scispace - formally typeset
Search or ask a question
Author

B. Valarmathi

Bio: B. Valarmathi is an academic researcher from VIT University. The author has contributed to research in topics: Sentiment analysis & Computer science. The author has an hindex of 4, co-authored 22 publications receiving 60 citations.

Papers
More filters
Proceedings ArticleDOI
01 Jan 2017
TL;DR: The architecture and design of Arduino based car parking system solves the parking issue in urban areas, also provides security to a vehicle and an unauthorized user is not allowed to enter into a parking place.
Abstract: This paper explains the architecture and design of Arduino based car parking system. Authorization of driver or user is the basic rule used to park a vehicle in a parking place. Authorization card will be given to each user, which carries the vehicle number or other details. If the user is authorized and space is available in the parking, then the parking gate will open and the user is allowed to park the vehicle in parking place else the user is not allowed even the user is authorized person. If car is allowed to park, then mobile notification will be send to user about parking. It solves the parking issue in urban areas, also provides security to a vehicle and an unauthorized user is not allowed to enter into a parking place. It helps to park vehicle in multifloored parking also as it will display which floor has free space.

29 citations

Journal ArticleDOI
N. Srinivasa Gupta1, D Devika, B. Valarmathi1, N. Sowmiya1, Apoorv Shinde1 
TL;DR: In this paper, a heuristic based on correlation analysis and relevance index is proposed for the formation of machine-part cells, which is the process of identifying part families and the appropriate machine cell for each part family.
Abstract: Machine-part cell formation is the process of identifying part families and the appropriate machine cell for each part family. Grouping efficacy (GE), the widely used measure for assessing the goodness of the machine-part cells depends on identification of correct part families and the appropriate machine cell for each part family. In this paper, a heuristic based on correlation analysis and relevance index is proposed for the formation of machine-part cells. Computational performance of the proposed heuristic on a set of group technology data-set available in the literature is also presented. GE of the solutions produced by the proposed heuristic is equal to the best efficacy reported in the literature for 63% of the test instances and improved the GE for 6% of the total test instances.

16 citations

Proceedings ArticleDOI
06 Apr 2017
TL;DR: The project aims to provide an efficient, low-cost automated energy management system for houses that provides features to cater to natural disasters like fire and uses embedded C as the programming language which provides a facility of easier coding for new features.
Abstract: The project aims to provide an efficient, low-cost automated energy management system for houses It also provides a facility for surveillance of the house The system has been built after evaluating the utility features of surveillance and energy management systems available at present and is an attempt to improve these features In addition to providing a cost-effective solution for energy management in the household, it also provides features to cater to natural disasters like fire The system is built on an Arduino UNO microcontroller board and uses embedded C as the programming language which provides a facility of easier coding for new features

14 citations

Posted ContentDOI
31 Dec 2014
TL;DR: The experimental results revealed that, the combination of RSART based on Genetic Algorithm approach and Bayesian Logistics Regression Classifier can be used for weather forecast analysis.
Abstract: Developments in information technology has enabled accumulation of large databases and most of the environmental, agricultural and medical databases consist of large quantity of real time observatory datasets of high dimension space. The curse to these high dimensional datasets is the spatial and computational requirements, which leads to ever growing necessity of attribute reduction techniques. Attribute reduction is a process of reducing the data space by removing the irrelevant, redundant attributes from large databases. The proposed model estimates the enhancement achieved in spatial reduction and classifier accuracy using Rough Set Attribute Reduction Technique (RSART) and data mining methods. The first module of this proposed model has identified an efficient attribute reduction approach based on rough sets for spatial reduction. The next module of the proposed model has trained and tested the performance of Naive Bayes (NB), Bayesian Logistic Regression (BLR), Multi Layer Perceptron (MLP), Classification and Regression Tree (CART) and J48 classifiers and evaluated the accuracy in terms of each classification models. The experimental results revealed that, the combination of RSART based on Genetic Algorithm approach and Bayesian Logistics Regression Classifier can be used for weather forecast analysis.

8 citations

DOI
30 Dec 2015
TL;DR: A meticulous comparison of the performance indicates ANN-BP model as a suitable HIS for effective rainfall prediction and a novel exhaustive search based Rough set reduct Selection using Genetic Algorithm (RSGA) is introduced.
Abstract: Uncertain atmosphere is a prevalent factor affecting the existing prediction approaches. Rough set and fuzzy set theories as proposed by Pawlak and Zadeh have become an effective tool for handling vagueness and fuzziness in the real world scenarios. This research work describes the impact of Hybrid Intelligent System (HIS) for strategic decision support in meteorology. In this research a novel exhaustive search based Rough set reduct Selection using Genetic Algorithm (RSGA) is introduced to identify the significant input feature subset. The proposed model could identify the most effective weather parameters efficiently than other existing input techniques. In the model evaluation phase two adaptive techniques were constructed and investigated. The proposed Artificial Neural Network based on Back Propagation learning (ANN-BP) and Adaptive Neuro Fuzzy Inference System (ANFIS) was compared with existing Fuzzy Unordered Rule Induction Algorithm (FURIA), Structural Learning Algorithm on Vague Environment (SLAVE) and Particle Swarm OPtimization (PSO). The proposed rainfall prediction models outperformed when trained with the input generated using RSGA. A meticulous comparison of the performance indicates ANN-BP model as a suitable HIS for effective rainfall prediction. The ANN-BP achieved 97.46% accuracy with a nominal misclassification rate of 0.0254 %.

5 citations


Cited by
More filters
Proceedings ArticleDOI
02 Jul 2018
TL;DR: A more adaptable and affordable smart parking system via distributed cameras, edge computing, data analytics, and advanced deep learning algorithms that can automatically detect when a car enters the parking space, the location of the parking spot, and precisely charge the parking fee and associate this with the license plate number is proposed.
Abstract: The smart parking industry continues to evolve as an increasing number of cities struggle with traffic congestion and inadequate parking availability. For urban dwellers, few things are more irritating than anxiously searching for a parking space. Research results show that as much as 30% of traffic is caused by drivers driving around looking for parking spaces in congested city areas. There has been considerable activity among researchers to develop smart technologies that can help drivers find a parking spot with greater ease, not only reducing traffic congestion but also the subsequent air pollution. Many existing solutions deploy sensors in every parking spot to address the automatic parking spot detection problems. However, the device and deployment costs are very high, especially for some large and old parking structures. A wide variety of other technological innovations are beginning to enable more adaptable systems—including license plate number detection, smart parking meter, and vision-based parking spot detection. In this paper, we propose to design a more adaptable and affordable smart parking system via distributed cameras, edge computing, data analytics, and advanced deep learning algorithms. Specifically, we deploy cameras with zoom-lens and motorized head to capture license plate numbers by tracking the vehicles when they enter or leave the parking lot; cameras with wide angle fish-eye lens will monitor the large parking lot via our custom designed deep neural network. We further optimize the algorithm and enable the real-time deep learning inference in an edge device. Through the intelligent algorithm, we can significantly reduce the cost of existing systems, while achieving a more adaptable solution. For example, our system can automatically detect when a car enters the parking space, the location of the parking spot, and precisely charge the parking fee and associate this with the license plate number.

67 citations

Journal ArticleDOI
01 Oct 2022-Big data
TL;DR: In this article , a multilevel approach for selecting base classifiers for building an ensemble classification model is proposed, which generalizes to predict all the class levels with an adequate percent of accuracy.
Abstract: To predict the class level of any classification problem, predictive models are used and mostly a single predictive model is built to predict the class level of any classification problem; current research considers multiple predictive models to predict the class level. Ensemble modeling means instead of building a single predictive model, it is proposed to build a multilevel predictive model, which generalizes to predict all the class levels with an adequate percent of accuracy, that is, from 70% to 90% by applying and using a different combination of classification algorithms. In this article, a multilevel approach for selecting base classifiers for building an ensemble classification model is proposed. The rudimentary concept behind this approach is to drop lousy performing features and collinearity from the selected data set for ensemble modeling. For the evaluation of the proposed multilevel predictive model, different data sets from the University of California, Irvine, repository have been used and comparisons with the modern classifier's models have been conducted. The implementation analyses demonstrate the potency and excellence of the novel approach when compared with other modern classification models (three-layered artificial neural network, Radial Variant Function Neural Network/Fish Swarm Algorithm). The classification accuracy achieved with selected algorithms lies in the range of 70%-88.3%. Among all the selected classification algorithms, the lowest accuracy is achieved by the naive Bayes algorithm, which is close to 71.9%. However, the proposed algorithm (NB-RF-LR-SEMod), which is a combination of different classifiers, achieved a maximum accuracy of 88.3% on the Photographic and Imaging Manufacturers Association Diabetes data set, which is, by far, the best to any single classifier. Hence, this proposed work is helpful for any health care official to detect the diabetes problem at an early stage and prevent the affected person from future complications of it.

45 citations

Journal ArticleDOI
TL;DR: The surveying of recent research in this area can support a better understanding of smart-city solutions based on popular platforms such as Raspberry Pi, BeagleBoard and Arduino, as presented in this article.
Abstract: With the increasing availability of affordable open-source embedded hardware platforms, the development of low-cost programmable devices for uncountable tasks has accelerated in recent years. In this sense, the large development community that is being created around popular platforms is also contributing to the construction of Internet of Things applications, which can ultimately support the maturation of the smart-cities era. Popular platforms such as Raspberry Pi, BeagleBoard and Arduino come as single-board open-source platforms that have enough computational power for different types of smart-city applications, while keeping affordable prices and encompassing many programming libraries and useful hardware extensions. As a result, smart-city solutions based on such platforms are becoming common and the surveying of recent research in this area can support a better understanding of this scenario, as presented in this article. Moreover, discussions about the continuous developments in these platforms can also indicate promising perspectives when using these boards as key elements to build smart cities.

40 citations

Journal ArticleDOI
TL;DR: Based on resource-based theory and enterprise ecosystem theory, this paper used the sample of Huang-huai-hai plain 487 grain family farms, in the basis of attribute reduction by rough set theory, introduce the important individual-level and provincial-level factors into hierarchical linear model, in order to reveal different level factors affect growth of grain family farm in structural differences and interaction.

30 citations