Volume 10 | Issue 3

 Abstract

Sign language is a very essential communique tool for plenty deaf and mute human beings. So we proposed a version to understand sign gestures the usage of YOLOv5 (You only look as soon as version 5). This version can locate sign gestures in complicated surroundings also. For this model we were given the accuracy of 88.4% with precision of 86.6% and don’t forget of 87.2%. The proposed model has evaluated on a labeled dataset Roboflow. Moreover we added some photographs for schooling and checking out to get higher accuracy. We as compared our model with CNN (convolutional neural network) in which we were given accuracy of 91.98%. We checked this model for actual time detection also and got the accurate consequences.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

SIGN LANGUAGE TO SPEECH CONVERTER FOR INDIAN LANGUAGES

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

A purposeful action that results in harm to one’s person, harm to one’s property, or both constitutes a crime. Depending on the offense’s seriousness, the state or other authorities may punish the offender. Authorities are being forced to devise effective preventive measures due to the worrisome rise in both the quantity and types of criminal activity. In the current climate, where crime has sharply increased, traditional crime resolution approaches are sluggish and ineffectual. Hence, it will lessen the strain on the police and aid in crime prevention if you can figure out a means to foresee crime, predict it in detail before it occurs, or develop a “machine” that can support police personnel. The sole goal of this research is to determine how government agencies, including law enforcement, may use computer vision and machine learning to spot, stop, and combat crime. In conclusion, advancements in computer vision and machine learning can speed up the growth of law businesses. The proposed research uses neural networks with autonomous coding, decoding, and Artificial Intelligence to learn condensed versions of raw inputs, autoencoder-style neural network kinds can be employed. The branch of AI known as computer vision teaches computers to extract and decipher information from picture and video data. By altering the typical CNN design and streamlining the connecting pattern between layers, DenseNet - 121 finds a solution to this issue. Based on a comparison of autoencoder and DenseNet - 121 for crime prediction, this suggested work was created.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Crime, Preventing Measures, Traditional crime resolution techniques, Machine Learning, Artificial Intelligence, Autoencoder, Neural Network.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The aim of this project is to explore different methodologies for sharing location while driving using GPS and to develop a safe and effective approach that minimizes distractions and prioritizes safety. The project will examine existing technologies and tools, such as GPS-enabled apps, hands-free technology, share location features on smartphones, and GPS tracking devices. The focus will be on identifying the advantages and limitations of each methodology, as well as any legal and regulatory considerations related to phone usage while driving. Based on this analysis, the project will propose a methodology that enables drivers to share their location safely and responsibly while on the road. The project aims to provide a comprehensive understanding of the best practices for location sharing while driving, with a focus on enhancing safety and minimizing distractions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Vehicle issues,GPS,Security,Prototyping

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Network traffic profiling is a process of characterizing packet flows on the network. Typical network traffic consists of packets exchanged between hosts. Network traffic profiling has increasingly been used as a mechanism to improve the efficiency and security of computer networks in businesses, research institutions, end users and other organizations. The rapid growth of Internet traffic has become a big problem with the rapid development of various Web applications and Internet services. Therefore, ISPS must study the traffic habits and user behavior of different locations, application usage trends, and thereby, propose solutions that can effectively, efficiently and economically support the traffic of its users. These network traffic analyses show that the campus network is experiencing staggering bandwidth, a serious and emerging challenge for nearly every IT organization operating in today’s world. Lack of proper bandwidth management prevents useful Internet access, which in turn reduces the quality of academic and research work.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

SourceIP, DestinationIP, Data rate, Total no of Packets, Bandwidth utilization.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Examining Successful Attributes for Undergraduate Students by Applying Machine Learning Techniques

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Examining Successful Attributes for Undergraduate Students by Applying Machine Learning Techniques

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project proposes the development of a home automation system using Wi-Fi and ESP8266. The system will allow users to control various household appliances such as lights, fans, air conditioners, and electronic devices using their smartphones or other connected devices. The proposed system will use the ESP8266 microcontroller, which has Wi-Fi capabilities, to connect to the internet and receive commands from the user’s device. The system will use a web interface that will allow users to control and monitor their devices remotely. The web interface will be hosted on a local server, and the system will use MQTT protocol for data communication.We created the Flutter application to turn on and off the all home appliances through the application.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IOT BASED HOME AUTOMATION SYSTEM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This abstract describes a supermarketbilling automation application that utilizes barcode inputfor faster and more accurate billing. The application is designed to simplify the billing process in supermarkets by automating the calculation of prices and reducing thepotential for human error. The application uses barcode scanning technology to read product information and automatically add items to the customer’s bill. This eliminates the need for manual input and speeds up the billing process. Additionally, the system can store product and pricing information in a database, which can be easily updated as needed. The application can also generate detailed billing reports and analytics, allowing supermarkets to better understand their sales patterns and inventory levels. This can help them make more informed decisions about pricing and stock management. Overall, the use of barcode input in this supermarket billing automation application offers a more efficient and accurate way to process customer purchases, improving the customer experience and enhancing supermarket operations.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

SUPERMARKET BILLING AUTOMATION AND LIBERATION SYSTEM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Organisations can benefit greatly from an attendance system. It enables a company to completely regulate every employee’s working hours. By decreasing overpayments�which are frequently brought about by transcription error, interpretation error, and purposeful error�it helps keep labour expenses under control. The staff required to maintain manual procedures is also removed. Although following labour laws can be challenging, a time and attendance system is crucial for ensuring that laws requiring proof of presence are followed. Every organisation has a precise location that the GPS pinpoints. A GPS device (such as a mobile phone, GPS watch, or other GPS- enabled device, etc.) can be used to locate an employee. It should be considered that an employee is in the office if their approximate locations are the same as the location of their employer. In parallel, face recognition is used to confirm a user’s identification.In this work, a novel attendance system based on location is developed and location is used as an evidence of attendance.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Access control, Attendance monitoring, Biometric, IoT, RFID tags,GPS.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In our daily life we face several issues in our society We have different portal for a particular domains like electrical complaints, water supply complaints etc� While a user is registering a complaint in our portal, this complaint text and images were being analyze using KNN algorithm which can be used for both classification and regression problems. The KNN algorithm uses ‘feature similarity’ to predict the values of any new data points. This means that the new point is assigned a value based on how closely it resembles the points in the training set, if this complaint already exits complaint will be wrapped under the existing previous complaint . Once the complaint is solved, it indicates the complaint status to all users. If the complaint did not previously exist in any complaints, it will be saved as a new complaint. Furthermore, if the same type of complaint registers multiple times, they will be analyze the severity of the complaint using the SVM algorithm of emotional prediction to identify the severity of the complaint. This algorithm helps us identify the motive and emotions behind a complaint, gain many more insights, and eventually predict the future response and after the prediction of the severity appropriate action will be taken. If the majority of complaints continuously arises, they will be analysed using KNN algorithm. The KNN algorithm is used to classify by finding the K-nearest matches in training data and then using the label of closest matches to predict, after analysing report of reason will send to the admin.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Data analytics, KNN algorithm, Emotional prediction, Support Vector Machine(SVM) algorithm

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Software Engineering is a branch of computer science that enables tight communication between system software and training it as per the requirement of the user. We have selected seven distinct algorithms from machine learning techniques and are going to test them using the data sets acquired for NASA public promise repositories. The results of our project enable the users of this software to bag up the defects are selecting the most efficient of given algorithms in doing their further respective tasks, resulting in effective results

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

INFLUENCES OF MACHINE LEARNING ALGORITHM FACTORSING SOFTWARE FAULT PREDICTION

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The photo and video editing industry are facing a critical challenge where talented editors are unable to showcase their skills on a centralized platform, leading to missed opportunities for freelance work. Furthermore, companies struggle to identify and recruit competent editors due to the lack of a reliable rating system. This problem highlights the need for an innovative platform that provides a one-stop solution for both editors and companies. The proposed platform would enable editors to showcase their portfolio and skills, connect with potential clients, and receive ratings and feedback, while companies would have access to a pool of talented editors with a reliable rating system to aid in their hiring decisions. By addressing these issues, the platform would create a mutually beneficial environment for the photo and video editing industry, facilitating growth and success for both parties.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Talent space

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In our day to day life we face environmental challenges associated with waste generation and inadequate waste collection, transport, treatment and disposal. The waste treatment process takes crucial procedures to segregate waste materials into reusable material. To separate reusable particles from E-waste, wet waste, plastic waste, metal waste are monitored and segregated using this System. In this paper, we propose a method where the waste particles are moving in the conveyor belt and they are detected using sensors. This System enables an IoT based waste monitoring system using Thing speak,which is an open IoT platform. This system consists of an Arduino microcontroller, a set of sensors and a Wi-Fi module. The Arduino microcontroller receives data from the sensors like IR sensor, proximity sensor, ultrasonic sensor and load cell. The wastes are detected and pulled to the respective dustbins. The depth of the garbage in the bin is measured using an ultrasonic sensor and the weight of the bin with garbage is measured from the load cell. The LCD screen is used to display the data. The Wi-Fi module transmits the above data to the internet. An open IoT platform Thingspeak is used to monitor the garbage system. IOT combined with smart dustin helps the administrator to monitor and schedule garbage collection more efficiently. Finally, the blockchain technology supports sharing the information among stakeholders to analyze and take action appropriately.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sensors, Internet of Things, Smart Waste Container

  License

Creative Commons Attribution 4.0 and The Open Definition