IJRCIT- International Journal of Research in Computer & Information Technology

e-ISSN: 2455-3743 | Published by Global Advanced Research Publication House (GARPH)

Home Instructions For Authors Call For Papers Editorial Board Archives Special Issues Conferences Ethics & Policies Downloads FAQ Contact

Archives of International Journal of Research in Computer & Information Technology(IJRCIT)

Volume 7 Issue 3 June 2022

1. An Effective Combination of Multi-Task Cascaded Convolutional Neural Networks ( MTCNN) and FaceNet in the Identification of Person from a Captured Group Photo

AUTHOR NAME : Sachin Manohar Inwate, Dr. G. R. Bamnote, Prof. Y. S. Alone

ABSTRACT : Identifying a person from a captured group photo has become the most researched topic these days. This is because of recent advancements in Face Detection and Recognition techniques and widespread applications of Facial Recognition. Facial Recognition is a biometric software application capable of uniquely identifying or verifying a person by comparing and analyzing patterns, based on the person’s facial features. There are several reasons for recent increased interest in face recognition, including rising public concern for security, the need for identity verification in the digital world, face analysis and modeling techniques in multimedia data management, and computer entertainment. Face recognition has recently gained significant attention, due to the availability of feasible technologies, and advances in face modeling and analysis techniques. Although systems have been developed for face detection and tracking, reliable face recognition still offers a great challenge to computer vision and pattern recognition researchers. The face recognition process includes major components such as face detection, tracking, alignment, feature extraction, classification, etc. Face detection plays an important role in the facial recognition process. This is because it is very challenging to identify a human face from the number of objects of similar shapes in the picture. Once a human face is identified, it is equally challenging to recognize a person uniquely owing to the dynamic changes in the human face due to emotion, expression, makeup, hairstyle, etc. In this paper, we have highlighted the effectiveness of a combination of Multi-task Cascaded Convolutional Networks (MTCNN) and FaceNet in the identification of a Person from a captured group photo. MTCNN plays important role in face detection while FaceNet is very effective in recognizing the people from their unique facial features. This paper will analyze the result obtained through MTCNN while detecting faces in the photograph and highlight the significance of the MTCNN model in the case of low resolution and high illumination pictures. This paper will also highlight the effectiveness of FaceNet in recognizing persons even from the low-sized dataset of trained images.

2. Social Media Sentiment Analysis for Covid-19 Tweets Based on Machine Learning

AUTHOR NAME : Swati Ganeshrao Dhoke, Dr. S. R. Gupta, Prof. R. A. Kale

3. Comparative Analysis for Association Rule Mining Based on Particle Swarm Optimization

AUTHOR NAME : Vitthal M. Kharmate, Dr. R. R. Tuteja

ABSTRACT : Association rule mining play an important role in various data mining process. The diversity of association rule mining spread in various field such as market bucket analysis, medical diagnose and share market prediction. For the mining of rule mining a variety of algorithm are used such as Apriori algorithm and tree-based algorithm. Some algorithm is wonder performance but generate negative association rule and also suffered from multi-scan problem. An effective data mining method to automatically extract association rules between product from the available historical data is essential for an efficient and cost-effective product. This research proposes a new binary particle swarm optimization- (BPSO) based association rule mining method for discovering the hidden relationships between products. In particular, proposed BPSO does not need to predefine thresholds of minimum support and confidence. Moreover, a novel overlapping measure indication is further proposed to eliminate those lower quality rules to further improve the applicability of BPSO. The effectiveness of proposed BPSO is demonstrated on a market basket dataset. The performance comparison indicates that proposed BPSO outperforms other regular methods (e.g., Apriori) for ARM. The experimental results indicate that BPSO is capable of discovering important association rules between products.

4. Performance Analysis and energy optimization in Wireless Sensor Network using AOMDV Protocol

AUTHOR NAME : Ms. Namrata Daga, Prof. Dr. S. M. Deshmukh, Dr. N. P. Dhole

5. Three Level Password Authentication System

AUTHOR NAME : Prof. Veena Katankar, Pranjali Fating, Apoorva Mamarde, Mansi Lokhande, Kritika Agrawal

ABSTRACT : Authentication is one of the most important security services provided to the system by the different authentication schemes or algorithms which must be provided so that only authorized persons can have the right to use or handle that system and data related to that information system securely. Techniques used include text-based, image-based as well as graphical-based. Despite these, no single mechanism is efficient and effective to provide adequate security for computing resources such as programs, files, messages, printers, the internet, etc. A 3 – level authentication is proposed in this paper that is more confidential for ensuring adequate security. The 3-level password authentication system is an authentication scheme that combines the benefits of authentication schemes in existence to form the 3-levels of security. The proposed system in this paper would provide a more secure authentication technique than the existing one, overcome the drawbacks and limitations of previously existing systems (such as textual passwords, graphical passwords. etc.) and combine more than one authentication technique.

6. Online Crime Reporting System

AUTHOR NAME : Prof. Veena Katankar, Lutika Patil, Divya Shivankar, Pornima Uke, Prajakta Narwade, Abhishek Bhure

7. Implementation on Smart Offline Attendance

AUTHOR NAME : Prof. Veena Katankar, Ms. Prachi Kedar, Mr. Rushikesh Pande, Ms. Anjali Karande, Ms. Srushti Kowe

8. Online Feedback System

AUTHOR NAME : Prof. Komal Dahaney, Ms. Samriddhi Painter, Ms. Usha Bhure, Ms. Mayuri Zade, Ms. Shivani Chaturkar

ABSTRACT : Online feedback is the web-based feedback collecting form from the student and provides the automatic generation of feedback which is given by students, teachers, and parents. We have developed an online feedback form to provide feedback in a quick and easy manner to the particular department. By using this technology, we can give feedback in the online system as fast as compared to the existing paper feedback form. The existing system carries more time to do a piece of work for this reason the online system feedback is implemented. In this paper, security is also maintained that the result of feedback is only visible to the authentic user. This paper is designed in order to reduce the burden of maintaining the bulk of records and all the feedback details. Which can easily be understandable, and maintaining the details in the database is manageable.

9. Design And Implementation of Lab Automation System

AUTHOR NAME : Prof. Pradip Balbudhe, Sumit Das, Monish Kuril, Vishal Rathod, Prajwal Majgawli

ABSTRACT : The main objective of this paper is to develop a lab automation system using a NodeMcU board with Wi-Fi being remotely controlled by any Android OS smartphone. As technology is advancing so houses are also getting smarter. Modern houses are gradually shifting from conventional switches to a centralized control system, involving remote-controlled switches. Presently, conventional wall switches located in different parts of the house make it difficult for the user to go near them to operate. Even more, it becomes more difficult for the elderly or physically handicapped people to do so. A remote-controlled lab automation system provides a most modern solution with smartphones. In order to achieve this, a Wi-Fi module is interfaced to the NodeMcU board at the receiver end while on the transmitter end, a GUI application on the cell phone sends ON/OFF commands to the receiver where loads are connected. By touching the specified location on the GUI, the loads can be turned ON/OFF remotely through this technology. The loads are operated by the NodeMcU board through optoisolators and thyristors using trials.

10. JOBINGO- Online Job Portal

AUTHOR NAME : Prof. Shilpa Chindamwar, Pratiksha Bele, Sanskruti Matkar, Namo Alone, Pratiksha Hedau

11. Smart Light Automation and Alert System

AUTHOR NAME : Prof. Pradip Balbudhe, Ayush Dadarao Raut, Ganesh Dipak Kawadkar, Sambodh Sanghpal Lamsonge, Vedant Umakant Jogekar

ABSTRACT : This paper discusses Smart light automation and alert system. The world is moving fastly towards automation. People have less time to handle any work so automation is simple way to handle any device or machine will work to our desire. This paper aim is to develop and design a Light automation using Esp8266 with PIR sensor. Lights are controlled by Light automation system using Esp8266 with relay circuit. Ultrasonic sensor and Buzzer are common parameters to alert the person sitting inside the lab. In this IOT based project we are going to alert the person through the buzzer who’s sitting inside the lab The paper mainly focuses on the monitor and control of smart Light automation using Esp8266 with a PIR sensor, when the person does not present at lab. This paper motive is controlled lights in smart home with user-friendly, design at low cost, simple installation.

12. Design Universal Remote

AUTHOR NAME : Prof. Pradip Balbudhe, Shital Kuthe, Pragati Morande, Neha Motghare, Arti Verma

ABSTRACT : The Internet of Things (IoT) is the future of networking that allows connection between physical and virtual institutions, or residential). Today, the home automation area offers timer control and remote control for embedded systems and electronic devices such as light, heating, entertainment systems, ventilation, appliances, etc., to improve comfort, convenience, security, and energy efficiency. However, the element of autonomous behavior is lacking, this is where the smart homes come into the picture. The categorization is done by the controlling mechanism throughout the world in highly unified and increasingly useful ways. The use of IoT devices is to control and monitor the electrical, mechanical, and electromechanical appliances used in many applications (e.g., industrial, offices, remote controls. These devices crave the user to be within the premises in order to operate the types of equipment. Applications such as Bluetooth, Radio, and other devices are coming in the vicinity of the spectrum. In this project, the system uses android smartphones as an interface for remotely controlling electronic appliances for home automation. That connects the sensors and all electronic home appliances to automate control through a remote controller.

13. Medicine Search Engine Optimization

AUTHOR NAME : Prof. Pradip Balbudhe, Neha Barsagade, Rutuja Birole, Ayesha Tirpude, Vaishnavi Pote, Mayuri Kapgate

ABSTRACT : Medical Search Engine Optimization is a web application designed and developed for local people. As popularity of web increases, millions of people use search engines to discover information. But search engine users are interested only in top few result pages. Search Engine Optimization (SEO) relates to the activity of optimizing individual web-pages or the entire website to make them friendlier to acquire higher raking in the search results. Not only in this search will engine likewise help the client with identifying medicines that are prescribed for some specific diseases. This engine will likewise give a list of the medical shops available based on filtered area and furthermore the cost of medicines in the market. All the major search engines such as Google, Yahoo, Ask, Bing, etc. rank web-pages based on certain factors that affect its ranking; therefore, SEO aims at generating the right types of signals on the web-pages. The optimized websites obtain better ranks, and typically get a higher number of visitors. This research is based on reviewing different optimization techniques for individual web-pages or the entire website to make them search engine friendly. This paper offers a comparative study of the previous research work regarding the techniques used in SEO and pinpoints certain gaps in the known search engine optimization techniques. Finally, we put forward some pertinent guidelines for optimizing the website

14. Fire & Gun Detection

AUTHOR NAME : Prof. Pradip Balbudhe, Mr. Akshay Thakre, Mr. Om Khope, Mr. Piyush Patel, Mr. Pravin Thawkar

15. Smart Health Disease Prediction

AUTHOR NAME : Prof. Veena Katankar, Saurabh Hedau, Nishant Khapekar, Prem Atkapurwar

16. Air Quality Detection and Monitoring System

AUTHOR NAME : Prof. Pradip Balbudhe, Aishwarya Ilame, Grishma Shingle, Megha Radke, Fariha Sheikh, Vishakha Dungare

17. IoT Based Smart Fingerprint Door Lock

AUTHOR NAME : Prof. Shillpa Chindamwar, Anshika Rajak, Shivani Kadwe, Pranoti Karemore

ABSTRACT : In this paper, developed an IoT-based mostly good door lock system employing a fingerprint detector to open and shut the door. we tend to use an Arduino Uno microcontroller and fingerprint detector, and a Servo motor to unlock the door the motor is including the door lock. once the fingerprint match then solely the door open or shut. WHO has approved person solely will open the door If any unauthorized person making an attempt to open the door means that they can’t open the door as a result of the fingerprint detector near accepts the fingerprint there is no response from the microcontroller facet? The buzzer is ringing once the unauthorized person tries to open the door and also the server can generate a message and send to the owner that someone making an attempt to open the door.

18. Cursor Movement by Hand Gesture using Python + OpenCV

AUTHOR NAME : Prof. Pradip Bulbudhe, Aachal Kamble, Pallavi Sawwalakhe

ABSTRACT : The paper designed the Mouse control using Hand Gestures is to better the process of human-computer interaction. It aims to provide the user a better understanding of the system and to let them use alternate ways of interacting with the computer for a task. The task here is to control the mouse even from a distance just by using hand gestures. It uses a program in python and various libraries such as PyAutoGUI, Numpy and image processing module OpenCV to read a video feed which identifies the users’ fingers represented by three different colors and track their movements. It retrieves necessary data and implements it to the mouse interface of the computer according to predefined notions. The project can be useful for various professional and non-professional presentations. It can also be used at home by users for recreational purposes like while watching movies or playing games.

19. Smart Driver Efficiency Using IoT

AUTHOR NAME : Mr. Palash Dhawale, Mr. Sameer Dhanorkar, Mr. Ritesh Chikhlonde, Ms. Srushti Selwate, Prof. Shilpa Chindmwar

20. A Review on Smart Library

AUTHOR NAME : Prof. Shilpa Chindmwar, Ms. Dhanshree Gogate, Ms. Prachi Bansod, Ms. Shubhangi Karmore, Ms. Vaishnavi Lute

ABSTRACT : Smart Library is a collection of sources of information and similar resources, made accessible to a defined community for reference or borrowing. Thus, the process of handling a library manually is very troublesome and clumsy. As regards this point of view, the computerized system for handling the activities of library management provides a comprehensive way to lessen physical labour, to reduce the complexity of the manual system, and soon. This paper aims to design and implement a computerized library management system. The library management system was designed and implemented using the HTML (Hypertext mark-up language), CSS (Cascading style sheet), PHP (Hypertext pre-processor), and My SQL database. The system was developed using the V-Model software development approach. An extensive evaluation of the project determines that the project achieved many of its predefined objectives. Additionally, fingerprint authentication is added as a layer of authentication for admin login.

21. Teachers Parents Diary

AUTHOR NAME : Prof. Komal Dahaney, Yuganshu K Mehar, Yash Sherekar, Siddharth Singh, Ajay Sangewar

ABSTRACT : Families and educational institutions have been working together since the beginning of formal schooling in the interest of students entire development. It is reported and discussed by Hill and Taylor (2004) in their empirical work. Globally it has been concluded by Levanda (2011) that the collaboration of parents with school management and teaching staff in students academic programs fosters quality of education. The policymakers, educationists, professionals, teachers, and community also encourage the participation of parents in educational programs of institutions. A variety of measures have been institutionalized for the engagement of parents and the community in the system of education for the improvement of students entire development. The engagement of parents is significant not only for privileged and marginalized students but also for ensuring that they are eagerly learning and contributing to the educational mechanism. Empirical studies revealed that parents participation in collaborative mechanisms plays a vital and significant role in developing educational infrastructure and college organization. Without the involvement of the community and parents in a cooperative mechanism, satisfactory target objectives cannot be obtained.

22. Campus Entry Record Intelligence Using PHP

AUTHOR NAME : Ashwin Kalbande, Rajat Gaiki, Ritik Mohite, Tejas Patil, Yash Jakhotiya, Prof. Shraddha Raut

ABSTRACT : Campus Entry Record Intelligence is a process of managing the information of the visitors visiting and employee attendance for the campus. For any organization maintaining the information of the visitor and employees is a very major issue. This system will replace the manual maintenance system and will help the authorities to keep track of the visitors visiting and the employees on the campus. This web app is being built with help of HTML, CSS, JS, and PHP. The data of the new visitors visiting the campus and employees’ details will be stored in the database and employees’ attendance will be stored in an excel sheet on the server. With this system, the visitor’s information can be stored in the database so that in the future it shall be used for reference. The data will be stored in the Mysql Server and Excel file as the backend. This software will help an organization to do the job effectively and give an all-around development of the system.

23. Implementation of Multi-Keyword Based Rank Search Over Encrypted Cloud with File Indexing

AUTHOR NAME : Miss. Tanvi Rajendra Dahake, Prof. Jayant P. Mehare

ABSTRACT : The cloud computing platform gives people the ability to share resources, services, and information among people from all over the world. In the increasing popularity of cloud computing, more and more data owners are motivated to outsource their data into cloud servers for great convenience and reduced costs in data management. The sensitive data should before the outsourcing of data protection requirements, data usage obsoletes such as keyword-based document retrieval is encrypted. Improved dynamic multi-keyword ranking search scheme with top key via encrypted cloud data that simultaneously supports dynamic update operations as deleting and inserting documents. The greedy depth-first search algorithm is provided for efficiency multi keywords on the place and index structure. The safe KNN algorithm is used to encrypt the index and query vectors and ensure precise meaning score calculation between the encrypted index and query vectors. A secure multi-keyword search is controlled via encrypted cloud data that simultaneously supports dynamic update operations, such as deleting and inserting documents. Here, focus on the data security problems with extended searchable symmetric encryption. For the first time formulate the issue of privacy in terms of relevance and similarity scheme robustness. The observation of these server-side rankings inevitably leaks based on order-preserving encryption protection. To eliminate the leak, we propose to support the top-k multi-full-text search. Thorough security and performance analysis shows that the proposed scheme guarantees high safety and practicality and dynamic update operations, such as deleting and inserting documents.

24. Computational Model for Enhanced Chatbot System Using Artificial Intelligence Based on Dataset Evaluation

AUTHOR NAME : Miss. Monal Vijay Dahake, Prof. Dr. Neeraj Sahu

ABSTRACT : For using software applications, user interfaces that can be used includes command line, graphical user interface (GUI), menu-driven, form-based, natural language, etc. The mainstream user interfaces include GUI and web-based, but occasionally the need for an alternative user interface arises. A chatbot-based conversational user interface fits into this space. The chatbot is a class of bots that have existed in the chat platforms. The user can interact with them via graphical interfaces or widgets, and the trend is in this direction. They generally provide a stateful service i.e., the application saves data of each session. On an educational website, one often doesn’t know where to search for some kind of information. It becomes difficult to extract information for a person who is not a student or employee there. The solution to these comes up with a college inquiry chatbot, a fast, standard, and informative widget to enhance the educational website’s user experience and provide effective information to the user. Chatbots are intelligent systems being developed using artificial intelligence (AI) and natural language processing (NLP) algorithms. It has an effective user interface and answers queries related to academic activities.

25. Automatic Number Plate Recognition Using Python-OPENCV And Tensorflow

AUTHOR NAME : Ankit Jambhulkar, Himanshu Patil, Aniket Patil, Prof. Prashant Govardhan

ABSTRACT : Object identification and image processing are two areas of research that overlap. Various notable works in the sector of transportation have been completed in order to provide a safe and legal traffic environment. A precise and fast vehicle number plate recognition system is a traffic management solution that leads to better regulations. This research is based on optical character recognition (OCR), which employs advanced approaches to get optimal results. A full-fledged number plate recognition technique is proposed, with improved accuracy over the existing system. The entire system can be installed as a traffic-related legal and security solution. The Automatic Number Plate Recognition (ANPR) technology combines machine learning, image processing, and pattern recognition into one system. Optical character recognition (OCR) is a machine learning and computer vision method that plays a major part in automatic number plate recognition. It is one of the most important aspects of research in machine learning and computer vision.

26. Machine Learning Based Pneumonia Diagnosis from X-Ray Images

AUTHOR NAME : Yogesh Futane, Dr. C. N. Deshmukh

ABSTRACT : Pneumonia is one of the serious and life-threatening diseases that is caused by a bacterial or viral infection of the lungs and has the potential to result in severe consequences within a short period. Therefore, early diagnosis is a significant factor in terms of the successful treatment process. Thus, there is a need for an intelligent and automatic system that has the capability of diagnosing chest X-rays and simplifying the Pneumonia detection process. This study aims to develop a model that will help with the classification of chest X-ray medical images and further diagnosis. To achieve this, existing state-of-the-art Machine Learning techniques with the inceptionv3 model have been used to increase efficiency and accuracy. This study, proposed machine learning for the classification task and uses supervised learning through array of input images. Experimentally, it showed that the InceptinV3 approach combined with SVM for the classification task performs the best as compared to the other Machine Learning techniques. This study, successfully classified chest infection from Chest X-ray Images using machine learning based on InceptionV3 with an overall accuracy of 86.66%. The developed system is capable of diagnosing pneumonia infection for most of the age groups.

© 2020 @ Global Advanced Research Publication House