Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Mining is a challenging and important task in a non-stationary data stream. It is used in financial sectors, web log analysis, sensor networks, network traffic management, etc. In this environment, data distribution may change overtime and is called concept drift. So, it is necessary to identify the changes and address them to keep the model relevant to the incoming data. Many researchers have used Drift Detection Method (DDM). However, DDM is very sensitive to detect gradual drift where the detection delay is high. In this paper, we propose Adaptive Drift Detection Method (ADDM) which improves the performance of the drift detection mechanism. The ADDM uses a new parameter to detect the gradual drift in order to reduce the detection delay. The proposed method, ADDM, experiments with six synthetic datasets and four real-world datasets. Experimental results confirm that ADDM reduces the drift detection delay and false-positive rate (FPR) while preserving high classification accuracy. © 2021 World Scientific Publishing Co.

Department of Information Security

School of Computer Science and Engineering

Vellore Campus

Department of Analytics

Journal of Information and Knowledge Management

Adaptive Drift Detection Mechanism for Non-Stationary Data Stream

Network Security is the most important aspect for all products and services offered by networking systems. The network density and usage in information systems, technical systems are humungous and is used by the entire world to provide connectivity from busiest hours to remote locations. Mission critical events, governmental organizations, information technology structures rely on continuous and smooth provision of network connection. This makes the basis of information security pillars-Confidentiality, which means that the data transferred between two users can be readable but should not be understandable, meaning it should be encrypted; Integrity, which focuses on the aspect of reliable message transfer preventing any kind of message tampering in the data transfer process; and finally Authentication and Availability, meaning that the user sending and receiving the data are genuine, and that the data is available, free from denial attacks. Copyright © 2019 American Scientific Publishers All rights reserved.

Department of Software Systems

VIT Unitversity

Journal of Computational and Theoretical Nanoscience

Comparison of Machine Learning Algorithms to Build Optimized Network Intrusion Detection System

(A Question and Answer Software is a software that focuses on answering the questions one might put up on an online platform. These are usually implemented by large organizations which aim on implementing a platform where users can clear their doubts about their respective fields. It varies from small scale to large scale or from topic to topic. Many of these platforms may restrict access to either their employees or make it a public one. The disadvantages of the existing systems are less security, searching efficiency is less, chances of faking answer. One may access these sites/applications from another's system in case they are not public or access the ones which are and post answers which aren't relevant. Sometimes people even lie on such platforms and there might not be any checker to cross-analyze these answers. Now one might also want similar answers to their question which may resolve their query beforehand. Problems which are undertaken are first, making sure that there is more security and safety. Second, helping the users to search answers for similar questions which may answer their question beforehand and even highlight other important points worth knowing. There had to be a way to find if the answers are worth trusting. One can’t just blindly trust anything they read on the internet. They either look for other users who've said the same thing or maybe a trustworthy person like an expert. So in order to resolve these problems, the software created focuses on ensuring that a user has to make an account in order to access the website. Both users and experts can make their accounts and help out people with their queries. Third, there would be a similarity check that would allow the person to review similar questions and get more information. Lastly, this is a system which allows you to grade the answer you read with respect to how much it helped a person so others can trust the answer and its eligibility and see if it’s legit. One can find a number of such platforms, varying from technical to a know-all domain. Quora or Yahoo! Answers are standalone Question and Answer Softwares and along with StackOverflow, Qhub, and they all are open source.). © 2018, Blue Eyes Intelligence Engineering and Sciences Publication. All rights reserved.

World University root node

International Journal of Recent Technology and Engineering

An online question &amp; answer platform

Agriculture falls under the primary sector category which indicates that the majority of the country’s economy is depending on that. China is the top in the list of agricultural countries and India is recorded as the second top agricultural country in the world. The yield of a crop depends upon several factors like water, external temperature, the fertility of the soil etc. Among these, irrigation is one of such factors where human attention has to be provided more. Traditional plant watering method has two important things to consider, that is when to water the plants and how much water will be sufficient for the plant. Not all types of crops require the same amount of water. Crops like rice need more amount of water than other weed plants. This paper proposes an idea of a smart irrigation system based on IoT applications to increase the crop yield. If the available land is less then multi-crop is one of the good ideas to improve the profits or the crop yield in less time. This paper proposes an idea of a smart irrigation system with smart control of decision in which decision is made by taking the real-time data from the land. In this automated irrigation system, the pumping motor turns ON and OFF based upon the moisture content of the soil. The pump will be operated by an operation-amplifier which takes the input from a soil moisture sensor. The soil moisture sensor is a sensor that detects the exact amount of moisture in the soil. Now here comes the role of IOT to give the information to the farmers about the status of the water moisture. Farmers can see the status of moisture content in a web page using a modem or in a mobile application. They can check whether the water sprinklers are turned ON or not at any time. The farmer will be proved with saved data of the amount of moisture required for a specific type of crop. With this, the human presence can be decreased and an accurate amount of water supply can be provided to the field. © BEIESP.

International Journal of Innovative Technology and Exploring Engineering

Smart multi-crop irrigation system using IOT

The Propelled analytics of data streams is rapidly turning into an important territory of processing the complicated data as the quantity of requesting such applications grows continuously. Web based mining when the input data advancing over period is getting to be most important center problem. In todays real world the data is not stationary but non stationary. The properties of attributed are changing over time. As a result the data stream has concept drift and noise which affects the performance. The aim of the paper is to first present an overview of the challenges in the data streams, followed by the measures to improve the factors that affect the performance. © BEIESP.

International Journal of Engineering and Advanced Technology

The impact of streaming data noise reduction by using chunk based ensemble

This is the era of automated cars or self-driving cars. All car vendors are trying to come up with different advancements in the cars (Like Automatic car parking, Automatic Lane changing, automatic braking systems, android auto, car connect, Vehicle to external environment technology etc). In the automation industry, TESLA, Google and Audi are the most competent leader among each other as well as for other automation business also. Modern vehicles are all equipped with different technologies like navigation system, driver assistant mode, weather mode, Bluetooth, and other safety features which brings broader impact to quality of human’s life, environmental sustainability. This paper explains how the proposed feature, unlocks the semiautonomous cars or autonomous cars safely and provides the safety to the entry level cars. The acknowledged pictures are put away in the picture database amid confront acknowledgment by utilizing Support Vector Machine (SVM) classifier. Information from confront pictures through picture pressure utilizing the two-dimensional discrete cosine change transformation (2D-DCT). A self-arranging map (SOM) utilizing an unsupervised learning method is utilized to order DCT-based element vectors into gatherings to distinguish if the picture is "available" or "not available" in the picture database. The face is detected by the event that the framework perceives faces, only the authentic users are able to start the ignition of the car and untheorized users are not allow to start the ignition. © 2018, Blue Eyes Intelligence Engineering and Sciences Publication. All rights reserved.

Security and safety with facial recognition feature for next generation automobiles

Mining in data stream plays a vital role in Big Data analytics. Traffic management, sensor networks and monitoring, weblogs analysis are the application of dynamic environments which generate streaming data. In a dynamic environment, data arrives at high speed and algorithms that process them need to fulfill the constraints on limited memory, computation time, and one-time scan of incoming data. The significant challenge in data stream mining is data distribution changes over a time period which is called concept drifts. So, learning model need to detect the changes and adapt according to that model. By nature, ensemble classifiers are adapting to changes very well and deal the concept drift very well. Three ensemble-based approaches were used to handle the concept drift: online, block-based ensemble, and hybrid approaches. We provide a survey on various ensemble classifiers for learning in data stream mining. Finally, we compare their performance on accuracy, memory, and time on synthetic and real datasets with different drift scenarios.

Soft Computing and Medical Bioinformatics SpringerBriefs in Applied Sciences and Technology

A Comparative Analysis on Ensemble Classifiers for Concept Drifting Data Streams

To verify that our daily life is going in a secure way. Lot of research programmers are going on in this entire society. The turning point comes through the internet of things, industry has been emerged with the lots of elements provided from IOT. We can able to connect our daily life things or objects with this had successfully evolved lots of things. This Facial recognition door unlock system is a process is which will detect the face and identifies the among people. People are having different types of face cut, in that particularly there are many unique faces which are different from each other which inspired us, from that concept this process has been established. Our main aim to create the smart door system to a house, that will secure the house and all your personal things at your home. In this concept of our system we have been used alive web camera in the front side of the door, along with the display monitor. this web camera shows the owner/particular viewer the whom the house is his control, this shows the person who stood front of the door, the system is setup the voice output is being processed by the processor that which is used to show the answers/instructions as the output on the screen. We are using a stepper motor that which is used to lock/open then the by sliding method, so that a normal person stand in front of the door and access it. This process is done through this Microsoft face API application. The display is being operated on a Microsoft Visual Studio application.

Fulltext

International Journal of Engineering & Technology

Facial recognition enabled smart door unlock system

International Journal of Advanced Research in Computer Science and Software Engineering

Automated Toll and Parking Systems

Smart Home Automation System using Bluetooth and Infrared

The influence of the Samarium ions (Sm3+) on the electrochemical properties TiO2 nanoparticles has been analyzed by incorporating Sm ions in two different combinations using the sol-gel method. The bare and doped samples have been characterized using XRD, SEM, TEM and EDX, for its structural, morphological and compositional analysis of the sample. The Galvanostatic cycling, Cyclic voltammetry and Impedance analyzer has been employed to point out the electrochemical properties of the assembled batteries. The electrochemical properties of the sol-gel derived bare TiO2 are comparable with the literature. The Sm0.1Ti0.9O2 exhibits better capacity and lower capacity fading over multiple cycles. The higher Sm concentration exhibits more capacity fading after the initial cycles. The study reveals that the lower concentration doping of Sm stabilizes the TiO2 nanoparticles which makes it as a better candidate for its application potential towards lithium ion batteries. © 2017 Elsevier B.V.

Department of Thermal and Energy Engineering

School of Mechanical Engineering

Department of Chemistry

School of Advanced Sciences

Journal of Alloys and Compounds

Investigations on the influence of Sm3+ion on the nano TiO2 matrix as the anode material for lithium ion batteries

The objective of this review paper is to discuss the various channel access methodologies applied in various sensor and actuation based wireless networks. In most of Wireless Sensor Networks (WSNs) researchers have focused on priority centered approaches for channel accessibility. This paper also explains the procedure for Medium Access Control (MAC) in Cyber Physical Systems (CPSs) which is a combination of Wireless Sensor Actuator Networks (WSANs) and WSNs. Finally, we discuss the successive collision avoidance technique using the IEEE 802.11 MAC protocol, and also brief on how the Internet of Thing (IoT) approach connects and transfers information among smart devices linked in a wireless network. © 2017, Walailak University. All rights reserved.