2022-23

Permanent URI for this collection

http://192.168.75.5:4000/handle/123456789/15946

Browse

Now showing 1 - 20 of 76

Analysis of Women Safety In India Using Machine Learning on Different Social Media Platform
(NHCE, 2022) Konapalli Sai Chaitanya Reddy; Guggulla Geetha Priyanka
In the current scenario, women community facing issues like gender discrimination, schooling, child marriage, sexual assault and harassment, and much more, not just from society but also from social media. Women are protected by organizations like the She Team, Disha Act, and many others in society, but these organizations are much less in social media. Social networking sites like Twitter, Instagram, Facebook, etc. cause problems for women. This paper focuses on the safety analysis and monitoring of women using various social media platforms in Indian cities. The posts on Facebook and Instagram, as well as tweets on Twitter, that abuse women are considered and show the percentage of threats that women face from social media, which aids in understanding by the youth of India who misuse the women's safety and harass them in social medias via tweets, posts, and text should face strict action. People may grasp the threats to women with the help of this, and it demonstrates that women face challenges not only from society but also from social media platforms. The outcome is easily comprehended in the form of a graph and a pie chart. Algorithms such as Nave Bayes (NB) and XGBoost are used in the analysis of women's safety on various social media sites. The goal is to use classification techniques to categorize or forecast the Type based on dataset properties. Using categorization algorithms, we can determine whether social media content is positive, negative, or neutral. It has been substantiated that Naive Bayes algorithm has proved better accuracy compared to random forest and decision tree algorithms.
BMyVision: A Virtual Eye For the Visually Impaired
(NHCE, 2022) ADITI VYAS : ARPITA GADO : CHIDANANDITA MOHANTY :
BMyVision is an advanced assistive technology designed to assist people who are visually impaired. It is a wearable device that functions as a virtual eye and provides users with an enhanced visual experience through the use of haptic feedback. This innovative technology works by capturing real-time images of the user's surroundings using a camera, which then processes the images to provide the user with a tactile representation of their environment. The device consists of a pair of glasses that houses a miniature camera and a microcontroller. The camera captures the images, and the microcontroller processes the information and converts it into tactile feedback, which is then transmitted to the user through vibration or pressure. The user can then use this feedback to navigate their environment, avoiding obstacles, and identifying objects in their surroundings. BMyVision has several advantages over traditional assistive technologies for the visually impaired. The most significant advantage is that it provides users with real-time information about their surroundings, which allows them to move around independently and confidently. Moreover, unlike traditional assistive technologies, BMyVision is not limited by the user's ability to process or interpret visual information. Instead, it provides users with an intuitive and easy-to-use system that can help them navigate their surroundings more effectively. The device is still in the early stages of development, and there are ongoing efforts to improve its functionality and usability. However, the potential benefits of this technology are enormous. It has the potential to significantly improve the quality of life for visually impaired individuals by providing them with greater independence, access to the world around them, and a more fulfilling and active lifestyle.
Open Dots: Securely Connecting Like-minded People Using Machine Learning
(NHCE, 2022) ACHUTH G A; AJAY P V : RANGANATH K
Often, in today's world, it is difficult to make new acquaintances if we discuss in our social group, and even for individuals, finding someone who has common interests can be challenging. Additionally, by utilizing web3, WebRTC, and machine learning, this project facilitates safe connections between individuals with shared interests located all over the world. Every person in this world has unique interests, preferences, and dislikes. Everyone wants to get in touch with someone who shares their interests so that they can communicate more effectively. We support the connection of all types of people in this project because some people need mentoring, others want to practice interviews, others enjoy listening to stories, and still, others want to perform stand-up comedy. People who enjoy learning about new cultures from various nations and languages can also connect. The entire user's interest data, including age, favourite subject, learned programming languages, consulting interest, interview interest, current employment history, favourite Netflix shows, favourite movies, favourite hero, and favourite song playlist, will be collected for this project. We use all the data from the various individuals to match people using a machine learning algorithm, and then, based on the outcomes, we connect the people using WebRTC so that they can communicate face-to-face while sharing real-time audio and video. More user interest information will increase the precision of finding the ideal match. Our algorithm matches you with various people who can observe, suggest to you, and help you eliminate loneliness by talking to other people while people share their screens and work on tasks like studying and coding. Keywords: interest, suggest, culture, practice, face to face...
Detection of Cyber Attacks Using Artificial Intelligence
(NHCE, 2022) E .VINAY BABU : P.Md.SIDDIQ : T.HAFEEZ
The integration of physical processes, computational resources, and communication capabilities has allowed cyber-physical systems (cps) to advance significantly in many dynamic applications. However, these systems are seriously threatened by cyberattacks. Cyber-attacks take place deliberately and covertly, unlike errors that result from accidents in cyber-physical systems. Some of these assaults, known as deception attacks, damage data or introduce false information into the system by interfering with certain cyber components or injecting fake data from sensors or controllers. If the system isn't aware that these attacks are happening, it won't be able to recognise them, which could lead to performance issues or even complete system failure. As a result, algorithms must be modified to recognise certain assaults in these systems. It should be highlighted that because the data produced by these systems is created in such enormous quantities, with such a wide diversity, and at such a rapid rate, it is crucial to apply machine learning algorithms to make it easier to analyse, evaluate, and spot hidden patterns in the data. The CPS is modelled in this study as a network of agents that move together, with one agent serving as a leader and the others being subordinated to him or her.
Personality Detection For Recruitment Using Machine Learning
(NHCE, 2022) S R MEGHANA SARVEPALLY: SONITHA MANDAVA: MEGANA M
For the growth and development of organizations, it is crucial to recruit candidates who not only possess the necessary skills for the role but also align with the company's values. However, with a large number of applicants for each job role, reviewing each resume can be a time-consuming process. While pre-tests like aptitude assessments provide some insights, they may not fully capture a candidate's suitability for the role and organizational fit. This is where personality assessment becomes valuable. Personality assessment helps in the initial screening of candidates by providing insights into how individuals behave in different situations. In this research paper, we propose the application of various machine learning and deep learning algorithms on three datasets to develop a system that can be utilized by recruiters alongside their existing pre-tests. The focus is on two popular personality indicators: the Myers-Briggs Type Indicator (MBTI) and O.C.E.A.N (the big five personality traits). By incorporating personality assessment into the recruitment process, recruiters can gain a more comprehensive understanding of candidates beyond their technical skills. This holistic evaluation enables better matching of candidates to job roles and organizational culture, ultimately contributing to the growth and success of the organization.
Detecting the Accuracy of Cancer Stem Cell In Brain Tumor
(NHCE, 2022) ADITYA RAJ: AKASH KUMAR BARIK: KEERTHANA BALAKRISHNAN:
The goal of this research is to create an auto-mated medical image analysis and detection system for reliable brain tumor categorization using MRI datasets. The study used our unique Inception-resnet-v2 architecture to identify normal brain pictures from brain tumor images in comparison to the VGG16 CNN architecture. The spectrum of Al is debatable: as robots become more capable, occupations seen as requiring "power" are usually removed from this description, a process known as the Al effect, giving rise to the adage, "Al is whatever hasn't been done yet." For example, visual character recognition is frequently removed from artificial intelligence, even though it has become a common application. Modern machine skills widely classed as Al include successfully comprehending human language, competing at the highest level in key play organizations, driving autonomously, and intelligent routing in content delivery networks and war simulations.
Design and Implementation of a method for diagnosing various stages of Alzheimer’s Diseases using Deep Learning
(NHCE, 2022) KAVYA.S: LIKITHA.R: GUNA KEERTHI.P
Deep learning, a cutting-edge approach to machine learning, has demonstrated superior performance over classical machine learning at recognizing detailed structures in complex, high-dimensional data, particularly in the field of computer vision. Due to the rapid advancement of neuroimaging techniques and the resulting large-scale multimodal neuroimaging data, the use of deep learning to automate the early identification and categorization of Alzheimer's disease (AD) has recently attracted a lot of attention. An organized review of articles using neuroimaging data and deep learning techniques for diagnosing AD was carried out. When fluid biomarkers and multimodal neuroimaging were coupled, the classification performance was at its greatest. Using multimodal neuroimaging data, deep learning algorithms appear to have promise for the diagnostic classification of AD since their performance keeps improving. Deep learning-based research on AD is still in its early stages, and it continues to advance in terms of performance by embracing new hybrid data types, such as omics data, and transparency by using explainable methods that incorporate knowledge of particular disease-related traits and mechanisms. The most frequent factor contributing to a deterioration in cognitive function is Alzheimer disease (AD). Language, memory, understanding, attention, judgement, and reasoning are all affected by this neurological condition, which often affects persons over the age of 65. Keywords—Alzheimer’s Disease, MRI, ADNI, Deep Learning, Diagnosis.
Synergy – Extending Consolation to people with ASD
(NHCE, 2022) RAKSHITHA B A ; SHRIYA B KRISHNAN
"Synergy - Extending Consolation to People with ASD" is a groundbreaking application developed specifically for people with autism spectrum disorder (ASD). This application is designed to detect emotions from the text entered by users and offer a mood board to learn different facial expressions. People with ASD often struggle to understand emotions, which leads to social isolation and difficulty in interpersonal communication. Therefore, Synergy aims to fill this gap by providing a platform that helps people with ASD identify emotions and facial expressions with ease. The application is highly user-friendly and interactive, allowing people with ASD to communicate their feelings effectively. The mood board, which is a unique feature of Synergy, offers a visual aid that helps users learn different facial expressions. This board displays a range of emotions, from happy to sad, and encourages users to mimic these expressions. This process not only improves their understanding of emotions but also enhances their ability to express themselves to others effectively. In conclusion, Synergy is an innovative application that provides a practical solution to the emotional communication problems faced by people with ASD. By offering a user-friendly interface and unique mood board, it helps users identify and express their emotions with ease. With its interactive features and visually appealing design, Synergy aims to extend consolation to people with ASD and improve their quality of life.
Diagnosis of Diabetes Mellitus in Bengaluru North using Gradient Boosting Algorithm
(NHCE, 2022) HARSHITHA K: HEMANTH M:LIKITH AB
Diabetes mellitus is one of the most distinguished illness all over the world. As the populace has developed to be generally solitary, the impact of diabetes is quickly spreading. It is the metabolic illness where the affected person has excessive blood sugar both because of the fiasco of the body to supply requisite insulin or the fiasco of the body cells to react to the already generated insulin. It may be recognized with the aid of analyzing numerous readings taken from the affected person which includes albumin, creatinine, fasting, glucose, potassium, sodium and plenty more. Due to the complicated interdependence of numerous elements and the fact that diabetes affects human organs including the kidney, eye, heart, nerves, foot, and others, early diabetes prediction is a difficult task for medical professionals. In the realm of data science, machine learning is a young scientific field that investigates how machines learn via experience. The purpose of this study is to create a system that can accurately and early diagnose diabetes in a patient.
Efficient Authentication key generator for data sharing on cloud by KAC Method
(NHCE, 2022) ESIKALA NITHISH MANI KRISHNA: GANGIREDDY RAMYA SRI: GUNDRE SAI SRUTHI
With the help of a sizable quantity of virtual storage, cloud computing provides services through the Internet on demand. The primary benefit of cloud computing is that it relieves users of the need to invest in pricey computer equipment. Lower expenses are related with infrastructure. Researchers are looking at new, relevant technologies as a result of recent breakthrough in cloud computing and other sectors. Due to its accessibility and scalability for computer operations, both private users and companies upload their software, data, and services into the cloud storage. While switching from local to remote computing provides advantages, there are also a few security issues and difficulties for both the supplier and the customer. There are many cloud services offered by reputable third parties, which is raising security concerns. The cloud service provider offers its services over the Internet and makes use of numerous online technologies, which raises fresh security concerns. Online data interchange for increased productivity and efficiency is one of today's most significant requirements. Owners of this data can keep and distribute the info online. This study aims to provide a secure key for online data sharing for users that includes cloud computing technologies and crypto algorithm principles. Data owners would ideally like to keep their data/files online in an encrypted way, delegate decryption rights for some of these to users, and maintain the ability to withdraw access at any moment.
Korus – Transpiling Speech into Code Using NLP
(NHCE, 2022) ANASUYA DUTTA: NIRUDH PANDITA : ANUSHA SALIMATH
The aim of the project is to develop a solution to enable voice python coding using natural language models. The hugging face dataset contains necessary data sets for image classification, voice classification etc. These datasets are optimized and can be used with the transformer model available in PyTorch, and Tensor Flow. Along with directly using the datasets, we can create our own datasets using the hugging face dataset library which does all the necessary work to perform data cleaning and preparation and splits the dataset into training data and testing data. These models are open source and free of cost allowing them to be cost-effective. Further improvements can be added on top of the pre- trained models for further performance improvements. Along with this, there will also be a code snippet fetching mechanism which can automatically lookup the code and pass it to the main area of automation i.e., end user screen. Currently, we will be focusing on catching syntax which can later turn to be more generic as we keep on improving the model for understanding generic statements. The goal is to assist the developer in times to reduce the overall stress of typing code.
Deepfake Detection Using Deep Learning
(NHCE, 2022) BHARAT PURI; SOMNATH MUKHERJEE : JAGADEESH KUMAR
In a narrow definition, deepfakes (stemming from "deep learning" and "fake") are created by techniques that can superimpose face images of a target person onto a video of a source person to make a video of the target person doing or saying things the source person does. This constitutes a category of deepfakes, namely face swap. In a broader definition, deepfakes are artificial intelligence-synthesized content that can also fall into two other categories, i.e., lip-sync and puppet-master. Lip-sync deepfakes refer to videos that are modified to make the mouth movements consistent with an audio recording. Puppet master deepfakes include videos of a target person (puppet) who is animated following the facial expressions, eye, and head movements of another person (master) sitting in front of a camera. We have created a project that tries to push the boundaries. and make the life of the user easier by telling the user if the image or the video uploaded is fake or real.
Crowd Counting for Risk Management using Deep Learning
(NHCE, 2022) SANJAY RAGHAVENDR: SRI TANMAYI CH: RISHTI HIREMATH
Malware Analysis and Sandboxing
(NHCE, 2022) CHINMAY ANAND; RAKSHA S: SHREYA KORADA
Security researchers and analysts may study and comprehend the behaviour of malware in a controlled environment using the open-source malware analysis tool SafeX. Including dynamic and static analysis, network traffic analysis, and memory forensics, the platform offers a complete set of tools and functionality to automate the study of malware samples. We present an overview, the analytical architecture, and the tools in this study. We go over the benefits of employing this for malware analysis, such as its adaptability and simplicity of use, as well as the capacity to modify the analysis procedure to suit particular needs in research or organisational needs. We also go over the difficulties and restrictions, like the requirement for constant upkeep and upgrades and the potential for evasion by sophisticated malware strains. We offer advice on the best methods for putting SafeX into use within an organisation, taking into account security and privacy concerns. By offering thorough insights into the behaviour and traits of malicious software, the SafeX platform is intended to assist researchers and organisations in improving their capacity to identify and address malware threats. Many different organisations utilise it, including security operations centres, incident response teams, and security researchers. Organisations wishing to enhance their malware analysis and detection capabilities can gain a lot from implementing our software. SafeX can assist organisations in promptly identifying and addressing emerging risks by automating the analysis process and offering thorough insights into the behaviour of malware samples. By offering thorough forensics data, SafeX may be utilised to improve incident response capabilities and be incorporated into existing security workflows. One of the main benefits is the ability to tailor the analysis process to match certain organisational needs. Keywords— Analysis, malware, Antivirus, cyber security, dynamic analysis, malware analysis, malware detection, malicious.
Detection of Cyber bullying In Social Media Using Machine Learning
(NHCE, 2022) G SHIVA TEJA REDDY; G KOUSHIK : M THEJESH REDDY
The study of online social networks involves the identification of various issues such as the detection of anonymous user behavior and offensive content, among others. One such issue is the detection of bully statements and offensive data in shared content on social networks. To address this problem, this project focuses on using Machine Learning algorithms with Text Mining concepts to predict offensive data and improve the accuracy of the results. The proposed system of “Cyber Bullying Detection (CBD) in Social Networking” uses two datasets - the ‘Hate Speech and Offensive Language Dataset’ and the ‘Harassment-Corpus Dataset’ - to train the Machine Learning classifiers. Three classifiers were used, namely, Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and Neural Network (NN) Algorithms. The performance of these classifiers was calculated and compared using the two datasets. The results of this project can help improve the safety and security of social networks by detecting and preventing cyberbullying. The Python-based Django web application developed for this project is a useful tool for users to identify and report offensive content on social networks. This project provides a valuable contribution to the field of online social networks and the detection of cyberbullying. The use of Machine Learning algorithms and Text Mining concepts to predict offensive data can help address the issue of bullying on social networks, and the Python-based Django web application can be a useful tool for users to report offensive content.
Agranomy Apparatus Using Convolution Neural Network
(NHCE, 2022) C .MOHITH REDDY: RANGANI ROSHINI: L.N.SAI NEHA
Shinakth – Envisioning Reliable Diagnosis of Diabetic Retinopathy Using U-Net
(NHCE, 2022) MALIK NAJEEB UL HABIB : PEERZADA ANZAR AZMAT : AVNI GARG
If not identified and treated promptly, diabetic retinopathy (DR), a frequent complication of diabetes, can cause vision loss. In this project, we created a web-based application that aids medical workers in the early detection and severity assessment of DR. It makes use of deep learning and fuzzy logic. The application is made up of two major parts: a severity assessment system that uses fuzzy logic and a deep learning-based DR segmentation model called DRS-UNet. The DRS-UNet model is trained using the freely accessible DRIVE dataset and is built on the well-known U-Net architecture. With great accuracy, it can separate the retinal fundus images into normal and abnormal regions. A severity number is generated by the fuzzy logic-based severity evaluation system using inputs like age, gender, and the percentage of the image that the DRS-UNet model has classified as abnormal. The user can submit a fundus image and additional patient data, and the application will produce a severity score and show the segmentation results. The method can help doctors make quick judgements about the severity of DR, which can be crucial in avoiding vision loss.
“Implementing an Interactive VBE and IPSL Aid for the Disabled
(NHCE, 2022) MUKUNDH J ; JOEL JACOB STEPHEN; KESHAV KRISHNA KUMAR
The Communication becomes the radical characteristic that makes us human in a world of billions. Without dialogue, individuals are just soulless objects. Unfortunately, not all of us are fortunate enough to have open communication. A major problem is interacting with those who are impaired. In order to help the less fortunate, this study provides a solution that involves creating a sign language identification using a combination of machine learning and web building techniques. An example of a language that is underrepresented is IPSL (Indo-Pakistani Sign Language). More than 15 million members of the deaf community actively utilize IPSL, but most others throughout the world are unaware of it.IPSL will be made detectable with the proposed model that is combined with a VBE (VoiceBased Email) system to aid not only the deaf but also the blind, using a GRU model for thesame. GRU is already a well-defined model, but this paper intends to show how this deep learning model can be used for IPSL, having never been done before, as it is usually donefor the popular languages like ASL and BSL. Keywords— Sign Language, IPSL, VBE
An Experimental Analysis on Mitigating the Effects of Malicious Nodes in a Federated Learning System
(NHCE, 2022) SATHISH KOTTURI : SHIBI STEPHEN K : SHUSHANK BALAJI REDDY
This paper describes how deep learning can be used to provide security for IoT devices by analyzing the data packets that arrive at an IoT device and classifying them as packets part of the normal operation of the device or packets sent with a malicious intent. An experimental analysis is performed to check the effectiveness of such an approach with the help of the data present in the MQTT dataset. Federated learning approach is suitable for the IoT platform as IoT devices tend to contain less computing power. But a consequence of this is that the networks can contain malicious nodes which send wrong updates to the model decreasing its accuracy. We propose the introduction of verifier nodes into the system which verify the given updates sent by a node and check if it actually increases the accuracy of the model before appending it to the global model. The extent to which the malicious nodes impact the accuracy of the model and the remedy provided by the introduction of verifier nodes is also studied in this paper.
Real Time Rice Leaf Disease Detection And Remedy Using CNN
(NHCE, 2022) G SHANMUKHA SRINIVASA REDDY : L V. SUBBA REDDY : G RAMESH
India is a land of agriculture and produces different types of crops in large quantities. And among those crops, Rice is majorly produced in India. With that topic aside Indian farmers are also uneducated. Which makes the farmers liable and exploitable. They need to have an idea of the diseases which have affected their crops and what to do with the occurring problem. Without the proper guidance, the farmers who entirely depend on the crop will definitely get affected and some leads to death. after much research, the researchers came to the conclusion of using the modern technology called the deep learning model. Which helps in finding the disease more efficiently. Among the model the convolutional neural network(CNN) model shows more accuracy. Here we have created our own dataset and have also used transfer learning where we have made a comparison of the results between two models and more over we are giving remedy for each diseased plant. In this way farmers will have an idea what to be done regarding the disease .

Browse

Browsing 2022-23 by Issue Date

Results Per Page

Sort Options