Papers by Roja Dasthavejula
SSRN Electronic Journal
A user's emotion or mood can be detected by his/her facial expressions. These expressions... more A user's emotion or mood can be detected by his/her facial expressions. These expressions can be derived from the live feed via the system's camera. A lot of research is being conducted in the field of Computer Vision and Machine Learning (ML), where machines are trained to identify various human emotions or moods. Machine Learning provides various techniques through which human emotions can be detected. People often use music as a means of mood regulation, specifically to change a bad mood, increase energy level or reduce tension. Also, listening to the right kind of music at the right time may improve mental health. Thus, human emotions have a strong relationship with music.
In the present day world, online shopping using WAP enabled mobile phone has widely come into use... more In the present day world, online shopping using WAP enabled mobile phone has widely come into use. Credit cards serve as the currency during e-business and E-Shopping. As technology has advanced in the negative side also hackers and spoofers steal misuse credit card numbers, even though the network has been made secure. So, in this paper, we have proposed a multi-biometric model (integrating voice, fingerprint and facial scanning) that can be embedded in a mobile phone, this making e-transactions more secure. The model is very cost effective as we have tried to use the hardware already present in the phone.This paper uses for image processing or facial reorganization and finger print. We have also simulated a few graphs for voice recognition and facial verification using MATLAB 6.0
A robust, computationally efficient and blind digital image watermarking in spatial domain has be... more A robust, computationally efficient and blind digital image watermarking in spatial domain has been discussed in this paper. Embedded watermark is meaningful and recognizable and recovery process needs only one secret image. Watermark insertion process exploits average brightness of the homogeneity regions of the cover image. Spatial mask of suitable size is used to hide data with less visual impairments. Experimental results show resiliency of the proposed scheme against large blurring attack like mean and Gaussian filtering, non linear filtering like median, image rescaling, symmetric image cropping, lower order bit manipulation of gray values and loss data compression like JPEG with high compression ratio and low PSNR values. Almost as discreetly as the technology itself, digital watermarking has recently made its debut on the geo-imaging stage. This innovative technology is proving to be a cost-effective means of deterring copyright theft of mapping data and of ensuring the authenticity and integrity of asterisked image data. First developed around six years ago, digital watermarking is a sophisticated modern incarnation of steganography-the science of concealing information within other information. In the field of e-commerce, digital watermarking has already established itself as an effective deterrent against copyright theft of photographs and illustrations. Now digital watermarking software is finding uses within national mapping agencies and others working with asterisked images or map data. Current applications range from protecting valuable map data against copyright theft to securing photographic survey or reconnaissance images against tampering.
2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)
As more sectors began to switch from conventional business models to e-commerce in response to th... more As more sectors began to switch from conventional business models to e-commerce in response to the general trend toward mobile Internet use, the scale of e - commerce grew rapidly. There are three types of recommendation systems: hybrid, collaborative, contentbased. Content based systems take into consideration the characteristics of the recommended objects. Then, titles in the database that have been classified as "romantic" are selected using a content-based recommendation method.Collaborative filtering systems utilize similarity measures to recommend items that are shared by individuals or objects with similar interests. Users are recommended items based on their preferences.In the recommendation system, collaborative filtering is the most popular and effective suggestion process. However, system performance impact as the amount of time required to locate the target user's closest neighbor across the entire user space increases with the number of users and products in the e -commerce system. The applied and designed Multi-Agent personalized recommendation system in E-commerce can be analyzed using user clustering in the Multi-Agent to E-commerce personalized recommendation system. An implementation strategy for recommendations based on user clustering is shown in this analysis. According to their scores for commodity categories, users are clustered, and only the nearest neighbours in their categories are searched, so that as many nearest neighbors as possible can be searched. The accuracy, recall, and specificity of this analysis are used to calculate its performance. In this analysis the presented method will give better results.
2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA)
Nowadays, digitalization in the healthcare organizations places great emphasis on technological a... more Nowadays, digitalization in the healthcare organizations places great emphasis on technological advances in clinical healthcare providers. Traditional methods for measuring and evaluating outcomes for patients in forecasting and diagnosing chronic diseases are being substituted by techniques that capture the most significant insights from medical information by combining predictive modeling with a highly valuable application of machine learning. Heart disease is nowadays among the worst disorders in the world. Because the death rate from heart disease remained largely significant, more intensive efforts in preventive are required, such as enhancing the accuracy of a heart disease prediction system. Additionally, an early diagnosis supports in the appropriate diagnosis of the condition as well as the management of its symptoms. By creating forecasting analytics, Machine Learning (ML) techniques can be used to anticipate chronic diseases including kidneys and cardiac disorders. Hence, this analysis presents coronary heart disease prediction and classification utilizing Hybrid Machine Learning methods. In this approach the combination of Decision Tree (DT) and Ada Boosting algorithms is used as a hybrid ML algorithm to predict the CHD. This method's performance is determined by the performance metrics such as accuracy, True Positive Rate (TPR), and S pecificity.
IARJSET
Unlike competing online Infringement solutions, Infringement is copy-paste elimination software. ... more Unlike competing online Infringement solutions, Infringement is copy-paste elimination software. Infringement is the illegal use of another person's words or ideas without permission. It's a dishonest thing to do. Copyscape is an anti-piracy programme that ensures all of our customers' essays and term papers are 100% unique. Users and organisations alike can now use cloud computing to access their data and run their programmes from any device with an internet connection, eliminating the need for local installations of software. Cloud computing is a method of storing and accessing information and software on remote servers and networks.Professors should be concerned about infringement because it happens frequently. Students in many engineering and computer science degree programmes take online courses where they are graded on the code they create on their own or in small groups. Multiple indicators make it hard to spot infringing code. Therefore, it is necessary to create an Infringement checking system that will accept code submissions from teachers and quickly identify instances of plagiarism. In other words, it analyses the structure of each uploaded assignment and finds any similarities. A straightforward style is used to summarise the similarity analysis results, which show which tasks are most similar to one another. This method has the advantage of relieving teachers of the tedious task of checking for Infringements.
International Research Journal of Modernization in Engineering Technology and Science
This work makes two significant contributions to the current status of viticulture technology stu... more This work makes two significant contributions to the current status of viticulture technology studies. We start with a detailed look at the history and current state of computer vision, image processing, and machine learning applications in the wine industry. We provide a concise overview of recent advances in vision systems and methodologies by analysing case studies from a wide range of fields, including as crop yield estimation, vineyard management and monitoring, disease detection, quality evaluation, and grape phonology. Here, we zero in on the ways in which modern vineyard management and vinification procedures can benefit from the application of computer vision and machine learning. In the paper's second section, we introduce the brandnew Grape CS-ML Database, which contains photos of grape varietals at various stages of development alongside the relevant ground truth data (e.g. pH, Brix, etc.) collected from chemical analysis. The creation of useful solutions for use in smart vineyards is a primary goal of this database, and it is hoped that it will inspire academics in computer vision and machine learning to work on this problem. We showcase the database's potential for a color-based berry recognition application by comparing white and red cultivars across a number of machine learning methods and colour spaces, and providing a set of reference data for evaluation. The study finishes by pointing out some of the issues that will need to be resolved in the future in order to fully utilise this technology in the viticulture industry.
2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS)
The banking industry has experienced significant transformations in terms of how effectively they... more The banking industry has experienced significant transformations in terms of how effectively they function and provide services over the past few decades. The banking services infrastructure will be challenged by an expanding worldwide population. While serving a sizable segment of clients, it improves the number of consumers, online transactions, and produces enormous amounts of data. Today, banks in the US and other nations use Big Data Analytics (BDA) to handle this scenario daily. It looks for different trends in their databases in order to help their organizations make more money. Banks are changing from a straightforward approach to managing credit risk to a comprehensive risk management methodology. Banking dangers originate from numerous systems and channels. Big data technology offers an insightful and effective method for managing data, making it appropriate for use in risk management applications that call for complicated data analysis and increased data. The big data architecture of a banking credit investigation and integrated risk management system is described in this analysis. Comparisons and analyses unambiguously show that the described system performs better. Hence, this model shows that efficiency and security has improved.
Mobile computing is a new emerging computing paradigm of the future. Data management and location... more Mobile computing is a new emerging computing paradigm of the future. Data management and location management in this paradigm poses many challenging problems to the Mobile database community. In the past decade, Mobile communications have experienced an expensive growth due to recent technological advances in mobile networks and cellular telephone manufacturing. Location management is a very important problem among these challenges. It consists of updating the location of the user, searching the location and performing searchupdates. When the host changes location, an update occurs. When the host want to communicate with a mobile host whose location is unknown to the requesting host, a search occurs. A search-update occurs after a successful search, when the requesting host updates the location information corresponding to the searched mobile host. The goal of a good location management scheme should be to provide efficient searches and updates. In this paper, the different location management schemes, various search & update strategies are discussed.
INTERNATIONAL JOURNAL OF PROGRESSIVE RESEARCH IN ENGINEERING MANAGEMENT AND SCIENCE (IJPREMS), 2023
Brain Fingerprinting is a new computer-based technology to identify the perpetrator of a crime ac... more Brain Fingerprinting is a new computer-based technology to identify the perpetrator of a crime accurately and scientifically by measuring brainwave responses to crime-relevant words or pictures presented on a computer screen. Brain Fingerprinting has proven 100% accurate in over 120 tests, including tests on FBI agents, tests for a US intelligence agency and for the US Navy, and tests on real-life situations including felony crimes.
INTERNATIONAL JOURNAL OF PROGRESSIVE RESEARCH IN ENGINEERING MANAGEMENT AND SCIENCE (IJPREMS), 2023
The word on just about every Internet user's lips these days is "broadband." We have so much more... more The word on just about every Internet user's lips these days is "broadband." We have so much more data to send and download today, including audio files, video files and photos, that it's clogging our wimpy modems. Many Internet users are switching to cable modems and digital subscriber lines (DSLs) to increase their bandwidth. There's also a new type of service being developed that will take broadband into the air. In this paper, we'll learn about the future of the Airborne Internet. We'll take a look at the networks in development, the aircraft and how consumers may use this technology. Land-based lines are limited physically in how much data they can deliver because of the diameter of the cable or phone line. In an airborne Internet, there is no such physical limitation, enabling a broader capacity. The airborne Internet will function much like satellite-based Internet access, but without the time delay. The airborne Internet will actually be used to compliment the satellite and ground-based networks, not replace them. These airborne networks will overcome the last-mile barriers facing conventional Internet access options. This paper addresses some of the trends and issues involved in developing an Airborne Internet capable of achieving this goal. Understanding relationships between these trends and issues and the objectives and functional requirements of the program will allow various participants in this complex program to keep activities in proper perspective. The all-round development and improvement are the key areas of research work performed in this paper.
The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Alg... more The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Algorithm by possible word of guesses. Word Guessing Game (Hangman) is a popular where the player attempts to build a missing word by guessing one letter at a time. T his is a simple Hangman game using Python programming language. We can use this as a small project to boost their programming skills and understanding logic. The Hangman program randomly selects a secret word from a list of secret words. The random module will provide this ability. This paper contains some more features like voice assistant where the system guides the actions we need to perform.
The Internet is constantly under serious threat from distributed denial of service (DDoS) attacks... more The Internet is constantly under serious threat from distributed denial of service (DDoS) attacks. In order to overload victim resources, modern DDoS attacks are moving up to the application layer by masquerading as valid HTTP requests, a technique that was previously only used in the lower tiers. When such attacks happen during the flash crowd event of a major website, it could be disastrous. For the purpose of spotting these novel DDoS attacks, a technique based on document popularity is presented. To represent the temporal and geographical dynamics of a typical flash mob, the concept of a "Access Matrix" is introduced. To simplify the n-dimensional Access Matrix, principal component analysis and independent component analysis are used. It is proposed that the dynamics of the Access Matrix be described using a hidden semi-Markovmodel, and that an innovative anomaly detector based on this model be used to detect attacks. Potential applicationlayer DDoS attacks are identified using the entropy of document popularity after fitting the model. Real-world Web traffic data is used to get numerical figures that prove the proposed strategy works.
The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Alg... more The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Algorithm by possible word of guesses. Word Guessing Game (Hangman) is a popular where the player attempts to build a missing word by guessing one letter at a time. T his is a simple Hangman game using Python programming language. We can use this as a small project to boost their programming skills and understanding logic. The Hangman program randomly selects a secret word from a list of secret words. The random module will provide this ability. This paper contains some more features like voice assistant where the system guides the actions we need to perform.
JETIR, 2023
Radio Frequency Identification (RFID) is currently being used for auto-identification of objects,... more Radio Frequency Identification (RFID) is currently being used for auto-identification of objects, assets, pets, and people. Its initial success in offering strategic advantages for businesses, by efficient tracking of inventory in the supply chain, has left this technology wide open to many applications that are only limited by people's imagination. This technology will have a tremendous impact on our society, once it starts to assist people in their daily life. A right step in this direction would be Mobile RFID, where a RFID reader chip is integrated into a portable mobile device like mobile phone, and PDA. Mobile RFID would help consumers in shopping, and allows quick and easy access to information, just by bringing their mobile devices near to an object that has a RFID tag. This paper pioneers in describing Mobile RFID's new applications and security challenges. It focuses on different Mobile RFID application zones, and their related security threats, and security requirements. Finally it proposes simple security architecture for Mobile RFID applications in Location-based Services zone.
The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Alg... more The Word guessing game as an example of using Quick sort, Binary search, a Divide and Conquer Algorithm by possible word of guesses. Word Guessing Game (Hangman) is a popular where the player attempts to build a missing word by guessing one letter at a time. T his is a simple Hangman game using Python programming language. We can use this as a small project to boost their programming skills and understanding logic. The Hangman program randomly selects a secret word from a list of secret words. The random module will provide this ability. This paper contains some more features like voice assistant where the system guides the actions we need to perform.
Digital image processing is the use of computer algorithms to perform image processing on digital... more Digital image processing is the use of computer algorithms to perform image processing on digital images. Digital image processing has the same advantages over analog image processing as digital signal processing has over analog signal processingit allows a much wider range of algorithms to be applied to the input data, and can avoid problems such as the build-up of noise and signal distortion during processing. The most common kind of digital image processing is digital image editing. Pattern recognition aims to classify data (patterns) based on either a priori knowledge or on statistical information extracted from the patterns. The patterns to be classified are usually groups of measurements or observations, defining points in an appropriate multidimensional space. This is in contrast to pattern matching, where the pattern is rigidly specified.
In this paper author proposed that fraud detection is a critical problem affecting large financia... more In this paper author proposed that fraud detection is a critical problem affecting large financial companies that have increased due to the growth in credit card transactions. This paper presents detection of frauds in credit card transactions, using data mining techniques of Predictive modeling, logistic Regression, and Decision Tree. The data set contains credit card transactions in September 2013 by European cardholders. This data set present transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The data set is highly unbalanced, the positive class(frauds) Account for 0.172% of all transactions.
A user's emotion or mood can be detected by his/her facial expressions. These expressions can be ... more A user's emotion or mood can be detected by his/her facial expressions. These expressions can be derived from the live feed via the system's camera. A lot of research is being conducted in the field of Computer Vision and Machine Learning (ML), where machines are trained to identify various human emotions or moods. Machine Learning provides various techniques through which human emotions can be detected. People often use music as a means of mood regulation, specifically to change a bad mood, increase energy level or reduce tension. Also, listening to the right kind of music at the right time may improve mental health. Thus, human emotions have a strong relationship with music.
zkg international , 2023
Aim of this project, deals with the matter of identifying the currency that if the given sample o... more Aim of this project, deals with the matter of identifying the currency that if the given sample of currency is fake. Different traditional strategies and methods are available for fake currency identification based on the colors, width, and serial numbers mentioned. In the advanced age of Computer Science and high computational methods, various machine learning algorithms are proposed by image processing that gives 99.9% accuracy for the fake identity of the currency. Detection and recognition methods over the algorithms include entities like color, shape, paper width, image filtering on the note. This project proposes a method for fake currency recognition using K-Nearest Neighbors followed by image processing. KNN has a high accuracy for small data sets making it desirable to be used for the computer vision task. In this, the banknote authentication dataset has been created with the high computational and mathematical strategies, which give the correct data and information regarding the entities and features related to the currency. Data processing and data Extraction is performed by implementing machine learning algorithms and image processing to acquire the final result and accuracy.
Uploads
Papers by Roja Dasthavejula
conventional business models to e-commerce in response to
the general trend toward mobile Internet use, the scale of e -
commerce grew rapidly. There are three types of
recommendation systems: hybrid, collaborative, contentbased. Content based systems take into consideration the
characteristics of the recommended objects. Then, titles in
the database that have been classified as "romantic" are
selected using a content-based recommendation
method.Collaborative filtering systems utilize similarity
measures to recommend items that are shared by individuals
or objects with similar interests. Users are recommended
items based on their preferences.In the recommendation
system, collaborative filtering is the most popular and
effective suggestion process. However, system performance
impact as the amount of time required to locate the target
user's closest neighbor across the entire user space increases
with the number of users and products in the e -commerce
system. The applied and designed Multi-Agent personalized
recommendation system in E-commerce can be analyzed
using user clustering in the Multi-Agent to E-commerce
personalized recommendation system. An implementation
strategy for recommendations based on user clustering is
shown in this analysis. According to their scores for
commodity categories, users are clustered, and only the
nearest neighbours in their categories are searched, so that
as many nearest neighbors as possible can be searched. The
accuracy, recall, and specificity of this analysis are used to
calculate its performance. In this analysis the presented
method will give better results.