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

In this paper, a method has been proposed to allot a parking spot after detecting it using single-shot multibox detector (SSD). The CCTV cameras will capture n number of frames and pass it through single neural network that is SSD. This will help in fetching details of the vacant parking spot. Subsequent convolution and non-maximum suppression will make the most accurate box around the detected object. Further, the coordinates will be fetched and will be allotted to the incoming cars. This will save time and fuel especially in leveled parking areas. The industrialization of the world, increment in population, moderate-paced city improvement, and bungle of the accessible parking spot have brought about parking-related issues. There is a critical requirement of clever, efficient, fast, protected, dependable, and secured framework for this paper which will be used for getting the vacant parking spots. The method proposed in this paper is better than the already existing one which is ultrasonic radiations and sensors as it is faster, and the drawback of an object/vehicle not being recognized due to its presence in the blind spot is overcome. SSD captures more number of frames compared with YOLO and CNN. It is best for large object recognition and real-time processing which will provide a secured framework for faster and efficient parking allotting. © Springer Nature Singapore Pte Ltd 2020.

VIT Unitversity

Department of Information Security

School of Computer Science and Engineering

Vellore Campus

Advances in Intelligent Systems and Computing Data Engineering and Communication Technology

Spot a Spot—Efficient Parking System Using Single-Shot MultiBox Detector

Most deaths occur around the world because of cardiac disorders. Cardiac rhythm disorders may cause severe strokes and heart diseases. Arrhythmias occur when the electric signals to the heart are irregular or not working properly. Mostly, these irregular heartbeats feel like racing hearts. Many times, arrhythmias are harmless, but if they are abnormal or they result due to damaged heart, then they can be fatal. Cardiac arrhythmia, being the leading cause of death in both men and women, can be prevented with the early and correct diagnosis. In this paper, the focus is mainly on predicting whether the patient has cardiac arrhythmia or not based on electrocardiography (ECG) reports. Pan–Tompkins algorithm has been used for QRS detection which predicts the abnormal deflections that lead to the arrhythmic events. The same reports have been used to classify which type of cardiac arrhythmia the patient has using Multilayer Perceptron (MLP) algorithm. © 2020, Springer Nature Singapore Pte Ltd.

World University root node

Smart Innovation, Systems and Technologies

Predicting Cardiac Arrhythmia Using QRS Detection and Multilayer Perceptron

Deep Q-learning is the incorporation of Q-Learning and Artificial Neural Network. Q-Learning is a reinforcement learning technique, which uses rewards to achieve the goal. This paper discusses about developing an AI such that it maintains the temperature of a server in an optimal range. Server environment will be set up, and the AI will be controlling the cooling/heating of the server so that it stays in an optimal range of temperatures while saving the maximum energy, therefore minimizing the costs using deep Q-learning. The number of users and the rate of data transmission will be randomly fluctuating to simulate an actual server. This will lead to randomness in the temperature and the AI has to understand how much cooling or heating power it has to transfer to the server so as not to deteriorate the server performance and, at the same time, expend the least energy by optimizing its heat transfer. © 2020 SERSC.

International Journal of Advanced Science and Technology

Reducing the operational costs of data centers through deep q-learning

The information technology field has emerged, established and improved over time, resulting in the utilization of Internet by many organizations. On the other hand, the data gathered by commercial and operational businesses is unstructured, hard to understand and of limited use. Business intelligence (BI) tools play a major role in extracting useful, intuitive, and graphical representation of accurate data that is useful for predictive analysis, trends, and patterns in business, and business decision making. The paper talks about current trends and techniques in BI segments (devices) and describes operational advances in an organization that utilizes BI framework, that results in the strengthening the connection between commercial business needs and IT technologies and how different BI methods are adopted and studies about current market business intelligence tools examples that give significance of usage of business intelligence in the enterprise business. © 2020, Springer Nature Singapore Pte Ltd.

Enterprise Reporting Solution on Integrating Business Intelligence for Operational and Financial Data

The cloud service is communicating between mobile devices through the Internet. They are prepended as platform independent and loosely conjoined. This paper’s objective is to obtain effective services with composition of services based on specific QoS parameters using principal component factor analysis method. The Factor analysis, analyzing the interrelationships among variables by characterizing highly correlated known as factors. In factor analysis, particularly statistical principal component analysis is used to consider the interrelationships among variables with a minimal loss of information. This analysis is made from the data collected from the cloud service providers. This result is based on components of cloud service availability, response time, throughput, reliability, successability, compliance, best practices, and web services resource framework. These are few parameters considered among the QoS parameters to find the best mobile cloud services. In this factor analysis based on principal component analysis considers these eight parameters which can be further improved to select the cloud services of QoS. © Springer Nature Singapore Pte Ltd. 2019.

Advances in Intelligent Systems and Computing Information Systems Design and Intelligent Applications

Evaluation of Quality of Service Parameters for Mobile Cloud Service Using Principal Component Analysis

Sentiment analysis makes use of natural language processing, computational linguistics, and analysis of text in order to extract information from text. In this project, we consider machine learning algorithm for classification of longer sentences with polarity from a huge amount of data from articles, forums, consumer reviews, surveys, blogs, Twitter, Whatsapp chat, etc., and come out with suitable results sentiments (e.g., sad, happy, surprised, angry) and give intensity/degrees. Naïve Bayes and SVM are complex and inaccurate and cannot handle large amount of data. Recurrent neural network takes into consideration the sequence of words in a sentence. We use a hybrid of both LSTM and GRU to learn the long-term dependency and do sentiment analysis. Our end goal is to perform sentiment analysis on long sentences and get accurate visualization results. Sentiment analysis can be widely applied to social media and reviews for various applications, such as customer service, marketing. © 2019, Springer Nature Singapore Pte Ltd.

Proceedings of the 2nd International Conference on Data Engineering and Communication Technology Advances in Intelligent Systems and Computing

Document-Level Analysis of Sentiments for Various Emotions Using Hybrid Variant of Recursive Neural Network

Recognition of human face is an important domain in unique identification of humans. It is currently being widely used in many industrial applications, such as video monitoring systems, human–computer interaction, and automatic gate control systems and for securing networks. Every university uses some method of attendance to keep a record of the number of students or people who attended that particular lecture. This paper delineates a method for taking attendance of people in a classroom which integrates the face recognition technology using local binary patterns histograms (LBPH) algorithm, along with face detection by Haar feature-based cascades and distance-based clustering. The proposed system records the attendance of the people in a classroom environment autonomously and provides the user with an output as a spreadsheet describing the attendance. © 2019, Springer Nature Singapore Pte Ltd.

Automatic Attendance System Using Face Recognition Technique

Image denoising is one of the most pressing challenges in Image Processing. Spatial Domain Filters are long existing method for denoising that are simple and effective against different types of noises, but they do not take into account the recurring patterns. Furthermore, due to ever increasing demand for image denoising on various applications in technology, the computational and memory intensiveness along with their performance on various types of noises becomes extremely important. Recently Convolutional Neural Networks have turned out to be state-of-the-art methods for denoising. We put forward a system which integrates a deep CNN preceded by Block Matching along with traditional spatial domain methods for image denoising for both random structures of an image as well as recurring patterns. This system is evaluated over a large data set of grey-scale images and various noises and has state-of-the-art results. © BEIESP.

International Journal of Recent Technology and Engineering

Image denoising using a combination of spatial domain filters and convolutional neural networks

The business framework architecture and evaluation are changing the growth of mobile cloud computing (MCC). The business service users required the facilities for selecting the mobile cloud services according to their quality of service (QoS) values in the business environment. In such a business environment, QoS parameter values help to build consumer confidence and provide a reliable environment for them. So the proposed system suggests a hybrid based on TOPSIS algorithm and plurality voting method which is more efficient, trustable for selecting the best cloud services. This algorithm has three phases to identify the service in the ranking process. The first phase is used to make a group the parameters based on the user’s requirements. The second phase applied the TOPSIS method on each of the parameters to get the service ranking. The final phase employed the plurality method which is counted the voting for each service to determine the best services. The hybrid algorithm takes O(n2) time in the best service selection process which is better than existing popular AHP, ANP multi-criteria decision methods in terms of time complexity. © 2019, Springer Nature Singapore Pte Ltd.

A QoS-Aware Hybrid TOPSIS–Plurality Method for Multi-criteria Decision Model in Mobile Cloud Service Selection

The mobile cloud services can be accessed over an internet by portable devices. The rapid growth of mobile services and cloud computing, the Mobile Cloud Computing becomes so popular. Mobile Cloud Computing (MCC) incorporates the cloud computing technology with mobile environment. The service associated with quality of service parameters which make it preeminent service to a user. This paper proposed a Preeminet Service Ranking (PSR) method using backward propagation neural network (BPNN) to find the best services. The method consists of two phases which are the Training phase and the Ranking phase. In the Training phase, the network is trained and obtain the deviation. It means that error of the current network from the ideal network. In the Ranking phase, determine the best services are at any given time using the deviation obtained from the training phase. The mobile cloud services are measured by using Quality of Service (QoS) parameters. This paper proved that a proposed method performs better over conventional methods like TOPSIS, AHP, and ANP. © 2018 The Authors. Published by Elsevier Ltd.

Fulltext

Procedia Computer Science

Neural Based QoS aware Mobile Cloud Service and Its Application to Preeminent Service Selection using Back Propagation

Mobile cloud computing is used utility based computing, where services are accessible over the internet through mobile devices, laptop, and other portable devices. In this generation where most applications run on the cloud, the quality of service (QoS) is an inherent element of service-oriented architecture. The performance of cloud service may change due to dynamic environments. The services are measured by the QoS parameters which are intrinsically uncertain. The growth of services on the internet, identifying the best services is very challenging in an economical manner. This paper proposed efficient QoS-aware cloud service ranking (CSR) method by using support vector machine (SVM). The CSR method decides a service ranking by using QoS parameters. The experimental results show the train model accuracy of the dataset. This algorithm takes O(n) time for cloud service ranking and its performance is better than conventional methods like AHP, ANP, and TOPSIS. © 2017 Inderscience Enterprises Ltd.