of the large community. Stable network and cloud infrastructures enable cognitive computing's machine-learning problem-solving. The unique qualities of advanced technology can improve medical care. Recursive analysis of unstructured data like X-ray images and computed axial tomography scans has advanced clinical diagnosis through statistics. DNA sequence classification also has infinite permutations due to its complexity.

12 May 2023
Verified
Conference Paper
Closed access
MGManish Gupta
Manish Gupta
SKSatish Kumar Kalhotra
Satish Kumar Kalhotra
Harish Reddy GantlaHarish Reddy Gantla
Harish Reddy Gantla
GAGaurav Kumar Arora
Gaurav Kumar Arora
SVS. Vaishnodevi
S. Vaishnodevi
ARAlgubelly Yashwanth Reddy
Algubelly Yashwanth Reddy
The efficiency of "conflict-based Clause-Learning Boolean Fulfilment (CDCLSAT)" solvers on engineering problems from several fields has been seeing notable modifications during the last 20 years. Various analyses have proposed SAT-based tactics for cryptanalysis, like finding conflicts in hash capabilities and disassembling symmetrical encryption schemes, as just a result of the availability of efficient broad sense look solvers like SAT Solver. The majority of the currently suggested SAT-based cryptanalysis techniques are Black Box inventions, in which the cryptanalysis problem is encrypted as SAT and illuminated using CDCLSAT Solvers. The method has the issue that now the encoding created in this method may be too extensive for any slashing arrangements to decode successfully. This approach's solution is not manner set up to handle a specific or provided example, which is a further notable drawback. The disadvantage of this technique is that decoding created in this manner may be too extensive for any sophisticated organization to correctly decode. One notable drawback of this strategy that the solution does not way set up to deal with a specific or given scenario. In order to understand these problems, SAT Solutions have provided solutions to two related existing gaps (exhibited in Fast Programme Encrypted 2009) about the presence or absence of these minute secrets. SAT nameservers have provided an effective solution, even though that such problems might appear difficult to address. SAT nameservers have provided a useful plan of action, despite the fact that such problems it might seem difficult to fix and also discuss the experiment that was conducted to see how well an intermediate SAT Solution performed when doing encrypted cryptanalytic tasks that proved to be relatively challenging. Allocation and or before assaults here on MD4 computation are far less similar.

23 November 2023
Verified
Conference Paper
Open access
UMUdit Mamodiya
Udit Mamodiya
RMRakhi Mutha
Rakhi Mutha
Harish Reddy GantlaHarish Reddy Gantla
Harish Reddy Gantla
SPSunil Kr Pandey
Sunil Kr Pandey
SASayed Sayeed Ahmad
Sayed Sayeed Ahmad
ABAbhishek Bhattacherjee
Abhishek Bhattacherjee
Data mining uses artificial intelligence and other methods to extract hidden potential information from large data sets, which provides an effective way to obtain valuable knowledge from a large amount of information. Data mining is also ubiquitous in the process of using deep learning to solve point cloud registration tasks. Global feature extraction and rigid body transformation estimation are two critical stages of uncorrelated point cloud registration. Mining the rich information hidden in the two stages is one of the essential tasks of point cloud registration. However, the recently proposed methods tend to ignore low-dimensional local features when extracting global features, resulting in the loss of a large amount of point cloud information, which makes the accuracy of solving transformation parameters in the subsequent rigid body transformation estimation stage unsatisfactory. In this paper, a feature mining network based on multi-dimensional information fusion is proposed, which thoroughly mines the high-dimensional global and low-dimensional local information in the point cloud, and effectively makes up for the lack of local features in the worldwide feature extraction stage of point cloud registration. Dual quaternions are used to estimate pose in the rigid body transformation estimation stage, which can simultaneously represent rotation and translation in a standard frame, providing a compact and accurate representation for pose estimation. Finally, extensive experiments on the ModelNet40 dataset show that compared with the existing state-of-the-art point cloud registration methods without corresponding points, the proposed method can achieve higher accuracy and is more robust to noise.


5 August 2024
Verified
Book Chapter
Closed access
PDF file
Harish Reddy GantlaHarish Reddy Gantla
Harish Reddy Gantla
PJP. N. Siva Jyothi
P. N. Siva Jyothi
RKRamesh Kumar
Ramesh Kumar
ASA. Sivaramakrishnan
A. Sivaramakrishnan
RNRania Mohy ElDin Nafea
Rania Mohy ElDin Nafea
VRV. K. Reshma
V. K. Reshma
The study offers a novel method for using medical imaging to diagnose Parkinson’s disease that is based on deep learning. When trained on medical pictures like magnetic resonance imaging and dopamine transporter scans, deep segmentation and persistent neural networks extract knowledge that is then analysed and applied. Interior models of the prepared DNNs make up the extricated information that is applied through move obtaining and space variation to create a solitary design for Parkinson’s disease prediction across various healthcare settings. Sizable experimental research is presented to demonstrate how the suggested method may accurately detect Parkinson’s disease by utilising various medical image sets taken in actual settings. <!----> <!----> <!----> <!---->