Manuscripts

Recent Papers

Research Paper

Nine-layer CNN for detection of the cancerous growth of abnormal cells in the brain

A brain tumor is a group development of abnormalities brain cells. There are numerous forms of brain tumors. Some brain tumors are cancerous, whereas others are noncancerous. Brain tumor identification involves several phases, including the capture of an input MRI image, the conversion of the input image to a grayscale image, the application of filters, segmentation, feature extraction, and classification. The detection of a tumor is a difficult process. The position, size, and shape of the tumor differ greatly from patient to patient, making segmentation a difficult process. The detection of a tumour is a difficult process. The position, shape, and structure of the tumour vary significantly from patient to patient, making segmentation a difficult process. A Nine Layer CNN architecture including an input layer, zero padding, Conv2D, Batch Normalization, Re-Lu, Max pooling, Max pooling, Flatten, and Dense layer is designed in this study. TCIA Brain tumor dataset is used to train the Nine Layer CNN. TCIA dataset is augmented to overcome overfitting circumstances. In order to overcome overfitting conditions, the TCIA dataset is augmented. CNN nine layer produced a decent outcome, with a training accuracy of 98.93%. If the classifier determines that the picture is a tumor present image, it will also provide the proportion of the tumor.

Published by: J. Guna Keerthana, N. Britto Martin Paul, S. Sravan Kumar, B. Kavya Pranathi, V. Divya, Prudhvi Kanth Bezawada

Author: J. Guna Keerthana

Paper ID: V8I4-1196

Paper Status: published

Published: September 14, 2022

Full Details
Research Paper

Credit Card Fraud Detection and Classification by Optimize Features and Deep Learning

Traditionally, rule-based systems have been the primary instrument for detecting fraud in today's financial systems, with fraud specialists defining the rules based on prior instances and outcomes. If a new transaction meets one or more of the previously established criteria, an alert is triggered, indicating that the new transaction may be fraudulent. For previously known fraud tendencies, the rule-based method is effective. Before adding a new rule to the current rule set, a sufficient number of fraudulent transactions must have happened that fit the rule. During this time span, fraud techniques may evolve, resulting in the induced rule expiring. Thus, the emphasis should be on using prior transactions that follow a rule-based approach in conjunction with an unsupervised method that detects previously unknown fraud activity. There is a need to use fraud detection systems that are capable of keeping up with the cardholder's updated spending behaviour. The detection process's goal is to identify as much fraud as possible while reducing the false positive rate, which has a negative effect on cardholder satisfaction as the cost of providing more false alarms increases. To accomplish this approach, the threshold value is determined at the account level of the cardholder by evaluating the probability sequence of previous and new incoming transactions. Additionally, identified fraudulent transactions are labelled in the database for future analysis in the event that additional assessment is required.

Published by: Razia Seema, Kumari Archana

Author: Razia Seema

Paper ID: V8I5-1146

Paper Status: published

Published: September 14, 2022

Full Details
Review Paper

Intrusion Detection Classification and Detection by Machine Learning and Deep Learning Approaches: Review

DoS attacks that disrupt important, intelligent services like healthcare can also result in human death due to the disruption of routine services. devices (for example, intelligent refrigerators, smart televisions, and air conditioners) are easily attacked by attackers who exploit their weaknesses to launch denial-of-service attacks. As a result, one of the primary concerns for researchers all over the world is the protection of these devices. Globally, intrusion detection is being studied to fix this matter. IDS are classified into three categories based on their detection capabilities: Depending on a signature, a specification, or an anomaly. Whenever a device or network connections analyses an attack against a signature contained in the inner IDS database, an attack is identified by IDSs. If a device or network operation matches one of the saved signatures/patterns, a warning will be generated. This method is extremely reliable and effective at recognizing identified risks, and its process is simple to comprehend. However, this technique is ineffective in classifying new attacks and discrepancies between current These sorts of assaults do not have a meaningful signature to identify them If the divergence from a specified behaviour profile exceeds a predefined threshold, an anomaly-based intrusion detection system (IDS) issues an alert. Classifying intrusions does not seem to follow a typical pattern, and understanding the whole spectrum of normal activity is not an easy task. Emerging threats may be identified using this method. As a consequence, there is a significant rate of false positives with this method. Routing tables, protocols, and nodes, for example, are all part of the specification-based approach since they are all defined by a set of rules and criteria. It is possible to identify intrusions when network behaviour deviates from standards' specifications, using specification-based techniques. Therefore, specification-based detection is used for the same goal as anomaly detection: to separate aberrant behaviour from normal behaviour.

Published by: Ayush Gautam, Shivani Rana

Author: Ayush Gautam

Paper ID: V8I5-1147

Paper Status: published

Published: September 14, 2022

Full Details
Research Paper

High school particle detector using Peltier cooling modules

This project aims to design a cloud chamber for use in a high school in order to educate and get students interested in particle physics. The cloud chamber shows the tracks of particles in real-time, which is excellent for engaging students. They will be able to identify different types of particles based on the appearance of their tracks, and will therefore gain a more intuitive understanding of particle physics. The inclusion of two compartments separated by a lead divider allows students to infer the direction of particle motion by observing its loss of energy. This cloud chamber also includes an interactive element, which comes from the introduction of a school-safe sample of radioactive metal and the manipulation of magnetic fields using an electromagnet. The cart is on wheels and is easily portable. It requires almost no time from the instructor outside of class, except for replacing the supply of isopropyl alcohol, which is inexpensive and easy to access.

Published by: Sadie Allspaw

Author: Sadie Allspaw

Paper ID: V8I4-1268

Paper Status: published

Published: September 12, 2022

Full Details
Research Paper

Sex education program for intellectually disabled

Individuals with special needs experience the same sexual feelings like the neurotypical population. This process consists of an interaction between the physical, cognitive, mental, social, relational, ethical, religious and cultural factors as illustrated by Murphy and Elias (2006). Sex education can support children and young people with disabilities in their sexual development and contribute to their health and wellbeing but most of them are deprived of this privilege and do not get the required education that would foster a positive image of sexuality and would empower them. The present paper aims at presenting a full-fledged curriculum design that can enable the intellectually disabled to learn about sex education in a step by step and gradual manner with reinforcement at different stages to gauge the level of understanding of the same.

Published by: Alisha Lalljee, Dr. Chandita Baruah

Author: Alisha Lalljee

Paper ID: V8I5-1136

Paper Status: published

Published: September 6, 2022

Full Details
Research Paper

Fatigue seen in caregivers of the intellectually disabled population

Individuals with disabilities are often dependent on their primary caregivers for assistance and activities of daily living. A caregiver here may either be a family member or a person trained in special health care. Most caregivers are found to be stressed and fatigued due to the nature of their work. In case the caregiver is a member of the family it is important to equally distribute the responsibilities of the disabled person amongst family members to avoid extra burden on any one person.

Published by: Alisha Lalljee, Dr. Chandita Baruah

Author: Alisha Lalljee

Paper ID: V8I5-1137

Paper Status: published

Published: September 6, 2022

Full Details