Akash Sanghi

Dr. Akash Sanghi

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
16 November 2024
Verified
Conference Paper
Closed access
RARupanshi Agarwal
Rupanshi Agarwal
IBIsha Bhardwaj
Isha Bhardwaj
ASAshish Kumar Sharma
Ashish Kumar Sharma
ASAkash Sanghi
Akash Sanghi
GAGaurav Agarwal
Gaurav Agarwal
Artificial intelligence (AI) is driving a massive shift in the agriculture industry, which is essential to both global food security and economic stability. This review article explores the use of AI technologies in agriculture, outlining their current and potential future applications while charting their evolution. We examine several AI applications such as computer vision, machine learning, robots and the (IoT) Internet of Things, highlighting their contributions to increasing efficiency, streamlining resource allocation, and strengthening decision-making. Machine learning techniques are utilized for predictive analytics in disease identification and crop yield estimation, while computer vision supports plant health monitoring and harvesting automation. Planting, weeding, and harvesting chores are revolutionized by robotics, and data collecting for precision agriculture is made easier by IoT devices in conjunction with sensors. Additionally, by offering indepth analyses of the soil and crops, drones and satellite imagery are essential to precision farming. The technological, financial, and social barriers to the broad adoption of AI are also covered in this study. These barriers include poor data quality, expensive implementation, and moral dilemmas with regard to labour displacement and environmental effects. In this paper, we propose that the future of global food security and sustainability depends on the strategic application of AI in agriculture. In order to fully realize the potential of artificial intelligence in agriculture Strategic implementation will determine the sustain ability and future of global food security. In this order, this study attempts to direct future research and policy development by offering a thorough overview of existing technology, applications, and difficulties.

16 November 2024
Verified
Conference Paper
Closed access
VKVinayak Khatri
Vinayak Khatri
GAGaurav Agarwal
Gaurav Agarwal
AGAmit Kumar Gupta
Amit Kumar Gupta
ASAkash Sanghi
Akash Sanghi
Rapid developments in machine learning (ML) and artificial intelligence (AI) have had a big impact on cyber security by providing creative answers to challenging security problems. This analysis examines how AI and ML are integrated into cyber security, emphasizing the uses, advantages, and drawbacks of each technology. To improve threat detection, malware categorization, phishing prevention, and network security, this study analyses many AI and ML methods, such as reinforcement learning, deep learning, supervised learning, and unsupervised learning. According to recent study findings, AI-driven intrusion detection systems can detect intrusions with up to 99% accuracy, which greatly lowers the number of false positives. Comparatively, compared to conventional techniques, machine learning algorithms for malware detection have increased detection rates by 20-30%. However, several technological obstacles stand in the way of AI's smooth integration with cyber security. These obstacles include problems with data quality, adversarial assaults, interpretability of models, and the computing demands of implementing AI at scale. There are other major obstacles, such as privacy and ethical considerations. Nonetheless, issues including adversarial attacks, ethical dilemmas, and poor data quality persist. This paper illustrates the usefulness of AI and ML technologies in cyber security through real-world case studies. Lastly, it emphasizes how AI and ML have the ability to revolutionize cyber security procedures by highlighting upcoming trends and research paths. This review attempts to provide useful insights for researchers, practitioners, and policymakers to harness AI and ML for a safer digital environment by providing a thorough overview and highlighting important discoveries.

29 October 2025 in International Journal of Research and Review in Applied Science, Humanities, and Technology
Verified
Journal Article
Open access
PDF file
YAYash Agrawal
Yash Agrawal
RARupanshi Agrawal
Rupanshi Agrawal
ASAkash Sanghi
Akash Sanghi
Federated Learning (FL) is a new paradigm in distributed machine learning that allows numerous participants to train a common model without exchanging raw data. This strategy improves data privacy and security, addressing major concerns in sensitive domains including healthcare, banking, and mobile applications. Unlike traditional centralized learning, FL moves model training closer to the data source, reducing data leakage risks and boosting regulatory compliance (e.g., GDPR, HIPAA). This paper provides a complete overview of federated learning, including its core architecture, distinct types (horizontal, vertical, and transfer learning), enabling technologies (such as secure multiparty computation, differential privacy, and homomorphic encryption), and real-world applications. The paper also examines the fundamental issues encountered by FL, such as data heterogeneity, communication overhead, and vulnerability to adversarial assaults. The report concludes with interesting research prospects for increasing model performance, security, and scalability in federated environments.

11 April 2025
Verified
Conference Paper
Closed access
ASAkash Sanghi
Akash Sanghi
RARupanshi Agarwal
Rupanshi Agarwal
SPSiddharth Pandey
Siddharth Pandey
AKAtul Kumar
Atul Kumar
KJKushal Johari
Kushal Johari
Diabetes prediction is critical for early intervention, which helps to avoid significant complications like cardiovascular disease, kidney failure, and neuropathy. This study investigates the efficacy of multiple machine learning algorithms for diabetes prediction utilizing a wide range of evaluation measures such as accuracy, precision, recall, F1-score, Area Under the Curve (AUC), Matthews Correlation Coefficient (MCC), and Cohen's Kappa. To ensure robustness and avoid overfitting, the models were validated with the k-fold cross-validation approach, which divides the dataset into numerous folds for training and testing, ensuring consistent and generalizable findings. The primary objective was to evaluate these models' capacity to effectively categorize diabetes patients, reduce misclassification, and strike a compromise between accuracy (avoiding false positives) and recall (detecting genuine positives). Gradient Boosting regularly outperformed other models in all metrics. Its high accuracy, precision, and memory revealed its ability to correctly identify diabetes and non-diabetic cases while minimizing categorization errors. The outstanding F1-score demonstrated the algorithm's ability to balance memory and precision, while the confusion matrix revealed high true positive (TP) and true negative (TN) rates, as well as low false positives (FP) and false negatives (FN). Furthermore, k-fold cross-validation confirmed the consistency of Gradient Boosting's performance across various data splits, bolstering its trustworthiness. In comparison to other algorithms, Gradient Boosting had the most consistent performance, making it an effective tool for improving diabetes risk prediction. This study demonstrates the potential of Gradient Boosting and k-fold cross-validation in generating more reliable, accurate models for early diabetes diagnosis, allowing doctors to make more informed decisions and improve patient outcomes.

1 January 2024 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
PDF file
RARupanshi Agarwal
Rupanshi Agarwal
ASAkash Sanghi
Akash Sanghi
GAGAURAV Agarwal
GAURAV Agarwal
SSShailesh Saxena
Shailesh Saxena
RKRakesh Kumar
Rakesh Kumar
Recommender systems are among the utmost popular and successful uses of machine learning in the corporate world. Recently, these schemes have made use of ML met Recommender systems are among the utmost popular and successful uses of machine learning in the corporate world. Recently, these schemes have made use of ML met

1 January 2024 in AIP Conference Proceedings
Verified
Conference Paper
Closed access
PDF file
AFAdebanjo Ambrose Falade
Adebanjo Ambrose Falade
GAGAURAV Agarwal
GAURAV Agarwal
ASAkash Sanghi
Akash Sanghi
AGAmit Kumar Gupta
Amit Kumar Gupta
With the growth of cloud computing (CC), privacy and security are crucial. This study provides a new paradigm to address the key issues of rising processing ove With the growth of cloud computing (CC), privacy and security are crucial. This study provides a new paradigm to address the key issues of rising processing ove