Rinika Paul

Ms. Rinika Paul

Electrical and Electronics Engineering, Amrita School of Engineering, Bangalore, Karnātaka, India
orcid

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
24 February 2023 in Electronics
Verified
Journal Article
Open access
PDF file
BPBathala Prasanth
Bathala Prasanth
Rinika PaulRinika Paul
Rinika Paul
DKDeepa Kaliyaperumal
Deepa Kaliyaperumal
Ramani KannanRamani Kannan
Ramani Kannan
Yellapragada Venkata Pavan KumarYellapragada Venkata Pavan Kumar
Yellapragada Venkata Pavan Kumar
NVNithya Venkatesan
Nithya Venkatesan
Innovations in electric vehicle technology have led to a need for maximum energy storage in the energy source to provide some extra kilometers. The size of electric vehicles limits the size of the batteries, thus limiting the amount of energy that can be stored. Range anxiety amongst the crowd prevents the entire population from shifting to a completely electric mode of transport. The extra energy harnessed from the kinetic energy produced due to braking during deceleration is sent back to the batteries to charge them, a process known as regenerative braking, providing a longer range to the vehicle. The work proposes efficient machine learning-based methods used to harness maximum braking energy from an electric vehicle to provide longer mileage. The methods are compared to the energy harnessed using fuzzy logic and artificial neural network techniques. These techniques take into consideration the state of charge (SOC) estimation of the battery, or the supercapacitor and the brake demand, to calculate the energy harnessed from the braking power. With the proposed machine learning techniques, there has been a 59% increase in energy extraction compared to fuzzy logic and artificial neural network methods used for regenerative energy extraction.

26 August 2023 in IET Renewable Power Generation
Verified
Journal Article
Open access
PSPraveen Kallukalam Sebastian
Praveen Kallukalam Sebastian
DKDeepa Kaliyaperumal
Deepa Kaliyaperumal
NNN. Neelima
N. Neelima
Rinika PaulRinika Paul
Rinika Paul
TÖTolga Özer
Tolga Özer
Traditional analog and digital meters are being substantially replaced with technological advances and the Internet of Things (IoT) introduction. The smart meter is highly preferred for accessing real‐time consumption, tariff calculation, and remote system control. These smart meters also prevent the majority from bypassing theft. Despite its intelligence, it cannot be 100% secure. An error in the readings can be caused by hacking or damage to meter components making the utility companies suffer significant losses. Based on past and future energy consumption data predictions on the consumer side, various methods are used in the proposed work to identify theft or anomalies in smart meter readings. Forecast‐based detection proved to be the most effective and accurate method. The primary and secondary decision models, which employ a variety of statical analyses to identify system anomalies, serve as the foundation for the energy consumption that follows the forecasting. Past 24‐h data is needed for forecasting, which is passed through different statical calculations such as RMSE, simple moving average, and Absolute Percentage Error to conclude detecting the normal values. Long short‐term memory gives high accuracy of 97% for forecasting and detecting abnormalities.

13 October 2022
Verified
Conference Paper
Closed access
Rinika PaulRinika Paul
Rinika Paul
RARashmi
Rashmi
EdTech courses are believed to provide industry-oriented practical skills to the students to bridge the gap between academics and the industry. They also provide supporting education to the students to crack competitive exams in various sectors. With education institutions being shut down due to lockdown and moved to online mode, many students enrolled themselves in EdTech courses online creating competition amongst EdTech organizations. Reduced prices at times lead to reduced quality of the course content and the delivery. Students are often the prey in the competition who are left unsatisfied with the course and would never return to the organization for further courses leading to a churn. At least 50% of college students enroll in online courses in India but the completion rate is only about 13% which is very low. Customer churn is a major challenge to an organization reducing their growth as well as revenue. Two different machine learning algorithms viz. K-Nearest Neighbor (KNN) and Support Vector Machines (SVM) are proposed in this paper to predict the churn rate of students for EdTech courses based on the feedback of the students collected through the course end survey. The model also tells if the student is interested to enroll further in any other courses offered by the organization or refer the courses to their friends or relatives. The data is collected in real-time based on the online courses offered by a startup company and the churn rate for the organization is calculated.

13 October 2022
Verified
Conference Paper
Closed access
Rinika PaulRinika Paul
Rinika Paul
SPSanketh B. Prabhu
Sanketh B. Prabhu
SYSudha Yadav
Sudha Yadav
India grows food in surplus quantity and also wastes tons of food by storing it in cold storage that goes unmonitored along with inefficient temperature controls. A lot of raw materials get rotten while transported from one cold storage to the food industry or directly to the consumer side be it the restaurants or the vegetable and fruit markets. Spoilt food when consumed by animals causes death and diseases. Even in restaurants, already preserved food is again stored in refrigerators for weeks. Today in the era of smart refrigerators, keeping a track of items inside became easier due to various alerting systems. As food spoilage is also a concern refrigerator should be able to detect the spoilage of food that is stored in it and should be able to alert the user. Often, the spoilage is known only when the food is smelt or tasted. In this paper, an FPGA-based food spoilage detection system is designed that detects early spoilage of food in storage systems through methane gas and moisture detection in foods as well as mold on bread surfaces. The system alerts the user through a buzzer and the inbuilt display of the storage at early spoilage itself so that the user discards the food even before it is completely rotten preventing other food from getting affected as well as saving the lives of animals who die from food poisoning. The YoloV5 machine learning model is retrained to detect the early formation of mold on food surfaces and discard the food items immediately.

11 July 2019
Verified
Book Chapter
Closed access
PDF file
RVR. Venkataswamy
R. Venkataswamy
Rinika PaulRinika Paul
Rinika Paul
JJJinu Jogy
Jinu Jogy