In the rapidly evolving landscape of computer applications and engineering, the integration of machine learning (ML) and data science has emerged as a transformative force in optimizing decision-making processes. This paper explores the synergetic convergence of these domains, emphasizing their potential to enhance efficiency, accuracy, and scalability in computational systems. As engineering challenges become increasingly complex, the ability to process and analyze vast, high-dimensional datasets in real-time is critical. Machine learning algorithms, when effectively harnessed through the analytical rigor of data science, enable predictive insights and adaptive systems capable of autonomous learning and continual improvement. The study investigates how ML techniques—ranging from supervised learning models like decision trees and support vector machines to unsupervised methods such as clustering and dimensionality reduction—can be applied to diverse engineering domains including structural analysis, signal processing, network optimization, and intelligent automation. Simultaneously, it assesses the role of data science workflows—comprising data acquisition, cleaning, transformation, and visualization—in providing a robust foundation for these ML models to perform optimally. Through case-driven illustrations, the paper highlights scenarios where integrated frameworks have led to significant performance enhancements, such as predictive maintenance in manufacturing, energy-efficient routing in communication networks, and adaptive control in robotics. Furthermore, the research addresses the computational and ethical challenges associated with such integrations, including data sparsity, model interpretability, and decision accountability. The need for explainable AI (XAI) is underscored, especially in critical systems where decision-making transparency is essential for regulatory and safety compliance. The paper also evaluates the effectiveness of hybrid models that combine domain-specific knowledge with data-driven learning to overcome the limitations of traditional engineering heuristics. Ultimately, the research advocates for a paradigm shift wherein machine learning and data science are not viewed as supplementary tools, but as integral components of modern engineering decision architectures. This interdisciplinary approach fosters not only technical innovation but also informed, agile, and sustainable problem-solving methodologies. By systematically unpacking the theoretical foundations and practical implications of this integration, the study contributes to the evolving discourse on intelligent systems design, offering valuable guidance for researchers, engineers, and decision-makers committed to advancing the frontiers of computational engineering.

Blockchain technology is rapidly becoming one of the most groundbreaking technologies for revolutionizing supply chain management with unprecedented security, transparency, and efficiency. This paper presents a comprehensive literature review of blockchain and its applications in leading industries such as transportation, manufacturing, food and beverage, and healthcare. Blockchain applies distributed ledger technology to secure tamper-evident record-keeping, which significantly enhances traceability and provenance verification across complex supply chains. By integrating smart contracts, IoT connectivity, and decentralized financial services, blockchain can solve significant challenges, such as counterfeiting, supplier management, and enforcing sustainable and responsible sourcing practices. Despite these benefits, the mass-scale adoption of blockchain faces serious challenges, such as scalability, interoperability, regulatory ambiguity, and a lack of standardized frameworks. The report also addresses the environmental concerns of blockchain’s power-intensive proof-of-work algorithm and discusses ways to counteract them. Future developments in artificial intelligence and 5G networks will continue to evolve supply chain management in ways that unleash unmatched efficiency and potential.

As the globe struggles to recover from COVID-19, the monkeypox virus has emerged as a new global pandemic threat. Monkeypox cases are still being reported daily from different nations despite the virus not being as harmful or contagious as COVID-19. As a result, the possibility of another worldwide pandemic occurring directly due to a lack of adequate preventative measures will not come as a complete shock to everyone. Diagnosing Monkeypox in its early stages may be challenging because it resembles chickenpox and measles. When confirmatory Polymerase Chain Reaction assays are not readily available, monitoring suspected cases and swiftly detecting them may be possible with computer-assisted detection of monkeypox lesions. Recent research has shown that deep learning models have significant promise for image-based diagnostics, including cancer diagnosis, identifying tumor cells, and detecting COVID-19 patients. To address these challenges, we built a deep learning model based on transfer learning that can assist medical professionals and other individuals in determining whether they are suffering from Monkeypox. The InceptionV3 model utilized in this study was trained with the publicly accessible Monkeypox dataset. During the studies, the model attained an accuracy of 98%.

The integration of Blockchain and Machine Learning (ML) technologies offers a transformative approach to combating fraud across various sectors, including finance, healthcare, and cybersecurity. Blockchain's decentralized and immutable nature ensures data integrity and transparency, while Machine Learning algorithms enable the detection of intricate fraud patterns through predictive analytics and anomaly detection. This synergistic combination provides a robust mechanism for identifying fraudulent activities in real time, minimizing human error, and optimizing decision-making processes. In the financial sector, Blockchain enhances the security and transparency of transactions, while ML models analyze transaction data to identify unusual patterns that may indicate fraud. In healthcare, Blockchain ensures the secure sharing of medical records, and ML assists in detecting fraudulent claims and potential identity theft. Cybersecurity applications leverage Blockchain for secure communication and data storage, with ML identifying potential threats or vulnerabilities. By combining these two cutting-edge technologies, organizations can strengthen their fraud detection systems, improve trust, and mitigate the risks associated with financial losses, data breaches, and privacy violations. This paper explores the multidisciplinary synergy of Blockchain and ML, illustrating their potential to revolutionize fraud detection mechanisms across multiple domains, providing a comprehensive overview of current advancements, challenges, and future directions for their integration in the fight against fraud.

The research on sentiment analysis has shown a great deal of utility in the field of public health, specifically in the investigation of infectious illnesses. As the world begins to recuperate from the devastating effects of the COVID-19 pandemic, there is a growing concern that a different pandemic, known as Monkeypox, may strike the world once more. The contagious illness known as Monkeypox has been documented in over 73 countries worldwide. This unexpected epidemic has become a significant cause of anxiety for many people and health authorities. Various social media platforms have presented various perspectives regarding the monkeypox epidemic. Our goal is to research how the public feels about the recent Monkeypox epidemic to assist policymakers in developing a deeper comprehension of how the public views the illness. This research uses a CNN-LSTM-based hybrid architecture to ascertain people's feelings regarding Monkeypox disease. A series of experiments were conducted on an open-access dataset of tweets related to the Monkeypox. The tweets undergo various pre-processing, global vectorization, and one-hot encoding techniques. According to the findings of our experiments, the hybrid model provided better accuracy, which was approximately 91%. In addition, the findings are validated by contrasting them with more conventional machine learning techniques. The outcomes of this investigation contribute to a general population that has a greater awareness of the Monkeypox infection.

Aims: To study the different levels of doses and time applications of topramezone on weed, growth and yield of chickpea (Cicer arietinum L.) in Bihar. Place and Duration of Study: Agronomy research farm of Tirhut College of Agriculture, Dholi, Muzaffarpur (Bihar), during the rabi 2020-21. Methodology: The experiment was carried out in an RBD design with three replications and ten treatments: topramezone (20.6 and 25.7 g/ha) applied at 14, 21, and 28 DAS, and quizalofop-p-ethyl (100 g/ha) applied at 25 DAS as post-emergence (PoE), pre-emergence (PE) application of valor 1000 g/ha + one hand weeding (HW) at 30 DAS, weed-free control (WFC), and weedy check. Results: PE application of valor 1000 g/ha + one HW 30 DAS recorded maximum plant height, number of branches/plants, plant dry matter, seed and straw yield while registered lowest weed dry weight and WCE as compared to all other herbicide treatments. Among all PoE-treated treatments, spray of topramezone (25.7 g/ha) after 21 days of sowing recorded maximum of all these growth parameters at harvest and lowest weed dry matter and highest WCE as compared to other PoE applications.

Sentiment analysis has become a precious tool for businesses because it can be used in so many ways: to find out what customers think about products and services, to build customer relationships and loyalty, to improve customer service, and to use emotional marketing. Over the last several years, developing an end-to-end image sentiment analysis approach has significantly emphasized transfer learning methods. Deep learning algorithms have been proven to achieve remarkable outcomes across a broad spectrum of applications. Examining feelings conveyed by images is complex, but there is much space for development. A technique known as Inception-v3 that can readily focus on large portions of the body, such as a person's face, offers a significant advantage compared to the work that was done in the past. This study makes use of Inception-v3, which is a well-known deep convolutional neural network, in addition to extra deep characteristics, to increase the performance of image categorization. A CNN-based Inception-v3 architecture is employed for emotion detection and classification. The datasets CK+, FER2013, and JAFFE are used in this process. The findings are also compared with various well-known machine learning approaches, and the results obtained by the suggested model are superior. The research indicates that the proposed method can reach an accuracy level of 99.5%. The proposed approach can be used in many business applications such as Information Management, Sales, Marketing, User Interaction, Healthcare, Education, Finance, Public Monitoring, Digital PR, etc.

Crypto currencies are one kind of digital currencies that resembles the stock market and operate on a block chain database. A bitcoin is an earliest form of crypto currency and due to its erratic price trends, the market is unstable. Similar to the stock market, bitcoin provides investment opportunities. But due to its volatility, investors find it difficult to invest. A user-friendly interface is used for predicting the price of bitcoin using several algorithms. Hence, to forecast the price of bitcoin, we apply a variety of machine learning (ML) algorithms during this research. The set of algorithms are SVM, Bayesian regression, Random Forest and boosting ensemble, ARIMA, Multilayer LSTM and GRU model. By comparing the resulting values of RMSE, we will establish the most successful method for the prediction of price of bitcoin.

There has been a recent shift from using text-based sentiment analysis in favor of an image-based method. In recent years, transfer learning methods have been widely utilized in developing a comprehensive image sentiment analysis approach. Deep learning algorithms have produced remarkable outcomes in a variety of contexts. Image-based sentiment analysis presents many difficulties, but there also appears to be much space for development. A significant improvement over prior work is provided by an InceptionV3 approach that can easily focus on huge body portions like a human face. This research improves image categorization performance with InceptionV3, a popular deep convolutional neural network, and other deep features. Using a Convolutional Neural Network based on InceptionV3 architecture, we identify and classify emotions using the famous CK + , FER2013, and JAFFE datasets. Experiments reveal that the proposed model achieves 99.5

eXplainable Artificial Intelligence (XAI) has attracted researchers in various domains over the last few years. Explainable AI includes the explainability in the AI systems which capable of explaining their decisions. This study performs a systematic literature review on XAI. In the first phase, we collected 78 high-quality web of science research journal papers from the Scopus data. It revealed that IEEE access and Expert systems with applications are the main targeted journals for researchers for XAI. Our study applies an Apriori algorithm and network analysis to get the dominant theme and check the connectivity among the methods/techniques respectively. The analysis showed that Robotics, Financial Services, Healthcare, Banking, Security, and business are the most dominant areas where XAI provides an explainability to the artificial intelligence (AI) systems. Based on our analysis, this literature review provides a future direction for researchers, academicians, and industrialists.

COVID-19 is a contagious disease that continues to be a scourge in the developing world. Chest radiology has also been proven useful for detecting abnormalities in patients’ lungs. Motivated by this, our methods propose a quick and automated detection system based on deep learning as a secondary COVID-19 diagnosis option. An imbalanced chest X-ray dataset called the COVID-Xray-5k dataset, containing X-ray scans of subjects diagnosed with COVID-19 and healthy individuals, has been used in the investigation. Transfer learning was used with VGG16 and VGG19, and then CNN model structures were proposed and parameters were tuned. One of the proposed CNN models classifies the test dataset with an F1 score of 0.91 and an accuracy of 99.45%. Proposed methods could also help with basic COVID-19 variant identification as long as a large enough dataset is given, even if it isn't balanced. To diagnose COVID-19, a proposal of two novel deep-learning sequential architectures, both of which are based on the conventional methods of convolutional neural networks.Employing machine learning to investigate subjective feature engineering and transfer learning was used for VGG16 and VGG19, with and without weighted sampling, to reliably classify COVID-19.The whole investigation supports dealing with an imbalanced dataset.

With the arrival of the current digital era and the advancement of information transmission technologies, there has been an unprecedented rise in data. Efficient extraction of useful information from the volumes of data has garnered growing interest from academics and the industry. Data mining research focuses on finding utility patterns in large datasets. But the inherent complications like frequent scans, creation of substantial candidate sets, etc. plague the mining process for large datasets. Distributive architecture-based approaches also prove inefficacious due to high communication overhead over iterations. High communication cost over data exchange both locally and remotely further aggravates the situation. We propose a Communication Cost Effective Utility-based Pattern Mining (CEUPM) algorithm based on the Spark framework to address this issue. Spark accelerates iterative scanning by storing scanned datasets in a memory abstraction called resilient distributed datasets (RDD). RDD operations need a redistribution of data among cluster nodes during processing. To minimize the communication cost incurred during the shuffle process, we adopt a search space division strategy based on data parallelism for a fair and effective task allocation across cluster nodes. Communication overhead is incurred during this redistribution or shuffle process while minimizing costs. Experimental results in four real datasets demonstrate that CEUPM considerably reduces shuffling overhead and outperforms other existing methods in terms of memory usage, communication cost, execution time, and scalability.

Atmospheric ozone (O3) concentration is impacted by a number of factors, such as the amount of solar radiation, the composition of nitrogen oxides (NOx) and hydrocarbons, the transport of pollutants and the amount of particulate matter in the atmosphere. The oxidative potential of the atmosphere and the formation of secondary organic aerosols (SOAs) as a result of atmospheric oxidation are influenced by the prevalent O3 concentration. The formation of secondary aerosols from O3 depends on several meteorological, environmental and chemical factors. The relationship between PM2.5 and O3 in different urban environmental regimes of India is investigated in this study during the summer and winter seasons. A relationship between PM2.5 and O3 has been established for many meteorological and chemical variables, such as RH, WS, T and NOx, for the selected study locations. During the winter season, the correlation between PM2.5 and O3 was found to be negative for Delhi and Bengaluru, whereas it was positive in Ahmedabad. The city of Bengaluru was seen to have a positive correlation between PM2.5 and O3 during summer, coinciding with the transport of marine air masses with high RH and low wind speed (as evident from FLEXPART simulations), leading to the formation of SOAs. Further, O3 concentrations are predicted using a Recurrent Neural Network (RNN) model based on the relation obtained between PM2.5 and O3 for the summer season using NOx, T, RH, WS and PM2.5 as inputs.

Sentiment identification on facial expression is an interesting study domain with applications in various disciplines, including security, health, and human-machine interfaces. The main goal of sentiment analysis is to decide an individual’s perspective on a topic or the document’s overall contextual polarity. In nonverbal communication, sentiment analysis plays a vital role in an individual’s feelings, reflecting on the faces. Researchers in this area are interested in improving models and methods and extracting various characteristics to provide a better computer prediction of sentiments. Sentiment polarities are mainly classified as positive, negative, and neutral. Many sentiment analysis approaches exist, but deep learning architectures can handle extensive data and provide better performances. We presented a solution based on the CNN (Convolutional Neural Network) model for handling this problem. This work uses the extended Cohn Kanade (CK+) and FER-2013 datasets for facial expression recognition study. Several existing architectures are used to evaluate the efficiency of the proposed model. Extensive experiments are carried out on both CK+ and FER-2013 data sets, and our framework outperforms state-of-the-art techniques. According to obtained results, the CNN3 model gives 79% and 95% accuracy for FER-2013 and CK+ datasets, respectively.

People have recently begun communicating their thoughts and viewpoints through user-generated multimedia material on social networking websites. This information can be images, text, videos, or audio. With the help of knowledge graphs, it is possible to extract organized knowledge from texts and images to aid in semantic analysis. Recent years have seen a rise in the frequency of occurrence of this pattern. Twitter is one of the most extensively utilized social media sites, and it is also one of the finest locations to get a sense of how people feel about events that are linked to the Monkeypox sickness. This is because tweets on Twitter are shortened and often updated, both of which contribute to the platform’s character. The fundamental objective of this study is to get a deeper comprehension of the diverse range of reactions people have in response to the presence of this condition. This study focuses on determining what individuals think about monkeypox illnesses, presenting a hybrid technique based on Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM). We have considered all three possible polarities of a user’s tweet: positive, negative, and neutral. Knowledge graphs are embedded in various healthcare applications to provide improved data representation and knowledge inference, and they have been shown to be helpful in healthcare analytics. We describe in this study a knowledge graph of related events based on Twitter data, which provides a real-time and eventful source of new information. The recommended model’s accuracy was 94% on the monkeypox tweet dataset. Other performance metrics such as accuracy, recall, and F1-score were utilized to test our models and results in the most time and resource-effective manner. The findings are then compared to more traditional approaches to machine learning. In addition, the ability to recognize semantic information has been built into the use of knowledge graphs. The findings of this research contribute to an increased awareness of monkeypox infection in the general population.

Indian tourism is the fastest-growing section of tourism; thus, the research of it is reasonable. This study examines the Indian tourism trends by examining the tweets on the social media Website Twitter. Twitter is a massive platform for sharing ideas all over the world. A total of 7, 91, 804 tweets were identified after removing the extra and non-related tweets from the downloaded tweets. When tourists visit any place, they often share their experience regarding service encounters at the destination on the social media platform. In this study, we endeavor to find out the sentiment and theme of discussions over social media by using sentiment analysis and topic modeling techniques. For sentiment analysis, we divided India into five zones (north, west, east, south, and north-east). Our findings show that overall tourists are enjoying their visits to the destination. However, east and north-east zones of India are facing some negativity. The Indian Government, service providers, and stakeholders can use these findings to do future planning for Indian tourism growth.

In practical scenarios, an entity presence can depend on existence probability instead of binary situations of present or absent. This is certainly relevant for information taken in an experimental setting or with instruments, devices, and faulty methods. High-utility patterns mining (HUPM) is a collection of approaches for detecting patterns in transaction records that take into account both object count and profitability. HUPM algorithms, on the other hand, can only handle accurate data, despite the fact that extensive data obtained in real-world applications via experimental observations or sensors are frequently uncertain. To uncover interesting patterns in an inherent uncertain collection, potential high-utility pattern mining (PHUPM) is developed. This paper proposes a Spark-based potential interesting pattern mining solution to work with large amounts of uncertain data. The suggested technique effectively discovers patterns using the probability-utility-list structure. One of our highest priorities is to improve execution time while increasing parallelization and distribution of all workloads. In-depth test findings on both real and simulated databases reveal that the proposed method performs well in a Spark framework with large data collections.