Search

A recent study conducted by researchers at Cochin University of Science and Technology explores the use of an ensemble approach for predicting associations between circular RNAs (circRNAs) and diseases. CircRNAs are non-coding RNAs that play a role in regulating genes and have been linked to various diseases. The proposed model, called VAGA-CDA, combines the use of a variational autoencoder and a genetic algorithm to predict novel circRNA-disease associations. The model achieved high accuracy in predicting these associations, demonstrating its robustness. This research contributes to the field of bioinformatics and computational biology and has implications for disease diagnosis, prevention, and treatment. [Extracted from the article]

A recent report from the Affiliated Hospital of Nanjing University Medical School discusses the need for biomarkers to guide treatment decisions in hepatocellular carcinoma (HCC), a leading cause of cancer deaths. The researchers used radiological data and machine learning techniques to develop a model that predicts the short-term efficacy of immunotherapy in HCC patients. They found that certain radiomics features derived from CT imaging, such as Gray Level Run Length Matrix (GLRLM) and Intensity Direct, were correlated with immunotherapy response. The study concludes that the machine learning model accurately forecasts the short-term efficacy of immunotherapy in HCC. [Extracted from the article]

A recent study conducted by researchers at ITMO University in St. Petersburg, Russia, has proposed an innovative approach to selectively eradicating pathogenic bacteria using antimicrobial nanoparticles. The researchers compiled a comprehensive database to characterize nanoparticles and their antibacterial activity, and then trained machine learning models to predict the minimal concentration and zone of inhibition of these nanoparticles. They also developed a machine learning reinforced genetic algorithm to identify the best-performing selective antibacterial nanoparticles. As a proof of concept, they identified a selectively antibacterial nanoparticle, CuO, for the targeted eradication of Staphylococcus aureus. These findings contribute to the emerging research domain of selectively toxic nanoparticles and have potential applications in the development of new antimicrobial therapies. [Extracted from the article]

A study conducted at the First Hospital of Jiaxing in China explores the use of MRI analysis for brain tumor diagnosis. The researchers propose a novel approach that optimizes the configuration of Convolutional Neural Networks (CNNs) and Artificial Neural Networks (ANNs) to improve the efficiency of learning models in brain tumor diagnosis. The suggested approach utilizes CNNs for brain MRI segmentation, with configurable hyper-parameters tuned using a genetic algorithm. The results indicate that this method achieves an average accuracy improvement of at least 1.1% over previous methods. [Extracted from the article]

A study conducted by researchers at Universitas Dian Nuswantoro in Semarang, Indonesia, aimed to optimize early prediction of coronary heart disease (CHD) using a genetic algorithm-based convolutional neural network (CNN) feature engineering approach. The researchers utilized a genetic algorithm for hyperparameter optimization and information gain for feature selection optimization, resulting in a CNN model that outperformed traditional methods and achieved a peak accuracy of 85% in hyperparameter optimization and 100% accuracy when integrated with machine learning algorithms. The integration of a genetic algorithm into CNN feature engineering shows promise for improving the accuracy of CHD predictions and could potentially be used for early detection in clinical settings. Future work will focus on expanding the approach to include a wider range of CHD data and potential integration with wearable technology for continuous health monitoring. [Extracted from the article]

Researchers from Universidade Nove de Julho in Sao Paulo, Brazil, have published a report exploring the application of complex network models and genetic algorithms in epidemiological modeling. The study aims to replicate the dynamics of disease spread in urban environments by accurately mapping individual contacts and social networks. Using a genetic algorithm, the researchers estimate the input parameters for network construction and simulate disease transmission within these networks. The results demonstrate the networks' resemblance to real social interactions and highlight the potential of complex network models and genetic algorithms in predicting and managing public health crises. [Extracted from the article]

A recent report from the Universidad Carlos III de Madrid discusses research findings on experimental stress. The study focuses on the calibration of a visco-hyperelastic model for soft tissue simulants, such as ballistic gelatin and styrene-ethylene-butylene-styrene. The researchers used a genetic algorithm to fit experimental stress-strain curves and calculate material model parameters with high accuracy. The study concludes that the semi-free relaxation time strategy yielded the most accurate results and shorter convergence times. This research provides valuable insights into understanding the mechanical response of soft tissues and can be applied to various strain rates. [Extracted from the article]

A study conducted by researchers at Islamic Azad University in Mashhad, Iran, explores a new method for detecting arousal levels through the analysis of electroencephalography (EEG) signals. The study utilizes a 64-channel EEG system and employs a genetic algorithm for feature selection to enhance classification accuracy. The results demonstrate the effectiveness of the proposed method in detecting arousal levels across diverse states, with improvements in accuracy, sensitivity, and specificity. The researchers conclude that the method has a high capability of detecting arousal levels in different scenarios and highlight the advantage of employing the proposed feature reduction method. [Extracted from the article]

A recent study conducted by researchers at Princess Nourah bint Abdulrahman University in Riyadh, Saudi Arabia, has developed a new approach called Swin-GA-RF to enhance the classification of cervical cells in Pap smear images for the detection of cervical cancer. The Swin-GA-RF approach combines the Swin transformer, genetic algorithm feature selection, and a random forest classifier. The researchers compared the performance of Swin-GA-RF with pre-trained CNN models and found that Swin-GA-RF outperformed other models in both binary and five-class classification tasks. These findings suggest that the Swin-GA-RF approach could be a valuable tool for early diagnosis and screening programs for cervical cancer. [Extracted from the article]

A recent report from the University Veracruzana in Mexico discusses the use of animation-based works for human-computer interaction applications. The researchers developed a method to generate animations of sign language letters using a numerical traced algorithm based on homotopy. The parameters of the algorithm were optimized with a genetic algorithm, and the resulting animations were found to be consistent with the execution of the letters by a person. The researchers suggest that these animations could be used in various deaf interaction applications to provide assistance. [Extracted from the article]

A study conducted by researchers at Jordan University of Science and Technology explores the use of a Siamese Network Genetic Algorithm (SN-GA) for classifying brain images related to various diseases. The researchers optimized a Bi-Convolutional Neural Network (Bi-CNN) using a genetic algorithm and evaluated its effectiveness using two datasets: brain tumors and Alzheimer's disease. The results showed that the proposed Siamese model achieved high levels of accuracy, precision, and recall, indicating its potential for advancing medical imaging and diagnosis in the context of brain diseases. The study emphasizes the importance of early intervention and patient care in conditions like Alzheimer's disease, which is projected to affect a significant number of people in the future. [Extracted from the article]

A research report from the Centro Federal de Educacao Tecnologica de Minas Gerais discusses a novel approach to controlling the Aedes aegypti mosquito, which is the main vector for diseases such as dengue, yellow fever, Zika, and chikungunya. The study proposes a two-dimensional diffusion-reaction model that describes the interaction between aquatic and adult female stages of the mosquito, taking into account parameters dependent on rainfall and temperature. The researchers used optimization techniques and genetic algorithms to find optimal solutions for minimizing the mosquito population. Numerical results showed a significant reduction in the Aedes aegypti population. [Extracted from the article]

A study conducted in Imphal, India, explores the use of machine learning algorithms to automatically classify dental types and anomalies using panoramic radiography images. The researchers propose an innovative approach using hyperparameter-optimized Random Forest ensemble learning achieved through Genetic Algorithm. The model achieved an impressive 98% accuracy in classifying dental types and anomalies. The study suggests that this approach could be applied in real-time for telemedicine and assist dental professionals in making decisions about prevention, diagnosis, and treatment planning. [Extracted from the article]

A report from Shahid Sadoughi University of Medical Sciences in Iran discusses a study on environmental health and sustainable development. The study focuses on the optimization of sound absorption coefficient (AC) using three different optimization methods: Guided Local Search (GLS), Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). The researchers found that GA and PSO were suitable methods for optimizing the AC of metal foam in both low and high frequencies. This research provides valuable insights into passive sound control and its potential applications in various fields. [Extracted from the article]

A study conducted by researchers at the Vellore Institute of Technology (VIT) in Chennai, India, focuses on the detection and treatment of skin diseases. The researchers highlight the complexity of diagnosing skin diseases due to the existence of approximately 3000 different types. They propose a deep learning-based system that utilizes an ensemble method with existing architectures to enhance performance in detecting and classifying skin diseases. The system achieves a Top-5 accuracy of 74% on the DermNet dataset and an accuracy of 91.73% on the HAM10000 dataset, showing improvements over previous works. The study provides valuable insights into the development of more accurate skin disease detection tools. [Extracted from the article]

A study compared the use of supervised machine learning variable selection methods in the psychological sciences. The researchers found that reducing the number of variables in a prediction model is important for various reasons, such as data collection efficiency. They evaluated five different variable selection methods and found that the genetic algorithm performed the best, with the lowest error rates in hold-out samples. However, the choice of method should be based on the specific performance measure that researchers deem most important. The study has not yet undergone peer review. [Extracted from the article]

Researchers from Southeast University in Nanjing, China have developed a constrained maximum power point tracking (MPPT) strategy for wave energy converters (WECs) using magnetic lead screws (MLSs). MLSs have been found to be efficient and powerful in sustainable wave energy conversion. The study analyzed the mechanism of MLS and established a dynamic model for MLS-based WECs. An adaptive constrained genetic algorithm (ACGA) was used to achieve MPPT under constraints, and simulations and experiments were conducted to verify the effectiveness of the strategy. The proposed ACGA improved the energy harvest rate by 3.95% to 6% compared to the standard constrained genetic algorithm (SCGA). [Extracted from the article]

Researchers from the University of Basque Country in Leioa, Spain have developed a quantum genetic algorithm (GA) that utilizes independent registers to codify individuals. The algorithm incorporates population-based search, selection of individuals, crossover, and mutation. The researchers analyzed the performance of different quantum cloning machines and found that while one had faster convergence, the other produced better final populations. They also introduced a mutation subroutine and determined that it had a minor impact on average performance. The algorithm was proven to have exponential convergence through a quantum channel analysis. [Extracted from the article]

Researchers at Beijing Information Science and Technology University have proposed a cache distribution strategy based on epidemic dynamics for 6G edge networks. By caching popular content on edge servers closer to users, the transmission load of backhaul links can be reduced. The strategy, called CDSED, utilizes a cache content model and a genetic-annealing cache content algorithm to predict cache content prevalence and maximize cache success ratio. Simulation results show that CDSED outperforms other caching strategies. [Extracted from the article]

• Jointly consider the task dependency and edge cloud environment. • Combine deep reinforcement learning and genetic algorithm. • Generate the initial population of genetic algorithm by DQN. Edge computing can greatly decrease the delay between users and cloud servers, which can significantly improve system service performance. However, it remains challenging for more efficient scheduling and allocation of users' application demands with dependence constraints to edge cloud servers. Due to the randomness of the initial population, traditional intelligent optimization algorithms have poor convergence speed in addressing resource scheduling. Therefore, to minimize the execution time of the application, this paper proposes a hybrid algorithm to solve the resource scheduling problem with parallelism and subtask dependency. To improve the convergence speed of the algorithm, this paper makes full use of the features of deep Q networks (DQN) and genetic algorithms (GA). The initial population of GA is generated using DQN. Finally, to evaluate the effectiveness of our proposed algorithm, this paper selects three real scientific workflows for experiments. The experimental results show that the hybrid algorithm can converge quickly and improve the optimization effect in a short time. [ABSTRACT FROM AUTHOR]

A study conducted at the University of Bologna in Italy explores the use of a hybrid approach that combines genetic algorithms and machine learning to address the order picking batch assignment problem in manual order picking systems. The study aims to consider the human factors of learning and fatigue, as well as the quantitative and spatial features of picking orders, to estimate the time required for order execution. The researchers propose a non-linear machine learning-based predictive model to predict batch picking time and use a genetic algorithm to optimize the assignment of future planned batches of orders to pickers. The study utilizes one year of picking data from a grocery retailer's warehouse and compares the proposed approach with linear models and an assignment strategy that does not optimize learning and fatigue indicators. The research concludes with an analysis of how quantitative and spatial features of batches and learning and fatigue indicators affect batch picking time. [Extracted from the article]

A study conducted at the University of Hyderabad in India has developed a deep learning and genetic algorithm-based ensemble model for the classification of breast ultrasound images. The researchers compared the performance of different deep neural networks and found that MobileNet was optimal for feature extraction. They used a genetic algorithm for feature selection and created an ensemble model that demonstrated improved diagnostic accuracy for breast abnormality identification. This research has the potential to improve treatment outcomes for breast cancer patients. [Extracted from the article]

A study conducted at the Faculty of Sciences in Oujda, Morocco, has developed a fusion framework that combines deep learning and a genetic algorithm to classify femoral neck fracture images. The researchers trained a convolutional neural network (CNN) on a dataset of 10,000 real patient cases and achieved an accuracy of 97%. The CNN model is currently being used by seven doctors at the University Hospital Center of Oujda. This research has been peer-reviewed and provides valuable insights into the automated classification of femoral neck fractures. [Extracted from the article]

A recent study conducted at Rowan University in Glassboro, New Jersey, has focused on the development of a robot-assisted mechanism for femur fracture surgery. The researchers aimed to address the limitations of traditional mechanisms by creating a 3-RRPS parallel mechanism called Robossis. They proposed an optimal design methodology using a single-objective genetic algorithm to evaluate different configurations based on clinical and mechanical design criteria. Experimental results showed that Robossis had an average error of 0.31 mm during force testing. This research has been peer-reviewed and provides valuable insights into the potential of robotics in long-bone fracture surgery. [Extracted from the article]

A report from the Kalasalingam Academy of Research and Education in Virudunagar, India discusses the development of an interactive toy agent that uses deep learning to teach autistic children yoga. The objective of the toy is to help autistic children become more socially adaptable by understanding their basic needs and acting as a companion. The toy is controlled by touch sensors and recognizes yoga postures performed by the child. The research concludes that the proposed framework is cost-effective compared to other humanoid toys. [Extracted from the article]

Researchers from VIT Bhopal University in Madhya Pradesh, India have developed a novel priority-based self-guided serial-parallel genetic algorithm for low-dose computed tomography (CT) reconstruction. The algorithm combines serial and parallel processing elements to reduce the loss of diversity in the population and increase the convergence rate. It also uses priority-based hybrid crossover and adaptive priority-based mutation operators to generate suitable offspring. Experimental results show that the algorithm produces satisfactory results with limited-view projections and outperforms other limited-view CT reconstruction algorithms. This research has been peer-reviewed and published in Applied Soft Computing. [Extracted from the article]

A study conducted by researchers at North Carolina State University has developed a multi-objective optimization framework to determine the optimal dosing and treatment duration for chemotherapy. The framework utilizes patient-specific biological parameters to create a mathematical model of cell population dynamics in the patient's body. By employing evolutionary heuristic search methods and a prescriptive analytics approach, the framework optimizes therapy sessions that transition from treatment to relaxation, adjusting the chemotherapy dose to reduce tumor cells while preserving host cells. This approach is particularly valuable in healthcare settings with limited resources, as it ensures efficient allocation and identifies high-risk patients for optimized resource utilization. [Extracted from the article]

A study conducted by researchers at China University of Mining and Technology explores the challenges of transporting medical waste generated by medical institutions (MIs) to disposal centers (DCs). The researchers propose a bi-level optimization model that aims to minimize costs and transportation risks associated with medical waste transportation. They use a simulated annealing algorithm and an improved genetic algorithm to address the optimal location problem and the capacity-constrained vehicle routing problem, respectively. The study emphasizes the importance of travel time reliability and loading reliability in designing an efficient medical waste recycling network. The researchers found that their modified genetic algorithm exhibited superior performance compared to other methods. [Extracted from the article]

A research report from Zhejiang University in Hangzhou, China, discusses the challenges of optimizing the performance of robots in intelligent manufacturing. The researchers propose a novel method called accelerated gradient descent and directed-mutagenesis genetic algorithm (AGD-DGA) for efficient robotic motion planning and performance optimization. The method considers optimization objectives such as time, energy consumption, and impact, and incorporates a power loss sub-model to improve evaluation accuracy. The researchers also introduce a directed-mutagenesis genetic algorithm to address the problem of local optima. Simulation and experimental results demonstrate that the proposed method outperforms existing algorithms in terms of optimization efficiency, success rate, and motion performance. The research concludes that the modified energy consumption model achieves high evaluation accuracy while maintaining computational efficiency. [Extracted from the article]

A recent study conducted by researchers from the National Autonomous University of Mexico (UNAM) explores the use of biomimetics in modeling the electrical activity of the heart. The researchers developed a mathematical model based on transfer functions and genetic algorithms to optimize heart dynamics. The model achieved a high level of accuracy in approximating real electrocardiography (ECG) signals, with a root-mean-square error of 4.7% and an R2 value of 0.72. The simplicity of the model allows for easy adjustment of waveform parameters, making it advantageous over other complex models. This research contributes to the understanding and improvement of heart disease detection and treatment. [Extracted from the article]

A recent study conducted by researchers at Jouf University has explored the use of machine learning models for the detection of dyslexia, a specialized learning disability that can impact academic performance. The researchers combined various machine learning models and introduced an optimal ensemble learning model based on genetic algorithms to improve prediction accuracy. The study found that their proposed technique significantly increased accuracy in predicting dyslexia. This research provides new insights into the potential use of machine learning in dyslexia detection, particularly for languages with straightforward orthographies like Arabic and Spanish. [Extracted from the article]

A study conducted by researchers at Taipei Medical University in Taiwan has proposed a novel framework called TPTM-HANN-GA for predicting the risk of cardiovascular disease (CVD). This framework integrates the Taguchi method, an artificial neural network (ANN), and a genetic algorithm (GA) to optimize the hyperparameters of the ANN model. The optimized ANN model achieved 74.25% accuracy in predicting CVD risk, surpassing existing models. The researchers believe that this framework can enable personalized CVD prediction on low-power computers and edge-AI devices, empowering individuals to effectively manage their heart health. [Extracted from the article]

A study conducted at the Vellore Institute of Technology in Tamil Nadu, India, has proposed a genetic algorithm and federated learning (GA-FL) approach to predict the risk of stroke in individuals. The researchers highlight the need for immediate diagnosis and treatment of stroke, and the role that artificial intelligence-based machine learning algorithms can play in prediction. The GA-FL model addresses concerns about data security and privacy by using federated learning, which allows for the exchange of training parameters without sharing the data itself. The study concludes that the GA-FL model provides enhanced security and more accurate stroke risk prediction compared to existing algorithms. [Extracted from the article]

The patent application titled "Ems Decision Support Interface, Event History, And Related Tools" discusses the use of computer-automated diagnosis in pre-hospital and acute care treatment settings to improve patient treatment. It explores the use of algorithms such as Bayesian algorithms, neural networks, and genetic algorithms for automated differential diagnosis. The application addresses the challenges of implementing automated differential diagnosis systems in emergency medical settings and proposes a system that integrates a tool for caregivers to perform a more efficient and accurate differential diagnosis during emergency situations. The method and system involve displaying a user interface with softkeys, collecting physiological data, displaying a clinical decision support tree, and incorporating event markers, playback controls, and a clinical decision support system. The patent application was filed in October 2023. [Extracted from the article]

A study conducted by researchers at the University of Mohaghegh Ardabili in Ardebil, Iran, has developed a method for the simultaneous determination of acetaminophen (ACT) and diclofenac (DCF) using a voltammetric approach and chemometric tools. ACT and DCF are nonsteroidal anti-inflammatory drugs (NSAIDs) known for their antipyretic, analgesic, and anti-inflammatory properties. The researchers used differential pulse voltammetry to establish a calibration set and evaluated the effectiveness of chemometric methods by analyzing synthetic mixtures and real samples. The study concluded that the developed method yielded favorable results for the simultaneous determination of ACT and DCF. [Extracted from the article]

Researchers from the College of Electrical and Computer Engineering in Hsinchu, Taiwan, have used finite element analysis to study the electrical conductivity profile of simulated stroke patients. They utilized a divide-and-conquer method and adaptive genetic algorithm to reconstruct the conductivity distribution inside the brain based on simulated stroke data. The study suggests that it may be possible to approximate the electrical conductivity distribution using a 45 dB signal-to-noise ratio measurement. The research was supported by the Ministry of Science and Technology, Taiwan, and published in IEEE Transactions on Magnetics. [Extracted from the article]

Hutom Co. Ltd., a company based in Seoul, South Korea, has been issued a patent for a method and device for optimizing surgery. The patent describes a method that uses a genetic algorithm to derive an optimized surgical procedure and instrument. It also includes a simulation of the surgical operation within a virtual body model to calculate the operation range of the surgical instrument and determine its structure. The method also provides an optimal entry position for the surgical instrument on the body surface of the patient. This technology aims to improve the accuracy and effectiveness of minimally invasive surgeries, such as laparoscopic and robot-assisted surgeries. [Extracted from the article]

Researchers from State University in Ukraine have published a report on telemedicine, proposing a method based on a genetic algorithm for optimizing the structure of telemedicine networks. The algorithm aims to ensure that the distribution of users and telemedicine stations is optimal in terms of signal delay time and network deployment cost. The researchers found that the proposed method produced close to optimal results and avoided local extremum. Future research could explore the scalability of this approach for larger networks and consider factors such as energy efficiency and fault tolerance. [Extracted from the article]

A recent study conducted in Telangana, India, explores the use of self-organizing maps and vulnerability data analysis to verify symptoms of fetal brain tumor glioblastoma. Glioblastoma is a disease caused by abnormal cells in the brain, which can be detected using MRI brain imaging. If left untreated, glioblastoma can be fatal, so early diagnosis is crucial. The study proposes a method that achieves a high accuracy rate of 98.12% in diagnosing glioblastoma, outperforming other methods such as genetic algorithms and support vector machines. This research has the potential to improve the diagnosis and treatment of brain cancer in both children and adults. [Extracted from the article]

International Business Machines Corporation (IBM) has been issued a patent for cohort selection for agile processes. The patent describes methods and systems for assigning entities, such as people, to different groups in processes like clinical studies. The invention utilizes genetic algorithms to determine rankings and measure fitness of entities in each group. The patent also includes a computer program product and a system that implement these methods. The patent was filed on April 29, 2019, and published online on April 9, 2024. [Extracted from the article]

A study conducted at Velagapudi Ramakrishna Siddhartha Engineering College explores the use of a genetic algorithm-based decision tree to detect dementia through MRI analysis. The researchers emphasize the importance of early and accurate detection of dementia for optimal therapy and management. By analyzing a large collection of MRI images and associated clinical data, the decision tree algorithm achieved an impressive accuracy rate of 96.67%. This research contributes to the development of a non-invasive diagnostic tool for dementia detection. [Extracted from the article]

Researchers at South China University of Technology have conducted a study on Streptomyces parvus, a type of bacteria, to optimize the production of a compound called 4'-N-demethyl-vicenistatin. This compound has potential applications in the pharmaceutical industry due to its antitumor activity. The researchers used a sequential approach involving various experimental designs and statistical models to identify the key components of the culture medium that influence the production of 4'-N-demethyl-vicenistatin. They found that cassava starch, glycerol, and seawater salt were the most important components. By employing an artificial-neural-network-genetic-algorithm model, they were able to achieve the highest production of 4'-N-demethyl-vicenistatin. This study provides valuable insights into optimizing the production of this compound. [Extracted from the article]

Phillips 66 Company has been issued a patent for a chemometric characterization process for refinery hydrocarbon streams. The process involves analyzing a sample of a hydrocarbon stream using various analytical methods, transforming the spectral data using wavelet theory, and training a genetic algorithm to classify the sample into different groups based on specific attributes. The trained algorithm can then be used to determine the appropriate action to take with the hydrocarbon stream, such as converting it into liquid transportation fuels or altering refinery operations. This process allows for rapid assessment of hydrocarbon stream attributes, optimizing refinery operations and minimizing waste. [Extracted from the article]

Purpose: This paper aims to apply grey wolf optimizer (GWO) algorithm for steady state analysis of self-excited induction generators (SEIGs) supplying isolated loads. Design/methodology/approach: Taking the equivalent circuit of SEIG, the impedances representing the stator, rotor and the connected load are reduced to a single loop impedance in terms of the unknown frequency, magnetizing reactance and core loss resistance for the given rotor speed. This loop impedance is taken as the objective function and minimized using GWO to solve for the unknown parameters. By including the value of the desired voltage as a constraint, the formulated objective function is also extended for estimating the required excitation capacitance. Findings: The experimental results obtained on a three phase 415 V, 3.5 kW SEIG and the corresponding predetermined performance characteristics agree closely, thereby validating the proposed GWO method. Moreover, a comparative study of GWO with genetic algorithm and particle swarm optimization techniques reveals that GWO exhibits much quicker convergence of the objective function. Originality/value: The important contributions of this paper are as follows: for the first time, GWO has been introduced for the SEIG performance predetermination and computation of the excitation capacitance for attaining the desired terminal voltage for the given load and speed; the predicted performance accuracy is improved by considering the variable core loss of the SEIG; and GWO does not require derivations of lengthy equations for calculating the SEIG performance. [ABSTRACT FROM AUTHOR]

• Development of a novel mathematical model PCRE. • Proposal of a novel cascade hybrid many-objective recommendation method CHMAOR. • Design of a multiparent probabilistic heuristic genetic algorithm MPPHX. • Comparison of the proposed algorithms with state-of-the-art methods. • Statistical testing to evaluate the efficiency of the proposed algorithms. Most previous studies of recommender systems (RSs) have particularly focused on optimizing user experience; however, users are not the only stakeholders of an RS. A pure concentration of users limits the ability to incorporate the perspectives of other stakeholders, such as providers. Furthermore, because users' preferences and providers' objectives may conflict, considering only users' views degrades the recommendation methods' utility. Therefore, we propose a cascade hybrid many-objective recommendation method (CHMAOR) to balance four objectives for two different stakeholders. CHMAOR combines provider coverage (PC), user reach coverage (URC), and provider entropy (PE) to create a new provider visibility model (PCRE). The many-objective optimization (MOP) stage includes a novel multiparent probabilistic heuristic genetic algorithm (MPPHX) that heuristically considers both parents' gene frequency and recommendation list features. Extensive experiments demonstrate the following. 1) CHMAOR effectively balances user and provider objectives in terms of accuracy, diversity, novelty, and provider visibility according to the baseline algorithms. 2) The PCRE model considers not only provider coverage but also provider appearance frequency and provider diversity while effectively changing imbalanced provider recommendations. Furthermore, PCRE dramatically reduces the complexity of high-dimensional many-objective recommendations. 3) Our MPPHX achieves better convergence and diversity solutions than the competing MOP algorithms. [ABSTRACT FROM AUTHOR]

A study conducted by researchers at Guangzhou University in China explores the principles and factors that influence the selection of emergency medical facilities for public health emergencies in megacities. The study proposes a logistic regression model and a site selection model for these facilities, using genetic algorithms (GAs) for simulation and analysis. The results show that the improved GA model outperforms traditional models, providing decision-makers with stable technical support and better action plans. The research findings offer a theoretical and decision-making basis for the location of government emergency medical facilities and guidance for enterprises constructing such facilities. [Extracted from the article]