This article describes a comparative assessment of four cutting-edge object detection architectures - YOLOv8, YOLOv12, Faster R-CNN, and SSD300 - for the application of automatic landmine detection. The goal is to evaluate detection accuracy, precision, recall, and inference speed in a low-data setting. The experiments were performed on the Landmine Detection Dataset of Roboflow, which was created by Northumbria University, and comprised around 1.2K labeled images. All the models were trained using annotations specific to its structure: YOLOv8 and YOLOv12 trained with YOLO-formatted annotations, whereas Faster R-CNN and SSD300 with COCO-formatted annotations. Those performance measures including mAP@0.5, Precision, Recall, F1-Score, and inference latency were examined. The findings show YOLOv8 had the greatest overall accuracy and velocity while YOLOv12 performed suboptimally even though it was newer in design - most probably because it relies on larger datasets for optimal feature learning. The research highlights dataset scale and annotation structure as being decisively important to detection performance and informing improved model choice for real-world landmine detection.

The rapid expansion of digital payment systems has been matched by a rise in fraudulent activities, emphasizing the importance of secure and intelligent detection methods. This study proposes a federated learning-based weighted ensemble framework that improves fraud identification accuracy while maintaining confidentiality of transaction records. Rather than sharing sensitive data, individual clients develop local models using XGBoost, CatBoost, and AdaBoost, transmitting only model parameters for safe aggregation. The optimal ensemble weights are calculated using Non-Negative Least Squares (NNLS), resulting in contributions of XGBoost (0.0516), CatBoost (0.9480), and AdaBoost (0.0004), highlighting CatBoost's primary influence. Tests on the OpenML Credit Card Fraud Detection dataset (284,807 transactions, 31 features) achieved 99.95% accuracy, 0.9691 ROC-AUC, 0.9180 precision, 0.7568 recall, and 0.8296 F1score, surpassing all individual base models. This methodology provides a viable solution for financial organizations, offering high detection performance alongside privacy protection and scalability in real-world digital payment environments.

Underwater object detection is particularly challenging due to the inherent distortions, scattering, and light attenuation present in aquatic environments, which degrade visual clarity and impact detection accuracy. This paper outlines a comprehensive approach to enhance object detection in such challenging conditions. The proposed methodology combines morphological edge enhancement techniques with an efficient detection model featuring bottleneck layers. The initial phase involves the acquisition of a meticulously labeled dataset comprising underwater images containing objects of interest. Prior to model training, a critical preprocessing step is undertaken to rectify underwater distortions, encompassing tasks like color correction and contrast enhancement. To further fortify the proposed method adaptability to various conditions in underwater, the dataset is enriched through augmentation, introducing variations in lighting conditions, water clarity, and object poses. Bottleneck layers act as information bottlenecks, reducing the dimensionality of features while simultaneously enhancing their depth. This transformation not only compresses information but also mitigates computational overhead, thereby facilitating efficient object detection. This proposed model undergoes experimental validation on the underwater dataset, achieving significantly higher metrics such as a mean average precision (mAP) of 85.1%, precision of 84.4%, and recall of 79.9%. These experimental findings strongly indicate that the suggested method surpasses current models in its ability to detect exceedingly underwater objects effectively.

The advancement of various energy systems has emerged as a pivotal solution to address the escalating energy demand. This objective can be attained through the enhancement of the performance of diverse sources under specific operational circumstances. Among the most significant applications of artificial intelligence (AI) algorithms in the field of energy management is the ability to achieve real-time energy consumption optimization by analyzing extensive datasets from diverse sources such as sensors, meters, weather predictions, etc. This not only leads to cost savings but also contributes to reducing carbon emissions, addressing a critical concern in our environmentally conscious society. This chapter provides a concise overview of global energy scenarios, technologies employed for energy conservation, diverse applications where energy optimization is essential, and the key factors required for enhancing energy efficiency. Furthermore, it explores how AI techniques are leveraged to enhance and reduce energy consumption in conjunction with these technologies. These techniques contribute to the construction of intelligent energy systems and offer significant support to numerous organizations in their development. Applying AI algorithms to the field of energy management enables real-time energy usage optimization by analyzing massive volumes of data.

The cognitive load triggers neural activity, which is crucial for understanding the brain’s response to mental stress or stimuli that induce stress. Electroencephalogram (EEG) signals were collected from a mental arithmetic task (MAT), simultaneous task EEG workload datasets and segmented into 4-second intervals. These segmented signals were then transformed into images using various time-frequency conversion methods (TF), including the Short-Time Fourier Transform (STFT), Continuous Wavelet Transform (CWT), Q Transform (QT), and Superlet Transform (SLT). The resulting TF images were fed into convolutional neural networks (CNNs), such as VGG19, ConvMixer, and a fusion of VGG19+ConvMixer. CNN models were trained using the Adam optimizer to detect cognitive load. The preprocessing involved normalization, and scaling in both phases. Among the models tested, the SLT-based TF-EEG with the fusion of the VGG19 and ConvMixer model outperformed other TF conversion methods and CNN architectures. The VGG19+ConvMixer utilizes the individual advantages of both VGG19 and ConvMixer models. It helps reduce overfitting and vanishing gradients, enhances performance with new data, improves GPU acceleration, and reduces computational cost due to its simpler architecture. However, the SLT effectively handles non-stationary data through its adaptive multi-resolution approach, making it ideal for EEG analysis. The SLT + VGG19 + ConvMixer model achieved accuracies of 97.26% on the MAT dataset and 96.04% on the STEW dataset, with all other evaluation metrics such as precision, sensitivity, specificity, F-score, MCC, Jaccard index, and Cohen’s kappa exceeding 94%. These findings can enhance real-time cognitive load monitoring, benefiting areas such as personalized learning, mental health, and stress management by detecting cognitive load to improve performance and reduce stress in critical situations.

In this work, we introduce a novel deep learning architecture, the Quantum Dilated Fourier Convolutional Neural Network (QF-BDL), designed to enhance image recognition performance by combining the strengths of quantum-inspired dilation mechanisms and Fourier spectral representations. Traditional convolutional networks often struggle to capture the Images of long-range dependencies and frequency-domain features simultaneously. To address this, QF-BDL integrates dilated convolutions to expand receptive fields without increasing computational complexity and applies Fourier transformations to encode frequency-specific patterns more effectively. This hybrid approach enables the model to extract both localized textures and global contextual cues, resulting in improved classification accuracy and robustness. Experimental evaluations on benchmark datasets demonstrate that QF-BDL outperforms standard CNNs and quantum dilated models in terms of accuracy and generalization, highlighting its potential in real-world visual recognition tasks. Index Terms Component, Formatting, Styling, Insert.

Pneumonia, a severe and potentially fatal infectious disease, primarily impacts the lungs in humans. Its main culprit is often identified as Streptococcus pneumonia, a type of bacteria. According to the World Health Organization (WHO), Pneumonia causes many deaths in India, responsible for one out of every three reported cases. Creating an automated system to detect pneumonia holds immense potential for expediting the treatment process, especially in remote regions where access to medical expertise may be limited. With the remarkable success of deep learning algorithms, Convolutional Neural Networks (CNN) have gathered significant interest for their effectiveness in analyzing medical images and facilitating disease classification. The methodology employed in this study revolves around the execution of a CNN known as VGG19. This architecture is utilized to process X-ray images and carry out predictive analysis. To carry out the experiments, a diverse collection of chest X-ray images is employed, including both cases with pneumonia and cases without pneumonia. This dataset is utilized to train and test the CNN model. Our main discoveries highlight the impressive effectiveness of the recommended DL model in accurately predicting pneumonia. The VGG19 model, once trained, attained an extraordinary accuracy of 95.35% on the test dataset. Additionally, the model displayed a high sensitivity of 98.77%, demonstrating its proficiency in accurately identifying both positive and negative pneumonia cases. These findings strongly emphasize the capability of deep learning algorithms in assisting radiologists and clinicians by Detecting pneumonia at an early stage, enabling swift and targeted treatment intervention.

This article aims to improving and refining energy processes by applying diverse technologies, strategies, or methodologies of Artificial Intelligence (AI). AI plays an essential role in transforming and optimizing energy systems across various sectors. This article provides how advanced techniques in AI to analyze data, predict necessary issues, and enact proactive maintenance protocols, ultimately contributing to a more resilient and intelligent energy infrastructure. We have used various Machine Learning (ML) models to optimize energy consumption by learning from benchmark data i.e., energy consumption of 2020, and adjusting system parameters accordingly, leading to improved efficiency. This article contributed to sustainability, cost-effectiveness, and improved reliability in the generation, distribution, and consumption of energy and also helps in proactive maintenance to minimizing downtime, and improving overall system reliability. By harnessing the power of AI technologies, industries can proactively address challenges and optimize energy resources to meet the growing demands of the future.

The aim of this research work is to classify credit card fraudulent transactions. Nowadays, online transactions have become a necessary part of our lives. Credit card fraud has skyrocketed. In fact, it is one of the most prevalent menaces of the banking, financial services, and insurance (BFSI) sector. In the era of digitalization, there are so many frauds happening. Credit card fraud is the most common thing happening nowadays; thus, the need to identify the same is necessary. In this work, firstly, collected the unstructured data related to this research from a frequently used site, i.e., Kaggle. Secondly, implemented different machine learning classification algorithms (supervised) like linear regression (LR), decision trees (DT), artificial neural networks (ANN), and gradient boosting (GB). Among all machine learning (ML) algorithms, DT outperforms the other algorithms with accuracy. The performance of these specified algorithms was marked by their comparative analysis with some performance metrics.

Smart healthcare relies on advanced technologies such as digital health records, the Internet of Things (IoT), cloud computing (CC), artificial intelligence (AI), and blockchain. However, the integration of blockchain into the healthcare sector presents a serious concern regarding scalability. Converting arbitrary values to fixed values and transferring diverse data from different resources pose challenges in the context of kidney transplantation processes (KTPs). Compared to dialysis, kidney transplantation, a therapeutic choice for end-stage kidney disease., is linked to extended survival and enhanced quality of life. Nevertheless, at its core, blockchain continues to be a decentralized, unchangeable ledger that safely logs data or transactions across a network of computers. This technology offers transparent and tamper-resistant data sharing, making it highly relevant to the healthcare industry. The KTP involves several essential steps, from patient evaluation to post-transplant care. Once the data pass through multiple verification and approval levels, it becomes eligible for inclusion in the blockchain. In addition to publicly accessible national datasets like OPTN-based registries (the UNOS and SRTR datasets) and USRDS datasets, there are also datasets from private non-profit organizations in the transplantation field. This chapter focuses on the utilization of blockchain processes to address survival analysis and challenges in kidney transplant patients. These advancements in the healthcare system hold the potential to save lives and greatly benefit individuals facing kidney diseases.

In recent days, credit card fraud has emerged as a significant challenge for researchers in the field of detection and prevention. Tackling this challenge holds substantial benefits for both public and private organizations, as it directly impacts economic statistics. Our proposed model introduces crucial advancements to address this issue in real-time scenarios. To achieve this, we harnessed the power of Deep Convolutional Neural Networks (DeepConvNet) in conjunction with various optimization techniques. Optimization algorithms encompass a group of mathematical and computational techniques employed to discover the most suitable solution or set of solutions for a given problem. The primary goal of these algorithms is to optimize, either by maximizing or minimizing, an objective function while ensuring compliance with specific constraints. In this research work, we provide a comparison of highly effective and validated optimization techniques: Stochastic Gradient Descent (Sgd), Adaptive Gradient (Adagrad), Adaptive Moment Estimation (Adam), and Root Mean Squared Propagation (Rmsprop). These optimization algorithms are applied to the Deep Convolutional Neural Network (DeepConvNet) in the subject of our specific problem statement, which involves credit card fraud detection (CCFD). After careful consideration of the problem's nature, objective function characteristics, and computational aspects, we fnd that all four algorithms are suitable for our CCFD task. However, based on experimental results, it is evident that Rmsprop outperforms others, leading to a remarkable 99.93% in accuracy.

Imbalanced Learning is a significant issue in machine learning, affecting the performance and accuracy of binary or multi-classification algorithms, especially in large-scale data handling and classification. There are some popular techniques to covert this imbalanced data into a balanced one such as undersampling, under-sampling with tomek links, randomized oversampling, synthetic minority oversampling technique (SMOTE), and adaptive synthetic generation (ADASYN). Generally, the ADASYN algorithm could be used to propagate minority sample points to rise the imbalanced ratio between majority and minority sample points, but in some cases, it may conflict with decision boundary points and noisy points. This paper proposed a Refitted AdaSyn Algorithm (RAA) with Gaussian Distribution (GD). So that new minority samples are distributed much closer to the center of the minority sample to spotlight the conflicts. The classification accuracy has improved with RAA over formal ADASYN. For examining the proposed work the imbalanced benchmark datasets like European, Banksim, Paymentcard, and UCI credit card are considered. Vanilla Generative Adversarial Network (GAN) is a deep learning model used to classify fraud and non-fraud transactions, demonstrating significant differences between balanced and imbalanced learning approaches and achieving an accuracy of 97.5% on dataset DS4.

This article proposes an artificial intelligence-empowered and efficient detection approach for customers with Severe Failure in Digital Transactions (SFDT) through a deep transfer network learning approach from discretized fraud data. Presently, the Real-time global payment system is suffered primarily by fraudsters based on customer behavior. For the identification of fraud, scientists used many techniques. However, identifying and tracking the customers infected by the fraud takes a significant amount of time. The proposed study employs pre-trained convolution neural network-based (CNN) architectures to find SFDT. CNN is pre-trained on the various network architectures using fraud data. This article contributed to pre-trained networks with newly developed versions ResNet152, DenseNet201, InceptionNetV4, and EfficientNetB7 by integrating the loss function to minimize the error. We run numerous experiments on large data set of credit payment transactions which are public in nature, to determine the high rate of SFDT with our model by comparing accuracy with other fraud detection methods and also proved best in evaluating minimum loss cost.

All financial sectors are facing the most common frauds, which are digital transactional frauds. Fraudsters have always engaged in illegal activities such as stealing personal information and logging in with unauthorised credentials. Many machine learning algorithms predict whether the transaction is factual or nonfactual but fail to decrease the processing time. Hybrid models are used in this case to identify the fraud in a quick and efficient manner. This article demarcates to construct a novel model, RDQN, i.e., deep reinforcement learning, that combines with the rough set theory. This article has three steps, including data pre-processing to determine the quality of the data, which affects the learning ability of the model, determining the structural relationship and gaining useful features from the data set using rough set theory, and doing a hybridization of DNN (deep neural network) and Q learning, which is called DQN. It uses the MISH activation function and the ReLU activation function in different layers for training dynamics in the neural network. The proposed model classifies and predicts that the transaction belongs to the category implemented by the agents by activating the reward function. The reinforcement-learning agent’s performance improves based on reward assessment. This reward function gives a more precise value for each transaction, and no fraudster can escape from the agent’s sight. This novel approach improves accuracy and reduces processing time by considering the best feature selection during the process.

Digital fraud is a major problem that influences the financial sector and the Indian economy. There has been an increase in financial losses in recent years due to various kinds of smart frauds like unauthorized access, stolen cards, and phishing activities. Hence, finding fraudulent behavior is critical for both individuals and financial institutions effectively. The popularity of Quantum theory with Machine Learning (QML) applications has expanded to larger audience. In this paper, Quantum Machine Learning (QML) is proposed for fraud identification in digital transactional payments. This paper presents an in-depth survey of the difference between classical neural networks and quantum neural networks on various smart digital transaction fraud detection. This paper serves as a pathway for various researchers to understand the advancements in this domain.

Fraud Transactions are haunting the economy of many individuals with several factors across the globe. This research focuses on developing a mechanism by integrating various optimized machine-learning algorithms to ensure the security and integrity of digital transactions. This research proposes a novel methodology through three stages. Firstly, Synthetic Minority Oversampling Technique (SMOTE) is applied to get balanced data. Secondly, SMOTE is fed to the nature-inspired Meta Heuristic (MH) algorithm, namely Binary Harris Hawks Optimization (BinHHO), Binary Aquila Optimization (BAO), and Binary Grey Wolf Optimization (BGWO), for feature selection. BinHHO has performed well when compared with the other two. Thirdly, features from BinHHO are fed to the supervised learning algorithms to classify the transactions such as fraud and non-fraud. The efficiency of BinHHO is analyzed with other popular MH algorithms. The BinHHO has achieved the highest accuracy of 99.95% and demonstrates a more significant positive effect on the performance of the proposed model.

The primary objective of this research is to monitor and detect fraudulent transactions within payment systems. As the use of smart transactions continues to increase, so does the prevalence of fraudsters. These individuals consistently seek to disrupt others by engaging in illegal activities, resulting in financial losses for customers while benefiting the fraudsters. Therefore, it is crucial to prioritize the monitoring and early detection of fraud. This article presents a unique Machine Learning (ML) model for the early identification of fraudulent transactions, utilizing a range-based classification approach. Many existing machine learning algorithms struggle to improve the misclassification rate while maintaining good accuracy. However, the proposed range-based classification model exhibits strong accuracy while addressing the issue of rising misclassification rates. The experimental results are presented through a bar graph and a classification report. Additionally, compare the proposed model with several existing technologies to showcase its effectiveness.

A Transaction plays a vital role in our daily routine life. It can be done through either Physical or Digital. Mostly people were travelled with digital transactions to make their activities in easy and convenient way in recent days. Digital Transactions are transactions in which the customer authorizes the transfer of money through an electronic mode. Generally Digital Transactions are also called E-Transactions. The main aim of our Indian system is to make India as Digital India. Many technologies were introduced to identify the frauds in E-Transactions. As a result, scams are also having increased alongside. According to information provided by the CERT (Indian Computer Emergency Response Team), the total number of cybercrimes was increased from the years 2018 to 2020 was 1,59,761;2,46,514 and 2,90,445 respectively [1]. Many authors surveyed about classification techniques for detecting frauds like data mining, a Machine Learning. This survey paper has related to how to detect frauds among the transactions with the help of machine learning and deep learning algorithms for a classification and the prediction, which gives more accuracy and works efficiently by considering different datasets. A brief discussion of future research developments is discussed in this article.