Riddhi Chawla

Prof. Dr. Riddhi Chawla

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 May 2022 in Journal of Healthcare Engineering
Verified
Journal Article
Open access
PDF file
RCRiddhi Chawla
Riddhi Chawla
SBS. Balaji
S. Balaji
RARaed N. Alabdali
Raed N. Alabdali
Ibrahim NaguibIbrahim Naguib
Ibrahim Naguib
NHNadir O. Hamed
Nadir O. Hamed
HZHeba Y. Zahran
Heba Y. Zahran
A variety of receptor and donor characteristics influence long-and short-term kidney graft survival. It is critical to predict the effectiveness of kidney transplantation to optimise organ allocation. This would allow patients to choose the best accessible kidney donor and the optimal immunosuppressive medication. Several studies have attempted to identify factors that predispose to graft rejection, but the results have been contradictory. As a result, the goal of this paper is to use the African buffalo-based artificial neural network (AB-ANN) approach to uncover predictive risk variables related to kidney graft. These two feature selection approaches combine to provide a novel hybrid feature selection technique that could select the most important elements to improve prediction accuracy. The feature analysis revealed that clinical features have varied effects on transplant survival. The collected data is processed in both training and testing methods. The prediction model's performance, in terms of accuracy, precision, recall, and F-measure, was examined, and the results were compared with those of other existing systems, including naive Bayesian, random forest, and J48 classifier. The results suggest that the proposed approach can forecast graft survival in kidney recipients' next visits in a creative manner and with more accuracy compared with other classifiers. This proposed method is more efficient for predicting kidney graft survival. Incorporating those clinical tools into outpatient clinics’ everyday workflows could help physicians make better and more personalised decisions.

4 April 2025
Verified
Book Chapter
Closed access
AAA. S. Arvind
A. S. Arvind
NMNiladri Maiti
Niladri Maiti
RCRiddhi Chawla
Riddhi Chawla
SMSimmi Madaan
Simmi Madaan
PRP. Sheela Rani
P. Sheela Rani
MPMukundan Appadurai Paramashivan
Mukundan Appadurai Paramashivan
The integration of Internet of Things (IoT) networks and secure image transmission in telemedicine is investigated in this chapter, with the purpose of highlighting the significance of these two concepts in the delivery of contemporary medical care. The Internet of Things (IoT) is utilized by telemedicine in order to facilitate remote patient monitoring, improve accessibility to medical services, and enhance the efficiency of healthcare systems. Considering the growing reliance on medical imaging for accurate diagnosis, the need for secure transmission methods is of the utmost importance in order to protect sensitive patient data from being accessed by unauthorized parties and being exposed to cyber threats.

31 July 2025 in Bioinformation
Verified
Journal Article
Open access
MAManish S. Agrawal
Manish S. Agrawal
RCRiddhi Chawla
Riddhi Chawla
SKShahid Ahmed Khan
Shahid Ahmed Khan
DPDivya Babuji Pandiyath
Divya Babuji Pandiyath
SDSovesh Das
Sovesh Das
JMJasmine Marwaha
Jasmine Marwaha
Orthodontic relapse remains a critical concern, often compromising long-term treatment success and patient satisfaction. Therefore, it is of interest to develop and validate an AI-driven predictive model using SMART microsensor-based retainer compliance data and patient-specific variables. Among 156 monitored patients over 24 months, the Random Forest algorithm achieved the highest accuracy (92.3%), sensitivity (89.7%) and specificity (94.2%). Key predictors included daily retainer wear duration, treatment complexity, age at completion and initial malocclusion severity. The model supports personalized retention strategies and early intervention to enhance post-treatment stability.

19 June 2026
Verified
Book Chapter
Closed access
MLMuthuvel Laxmikanthan
Muthuvel Laxmikanthan
KMK. Siva Agora Sakthivel Murugan
K. Siva Agora Sakthivel Murugan
RCRiddhi Chawla
Riddhi Chawla
PBPrasanta Chatterjee Biswas
Prasanta Chatterjee Biswas
SFSamandar Fayziev
Samandar Fayziev
DUDeemed to be University
Deemed to be University
The rapid growth of cyber threats and digital data has significantly increased the complexity of modern forensic investigations, necessitating the adoption of intelligent analytical approaches for accurate and scalable evidence analysis. This chapter presents a comparative evaluation of supervised and unsupervised machine learning paradigms for digital forensic investigations using real-world cyber intrusion datasets. Supervised learning models demonstrated strong classification performance with an average detection accuracy of 92.3%, precision of 90.8%, and recall of 89.6% in identifying known malicious artefacts. In contrast, unsupervised clustering techniques exhibited improved adaptability in detecting unknown anomalies, achieving an average anomaly detection rate of 88.7% in unlabeled forensic datasets. The proposed hybrid analytical framework integrating both paradigms achieved a superior overall accuracy of 94.6%, precision of 92.8%, and recall of 91.9%, thereby outperforming baseline forensic investigation models reported in recent studies.

19 August 2026 in Discover Education
Verified
Journal Article
Open access
PDF file
RCRiddhi Chawla
Riddhi Chawla
Introduction: The accelerated digitization of education due to the pandemic has introduced a new shift of the educational process. However, the issue of the pedagogical effectiveness of online platforms in comparison with traditional on-campus systems still remains. This research explores the views of students to determine the mediators involved while opting for learning modes and the effects they have on academic satisfaction. Methodology: Qualitative research employing semi-structured interviews with relativist social constructive perspective was used to collect in-depth information on forty university students. The heterogeneous sample was recruited via convenience sampling and spanned multiple academic tiers (Undergraduate, Postgraduate, and PhD candidates) across contrasting clinical (Medicine and Dentistry) and theoretical (Psychology and Business Administration) disciplines, all holding direct experience with both learning modes within the past 5 years. Thematic analysis was employed to analyze the data with Taguette software, to determine recurring patterns. A rigorous audit trail, reflexive journal and peer-debriefing were executed to reduce interpretative bias thereby ensuring trustworthiness. Results: Thematic analysis revealed three key mediators that influenced the decisions of students, including personal life situations, preferred learning styles, and underlying disciplinary requirements. Although online learning was preferred because of its flexibility and convenience, students complained of digital fatigue, social isolation and loss of peer interaction. On the other hand, face-to-face learning was lauded to create a high level of engagement and instant feedback but was faulted on strict scheduling and logistical limitations. Conclusion: The results indicate that both modes are not entirely satisfactory with the secret of effective academic delivery is a hybrid approach. This paradigm must balance the spatial adaptability of asynchronous online segments and collaborative advantages of face-to-face workshops to help maximize the learning results and inclusiveness.

30 September 2026 in Frontiers in Education
Verified
Journal Article
Open access
PDF file
RCRiddhi Chawla
Riddhi Chawla
Introduction: University students’ metacognition, including metacognitive knowledge, monitoring, and regulation, plays a crucial role in their academic success in higher education but students often have systematic self-monitoring problems, including the Dunning-Kruger effect, calibration errors and fluency illusions. This systematic review collates empirical evidence from around the world on these errors and examines the structural effectiveness of institutional and instructional practices and interventions for reducing errors and promoting equity in education. Methodology: Following the PICOS framework, a thorough search was conducted across five electronic databases (PsycINFO, ERIC, Scopus, Web of Science and Google Scholar)for peer-reviewed empirical literature published from January 2007 onwards. The active search, screening, and selection workflows were executed from January 2025 to June 2026, with the final literature update completed on June 15, 2026. While the search window remained open to contemporary literature up to the final search date, the final pool of eligible included studies empirically spanned from 2007 to December 2024. The methodological quality and risk of bias were assessed using the Mixed Methods: Appraisal Tool and the certainty of evidence was assessed by an adapted GRADE approach. The entire process followed the PRISMA checklist and the review was registered on PROSPERO to enhance transparency. Result: Of 1,288 identified, 37 were eligible primary empirical studies. The results were summarized using a narrative synthesis, which resulted in two categories: baseline errors( n = 15) and interventions ( n = 22). In 11 studies, there was evidence of severe overconfidence and miscalibration among students who are not performing well. Explicit metacognitive instruction ( n = 10)was found to have high-certainty evidence of improving calibration discrepancies and narrowing demographic performance gaps among tested interventions. Scaffolded problem-solving frameworks ( n = 5) and digital prompting tools ( n = 7)demonstrated moderate-to-low certainty as there were inconsistencies in the baseline of each, student exposure to cognitive load, and an absence of proven demographic equity closures. Conclusion: University students are highly susceptible to metacognitive miscalibration. Self-regulation and equity are significantly improved by explicit classroom instruction, whereas technology-mediated interventions exhibit moderate-to-low certainty due to cognitive load constraints and fail to systematically narrow historical performance gaps. Sustained success will require structured training of instructors and integration of the curricula across the entire organization Systematic Review Registration: https://www.crd.york.ac.uk/PROSPERO/recorddashboard , PROSPERO CRD420261436943.