Papers by Dheeraj Varun Buddula
International Journal of Emerging Trends in Computer Science and Information Technology, 2025
People are particularly conscious of their clothing choices since fashion has a big influence on ... more People are particularly conscious of their clothing choices since fashion has a big influence on daily life. Large populations are usually recommended fashion goods and trends by specialists via a manual, curated process. On the other hand, e-commerce websites greatly benefit from automatic, personalized recommendation systems, which are becoming more popular. This study introduces a deep learning-based framework for personalized fashion recommendation, utilizing the Fashion-MNIST dataset as the primary data source. The dataset was divided into training and testing sets in a 70:30 ratio to ensure robust evaluation. CNN, Feedforward Neural Networks (FNN), and LSTM models were employed for fashion item classification. Evaluation metrics such as F1-score, recall, accuracy, precision, and loss, along with confusion matrix analysis, were utilized to assess model performance. Among the tested models, the CNN demonstrated superior performance, achieving 93.99% accuracy, with F1score, recall, and precision all at 94% and a loss value of 0.2037. Comparative analysis further highlighted the CNN's effectiveness over FNN and LSTM models. These findings demonstrate the promise of CNN architectures for improving the precision and consistency of individualized clothing recommendation systems.
Universal Library of Engineering Technology, 2025
The rise of "smart cities" made possible by the IoT is revolutionizing cityscapes by boosting pub... more The rise of "smart cities" made possible by the IoT is revolutionizing cityscapes by boosting public services, maximizing the use of available resources, and generally enhancing people's quality of life. A smart city creates responsive, sustainable, and efficient settings by fusing cutting-edge IoT technology with conventional urban processes. Sensors, RFID, MQTT protocols, and Raspberry Pi devices are some of the essential technologies discussed in this article as it pertains to the IoT and its function in smart cities. Key domains such as infrastructure management, governance, transportation, energy, healthcare, waste management, and public safety are analyzed through case studies from global implementations. The study highlights major challenges, including data privacy, scalability, interoperability, and security, that hinder IoT adoption. It also explores future trends like AI, machine learning, and 5G as enablers for next-generation smart cities. By addressing these challenges and leveraging advanced technologies, IoT can pave the way for sustainable urban growth and a citizen-centric approach to urban development. Future trends in IoT, including an integration of AI, ML, and 5G, are also explored as enablers for the next generation of smart cities.
INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN MULTIDISCIPLINARY EDUCATION, 2024
Real-time cyber threat identification and mitigation depend heavily on intrusion detection system... more Real-time cyber threat identification and mitigation depend heavily on intrusion detection systems (IDS) for secure networks. Network systems utilize analysis to spot malicious events unauthorized access and system vulnerabilities in network traffic. Machine learning forms the foundation of these security implementations. Through improved network security measures, IDS protect business assets by ensuring both data availability and uncompromised security. After enhancing the effectiveness of intrusion detection, this study suggests a strong method based on DL. A CNN model is developed and evaluated against traditional models, including KNN, Autoencoders (AE), and DNN that are trained on the NSL-KDD dataset. CNN delivers remarkable performance when used in network threat detection with success metrics of 98.63% accuracy alongside 98.45% precision, 98.98% recall, and an F1-score of 98.72%, proving its efficiency for threat recognition. Visualization and comparative performance analysis further prove the model's effectiveness, paving the way for its possible use in safe network settings. The benefits of using DL frameworks to improve IDS systems are highlighted in this paper.
INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN MULTIDISCIPLINARY EDUCATION , 2024
Automation, optimization, and enhanced decision-making are just a few ways artificial intelligenc... more Automation, optimization, and enhanced decision-making are just a few ways artificial intelligence (AI) changes the game across several sectors. Its applications extend across diverse fields, including healthcare, transportation, finance, education, and software engineering. This study explores the integration of AI in software engineering, highlighting its transformative role in streamlining development workflows, improving software quality, and fostering collaboration between technical and non-technical stakeholders. The rise of no-code and low-code platforms has democratized access to AI, allowing users with limited technical expertise to implement AI-powered solutions like NLP and predictive analytics. Key benefits of AI in software development include automation of repetitive tasks, early bug detection, efficient project management, and personalized user experiences. The study also discusses the current trends in AI integration, including ML, NLP, robotics, and explainable AI, while addressing the challenges. Furthermore, AI tools for software development demonstrate their impact on education and skill development. Finally, the paper explores prospects in AI-driven software development. By analyzing the current and future trends, this study provides insights into how AI can shape the next generation of software development.
JOETSR-Journal of Emerging Trends in Scientific Research, 2023
E-commerce follows a revolution thanks to predictive analytics technology and machine learning be... more E-commerce follows a revolution thanks to predictive analytics technology and machine learning because it enhances operational effectiveness and corporate performance through data-driven decision-making. The research examines the application of individualized marketing methodologies for behavior analysis of consumers that produces more accurate sales predictions through analytical techniques. The research presents an analysis of three primary machine-learning techniques: logistic regression, random forests, and deep learning models. The techniques measure their prediction abilities in setting prices detecting fraud and assessing market demand. The market advantages for e-commerce companies include enhanced operational processes by predictive modelling AI, lowered risks, and the creation of personalized experiences for consumers. E-commerce progress in this field faces multiple challenges especially because of data quality issues and complex predictive model interpretation processes as well as requirements for large computational capabilities. E-commerce businesses use predictive analytics as their essential strategic tool to gain market advantages through data-driven operations and make more accurate choices while the market becomes data-first
JOETSR-Journal of Emerging Trends in Scientific Research, 2023
The advent of edge computing has been revolutionary in improving data processing efficiency and r... more The advent of edge computing has been revolutionary in improving data processing efficiency and reducing latency in IoT networks. By decentralizing computational tasks, edge computing enables real-time analytics and scalability while reducing reliance on centralized cloud infrastructures. This paper explores advanced frameworks, including hierarchical and decentralized architectures, that integrate AI and machine learning to enhance predictive optimization and resource management. It also addresses challenges such as protocol compatibility, energy efficiency, and operational complexities. The review provides insights into current advancements and identifies future opportunities for improving IoT network performance and supporting latency-sensitive applications like smart cities and industrial automation.
International Journal of Engineering, Science and Mathematics , 2021
Sentimental analysis is a crucial method for opinion mining in light of the ever expanding reach ... more Sentimental analysis is a crucial method for opinion mining in light of the ever expanding reach of social media and the Internet. Recently research work describing the performance of some common methods for determining an individual's emotional state, ranging from basic lexicon-and rule-based approaches to deep learning algorithms. In this study, an Artificial Neural Network (ANN) model for sentiment classification on a Twitter dataset with various data preprocessing, feature extraction using TF-IDF and word embeddings as well as performance evaluation. It is observed that the ANN model surpasses Naïve Bayes (95.98% accuracy) and K-Nearest Neighbors (88.80% accuracy) on all evaluation metrics, accomplishing an improvement in accuracy (97.59%), precision (97.79%), recall (98.64%), and F1 score (97.45%). ANN model is fairly effective in capturing complex sentiment patterns using TFIDF and embedding features, has high classification accuracy and overfitting is modest, therefore leading to strong generalization to new data. These findings validate ANN as a suitable tool for decision-making based on sentiments to enhance marketing, customer engagement and brand reputation management.
Scientific Publications, 2021
Crime is a serious and widespread problem in their society, thus preventing it is essential. Assi... more Crime is a serious and widespread problem in their society, thus preventing it is essential. Assignment. A significant number of crimes are committed every day. One tool for dealing with model crime is data mining. Crimes are costly to society in many ways, and they are also a major source of frustration for its members. A major area of machine learning research is crime detection. This paper analyzes crime prediction and classification using data mining techniques on a crime dataset spanning 2006 to 2016. This approach begins with cleaning and extracting features from raw data for data preparation. Then, machine learning and deep learning models, including RNN-LSTM, ARIMA, and Linear Regression, are applied. The performance of these models is evaluated using metrics like Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). The RNN-LSTM model achieved the lowest RMSE of 18.42, demonstrating superior predictive accuracy among the evaluated models. Data visualization techniques further unveiled crime patterns, offering actionable insights to prevent crime.
International Journal of Advanced Research in IT and Engineering, 2021
In the fiercely competitive retail industry, satisfying consumer expectations while optimizing co... more In the fiercely competitive retail industry, satisfying consumer expectations while optimizing company processes is more important than ever. Therefore, it is crucial to handle and channel data in a way that both seeks to delight consumers and generates healthy revenues if you want to survive and prosper. Data-or more specifically, Big data analytics is being utilized by large retailers at every stage of the process, participants in the global and Indian retail markets, including tracking new, popular items and predicting sales. The use of machine learning classification approaches for sentiment analysis in online shopping is examined in this research, utilizing a publicly available Amazon review dataset. The text-cleaning techniques processed the dataset before converting texts into numerical representations by implementing TF-IDF measures. The assessment concentrated on the three machine learning models' F1-score, accuracy, and precision-recall: Bidirectional Encoder Representations from Transformers (BERT), Support Vector Machine (SVM), and Gradient Boosting (GB). BERT ended up outperforming all other models by demonstrating 89% accuracy, which proves its extraordinary capability to detect customer sentiments. The research results show how transformer-based models work for improving sentiment analysis procedures in marketing analytics applications.
International Journal of Research in Engineering and Applied Sciences (IJREAS), 2021
The rapid advancements in Artificial Intelligence (AI) have led to significant transformations ac... more The rapid advancements in Artificial Intelligence (AI) have led to significant transformations across various fields, with software development and cybersecurity being two key areas of profound impact. Software development, testing, and maintenance are being completely transformed by artificial intelligence (AI), namely through machine learning deep learning, and natural language processing. It automates repetitive tasks, enhances decision-making processes, and accelerates development cycles, thus driving efficiency in the software industry. AI has emerged as a crucial weapon in the fight against changing cyberthreats in the field of cybersecurity. Patterns are found using AI algorithms, identify vulnerabilities, and predict potential attacks, providing a more proactive approach to security than traditional methods. Despite its potential, the integration of AI into software development and cybersecurity poses challenges such as data privacy concerns, ethical implications, and the need for specialized skills. The revolutionary significance of AI in cybersecurity and software development is examined in this research, highlighting the benefits, challenges to further leverage AI's capabilities in these domains.
INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN MULTIDISCIPLINARY EDUCATION, 2024
Platforms and movie theatres provide a large range of movies that need to be filtered to each use... more Platforms and movie theatres provide a large range of movies that need to be filtered to each user's tastes. For this objective, recommender systems are a useful tool. This research presents a novel hybrid recommender system for personalized movie suggestions, which integrates content-based methods with collaborative filtering. This study develops a personalized movie recommendation system utilizing the MovieLens 1M dataset, comprising user ratings for a diverse set of movies. The research data undergoes separation into training segments that constitute 80% of the total sample while testing comprises 20% of the data. The evaluation framework incorporates multiple metrics which include F1-Score together with Precision and Root Mean Square Error (RMSE) as well as Mean Absolute Error (MAE) alongside Recall. A Multilayer Perceptron (MLP) model is employed for movie recommendations and compared to a Deep Neural Network (DNN). The outcomes show that a MLP model outperforms the DNN, achieving a lower RMSE of 0.99 and an MAE of 0.80, in contrast to the DNN's RMSE of 1.011 and MAE of 73.5. The training and validation loss trajectories show continuous progress and maintain minimal avoidable patterns. Future work will refine the model accuracy by performing hyperparameter tweaking and developing advanced feature extraction processes together with implementing distinct deep learning models for enhanced recommendation capability and user satisfaction.
IJASTR- International Journal of Applied Science and Technical Research, 2024
Companies rely on data-driven insights to improve decision-making and reduce uncertainty in the i... more Companies rely on data-driven insights to improve decision-making and reduce uncertainty in the insurance industry, where risk management is an essential aspect of operations. This study delves into the revolutionary effects of analytics in risk management via the use of cutting-edge technologies like automation, AI, and predictive modelling. It examines various data sources, including internal, external, third-party, and sensor data, to assess their influence on risk identification, classification, and mitigation strategies. The study highlights the significance of emerging technologies such as robotic process automation (RPA), AI-powered chatbots, blockchain, and cloud computing in optimizing underwriting processes, claims management, and fraud detection. Additionally, it discusses how analytics-driven strategies contribute to business agility by enabling real-time decision-making, improving operational efficiency, and fostering adaptability in a rapidly evolving digital landscape. Furthermore, the paper addresses key challenges in implementing analytics, including data quality, integration, accessibility, and security concerns, which can impact the effectiveness of risk management frameworks. The study concludes by proposing future research directions focused on enhancing AI-driven risk assessment models, improving data governance, and exploring innovative approaches to regulatory compliance in risk management.
IJASTR- International Journal of Applied Science and Technical Research, 2024
The entry of Artificial Intelligence into e-learning platforms has drastically changed the method... more The entry of Artificial Intelligence into e-learning platforms has drastically changed the method of providing and experiencing education. In the present context, where educational institutions and organizations strive to offer more personalized, adaptive, and engaging learning environments, Artificial Intelligence (AI) technologies have come into being, which can help both. The efficacy and efficiency of educational procedures. Artificial Intelligence (AI) through Natural Language Processing (NLP), Learning Analytics (LA), and Educational Data Mining (EDM) are used to customize learning with tailored learning paths to meet the needs of each student in this study as to how AI is changing e-learning systems. AI looks at student behaviors, particularly the learning patterns and performance data, and makes real-time changes to the content, assessments and feedback that help improve engagement and retention. Furthermore, the study also looks at the problems and ethical issues of its use in education on the large scale as it can bring issues related to the data privacy, algorithmic fairness and the idea of the erasure of the human part of the teacher. This paper also discusses emerging trends and future research directions on AI-powered e-learning, focusing on creating an inclusive, scalable, and human-centered approach for the technology to work with and for the pedagogical goals. In the end, these innovative practices are meant to contribute to growing AI research literature on how AI can fundamentally alter the ways teaching is done and how learning can occur in the future.
INTERNATIONAL JOURNAL OF INNOVATION IN ENGINEERING RESEARCH & MANAGEMENT, 2022
One of the biggest problems for big businesses is customer attrition. Since consumers are the pri... more One of the biggest problems for big businesses is customer attrition. Since consumers are the primary source of income for businesses in the rental industry, they are specifically searching for strategies to keep them as clients. This study presents the data driven machine learning technique for telecom sector churn prediction, addressing challenges of noisy, imbalanced, and high-dimensional data through a comprehensive preprocessing pipeline that includes noise removal, SMOTE-based balancing, feature selection, and outlier detection. In order to create predictive models using Decision Trees and Random Forest classifiers, the preprocessed data-which consists of 3,333 customer records with attributes ranging from call metrics to charge information-is separated into training and testing sets. When measured using measures like accuracy, precision, recall, F1-score, and ROC analysis, the Decision Tree model performed better than other models like ANN and SVM, achieving 88% accuracy, 83% precision, 93% recall, and 88% F1-score. These outcomes show how the approach may produce useful insights for improving customer retention and marketing strategy optimization in changing telecom contexts.
ACCENT JOURNAL OF ECONOMICS ECOLOGY & ENGINEERING, 2022
The rapid proliferation of Internet of Things (IoT) Devices has made cybersecurity more difficult... more The rapid proliferation of Internet of Things (IoT) Devices has made cybersecurity more difficult, requiring strong security frameworks to safeguard private information and maintain system integrity. Conventional security solutions usually fall short of the dynamic and ever-evolving nature of cyber threats that target IoT ecosystems. This paper explores advanced security strategies, including artificial intelligence (AI)-driven threat detection, blockchain-based authentication, and post-quantum cryptographic algorithms, to enhance IoT security and their ecosystem. It also emphasizes the necessity of standardized regulatory frameworks to harmony security techniques worldwide and the significance of lightweight security solutions designed for IoT devices with limited resources. In order to reduce risks and promote a more secure IoT environment, the study highlights the need for awareness and training. To ensure that IoT infrastructures are resilient, future research will concentrate on improving security procedures to adjust to new threats and technological developments.
INTERNATIONAL JOURNAL OF INNOVATION IN ENGINEERING RESEARCH & MANAGEMENT ISSN: 2348-4918, 2022
The difficulty in managing and controlling supply networks is exacerbated by their glo... more The difficulty in managing and controlling supply networks is exacerbated by their globalization. Blockchain, a decentralized digital ledger technology, has the power to improve global supply chain management by making it more transparent, traceable, and secure. This paper explores the amazing potential of blockchain technology in logistics and supply chain management (SCM), particularly in regards to its capacity to enhance trust, transparency, and traceability. Blockchain offers a distributed and immutable record that guarantees safe transactions and real-time monitoring, in contrast to conventional supply chains that encounter problems including data sharing, fraud, and a lack of responsibility. The paper discusses the integration of blockchain with key supply chain entities, including registrars, certifiers, and standards organizations, and highlights its role in automating processes through smart contracts and IoT integration. Despite its promising benefits, the paper identifies several challenges, including system integration, scalability, data privacy, and regulatory uncertainties, and suggests future research directions to overcome these barriers. The study aims to advance the understanding of blockchain applications in SCM and provide insights for developing efficient, resilient supply chain networks. Keywords: Blockchain Technology, Logistics, Supply Chain, Transparency, Accountability, Smart Contracts, Blockchain Integration.
ACCENT JOURNAL OF ECONOMICS ECOLOGY & ENGINEERING, 2022
Blockchain technology functions as a security solution at the advanced level because ... more Blockchain technology functions as a security solution at the advanced level because its decentralized system along with cryptographic security measures and immutable data storage work together. Blockchain technology reduces security risks because it operates differently from centralized authorities thus protecting against solitary weak points unauthorized data modification and identity theft. The technology handles three main domains including secure communication and identity management with fraud prevention functions which improve data trustworthiness between digital senders and recipients. The widespread adoption of blockchain systems is impeded because they currently deal with scalability problems along with government standards and control regulation needs. The research investigates blockchain's capabilities together with its security boundaries in addition to its preventive measures against contemporary cyber-attacks. The paper explores smart contracts while identifying secure identity frameworks for controlling decentralized access mechanisms. This paper examines blockchain capabilities through strength versus weakness evaluation to explain how blockchain will transform security infrastructure while presenting solutions to current issues.
Uploads
Papers by Dheeraj Varun Buddula