Sraboni Clara Mohonta

Sraboni Clara Mohonta

Auto-generated profile, based on publicly available information

Sraboni Clara Mohonta

Zicklin School of Business, Baruch College

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
15 January 2025 in Journal of Posthumanism
Verified
Journal Article
Open access
PDF file
MMMia Md Tofayel Gonee Manik
Mia Md Tofayel Gonee Manik
SMSraboni Clara Mohonta
Sraboni Clara Mohonta
FKFarhana Karim
Farhana Karim
MMMd Alamgir Miah
Md Alamgir Miah
SIShafiqul Islam
Shafiqul Islam
ASAbu Saleh Muhammad Saimon
Abu Saleh Muhammad Saimon
The clinical use of artificial intelligence for precision medicine delivers transformative results in drug discovery through its combination of big data analytics and machine learning with genomic research. The traditional methods used in the drug discovery process are expensive to implement and take lengthy durations while failing to deliver customized therapy for patients. The advent of artificial intelligence now conducts fast genomic database analysis to find new drug aims and develop targeted medicine for individual patients. The application of ML algorithms enables researchers to make disease progression forecasts as well as identify drug effectiveness and potential adverse effects leading to improved outcomes for genomic drug discovery patients. The research discusses how deep learning and reinforcement learning models are applied to work with big genomic and biomedical information datasets. Data storage through cloud computing platforms together with high-performance computing systems allows precision medicine to scale and become more efficient. AI computational biology combined with clinical information enhances pharma research by optimally structuring drug reuse analysis and promoting new drug development processes. The use of artificial intelligence leads genomics-based drug discovery to a new direction through high efficiency and cost reduction and individual patient therapy delivery. Precision medicine based on AI and bioinformatics advancements push forward personal healthcare into the future despite ongoing obstacles such as data security problems and interpretation challenges and regulatory limitations.

25 April 2025 in Journal of Posthumanism
Verified
Journal Article
Open access
PDF file
MMMohammad Moniruzzaman
Mohammad Moniruzzaman
SIShafiqul Islam
Shafiqul Islam
SMSraboni Clara Mohonta
Sraboni Clara Mohonta
MAMuhammad Adnan
Muhammad Adnan
АCАsikur Rаhmаn Chy
Аsikur Rаhmаn Chy
MMMia Md Tofayel Gonee Manik
Mia Md Tofayel Gonee Manik
The high price opacity of the United States healthcare persistently weighs down on consumers, as evidenced by studies indicating that more than 65% of patients are surprised by the cost of the treatment after getting care. Finally, it provides a solution to enhanced ‘transparency’ and cost predictability leveraging big data technologies. The analysis of a dataset comprising of more than 5 million hospital billing records from more than 1,200 US hospitals, obtained from the Centers for Medicare & Medicaid Services (CMS) data, in this research helps analyze how big data strategies can improve price transparency. The study employs a data mining technique, regression analysis and visualization tools to quantify price discrepancies exceeding 300% for identical procedures between different regions. Both predictive analytics models were useful in consumer facing pricing tools and were able to predict average procedure costs with an average 92% accuracy. The results verify that big data can revolutionize the process of identifying pricing anomalies and informing regulatory strategies. However, one of the challenges present today is the lack of standardization of data and interoperability. This dissertation presents a scalable framework for bringing big data into national healthcare pricing systems that better advance transparency, equity, and consumer trust.

1 January 2025 in Journal of Engineering
Verified
Journal Article
Open access
MAMd Kamal Ahmed
Md Kamal Ahmed
EREvha Rozario
Evha Rozario
SMSraboni Clara Mohonta
Sraboni Clara Mohonta
JFJannatul Ferdousmou
Jannatul Ferdousmou
ASAbu Saleh Muhammad Saimon
Abu Saleh Muhammad Saimon
RHRakibul Hasan
Rakibul Hasan
Big data analytics’ incorporation into customized cancer care is a revolutionary development in medical science. Using knowledge from genomic sequencing, electronic health records (EHRs), clinical trial databases, and social determinants of health, this systematic review investigates the relationship between artificial intelligence (AI), machine learning, and big data analysis in customizing cancer treatments for each patient. The study highlights how AI‐driven prediction models might improve treatment outcomes, reduce side effects, and increase patient safety by synthesizing insights from the last 10 years of academic research. A systematic literature review that follows PRISMA guidelines and includes both quantitative and qualitative evaluations of academic publications is among the key approaches. The findings show that multiomics approaches, which combine transcriptomics, proteomics, metabolomics, and genomics, are becoming increasingly important for customized medicine. Real‐time data analytics and wearable technology are also noted as promising resources for prompt responses. Notwithstanding obstacles, including data heterogeneity, moral dilemmas, and validation problems, the results highlight how crucial AI is to treating tumor complexity and developing precision medicine. In order to improve regulatory frameworks, promote interdisciplinary collaboration, and optimize AI applications in cancer treatment planning, the study concludes by suggesting future research areas. For scientists, physicians, and legislators hoping to transform cancer treatment using big data analytics–driven tailored medicine, this review provides insightful information.

13 November 2025
Verified
Conference Paper
Closed access
MRMohon Raihan
Mohon Raihan
MAMuhammad Adnan
Muhammad Adnan
JHJubayar Hossain
Jubayar Hossain
KSKazi Bushra Siddiqa
Kazi Bushra Siddiqa
FKFarhana Karim
Farhana Karim
USUdoy Sankar Saha
Udoy Sankar Saha
Recent years have seen the rise of adversarial attacks targeting deep learning authentication systems by taking advantage of flaws in these models. While there is some excellent work assessing the probability of adversarial attacks in general, most existing research focuses on specific modules or types of attacks. The paper proposes the Adversarially Robust Biometric Verification (ARBV) Framework, with the primary goal of protecting biometric authentication in mobile banking apps from constantly emerging adversarial threats. ARBV uniquely employs a multitiered defense strategy that integrates the Dynamic Adversarial Feature Selector (DAFS), which adaptively identifies and suppresses adversarial perturbations at the feature representation level using an explainable AI (XAI)- guided instance-wise selection process. This mitigation removes adversarially tuned noise components to minimize overfitting and preserve discriminative biometric characteristics. Complementing DAFS, a Dual Channel Noise Discriminator (DCND) module leverages a hybrid convolutional-recurrent neural network architecture enhanced with temporal attentive gating mechanisms to isolate adversarial noise patterns in real-time, preventing their propagation through the feature extraction layer. The proposed model further incorporates Federated Adversarial Adaptation Learning (FAAL), which federates model updates from distributed mobile devices, allowing for continuous adaptation to novel adversarial signatures. The results demonstrate that ARBVF achieves a verification accuracy of up to 98.7 percent, even when subjected to the most sophisticated adversarial attacks, in simulated mobile financial verification scenarios using multimodal biometric datasets.

1 August 2026
Verified
Conference Paper
Closed access
SMSraboni Clara Mohonta
Sraboni Clara Mohonta
RMRahul P. Mahajan
Rahul P. Mahajan
NMNitin Mukhi
Nitin Mukhi
SASai Arundeep Aetukuri
Sai Arundeep Aetukuri
PKPonnarasan Krishnan
Ponnarasan Krishnan
MBMohammed Majid Bakhsh
Mohammed Majid Bakhsh