September 2025 VOLUME:11, ISSUE-3

ENGINEERING & TECHNOLOGY JOURNAL

Transforming Big Data Analysis Through Modern AI Techniques

Gyanendra K. Gautam Devendra K. Mishra

  • Pages: 1-6
    • <p>Modern techniques of AI have revolutionized the entire management, analysis, and utilization processes of big data in any company. Indeed, the problem is that Big Data puts the traditional model in danger owing to its volume, velocity, and variety. yet Artificial Intelligence, and notably machine learning and deep learning, provides a strong set of solutions for the same issues. This paper will discuss the interaction between AI and big data, where AI applications like neural networks, reinforcement learning, and NLP are recognized as advanced techniques to produce useful concepts, such as relations, trends, forecasts or actionable intelligence, from large volumes of information. Such information is processed fully with the help of AI integrated systems in such a way as to remove the need of integration, cleansing, and transforming data focusing on saving effort and time. These technologies lead to better precision and because of this, inform choices made by using predictive analytics, clustering, and classification that make them essential in industries such as marketing, banking, and healthcare. In any case, the class of Big Data is not just structured datasets since AI models may be trained on various unstructured data including text, images, video. This paper also examines the issues connected with AI in Big Data analysis, like computational resource demands, algorithm transparency, and bias in data models. It focuses how important scalable, distributed AI architectures are for managing the enormous computational demands of big data, such as edge and cloud computing.</p>

ANALYSIS OF SELF-COMPACTING CONCRETE'S STRENGTH BEHAVIOR WITH ALCCOFINE AND GGBS AS A PARTIALLY CEMENT SUBSTITUTE

Varsha rajpoot, Satish Parihar

  • Pages: 1-4
    • <p>The study investigates that alccofine and GGBS combination can be used in the SCC as the strength enhancer. SCC being a high performance concrete after the addition of alccofine, produces a high performance and high strength concrete. Mix design for SCC can be carried out by Nan-Su method which is considered as a simple mix design and the dosage of super plasticizer will be determined by trial and erroras substantial result of characteristics of fresh and hardened concrete and effect of alccofine (5%, 10%, 15% and 20%by volume) by keeping the GGBS percentage constant (30%) on rheological properties and strength properties were investigated. The improvement in behaviour of SCC is because of enhancement in union strength and pore refinement by GGBS. The outcome implies that the workability of SCC with 5% and 10% alccofine by volume of concrete leads to decline of other rheological properties given by codal provisions (EFNARC). In contrast, the improvement in properties of concrete like compressive strength from 36.6 to 42.9 N/mm2 , splitting tensile strength from 3.8 to 7.9 N/mm2 and flexural strength from 4.9 to 8.3 N/mm2 at 28 days was observed with increase in alccofine dosage. Finally, the conclusion has been drawn that alccofine and GGBS combination can be used in the SCC asthe strength enhancer.</p>

Enhance Performance of Data using Visualization Tool: A Systemic Review

Archana Acharya, Harshita Sharma , Aisha Dhakre , Nitesh K. Rathore , Satyam Agarwal

  • Pages: 1-9

    • <p>Big volumes of data are being produced every day in the world in which we live. Data visualization is a crucial component of the data-driven decisions that corporations make based on their data. Through the use of graphics and science, data visualization is a relatively new and exciting area of computer science that tells tales through data. Patterns, trends, and correlations are extracted from databases using computer graphic effects. Tableau, Google Charts, Data Wrapper, Infogram, and other tools are among the many available for data visualization on the market. With a focus on their significance in a number of domains for efficient data transfer and analysis, the study attempts to give a thorough review of data visualization tools and approaches. Furthermore, we'll serve as an example project for data visualization using tableau desktop tool. Because it makes it easier for data scientists to convey insights, make decisions, tell stories, and study data, data visualization is essential to data science too. It would be difficult to draw conclusions from large, complicated data sets and make wise judgments without data visualization. This paper focuses on the importance of data visualization, primary tools, and software for data visualization, and theoretical architectural framework for data visualization. The article's last section will address mitigating strategies for the major problems with data visualization.</p>

The Impact of Machine Learning Algorithms on Big Data Analysis

Gyanendra K. Gautam , Devendra K. Mishra

  • Pages: 1-9
    • <p>This study extends on the intricate relationship between Big Data and Machine Learning, focusing on how both novel technologies are working in synergy to provide new opportunities in various fields. Due to the ever-increasing volume, velocity, and variety of Big Data, its elements include rapidly turning into something that will need advanced tools and technologies for its processing, analysis et al and storage. Such complexities of Big Data are solved by machine Learning where powerful algorithms and learning techniques are employed to find patterns, enhance decisions and foster innovations. In this research, it is explored the background, problems, and characteristics of big data (5Vs), including the scope of machine learning, and its types like supervised, unsupervised, and reinforcement learning for assisting big data in various aspects. It follows up these technologies with real usages in health care, banking, retail, manufacturing and student telecommunication industries. The study also reviews trends that will impact the direction of Big Data and Machine Learning convergence including challenge of ethical AI, immediate overviews, and protests concerning data privacy and security, as well as expansion concerns. It also discusses some concerns related to interpretability, scalability, and diversity of data. It also provides some perspective of further investigations that may include: real time analytics, edge computing, and ethics in artificial intelligence. Finally, a tabular condemnation of the various Machine Learning techniques utilized in the setting of Big Data is provided.</p>

ARTIFICIAL INTELLIGENCE FOR PREDICTING DEVELOPMENTAL RISKS AND MENTAL HEALTH OUTCOMES IN PSYCHOLOGY

Shivangi Pathak and Daya Shankar Pandey

  • Pages: 1-13
    • <p>Certain individuals imagine that medical services and the study of brain science couldn't be more unique. The utilization of expectation stands apart as a vital differentiation between the two disciplines. The clinical and medical care enterprises can predict a person's actual wellbeing results by dissecting variables like their hereditary synthesis, level of actual work, and the food they eat. There is a little contrast among brain research and the clinical region. Clinicians succeed in expecting patients' social changes, however there are various motivations behind why emotional well-being expectations miss the mark regarding actual wellbeing forecasts. The motivation behind this exploration is to reveal insight into computer based intelligence's commitments to the investigation of brain science. In particular, the manners by which simulated intelligence might recognize burdensome side effects, as well as the manners by which ML and DL have been utilized to estimate the probability of self-destructive and selfharmful ways of behaving and psychological well-being issues in kids and youths.</p>
other Journals