Chanthini Baskar

Bio: Chanthini Baskar is an academic researcher from Shanmugha Arts, Science, Technology & Research Academy. The author has contributed to research in topics: Defuzzification & Cold storage. The author has an hindex of 4, co-authored 9 publications receiving 64 citations.

A framework for analysing E-Nose data based on fuzzy set multiple linear regression: Paddy quality assessment

Abstract: Paddy is one of the important long stored grains. It is usually stored in granaries to ensure continuous supply throughout the year, which can be subjected to deterioration due to various environmental conditions. Electronic nose (E-Nose) is used for non-destructive rapid in-situ detection of paddy for qualitative and quantitative assessment. Further, soft computing techniques are a promising solution for data analysis to enhance prediction accuracy. In this work, paddy quality assessment has been carried out using an E-Nose. Six different metal oxide semiconductor gas sensors are used for detecting simple and assorted volatile organic compounds evolving from paddy when stored over a period of time at different conditions. A Fuzzy Set based Multiple Linear Regression (FSMLR) has been proposed and implemented for paddy quality assessment. In the first stage, four fuzzified sensor data are given as input for assessment. While in the second stage, piecewise multiple linear equations were used for quality assessment and defuzzification. Quantitative assessment was carried out for nineteen multiple linear regression models built using fuzzy set theory. The proposed model achieves better performance metrics in terms of low root mean square error for cross validation and relative prediction error (RMSECV

Analysis of Moisture Content in Beetroot using Fourier Transform Infrared Spectroscopy and by Principal Component Analysis.

Abstract: The moisture content of beetroot varies during long-term cold storage. In this work, we propose a strategy to identify the moisture content and age of beetroot using principal component analysis coupled Fourier transform infrared spectroscopy (FTIR). Frequent FTIR measurements were recorded directly from the beetroot sample surface over a period of 34 days for analysing its moisture content employing attenuated total reflectance in the spectral ranges of 2614–4000 and 1465–1853 cm−1 with a spectral resolution of 8 cm−1. In order to estimate the transmittance peak height (T p ) and area under the transmittance curve $$({\int }_{{\bar{ u }}_{i}}^{{\bar{ u }}_{f}}{T}_{p}d\bar{ u })$$ over the spectral ranges of 2614–4000 and 1465–1853 cm−1, Gaussian curve fitting algorithm was performed on FTIR data. Principal component and nonlinear regression analyses were utilized for FTIR data analysis. Score plot over the ranges of 2614–4000 and 1465–1853 cm−1 allowed beetroot quality discrimination. Beetroot quality predictive models were developed by employing biphasic dose response function. Validation experiment results confirmed that the accuracy of the beetroot quality predictive model reached 97.5%. This research work proves that FTIR spectroscopy in combination with principal component analysis and beetroot quality predictive models could serve as an effective tool for discriminating moisture content in fresh, half and completely spoiled stages of beetroot samples and for providing status alerts.

A low power ammonia sensor node embedded with a light weight non-linear analytics

Abstract: A wireless gas sensor node with nanosensor for rapid in-situ detection of ammonia gas is developed and an analytical model for precise and accurate quantification of ammonia in any industrial or closed environment has been proposed. A nanosensor is preferred due to its highly selective and sensitive properties for target gases. In this work, a traditional sensing circuit is replaced with a single sensor based voltage divider sensing circuit for signal feeding to microcontroller. As the room temperature operated chemiresistive ammonia sensor has eliminated the use of micro heater, overall power consumption is reduced. A low sensing power consumption of 56 mW was observed and the performance of non-linear model based gas detection algorithm was analysed using Relative Prediction Error (RPE), Root Mean Square Error for Cross Validation (RMSECV) and percentage recovery (% recovery). Best performance metrics values (RPE = 0.04%, RMSECV = 6.128, % recovery = 99.273) were obtained. In addition to this, the wireless sensor node is designed with power harvesting techniques to overcome the issues on node lifetime.

Advanced lightweight encryption algorithms for IoT devices: survey, challenges and solutions

Abstract: There are many emerging areas in which highly constrained devices are interconnected and communicated to accomplish some tasks Nowadays, Internet of Things (IoT) enables many low resources and constrained devices to communicate, compute process and make decision in the communication network In the heterogeneous environments for IoT, there are many challenges and issues like power consumption of devices, limited battery, memory space, performance cost, and security in the Information Communication Technology (ICT) network In this paper, we discuss a state-of-art of lightweight cryptographic primitives which include lightweight block ciphers, hash function, stream ciphers, high performance system, and low resources device for IoT environment in details We analyze many lightweight cryptographic algorithms based on their key size, block size, number of rounds, and structures In addition, we discuss the security architecture in IoT for constrained device environment, and focus on research challenges, issues and solutions Finally, a proposed security scheme with a service scenario for an improvement of resource constrained IoT environment and open issues are discussed

Securing the Internet of Things in the Age of Machine Learning and Software-Defined Networking

Abstract: The Internet of Things (IoT) realizes a vision where billions of interconnected devices are deployed just about everywhere, from inside our bodies to the most remote areas of the globe. As the IoT will soon pervade every aspect of our lives and will be accessible from anywhere, addressing critical IoT security threats is now more important than ever. Traditional approaches where security is applied as an afterthought and as a “patch” against known attacks are insufficient. Indeed, next-generation IoT challenges will require a new secure-by-design vision, where threats are addressed proactively and IoT devices learn to dynamically adapt to different threats. To this end, machine learning (ML) and software-defined networking (SDN) will be key to provide both reconfigurability and intelligence to the IoT devices. In this paper, we first provide a taxonomy and survey the state of the art in IoT security research, and offer a roadmap of concrete research challenges related to the application of ML and SDN to address existing and next-generation IoT security threats.

Electronic Nose and Its Applications: A Survey

Abstract: In the last two decades, improvements in materials, sensors and machine learning technologies have led to a rapid extension of electronic nose (EN) related research topics with diverse applications. The food and beverage industry, agriculture and forestry, medicine and health-care, indoor and outdoor monitoring, military and civilian security systems are the leading fields which take great advantage from the rapidity, stability, portability and compactness of ENs. Although the EN technology provides numerous benefits, further enhancements in both hardware and software components are necessary for utilizing ENs in practice. This paper provides an extensive survey of the EN technology and its wide range of application fields, through a comprehensive analysis of algorithms proposed in the literature, while exploiting related domains with possible future suggestions for this research topic.

Securing the Internet of Things in the Age of Machine Learning and Software-defined Networking

Abstract: The Internet of Things (IoT) realizes a vision where billions of interconnected devices are deployed just about everywhere, from inside our bodies to the most remote areas of the globe. As the IoT will soon pervade every aspect of our lives and will be accessible from anywhere, addressing critical IoT security threats is now more important than ever. Traditional approaches where security is applied as an afterthought and as a "patch" against known attacks are insufficient. Indeed, next-generation IoT challenges will require a new secure-by-design vision, where threats are addressed proactively and IoT devices learn to dynamically adapt to different threats. To this end, machine learning and software-defined networking will be key to provide both reconfigurability and intelligence to the IoT devices. In this paper, we first provide a taxonomy and survey the state of the art in IoT security research, and offer a roadmap of concrete research challenges related to the application of machine learning and software-defined networking to address existing and next-generation IoT security threats.