Explore the vast range of titles available.

Financial fraud, considered as deceptive tactics for gaining financial benefits, has recently become a widespread menace in companies and organizations. Conventional techniques such as manual verifications and inspections are imprecise, costly, and time consuming for identifying such fraudulent activities. With the advent of artificial intelligence, machine-learning-based approaches can be used intelligently to detect fraudulent transactions by analyzing a large number of financial data. Therefore, this paper attempts to present a systematic literature review (SLR) that systematically reviews and synthesizes the existing literature on machine learning (ML)-based fraud detection. Particularly, the review employed the Kitchenham approach, which uses well-defined protocols to extract and synthesize the relevant articles; it then report the obtained results. Based on the specified search strategies from popular electronic database libraries, several studies have been gathered. After inclusion/exclusion criteria, 93 articles were chosen, synthesized, and analyzed. The review summarizes popular ML techniques used for fraud detection, the most popular fraud type, and evaluation metrics. The reviewed articles showed that support vector machine (SVM) and artificial neural network (ANN) are popular ML algorithms used for fraud detection, and credit card fraud is the most popular fraud type addressed using ML techniques. The paper finally presents main issues, gaps, and limitations in financial fraud detection areas and suggests possible areas for future research.

In this work, we describe the creation of a new magneto-electrochemical biosensor that detects metronidazole (MTZ), an antibiotic that is frequently used to treat anaerobic bacterial and protozoal infections, with extreme sensitivity. The sensor platform is engineered by integrating α-Fe 2 O 3 magnetic core nanoparticles with reduced graphene oxide (rGO) to fabricate a core-enhanced carbon electrode (α-Fe₂O₃/rGO@CE). The synergistic combination of α-Fe 2 O 3 and rGO significantly enhances the electrocatalytic activity, electron transfer rate, and surface area of the sensing interface. Using X-ray diffraction (XRD), electrochemical impedance spectroscopy (EIS), and scanning electron microscopy (SEM), structural and morphological characterizations were carried out to verify the uniform distribution of spherical α-Fe 2 O 3 nanoparticles (~ 25 nm) anchored on rGO nanosheets. Electrochemical performance was systematically investigated through cyclic voltammetry (CV) and Differential Pulse voltammetry (DPV). When compared to the unmodified Counter Electrode (CE) (-0.65 V against Ag/AgCl), the suggested biosensor showed a notable change in the metronidazole reduction peak to a higher positive potential (-0.4 V vs. Ag/AgCl), suggesting superior catalytic efficiency. With a remarkable limit of identification (LOD) of 2.80 × 10 −6 M and a limit of quantization (LOQ) of 8.0 × 10 −6 M, a broad linear detection range of 8.0 × 10 −6 to 1.0 × 10 −5 M was attained. The sensor was effectively used for the quantitative measurement of metronidazole in medication and in human urine samples (collected from Mangalore Medical Centre with informed consent obtained from the respective patients, ensuring ethical compliance for clinical analysis) due to its exceptional sensitivity, stability, and reproducibility. This study demonstrates how α-FeO₃/rGO hybrid nanomaterials can be used to create effective magneto-electrochemical biosensors for use in clinical and pharmaceutical diagnostic settings.

With the integration of Internet of Things (IoT) technology, smart cities possess the capability to advance their public transportation modalities, address prevalent traffic congestion challenges, refine infrastructure, and optimize communication frameworks, thereby augmenting their progression towards heightened urbanization. Through the integration of sensors, cell phones, artificial intelligence (AI), data analytics, and cloud computing, smart cities worldwide are evolving to be more efficient, productive, and responsive to their residents’ needs. While the promise of smart cities has been marked over the past decade, notable challenges, especially in the realm of security, threaten their optimal realization. This research provides a comprehensive survey on IoT in smart cities. It focuses on the IoT-based smart city components. Moreover, it provides explanation for integrating different technologies with IoT for smart cities such as AI, sensing technologies, and networking technologies. Additionally, this study provides several case studies for smart cities. In addition, this study investigates the challenges of adopting IoT in smart cities and provides prevention methods for each challenge. Moreover, this study provides future directions for the upcoming researchers. It serves as a foundational guide for stakeholders and emphasizes the pressing need for a balanced integration of innovation and safety in the smart city landscape.

Future 6 Generation (6G) networks will rely on Terahertz (THz) wireless communication as their main enabler for delivering both ultra-high data speed and minimal delay. THz wireless systems become crucial for upcoming communications by using Unmanned Aerial Vehicles (UAVs) together with Intelligent Reflecting Surfaces (IRS) while improving reliability and efficiency. In UAV-IRS-assisted networks, minimizing mission completion time and energy consumption is critical. However, achieving rapid mission execution often requires UAVs to operate at higher speeds, increasing energy usage and creating a trade-off that demands optimization. This paper addresses the challenge of optimizing UAV-IRS trajectories in THz networks to reduce mission time while adhering to energy constraints. Given the non-convex and NP-hard nature of the problem, traditional optimization methods are insufficient. To tackle this, we propose a Multi-Agent Deep Reinforcement Learning (MADRL) algorithm, which provides an efficient, low-complexity solution for trajectory optimization. MADRL dynamically adapts UAV-IRS paths, balancing mission efficiency and energy savings. Simulation results demonstrate that the proposed MADRL-based approach outperforms existing benchmarks, achieving shorter mission times and near-optimal energy consumption across varying scenarios. By leveraging cooperative learning, the algorithm effectively handles complex environments with multiple users and IRS elements. This work highlights the potential of MADRL for UAV-IRS trajectory optimization, offering a scalable solution for energy-efficient and high-performance THz communication systems.

An electrochemical sensor with excellent sensitivity has been developed for the continuous and selective identification of (DA) dopamine and (5-HT) serotonin via a platinum (pt) - doped reduced graphene oxide nanocomposite (Pt-doped rGO). The sensor utilizes the synergistic properties of its components: the increased surface area and electrical conductivity of rGO, the improved electron transfers due to platinum doping, and the structural benefits of the composite for efficient neurotransmitter detection. The Pt-doped rGO nanocomposite is produced by directly oxidizing graphite to generate graphene oxide (GO), subsequently reducing and functionalizing GO with platinum nanoparticles. Electrochemical characterization using differential pulse voltammetry (DPV) demonstrated clear separation of oxidation peaks for DA and 5-HT, allowing precise multiplexed detection. The sensor demonstrated superior electrocatalytic activity, selectivity, and no interference from ascorbic acid (AA), frequently found in electrochemical biosensing. The detection limits were 0.012 µM for both dopamine (DA) and serotonin (5-HT). The analysis of actual samples in human urine and serum validated the sensor’s practicality and reproducibility. The Pt-doped rGO composite effectively tackles significant issues in electrochemical biosensing, such as overlapping redox potentials and interference from intricate biological matrices, rendering it a promising platform for the highly sensitive and selective detection of neurotransmitters.

The need for optoelectronic devices is growing right now, but the production of these devices is having a difficult time keeping up with the advancement of the machinery, instruments, and manufacturing techniques they support. Pictures from big, unlabeled image collections are commonly retrieved using a technique called content-based image retrieval (CBIR). The availability of photographs is also growing as internet growth and transmission networks increase. This study suggests brand-new image retrieval methods for multispectral images used in Optoelectronic device monitoring that are based on image segmentation and classification methods with deep learningtechniques for failure management. Optoelectronic device Monitoring field-based multispectral images were used as the input, which was then processed for noise removal, resizing, and smoothing.Fuzzy c-means clustering-based image segmentation was used to divide up this processed image into its component parts. Following that, a hybrid multilayer transfer learning perception was used to classify the clustered segmented picture. The proposed technique has an accuracy of 95%, precision of 85%, recall of 75%, F-1 score of 63%, error rate of 51%, MAP of 55%; existing MRCN accuracy of 85%, precision of 75%, recall of 63%, F-1 score of 55%, error rate of 45%, MAP of 51%, OC-LBP accuracy of 89%, the precision of 79%, recall of 71%, F-1 score of 59%, error rate of 49%, MAP of 53%.

With micrometre resolution, optical coherence tomography (OCT) is a noninvasive cross-sectional imaging method. The centre wavelength and bandwidth of the light source define the theoretical axial resolution; the greater the axial resolution, the broader the bandwidth. The optical wavelength that is employed determines the properties of OCT imaging. In the field of cognitive computing for healthcare, this study suggests an architecture for evaluating artificial intelligence based on neuro-monitoring. In this work, a novel machine learning approach to Internet of Things (IoT) architecture for brain activity analysis based on electroencephalogram (EEG) signal employing semantic analysis of brain neurophysiology is proposed. Here, a neuromonitoring system uses an EEG signal to determine what input to gather. The gathered information is processed for normalisation and noise reduction. Transfer adversarial convolutional architecture is used to choose these processed input features, and reinforcement federated neural networks are used for feature selection and classification. In terms of accuracy, precision, recall, F-1 score, Normalised Square error (NSE), and Root Mean Squared Error (RMSE), experimental analysis is examined for a variety of EEG datasets. Proposed technique attained an accuracy of 95%, precision of 83%, recall of 73%, F-1 score of 63%, NSE of 63%, and RMSE of 51%.

In this work, we describe the creation of a new magneto-electrochemical biosensor that detects metronidazole (MTZ), an antibiotic that is frequently used to treat anaerobic bacterial and protozoal infections, with extreme sensitivity. The sensor platform is engineered by integrating α-Fe O magnetic core nanoparticles with reduced graphene oxide (rGO) to fabricate a core-enhanced carbon electrode (α-Fe₂O₃/rGO@CE). The synergistic combination of α-Fe O and rGO significantly enhances the electrocatalytic activity, electron transfer rate, and surface area of the sensing interface. Using X-ray diffraction (XRD), electrochemical impedance spectroscopy (EIS), and scanning electron microscopy (SEM), structural and morphological characterizations were carried out to verify the uniform distribution of spherical α-Fe O nanoparticles (~ 25 nm) anchored on rGO nanosheets. Electrochemical performance was systematically investigated through cyclic voltammetry (CV) and Differential Pulse voltammetry (DPV). When compared to the unmodified Counter Electrode (CE) (-0.65 V against Ag/AgCl), the suggested biosensor showed a notable change in the metronidazole reduction peak to a higher positive potential (-0.4 V vs. Ag/AgCl), suggesting superior catalytic efficiency. With a remarkable limit of identification (LOD) of 2.80 × 10 M and a limit of quantization (LOQ) of 8.0 × 10 M, a broad linear detection range of 8.0 × 10 to 1.0 × 10 M was attained. The sensor was effectively used for the quantitative measurement of metronidazole in medication and in human urine samples (collected from Mangalore Medical Centre with informed consent obtained from the respective patients, ensuring ethical compliance for clinical analysis) due to its exceptional sensitivity, stability, and reproducibility. This study demonstrates how α-FeO₃/rGO hybrid nanomaterials can be used to create effective magneto-electrochemical biosensors for use in clinical and pharmaceutical diagnostic settings.