Institute Of Electrical And Electronics Engineers Research Articles

Fuzzy Classification Approach to Select Learning Objects Based on Learning Styles in Intelligent E-Learning Systems

In e-learning systems, even though the automatic detection of learning styles is considered the key element in the adaptation process, it does not represent the main goal of this process at all. Indeed, to accomplish the task of adaptation, it is also necessary to be able to automatically select the learning objects according to the detected styles. The classification techniques are the most used techniques to automatically select the learning objects by processing data derived from learning object metadata. By using these classification techniques, considerable results are obtained via several approaches and consist of mapping the learning objects into different teaching strategies and then mapping these strategies into the identified learning styles. However, these approaches have some limitations related to robustness. Indeed, a common feature of these approaches is that they do not directly map learning object metadata elements to learning style dimensions. Moreover, they do not consider the fuzzy nature of learning objects. Indeed, any learning object can be suitable for different learning styles at varying degrees of suitability. This highlights the need to find a way to remedy this shortcoming. Our work is part of the automatic selection of learning objects. So, we will propose an approach that uses the fuzzy classification technique to select learning objects based on learning styles. In this approach, the metadata of each learning object that complies with the Institute of Electrical and Electronics Engineers (IEEE) standard are stored in a database as an Extensible Markup Language (XML) file. The Fuzzy C Means algorithm is used, on one hand, to assign fuzzy suitability rates to the stored learning objects and, on the other hand, to cluster them into the Felder and Silverman learning styles model categories. The experiment results show the performance of our approach.

Enhancing Ethiopian power distribution with novel hybrid renewable energy systems for sustainable reliability and cost efficiency

Economic development relies on access to electrical energy, which is crucial for society’s growth. However, power shortages are challenging due to non-renewable energy depletion, unregulated use, and a lack of new energy sources. Ethiopia’s Debre Markos distribution network experiences over 800 h of power outages annually, causing financial losses and resource waste on diesel generators (DGs) for backup use. To tackle these concerns, the present study suggests a hybrid power generation system, which combines solar and biogas resources, and integrates Superconducting Magnetic Energy Storage (SMES) and Pumped Hydro Energy Storage (PHES) technologies into the system. The study also thoroughly analyzes the current and anticipated demand connected to the distribution network using a backward/forward sweep load flow analysis method. The results indicate that the total power loss has reached its absolute maximum, and the voltage profiles of the networks have dropped below the minimal numerical values recommended by the Institute of Electrical and Electronics Engineers (IEEE) standards (i.e., 0.95–1.025 p.u.). After reviewing the current distribution network’s operation, additional steps were taken to improve its effectiveness, using metaheuristic optimization techniques to account for various objective functions and constraints. In the results section, it is demonstrated that the whale optimization algorithm (WOA) outperforms other metaheuristic optimization techniques across three important objective functions: financial, reliability, and greenhouse gas (GHG) emissions. This comparison is based on the capability of the natural selection whale optimization algorithm (NSWOA) to achieve the best possible values for four significant metrics: Cost of Energy (COE), Net Present Cost (NPC), Loss of Power Supply Probability (LPSP), and GHG Emissions. The NSWOA achieved optimal values for these metrics, namely 0.0812 €/kWh, 3.0017 × 106 €, 0.00875, and 7.3679 × 106 kg reduced, respectively. This is attributable to their thorough economic, reliability, and environmental evaluation. Finally, the forward/backward sweep load flow analysis employed during the proposed system’s integration significantly reduced the impact of new energy resources on the distribution network. This was evident in the reduction of total power losses from 470.78 to 18.54 kW and voltage deviation from 6.95 to 0.35 p.u., as well as the voltage profile of the distribution system being swung between 1 and 1.0234 p.u., which now comply with the standards set by the IEEE. Besides, a comparison of the cost and GHG emission efficiency of the proposed hybrid system with existing (grid + DGs) and alternative (only DGs) scenarios was done. The findings showed that, among the scenarios examined, the proposed system is the most economical and produces the least amount of GHG emissions.

Applied Deep Learning-Based Crop Yield Prediction: A Systematic Analysis of Current Developments and Potential Challenges

Agriculture is essential for global income, poverty reduction, and food security, with crop yield being a crucial measure in this field. Traditional crop yield prediction methods, reliant on subjective assessments such as farmers’ experiences, tend to be error-prone and lack precision across vast farming areas, especially in data-scarce regions. Recent advancements in data collection, notably through high-resolution sensors and the use of deep learning (DL), have significantly increased the accuracy and breadth of agricultural data, providing better support for policymakers and administrators. In our study, we conduct a systematic literature review to explore the application of DL in crop yield forecasting, underscoring its growing significance in enhancing yield predictions. Our approach enabled us to identify 92 relevant studies across four major scientific databases: the Directory of Open Access Journals (DOAJ), the Institute of Electrical and Electronics Engineers (IEEE), the Multidisciplinary Digital Publishing Institute (MDPI), and ScienceDirect. These studies, all empirical research published in the last eight years, met stringent selection criteria, including empirical validity, methodological clarity, and a minimum quality score, ensuring their rigorous research standards and relevance. Our in-depth analysis of these papers aimed to synthesize insights on the crops studied, DL models utilized, key input data types, and the specific challenges and prerequisites for accurate DL-based yield forecasting. Our findings reveal that convolutional neural networks and Long Short-Term Memory are the dominant deep learning architectures in crop yield prediction, with a focus on cereals like wheat (Triticum aestivum) and corn (Zea mays). Many studies leverage satellite imagery, but there is a growing trend towards using Unmanned Aerial Vehicles (UAVs) for data collection. Our review synthesizes global research, suggests future directions, and highlights key studies, acknowledging that results may vary across different databases and emphasizing the need for continual updates due to the evolving nature of the field.

Multi-Objective Stochastic Paint Optimizer for Solving Dynamic Economic Emission Dispatch with Transmission Loss Prediction Using Random Forest Machine Learning Model

Dynamic economic emission dispatch problems are complex optimization tasks in power systems that aim to simultaneously minimize both fuel costs and pollutant emissions while satisfying various system constraints. Traditional methods often involve solving intricate nonlinear load flow equations or employing approximate loss formulas to account for transmission losses. These methods can be computationally expensive and may not accurately represent the actual transmission losses, affecting the overall optimization results. To address these limitations, this study proposes a novel approach that integrates transmission loss prediction into the dynamic economic emission dispatch (DEED) problem. A Random Forest machine learning model was offline-trained to predict transmission losses accurately, eliminating the need for repeated calculations during each iteration of the optimization process. This significantly reduced the computational burden of the algorithm and improved its efficiency. The proposed method utilizes a powerful multi-objective stochastic paint optimizer to solve the highly constrained and complex dynamic economic emission dispatch problem integrated with random forest-based loss prediction. A fuzzy membership-based approach was employed to determine the best compromise Pareto-optimal solution. The proposed algorithm integrated with loss prediction was validated on widely used five and ten-unit power systems with B-loss coefficients. The results obtained using the proposed algorithm were compared with seventeen algorithms available in the literature, demonstrating that the multi-objective stochastic paint optimizer (MOSPO) outperforms most existing algorithms. Notably, for the Institute of Electrical and Electronics Engineers (IEEE) thirty bus system, the proposed algorithm achieves yearly fuel cost savings of USD 37,339.5 and USD 3423.7 compared to the existing group search optimizer algorithm with multiple producers (GSOMP) and multi-objective multi-verse optimization (MOMVO) algorithms.

Metoda Sederhana untuk Memperbaiki Kinerja Motor Listrik 3 Fasa berdasarkan Insulation Resistance Test

In the electrical energy conversion laboratory, the stable operation of the induction motor is one of the most important factors. Failure of induction motor operation can be fatal in research activities in energy conversion laboratories. Prevention is needed so that the performance of induction motors remains optimal. this paper was created as an alternative for laboratory users of electrical energy conversion in maintaining the performance of induction motors. Based on a survey conducted by the Institute of Electrical and Electronics Engineers (IEEE), the main cause of electric motor operation failure is generally caused by insulation failure, so electric motor testing is generally dominated by insulation testing. Many insulation testing methods such as Insulation Resistance (IR) testing, Polarization Index (PI), Delta tangent, and other tests. In this paper, IR-based testing is proposed, because it is relatively cheap and easy to implement. The IR testing process is carried out using direct voltage from the Insulation Tester to the sample to be tested using the IEEE 43TM-2013 Standard. The test results show the IR value of the sample motor is good. This condition is categorized as safe to operate, so research activities that use induction motors can run well and safely.

Personal exposure to radiofrequency electromagnetic fields: A comparative analysis of international, national, and regional guidelines

A worldwide overview and analysis for the existing limits of human exposure to Radiofrequency Electromagnetic Fields (RF-EMF) is given in this paper. These reference levels have been established by different national and even regional governments, which can be based on the guidelines provided by the recommendations of the International Commission on Non-Ionizing Radiation Protection (ICNIRP), the International Committee on Electromagnetic Safety of the Institute of Electrical and Electronics Engineers (IEEE), and even in the United States of the Federal Communications Commission (FCC), as well as, are based on the so-called precautionary principle. Explicit reference is made to the exposure limits adopted in countries or regions, such as Canada, Italy, Poland, Switzerland, China, Russia, France, and regions of Belgium (Brussels, Flanders, Wallonia), where the limits are much lower than the international standards.The limits are compared to a selected set of in-situ measurements. This clearly shows that the measured values are typically very small compared to the international standards but could be somewhat higher compared to the reduced limits. Based on this observation and the reasonable assumption that the sensitivity of people to Electromagnetic Fields (EMF) is the same everywhere (whole-body), we propose the idea to establish a worldwide reference limit for the general public, thus applicable in all countries, if the ICNIRP considers it appropriate. Research must continue to generate measurement data that demonstrate the levels of exposure to which we are really exposed, and with this, provide arguments to the organizations that established the guidelines, especially the ICNIRP, to evaluate whether the current limits are too much. High and can be modified when considered pertinent. To the best of our knowledge, at no time has the reference level for the general public been exceeded.

Use of Artificial Intelligence in the Identification and Management of Frailty: A Scoping Review Protocol

IntroductionRapid population ageing and associated health issues such as frailty are a growing public health concern. While early identification and management of frailty may limit adverse health outcomes, the complex...

Control tuning methodology for modular multilevel converter‐based STATCOM

SummaryThe application of modular multilevel converters (MMC) in medium voltage static synchronous compensators (STATCOMs) has been investigated in recent years. A huge challenge for MMC‐STATCOM is to compute the gain of the controllers. Therefore, the contribution of this paper is the proposal of a control tuning methodology for MMC‐STATCOM. For this purpose, the control and tuning strategies are presented. Since MMC‐STATCOM can employ different modulation strategies, two distinct modulation strategies are considered: nearest‐level control, with variable switching frequency; and phase‐shifted carrier pulse‐width modulation, with fixed switching frequency. Moreover, the proposal was validated through simulation and an experimental platform. The results indicate that the power response follows the reference, besides supplying the internal losses of the converter. The 10% ripple tolerance of the submodule voltages is respected in steady state for both modulation strategies. Moreover, the 5% total demand distortion (TDD) limit recommended by the Institute of Electrical and Electronics Engineers (IEEE) standard is attended. These results demonstrate the effectiveness of the controls employed.

A resilient self‐healing approach for active distribution networks considering dynamic microgrid formation

AbstractA large number of renewable distributed generation (DG) systems connect to the distribution network, affecting the structure of the traditional distribution network and forming an active distribution network (ADN). Although the accelerating grid penetration of DGs brings significant challenges to the distribution network operation, the islanded operation capability of DGs provides a flexible solution to the self‐healing of ADNs from faults. To ensure that ADN can quickly recover and reconfigure in the event of a fault and continue to maintain safe, economical, and reliable operation, this paper proposes a dynamic microgrid formation method for ADNs combined with the dynamic network reconfiguration and intentional islanding operation of DGs. An optimization model is designed to represent the proposed self‐healing method, maximizing the load restoration and minimizing the DG cost, line network loss, and voltage excursion simultaneously. A binary hybrid optimization solver is applied to pursue the optimal self‐healing schedules from the optimization model. The self‐healing method is evaluated on the Institute of Electrical and Electronics Engineers (IEEE) 33‐node system and the IEEE 123‐node system, which indicate its rationality and effectiveness fully verified. By optimizing the on and off states of the normally open switches and the on‐grid and off‐grid operation states of DGs, ADNs not only get healed with minimum load curtailment, but also achieve minimal DG generation cost, network loss, and node voltage deviation. In addition, compared with traditional solvers, the proposed solver has a slightly higher computational time than the corresponding solver.

Walrus optimizer: A novel nature-inspired metaheuristic algorithm

Metaheuristic algorithms are intelligent optimization approaches that lead the searching procedure through utilizing exploitation and exploration. The increasing complexity of real-world optimization problem has prompted the development of more metaheuristic algorithms. Hence, this work proposes a novel swarm intelligence algorithm, Walrus optimizer (WO). It is inspired by the behaviors of walruses that choose to migrate, breed, roost, feed, gather and escape by receiving key signals (danger signals and safety signals). To test the capability of the proposed algorithm, 23 standard functions and the benchmark suite from the IEEE (Institute of Electrical and Electronics Engineers) Congress on Evolutionary Computation (CEC) 2021 are used. In addition, to evaluate the practicability of the proposed algorithm to solve various real-world optimization problems, 6 standard classical engineering optimization problems are examined and compared. For statistical purposes, 100 independent optimization runs are conducted to determine the statistical measurements, including the mean, standard deviation, and the computation time of the program, by considering a predefined stopping criterion. Some well-known statistical analyses are also used for comparative purposes, including the Friedman and Wilcoxon analysis. The results demonstrate that the proposed algorithm can provide special stability features and very competitive performance in dealing with high-dimensional benchmarks and real-world problems. The proposal of WO promotes the continuous development and application expansion of artificial intelligence, improves the efficiency of optimization calculation, and provides powerful tools for solving complex problems in the real world. The source code of WO is publicly availabe at https://ww2.mathworks.cn/matlabcentral/fileexchange/154702-walrus-optimizer-wo.

Determining optimal paths of virtual links in Avionics Full-Duplex Switched Ethernet networks using modified ant colony optimization algorithm

The Aeronautical Radio Incorporated (ARINC) 664 Avionics Full Duplex Switched Ethernet (AFDX) data bus has been developed based on the Ethernet standard Institute of Electrical and Electronics Engineers (IEEE) 802.3, including redundancy, guaranteed bandwidth, and deterministic timing of transmit interval time to meet the increasing amounts of data exchange needs among aircraft equipment while reducing the harness weight. Isolated data tunnels, called Virtual Links (VLs), are established to route Ethernet frames from a single source to one or more destinations using end systems and switches that contain a static routing mechanism specific to ARINC 664 AFDX. A limited number of algorithmic approaches are presented in the literature to route VLs; however, they are proven in uncomplicated topologies. Depending on the technological development, the node amount consisting of End Systems (ESs), Switches, and Remote Data Concentrators (RDCs) in the aircraft data bus structure will increase enormously. Bandwidth utilization (BWU), bandwidth flexibility limit for further extensions, port usage, total harness weight, latency, and redundancy should be considered in addition to number of nodes to determine VLs’ route paths in ARINC 664 AFDX networks. In such cases, determining optimal paths of VLs in ARINC 664 AFDX networks becomes a challenging problem to solve with the existing methods in the literature. This paper proposes an Ant Colony Optimization (ACO) based algorithm to determine optimal VL path routes in the complex topology of ARINC 664 AFDX networks considering multi-effective parameters. Experimental simulations are executed to confirm the validity of the presented algorithm in different case studies and show its applicability in the industry. The obtained results of the proposed algorithm outperform conventional algorithms existing in the literature in terms of bandwidth usage depending on predefined expansion capacity and solution time. The proposed algorithm also introduces novelty by considering the redundancy, total harness weight, and delay limit, which is deficient in the existing literature.

PEREGRINATIONS ON THE STUDY OF THE OPTICAL PROPERTIES OF NONSPHERICAL PARTICLES

PEREGRINATIONS ON THE STUDY OF THE OPTICAL PROPERTIES OF NONSPHERICAL PARTICLES

Methods for the Clinical Validation of Digital Endpoints: Protocol for a Scoping Review Abstract.

Clinical trials often use digital technologies to collect data continuously outside the clinic and use the derived digital endpoints as trial endpoints. Digital endpoints are also being developed to support diagnosis, monitoring, or therapeutic interventions in clinical care. However, clinical validation stands as a significant challenge, as there are no specific guidelines orienting the validation of digital endpoints. This paper presents the protocol for a scoping review that aims to map the existing methods for the clinical validation of digital endpoints. The scoping review will comprise searches from the electronic literature databases MEDLINE (PubMed), Scopus (including conference proceedings), Embase, IEEE (Institute of Electrical and Electronics Engineers) Xplore, ACM (Association for Computing Machinery) Digital Library, CENTRAL (Cochrane Central Register of Controlled Trials), Web of Science Core Collection (including conference proceedings), and Joanna Briggs Institute Database of Systematic Reviews and Implementation Reports. We will also include various sources of gray literature with search terms related to digital endpoints. The methodology will adhere to the Joanna Briggs Institute Scoping Review and the Guidance for Conducting Systematic Scoping Reviews. A search for reviews on the existing evidence related to this topic was conducted and has shown that no such review was previously undertaken. This review will provide a systematic assessment of the literature on methods for the clinical validation of digital endpoints and highlight any potential need for harmonization or reporting of methods. The results will include the methods for the clinical validation of digital endpoints according to device, digital endpoint, and clinical application goal of digital endpoints. The study started in January 2023 and is expected to end by December 2023, with results to be published in a peer-reviewed journal. A scoping review of methodologies that validate digital endpoints is necessary. This review will be unique in its breadth since it will comprise digital endpoints collected from several devices and not focus on a specific disease area. The results of our work should help guide researchers in choosing validation methods, identify potential gaps in the literature, or inform the development of novel methods to optimize the clinical validation of digital endpoints. Resolving these gaps is the key to presenting evidence in a consistent way to regulators and other parties and obtaining regulatory acceptance of digital endpoints for patient benefit. PRR1-10.2196/47119.

Mind the Gap: Understanding Coverage Breaks of Newly Launched Engineering and Computer Science Journals in Core Databases

Journal coverage is an important factor to consider when evaluating a database. In this study, we counted the number of articles (including early access articles) in newly-launched journals (2018-2022) from two major association publishers in engineering and computer science: the Institute of Electrical and Electronics Engineers (IEEE) and the Association for Computing Machinery (ACM). We then compared these numbers with the number of articles from these journals in Web of Science (WOS) Core Collection, Scopus, and Google Scholar (GS). Results indicated that GS had higher percentages for coverage for all the journals that were assessed and outperformed WOS and Scopus in terms of how fast newly-launched journals were indexed. Findings from this study will help librarians evaluate each database in reference, instruction, and collection development.

Enhancing distribution generator impact mitigation using an adaptive protection scheme based on modified pelican optimization algorithm and active database management system

AbstractThis paper addresses the challenge of protecting electrical networks in the presence of distribution generators (DGs). The use of DGs affects fault currents, leading to miscoordination between protection relays and causing constraints on network reliability. To tackle this issue, the authors propose an adaptive protection scheme (APS) based on a modified pelican optimization algorithm (MPOA) and active database management system (ADBMS). The APS coordinates directional overcurrent relays and distance relays, while the MPOA simulates a pelican mating strategy and includes a modified internal equation. The proposed APS is further upgraded with ADBMS to save system resources by storing relay settings in the database and calling them when the state of DGs changes without running optimization algorithms. The effectiveness of the proposed APS is validated on the Institute of Electrical and Electronics Engineers (IEEE) eight‐bus test system and the IEEE 14‐bus distribution network. Results indicate that the APS can effectively protect electrical networks in the presence of DGs, while the ADBMS upgrade saves system resources.

The effect of orthosis management on joint instability in knee joint disease: A systematic review.

Joint instability is a common finding of clinical importance in patients with knee disease. This literature review aimed to examine the evidence regarding the effect of orthosis management on joint instability in knee joint disease. The detailed protocol for this study was published in the International Prospective Register of Systematic Reviews in the field of health and social welfare (CRD 42022335360). A literature search was conducted on May 2023, using the following databases: Cochrane Central Register of Controlled Trials (CENTRAL), PubMed, Physiotherapy Evidence Database (PEDro), and Institute of Electrical and Electronics Engineers (IEEE) Xplore. A secondary search was manually conducted using Google Scholar to address publication bias. Each database search strategy was described, and the search was conducted by independent reviewers. A total of 281 studies were retrieved, 11 articles were included in the systematic review. Of the 11 articles selected, the number of included diseases was 2 for osteoarthritis, 7 for anterior cruciate ligament injuries, and 3 for posterior cruciate ligament injuries. In result, orthosis management may improve self-reported instability and functional assessment in patients with osteoarthritis, anterior cruciate ligament injury, and posterior cruciate ligament injury. However, an objective evaluation of anatomical instability did not indicate an improvement in joint instability. The effects of orthosis management on knee instability might improve physical function and self-reported instability.

Assessment of Background Radiation Around Telecommunication Masts of the Major Network Service Providers in Kaduna South, Kaduna State, Nigeria

This work assessed the electromagnetic radiation from telecommunication masts of major service providers (AIRTEL, ETISALAT, GLO, and MTN) around residential areas in Kaduna South, Nigeria. The Radio Frequency Electromagnetic Force (RF EMF) strength meter of serial number (480836) and a measuring tape were used to obtain readings away from the masts. The electric field strengths E, magnetic field strengths H, and power densities were measured at 0 m, 100 m, 200 m, 300 m, 400 m, and 500 m away from the mast base in V/m, A/m, and W/m2, respectively. The power densities measured were: 0.000091 W/m2 for Airtel, 0.000195 W/m2 for Etisalat, 0.000488 W/m2 for GLO, and 0.421352 W/m2 for MTN. These readings were compared with the standard valve (4.5 W/m2) recommended by the International Commission on Non-Ionizing Radiation Protection (ICNIRP) and the 6.05 W/m2 recommended by the Institute of Electrical and Electronic Engineers (IEEE) for exposure limits of radio frequency waves and the Federal Communications Commission (FCC) and were discovered to be below the recommended values. The radiological health effects, absorbed radiation dose rates, the annual effective dose equivalent (AEDE), and the excess lifetime cancer risks (ELCR) were evaluated. The values of absorbed dose rates were 0.000091 Gys-1 for Airtel, 0.000195333 Gys-1 for Etisalat, 0.000488333 Gys-1 for GLO, and 0.421352 Gys-1 for MTN, which were observed to be far lower than the world permissible value of 0.02472 Gys-1, except that of MTN, which is higher than the permissible value. However, the estimated annual effective dose equivalents (AEDE) were found to be higher than the ICNIRP permissible limits of 1.00 mSvy-1 for the public, which implies that the base stations do pose radiological risks in the long term. Also, the excess lifetime cancer risk for the stations’ users was all above the 0.29 × 10-3 per Sievert world recommended value by the United Nations Scientific Committee on the Effects of Atomic Radiations, UNSCEAR (2018), and Audu et al., (2019). This, therefore, suggests there is a high probability of the base station workers and residents within 500 m of the base mast to develop radiation-related illnesses over a long time. Regular radiological monitoring of all the base stations is recommended.

A weighted-sum chaotic sparrow search algorithm for interdisciplinary feature selection and data classification

In today’s data-driven digital culture, there is a critical demand for optimized solutions that essentially reduce operating expenses while attempting to increase productivity. The amount of memory and processing time that can be used to process enormous volumes of data are subject to a number of limitations. This would undoubtedly be more of a problem if a dataset contained redundant and uninteresting information. For instance, many datasets contain a number of non-informative features that primarily deceive a given classification algorithm. In order to tackle this, researchers have been developing a variety of feature selection (FS) techniques that aim to eliminate unnecessary information from the raw datasets before putting them in front of a machine learning (ML) algorithm. Meta-heuristic optimization algorithms are often a solid choice to solve NP-hard problems like FS. In this study, we present a wrapper FS technique based on the sparrow search algorithm (SSA), a type of meta-heuristic. SSA is a swarm intelligence (SI) method that stands out because of its quick convergence and improved stability. SSA does have some drawbacks, like lower swarm diversity and weak exploration ability in late iterations, like the majority of SI algorithms. So, using ten chaotic maps, we try to ameliorate SSA in three ways: (i) the initial swarm generation; (ii) the substitution of two random variables in SSA; and (iii) clamping the sparrows crossing the search range. As a result, we get CSSA, a chaotic form of SSA. Extensive comparisons show CSSA to be superior in terms of swarm diversity and convergence speed in solving various representative functions from the Institute of Electrical and Electronics Engineers (IEEE) Congress on Evolutionary Computation (CEC) benchmark set. Furthermore, experimental analysis of CSSA on eighteen interdisciplinary, multi-scale ML datasets from the University of California Irvine (UCI) data repository, as well as three high-dimensional microarray datasets, demonstrates that CSSA outperforms twelve state-of-the-art algorithms in a classification task based on FS discipline. Finally, a 5%-significance-level statistical post-hoc analysis based on Wilcoxon’s signed-rank test, Friedman’s rank test, and Nemenyi’s test confirms CSSA’s significance in terms of overall fitness, classification accuracy, selected feature size, computational time, convergence trace, and stability.

Systematic Review for Risks of Pressure Injury and Prediction Models Using Machine Learning Algorithms.

Pressure injuries are increasing worldwide, and there has been no significant improvement in preventing them. This study is aimed at reviewing and evaluating the studies related to the prediction model to identify the risks of pressure injuries in adult hospitalized patients using machine learning algorithms. In addition, it provides evidence that the prediction models identified the risks of pressure injuries earlier. The systematic review has been utilized to review the articles that discussed constructing a prediction model of pressure injuries using machine learning in hospitalized adult patients. The search was conducted in the databases Cumulative Index to Nursing and Allied Health Literature (CINAHIL), PubMed, Science Direct, the Institute of Electrical and Electronics Engineers (IEEE), Cochrane, and Google Scholar. The inclusion criteria included studies constructing a prediction model for adult hospitalized patients. Twenty-seven articles were included in the study. The defects in the current method of identifying risks of pressure injury led health scientists and nursing leaders to look for a new methodology that helps identify all risk factors and predict pressure injury earlier, before the skin changes or harms the patients. The paper critically analyzes the current prediction models and guides future directions and motivations.

PPG Signals-Based Blood-Pressure Estimation Using Grid Search in Hyperparameter Optimization of CNN-LSTM.

Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients' health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN-LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN-LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN-LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.