IIRJET

Advancements in Text Summarization Using LSTM and Transformer-Based Models: A Comparative Review

M. Rukhsah — 2025-12-31

Text summarization has proved to be a vital part of NLP as it has turned long texts short and yet with the primary components. This survey investigates the development of text summarization algorithms, putting a particular focus on the Long Short-Term Memory (LSTM) and Transformer-based summarization. Initially, LSTM models had significantly advanced the way neural text summarization was conducted by carefully managing sequential connections through encoder-decoder architectures and, on numerous occasions, through attention and pointer-generator networks. But why they suffer in distant connections and fail to employ parallel computing is the question that gave rise to Transformer-based models, which introduce self-attention and increase the summarization performance. Recently, systems based on BERTSUM, PEGASUS, BART and T5 have set new scores in both summarization tasks. This paper critically compares these architectures in terms of their model, the complexity of the training algorithm involved, the metrics to be used in evaluating and the areas of application they operate in. Besides that, the paper also highlights highly relevant dataset and trends in progress such as the absorption of ready-learned language models, adapting to new domains and encountering new evaluation challenges. The necessity to cope with the concerns like consistency, summarizing low-resource texts and scalability guides the choice of the future research direction.

An Intelligent Predictive Framework for Early Diagnosis of Cardiovascular Disease Using Deep Neural Network

Mathan. S — 2025-12-31

Cardiovascular disease (CVD) is a major cause of death worldwide. Congenital heart disease, arterial disease, heart failure, rheumatic heart condition, and cerebral disease are some of its most prevalent types. Early disease detection can help us avoid potentially fatal diseases and provide patients with better care than we could in later stages because prevention is always preferable than therapy. Those who are diagnosed may have a very high death rate because they are not accessible at an early stage. A variety of research techniques in the machine learning domains can assist in anticipating CVDs and identifying their behavioral patterns in enormous amount of data in order to solve these issues. The results of these estimates will help doctors make judgments and identify patients early, reducing the likelihood of death. This research covers the creation of an innovative, reliable, effective, and intelligent predictive system for early CVD detection using Deep Neural Network (DNN) model in order to optimize prevention and treatment for CVDs. Its goal is to automatically select significant features and detect heart disease in its earlier stages. The presented model's average accuracy, precision, recall, sensitivity, and F1-score are 99.98%, 98.78%, 97.86%, and 98.56%, respectively. Compared to other existing models, the presented method successfully achieved and maximized classification effectiveness with greater amounts of precision and pinpointing.

A Review of Blockchain-Driven Access Control Frameworks for Secure Smart Contracts in Cloud Environments

Marwa Ali Hamdan AL-Jabri — 2025-12-31

Access control is an important part of cybersecurity in distributed systems since conventional centralized mechanisms are not always sufficient. Due to blockchain, individuals have begun to employ decentralized access control models as they are capable of enhancing transparency, auditing and defending against fraud. At the reason of this report, we survey various blockchain-based access control systems, paying special attention to their architectures, confirmation mechanisms, identity models and policy enforcement mechanisms. We categorize the current literature into various groups based on their platforms (e.g. Ethereum, Hyperledger, Fabric), control mechanisms (e.g. RBAC, ABAC and capability-based) and whether they introduce additional privacy-tools such as zero-knowledge proofs and decentralized identifiers. The paper analyzes and describes the key gaps in current frameworks in terms of scalability, interoperability and computing expenses. Then, the shortcomings of the current research are pointed out so that they could guide future efforts in the field of blockchain-based access control systems.

Fault Diagnosis in Smart Transformers Using Machine Learning Techniques

Adi Febrianton — 2025-12-31

Smart transformers bring major change to present-day power systems, allowing for better voltage control, easy monitoring and improved connection with the grid. Because they are used in smart substations and for renewables, these transformers have sensors and communication technology built in so that they can be controlled from a distance and diagnosed while they are operating. The typical ways to detect faults like dissolved gas analysis (DGA), thermography and manual inspection are mostly used once problems occur, are expensive and have limited capabilities for ongoing and prompt diagnostics. This study therefore suggests a strong and flexible machine learning-based method for automatically detecting faults in smart transformers. It includes bringing in data from many sensors, processing the signals with the discrete wavelet transform and cutting down on the amount of data to be processed with principal component analysis. These supervised learning models—Support Vector Machines (SVM), Random Forest (RF) and Convolutional Neural Networks (CNNs)—are all trained with data collected from simulations and real sensors. They are assessed for accuracy, precision, recall, F1-score and AUC. The CNN-based approach is better than classic classifiers, reaching an accuracy rate of over 96% in identifying faults while having very little trouble with both false positives and brief interruptions in data. CNN gets such high accuracy since it can learn useful features by itself from the temporal patterns of the signals. The structure was built to fit into edge computing, letting it address real-time applications with low resources. Integrating advanced signal processing and deep learning helps find faults at an early stage in smart transformers, cutting maintenance expenses, lowering downtime and strengthening the overall resistance of upgraded power distribution systems.

Visualizing Deep Learning Decisions: Grad-CAM-Based Explainable AI for Medical Image Analysis

Isyaku Uba Haruna — 2025-12-31

Regarding the medical image classification task, convolutional neural networks (CNNs) have already achieved good feats and can make the process of disease identification fully automated. Nevertheless, the problem is that these models are operated in a so-called black-box way, which makes it difficult to apply them to healthcare context, where transparency and simplicity of explanation are highly valued. This drawback is addressed in the case study by using an explainable AI method, Gradient-weighted Class Activation Mapping (Grad-CAM), to visualize and interpret the completed a deep CNN model in detecting pneumonia on chest X-rays. The ResNet-50 architecture was fine-tuned with the help of the ChestX-ray14 repository one of the most widespread repositories of approximately 102,000 labeled images used in this kind of study. The model performance was estimated at 93.2% accuracy, 91.8% precision and 94.5% recall, and the area under the curve (AUC) of 0.96 that represents good diagnostic outcomes. The training was done with Grad-CAM to visualize which parts of the X-ray images were the most important during the predictions that the model was making. Based on the observation of the 3D views, it became evident that overall, the identified areas correspond to things defined in clinical examination, such as pulmonary opacities, infiltrates and the numerous types of consolidation that are common in pneumonia. Grad-CAM enabled the clinicians to see and verify if the AI predictions are accurate. Moreover, any errors in the classifier output were located with the assistance of heatmaps, thus, they could be corrected, and the model could be advanced. Hence, Grad-CAM will result in better diagnosis and will assist in transitioning sophisticated AI strategies into practice. Grad-CAM interprets AI decisions into diagrams, allowing doctors to trust the AI diagnosis prompting the further use of deep learning models in hospitals. Due to this case, explainable AI becomes valuable in enhancing transparency, accountability and more informed clinical decision making.

Reinforcement Learning Approaches for Load Forecasting in Microgrids: A Comprehensive Review

Misoon Rashid Ali Almarzouqi — 2025-12-31

Increased use of renewables makes good load forecasting crucial to the more efficient running of microgrids, and to the proper management of their energy. The conventional methods of prediction are not typically capable of dealing with the highly non-linear, stochastic and time-varying dynamics commonly observed in modern microgrid systems. During the last several years, reinforcement learning (RL) has started to be preferred due to its capabilities of assisting systems to progress independently and follow the best learning patterns depending on their real-world experiences. In this review, a large number of RL-based load forecasting approaches applied in microgrid environments are considered. The method is used to arrange past research according to forecasting horizon, the kind of algorithms employed, character of the information and judgment basis of outcome. Their efficiency and drawbacks in terms of real-time forecasting assignments are compared in terms of Q-learning, Deep Q-Networks (DQN), Proximal Policy Optimization (PPO) and Actor-Critic. Hybrid models, computation problems and challenges of merging IoT and edge computing layouts are also examined by the authors. It talks about the fields in which the recent research has been lacking and outlines how to proceed, naming federated learning, multi-agent reinforcement learning and the standardization of datasets as requirements. This work aims at demonstrating to the research and developer communities how they can deploy solid RL techniques to achieve smart, scalable and reliable microgrid load forecasting.

Fault Detection in Smart Grids Using Deep Learning-Based Phasor Measurement Unit Data Analysis

Depandi Enda — 2025-12-31

With the rapid growth of smart grids, their operation has become more involved, so new intelligent fault detection systems are needed to maintain grid stability, dependability and strength. Usually, traditional systems have trouble detecting and identifying faults quickly and exactly when the grid is operating under changing conditions and has a high amount of renewables. Because they provide highly detailed and synced measurements, Phasor Measurement Units (PMUs) are now a key tool for real-time monitoring of the grid. In our study, we offer a reliable fault detection method using deep learning which makes use of data from several PMU channels for accurate detection and localization of faults in the system. In the architecture, CNNs are used to find local information from phasor streams and this is followed by sets of BiLSTM layers that model both forward and backward relations in the data related to grid events. A hybrid CNN-BiLSTM model is constructed using data collected from the IEEE 39-bus system that covers many kinds of faults and different levels of noise and loading. The outcomes from experiments show that the presented model does better than traditional Support Vector Machines, Random Forests and k-Nearest Neighbors at classifying faults and at reaction time. With noise and missing information present, the model is able to give highly accurate and comprehensive results. In addition, the framework is fast-responsing, letting it suit real-time use in monitoring over networks. The research results help build intelligent protection systems that can handle issues automatically and quickly, support self-healing of the grid and support future research in maintenance, grid cybersecurity and reserving grid operations with smart analytics.