SHARMILA BEGUM M | Periyar Maniammai University (original) (raw)

Papers by SHARMILA BEGUM M

2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS)

Automated plant identification is a very promising solution for bridging the taxonomic gap, which... more Automated plant identification is a very promising solution for bridging the taxonomic gap, which is receiving much attention from botany and computer science. As machine learning technology advances, more complex models have been proposed to automate crop identification. Herbal remedies are considered in the pharmaceutical industry due to fewer harmful side effects and less expensive than modern medicine. Based on these data, many researchers have shown great interest in studying the recognition of natural herbal medicines. There are various possibilities for moving towards solid phase production capable of accurately discriminating medicinal plants in real time. In this project, efficient and reliable machine learning algorithms for plant catalogues using leaf images used in recent years are being studied. The review covers image processing techniques used to locate leaves and extract important leaf features from other machine learning steps. These deep learning stages are classified according to their function when it comes to discriminating leaf images based on common plant characteristics, i.e. shapes, ridges, textures and combinations of many elements. Then you get results using herbs with improved accuracy. The test results indicate that the proposed system provides an improved level of accuracy.

Environment, Development and Sustainability, 2021

In recent years the importance and demand of renewable energy has been increased drastically. The... more In recent years the importance and demand of renewable energy has been increased drastically. The energy producers are facing ongoing challenges in executing biogas production due to lack of automation facilities and intelligent mechanisms to optimize the gas production. Our research work aims to design and develop Internet-of-things (IoT) controlled system coupled with a logic controller to monitor, predict and enhance biogas production thereby to overcome the current barriers and shortcomings of biogas production. The proposed architectural framework comprises three layers firstly the sensing layer followed by the predicting lawyer then the resolving layer. The sensing layer senses the data from the microcontroller coupled with temperature, pH, pressure and the methane sensor. In the predicting layer the sensed data are transported into the fuzzy domain by the fuzzification process. A rule-based inference engine predicts the appropriate consequences based on the antecedents. In th...

Outcome based education (OBE) in higher-education institutions is to improve the quality of teach... more Outcome based education (OBE) in higher-education institutions is to improve the quality of teaching-learning experience. This paper presents a "OBE", a web based software system for the implementation of OBE in Higher Education institutions. This web based system extends higher education institution programme design, based on well-defined Programme educational objectives, Programme Outcomes and programme specific outcomes. This model uses criterion-referenced assessment, membership functions and rubrics for performance evaluation. Iterative software development approach is used in this system development to support corrective actions for the objectives and outcome of stakeholders. This paper includes a case study with software engineering programme in a university. Results show that the teaching-learning quality of Outcome Based Education outperforms conventional educational system. The result also show that the proposed system assist faculties in understanding students&#...

The two most important tasks in information extraction from the Web are webpage structure underst... more The two most important tasks in information extraction from the Web are webpage structure understanding and natural language sentences processing. However, little work has been done toward an integrated statistical model for understanding webpage structures and processing natural language sentences within the HTML elements. Our recent work on webpage understanding introduces a joint model of Hierarchical Conditional Random Fields (HCRFs) and extended Semi-Markov Conditional Random Fields (Semi-CRFs) to leverage the page structure understanding results in free text segmentation and labeling. In this top-down integration model, the decision of the HCRF model could guide the decision making of the Semi-CRF model. However, the drawback of the topdown integration strategy is also apparent, i.e., the decision of the Semi-CRF model could not be used by the HCRF model to guide its decision making. This paper proposed a novel framework called WebNLP, which enables bidirectional integration o...

2017 International Conference on Intelligent Sustainable Systems (ICISS), 2017

Advances in Intelligent Systems and Computing, 2018

Data analytics is the science of extracting patterns, trends, and actionable information from lar... more Data analytics is the science of extracting patterns, trends, and actionable information from large sets of data. The growing nature of data in from different servers with in consistent data formats like structured, semi-structured and unstructured data. Traditional IT infrastructure is simply not able to meet the demands of this new "Data Analytics" landscape. For these reasons, many enterprises are turning to the Hadoop (open source projects) as a potential solution to this unmet commercial need. As the amount of data especially unstructured data collected by organizations and enterprises explodes, Hadoop is emerging rapidly as one of the primary options for storing and performing operations on that data. The secondary problem for data analytics is security, this rapid increase in usage of Internet, drastic change in acceptance of people using social media applications that allow users to create contents freely and amplify the already huge web volume. In today's businesses, there are few things to keep in mind while beginning big data and analytics innovation projects. The need of secured data analytics tool is mandatory for the business world. So, in the proposed model, major intention of work is to develop the two-pass security-enabled data analytics tool. This work concentrates on two different ends of current business worlds need namely attribute-based analytical report generation and better security model for clients. This proposed work for Key generation and data analytics is the process of generating keys is used to encrypt and decrypt whatever data need to be analyzed. The work is to develop the two-pass security-enabled data analytics tool. The software and hardware keys are programmed and embedded in the kit. When the user inserts the software and hardware key, the unique key will be generated in 1024 bit key size. This will provide high level of authentication for the data to be analyzed. The data analytics part is performed with attribute-based constraints

Hybrid Warehouse System is to shield the reaped grains from being ruined by creepy crawlies, micr... more Hybrid Warehouse System is to shield the reaped grains from being ruined by creepy crawlies, microbial assault, air and water which decline the quality just as amount of sifted gathered grains. Capacity is perhaps the most concerning issue in an agrarian nation like India where million tons' of reaped grains is lost by various components headed previously. Half and half Warehouse arrangement comprise of installed IoT with a programmed rooftop which is comprised of board of sun oriented cells which has sensors for downpour, daylight, fire, biogas and stickiness and programming to foresee the harvests. We propose a half breed stockroom to securely ensure the nourishment grains in huge sum. For security reason we here utilize more sensors. This paper is planned with arduino which goes about as a microcontroller and the sensors send data to cloud based IoT. The framework for the most part screens the information by keen sensors. The framework can caution the client (rancher), when t...

The foremost aim of our paper is to predict next-day and any particular month Bitcoin prices with... more The foremost aim of our paper is to predict next-day and any particular month Bitcoin prices with respect to the company as early as possible. To obtain results at the earliest we made our implementation in Apache Spark, a big data tool. We have also utilised one of the widely used machine learning libraries namely pandas for dataset manipulation, and preferred Pyspark since it is the combination of Apache Spark and Python. For investor interaction with our system we have designed a Graphical User Interface (GUI) and named it as ‘PMIST’ with Tkinter which is a Python’s GUI. The result predicted will be seen in the form of line and bar graphs along with a message prompt where right date for doing investments are suggested. By analyzing those graphs, investors can be able to get idea about the future prices and they can take decision to either invest in future or change their investment time. Also a rewarding system is designed for the investors in which we will provide 50% offer in S...

Journal of emerging technologies and innovative research, 2019

2016 International Conference on Emerging Trends in Engineering, Technology and Science (ICETETS), 2016

The paper titled “STEP-A career zone Android APP for Higher Secondary Students” is an application... more The paper titled “STEP-A career zone Android APP for Higher Secondary Students” is an application which helps the higher secondary school students for their career. STEP stands for (Skill towards Entry and Prediction). It involves the analysis and prediction process to choose the students' career using Mobile and Tablets. It creates awareness among the students about the courses, degrees, entrance exams, eligibility criteria and institutions available. Students can choose their desired course with their own will of free to act upon the destination. In order to build their future in a prosperous manner, the STEP will be very much useful. STEP incubates lots of resources about individual subjects, scholarships, schemes available, institutional ratings, fees, etc. Students can easily obtain their maximum expected courses and colleges list in the priority they define.

International Journal of Engineering and Technology, 2017

In recent years, much interest in developing Data analytics tools has been mainly intense on expl... more In recent years, much interest in developing Data analytics tools has been mainly intense on exploring and understanding massive data formats in social media and growing internet. Such data are a typical form of multimedia data that comprise text, images, videos, and networks. In this survey work, we present a comprehensive overview of the Data analytics tools, their merits and challenges. A taxonomy of prior studies is introduced to classify the state-of-the-art techniques into two categories, namely, Data analytics for gathering information and understanding user behaviors. The proposed taxonomy can provide a coherent vocabulary for researchers to share knowledge and simplify analysis tasks. The Data analytics is rapidly developing with numerous new methods emerging every year. However, the area is still in its infancy with many challenges and open questions. Many of the challenges cannot be addressed using techniques from only one discipline. We believe that multidisciplinary research that combines Dataization, multimedia, NLP, and human computer interaction will lead to more powerful and enabling approaches and technologies to handle and understand data. Keywords-Big data analytic, Tools, Business Intelligence (BI)and Frameworks I. INTRODUCTION Managing and analyzing challenges data have for organizations always offered benefits across all industries. The biggest challenges for today's technology lies in the increasing prevalence of data. This is frequently referred to as "big data" [1]. Never before in the history of humankind, have we been able to generate a living history of ourselves. In the process, we are creating new data of immense size and scope. It is indeed a trans formative change to see that within a few decades we have moved from complaining about the lack of data to a data deluge. [2] This makes data analytics even more exciting and indispensable. Big data analytics is the process of examining large data sets containing a variety of data types-i.e. ,big data to uncover hidden patterns, unknown correlations, market trends, customer preferences and other useful business information. The analytical findings can lead to more effective marketing, new revenue opportunities, better customer service, improved operational efficiency, competitive advantages over rival organizations and other business benefits. The primary goal of big data analytics is to help companies make more informed business decisions by enabling data scientists, predictive modelers and other analytics professionals to analyze large volumes of transaction data, as well as other forms of data that may be untapped by conventional business intelligence (BI) programs. That could include Web server logs and Internet click stream data, social media content and social network activity reports, text from customer emails and survey responses, mobile-phone call detail records and machine data captured by sensors connected to the Internet of Things. Some people exclusively associate big data with semi-structured and unstructured data of that sort. The International Data Corporation (IDC) research forecasts that overall details will develop by 50 times by 2020, motivated mainly by more included systems such as receptors in outfits, medical gadgets and components like structures and connects. The research also identified that unstructured details-such as data files, email and video-will account for 90% of all details designed over the next several years. But the number of IT experts available to handle all that details will only develop by 1.5 times the present levels. II. BIG DATA ANALYSIS PREREQUISITE Big data frequently involves a development of cultural and technical changes throughout a business or provide new business opportunities to expanding the sphere of inquiry to exploit new acumen's to combine both traditional and big data analytics. It involves making "sense" out of huge volumes of mixed data that in its raw form absences a data model to define what each element means in the context of the others [3]. There are some new issues like discovery, iteration, flexible capacity, mining and predicting or decision management. For ex. many organizations have no idea whether or not data huts light on sales trends or challenge comes with figuring out which data element relate to other data elements, and in what data storage capacity. This process of discovery not only involves sightseeing the data to understand how to use it but also to grasp its relation to traditional database.

Promotion and propagation of Ancient Indian Medical System has been our aim, as we foresee the us... more Promotion and propagation of Ancient Indian Medical System has been our aim, as we foresee the usefulness and cost effectiveness of traditional medical system. Even though there has been a tremendous advancement in medical technology, the prediction or diagnosis of diseases are costlier than the treatment. Intelligence can be spotted out in each and every cell in an human body and this intelligence gets communicated throughout the body in the form of vibration which can be examined through Wrist Pulse Examination. Since this wrist pulse signals contains vital information which explicitly points out the pathologic changes in a human body. Here, we propose a new methodology named "Wrist Energy Fuzzy Assist Cancer Engine – WE-FACE" for prediction and diagnosis of diseases using fuzzy logic. We mainly focus on the prediction and diagnosis of cancer through wrist pulse signals with the use of appropriate sensors.

2012 International Conference on Data Science & Engineering (ICDSE), 2012

Diagnosing Diseases through pulse-"finding any disease using nadi" is an automated system to find... more Diagnosing Diseases through pulse-"finding any disease using nadi" is an automated system to find the diseases and its related informations about the human body. This project provides detailed information and reports on patients by obtaining their nadi as a time series.The nadi pulses are sensed by the fingertip, which actually measure the pressure exerted by the artery. These pulsations are very minute in pressure units and a set of three such pressure transducers is mounted on the wrist to sense three location pulses, namely vata, pitta and kapha. The electrical signal proportional to the pressure experienced, in differential mode, by the pressure sensing element is then digitized using the 16-bit multifunction data acquisition card NI USB-6210 (National Instruments, TX, USA), having an interface with the personal computer. The data is captured at a sampling rate of 500 Hz (which is sufficiently higher than the Nyquist criteria) for a predetermined length of time. Our application shows the probable disease results according to the pulse waveform and pressure applied at the sensing element per unit time. Hence our Indian Medicine Practitioners can use this system as automated computer-aided diagnostic tool.

2011 International Conference on Recent Trends in Information Technology (ICRTIT), 2011

ABSTRACT

2011 3rd International Conference on Electronics Computer Technology, 2011

Ayurveda is a traditional medicine and natural healing system in India. Nadi Aridhal-"finding any... more Ayurveda is a traditional medicine and natural healing system in India. Nadi Aridhal-"finding any disease using nadi pulse" is an automated system to find and dictate the disease and its related information of the human body. In this paper we provide the detailed information and reports by obtaining nadi pulse from the patients as a time series. By reading the signal from the sensors that are send to transmitters and amplifier and a DC (digitizer) for quantifying analog signal. Our system acquire the data with 32-bit accuracy with practically external noise can be minimized of our application .The reading are send to our Nadi Aridhal programmatic application receives it and plot the reading into (vata,pitta,kapha) pulse waveform graphs per time. Our application shows the probable disease results according to the pulse waveform and pressure applied at the sensing element per time.

2019 Third International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), 2019

With the increased usage of internet, the concerns on data security and accuracy have become majo... more With the increased usage of internet, the concerns on data security and accuracy have become major challenges. Usage of internet and impact of various social networks amplify the security concerns for data storage. Report generation of attribute based analysis and better security model for clients were implemented with the attribute based association rule which helps to generate keys using improved apriori algorithm. This mainly focus on enabling and ensuring the data security through data analytic integrated framework which uses asymmetric key based RSA algorithm up to 8192 bit to secure from unauthorized users. This model focuses on the security of data when incorporated with embedded technique. Result analysis of key generation for strong password are carried out by increasing the bit size and analysed the execution time of both public and private key generation.

International Journal of Engineering & Technology

Data analytics (DA) is the process of exploring datasets in order to illustrate conclusions about... more Data analytics (DA) is the process of exploring datasets in order to illustrate conclusions about the information they contain. It is a process of inspecting, cleansing, transforming, and modeling data with the goal of discovering useful information. A database contains both structured and semi-structured data. The semi-structured data are from different sources. The system is provided with an open grid rule generationfor analyzing the data from whole data container. According to this concept, the analysis is much absolute rather than other, data mining technique.The main objective of the proposed study is to provide data having better and significant perspective.