Browse Items (16481 total)
Sort by:
-
Optimized Multi-Scale Attention Convolutional Neural Network for Micro-Grid Energy Management System Employing in Internet of Things
The combination of micro-grid energy management systems (EMSs) with the Internet of Things (IoT) offers a promising way to improve energy use and distribution. However, challenges such as device compatibility and the difficulty of managing energy efficiently make it hard to implement these systems effectively. This study offers a significant advancement in energy management by using IoT for microgrid systems. An Optimized Multi-scale Attention Convolutional Neural Network for microgrid EMS employing IoT (OMACNN-MGEMS-IoT) is proposed in this study, which enables efficient monitoring and control of energy resources. The proposed model's input data are gathered from the MQTT dataset. This research employs a Regularized Bias-aware Ensemble Kalman Filter (RBAEKF) for pre-processing input data, ensuring the removal of outliers and updating missing values. The MACNN is then used for effective fault detection within the microgrid. To enhance its performance, the Sheep Flock Optimization Algorithm (SFOA) is introduced to optimize the MACNN parameters, ensuring accurate fault detection. Implemented on the MATLAB platform, the performance of the OMACNN-MGEMS-IoT method is assessed through various performance metrics, demonstrating significant improvements. Notably, the proposed method achieves higher cost reductions of 25%, 22%, and 26% compared to existing approaches such as the IoT platform for energy management in multi-micro grid systems (IoT-PEM-MMS), a micro-grid system infrastructure implementing IoT for efficient energy management in buildings (MSII-IoT-EEM) and a hybrid deep learning-based online energy management scheme for industrial microgrids (HDL-OEM-IM). The findings highlight the impact of the proposed OMACNN-MGEMS-IoT method in enhancing energy efficiency and cost-effectiveness in microgrid systems. 2025 John Wiley & Sons Ltd. -
Optimized placement and sizing of solar photovoltaic distributed generation using jellyfish search algorithm for enhanced power system performance
The strategic integration of distributed generation (DG) units into distribution power networks (DPNs) is pivotal for augmenting system efficiency and stability. This study introduces an advanced metaheuristic optimization framework leveraging the Jellyfish Search Algorithm (JSA) for the optimal placement and sizing of solar photovoltaic (PV) DG units. The formulated multi-objective function incorporates real power loss (RPL) minimization, voltage deviation index (VDI) reduction, and voltage stability index (VSI) enhancement, employing a weighted sum approach (WSA) to ensure computational rigor. The efficacy of the proposed methodology is rigorously validated on the IEEE 33-bus radial DPN under single and multiple PV system deployment scenarios. For single PV system optimized inclusion, RPL of the DPN is cut down from 210.98kW to 102.89kW, total VDI is reduced from 1.8047 p.u to 0.5331 p.u, and minimum VSI is increased from 0.6671 to 0.7559. For two PV DG units inclusion, RPL is reduced to 82.99kW, total VDI is reduced to 0.6518 p.u with a least VSI improved to 0.8848. However, better result is obtained with three units of DG placement with RPL reduced to 69.59kW, total VDI decreased to 0.3293 p.u with a least VSI of the test system increased to 0.8916. Comparative analyses against state-of-the-art metaheuristic algorithms underscore the superior convergence efficiency and optimality of JSA in addressing nonlinearity and high-dimensionality constraints. Empirical results substantiate substantial RPL reduction, bus voltage enhancement, and system stability reinforcement, establishing JSA as an avant-garde paradigm in DG optimization. This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply 2025. -
Optimized production of keratinolytic proteases from Bacillus tropicus LS27 and its application as a sustainable alternative for dehairing, destaining and metal recovery
The present study describes the isolation and characterization of Bacillus tropicus LS27 capable of keratinolytic protease production from Russell Market, Shivajinagar, Bangalore, Karnataka, with its diverse application. The ability of this strain to hydrolyze chicken feathers and skim milk was used to assess its keratinolytic and proteolytic properties. The strain identification was done using biochemical and molecular characterization using the 16S rRNA sequencing method. Further a sequential and systematic optimization of the factors affecting the keratinase production was done by initially sorting out the most influential factors (NaCl concentration, pH, inoculum level and incubation period in this study) through one factor at a time approach followed by central composite design based response surface methodology to enhance the keratinase production. Under optimized levels of NaCl (0.55 g/L), pH (7.35), inoculum level (5%) and incubation period (84 h), the keratinase production was enhanced from 41.62 U/mL to 401.67 9.23 U/mL (9.65 fold increase) that corresponds to a feather degradation of 32.67 1.36% was achieved. With regard to the cost effectiveness of application studies, the crude enzyme extracted from the optimized medium was tested for its potential dehairing, destaining and metal recovery properties. Complete dehairing was achieved within 48 h of treatment with crude enzyme without any visible damage to the collagen layer of goat skin. In destaining studies, combination of crude enzyme and detergent solution [1 mL detergent solution (5 mg/mL) and 1 mL crude enzyme] was found to be most effective in removing blood stains from cotton cloth. Silver recovery from used X-ray films was achieved within 6 min of treatment with crude enzyme maintained at 40 C. 2023 Elsevier Inc. -
Optimized score card for mentoring student using artificial intelligence and methods thereof /
Patent Number: 202011040658, Applicant: Dr Priti Verma.
The invention discloses a mentoring system capable of improving student™s performance in the field of Learning in Theoretical, practical, behavioral, sports, cultural activities and life skills for the betterment of the life of an individual. -
Optimized score card for mentoring students using artificial intelligence and methods thereof /
Patent Number: 202011040658, Applicant: Dr Priti Verma.
The invention discloses a mentoring system capable of improving student's performance in the field of Learning in Theoretical, practical, behavioral, sports, cultural activities and life skills for the betterment of the life of an individual. The feedback system has the capability of generating feedback with better accuracy and hence easily identifying the areas of weaknesses and strengths of the students. -
Optimized task group aggregation-based overflow handling on fog computing environment using neural computing
It is a non-deterministic challenge on a fog computing network to schedule resources or jobs in a manner that increases device efficacy and throughput, diminishes reply period, and maintains the system well-adjusted. Using Machine Learning as a component of neural computing, we developed an improved Task Group Aggregation (TGA) overflow handling system for fog computing environments. As a result of TGA usage in conjunction with an Artificial Neural Network (ANN), we may assess the models QoS characteristics to detect an overloaded server and then move the models data to virtual machines (VMs). Overloaded and underloaded virtual machines will be balanced according to parameters, such as CPU, memory, and bandwidth to control fog computing overflow concerns with the help of ANN and the machine learning concept. Additionally, the Artificial Bee Colony (ABC) algorithm, which is a neural computing system, is employed as an optimization technique to separate the services and users depending on their individual qualities. The response time and success rate were both enhanced using the newly proposed optimized ANN-based TGA algorithm. Compared to the present works minimal reaction time, the total improvement in average success rate is about 3.6189 percent, and Resource Scheduling Efficiency has improved by 3.9832 percent. In terms of virtual machine efficiency for resource scheduling, average success rate, average task completion success rate, and virtual machine response time are improved. The proposed TGA-based overflow handling on a fog computing domain enhances response time compared to the current approaches. Fog computing, for example, demonstrates how artificial intelligence-based systems can be made more efficient. 2021 by the authors. Licensee MDPI, Basel, Switzerland. -
Optimized Tree Strategy with Principal Component Analysis Using Feature Selection-Based Classification for Newborn Infant's Jaundice Symptoms
One of the most important and difficult research fields is newborn jaundice grading. The mitotic count is an important component in determining the severity of newborn jaundice. The use of principal component analysis (PCA) feature selection and an optimal tree strategy classifier to produce automatic mitotic detection in histopathology images and grading is given. This study makes use of real-time and benchmark datasets, as well as specific approaches for detecting jaundice in newborn newborns. According to research, the quality of the feature may have a negative impact on categorization performance. Additionally, compressing the classification method for exclusive main properties can result in a classification performance bottleneck. As a result, identifying appropriate characteristics for training the classifier is required. By combining a feature selection method with a classification model, this is possible. The major outcomes of this study revealed that image processing techniques are critical for predicting neonatal hyperbilirubinemia. Image processing is a method of translating analogue images to digital formats and manipulating them. The primary goal of medical image processing is to collect information useful for disease detection, diagnosis, monitoring, and therapy. Image datasets can be used to validate the performance of newborn jaundice detection. When compared to conventional approaches, it offers results that are accurate, quick, and time efficient. Accuracy, sensitivity, and specificity, which are common performance indicators, were also predictive. 2021 Debabrata Samanta et al. -
Optimized trimetallic CoNiFe phospho-boride electrocatalyst for overall seawater electrolysis
Utilizing abundant seawater for hydrogen production by electrolysis poses new challenges to electrocatalyst performance, demanding effectiveness, resilience, and selectivity for oxygen evolution reactions (OER) over undesired reactions in harsh saline conditions. Herein, trimetallic phospho-boride, CoNiFePB, was synthesized via a chemical reduction method by carefully tuning the concentrations of all elements for overall seawater splitting. The optimized CoNiFePB demonstrated superior OER activity, requiring only 239 mV to achieve 10 mA/cm2 in alkaline simulated seawater, outperforming bimetallic configurations (CoNiPB and CoFePB). The enhancement in hydrogen evolution reaction (HER) activity was attained by adjusting the B/P molar ratio in CoNiFePB, resulting in a low overpotential of 137 mV. A comprehensive kinetic analysis revealed that Ni and Fe play crucial roles in enhancing the adsorption and desorption of the reactant and product, respectively, while Co serves as the active site for intermediate formation, collectively boosting the activity of the trimetallic CoNiFePB. While the electron modulation achieved by B and P triggers the formation of active sites and avoids chloride ion oxidation. The bifunctional CoNiFePB catalyst deposited on Ni foam (NF) demonstrated excellent durability for 10,000 cycles and maintained performance for 70 h in chronoamperometric testing at a high current density of 0.7 A/cm2, emphasizing its long-term stability in alkaline seawater. When integrated into an advanced seawater electrolyzer with a zero-gap assembly, CoNiFePB/NF achieved a current density of 2 A/cm2 at a cell voltage of approximately 2.43 V in alkaline natural seawater. These findings provide significant insights into electrocatalysis for seawater splitting with promising implications for commercial applications. 2025 Elsevier B.V. -
Optimized uplink scheduling model through novel feedback architecture for wimax network
Broadband Wireless Access has drawn the fine attention due to the wide range of data requirement and user mobility all the time. Moreover, WiMAX provides the best QoE (Quality of Experience) which is based on the IEEE 802.16 standards; this includes several services such as data, video and audio. However, in order to provide the effective and smooth experience i.e. QoS scheduling plays one of the critical part. In past several mechanism has been proposed for effective scheduling however, through the research it is observed that it can be furthermore improvised hence in this we propose a mechanism named as OUS (Optimized Uplink Scheduling) which helps in improvising the QoS. In here, we have proposed a novel feedback architecture and proposed optimized scheduling which helps in computing the bandwidth request this in terms helps in reducing the delay as well as jitter. Moreover, the performance evaluation is performed through extensive simulation by varying the different SS and frequency and the results analysis confirms that our mechanism performs way better than the existing algorithm. BEIESP. -
Optimizing Algorithmic Trading Through DRL: A Comparative Analysis of Single-Agent and Multi-Agent Models
This work investigates how Deep Reinforcement Learning (DRL) can elevate algorithmic tradingespecially in fast-paced, high-frequency markets. We propose a full-fledged framework to compare different setups, from solo agents to multi-agent systems, applying DRL methods like Proximal Policy Optimization (PPO), Deep Q-Network (DQN), and Advantage Actor-Critic (A2C), along with combinations of these. We trained on hourly stock data from 24 firms over two years (Jan 1, 2020Jan 1, 2022) and tested performance over the next year (Jan 1, 2022Jan 1, 2023). We evaluated key factorsreturns, risk control, and how well these models adapt to changing markets. The single-agent PPO model stood out, achieving a remarkable profit factor of 28.07 on BIDU and keeping peak drawdowns frequently under 1%. This demonstrates both solid capital protection and high risk-adjusted performance. Ensemble models showed balanced performance in both single-agent and multi-agent setups, achieving a Sharpe ratio of 0.75 and Sortino ratios up to 7.7, outperforming existing benchmarks. Comparative analyses revealed that ensemble strategies enhance market responsiveness and improve both stability and profitability in volatile environments. Sensitivity analysis confirmed the robustness of model performance across various hyperparameter settings. Overall, the proposed DRL-based ensemble framework demonstrates strong potential to improve real-world HFT systems by delivering more adaptive, stable, and efficient algorithmic trading solutions. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Optimizing Antenna Structures for 60 GHz Systems Microstrip Patch vs Microstrip Slot
This paper conducts a thorough comparison between microstrip patch and microstrip slot antennas for 60 GHz wireless communication systems, excluding the meander line antenna. The design process involves meticulous selection of substrate material, antenna geometry, and feed mechanism to achieve a compact, efficient, and wideband antenna suitable for 60 GHz applications. Performance analysis, based on theoretical derivations and HFSS simulator simulations, covers key parameters like radiation pattern, gain, and bandwidth. Results demonstrate that the proposed microstrip antenna meets 60 GHz system requirements, indicating potential for further optimization. The study highlights the unique advantages and disadvantages of each antenna structure, emphasizing that selection should align with specific application needs. This comparative analysis aids researchers and engineers in making informed decisions regarding the most suitable antenna structure for their 60 GHz wireless communication requirements. 2024 IEEE. -
Optimizing Base Station Placement toMinimize Interference forSatellite Terrestrial Networks (STN)
The rapid advancement of 5G and 6G technologies has spurred the development of Satellite-Terrestrial Networks (STNs), integrating terrestrial infrastructure with Low Earth Orbit (LEO) satellites to enable seamless global connectivity. Efficient spectrum allocation and interference management remain major challenges due to limited resources and the dynamic behavior of satellites. This study addresses these challenges by optimizing base station (BS) deployment to enhance spectral efficiency and reduce interference in STN environments. Delaunay Triangulation (DT) is employed to establish initial spatial separation between BSs, followed by gradient descent (GD) for fine-tuned optimization. Simulation results demonstrate that the optimized scenario substantially reduces interference and improves key performance metrics, including SINR, INR, CI Ratio, and received power, with gains ranging from 30% to 400%. These findings, derived from small-scale simulations, indicate the frameworks potential for enhancing STN performance in dense and interference-prone environments and provide a foundation for future research on interference-resilient STN architectures. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Optimizing Car Recommendations: Power Analysis of Machine Learning Algorithms
The growing demand for efficient automobile recommendation systems has called for the need of algorithms that can proficiently assess and predict user preferences. This research focuses on the assessment of various machine learning algorithms, K-Nearest Neighbors (KNN), Decision Trees, Linear Regression, Weighted Scoring, and Content-Based Filtering. One of the main concerns of this study is to identify which recommendation algorithm is best suited for vehicle suggestions from an application perspective based on cost, mileage, engine size, fuel category, and user reviews. A dataset of 100 records was utilized to perform preliminary analyses so that algorithms were tested. Preprocessing procedures involved missing data handling, normalization of numerical features, and categorical variables encoding so that full precision predictions were obtained. Performances of algorithms were tested in terms of accuracy, scalability, and computational efficiency. Based on results, the highest accuracy was realized by Decision Trees with 85%, followed by Weighted Scoring at 82% and Linear Regression at 78%. Although KNN has an excellent accuracy of 74%, it is less scalable for very large datasets that are needed for an automobile recommendation system. The experimental results of this paper add to the evolving knowledge on the application of machine learning in the automobile world, again reinforcing the adequacy of Decision Trees as a valid technique for car recommendation systems. Recommendations for future studies include enhancing the database and exploring contemporary approaches to improve the accuracy of recommendations. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Optimizing citrus disease detection: a transferable convolutional neural network model enhanced with the fruitfly optimization algorithm
Fungal, bacterial, and viral diseases significantly threaten citrus production and quality worldwide, prompting producers to explore technological solutions to mitigate the financial impact of these diseases. Image analysis techniques have emerged as powerful tools for detecting citrus diseases by differentiating between healthy and diseased specimens through the extraction of discriminative features from input images. This paper introduces a valuable dataset comprising 953 color images of orange leaves from the species Citrus sinensis (L.) Osbeck, which serves to train, evaluate, and compare various algorithms aimed at identifying abnormalities in citrus fruits. The development of automated detection systems is crucial for reducing economic losses in citrus production, with this research focusing on twelve specific diseases and nutrient deficiencies. We propose a novel approach to citrus plant disease detection utilizing a hyper-parameter tuned transferrable convolutional neural network (TCNN) model, referred to as the enhanced fruitfly optimization algorithm (EFOA)-TCNN model. This model optimizes the parameters of TCNN using the EFOA and enhances architectural design by incorporating three convolutional layers alongside an energy layer instead of a traditional pooling layer. Experimental results demonstrate that the proposed EFOA-TCNN model outperforms existing state-of-the-art methods, achieving a sensitivity of 0.975 and an accuracy of 0.995. 2025, Institute of Advanced Engineering and Science. All rights reserved. -
Optimizing Cybersecurity in Digital Domain Through Proactive Cyber Monitoring
In todays linked digital landscape, cybersecurity is a top priority for individuals, organizations, and governments alike. As cyber threats grow in sophistication and frequency, the necessity for proactive and comprehensive defense strategies become more pressing. This study paper goes into the topic of improving cybersecurity through proactive cyber monitoring, providing an in-depth analysis of both hacker approaches and defense strategies. The study takes a multifaceted approach, starting with a thorough examination of common hacking strategies used by cyber enemies. By deconstructing popular attack routes such as phishing, virus propagation, and social engineering, the article sheds light on the complexities of cyber threats and hostile actors strategies for exploiting system vulnerabilities. Building on this foundation, the study investigates proactive cyber monitoring as a proactive defensive measure. Organizations can improve their cybersecurity posture by using advanced monitoring technologies, anomaly detection algorithms, and threat intelligence feeds to identify and mitigate possible threats before they become full-scale attacks. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Optimizing Diabetes Prediction Models for Enhanced Health Data Processing
Diabetes prediction is crucial for early intervention and personalized treatment. This study uses a multimodal strategy, including prediction algorithms, downsampling, feature engineering, exploratory data analysis (EDA), cross-validation, and classification techniques. EDA is used to understand diabetes-specific features, while downsampling ensures fair representation of instances with and without diabetes. Classification algorithms categorize people into appropriate diabetes risk groups using machine learning. Cross-validation evaluates predictive models in various data scenarios. The study emphasizes the value of specialized methods and domain-specific expertise in diabetes prediction, emphasizing the need for accurate risk assessment in healthcare decision-making and the potential for proactive interventions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Optimizing Disease Diagnosis and Treatment Through AI and Deep Learning Algorithms
A Primer for Cancer Center Leaders Session 2 Natural Language Processing for Biomedical Text Medical data is not only numeric but also composed of unstructured text. These algorithms listen to various medical imaging, genomic data, and electronic health records to find correlations that can predict different diseases. Using convolutional neural networks to analyze images and recurrent neural networks to process sequential data, AI systems improve diagnostic accuracy and minimize the risk of human error. Additionally, deep learning algorithms targets patient-oriented drug administration by predicting therapeutic responses of individual patients, enhancing treatment response. Incorporating AI into clinical workflows allows us to synthesize vast datasets in real-time, provide clinicians with action items, and advocate for evidence-based medicine. However, problems including data privacy, model interpretability, and the need for large, annotated datasets continue. Such solutions in the form of explainable AI and deep learning would play an integral role in promoting the usage of these technologies over a longer duration in the medical ecosystem. This work shows how AI and deep learning can open avenues that may fundamentally change disease detection and treatments, leading to improved diagnosis and treatments tailored to the individual patient. 2025 IEEE. -
Optimizing Drug Discovery for Breast Cancer in a Laboratory Environment Using Machine Learning
Breast cancer therapy can be greatly enhanced by the proposed method that combines experimental and computational techniques. Employing a state-of-the-art in vitro system, we evaluated biopsy tissues at different cancer stages, monitoring them for 48 hours. Later on, our investigation involved the application of machine learning models including nae Bayes (NB), artificial neural networks (ANN), random forest (RF), and decision trees (DT). Surprisingly, these models reached high test accuracies - ANN 93.2%, NB 90.4%, DT 87.8%, and RF 85.9%. The dataset's impedance dynamics data provide evidence for treatment efficacy. Therapeutic strategies need to be adjusted for particular patients and their stage of cancer since the results underscore the usefulness of personalized breast cancer therapy. This study will significantly contribute to new tailored treatment options available for breast cancer patients. 2024 IEEE. -
Optimizing energy consumption in iot sensors through deep learning-based power management
The rapid growth of internet of things (IoT) devices necessitates efficient power management to curb escalating energy consumption. This chapter proposes a novel solution by employing deep learning techniques to optimize energy use in IoT sensors. The authors review existing IoT sensor energy consumption challenges and conventionalpower management limitations. Drawing ondeep learning's successes, they develop an architecture trained on curated sensor data. Practical implications span industries, scalability, and generalizability to diverse IoT setups. Economic insights highlight potential cost savings and benefits. In conclusion, the innovative deep learning-based approach addressesIoT energy challenges, offering a promising solution that optimizes usage and could reshape IoT device efficiency. This work opens avenues for hybrid strategies, merging deep learning with other techniques, further advancing energy efficient IoT systems. 2025 by IGI Global Scientific Publishing. All rights reserved. -
Optimizing energy consumption in wireless sensor networks using python libraries
Wireless sensor networks (WSNs) are widely utilized in various fields, including environmental monitoring, healthcare, and industrial automation. Optimizing energy consumption is one of the most challenging aspects of WSNs due to the limited capacity of the batteries that power the sensors. This chapter explores using Python libraries to optimize the energy consumption of WSNs. In WSNs, various nodes, including sensor, relay, and sink nodes, are introduced. How Python libraries such as NumPy, Pandas, Scikit-Learn, and Matplotlib can be used to optimize energy consumption is discussed. Techniques for optimizing energy consumption, such as data aggregation, duty cycling, and power management, are also presented. By employing these techniques and Python libraries, the energy consumption of WSNs can be drastically decreased, thereby extending battery life and boosting performance. 2023, IGI Global. All rights reserved.