Journal of Information Technology and Sciences

Real-time Predictive Maintenance in Manufacturing using Streaming Sensor Data and Machine Learning

Rekha Sahu, Shikha Tiwari — Fri, 17 Jul 2026 00:00:00 +0000

The rationale for the new framework of real-time predictive maintenance is that it directly addresses some of the major shortcomings of traditional maintenance methods; in particular, those that utilize reactive and scheduled routines. These normal practices often result in unplanned failure or unnecessary repairs, both of which increase operating costs and reduce the overall output of the system. With the integration of industrial-type sensors and real-time continuous monitoring, there is now the ability to collect accurate data from high-value equipment, such as motors, pumps and compressors. The data that can now be collected includes vibration, temperature, pressure, and electrical current, providing a complete picture of the condition of the equipment, and such data serves as a fundamental data source for the use of predictive analyses. The ability to utilize streaming data analytics through platforms such as Kafka Streams and Apache Spark Streaming allows for the real-time ingestion and processing of data. This means that the capability of doing window-based feature extraction and producing near-instantaneous predictive results is necessary for effective early detection or prevention of failures. Additionally, through the use of machine learning models, the reliability of the predictions of failure can be enhanced. For example, Long Short-Term Memory (LSTM) models are particularly effective for predicting Remaining Useful Life (RUL) by examining temporal relations, and utilizing Random Forest and anomaly detection methods can improve the accuracy of classifying faults. This use of predictive models will enable the ability to quickly detect short-term anomalies and foresee long-term failures. The dual implementation method - edge-based and cloud-based - brings great benefit to the structure of the framework. Edge computing works to support real-time, low-latency decision-making by processing data closer to where the data is created, whereas the cloud provides scalability, storage, and higher-level analytics. Together, these two forms form a hybrid architecture that can meet the needs of Industry 4.0 Smart Manufacturing Systems. The experimental validation of the framework against a “simulated” dataset that accurately represents a multitude of “real-world” conditions further provides credibility to this framework. The efficiency of the prototype confirms that the proposed framework will reduce both unplanned downtimes and maintenance costs while also improving the reliability and accuracy of prediction results.

AI-Voice-based Automated Form Filling System

B. Adidurga, B. Yamini, Ch. Rameshbabu — Tue, 16 Jun 2026 00:00:00 +0000

Manual completion of banking forms is often time-consuming, error-prone, and challenging for elderly, visually impaired, and physically challenged individuals. To address these issues, an AI Voice-Based Automated Form Filling System is proposed that enables users to complete banking forms through voice interaction. The system utilizes Speech Recognition technology to capture user responses and convert spoken input into text. Natural Language Processing (NLP) techniques are employed to extract, organize, and validate relevant information before automatically populating the required form fields. The system interacts with users by asking questions related to personal and banking details, thereby reducing the need for manual typing. Validation mechanisms are incorporated to ensure the correctness and consistency of information such as names, phone numbers, and identification details. After successful validation, the collected data is automatically entered into the selected banking form, and a completed PDF document is generated. The proposed system improves form-filling efficiency, minimizes human errors, and enhances accessibility for users with limited technical skills. Experimental observations indicate that the system significantly reduces the time required for form completion compared with traditional manual methods. The integration of Artificial Intelligence, Speech Recognition, and NLP technologies provides a user-friendly and efficient solution for modern banking applications.

A Comprehensive Literature Survey on AI-Driven Clinical Decision Support Systems for Automated Chest X-ray Analysis

Wed, 22 Jul 2026 00:00:00 +0000

The Chest X-ray Clinical Decision Supported by Artificial Intelligence (AI) The Support System (CDSS) is designed to help healthcare professionals. to identify lung-related diseases with the help of chest X-ray images accurately and at an early stage. This project uses deep learning and machine learning to study X-ray images and distinguish the possible presence of irregularities. Algorithms, namely CNNs or convolutional neural networks. such conditions as respiratory diseases, tuberculosis, and pneumonia. The system takes medical images, obtains significant features, and delivers predictive outcomes to aid in clinical decision-making. The AI-based system eliminates human mistakes and minimizes the work of the hands. CDSS. and promotes timely treatment by accelerating the process of diagnosis. This project demonstrates that artificial intelligence can and will improve the analysis of medical imaging and be a supporting tool to doctors, rather than a replacement tool, and improve the overall effectiveness of healthcare and patient outcomes. Automated Chest X-ray (CXR) Analysis Decision Support Systems (DSS) are revolutionizing radiology by offering fast, accurate, and interpretable support to physicians in the detection of thoracic diseases. CNNs and Transformers are artificial eyes that help to eliminate reporting delays and human weariness, especially in high-throughput settings. These systems are often used in deep learning. Agent-Based Decision Frameworks are recent systems that employ intelligent agents to control a closed-loop process that integrates perception, memory, and reasoning to provide contextual decision assistance. Multimodal Learning & RAG systems are trending towards Retrieval-Augmented Generation (RAG) and cross-modal retrieval, directly matching photos to historical text reports for evidence-based, structured Electronic Medical Record (EMR) drafting.

Automated Drug Dispenser for Efficient Hospital Medication Management

K. Murugan, N. B. Mahesh Kumar, Dushyan S, Balamurugan R, Dhivahar R, Divakar R — Sat, 20 Jun 2026 00:00:00 +0000

Medication errors and non-adherence remain critical challenges in modern healthcare systems, especially among elderly patients and individuals with chronic illnesses. Manual methods of medication management often lead to missed doses, incorrect timing, and increased dependency on caregivers. To address these issues, this project proposes an IoT-based Automated Drug Dispenser (ADD) that ensures accurate, timely, and secure medication delivery. The system integrates key technologies such as RFID for patient authentication, a servo/gear motor for automated dispensing, GSM for real-time SMS alerts, and IoT platforms like Blynk for remote monitoring. Each patient is assigned a unique RFID tag, which enables secure identification and personalized medication scheduling. The system verifies the prescribed schedule using a real-time clock and dispenses the correct dosage automatically at the appropriate time. Additionally, the system sends alerts to caregivers in case of missed doses or system errors, ensuring continuous monitoring and timely intervention. The inclusion of a user-friendly LCD interface enhances usability by providing real-time feedback and instructions to the user. The system is designed to be cost-effective, scalable, and suitable for hospitals, elderly care centers, and home healthcare environments. Overall, the proposed solution improves medication adherence, reduces human errors, and minimizes the workload on healthcare professionals, contributing to safer and more efficient patient care.