Epilepsy, the most prevalent neurological disorder, is marked by spontaneous, recurrent seizures due to widespread neuronal discharges in the brain. This condition afflicts approximately 1% of the global population, with only two-thirds responding to antiepileptic drugs and a smaller fraction benefiting from surgical interventions. The social stigma and emotional distress associated with epilepsy underscore the importance of timely and accurate seizure detection, which can significantly enhance patient outcomes and quality of life. This research introduces a novel convolutional neural network (CNN) architecture for epileptic seizure detection, leveraging electroencephalogram (EEG) signals. Contrasted with traditional machine-learning methodologies, this innovative approach demonstrates superior performance in seizure prediction. The accuracy of the proposed CNN model is established at 97.52%, outperforming the highest accuracy of 93.65% achieved by the Discriminant Analysis classifier among the various classifiers evaluated. The findings of this study not only present a groundbreaking method in the realm of epileptic seizure recognition but also reinforce the potential of deep learning techniques in medical diagnostics.
The swift global spread of Corona Virus Disease 2019 (COVID-19), identified merely four months prior, necessitates rapid and precise diagnostic methods. Currently, the diagnosis largely depends on computed tomography (CT) image interpretation by medical professionals, a process susceptible to human error. This research delves into the utility of Convolutional Neural Networks (CNNs) in automating the classification of COVID-19 from medical images. An exhaustive evaluation and comparison of prominent CNN architectures, namely Visual Geometry Group (VGG), Residual Network (ResNet), MobileNet, Inception, and Xception, are conducted. Furthermore, the study investigates ensemble approaches to harness the combined strengths of these models. Findings demonstrate the distinct advantage of ensemble models, with the novel deep learning (DL)+ ensemble technique notably surpassing the accuracy, precision, recall, and F-score of individual CNNs, achieving an exceptional rate of 99.5%. This remarkable performance accentuates the transformative potential of CNNs in COVID-19 diagnostics. The significance of this advancement lies not only in its reliability and automated nature, surpassing traditional, subjective human interpretation but also in its contribution to accelerating the diagnostic process. This acceleration is pivotal for the effective implementation of containment and mitigation strategies against the pandemic. The abstract delineates the methodological choices, highlights the unparalleled efficacy of the DL+ ensemble technique, and underscores the far-reaching implications of employing CNNs for COVID-19 detection.
In the field of computer-aided diagnostics, the segmentation and classification of biomedical images play a pivotal role. This study introduces a novel approach employing a Self-Augmented Multistage Deep Learning Network (SAMNetwork) and Deep Belief Networks (DBNs) optimized by Coot Optimization Algorithms (COAs) for the analysis of dermoscopy images. The unique challenges posed by dermoscopy images, including complex detection backgrounds and lesion characteristics, necessitate advanced techniques for accurate lesion recognition. Traditional methods have predominantly focused on utilizing larger, more complex models to increase detection accuracy, yet have often neglected the significant intraclass variability and inter-class similarity of lesion traits. This oversight has led to challenges in algorithmic application to larger models. The current research addresses these limitations by leveraging SAM, which, although not yielding immediate high-quality segmentation for medical image data, provides valuable masks, features, and stability scores for developing and training enhanced medical images. Subsequently, DBNs, aided by COAs to fine-tune their hyper-parameters, perform the classification task. The effectiveness of this methodology was assessed through comprehensive experimental comparisons and feature visualization analyses. The results demonstrated the superiority of the proposed approach over the current state-of-the-art deep learning-based methods across three datasets: ISBI 2017, ISBI 2018, and the PH2 dataset. In the experimental evaluations, the Multi-class Dilated D-Net (MD2N) model achieved a Matthew’s Correlation Coefficient (MCC) of 0.86201, the Deep convolutional neural networks (DCNN) model 0.84111, the standalone DBN 0.91157, the autoencoder (AE) model 0.88662, and the DBN-COA model 0.93291, respectively. These findings highlight the enhanced performance and potential of integrating SAM with optimized DBNs in the detection and classification of skin cancer in dermoscopy images, marking a significant advancement in the field of medical image analysis.
Recent years have seen a significant increase in the incidence of falls among the elderly, leading to accidental injuries and fatalities. This trend underscores the critical need for accurate fall risk assessment, a major concern for public health and safety. In addressing this challenge, a novel approach has been developed, leveraging a pressure sensor placed on the foot's sole to gather gait data from elderly individuals. This method provides a precise analysis of gait stability on a daily basis. The research introduced here utilizes the gramian angular summation field (GASF) technique for converting this data into two-dimensional images, which are then processed using an enhanced EfficientNet model. The innovation lies in the integration of a convolutional block attention module (CBAM) into this model, resulting in a CBAM-EfficientNet algorithm. This approach includes freezing the first four stages of the EfficientNet model, focusing training on the deeper layers that incorporate CBAM. This strategy is aimed at augmenting the network's ability to extract critical features from foot pressure data, consequently improving the accuracy of fall risk classification. Experimental evaluation of this optimized model demonstrates a classification accuracy of 98.5% and a sensitivity of 99.0%, indicating its practical efficacy and strong generalization capacity. These findings reveal that the methodology significantly enhances the classification of plantar pressure data, offering valuable support in medical diagnosis and has substantial practical implications.
In contemporary military contexts, the determination of an optimal course of action (COA) in combat operations emerges as a critical challenge. This study delineates a decision support methodology for military applications, employing sophisticated decision analysis techniques. The initial phase entails the identification of pivotal criteria for assessing and ranking COAs, followed by the assignment of weight coefficients to each criterion via the full consistency method (FUCOM). Subsequently, the Einstein weighted arithmetic average operator (EWAA) was utilized for the aggregation of expert opinions, ensuring a consensual evaluation of these criteria and culminating in the final values of their weight coefficients. The ensuing phase focuses on the selection of an optimal COA, incorporating the grey complex proportional assessment (COPRAS-G) method. This method addresses uncertainties and varying criterion values. Expert ratings were again aggregated using the EWAA operator. The findings from this phase are designed to provide military commanders with precise, data-driven guidance for decision-making. To validate and verify the stability of the proposed model, a series of tests were conducted, including a rank reversal test, sensitivity analysis regarding changes in weight coefficients, and a comparative analysis with alternative methods. These assessments uniformly indicated the model's consistency, stability, and validity as a military decision support tool. Emphasizing a high degree of confidence in COA selection, the methodology advocated herein is applicable to decision-making processes in the planning and execution of military operations. The uniform application of professional terms, consistent with the broader context of this research, ensures clarity and coherence in its presentation. The approach outlined in this study stands as a testament to rigorous analytical methodologies in the realm of military strategic planning, offering a robust framework for decision-making under conditions of uncertainty and complexity.
This study presents a comprehensive evaluation of linear and non-linear control systems, specifically Proportion Integration Differentiation (PID) and fuzzy logic controllers, in the context of position control within double-link robotic manipulators. The effectiveness of these controllers was rigorously assessed in a simulated environment, utilizing MATLAB Simulink for the simulation and SOLIDWORKS for the model design. The PID controller, characterized by its Kp, Ki, and Kd components, was implemented both in the simulation and on the hardware. However, due to the constraints of the microcontroller's RAM and processor, which facilitate the hardware's connection with MATLAB, the application of the Fuzzy Logic concept to hardware was not feasible. In the simulated environment, the fuzzy logic controller demonstrated superior stability in comparison to the PID controller, evidenced by a lower settling time (1.0 seconds) and overshoot (2%). In contrast, the PID controller exhibited a settling time of 0.2 seconds and an overshoot of 32%. Additionally, the fuzzy logic controller showcased a 44% reduction in steady-state error relative to the PID controller. When applied to hardware, the PID controller maintained stable results, achieving a settling time of 0.6 seconds and an overshoot of 2%. The steady-state errors for Link 1 and Link 2 were recorded as 3.6° and 1.4°, respectively. The findings highlight the fuzzy logic controller's enhanced stability, rendering it more suitable for ensuring the accuracy and protection of the manipulator system. As a non-linear controller, the fuzzy logic controller efficiently addresses various potential errors through its intelligent control mechanism, which is embedded in its fuzzy rules. Conversely, the PID controller, a linear controller, responds rapidly but may lack flexibility in complex scenarios due to its inherent linearity. This study underscores the importance of selecting an appropriate controller based on the specific requirements of robotic manipulator systems, with a focus on achieving optimal performance and stability.
In the context of rapid economic development, air pollution has emerged as a critical environmental issue, particularly in the Beijing-Tianjin-Hebei region. This study, through the application of Air Quality Index (AQI) data and K-means clustering, investigates the seasonal variations and spatial distribution of air quality in this region. It has been identified that air pollution in this area is not only subject to seasonal fluctuation but also exhibits distinct patterns of local spatial aggregation. Utilizing a Back Propagation (BP) Neural Network model, this research predicts AQI values, offering foresight into the development and transformation of haze weather conditions. The findings of this investigation are instrumental in enhancing the understanding of air pollution dynamics, facilitating the formulation of effective air control strategies. Such strategies are vital for the issuance of accurate pollution warnings and reminders, thereby contributing to the mitigation of severe pollution impacts.
This investigation explores the transformative effect of the COVID-19 pandemic on the risk assessment processes employed by auditors. The primary focus is on how the pandemic has reshaped the identification and evaluation of risks, necessitating alterations in the timing, nature, and extent of risk assessment procedures (RAPs) in the audit risk assessment context. This study, through semi-structured interviews with audit partners and senior managers from Big Four and mid-tier firms in Malta, comprising a total of 15 interviews, delves into the evolving landscape of risk assessment. It has been observed that the pandemic demanded increased vigilance and effort from auditors in understanding clients' businesses and their operational environments. This heightened attention was crucial to identify emerging risks aptly. A shift in the RAPs was discerned, favoring inquiries and analytical procedures (APs) over traditional methods like observation and inspection. The incorporation of Information Technology (IT) tools has markedly transformed the approach to gathering sufficient and appropriate audit evidence, particularly in verifying inventories and property, plant, and equipment (PPE), along with third-party confirmations. Furthermore, the study identifies material risks such as going concern (GC), asset impairment (including plant, equipment, inventory, and receivables), and the impact of external events on companies. An important outcome of this shift is the increased reliance on Artificial Intelligence (AI) and blockchain-based applications, heralding a more efficient and effective risk assessment process. This evolution not only enhances audit quality but also serves the public interest more robustly. The findings imply a long-term impact on audit risk assessment, projecting a continued evolution in the post-COVID era. These insights contribute significantly to the discourse on audit practices in times of crisis, underscoring the need for adaptive methodologies and the integration of advanced technologies in audit procedures.
In the realm of financial markets, the manifestation of volatility clustering serves as a pivotal element, indicative of the inherent fluctuations characterizing financial instruments. This attribute acquires pronounced relevance within the sphere of cryptocurrencies, a sector renowned for its elevated risk profile. The present analysis, conducted through the Autoregressive Moving Average - Generalized Autoregressive Conditional Heteroskedasticity (ARMA-GARCH) model, seeks to elucidate the enduring nature of volatility clustering and the occurrence of leverage effects within this domain. Over the course of a four-year time frame, it was observed that Bitcoin diverges from the anticipated Autoregressive Conditional Heteroskedasticity (ARCH) effects, in contrast to Ethereum and Cardano, which exhibit marked volatility clustering. Binance Coin, Ripple, and Dogecoin, whilst demonstrating moderate clustering, uniformly reflect the existence of leverage effects. An exception to this pattern was identified in Ripple, where it was discerned that positive market news exerts a disproportionate influence on log returns. The findings of this study illuminate the critical influence of both leverage effects and volatility clustering on the pricing dynamics of cryptocurrencies. It underscores the imperative for a nuanced comprehension of risk management in the context of cryptocurrency investments, given their susceptibility to abrupt price fluctuations. The distinct degrees to which these phenomena are manifested across diverse cryptocurrencies accentuate the necessity for a tailored risk management approach, resonant with the unique attributes of the asset in question. Such strategies, accounting for the potential amplification of losses through leverage, may encompass prudent position sizing, portfolio diversification, and the implementation of stress tests, thereby fortifying the investment against the dual perils of volatility clustering and leverage effects. The implications of this analysis serve to inform investors, providing a foundation upon which to construct risk management tactics that are responsive to the idiosyncrasies of the cryptocurrency market.
In the context of increasing electric vehicle (EV) prevalence, the integration of renewable energy sources, particularly solar energy, into EV charging infrastructure has gained significant attention. This study investigates the economic viability of grid-connected photovoltaic (PV) systems for EV charging stations in Ngawi City, Indonesia, selected due to its substantial solar energy potential and ongoing renewable energy initiatives. Key factors influencing the economic feasibility of these systems include load requirements, renewable energy potential, system capacity, levelized cost of electricity, payback period, net present cost (NPC), and cost of energy (COE). A comprehensive techno-economic assessment was conducted to estimate the capital recovery time, incorporating both utilization costs and payback periods. The analysis utilized the Hybrid Optimization Model for Electric Renewables (HOMER) software, focusing on the application of PV energy in EV charging stations within Ngawi Regency. Findings indicate that a PV system-based generation approach can adequately meet the power needs of EV charging stations. Notably, this system is capable of generating surplus energy, which presents an opportunity for additional revenue, thus enhancing its economic attractiveness. The analysis determined that to produce an annual output of 562,227 kWh, a total of 1245 PV modules, each with a 370-watt capacity, are necessary. This off-grid PLTS system, relying exclusively on PV modules for electrical energy generation, can sufficiently supply a daily load of 342.99 kWh for an EV charging station. The study underscores the potential of solar-powered EV charging stations in contributing to sustainable urban development, reinforcing the integration of renewable energy into urban infrastructure.
This study conducted a comprehensive analysis of the carbon components in $\mathrm{PM}_{2.5}$ particulate matter in Linfen City for the year 2020. Utilizing the thermal-optical transmittance (TOT) method, the mass concentrations of organic carbon (OC) and elemental carbon (EC) in $\mathrm{PM}_{2.5}$ were quantitatively assessed. Findings revealed seasonal variations in the concentrations of $\mathrm{OC}$ and EC. Specifically, concentrations in spring were registered at $4.45 \mu \mathrm{g} / \mathrm{m}^3$ for OC and $1.03 \mu \mathrm{g} / \mathrm{m}^3$ for EC; in summer, these were $3.89 \mu \mathrm{g} / \mathrm{m}^3$ and $0.74 \mu \mathrm{g} / \mathrm{m}^3$; in autumn, $6.01 \mu \mathrm{g} / \mathrm{m}^3$ and $1.30 \mu \mathrm{g} / \mathrm{m}^3$; escalating significantly in winter to $16.76 \mu \mathrm{g} / \mathrm{m}^3$ for OC and $4.24 \mu \mathrm{g} / \mathrm{m}^3$ for EC. This seasonal trend highlighted a notable peak in winter, with OC concentrations being 4.31 times, and EC concentrations 5.73 times, those observed in summer. The correlation analysis between OC and EC demonstrated the highest correlation in winter $\left(\mathrm{R}^2=0.961\right)$, suggesting similar sources for these components in the colder months, followed by autumn $\left(\mathrm{R}^2=0.936\right)$ and spring $\left(\mathrm{R}^2=0.848\right)$, with the least correlation observed in summer $\left(\mathrm{R}^2=0.584\right)$. The EC tracer method, employed to estimate secondary organic carbon (SOC) concentrations, indicated a seasonal pattern in SOC levels, with the highest concentrations occurring in winter, thereby suggesting a significant secondary pollution impact during this period. Moreover, the study identified meteorological conditions, particularly long-distance horizontal transport, as a primary influencer of winter pollution levels in Linfen City.
The review provides a comprehensive overview of the application of membrane technology in addressing the challenges associated with water pollution and waste management. Membrane technology is a process used in various fields, primarily in filtration, separation, and purification applications. It involves the use of semi-permeable membranes to separate substances when a driving force is applied, such as pressure, concentration gradients, or electrical potential. The article highlights the role of membrane technology in sustainable remediation, focusing on its ability to remove contaminants from contaminated water sources. Various membrane-based processes, including reverse osmosis, nanofiltration, and ultrafiltration, are discussed in terms of their efficiency and effectiveness in achieving purified water and concentrated waste streams. It emphasizes the importance of recent trends in membrane technology for wastewater treatment, particularly in achieving high-quality effluent and meeting stringent regulatory standards. The integration of biological treatment with membrane filtration, as exemplified by membrane bioreactors (MBRs), is explored, along with their advantages in terms of biomass concentration, sludge reduction, and improved. The removal of suspended solids, pathogens, and micropollutants through membrane filtration is highlighted as a crucial aspect of wastewater treatment. Furthermore, the review article addresses the challenges and limitations associated with membrane technology, such as fouling, scaling, energy consumption, and membrane degradation. It discusses ongoing research efforts to develop sustainable membrane materials, advanced fouling control methods, and process optimization strategies to overcome these challenges. Overall, the review article provides valuable insights into the role of membrane technology in sustainable remediation and wastewater treatment, highlighting its potential for efficient water management, environmental protection, and resource recovery.
Open Access
