14 results on '"Sridevi, S."'
Search Results
2. Estimation of state of charge and state of health of batteries using hybrid method and recurrent neural network.
- Author
-
Sattianadan, D., Sharma, Rohit Kumar, Fernandez, S. George, Sudhakaran, M., and Sridevi, S.
- Subjects
RECURRENT neural networks ,LEAD-acid batteries ,ELECTRIC circuits ,STORAGE batteries ,OPEN-circuit voltage - Abstract
This paper uses the hybrid method to estimate state of charge (SOC) for lead acid battery and the recurrent neural network (RNN) technique in order to estimate the state of health of a li-ion battery. The hybrid method utilises (i) the Coulomb Counting Method, (ii) the Electrical Circuit Model, and (iii) a mathematical model based on the Peukert Law in order to estimate state of charge of battery. In this work, the method that is used to measure the internal resistance of the battery in order to determine the open-circuit voltage and approximate the State of Charge is provided. The LSTM (Long-Short Term Memory) algorithm is used which is based on the recurrent neural network are to determine the State of Health (SOH) of a li-ion battery. Estimation of the battery's state of health can be derived from the NASA Li-ion battery dataset. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
3. Comprehensive analysis of optimal apportionment of EV charging station in a radial distribution system.
- Author
-
Sattianadan, D., Anusha, R., Fernandez, S. George, Sudhakaran, M., and Sridevi, S.
- Subjects
ELECTRIC vehicle charging stations ,LARGE scale systems ,OPTIMIZATION algorithms ,DISTRIBUTED power generation ,GRIDS (Cartography) ,ELECTRIC vehicles - Abstract
To Electric vehicles (EVs) are large loads and with the penetration of more EVs into the grid, they always can affect the power system network on a large scale. While investigating, the impact of EV is felt in the grid system from an electrical perspective (like voltage stability, losses, reliability). The project aims at finding a feasible solution for reducing the burden on the power system. The main areas of concern while integrating EVs into the system are power losses, utilization factors, voltage, and reliability. The extended view of the project is to implement renewable sources of energy in the form of distributed generation that can greatly help in reducing the impact of a large number of EV charging station (CS) loads on the grid. Hence this paper presents a comprehensive analysis using TLBO and Grey Wolf optimization algorithms for reducing power loss, and reliability while improving the utilization factor of the system. The method is tested in a standard IEEE 33 bus system using MATLAB. The results show a reduction in power loss and other parameters apart from which the system's voltage profile has been improved to a large extent. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF
4. Establishing trust enhanced blockchain-based distributed web service registry.
- Author
-
Sridevi, S., Karpagam, G. R., and Kumar, B. Vinoth
- Subjects
- *
WEB services , *TRUST , *SEMANTIC Web , *BLOCKCHAINS , *INTERNET users - Abstract
The W3C typically describes web services as: "a piece of software that is designed to support machine-to-machine interoperability over a network. With the rapid expansion of functionally similar web services over the internet exposes a great challenge for users to identify the web service origin and integrity process. A traditional centralized web service registry drastically shifts the dynamic power of web services, by establishing a platform for service provider‟s to advertise their self-contained, self-reliable and self-governing data. Though, these centralized infrastructures do not offer easy way to explore available services for users in thenetwork, and also nor have the ability to verify their origin and history. The contribution of the paper is to address these challenges by leveraging the decentralized, immutable, tamper-proof Blockchain technology by establishing Blockchain service registry and execution via smart contract for secured semantic web service discovery. This allows users to explore the services in a network and also able to identify its service origin and integrity. Our first evaluation shows the promising results with this system paradigm in the field of web service provisioning. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF
5. Interstitial lung disease - Case study.
- Author
-
Sridevi, S., Ilavendhan, A., Devi, M. Shyamala, Rahila, J., Kumari, D. Abitha, and Pandeeswari, B.
- Subjects
- *
INTERSTITIAL lung diseases , *LUNGS , *PULMONARY fibrosis , *BLOOD vessels - Abstract
In this research, we will look at interstitial lung disease (ILD), which is an inflammation and fibrotic respiratory illness that mostly damages the cells and area around the lungs' air sacs known as the interstitium. There are around group of 200 diseases belonging to this category. This disease affects the other compartments of lungs, the airways known as alveoli, the blood vessels and the outside lining of lung known as pleura. This disease is characterized by respiratory symptoms, chest radiographic abnormalities, pulmonary fibrosis and fibrosis results from chronic inflammation. The lung biopsies with predominance of fibrosis results in poor prognosis comparatively than inflammation. Many studies reported that 80.9 per 1, 00,000 men and 62.7 per1, 00,000 women was diagnosed with this disease every year. There is no established treatment that prolongs life for patients with these diseases. It is critical to do accurate diagnosis in order tohave significantly dissimilar treatment choices and a improved prognosis. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
6. Factor significance based mortality grading of heart failure patients.
- Author
-
Devi, M. Shyamala, Sridevi, S., Anandaraj, A. Peter Soosai, Reddy, B. Chengal, Gopichand, B., and Sai, T. Leela Sankara
- Subjects
- *
HEART failure patients , *DATA libraries , *RANDOM forest algorithms , *DATA scrubbing , *VENTRICULAR ejection fraction - Abstract
The rate of death in heart failure patients keeps increasing, but the causes of death are always uncertain. Even though heart failure is a diverse syndrome classified by ejection fraction, the relationship among both ejection fraction and death rates is significant but elusive. According to health cardiology report, Patients with heart failure and reduced ejection fraction have greater risk of dying, compared with heart failure patients and preserved ejection fraction. However, the factors influencing the death rate of heart failure patients remains a challenging task for the doctors and researchers. With this motivation, this paper attempts to analyze the important features that influences the mortality rate of the patients. The Heart Failure dataset from UCI data warehouse repository is subjected for analyzing the heart failure patients. The dataset is preprocessed with data cleaning process and missing values. The preprocessed dataset is applied to all the classifiers and the performance of the mortality grading is analyzed before and after feature scaling. The raw dataset with entire 12 features are applied to Ada Boost, Random Forest, Extra Tree and Gradient Boost classifier to extract the top six important features to increase the accuracy performance. The feature importance dataset is then applied to all the classifier and the performance is analyzed in terms of accuracy, precision, recall, FScore and Run Time. The implementation results shows that random forest classifier is showing the accuracy of 89% after feature scaling and the random forest classifier with the feature importance of Gradient Boost classifier shows the accuracy of 97%. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
7. Predicting prostate cancer in early stage using adaptive randomized tree.
- Author
-
Anandaraj, Peter Soosai, Devi, M. Shyamala, Sridevi, S., Sherly, Steffy, and Punitha, A. Amali Angel
- Subjects
PROSTATE cancer ,PROSTATE-specific antigen ,TUMOR classification ,IMAGE analysis ,FORECASTING - Abstract
Precise and early diagnosis is crucial for the cancer patients to get optimal care. Tools available to predict cancer in advance remains deficient and also there are considerable false positive rates. In order to avoid this, the proposed work focuses on Clinical Data analysis and Image analysis of Ultra sound images to predict cancer at initial stages. In this analysis, Adaptive Randomized Tree (ART) uses clinical data such as percentage of unbound Prostate Specific Antigen (PSA), bound PSA, age, PSA density and PSA velocity and intensity extracted from Ultra sound images as metrics to predict carcinoma. Hence ART has a better prognostic performance than other diagnostic indicators for prostate cancer. This gives the preliminary evidence that ART can be used as an effective diagnosis tool for other type of cancers with appropriate metrics. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
8. Big data analysis of traditional Indian Ayurveda medicine and treatment process.
- Author
-
Keerthi, K. Laleeth and Sridevi, S.
- Subjects
- *
AYURVEDIC medicine , *HUMAN constitution , *DATA analysis , *NOSOLOGY , *HUMAN behavior - Abstract
Prakriti (Human Body constitution) clearly defines harmony with human nature and cause for moving out of balance and experience disease. Basically, there are 3 energies called VATT, PITT, and KAPH which decides body function on physical and emotional levels. These 3 energies known as Tridosha. Few people may predominant in one or mixture of 2 or more. For the long time, Ayurveda Dosha have been utilized. However, these diagnostic methods actually lingers behind in quantitative unawaring quality estimations. A cautious and proper examination prompts a powerful treatment. This work review academic journal and conference papers which adopted Machine Learning (ML) techniques in Ayurveda based disease classification and diagnosis using public medical datasets published in recent years. The aftereffects of this review showed that the use of ML procedures in illness order has encountered an intense rise in recent years. The finding of this paper additionally uncovered that there was negligible spotlight on creating strategies utilizing steady form of ML procedures. We trust that this examination will give valuable data about different ML strategies, their application in illness conclusion, and especially help specialists for creating medical decision support networks with experiences into the best in class of improvement techniques. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
9. Secure deep learning model for disease prediction and diagnosis system in cloud based IoT.
- Author
-
Parvathy S. and Sridevi, S.
- Subjects
- *
INTERNET of things , *DIAGNOSIS , *DEEP learning , *PREDICTION models , *NOSOLOGY , *MACHINE learning - Abstract
In the past few decades, IoT (Internet of Things) based m-healthcare applications are arising to provide real time services in the fast world. These applications save people's lives by getting regular updates about health conditions of them for their easy lifestyle. Cloud based health care framework are provide better outcomes when compared to conventional methodologies. Nowadays Incorporating IoT devices in clinical environments plays major role in handling huge volume of medical data. Researchers thus sought to automate the process of detecting and diagnosis diseases using could computing technology. Accordingly, number of explores has been proposed an infection forecast and analysis framework in cloud based IoT utilizing distinctive secure ML (Machine Learning) calculations. This paper reviews the existing heart disease classification research frameworks with its pros and cons. Here, totally twenty-five papers are analyzed. In addition, this study gives an elaborate idea about disease prediction and diagnosis system. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
10. Study of cloud sensor network with reliable infrastructure and architecture.
- Author
-
Monica, K. M., Sridevi, S., and Bindu, G.
- Subjects
- *
SENSOR networks , *COMMUNICATION infrastructure , *INFRASTRUCTURE (Economics) , *DISTRIBUTED sensors , *HOME security measures , *EDUCATIONAL technology , *HUMAN activity recognition - Abstract
Numerous associations wanted to work their organizations, works and administrations in an extremely portable (for example with perfect timing and anyplace), dynamic, and information situated style. Exercises like e-learning, natural learning, distant assessment, medical services, home security and wellbeing components and so on needs an uncommon foundation which may offer persistent, got, solid and versatile information with right data/information the board situation in setting to their restricted climate and its clients. An uncertain assortment of finder networks for different medical services applications has been planned and implemented anyway every one of them lacking extensibility, adaptation to non-critical failure, portability, steadfastness and transparency. Consequently, in this paper an open, adaptable and re-arrange able foundation is anticipated medical services recognition applications, here the sensors utilized as virtual sensors on distributed computing organization. In this paper we will in general audit a few ways to deal with rush the assistance manifestations in field of medical services and various applications with Cloud-Sensor plan. This plan offers types of assistance to complete clients while not stressing in regards to its execution subtleties. The plan allows the help requesters to utilize the virtual sensors without anyone else or they will create diverse new administrations by expanding virtual sensors. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
11. A survey on recognition and classification of paddy leaf diseases using image processing and machine learning techniques.
- Author
-
Kalpana, P. and Sridevi, S.
- Subjects
- *
IMAGE processing , *RICE , *MACHINE learning , *PLANT parasites , *PLANT diseases - Abstract
From the past few years spreading of the pests and diseases in plants have been increasing significantly. Paddy plants are the most important crop used in our country for the food, so it is most necessary to detect any disease of them within a short period of time for ensuring a proper and healthy growth of paddy plants. The process of manual disease detection requires labor and a large amount of time. Then utilizing the leaf images of plants for recognizing and classifying of diseases is the more focused research topic in the agriculture field. A survey on recognition and classification of paddy leaf diseases using image processing and machine learning techniques is presented in this paper based on the disease infected leaf images of paddy plants. Firstly the concept of various plant diseases and the standard process of plant disease detection are discussed in this paper. A study and survey on the totally 5 papers of work is carried out in detail by covering a work on leaf diseases of the paddy plants based on the certain criteria. Such criteria are different preprocessing techniques, various diseases/ classes, different segmentation methods, various classifiers and accuracy of employed techniques. The experimental results of these various techniques are compared and evaluated to design a best on detecting and classifying of paddy plant leaf diseases. [ABSTRACT FROM AUTHOR]
- Published
- 2022
- Full Text
- View/download PDF
12. A Study on Shortest Distance Measurement RSSI Localization in Mathematical Software of Cooperative Game Theory with Floyd’s Algorithm.
- Author
-
Chithra, S. M., Sridevi, S., and Satheesh, S.
- Subjects
- *
COOPERATIVE game theory , *SOFTWARE localization , *LOCALIZATION (Mathematics) , *ALGORITHMS - Abstract
In this paper, we introduced some new concepts of the distance measurement based on RSSI localization of cooperative game theory technique in Mathematical software. Investigating some of their properties, we show that the detachment sandwiched between node i and node j is Gij, which is defined as the smallest path in RSSI localization of cooperative game theory technique in Mathematical software d1 and dj i. e we find the shortest path between all the pair of nodes in Mathematical software is termed as all pair shortest path using Floyd’s algorithm. [ABSTRACT FROM AUTHOR]
- Published
- 2019
- Full Text
- View/download PDF
13. Enhancement of anisotropic conductivity, elastic, and dielectric constants in a liquid crystal-gold nanorod system.
- Author
-
Sridevi, S., Prasad, S. Krishna, Nair, Geetha G., D'Britto, Virginia, and Prasad, B. L. V.
- Subjects
- *
ELECTRIC conductivity , *DIELECTRICS , *ELASTICITY , *ANISOTROPY , *NANOSTRUCTURES , *LIQUID crystals , *COLLOIDAL gold , *CRYSTAL defects - Abstract
We report electrical conductivity (σ), dielectric constant ([variant_greek_epsilon]) and the elastic constant measurements in a nematic liquid crystal (LC) doped with small concentrations of gold nanorods. This LC-nanoparticle complex, shows not only orders of magnitude higher σ, but also stabilizes its anisotropy. The [variant_greek_epsilon] data suggests an increased ordering in the nematic phase, and an improved antiparallel correlation of the molecules in the isotropic phase. Surprisingly, an anisotropic enhancement of the Frank elasticity is also seen. We suggest a possible electro/magnetomechanical conductivity switch and also provide explanations based on the aspect ratio of the nanoparticles vis-à-vis the LC molecules. [ABSTRACT FROM AUTHOR]
- Published
- 2010
- Full Text
- View/download PDF
14. An optimization-based algorithm for obtaining an optimal synchronizable network after link addition or reduction.
- Author
-
Parastesh F, Sriram S, Natiq H, Rajagopal K, and Jafari S
- Abstract
Achieving a network structure with optimal synchronization is essential in many applications. This paper proposes an optimization algorithm for constructing a network with optimal synchronization. The introduced algorithm is based on the eigenvalues of the connectivity matrix. The performance of the proposed algorithm is compared with random link addition and a method based on the eigenvector centrality. It is shown that the proposed algorithm has a better synchronization ability than the other methods and also the scale-free and small-world networks with the same number of nodes and links. The proposed algorithm can also be applied for link reduction while less disturbing its synchronization. The effectiveness of the algorithm is compared with four other link reduction methods. The results represent that the proposed algorithm is the most appropriate method for preserving synchronization.
- Published
- 2023
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.