Volume-13 Issue-1, May 2024 – International Journal of Recent Technology and Engineering (IJRTE)

A806613010524

IJRTE Journal — Tue, 28 May 2024 05:24:14 +0000

Enhancing Contextual Masking in Reversible Linguistic Steganography with Ensemble Methods
M Prasha Meena¹, N J S Deepalakshmi², R Dharsni³, R Subashree⁴

¹Mrs. M. Prasha Meena, Department of Information Technology, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.

²N J S Deepalakshmi, Department of Information Technology, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.

³R Dharsni, Department of Information Technology, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.

⁴R Subashree, Department of Information Technology, Mepco Schlenk Engineering College, Sivakasi (Tamil Nadu), India.

Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Various cybercrimes can be prevented by text authentication, which is responsible for preserving digital identities and contents. Digital signatures are a convenient method for authenticating texts, which is an approach that is widely used. One approach to this problem is linguistic steganography, which enables the hiding of the signature within other words within the text, thereby facilitating efficient data management. However, it should be noted that there is a danger that these kinds of changes may result in inappropriate decisions being made by automated computing systems, not to mention altering their final outputs (unseen). As such, many people are becoming increasingly concerned about the possibility of reversing steganography, making it possible to eliminate any distortions introduced during the process. This paper employs contextual masking instead of random masking with the BERT model. The goal of this research was to develop a natural language text-specific reversible steganographic system. Our model utilises pre-trained BERT as a transformer-based masked language model and reversibly embeds messages through predictive word substitution. To quantify predictive uncertainty, we introduce an adaptive steganographic technique using Bayesian deep learning. This experiment demonstrates how our proposed system strikes a balance between imperceptibility and capacity, while maintaining near-semantic accuracy at all times. Additionally, we employ ensemble methods instead of Monte Carlo to enhance the imperceptibility.

Keywords: Contextual, Ensemble Methods, Reversibility, Steganography.
Scope of the Article: Deep Learning

Download PDF

The post A806613010524 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

A805213010524

IJRTE Journal — Tue, 28 May 2024 05:15:45 +0000

A Framework to Optimize Student Performance using Machine Learning
Abhijeet Joshi¹, A. S. Kapse²

¹Mr. Abhijeet Joshi, Department of Computer Science & Engineering, Anuradha Engineering College Chikhli (Maharashtra), India.

²Dr. Avinash S. Kapse, Associate Professor & Head of Department Computer Science & Engineering, Anuradha Engineering College Chikhli (Maharashtra), India.

Abstract: For scholars, mining data and extracting information from massive databases has emerged as an intriguing field of study. For several decades, the concept of using data mining techniques to extract information has been around. The dataset was initially intended to be partitioned, and the inherent features were examined using classification and clustering algorithms. They base their predictions on these characteristics. These forecasts have been developed in the area of educational data mining for several reasons, including predicting student success based on personal traits and helping students find the right professors and courses. These goals have been drawn from the attrition and retention of students. These objectives are the focus of our research on student attrition and retention. Additionally, we have found exciting variables that aid in predicting students’ success, suggesting the most qualified instructors, and assisting them in course selection.

Keywords: Mining, Databases, Information, Dataset, Predictions, Performance.
Scope of the Article: Machine Learning

Download PDF

The post A805213010524 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

A805413010524

IJRTE Journal — Tue, 28 May 2024 05:09:37 +0000

Synergy of Real and Digital Worlds – Promising Insights for the Future Generations of Fashion
Srivani Thadepalli¹, Uday Choudhary²

¹Srivani Thadepalli, Associate Professor, Department of Fashion Technology, National Institute of Fashion Technology, Hyderabad, 500081 Telangana, India.

²Mr. Uday Choudhary, Student, Department of Fashion Technology, National Institute of Fashion Technology, Hyderabad (Telangana), India.

Abstract: Digital transformation (DT) is reshaping the fashion industry, revolutionizing the way brands, retailers, and consumers interact. It is not a fad but a necessary step towards innovation and survival in today’s business context. Implementing digital transformation requires a bespoke approach that addresses specific challenges and goals within the existing framework of each brand or retailer. Fashion brands are leveraging digital technologies throughout their value chain, from product design and production to marketing and distribution. Computer-aided design (CAD) software, predictive analytics, and 3D printing are streamlining the design and prototyping phases, reducing time-tomarket and improving product quality. Technologies such as 3D body scanning, seamless garments, and digitised looms are also being adopted. Brands like Hugo Boss are using smart factories that incorporate robotics, artificial intelligence (AI), analytics, and the Internet of Things (IoT) to increase efficiency. Moreover, digital-integrated supply chain platforms, such as blockchain, are enabling faster and more efficient production by connecting brands with manufacturers and suppliers globally. The adoption of digital solutions extends to the production of futuristic textiles, digital clothing, and virtual models, as well as digital showstoppers. Retailers are also embracing digital transformation (DT) to enhance the customer experience and expand their reach. E-commerce has become a vital channel, enabling retailers to sell products online and expand their customer base. Many retailers are investing in robust online platforms and incorporating augmented reality (AR) and virtual reality (VR) technologies to offer immersive in-store shopping experiences. Data analytics and AI are being leveraged to personalise recommendations and offers, thereby enhancing customer engagement and loyalty. Instore virtual assistants or kiosks are worth mentioning in light of digital clientele. Social media platforms play a vital role in the fashion industry’s digital transformation. Fashion brands are partnering with social media influencers to promote their products and expand their reach to a broader audience. Additionally, collaborative consumption models are emerging through digital apps, supporting sustainability efforts such as zero waste, recycling, and sharing goods or services. Consumers are benefiting from greater convenience, choice, and personalized experiences in the digital fashion landscape. They have access to a wide array of products from around the world and can find inspiration and style ideas on social media platforms. Usergenerated content and reviews facilitate informed purchase decisions. Mobile technology advancements have blurred the lines between online and offline retail experiences, enabling consumers to shop anytime and anywhere. Adaptability, inclusivity, diversity, authenticity, and traceability of the product life cycle (Utilising Blockchain Technology) have become key factors driving the purchasing decisions of Gen Zers and Millennials. However, traditional industry players and small independent retailers face increased competition from e-commerce giants, necessitating their adaptation to digital technologies to remain relevant. The COVID-19 pandemic has accelerated this shift and normalized the idea of going digital. This paper presents an in-depth review of how digital transformations have impacted various players within the fashion Industry, with special reference to the brands, designers, and enterprises that are implementing these changes to drive their evolution and progression in this rapidly evolving landscape.

Keywords: Digital, Data Analytics, Mobile, Blockchain, COVID-19
Scope of the Article: Data Analytics

Download PDF

The post A805413010524 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

F801912060324

IJRTE Journal — Tue, 28 May 2024 05:01:47 +0000

Leveraging Cryptographic Hash Functions for Credit Card Fraud Detection
Govind Prasad Buddha

Govind Prasad Buddha, Vice President, Software Engineer III Bank of America.

Abstract: Credit card fraud remains a significant challenge in the financial industry, posing substantial economic losses to both consumers and businesses. Traditional fraud detection methods often rely on rule-based approaches and statistical models, which may struggle to keep pace with evolving fraud tactics and sophisticated cyber threats. In this paper, we propose a novel approach to credit card fraud detection leveraging cryptographic hash functions. Cryptographic hash functions offer robust security guarantees, including collision resistance and preimage resistance, making them well-suited for ensuring the integrity and authenticity of transaction data. Our proposed system employs cryptographic hash functions, such as SHA-256, to generate unique hash values for credit card transactions. These hash values serve as digital fingerprints of the transaction data, enabling secure verification and auditing of transactions on the blockchain. We conducted experiments using a dataset of 100,000 credit card transactions to evaluate the performance of our system in terms of accuracy, precision, recall, and F1-score. The results demonstrate the effectiveness of our approach in accurately identifying fraudulent transactions while minimizing false positives. Furthermore, we discuss the implications of our findings and explore future research directions, including the integration of advanced cryptographic techniques and blockchain technology to enhance the security and privacy of credit card transactions. Overall, our study underscores the importance of cryptographic hash functions in developing robust and secure fraud detection systems that can effectively counter emerging digital-era fraud threats.

Keywords: Credit Card Fraud Detection, Cryptographic Hash Functions, Blockchain, Transactional Data.
Scope of the Article: Software Defined Networking and Network Function Virtualization

Download PDF

The post F801912060324 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

A803013010524

IJRTE Journal — Tue, 28 May 2024 04:55:10 +0000

A Review on Classification Algorithm for Customer Churn Classification
Nurul Nadzirah Adnan¹, Mohd Khalid Awang²

¹Nurul Nadzirah Bt Adnan, Department of Informatic & Computing, University Sultan Zainal Abidin, Terengganu, Malaysia.

²Mohd Khalid Bin Awang, Department of Informatic & Computing University Sultan Zainal Abidin, Terengganu, Malaysia.

Abstract: Any sector faces a huge obstacle when it comes to retaining existing customers. The percentage of consumers who have quit using a product or service is referred to as customer churn, and it is a vital indication that offers reliable information about this percentage. When it comes to achieving long-term success in a market or industry, one of the most significant challenges that any company must face is retaining its valuable clients and fulfilling their needs. A review of the most important studies on Customer Churn Prediction is presented in this paper to furnish the reader with an overview of frequently employed data mining methodologies and their respective performances. We provide available statistics, in addition to customer information, to approximate customer attrition. The survey period spans from 2003 to 2023. During the process of Customer Churn Prediction, we identified the issues and difficulties associated with it and offered guidance and potential remedies.

Keywords: Artificial Neural Network, Churn Prediction, Survey, Customer
Scope of the Article: Classification

Download PDF

The post A803013010524 appeared first on International Journal of Recent Technology and Engineering (IJRTE).

A802913010524

IJRTE Journal — Tue, 28 May 2024 04:45:21 +0000

Visual Fall Detection Analysis Through Computer Vision and Deep Learning – Technology Proposition
C Kiranmai¹, B Srivalli², CH Komali³, G Apurva⁴, B Sneha Yesshaswi⁵

¹Dr. C Kiranmai, Department of Computer Science, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad (Telangana), India.

²B Srivalli, Department of Computer Science Engineering, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad (Telangana), India.

³CH Komali, Department of Computer Science Engineering, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad (Telangana), India.

⁴G Apurva, Department of Computer Science Engineering, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad (Telangana), India.

⁵B Sneha Yesshaswi, Department of Computer Science Engineering, Yesshaswi, Vallurupalli Nageswara Rao Vignana Jyothi Institute of Engineering and Technology, Hyderabad (Telangana), India.

Abstract: Advances in modern medicine have increased humans’ life span. Older adults face mobility problems as they age. They also feel less fit to continue any activity for short intervals. This is due to declining fitness levels or muscle strength, diminished dexterity, and loss of balance. These symptoms can lead to the individual’s fall and sometimes be fatal if not immediately attended to. It’s an alarming issue for people staying alone. They may pose significant health risks and need immediate assistance. Fall detection technologies are majorly categorised as wearable sensors and ambient sensors. Fall detection wearable devices, such as pendant necklaces, watches, and wristband devices, as well as clip-on medical alerts, use accelerometers to detect rapid downward movements that can indicate a fall. They often also include manual alert buttons for increased accuracy. This requires a level of comfort and awareness with technology for practical usage. Ambient home sensors use video cameras to monitor the user’s movement and detect falls. When the fall is transmitted to a monitoring centre, a representative typically calls the user to check on them before notifying contacts or calling for emergency services, but this can depend on the user’s preferences and risk factors. In this paper, we propose a technology that utilises security cameras to record videos and create a video-based fall detection system. The system utilises computer vision and deep learning algorithms to recognise fall-related movements and distinguish them from regular activities accurately. This system can be integrated to prompt alerts to emergency contacts, thus assisting in providing immediate aid to individuals who have experienced a fall. For higher accuracy, this system integrates multiple-angle videos and multi-person tracking to estimate the intensity of the fall, enabling immediate attention. Thus, this fall detection system can contribute to the safety, well-being and independence of individuals at risk of falling.

Keywords: Vision-based Fall Detection, Human Pose Estimation, Multi-directional Fall Detection, Multi-person Tracking, Fall Intensity Detection, Healthcare Monitoring, Deep Learning, Computer Vision
Scope of the Article: Deep Learning

Download PDF

The post A802913010524 appeared first on International Journal of Recent Technology and Engineering (IJRTE).