JRE Group of Institutions

Infection remains a significant global health concern, with millions of new cases and deaths occurring due to infectious diseases. Currently, chemoprophylaxis and chemotherapy are the primary treatments, but side effects and toxicities pose challenges. Pathogenic microorganisms have developed resistance to antimicrobial medications. Nitrogen containing heterocyclic scaffolds possess the potential in drug discovery and are explored in various fields like pharmaceuticals, cosmetics, and agrochemicals. To minimize antimicrobial drug resistance, there is a need to design potent, safer antimicrobial lead compounds with higher selectivity and minimal cytotoxicity. The present review aims to outline several recent developments in medicinal chemistry aspect of nitrogenous heterocyclic derivatives with the following purposes: (1) To cast light on the recent literature reports of the last eight years ranging from 2015 to 2023 describing anti-microbial potential of nitrogen-containing heterocyclic derivatives which includes pyrazole, pyrazoline, imidazole, tetrazole and quinoline; (2) To brief the recent developments in the medicinal chemistry of nitrogenous heterocyclic derivatives that is directed towards their anti-microbial profile; (3) To summarize the complete correlation of structural features of nitrogenous heterocyclic molecules with the pharmacological action including in silico as well as mechanistic studies to provide thoughts accompanying the generation of lead molecules. Antimicrobial potential of nitrogenous heterocyclic molecules has been displayed by relating the structural features of various lead candidates with their in vitro as well as in vivo antimicrobial outcomes. In contrast, in silico computational analysis from different articles also helped to predict the SAR of potent molecules. Nitrogen containing heterocycles are involved in a range of natural to synthetic analogues with keen antimicrobial potency. It is an emerging need to generate new nitrogenous heterocyclic molecules in order to tackle the drug resistance in micro-organisms with more targeted selectivity as well as specificity. To limit the side effects associated with them and to combat the microbes acquired resistance towards the current drug regimen, novel nitrogenous heterocycle based antimicrobial agents are essential to be developed. This review connects the structural units present in lead compounds with their promising antimicrobial action.

Customer churn prediction represents a critical challenge for the banking sector, with significant implications for revenue retention and customer relationship management. This study investigates the factors influencing churn behavior among clients of a European retail bank, utilizing a dataset comprising 10,000 customer records. We employ a comprehensive machine learning framework incorporating seven distinct algorithms: Logistic Regression (as baseline), K-Nearest Neighbors, Decision Tree, Random Forest, AdaBoost, XGBoost, and an Artificial Neural Network. The analysis includes feature engineering to identify key predictors of churn, encompassing demographic characteristics, account activity patterns, and service usage metrics. Our comparative approach examines how different algorithmic architectures capture the complex relationships underlying customer attrition. The study contributes to financial analytics literature by providing empirical insights into machine learning applications for churn prediction in the European banking context. Furthermore, the results offer practical value for bank managers seeking to develop targeted retention programs and optimize customer engagement strategies through data-driven decision making.

HIV (Human Immunodeficiency Virus) targets and weakens the immune system. If left untreated, it can progress to AIDS (acquired immunodeficiency syndrome), a condition marked by a high viral load and increased infectiousness. Without treatment, individuals with AIDS typically survive about three years. While there is no cure for HIV, it can be managed effectively with proper medical care. This study focuses on identifying conserved regions within the genetic and protein sequences of HIV-1 from large-scale data. By leveraging multiple sequence alignment and machine learning techniques, conserved regions in the mutational patterns of HIV-1 are identified. These conserved regions hold significant potential for the pharmaceutical industry, particularly in development of vaccine.

In automated detection besides diagnosis of pneumonia represents a serious task in the health images outcome. When the disease is detected through CT or X-ray images there are sometimes fewer signs of illness. Millions of individual's decease due to pneumonia every day. The key area and the important task are using deep neural networks and machine learning. Pneumonia is a life- threatening infectious disease that affects the human lungs. The common reason for spreading disease is bacteria which is called streptococcus pneumoniae.as globally the quantity of demises in India caused by the due to this disease.to identify the disease by examining early signs through chest X-rays. It is a process that needs expert radio rapists for the implementation and evaluation. In the remote areas for automatic system in the disease detection. In this proposed work feature selection and feature extraction techniques to analyze the results for pretraining the models by using different classifiers and the models. This proposed work has taken the 5896 samples in the form of images which are available on the UCI machine learning repository for many medical challenges regarding imaging. The proposed perfect is evaluated and created on various parameters the projected model obtained accuracy such as <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 4. 7 8 \%}$</tex> etc.

Due to considering smarter cities path in upward direction; more sustainable techniques with monitoring about environment has now become the crucial problem related to urban development. This paper evaluates about role with advancement tools for air quality monitoring, along with the main focus upon communication tools that make able real-time transformation about environmental information. The study focuses on various challenges, consisting ensuring data with accuracy, minimizing delays via transmission, enabling various sensors to make the work easier along with the mentioning cybersecurity challenges. The findings recommend about power related to air quality management, with their all success depends upon strong communication modules, a very clear regulatory support, as well as transparency considering public.

Epilepsy is a chronic neurological disorder characterized by recurrent, unprovoked seizures caused by abnormal electrical activity in the brain. Many people suffer at some stage in their lifetime from Epilepsy, this is mostly seen in children. Hence detecting the problem at an early stage helps in curing it effectively. In rural areas, where medical diagnosis is not that fast which delays treatment, Epileptic Seizure detection model helps in quick diagnosis right after the report is received. A specialist is needed to analyze all electroencephalogram recordings to detect epilepsy rendering the method of detection time consuming and tedious process. Accurate detection and timely treatment can lead to faster drug therapy and increase the body capability to fight against future seizure related complications. There are some systems developed that are used for the Epileptic Seizure Detection using some classification algorithms. We are also developing a model to detect Epileptic Seizure Detection using an effective Machine Learning algorithm, also carrying out a deep comparative study on different algorithms that have been used by other developers, and on the algorithms that can be used, leaving no other possibilities. Authors in this paper have clear objective that is to apply all possible algorithms and comparing the results like accuracy and effectiveness.

Block chain- XAI symbiosis is revolutionizing trustworthy decision-making in the IoT network of Industry 4.0. Block chain involves the use of distributed, tamper-evident and transparent means for data management; it solves the problem that data integrity and security lack of guarantee in industrial IoT (1IoT) networks. But AI models behind IIoT application development are typically black-box systems, which can create distrust and regulatory concerns. Incorporating XAI into existing and future AI-enabled IIoT systems would make the underlying decision-making logic transparent, interpretable and auditable. This synergy allows the building of reliable, end-to-end trust-worthy systems, in which block chain guards universally transaction data and decision traces. At the same time, XAI components make AI outputs interpretable in a human-comprehensible language. This structure not only allows the verification of sensor data and autonomous access control but also generates verifiable and auditable justifications for automated actions - these are necessary for mission-critical operations and for predictive maintenance within smart factories. Experimental results show the potential of block chain in converging with XAI to minimize attack surfaces, build user trust, and simplify regulatory accreditation in IIoT installations. This coupled machine-human approach opens perspectives towards secure, transparent and explainable AI-driven industrial automation, fulfilling essential needs for reliability, accountability and compliance in future Industry 4.0 environments.

Drug delivery systems have come to be precise, effective, and patient-friendly—the very design features of modern treatment. The current review covers a wide range of topics, such as the use of nanocarriers, vesicular systems, solid lipid nanoparticles, and new oral dosage forms in pharmaceutical practice. Liposomes, proniosomes, and naso-pulmonary vesicular carriers not only protect unstable drugs but also enable delivering the drug right to the site and thus increasing its bioavailability. Besides its great potential for both hydrophilic and hydrophobic drugs, the system based on nanoparticle power maximizes the efficacy of drug action by penetrating through biological barriers and altering pharmacokinetic profiles in a favorable way. The solid lipid systems, consisting of SLNs and NLCs, provide controlled release and stability while ensuring biocompatibility. The oral dosage innovations, for example, mouth dissolving tablets, films, effervescent, and chewy ones, not only improve patient compliance but also offer either rapid or sustained drug action. Controlled and sustained release technologies, which include polymeric and vesicular strategies, make it possible to attain therapeutic effect for a longer time, maintain plasma concentrations predictable, and hence reduce dosing frequency. All these technologies together represent a credible changeover in part towards precise therapeutics, wherein formulation science is merged with nanotechnology to resolve clinical issues in contemporary medicine. The review brings out the great importance of the advanced drug delivery systems in the enhancement of the treatment outcomes, reduction of the side effects, and increased patient adherence, also being a future hope in personalized and targeted therapies.