ICAIMCS-PROCEEDING

Synthesis, Characterization and Antibacterial Evaluation of New 2-Methoxynicotinonitrile Analogues

Authors- S. N. Lakhekar, G. B. Rahatikar, B. D. Kalyankar, Seema Habib, A.V. Chakinarpuwar, U.K. Warghane, T. E. Khatke, M. A. Baseer

Abstract- – The new series of 2-methoxynicotinonitrile derivatives (solid) were prepared from mixture of Chalcones (solid) (0.001 mol) (1a-i), malononitrile (liquid) (0.078 ml) (0.001 mol) and 0.040 mg (0.001 mol) of sodium hydroxide in methanol (15ml) as a solvent by reflux technique for 7-8 hours at 80oC. all the newly synthesized compounds were evaluated for their antibacterial action in vitro against gram +ve bacteria S. aureus, B. subtilis and gram -ve bacteria P. aeruginosa, E. coli by agar well diffusion method. The tested compounds (2a) presented excellent and good antibacterial activity against P. aeruginosa and E. coli respectively. (2b) presented excellent and good antibacterial activity against B. subtilis and S. aureus, P. aeruginosa respectively. (2d) showed excellent activity against S. aureus. (2e) showed good antibacterial activity against B. subtilis w.r.t penicillin as a std. drug. The chemical structures of the compounds were proved by IR, 1H NMR, Mass, C13 NMR spectrometric data.

Some Novel Applications of AI in Chemical Sciences

Authors- Mr.Pradeep R.Totawar (Assist.Prof.), Mr.Vijay B.Rathod (Assist. Prof.)

Abstract- – Artificial Intelligence (AI) is revolutionizing chemical science and presents numerous opportunities to accelerate research, improve procedures, and improve the accuracy of various chemical applications. This study looks at how digital chemistry came to be and how it developed. It focuses on how artificial intelligence (AI) helped make big changes in chemical science and take it to a new level of development. The top twenty AI-driven technologies are the primary focus of the analysis. It emphasizes the incorporation of digital tools such as machine learning, big data, digital twins, the Internet of Things, robotic platforms, intelligent management of chemical processes, virtual reality, and blockchain, among many others, in improving research methodologies, educational strategies, and industrial applications in the field of chemistry. The significance of this study lies in its focused overview of how these digital innovations foster a more efficient, sustainable, and innovative future in chemical sciences.

Mathematical Framework for Analyzing Quinoline: Applications of Graph Theory in Medicinal Chemistry

Authors- Assistant Professor O. K. Berdewad, Assistant Professor V. A. Jadhav, Assistant Professor G. D. Kottapalle

Abstract- – This research employs molecular graph theory to investigate the structural and chemical characteristics of quinoline molecules. In this approach, quinoline is represented as a planar graph, with atoms as vertices and bonds as edges. The molecular graph of quinoline is constructed, and topological indices, including the Randic index (4.801), are calculated to elucidate structural features. These topological indices function as descriptors in quantitative structure–activity relationship (QSAR) and quantitative structure–property relationship (QSPR) models [1], providing insights into quinoline’s chemical behavior and biological activities, such as antibacterial, antifungal, and antimalarial properties. The molecular graph representation underscores quinoline’s electronic properties, influenced by its dense atomic arrangement and minimal vertex degree variation, facilitating efficient electron transport. This study illustrates how molecular graph theory links structural features to chemical and biological properties, highlighting the significance of topological methods in contemporary chemistry.

Graph Theory Application in Heterocyclic Chemistry: Advancing Molecular Analysis and Drug Discovery

Authors- Assistant Professor Berdewd O.K, Assistant Professor Tiwde S.S, Assistant Professor Dr. Kottapalle G.D

Abstract- – Graph theory has emerged as a potent analytical tool for examining heterocyclic compounds, which hold significant importance in the fields of pharmaceuticals, agrochemicals, and materials science. This study investigates the confluence of graph theory and heterocyclic chemistry, highlighting the ways in which graph-based models enhance the comprehension and prediction of chemical properties. The mathematical underpinnings, such as adjacency matrices, connectivity, and cyclomatic numbers, offer a structured framework for the analysis of heterocyclic compounds. Computational methodologies, including graph isomorphism detection and the Wiener index, enable efficient molecular analysis. Graph theory plays a pivotal role in predicting molecular properties, facilitating drug discovery, and elucidating reaction mechanisms. Applications encompass property prediction through topological indices, drug candidate identification via structural analysis, and the modeling of chemical transformations. The integration of graph theory with computational chemistry, machine learning, and quantum chemistry further propels research in heterocyclic chemistry. Future directions involve the development of novel graph-based descriptors, the enhancement of graph neural network models, the exploration of quantum computing, and the advancement of cheminformatics software for real-time reaction mechanism modeling. This study underscores the potential of graph theory to advance heterocyclic chemistry and its applications, bridging mathematical, computational, and quantum chemical techniques for innovative discoveries.

Machine Learning for Predicting Physical Properties of Materials from Atomic Configurations

Authors- Dr. Sarika Vaijanathrao Jadhav

Abstract- – Predicting the physical properties of materials—like how strong, conductive, or stable they are—based on their atomic structure is a key goal in materials science and chemistry. These predictions are essential for designing new materials used in things like batteries, electronics, and clean energy technologies. Traditionally, scientists use accurate methods like density functional theory (DFT) to simulate the behavior of atoms and electrons. However, DFT is very slow and requires a lot of computing power, especially for large or complex systems. This makes it difficult to use for fast or large-scale materials discovery. Machine learning (ML) offers a powerful solution. Once trained on large, reliable datasets, ML models can quickly learn how atomic structure relates to material properties—such as band gaps, formation energy, or elasticity—making predictions much faster than traditional methods. This paper reviews how ML is being applied in this field. We look at how atomic structures are converted into machine-readable formats using descriptors like symmetry functions, Coulomb matrices, and graph-based methods. We then explore different ML models, from basic regression methods to advanced deep learning architectures like graph neural networks (GNNs) and convolutional neural networks (CNNs). We also highlight important challenges, including the need for high-quality data, making models understandable, and ensuring they follow physical laws. Special attention is given to physics-informed ML, which builds real-world scientific knowledge into model design to improve accuracy and generalization. Finally, we showcase real-world examples where ML has successfully predicted material properties and compare the results with traditional methods and experiments. The goal of this paper is to map out the current progress in this field and suggest where future research should focus.

A Unified Framework for Solving Fractional Differential Equations Using Modern Integral Transform Methods

Authors- Saiganesh R. Yadav, Amitkumar B. Pandey

Abstract- – Fractional Differential Equations (FDEs) have become essential tools for modeling complex systems with memory and hereditary characteristics across diverse scientific and engineering fields. Traditional methods, while effective for integer-order systems, often fall short in addressing the unique challenges posed by FDEs. This research presents a unified framework for solving FDEs using modern integral transform methods, introducing a novel approach based on the Fractional Spectral Convolution Theorem. Leveraging the frequency properties of integral transforms, the proposed framework extends classical convolution theorems into the fractional domain, enabling the systematic conversion of FDEs into solvable algebraic equations in the spectral domain. A new theorem and its corresponding corollary are formulated using this innovative technique, providing general solutions for linear FDEs with constant coefficients. To demonstrate the practical utility of the framework, a comprehensive problem is solved, highlighting the method’s efficiency and accuracy. The approach seamlessly integrates various integral transforms, including the Laplace, Sumudu, and Elzaki transforms, and introduces a spectral convolution function to enhance solution versatility. The framework not only simplifies the analytical process of solving FDEs but also opens pathways for future research in extending these techniques to nonlinear and multi-term fractional systems. This unified approach offers a powerful and flexible toolset for researchers and practitioners tackling complex dynamical systems governed by fractional- order behaviors.

Effect of Ligand and Their Metal Complexes On the Root Growth

Authors- Dr. J. H. Deshmukh

Abstract- – Ligands are the electron rich species. They have tendency to form complexes with metal ion. The root is important part of plant, present in the soil. Although soil is source of nutrient but root system absorbs nutrients from the soil and provide to the leaves, stem and other parts of plants. The root system gives the protection to the plant. Therefore root system plays very important role in the plant growth. It is observed that the plant having good root system absorbs the sufficient water and nutrients from the soil. Seed dressing method is used for the study. Seed are treated with ligand, metal complexes, CowUrine and dung.

Physicochemical Investigations of Water from Diverse Sources and Their Comparisons

Authors- Dr. P.D.Tawde, Mr.S. S..Tiwade

Abstract- – Water is a critical natural resource, essential for sustaining life, maintaining ecological balance, and supporting economic development. The safety and quality of drinking water are vital for human health, yet they are often compromised by chemical and microbiological contaminants. This study investigates the physicochemical and biochemical characteristics of Groundwater water in the Talni region to evaluate their suitability for human consumption. Results showed that most physical and chemical parameters of the water samples were within the permissible limits as prescribed by WHO (1971) and BIS (1991). The study further highlights the influence of these water quality parameters on aquatic biotic communities and primary productivity. Regular monitoring of water quality is emphasized to ensure public health and ecological stability.

Ensemble-Based Identification of Chronic Kidney Disease

Authors- Pavan Gautam, Priya Agrawal, Atharva Harsulkar, Nikita Warade

Abstract- – A serious public health issue, chronic kidney disease (CKD) needs to be identified early and accurately in order to be effectively treated and managed. To improve CKD prediction accuracy, this work suggests a unique machine-learning strategy that makes use of stacking techniques and a weighted average ensemble. With optimum weights allocated according to individual model performance, the ensemble approach integrates the predictive capabilities of several base classifiers, such as Decision Tree, Random Forest, and Support Vector Machine (SVM). To improve predictions, stacking further combines these models with a meta-classifier, usually a Gradient Boosting or Logistic Regression model. A benchmark CKD dataset is used to assess the effectiveness of the suggested method, with an emphasis on measures like accuracy, precision, recall, and F1-score. The weighted average ensemble and stacking are superior to traditional single classifiers and other ensemble techniques like bagging and boosting when it comes to handling imbalanced datasets, enhancing model interpretability, and attaining greater robustness against overfitting. The study highlights the usefulness of the suggested approach in actual clinical settings and shows how it may be used to provide more accurate CKD identification. Future research attempts to expand the scope of CKD prognosis and management by investigating the incorporation of further variables and integration with survival prediction models.

Application of Artificial Intelligence in Forest Research and Management: A Review

Authors- Tarun A. Shinde Asst. Prof

Abstract- – Artificial Intelligence is deals with automatic presentation, collection and use of information that attempt to to utilise human thought. The development of AI application involve the advanced technology in computer science. The role of artificial intelligence in the field of forest facilitate the efficient surveillance, administration and preservation of forest. The conservation strategies also constitute the the restriction from pandemic situations in forest. Now a days forest fire is also create challenge for the conservation of biodiversity and forest strata. Likewise such kind of similar situations are to be controlled by the usage of artificial intelligence. The objective of this paper is to present a comprehensive review of how AI are to be utilised in forestry sector and the conservation of biodiversity worldwide. The application of AI technology enhances the availability of extensive data pertaining to forest and biodiversity in the utilisation of cloud computing, digital and satellite technology the facilitate the wider acceptance and implementation of AI technology. In this paper the application of AI in forest research and management is to be understood in the context with the monitoring of the forest and assessment. For the detection and prevention of the forest from wildfire and for the precision forestry the application of AI is to be applied.

Integrating AI Techniques into Mathematical Modelling of Complex Systems

Authors- Santosh M. Popade

Abstract- -Mathematical modelling is a cornerstone of understanding and predicting complex systems in fields ranging from physics and biology to economics and engineering. With the advent of Artificial Intelligence (AI), especially machine learning and deep learning techniques, there has been a transformative shift in how models are constructed, validated, and interpreted. This paper explores the integration of AI into mathematical modelling, discussing the synergies between traditional analytical methods and modern computational intelligence. Case studies in epidemiology, climate modelling, and financial forecasting are reviewed to illustrate the practical applications and benefits of this integration. Challenges and future research directions are also discussed.

The Role of Artificial Intelligence in Mathematical Education

Authors- B. G. Urekar, S.B. Chavhan

Abstract- -Artificial Intelligence (AI) is transforming various aspects of education, including mathematical education. AI-powered tools and systems can provide personalized learning experiences, improve student engagement, and enhance teacher effectiveness. This paper explores the role of AI in mathematical education, including its benefits, challenges, and future directions. We discuss the potential of AI to improve mathematical education, including the use of machine learning, natural language processing, and computer vision. We also examine the challenges and limitations of AI in mathematical education, including data quality and availability, teacher training and support, equity and access, and ethics and bias.

Wavelet Transform: A Generalized Integral Transform for Non-Stationary Signal Analysis

Authors- Assistant Professor Chavhan S.B., Assistant Professor Berdewad O.K.

Abstract- -The Wavelet Transform has emerged as a powerful generalization of classical integral transforms, offering a flexible approach to analyzing non-stationary signals. Unlike traditional transforms like the Fourier Transform, which provide only frequency information, the Wavelet Transform uses finite, localized basis functions called wavelets to enable analysis in both time and frequency domains. This paper explores the mathematical foundations of the Wavelet Transform and its relationship to classical integral transforms, presenting a unified view within a broader class of analytical tools. The Continuous Wavelet Transform (CWT) and Discrete Wavelet Transform (DWT)[1] are introduced, highlighting their ability to adapt time-frequency resolution based on signal characteristics. The paper examines the Wavelet Transform as a generalized integral transform, drawing parallels with the Fourier Transform and discussing its kernel-based formulation. Applications are showcased, with an example of image denoising using wavelet coefficients. Recent advances are discussed, including adaptive and data-driven wavelets, integration with machine learning, and emerging applications such as brain-computer interfaces and quantum signal processing [8]. The paper concludes by emphasizing the transformative potential of wavelet-based techniques across scientific and engineering disciplines.

Transforming Mathematics Education in India through Artificial Intelligence: Current Trends and Future Prospects

Authors- Associate Professor Bhimanand Pandurang Gajbhare,
Associate Professor Manohar B. Bhagirath

Abstract- -This paper examines the integration of Artificial Intelligence (AI) in mathematics education across India, analyzing its implementation, effectiveness, and challenges from 2018-2023. Through quantitative analysis of adoption rates, student performance metrics, and teacher feedback, we evaluate the transformative potential of AI-powered educational tools in the Indian mathematics education landscape. Our research contributes practical recommendations for sustainable AI integration in mathematics education, emphasizing the development of cost-effective solutions and comprehensive teacher training programs. These insights aim to support India’s vision of creating an equitable, innovative, and globally competitive education system.

Some Review on Use of Mathematics & AI in stock Market

Authors- Santosh C. Rudrawar

Abstract- -In this paper we discus on Mathematics plays a crucial role in the stock market, particularly in understanding financial concepts, evaluating investments and developing trading strategies. Key mathematical concepts used in the stock market include compound interest, probability, averages and various financial ratio like Return on Equity and Price/Earnings ratios. AI trading techniques possess a higher accuracy rate than traditional methods. It is due to their ability to analyze and learn from massive models have in built risk management algorithms that adjust portfolios based on real time data. It helps minimize potential losses.

Integrating Artificial Intelligence and Mathematical Modeling for Drug Design in Structural Biophysics

Authors- V. A. Jadhav, S. B. Chahvan

Abstract- -The complexity of drug discovery and development presents substantial challenges in terms of time, cost, and overall success rates. Integrating structural biophysics with artificial intelligence (AI) and mathematical modeling offers transformative potential to accelerate and enhance the drug design process. This study explores a multidisciplinary framework that combines advanced AI techniques—such as deep learning, reinforcement learning, and natural language processing—with biophysically informed mathematical models, including quantitative structure-activity relationships (QSAR), pharmacokinetic (PK), and pharmacodynamic (PD) simulations. By leveraging high-resolution structural data from X-ray crystallography, cryo-electron microscopy, and NMR spectroscopy, the approach enables more accurate predictions of protein-ligand interactions, conformational dynamics, and binding affinities. Results indicate significant improvements in hit identification, lead optimization, and toxicity prediction. This article underscores the significance of structural biophysics in enhancing AI-driven drug design and outlines the path toward developing fully automated, structure-based drug discovery pipelines.

Involutions in Banach Algebra

Authors- Mr.V G. Lamb

Abstract- -In this paper, we define some definition related to involution, examples, Gelfand Nahnark Theorem has important role.

Role of Ideals and Homomorphisms in Banach Algebra

Authors- S.R.Gadhe

Abstract- -In thepresent paper we discuss ideal, maximal ideal, theorem homomorphism.

Involutions in Banach Algebra

Authors- Mr.V G. Lamb

Abstract- -In this paper, we define some definition related to involution, examples, Gelfand Nahnark Theorem has important role.

Voice Controlled Robo Child

Authors- Dr. S. A. Awachar, Maitreyee Joshi, Muskan Jattawale, Nayana Bhatkar, Pallavi Bhagat

Abstract- -This project is all about creating a voice-controlled robo child that can show simple emotions like crying, laughing, singing, and even dancing, just by listening to voice commands. At the heart of it is an Arduino Uno, which works together with a Bluetooth module (HC-05) to receive voice commands through a mobile app. To bring the robo’s emotions to life, we used an ISD1820 voice recording module that plays recorded sounds like laughter, crying, or songs. This robot child shows how voice-controlled robots can become more emotionally engaging, and it opens the door to building even smarter, more human-like machines in the future.

Synthesis and Characterization of Novel Pyrazoline Derivatives: Design, Development and Applications

Authors- Arati A. Narwade, Dr. S. P. Rathod

Abstract- -The synthesis of a novel substituted pyrazoline compound, a derivative with significant , was accomplished through a series of chemical reactions starting from suitable precursor materials. The process began with the condensation of 2-hydroxyacetophenone and anisic acid under basic conditions, yielding the corresponding intermediate. Following this, a base-mediated BVT of the intermediate resulted in the formation of a flavanone derivative. This derivative was then reacted with hydrazine to produce the novel substituted pyrazoline derivative. The final product was characterized by various spectroscopic techniques, including NMR spectroscopy and mass spectrometry, to confirm both its structure and purity. This synthesis route offers a straightforward approach to obtaining the substituted pyrazoline derivative, which holds potential for further pharmacological exploration.

An Inventory Model Using System Dynamics Analysis for Declining Items in a Supply Chain

Authors- Mr. Avinash D. Rajegore, Dr. Kishor Y. Ingale

Abstract- -An integrated inventory model of the supply chain for degrading products among a supplier, a manufacturer, and a customer was created by Rau et al. in 2004. The ideal order lot-size and delivery number n was determined under the least joint cost of the supply chain by using a mathematical model. In order to determine the ideal inventory policy and order timing, Rau et al. focused mostly on conventional statistical and mathematical calculations. However, they did not go into greater detail about the complicated dynamics that arise from time evolution. The inventory model of decaying objects must be carefully and methodically considered in order to accurately reflect the operating process. Thus, in order to suggest a novel order system and carry out a systematic simulation, we employ system dynamics thinking in this research. The developed model’s validation and model testing results demonstrated the suitability of the system dynamics simulation approach. In the end, the ideal least joint cost of the supply chain was found using the system dynamics simulation.

A Study of the Double Soham Transform and its Utility in Applied Sciences

Authors- G.G.Bhuttampalle, D. D. Pawar, S.B.Chavhan, Wfs Ahmed

Abstract- -In this article, we examine a new double transform which is a com- bination of ARA transformand Sawi transform (double ARA-SW). We present some basic properties of double ARA-SW transform like linearity, shifting, ex- istance and uniqueness and double convolution theorem. We proved some important results of double ARA-SW transform related to partial derivatives. In order to show that useablity of double ARA-SW transform, some examples of partial differential equation are illustrated.

Some Applications of Artificial Intelligence (AI) In Mathematical Sciences

Authors- Dr.Archana V.Bhosle

Abstract- -The use of artificial intelligence (AI) tools in mathematical sciences is revolutionizing a wide range of areas, encompassing everything from symbolic computation to data analysis and optimization. These tools create new possibilities for addressing traditional mathematical challenges, provide enhanced insights from large datasets, and facilitate quicker and more precise simulations. As AI technology progresses, its integration within the realm of mathematical sciences are expected to strengthen, establishing it as an essential resource in both theoretical and practical mathematics.

Graph Based Decision Making Method Using Soft Set Relations

Authors- Assistant Professor Sayyed Jalil, Rahul Deshmukh

Abstract- -In this paper, we describe a novel approach to analyzing and evaluating complex choice issues by utilizing graph representations of soft set relations in our choice-making method. By looking at the incoming and outgoing values of choices inside a graph-based framework, the suggested algorithm offers an organized method for determining the optimum option. This method may be adapted to a variety of decision-making models and is especially helpful for tackling issues in a variety of domains, including social decision-making.

Mathematics: The Backbone of Artificial Intelligence Evolution

Authors- Dr.Sandeep Awachar

Abstract- -Mathematics serves as the backbone of Artificial Intelligence (AI), offering the theoretical and practical tools required to model, train, and optimize intelligent systems. From the geometrical intuition underlying neural networks to the stochastic processes driving decision-making in uncertain environments, AI is deeply rooted in mathematical theory. This paper presents an in-depth exploration of the mathematical underpinnings that support AI methodologies, with emphasis on key mathematical domains including algebra, calculus, probability, statistics, information theory, and emerging mathematical fields. Additionally, it examines how mathematical reasoning contributes to state-of-the-art applications in computer vision, natural language processing, reinforcement learning, and ethical AI design. A forward-looking perspective on the role of mathematics in explainability, fairness, and general AI concludes the discussion.

Real-Time Fire and Smoke Detection System

Authors- Assistant Professor Vaishali Shende, Sejal Kumbhare, Khushbu Katakwar

Abstract- -Around the world, fire events continue to rank among the top causes of property loss, injuries, and fatalities. Traditional fire detection systems mostly rely on smoke alarms and heat sensors, which frequently identify fires at an advanced stage with little time for evacuation and response. The likelihood of uncontrollable fires, which cause extensive damage and health risks, especially respiratory and skin-related illnesses from extended exposure to toxic smoke, is greatly increased by delayed detection. In order to overcome these obstacles, we suggest a cutting-edge Fire and Smoke Detection System that makes use of artificial intelligence, sensor-based environmental monitoring, and contemporary computer vision techniques to guarantee early fire detection and risk assessment.