Deepa T

Dr. Deepa T


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
12 April 2019 in IET Circuits, Devices & Systems
Verified
Journal Article
Open access
PDF file
MTMariammal Thirumeni
Mariammal Thirumeni
DTDeepa T
Deepa T
In this Letter, a hybrid particle swarm optimisation and gravitational search algorithm (PSO–GSA) to tune the parameters of proportional–integral (PI) controller operating in cascade with sliding mode controller (SMC) is proposed for the design of Cuk converter for low‐voltage electric vehicle application. The PI controller in the outer loop regulates the voltage and SMC in the inner loop regulates the current of converter operating in continuous conduction mode. The main objective of Cuk converter with PSO–GSA tuned PI & SMC controller is to track the reference voltage amidst disturbances, and to reduce the performance indices such as integral absolute error (IAE) and integral time absolute error. Initially, PI controller was tuned using Routh Hurwitz and root locus method. Then to improve its steady‐state performance index, PSO–GSA technique is applied to tune the proportional and integral gains. To validate the effectiveness of the proposed scheme, the performance indices such as IAE, integral squared error was measured and compared. The results obtained reveal that IAE is reduced to minimal value and the solution converges at a faster rate with the proposed controller than the conventional control methods. Moreover, the stability analysis was carried out using the Lyapunov method of stability.

26 September 2025 in IEEE Access
Verified
Journal Article
Open access
VAV. Raju Arvind
V. Raju Arvind
RSR. M. Shrinidhi
R. M. Shrinidhi
DTDeepa T
Deepa T
MMM. Maheedhar
M. Maheedhar
The evolution of intelligent warehousing represents a paradigm shift in supply chain logistics, driven by the synergistic integration of machine learning (ML) algorithms, Internet of Things (IoT) networks, and robotic automation to address systemic inefficiencies in traditional inventory systems. This research establishes a holistic framework that leverages XGBoost, Random Forest, and synthetic data generation to optimize demand forecasting (reducing mean absolute error by 32% compared to ARIMA models), mitigate inventory discrepancies (achieving 99.9% accuracy via RFID-enabled IoT sensors), and minimize operational costs (35% reduction through predictive maintenance and energy-efficient automation). By synthesizing real-time data streams from IoT edge devices—including smart shelves, environmental sensors, and autonomous mobile robots (AMRs)—the proposed system enables dynamic decision-making, reducing order fulfillment times by 72% and carbon emissions by 25% through AI-optimized routing and renewable energy integration. A procedurally generated synthetic dataset (913,000 transactions across 10 simulated warehouses) was engineered to replicate real-world variables such as demand volatility, shipment delays, and SKU heterogeneity, enabling stress-testing of ML models without operational risks. The framework’s core innovation lies in its multi-echelon architecture, which unifies IoT-driven inventory tracking, blockchain-enhanced traceability, and reinforcement learning (RL)-optimized warehouse layouts. Case studies demonstrate that XGBoost-based demand forecasting aligns procurement with market trends (95% accuracy in retail trials), while Random Forest classifiers reduce stockouts by 45% through anomaly detection in IoT sensor data. The system’s edge computing infrastructure processes data with <10ms latency, enabling real-time adjustments to inventory buffers and robotic workflows. Sustainability metrics reveal a 20% reduction in material waste via ML-optimized packaging and a 12% decrease in fuel consumption through KNN-driven route optimization. Challenges such as IoT signal interference (20% error rates in metal-rich environments) and workforce resistance (60% employee apprehension) are addressed through hardware retrofitting and blockchain-auditable training programs. This research advances intelligent warehousing beyond incremental automation, positioning it as a cognitive supply chain ecosystem capable of self-optimization in response to demand shocks, geopolitical disruptions, and environmental constraints. By achieving 99% order accuracy and 40% lower carrying costs, the framework establishes a blueprint for Industry 4.0-compliant logistics, bridging the gap between predictive analytics and operational execution in global supply chains.

22 September 2023 in IEEE Access
Verified
Journal Article
Open access
MMMarabathina Maheedhar
Marabathina Maheedhar
DTDeepa T
Deepa T
Recent growth in magnetic levitation can be attributed to its ability to minimize friction and disturbance in industries, transportation, aerospace, biomedicine, and magnetic bearings. Due to the magnetic levitation system’s nonlinear and unstable nature, control engineers found it exceedingly challenging to design a stabilizing controller. The magnetic levitation system is abbreviated as a maglev system. Using the integral square error criterion, a newly developed metaheuristic algorithm named the COOT algorithm is used to optimize the PID controller parameters. The performance of the proposed algorithm is evaluated using simulation and hardware with several kinds of reference trajectories and compared to the performance of other algorithms, such as the genetic algorithm and the whale optimization algorithm. Based on simulation and hardware results, it was determined that the proposed algorithm performed well with less settling time, rise time, and integral square error.

15 December 2021 in Journal of Nanomaterials
Verified
Journal Article
Open access
PDF file
MKMohana sundaram Kuppusamy
Mohana sundaram Kuppusamy
PPP. Prakash
P. Prakash
APAngalaeswari Sendraya Perumal
Angalaeswari Sendraya Perumal
DTDeepa T
Deepa T
Natrayan LakshmaiyaNatrayan Lakshmaiya
Natrayan Lakshmaiya
Prabhu ParamasivamPrabhu Paramasivam
Prabhu Paramasivam
Carbon nanotube field-effect transistor (CNTFET) is a good option to replace silicon for low power consumption application. Recent research shows that CN-FET thermal and electrical properties alter with length, diameter, and gate parameters. Optimization of CNTFET design parameters helps control some of the factors. Double gate and cylindrical gate layouts are introduced to overcome these facts. Carbon nanotubes have an intercapacitance between them that increases as their diameter increases. Total capacitance and inductance of CNTFETs increase with nanotube count. In order to reduce the voltage drop between semiconducting and metallic terminals, the diameter and pitch must be raised. This study employs response surface methodology and ANOVA technique that were used to optimize CNTFET process parameters. Thickness, voltage, delay, and power were all considered. The most affecting parameter was investigated.

12 May 2023 in IEEE Access
Verified
Journal Article
Open access
JAJ. K. Adarsh
J. K. Adarsh
SVSreedevi VT
Sreedevi VT
DTDeepa T
Deepa T
There are many ways to collect the product review, either by using a website or by manually asking the customers to leave their comments after buying the product. The traditional product feedback process is time-consuming. Nowadays, although industries use online review system to rate their product, the process lacks modernization. In this paper, BERT sentiment analysis is used to process the product review from the customers and automatically convert the review into a numeric score. This average score value is used for processing the sentiment analysis. The system is built entirely on Node-RED as a backbone to gather the review from the users with certain administrator privileges. An interactive dashboard is created to analyze the feedback of the product review. The above method of review system also reduces malpractice that the manufacturer or service provider may indulge into increase their ratings.

6 April 2021 in IETE Journal of Research
Verified
Journal Article
Closed access
KTKripalakshmi Thiagarajan
Kripalakshmi Thiagarajan
DTDeepa T
Deepa T
This paper presents a detailed review of the design aspects and performance analysis of high-frequency inverters used in inductive power transfer application (IPT) for electric vehicles. The paper’s main scope is focused on the design of inverters used explicitly for wireless charging with misalignment variations and coil dimensions. The research articles in the literature focus on the high-power transfer and coil structures for the existing topologies. The magnetic resonance coupling in the IPT system depends on the resonance phenomenon. The operating frequency of the inverter must be the same as the resonant frequency in the compensation network. On complete assessments, the paper emphases on suitable inverter specifications for wireless charging and its related issues. In addition, the resonant inverters can be replaced with H-bridge inverters in consideration of voltage stress and harmonic control. Investigations on harmonic elimination strategies for H-bridge and resonant inverters are also discussed in the paper.