IP traffic classification of 4G network using Machine Learning techniques
In today's world, the number of online services and users is growing rapidly. This leads to a huge increase in internet traffic. Therefore, the task of separating IP traffic is approx. it is important for Internet service providers or ISPs, as well as a variety of government and the private sector for better network management and security. IP traffic separation includes identifying user activity using network traffic flowing into the system. This will also help to improve the network performance. The use of traditional IP traffic Classification methods based on the evaluation of packet capacity and hole numbers dropped significantly because there are so many online apps today that use naturally incorrect port numbers than well-known port numbers. Also, there are several encryption strategies today as a result of when testing the package payload is blocked. Currently, various machine reading techniques are commonly used to differentiate IP traffic. However, not much research has been done on IP fragmentation 4G network traffic. During this study, we did a new database by downloading real-time Internet traffic packets 4G network data using a tool called Wireshark. After that, we released the considered features of the packaged packages using the python script. Then we used five typewriters models, namely, Decision Tree, Vector Support Equipment, K Very Near Neighbors, Random Forest, and Naive Bayes IP splitting traffic. It was noted that Random Forest offered the best almost 87% accuracy
Published by: S. Mahammad Rafi, T. Lavanya, B. Shamitha, S. Phaneeswar, N. Chandu
Author: S. Mahammad Rafi
Paper ID: V8I3-1178
Paper Status: published
Published: May 16, 2022
Traffic Sign Classification using Federated Deep Learning model
For several years, much research has focused on the importance of traffic sign recognition systems, which have played a very important role in road safety. Researchers have exploited the techniques of machine learning, deep learning, and image processing to carry out their research successfully. The new and recent research on road sign classification and recognition systems is the result of the use of federated deep learning-based architectures such as the convolutional neural network (CNN) architectures. In this research work, the goal was to achieve a CNN model that is lightweight and easily implemented for an embedded application and with excellent classification accuracy. We choose to work with an improved network ResNet34 model for the classification of road signs. We trained our model network on the German Traffic Sign Recognition Benchmark (GTSRB) database and also on the Belgian Traffic Sign Data Set (BTSD), and it gave good results compared to other models tested by us and others tested by different researchers. The results we found are efficient, which emphasizes the effectiveness of our method
Published by: Shaik Mahammad Rafi, Maddina Nikhil, T. Sathish Kumar Reddy, K. Kanchana, M. Ravali
Author: Shaik Mahammad Rafi
Paper ID: V8I3-1211
Paper Status: published
Published: May 16, 2022
Prognosticate Diabetic Mellitus in Women by using Performance Evaluation and Classification Algorithms
Diabetes is a persistent disorder that takes place while the pancreas does now no longer produces sufficient insulin or while the frame can’t use the insulin it produces Diabetes is known as one of the deadliest and most chronic diseases that cause blood sugar levels to rise. Many headaches arise if diabetes stays untreated and unidentified. Early prediction of diabetes can save a life. In our undertaking, prediction of diabetes for women between the ages of 30 and 80 through the use of classification algorithms. We used various Machine Learning classification algorithms like Logistic Regression, Decision Tree, and Random Forest on various attributes like Glucose, Blood Pressure, Skin thickness, Insulin, BMI, Diabetes pedigree function, Age, Pregnancies, and discover goal variable i.e., outcome. Finally, different classification algorithms along with their comparison of performances with the use of Confusion Matrix, Accuracy, F-Measure, and Recall.
Published by: Patnayakuni Pragathi, Komali Yasudha, Maddila Suresh Kumar
Author: Patnayakuni Pragathi
Paper ID: V8I3-1251
Paper Status: published
Published: May 16, 2022
Retailer’s perception towards Edible oil in and around Coimbatore
This research was made to analyze the factors that are needed to be strengthened for the product’s sales growth, it helped to determine the retailer perception towards edible oil brands, and also it helps to specify the reason for the specify Edible product which is not sold in the shop. These are the objective of this research. The research area was conducted in Coimbatore particularly in developing areas in Coimbatore like Eachanari, Malumichampatti, Othakalmandapam, and Kinathukadavu. The sample collected for this research is 181. The research design of the project is descriptive in nature. By using a structured questionnaire, the primary data was collected. Secondary data is collected from various journals, books, literatures, websites, and magazines. Convenient sampling is the sampling method used for the study. Chi-square test, Regression analysis,r correlation, and Cronbach Alpha test are the tools used for analyzing the data which are collected in the survey. From this study, it determines that the Majority of the retailers prefer that lowering the price can influence the new customer. In various retail outlets, customers are not specifying the brand while they are buying the product is the main reason for the reduction in sales. Because the majority of the retailers are not having awareness of Sim Sim oil which contributes to the reduction in sales due to not having awareness.
Published by: Mugunthan P., Ivan Kenny Raj L.
Author: Mugunthan P.
Paper ID: V8I3-1263
Paper Status: published
Published: May 16, 2022
The Concept of Ethics in Buddha Philosophy as Heterodox
The universal Noble Eightfold Path is an ethical principle in Buddha's philosophy. Nirvana is a state of mind or being in which one simultaneously realizes one’s true identity, which is infinite and eternal, the illusory nature of the world, perfect bliss, and equanimity. There is no separate existence of “God” who is the arbiter of ethical action and soul (flow of the mental states) and also a stream of changeable consciousness in mainstream Buddhism. Rather, it is a common psycho-spiritual law that certain behaviors promote nirvana and abate suffering while others impede nirvana and bring about suffering. It is in these terms that an act or sequence of acts is usually deemed moral or immoral i.e. ethical or unethical. From an enlightened mind ethical behavior, both leads to and runs. As ethics Lord Buddha advised his disciples to abstain from (a) harming living beings, (b) taking things not freely given, (c) sexual misconduct, (d) false speech, and (e) intoxicating drinks and drugs causing heedlessness (knierim). These five virtues are the most vital and significant while there are up to ten precepts for lay practitioners and sometimes hundreds for ordained monks. These Noble Eightfold paths generally fall into three types. The first two tend toward nurturing knowledge (jnana), the middle three toward ethical conduct, and the latter three toward psychological (manosik) development. Among the Noble Eightfold Path of Right, Speech is abstinence from lying, deception, slander, and idle chatter. In a positive way, Buddha promotes speaking only when necessary, and with honesty, mindfulness, and loving-kindness. Right action generally entails the first three points of the five precepts listed above. The emphasis is to behave so as not to harm any sentient being physically, emotionally, or spiritually. Right livelihood follows from right action in that one ought to make their living in a peaceful way. Buddha listed four occupations that ought to be avoided for their promotion or consonance of harmful behavior (a) arms trading (2) dealing in living beings (3) meat products such as butchery, and (4) dealing in intoxicants and poisons.
Published by: Dr. Monoranjan Das
Author: Dr. Monoranjan Das
Paper ID: V8I3-1269
Paper Status: published
Published: May 16, 2022
Cloud storage scheme based on computational intelligence in fog computing
Traditional privacy protection schemes are usually based on cipher technology, but these kinds of methods cannot effectively resist attacks from the inside of a cloud server. In order to achieve the goal problem, the motive of a three-layer storage framework supported fog computing. The future framework can both take full advantage of cloud storage and protect the privacy of knowledge. The hash-Solomon code algorithm is meant to cleave data into different parts. Then, this can add a small part of data in the local machine and fog server in order to protect privacy. With the explosive growth of disorderly data, cloud storage technology gets more attention and better development. However, in Education, Financial, and Healthcare storage schema, users’ data is totally stored in cloud servers.
Published by: G. Thanuja Reddy, Dr. Vanitha Kakollu
Author: G. Thanuja Reddy
Paper ID: V8I3-1260
Paper Status: published
Published: May 16, 2022
