scispace - formally typeset
Search or ask a question
Author

Pradeep Kumar S

Bio: Pradeep Kumar S is an academic researcher. The author has an hindex of 1, co-authored 8 publications receiving 3 citations.

Papers
More filters
Proceedings ArticleDOI
16 Oct 2022
TL;DR: In this article , the authors show that a smaller number of range estimations will likely be enough to offset the time-changeability of range inhabitance and the veiled station issue.
Abstract: In the beginning, it is important to show that a smaller number of range estimations will likely be enough to offset the time-changeability of range inhabitance and the veiled station issue. In order to improve the precision of spectrum recovery detection, I'd like to second the idea of framework plan detection. Simulators are used to validate our theoretical findings and show that collaboration increases the likelihood of identification even when each auxiliary client provides only a few estimates. Furthermore, show that it is sufficient to consider a subset of close-by optional customers in order to obtain comparable results. It is suggested to use a conveyed compressive inspecting technique, which takes less estimates when conquering, for acceptable wideband spectrum sensing.

2 citations

Proceedings ArticleDOI
24 Feb 2023
TL;DR: In this article , a Co-Active Adaptive Neuro-Fuzzy Expert System (CANFES) classifier has been used for brain tumor classification, which achieved an accuracy of 98.73%.
Abstract: Classification, preprocessing, feature extraction, and segmentation are all parts of the planned study that will be utilized to categories and detect brain tumor pictures. Magnetic resonance imaging (MRI) gives direct information about anatomical structures as well as possibly abnormal tissues where patients are being watched by physicians, making brain tumor identification not as much simpler for clinical diagnosis. This suggested system utilizes a machine learning strategy to identify, and categories brain tumors known as gliomas. Kirsch's edge detected pixels are used to identify the edges of the boundaries. Using this improved brain scan, the ridge let transform is used to extract the ridge let multi-resolution coefficients. As an added step, the ridge let converted coefficients are used to create features, which are then improved with the help of the CANFES classifier. Evaluation factors like as sensitivity, specificity, and accuracy are applied to the results in the context of tumor detection. Both the old approach and the suggested methodology are implemented in simulation using a programming environment like MATLAB, and the results of these simulations are compared to demonstrate the efficacy of the proposed algorithm. The suggested tumor detection approaches employing Co-Active Adaptive Neuro-Fuzzy Expert System Classifier have an accuracy of 98.73%, which offers iv accurate detection of the tumor, and so should be regarded as superior to the current traditional procedures.

1 citations

Proceedings ArticleDOI
29 Apr 2023
TL;DR: In this article , a data driven method for the estimation of the State of Charge (SOC) of a 3Ah bat-tery LG HG2 battery was developed using the dataset val-ues obtained from a experimental data of the battery.
Abstract: Lithium-Ion batteries are used popularly in many technologies used in day-to-day life. Engineering research on Lithium-Ion battery efficiency assessment is underway due to its large size acceptance. This paper develops the SOC estimation using the data driven method. Recurrent Neural Network based implementation is developed using the dataset val-ues obtained from a experimental data of 3Ah bat-tery LG HG2. Parameters including voltage, current, temperature, average voltage and average current is observed in the experiment available for research. A dataset that includes different battery parameters with temperature, voltage and current are mapped to the State of Charge of the battery. This dataset is used to train the Recurrent Neural Network in this paper for SOC estimation. The major goal of this research is to establish the appropriate Recurrent Neural Net-work (RNN) design procedure for a SOC estimator. Performance evaluation of the algorithm this used is done and tabulated. Python scikit learn toolbox is used to develop the algorithm and results is found to be satisfactory.
Proceedings ArticleDOI
24 Feb 2023
TL;DR: In this article , a technique for screening for obstructive sleep apnea by analysing Heart Rate Variability of Electrocardiogram (ECG) data while the subject is asleep is presented.
Abstract: Sleep is essential for human survival since it helps to restore and maintain our bodies' immune systems and other essential processes. One-third of a person's life is devoted to sleeping, although few are aware of the many positive aspects of this activity. Two distinct types of sleep, REM and NREM, have been identified. A good night's rest is achieved when REM and NREM sleep alternate in a regular pattern. Disruptions to this cycle, whether they originate physiologically or psychologically, have been linked to a variety of health problems. Polysomnography (PSG) equipment is often used in sleep labs inside hospitals to perform sleep studies. A polysomnogram is an in-depth medical technique that records a patient's vital signs while they sleep and necessitates a hospital stay. Clinically, sleep apnea is defined as a breathing disease in which there are periodic pauses in breathing lasting 10 seconds or more that occur more than five times during the night. Sleep apnea may be classified as either Obstructive, Central, or Mixed. The prevalent sleep problem known as obstructive sleep apnea (OSA) is caused by the relaxation of muscles in the upper airway during sleep. The purpose of this study is to provide a technique for screening for Obstructive Sleep Apnea by analysing Heart Rate Variability of Electrocardiogram (ECG) data while the subject is asleep. The goals of this study are to create computational approaches for identifying OSA based on characteristics extracted from Heart Rate Variability (HRV) signals derived from sleep electrocardiograms (ECGs). Physio Net's Apnea-ECG recordings serve as the source for the ECG data.
Proceedings ArticleDOI
29 Apr 2023
TL;DR: Wang et al. as mentioned in this paper developed a personalized Chinese course recommendation model for online vocational education learning platform using collaborative filtering algorithm to analyze students' past experience and preferences to provide personalized Chinese courses.
Abstract: The current Chinese education system is mainly based on traditional teaching methods. Facts have proved that this method cannot meet the needs of students and their learning methods. In order to improve China's education system, it is necessary to find a new teaching method. One of the most effective methods is to use technology. Technology can help teachers and students interact more effectively, thus improving students' learning outcomes. This study aims to develop a personalized Chinese course recommendation model for online vocational education learning platform. In order to achieve this goal, the author uses collaborative filtering algorithm to analyze students' past experience and preferences to provide personalized Chinese courses. The study was conducted using data sets collected from actual case studies. This dataset contains information about students who have registered for online careers. First, we will use the KDD process to develop a problem statement and data collection plan. Secondly, we will use a priori method to analyze the data and build a database for further analysis. Third, we will apply different algorithms and use different methods to solve this problem.

Cited by
More filters
Proceedings ArticleDOI
20 Nov 2022
TL;DR: In this article , the authors demonstrate how to use an ESP32-CAM module and a few electronic sensors to build a clever military robot to monitor border regions in a real-time computer vision workload.
Abstract: Robots are designed to carry out specialised tasks that humans are unable to do or in hazardous environments where human labour is not guaranteed. As a result, these kinds of vehicles can carry out tasks that are challenging for humans. Allowing a soldier the responsibility of surveillance in such circumstances is challenging since it could endanger the soldier's life. Instead, we can utilise a robot to monitor border regions. In this project, we'll demonstrate how to use an ESP32-CAM module and a few electronic sensors to build a clever military robot. Although the ESP32-CAM is a low power and low latency video streaming module and has GPIOs and serial connection, it does not appear powerful enough to handle some demanding real-time computer vision workloads.
Journal ArticleDOI
TL;DR: In this paper , the authors systematically evaluate the recent trends in multi-omics data analysis based on deep learning techniques and their application in disease prediction, highlighting the current challenges in the field and discuss how advances in deep learning methods and their optimization for application is vital in overcoming them.
Abstract: Accurate diagnosis is the key to providing prompt and explicit treatment and disease management. The recognized biological method for the molecular diagnosis of infectious pathogens is polymerase chain reaction (PCR). Recently, deep learning approaches are playing a vital role in accurately identifying disease-related genes for diagnosis, prognosis, and treatment. The models reduce the time and cost used by wet-lab experimental procedures. Consequently, sophisticated computational approaches have been developed to facilitate the detection of cancer, a leading cause of death globally, and other complex diseases. In this review, we systematically evaluate the recent trends in multi-omics data analysis based on deep learning techniques and their application in disease prediction. We highlight the current challenges in the field and discuss how advances in deep learning methods and their optimization for application is vital in overcoming them. Ultimately, this review promotes the development of novel deep-learning methodologies for data integration, which is essential for disease detection and treatment.
Proceedings ArticleDOI
A. P*, Pradeep Kumar S, L. N., Rajini H, Saahithi S 
20 Nov 2022
TL;DR: In this article , a 13 level symmetric multi-level inverters, having a reduced number of switches by using particle swarm optimization technique, capacitors, diodes, are compared with other topologies and are simulated using MATLAB.
Abstract: Power electronic inverters are gaining extensive attention in various industrial drive applications. Incorporating renewable energy sources with energy storage devices with efficient power electronic converters overcomes the major difficulties associated with carbon foot prints. Multi-level inverters are designed to achieve high power ratings, with reduced number of switches. Many of the researchers are focusing on issues that can minimize harmonics in order to obtain higher voltage levels. In this paper 13 level symmetric multi-level inverters, having a reduced number of switches by using particle swarm optimization technique, capacitors, diodes, are compared with other topologies and are simulated using MATLAB. Microcontroller is used to develop the required gating pulses for the inverter switches. The prototype hardware is developed which generates 13 level output voltage and the effectiveness was demonstrated using harmonic analysis with THD of 3.36%.