IJSRET » Blog Archives

Author Archives: Kajal Tripathi

The Symbiotic Relationship: Ethernet and the Rise of 5G Networks

Uncategorized

The Symbiotic Relationship: Ethernet and the Rise of 5G Networks/strong>
Authors:-Hrishikesh Bhatawadekar, Professor Dr. Shivani Budhkar

Abstract-The emergence of 5G promises a transformative era in wireless communication, boasting ultra-fast speeds, minimal delays, and the ability to connect a multitude of devices. However, this revolution rests upon a foundation often overlooked – Ethernet technology. This paper delves into the critical role Ethernet plays in the success of 5G networks. We explore how Ethernet’s established standards, exceptional reliability, and high bandwidth capabilities significantly contribute to the efficient functioning of 5G infrastructure. This analysis delves into the specific functionalities of Ethernet within the 5G Radio Access Network (RAN), particularly the potential of Ethernet Fronthaul for future deployments. Additionally, the paper examines the strengths and limitations of both technologies, highlighting the synergistic relationship that allows them to operate seamlessly together. Finally, we explore ongoing research regarding the convergence of Ethernet and 5G, emphasizing the potential for more efficient and secure future networks.

DOI: 10.61137/ijsret.vol.10.issue5.294
55

Published by:

Reinforcement Learning in Autonomous Racing

Uncategorized

Reinforcement Learning in Autonomous Racing/strong>
Authors:-Mr. Mihir Pawaskar, Dr. Jasbir Kaur, Assistant Professor Ms. Sandhya Thakkar

Abstract-Reinforcement Learning (RL) is rapidly advancing as a key approach to training autonomous agents, particularly in complex, real-time environments such as autonomous racing. This review discusses the latest developments in RL applied to endurance and competitive racing, including telemetry data integration and the application of advanced deep reinforcement learning models. The paper explores the architecture and strategies behind “Formula RL,” a system designed to optimize vehicle performance on the racetrack through RL. We delve into how RL algorithms such as Deep Deterministic Policy Gradient (DDPG) and Proximal Policy Optimization (PPO) are employed to enhance racing strategies, vehicle control, and decision-making, ultimately setting a course for the future of autonomous racing.

DOI: 10.61137/ijsret.vol.10.issue5.293
55

Published by:

AI and the Arts: Can Machines Truly Create

Uncategorized

AI and the Arts: Can Machines Truly Create/strong>
Authors:-Aditya Dubey, Archana Raj, Manish Rai, MD Owais Alam, Raj Mandwal

Abstract-The following paper deals with the modern trend of AI regarding artworks that have so far been challenging for human creativity. It goes as far as finding an answer to the question of whether machines can be attributed to true creators from analyses on AI-generated works on art, music, and literature. It similarly raises questions about philosophical matters with regard to the authorship, originality, and the emotional level of works by machines. The paper seeks to describe a wide capability and limitation of a potential creative force that AI carries about by reviewing the processes that are technical behind AI-generated art as well as the response towards this creativity in the world of art.

DOI: 10.61137/ijsret.vol.10.issue5.292
55

Published by:

Artificial Intelligence with Cloud Computing

Uncategorized

Artificial Intelligence with Cloud Computing/strong>
Authors:-Mr. Ankit Pandey, Dr.Jasbir Kaur, Assistant Professor Mrs.Sandhya Thakkar

Abstract-Artificial Intelligence (AI) boasts the ability to perform tasks that typically require human intelligence. Ability to completely transform many sectors within the market, facilitating decision-making that is both more efficient and effective. Cloud Computing offers the infrastructure needed for the expansion of AI applications and work together without any problems. This offers a thorough examination of the methodologies and techniques, AI integration with Cloud Computing. It had been a long time since she had [1] last seen her childhood friend, but when they finally reunited, it felt as if no time had passed at all, explores different methods of artificial intelligence, different types of cloud computing structures, as well as techniques for combining different systems. Moreover, the paper explores instances of successful outcomes, research and practical applications of artificial intelligence in cloud computing along with the difficulties that come with it. The article ends by discussing upcoming plans, potential areas for future research in this field.

DOI: 10.61137/ijsret.vol.10.issue5.291
55

Published by:

Application of Hybridized Model of Shunt and Series Facts Controllers for Improvement of Generator Oscillation Damping Stability of Electrical Power System

Uncategorized

Application of Hybridized Model of Shunt and Series Facts Controllers for Improvement of Generator Oscillation Damping Stability of Electrical Power System/strong>
Authors:-Abass Balogun, Isaiah Gbadegeshin Adebayo

Abstract-One of the technical solutions for improving the stability of power system is incorporation of Static Synchronous Compensators (STATCOM) and Static Synchronous Series Compensator (SSSC) controllers. However, the impact of hybridized STATCOM and SSSC on the generator damping stability of the power system to improve the post disturbance recovery voltages of the generator is necessary. Thus, in this study, hybridized model of STATCOM and SSSC controllers were incorporated in the Nigerian 31-bus power system to improve the system generator damping stability during disturbance. Transient stability of electrical power system with contingency was performed using swing equations technique. Line-Voltage Stability Index (L-VSI) technique was employed to determine the critical load bus for the placement of the controllers. Hybridized model of the STATCOM and SSSC was developed and incorporated into the selected load buses and its impact on stability of the generator oscillation damping was examined. Simulation was done in MATLAB R2023a. The generator damping ratio, total active power losses and total cost of controllers were determined. Results verified the effectiveness of hybridized model of STATCOM and SSSC controllers in improving the stability of power generator oscillation damping.

DOI: 10.61137/ijsret.vol.10.issue5.290
55

Published by:

Digital Marketing Grow in India

Uncategorized

Digital Marketing Grow in India/strong>
Authors:-Assistant Professor Tanmoy Ghosh

Abstract-Digital Marketing grow in India has seen outstanding development as of late, determined by the quick expansion in web entrance, cell phone utilization, and the computerized change across different enterprises. With more than 700 million web clients, India is one of the biggest internet based showcases universally, making a fruitful ground for organizations to use computerized promoting techniques. The multiplication of virtual entertainment stages, web crawlers, web based business, and portable applications has reshaped purchaser conduct, making computerized channels fundamental for arriving at interest groups. Factors, for example, the reception of advanced installment frameworks, the ascent of neighborhood language content, and government drives like Computerized India have additionally energized this development. Little and medium endeavors (SMEs), as well as huge organizations, are progressively putting resources into Web optimization, virtual entertainment promoting, email showcasing, and powerhouse coordinated efforts to drive commitment and deals. Also, the accessibility of reasonable information plans and the ascent of video content, especially on stages like YouTube and Instagram, have opened new open doors for advertisers. As digital marketing keeps on developing with the coordination of man-made brainpower (artificial intelligence) and information examination, organizations in India are zeroing in on customized and information driven ways to deal with upgrade their showcasing endeavors. The fate of computerized showcasing in India guarantees development, development, and a critical effect on business achievement.

DOI: 10.61137/ijsret.vol.10.issue5.289
55

Published by:

Cloud kitchen Inventory System

Uncategorized

Cloud kitchen Inventory System/strong>
Authors:-Assistant Professor Mr. Vishal Jaiswal, Ms. Bhakti Sarode, Mr. Dipesh Bobade, Ms. Nikita Chhapparghare, Ms. Shrutika Chauhan, Ms. Sneha Kolte

Abstract-Fast growth in cloud kitchens, driven by increased demand for food delivery services, is coupled with massive challenges to inventory management. Traditional inventory systems usually cannot meet dynamic requirements like those of cloud kitchens—fast-moving environments needing precise, real- time tracking of ingredients to ensure minimal wastage and resource optimization. This paper investigates how an IoT- enabled inventory management system can be implemented in a cloud kitchen setting. The system provides real-time observations of inventory levels, expiration dates, and storage conditions through the use of IoT technologies such as smart sensors, and other connected devices. It provides a holistic solution to inventory management problems within cloud kitchens since it allows for the automation of replenishment, demand prediction using data analytics, and compliance with food safety standards. The integrating technology will increase operational efficiency, generate cost savings, and sustain them by decreasing food wastage. This paper also discusses the possible challenges of IoT adoption related to data security and system integration, proposing strategies for successful implementation.

DOI: 10.61137/ijsret.vol.10.issue5.288
55

Published by:

Advanced Skin Cancer Detection using Hybrid CNN Feature Extraction

Uncategorized

Advanced Skin Cancer Detection using Hybrid CNN Feature Extraction/strong>
Authors:-Mr. S. Sinimoxon Lee, Professor Arpita Das

Abstract-Skin cancer is one of the deadliest types of cancer, with a rapidly increasing incidence worldwide. Early detection is crucial to reducing the mortality rate. In this paper, we present an effective computer-aided diagnostic model for accurate skin cancer detection and classification. Our proposed system consists of three primary steps: a) Preprocessing, b) Feature extraction, and c) Classification. During preprocessing, image quality is enhanced through median filtering. In the feature extraction phase, features are extracted from three powerful pretrained CNN models—GoogleNet, AlexNet, and ResNet-101—using transfer learning and are then combined. In the classification stage, the hybrid features are classified using three successful Machine Learning (ML) classifiers: Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN). We validated our model on 3000 images from the MNIST dataset, achieving an accuracy of 96.66%, a precision of 96.5%, a recall of 96.66%, and an F1-score of 96.5%.

DOI: 10.61137/ijsret.vol.10.issue5.287
55

Published by:

Solar- Powered Water Purification System

Uncategorized

Solar- Powered Water Purification System/strong>
Authors:-Prakalya E, Priyadharshini S M, Srilatha B

Abstract-The Solar-Powered Water Purification System provides a sustainable solution for remote areas lacking clean drinking water. Powered by solar energy, it uses advanced filtration technology to operate independently of traditional electricity sources. IoT sensors allow real-time monitoring and maintenance. Designed for portability and user-friendliness, the system is adaptable to various environments. Targeted at NGOs and rural communities, it offers a cost-effective way to improve water access, with significant health and quality of life benefits.

DOI: 10.61137/ijsret.vol.10.issue5.286
55

Published by:

Classification of Online Toxic Comments Using Machine Learning Algorithms

Uncategorized

Classification of Online Toxic Comments Using Machine Learning Algorithms/strong>
Authors:-Professor Shubhangi Chatnale, Shivai P. Gore, Rutwik J. Shetty, Soham A. Mahajan

Abstract-The increasing prevalence of toxic comments on social media necessitates efficient automated systems for content moderation. This paper presents a machine learning-based approach to classifying toxic comments, aiming to detect harmful content such as hate speech, threats, and offensive language. We evaluate various supervised learning algorithms, including logistic regression, support vector machines (SVM), random forests, and advanced deep learning models such as recurrent neural networks (RNNs) and transformer-based models like BERT. Text preprocessing techniques like tokenization and feature extraction using TF-IDF and word embeddings are applied to optimize model performance. The models are trained on large labeled datasets and evaluated using accuracy, precision, recall, and F1-score. Our results show that deep learning models, particularly transformer-based architectures, achieve superior performance in identifying toxic comments, highlighting their effectiveness in supporting content moderation on social media platforms.

DOI: 10.61137/ijsret.vol.10.issue5.285
55

Published by:
× How can I help you?