Y. Sukhi has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Heuristic-based optimization for smart home energy management with renewable integration and energy storage systems

    by M. J. Suganya, Y. Sukhi, J. C. Vinitha, J. Sumithra

    The rapid growth of energy demand in urban areas emphasizes the necessity of efficient demand-side management (DSM) strategies in smart homes. This study presents a heuristic-based optimization framework for appliance scheduling in smart home environments that incorporates renewable and sustainable energy resources (RSERs) and energy storage systems (ESSs). The objective is to minimize the electricity cost and the peak-to-average ratio (PAR) while satisfying the user comfort constraints. Three optimization techniques, genetic algorithm (GA), binary particle swarm optimization (BPSO), and wind-driven optimization (WDO), are implemented and evaluated in three scenarios: without renewable integration, with RSERs, and with both RSERs and ESSs. Simulation results show that BPSO has the lowest electricity cost and carbon emissions, while WDO has a faster convergence speed and competitive performance in PAR reduction. RSER and ESS integration has a major positive impact on energy efficiency, grid dependence, and sustainability. The results give useful insights to choose appropriate optimization methods and contribute to the development of effective, sustainable, and user-centric smart home energy management systems.

  • Alcohol Detection and Engine Locking Using Arduino

    by Y. Sukhi, P. Kavitha, C. R. A. Darshan, M. C. Brijesh Immanuel, E. Disam, Sai Prasad, Y. Jeyashree

  • Powering Low-Power Wireless Sensor in Industrial Environment Using Thermoelectric Generator

    by Y. Jeyashree, S. Lourdu Jame, Betty Lincoln, A. Vimala Juliet, H. Rebecca Shirly, Y. Sukhi

  • AI and Machine Learning-Driven Model for Assessing Financial Risk Networks

    by J. Shobana, Chandrasekar Thangavelu, T. P. Anish, Umamageswaran Jambulingam, Y. Sukhi, S. D. Lalitha

    The application of artificial intelligence (AI) and its foundational machine learning techniques is revolutionizing and is already changing the way we think about financial risk management. The rise of AI-driven solutions has opened opportunities for anyone involved in understanding and managing risk, including determining the appropriate loan amount for a customer from a bank, alerting traders on position risk, identifying insider and customer fraud, and enhancing compliance while lowering model risk. This chapter describes the state-of-the-art AI and machine learning techniques and their present applications. We also envision the role that completely AI solutions will play in the future, helping the organization manage risk as a logical progression from the widespread usage of machine learning.


  • Torque fault compensation in electric vehicle switched reluctance motor drives: A jellyfish search optimization method

    by S. Anita, Y. Sukhi, Y. Jeyashree, N. Manoj Kumar

    In this paper, an enhanced indirect instantaneous‐torque‐control is proposed based on the torque sharing function approach of switched reluctance motor drives for electric vehicles by employing the jelly fish search. The major goal is to attain vehicle desires that include minimal torque ripple, maximum torque per ampere (MTPA), and huge performance and extend speed limit. First, a simplest analytic design is developed a determine more proficient turn‐on angle for the torque product. Second, an altered torque sharing function (TSF) is used for compensating the faults of torque tracking. The proposed technique is calculated to represent an accurate switched reluctance motor and its magnetized features. They have worked to create the machine model and execute the necessary transmits. The torque fault is evaluated and compensated inside the torque sharing function. The adapting TSF is compensates for the torque fault with receiving the phase because it is the minimal flux rate connecting variation. Finally, the jellyfish search technique is accepted to determine the optimal control parameters. The proposed strategies are done in MATLAB and its performance is contrasted with different existing strategies. According to the simulation result, the proposed strategy‐based accuracy is 94.2% at 50 iteration and 80% at 100th iteration which is higher than the existing methods. From this analyses, it proved that the proposed technique gives superior performance to existing one.


  • Open Access

    PIR sensor-based automatic solar-powered UVC LED sterilizer lamp

    by K. A. Mohamed Junaid, Y. Sukhi, Y. Jeyashree, K. Mohana Sundaram

    A PIR sensor-based automatic solar-powered UVC LED sterilizer lamp is UV-based air disinfection system that kills the microorganisms, including COVID-19 virus, floating freely in the air of a room. This lamp is designed using embedded system for automatic control of UV lamps based on the human presence. This is carefully designed to ensure that the end user is protected. The automatic detection unit shuts OFF the UV in case if a human is detected. The product is PV powered but also has an option with line 220 V mains supply. The bank of UV LEDS is completely enclosed. The battery is charged using a solar panel that has a backup of 8 h. This study includes the design and implementation of PIR sensor-based automatic solar-powered UVC LED sterilizer lamp using the components such as PIR sensor, DC-DC converter, Arduino board, PV panel, battery, charging circuit, and UV LED array.

  • Open Access

    Analysis and design of wind energy conversion with storage system

    by T. Snehitha Reddy, K.A. Mohamed Junaid, Y. Sukhi, Y. Jeyashree, P. Kavitha, Vijay Nath


  • Low-Cost Smart Irrigation for Agricultural Land Using IoT

    by K. A. Mohamed Junaid, Y. Sukhi, S. Anita

    This manuscript particularly provides low-cost smart irrigation for agricultural land that depends on the IoT. For irrigation purposes, using a farmland manual system is time-consuming and risky. Agriculture is the most important occupation in India. Particularly our villages are based on agriculture. To offer a solution to this tedious process, it began to design a smart machine that is no longer used for irrigation methods and makes more effective. Farmland houses are measured by sensors through the node’s microcontroller MCU. The statistics are handled with the microcontroller and sent to the cloud server. It acts as a bridge to send statistics through cell phones. The valve is activated using information acquired from signals sent to a cell phone. This increases performance and saves a lot of water. The hardware configuration becomes advanced and is examined within the farmland. The advantage is that the acquisition yields and labor are more considerable for farmers.


  • Open Access

    Modeling of Hybrid Henry Gas Solubility Optimization Algorithm with Deep Learning based LED Driver System

    by Fayaz Ahamed, Y. Sukhi

    Light emitting diodes (LED) become an effective lighting solution because of the characteristics of energy efficiency, flexible controllability, and extended lifetime. They find use in numerous lighting systems for residents, industries, enterprises, and street lighting applications. The efficiency and trustworthiness of the LED systems considerably based on the thermal mechanical loading improved several degradation schemes and respective interfaces. The complication of the LED systems limits the theoretic interpretation of the core reasons for the luminous variation or the formation of the direct correlation among the thermal aging loading and the luminous output. Therefore, this article designs a new Hybrid Henry Gas Solubility Optimization with deep learning (HHGSO-DL) algorithm for LED driver system design. The presented HHGSO-DL technique mainly concentrates on the derivation of empirical relationships among the design parameters, thermal aging loading, and luminous outcomes of the LED product. In the presented HHGSO-DL technique, bidirectional long short-term memory (BiLSTM) algorithm is executed for examining the empirical relationship and its hyperparameters can be tuned by the HHGSO algorithm. In this work, the HHGSO algorithm is derived by the integration of traditional HGSO algorithm with oppositional based learning (OBL) concept. The performance of the HHGSO-DL technique can be investigated on LED chip packaging and LED luminaire with thermal aging loading. The extensive results demonstrate the promising performance of the HHGSO-DL technique over other state of art approaches.