Search

Artificial Intelligence (AI) techniques are transforming various sectors and hold significant potential to advance sustainable development in Africa. However, their effective integration is constrained by region-specific challenges, limiting widespread deployment. This study reviews the current state of sustainable development in Africa, highlighting the role AI can play in driving progress across key sectors, including healthcare, agriculture, education, environmental protection, and infrastructure. The paper outlines the challenges hindering AI adoption and presents strategic approaches to address these obstacles, specifically targeting Africa’s socio-economic and environmental needs. In addition, the study proposes a comprehensive framework for integrating AI into Africa’s sustainable development efforts, offering tailored AI-driven strategies that align with the continent’s unique context. This framework provides a valuable resource for AI researchers, policymakers, and practitioners working towards sustainable development in Africa.

Integrating photovoltaic (PV) and battery energy storage systems (BESS) in modern power distribution networks presents opportunities and challenges, particularly in maintaining voltage stability and optimizing energy resources. This systematic review and bibliometric analysis investigates the coordination of smart inverter-enabled distributed energy resources (DERs) for enhancing PV-BESS integration and ensuring voltage stability. The study synthesizes recent advancements in smart inverter technologies, which provide grid support functions such as Volt/VAr control, and their applications in DER coordination. A comprehensive review of the literature is conducted to identify prevailing trends, research gaps, and emerging techniques in the field. Bibliometric analysis is employed to quantify the research landscape, highlighting key publications, citations, publications per country, and collaborative networks. The findings reveal that smart inverters play a crucial role in mitigating voltage violations and improving the hosting capacity of PV systems in distribution networks. Furthermore, optimal inverter settings, strategic placement of PV-BESS, and advanced control algorithms are identified as critical factors for effective DER integration. The study concludes by proposing future research directions, including the exploration of smart inverter interactions with legacy grid management systems and the development of robust algorithms for dynamic and adaptive DER coordination. This review serves as a valuable resource for researchers and practitioners aiming to enhance the stability and efficiency of power distribution networks through advanced DER management strategies.

Voltage instability is a major problem facing power utility companies due to a lack of maintenance and financial support to maintain the existing power system networks (PSN). Lack of maintenance occurs when PS fails to replace the aging equipment and services and upgrades existing networks. Also, the lack of financial support occurs when there is insufficient financial capital to carry out the above maintenance activities, which has incurred greater power loss in the systems. There is a need to eliminate the loss incurred in the system to avoid voltage collapse. The best way to increase the lifespan of a PSN and improve voltage stability is the optimum allocation of distributed generation (DG). The most common DG are solar photovoltaic (PV) and wind turbines. This review discusses the economic, environmental, and technical benefits of non-traditional DG technologies over a traditional system. However, this work reviewed different DG technologies that can be incorporated into PSN for better loss reduction. Detailed descriptions of energy loss, power loss, and multi-objectives for optimal DG planning were also discussed, along with comprehensive methods used in the sizing and placement of DG for voltage profile improvement (VPI). The findings recommend that the hybrid meta-heuristic algorithm be used for DG placement has it significantly improves voltage profile and lowers power loss. The present study concluded that with proper DG placement, the advantage of DG can be maximally accomplished, the voltage profile is improved, and losses are minimized.

This study uses JAYA optimized model predictive control to address a three-area load frequency regulation problem that actively involves stochastic renewable energy sources. Some physical constraints employed in the system model, such as the generation rate constraint, dead band, and time delay by governor-turbine, negatively impact the control performance of the classical MPC technique. As such, a more robust control scheme is required to get rid of this flaw. The JAYA algorithm is adopted to dynamically tune the parameters of MPC, which is a parameter-driven controller for optimal system performance. The performance indices such as the integral of square error (ISE), integral of time multiplied by square error (ITSE), integral of the absolute value of error (IAE), and integral of time multiplied by the absolute value of error (ITAE) have been used to compare the effectiveness of the proposed controller with the classical MPC with constant tuning parameters. The suggested controller is superior to the conventional MPC, as demonstrated by the results from the MATLAB/Simulink environment.

In order to address the load frequency issue in a three-area power generating system, this research suggests a teaching learning-based optimization-linear matrix, inequalities-tuned proportional–integral controller. The suggested TLBO-LMI approach synchronizes TLBO with LMI control toolbox optimization to acquire the ideal control parameters of the traditional PI controller that adhere to the robust H∞constraints. Based on the suggested control’s simplicity of implementation, adaptability to changes in the system’s characteristics, and resilience to tuning, it is contrasted with the robust H∞controller. Several performance indicators were also employed to evaluate and contrast the efficiency and performance of the H∞controller and the suggested control techniques. Based on the simulation results used to study the performance and robustness of the suggested controller, it is clear that the proposed control approach outperforms the H∞controller in terms of both performance and applicability for the LFC problem.

The number of coronavirus disease 2019 (COVID-19) cases continues to surge, overwhelming healthcare systems and causing excess mortality in many countries. Testing of infectious populations remains a key strategy to contain the COVID-19 outbreak, delay the exponential spread of the disease, and flatten the epidemic curve. Using the Omicron variant outbreak as a background, this study aimed to evaluate the effectiveness of testing strategies with different test combinations and frequencies, analyze the factors associated with testing effectiveness, and optimize testing strategies based on these influencing factors. We developed a stochastic, agent-based, discrete-time susceptible–latent–infectious–recovered model simulating a community to estimate the association between three levels of testing strategies and COVID-19 transmission. Antigen testing and its combination strategies were more efficient than polymerase chain reaction (PCR)-related strategies. Antigen testing also showed better performance in reducing the demand for hospital beds and intensive care unit beds. The delay in the turnaround time of test results had a more significant impact on the efficiency of the testing strategy compared to the detection limit of viral load and detection-related contacts. The main advantage of antigen testing strategies is the short turnaround time, which is also a critical factor to be optimized to improve PCR strategies. After modifying the turnaround time, the strategies with less frequent testing were comparable to daily testing. The choice of testing strategy requires consideration of containment goals, test efficacy, community prevalence, and economic factors. This study provides evidence for the selection and optimization of testing strategies in the post-pandemic era and provides guidance for optimizing healthcare resources.

Objectives: Global trade and travel have facilitated infectious disease transmission. In 2022, over a short time, cross-border Mpox (monkeypox) outbreaks were reported. Since, most countries are at risk of cross-border Mpox transmissions, in this study, we developed a real-time risk assessment model for the cross-border transmission of Mpox. Methods: This model includes priori indicators related to the source area before the Mpox outbreak and posterior indicators derived from the quantitative data evaluation afterward. Based on transportation, this model can also be used to assess the global import risk of Mpox for specific countries and cities. Results: European risk values displayed high levels between May and July 2022 and gradually decreased after July. After September 2022, risk values elevated in most countries and regions in the Americas. As for China, high importation risk cities were highly exposed to the United States and moderately exposed to Australia and Germany. Some cities were exposed to the potential risks from only one source country. Conclusions: Dynamic surveillance of the cross-border spread of infectious diseases is essential. Importation risks vary widely across cities and regions, and developing risk prevention and control strategies specific to the traffic flow, medical care capabilities, and risk levels in the main source countries are essential.

Background: The impact of regional anesthesia and analgesia (RAA) on long-term survival following cancer surgery is a topic of debate. The aim of this study was to investigate the effects of perioperative RAA on long-term oncological outcomes in patients undergoing major abdominal cancer surgery. Methods: The authors searched computerized databases and reference lists from inception to December 20, 2022. All studies that investigated the effects of perioperative RAA on long-term oncological outcomes following major abdominal cancer surgery were included. Using the inverse variance method with a random-effects model, hazard ratios (HR) and 95% confidence intervals (CI) were calculated. Results: The systematic review included 51 retrospective studies, one prospective study, and three randomized controlled trials (RCTs), with a total of 95,046 patients. The results showed that perioperative RAA may improve long-term overall survival (HR: 0.85, 95% CI: 0.80 to 0.91, P = 0.00, I2 = 60.2%). However, there was no significant association between perioperative RAA and reduced cancer recurrence (HR: 0.98, 95% CI: 0.90 to 1.03, P = 0.31, I2 = 52.3%). When performing a pooled analysis of the data from the three RCTs, no statistically significant effect of RAA was found in either case. Conclusion: The systematic review suggests perioperative RAA may improve long-term overall survival but does not appear to reduce cancer recurrence in patients undergoing major abdominal cancer surgery. The limited number of RCTs included in this study did not confirm this finding, highlighting the need for further RCTs to corroborate these results.

Purpose: This study aimed to conduct a bibliometric analysis of the data acquired and clarified the current research status of sexual health problems in patients with cancer, to provide a comprehensive visual perspective suitable as a reference for subsequent research. Methods: We searched the Web of Science Core Collection (WoSCC) up to April 30, 2023 to identify studies associated with sexual health problems in patients with cancer. CiteSpace was used to create visualization networks for countries, institutions, authors, and journals. Results: A total of 3183 publications related to sexual health problems in patients with cancer were collected from the WoSCC. In terms of volume, the USA (1259 papers) was the leading country, the Memorial Sloan Kettering Cancer Center (119 papers) was the leading institution, and Carter (39 papers) was the author with the most publications. The top-cited references and keywords were related to quality of life. The top five clusters of reference cocitation were ‘brachytherapy’, ‘prostate cancer’, ‘radical prostatectomy’, ‘hypogonadism’, and ‘breast cancer’. Meanwhile, the top five clusters of keyword cocitation were ‘breast cancer’, ‘prostate cancer’, ‘rectal cancer’, ‘testicular cancer’, and ‘sexual function’. The analysis of the top 25 references and keywords with the strongest citation bursts of published papers on sexual health problems in patients with cancer to reveal the research hotspots and trends. Conclusions: Research on sexual health among patients with cancer is constantly developing. The current research focuses on the impact of different treatment options for sexual health and quality of life of patients with breast, rectal, and genitourinary neoplasms. Exploring the long-term changing regularities of sexual function among cancer survivors and formulating sexual health interventions toward patient-reported outcomes and needs are key research directions.

Optimization of power in Photovoltaic (PV) systems and extraction of cell parameters in PV cells using well-known metaheuristic techniques have been implemented by different researchers. However, under fast-changing irradiances and complex partial shading conditions, these algorithms underperform by getting trapped at the local maxima and with a poor convergence exploration, which in turn leads to a loss in energy supplied from a PV system. This paper proposes an innovative use of improved firefly algorithm (IFA) technique suitable for effective extraction of both the unknown cell parameters in PV cells and locating the global maximum power point (GMPP) that yields optimum power in PV array systems within the shortest possible time and with minimal loss in power when operated under different environmental conditions. To validate the effectiveness of the proposed IFA technique, six experimental analyses were conducted using four optimization techniques comprising of particle swarm optimization, cuckoo search algorithm, flower pollination algorithm, and the proposed IFA technique as case studies. Results achieved confirmed that IFA technique can be used to solve real-world problems in PV systems.

Transactive energy trading, control, and management have gained much importance, receiving significant interest from both industry and academia. As a result, new strategies for its development and implementation are emerging. Prosumage, which combines household loads with solar PV and battery storage systems, has been presented as an effective technique for facilitating the integration of renewable energy sources while reducing distribution grid stress. Therefore, this paper proposes a grid-connected prosumer-centric residential smart community that uses cooperative game theory to exchange, regulate, and plan surplus energy generated by distributed energy resources (DERs) with the other neighbouring prosumers with energy deficits. The energy community considered in this work comprises ten identical prosumers (residential load, solar PV, and battery storage system), an energy community manager, and an energy retailer, all of whom are linked as a group to a distribution grid. The proposed market model seeks to examine the economic benefits of such renewable sources participating in centralized transactive energy trading. A centralized approach is adopted in the transactive energy trading among the ten proactive prosumers and the power grid through an energy community manager that administers trading activities inside the energy community. An optimization model is proposed in the centralized transactive energy trading market to optimize the financial benefits of rooftop solar PV-battery systems. The proposed model will not only optimally exchange, plan, and regulate the community domestic load, but it will also minimize total energy costs, increase system operation efficiency, and reduce system operating stress and carbon emissions.

This paper investigates energy management systems in micro-grid using an optimization-based approach, optimizing the operating cost related to the energy purchased from the utility grid, the operation cost of the energy storage system, and revenue from the selling of energy to the utility grid. This research uses a constrained Particle Swarm Optimization-Based Model Predictive Control (CPSO-MPC) and a Linear Program-Based Optimization approach to solve the constrained optimization problem formulated in micro-grid energy management. Due to the absence of constraint management strategies in the traditional PSO algorithm, it is incapable of solving constrained optimization problems. Hence, to overcome this drawback, an intuitive approach known as Deb’s rule is applied to handle the constraints. The simulation results show the modified particle swarm optimization’s effective performance embedded in the model predictive control algorithm compared to the linear programming algorithm.

This study proposes a primal–dual interior-point algorithm, which is used by the prosumers to efficiently manage the operation of their generating and consuming devices, to maximize their own profits while contributing to the stability of the overall electricity grid. The energy management problem investigated in this study is formulated as a convex optimization problem and the primal–dual interior-point algorithm is leveraged to acquire the optimal solution which minimizes the energy cost for prosumers in a smart grid environment. The proposed algorithm considers the cost of energy generation by each available device or the charge of a utility company, as well as the predicted consumption and production levels of the facility, and develops an operating plan that maximizes the prosumer’s profitability. The cost function for energy generation is convex, as are the constraints that must be satisfied. The primal–dual interior-point algorithm is an efficient algorithm and has attracted attention in the optimization community. The proposed algorithm is evaluated on three prosumer profiles that have different generation and storage characteristics. A variable pricing structure for power supplied or bought by the utility company is considered in this study and a scenario in which prosumers are not allowed to sell to the utility company. It is evident from the simulation results of the MATLAB environment that scenario 1 generates the minimum cost operation profiles compared to scenario 2. The effectiveness and the robustness of the proposed algorithm are demonstrated in the optimal solution obtained in solving the energy management problem.

The role of solar PV in the global energy mix is becoming more significant as the cost of solar modules continues to decline. The African continent has a good degree of solar irradiation. Therefore, it is imperative that the benefits of alternative energy generation through solar PV are maximized. In this paper, we present an optimization model of a case study in Sierra Leone which can be adapted for the Nigerian distribution system. This is because both countries are located in the same region (West Africa) and power systems are similar. We consider two demand response (DR) scenarios: price-based and incentive-based. The various DR schemes are compared to a situation in which there is no DR utilization to examine the impact of DR on peak load reduction and financial benefit to participants, and impact of renewable energy dispatch during peak and off-peak periods on financial benefits to participants. Simulation results show that the time- and incentive-based DR strategies reduce peak load demand by 11% and 14% respectively.

This paper presents a novel nature-inspired meta-heuristic optimization algorithm known as the Enhanced Whale Optimization Algorithm (EWOA), which imitates humpback whales' social behavior to solve the optimization of multi-area automatic load frequency control (LFC) problems of a stochastic renewable energy-based power system with superconducting magnetic energy storage (SMES). An EWOA algorithm is presented in response to the limitations of the conventional WOA algorithm, including its sluggish convergence time, low accuracy, and propensity to easily enter local optimum. The system model investigated includes some physical constraints such as the time delay (TD), generation rate constraint (GRC), reheat turbine (RT), and the dead band (DB). The impacts of these physical constraints on the dynamic performance of the proposed controller were investigated. The EWOA algorithm is utilized to dynamically optimize the parameters of the PID controller for optimal system performance. The effectiveness and dynamic performance of the proposed controller are compared with the conventional WOA using some performance metrics. The system model also includes superconducting magnetic energy storage (SMES) units in both areas and their impacts on the system performances are also investigated. The effects of the changes of two different parameters of the system (frequency bias parameter, B, and the governor speed regulation, R) on the frequency deviation responses and the controller's robustness are examined. It is evident from the results that the dynamic performance of the proposed controller is better than that of the conventional WOA and it is more robust and stable to changes in system loading, parameters, and step load perturbation.

Due to growing activities of avian influenza, more attention should be paid to avian influenza virus infections. Global summaries or national reports lack data on epidemiological patterns of avian influenza. A descriptive epidemiological analysis of avian influenza outbreaks from 2018 to 2022 was conducted, particularly fowl infections, human infections, and sequence alterations. The number of fowl infection outbreaks in the first half of 2022 was the highest level in the five-year period. Countries or regions could reliably be classified into three clusters according to fowl infection activity scores, with 60.0% of countries or regions in C1 in Europe. Additionally, two host infection patterns of countries were noted, led by the Taiwan (China) region and Germany. Human infections also increased, with 88.1% of cases being in China with an increasing risk of cases in northern China. Sequences that were furin cleavage motif present spread from Asia to Europe and North America over the five-year period. Continuous changes in the global activities of avian influenza highlight the need for sustained global surveillance, including strengthening monitoring capacity for vulnerable population and dynamically detecting new cases or genetic variations of the avian influenza virus under the One Health framework.

Electric vehicles (EVs) with voltage-to-grid (V2G) capability are useful in augmenting grid capability to handle high energy demand of end users during peak periods. We propose a hybrid state-of-charge (SOC) battery model with aggregator to optimize battery charging and maintain grid stability during peak periods. The proposed SOC model leverages the advantages of three well-known previously proposed battery models namely: Shepherd, Unnewehr and Nernst models. The proposed hybrid model is a combination of the merits of the three specified empirical Lithium-ion battery models to optimize slow charging. This will enhance battery performance by improving its depth-of-discharge profile. This results in enhanced V2G capability and longer driving time for EV owners. Battery parameters used in the simulation are for Nissan Leaf 2019 EV. The proposed SOC model parameters are used to optimize a two-objective function which is used by the aggregator to maximize benefits to both EV owners and DSO. Multi-objective genetic algorithm (MOGA) is used to optimize the objective function because of its ability to obtain non-dominated solutions while still maintaining diversity of the solutions. From simulation results, proposed OCV model improves battery SOC by 10% after V2G operating period (2 p.m.) compared to a case without the model. Also, proposed model earns aggregator $445 and $45 more for voltage and frequency regulation services, respectively. Voltage stability of all 5 considered grid buses of the IEEE 33-node system remains at 0.9–1.0 p.u.

The dual tyrosine kinase (EGFR/HER2) inhibitor lapatinib is currently used to clinically treat HER2-positive breast cancer. However, a majority of patients do not respond to lapatinib therapy within 6 months. Therefore, potentiating the anti-tumor effect of lapatinib by combination treatment has a great potential to overcome the obstacle. Herein, we aim to investigate the anti-tumor activity of lapatinib in combination with brusatol and explore the potential mechanism involved in the combinatorial treatment. Our findings revealed that the Nrf2 inhibitor brusatol potently enhanced the anti-tumor effect of lapatinib against SK-BR-3, SK-OV-3 and AU565 cancer cells in a synergistic manner. Furthermore, we found that lapatinib plus brusatol more effectively decreased Nrf2 level and induced ROS generation in both SK-BR-3 and SK-OV-3 cells. Moreover, we also observed a significant reduction on the phosphorylation of HER2, EGFR, AKT and ERK1/2 in SK-BR-3 and SK-OV-3 cells when treated with lapatinib plus brusatol compared to either agent alone. More importantly, brusatol significantly augmented the anti-tumor effects of lapatinib in the SK-OV-3 xenograft model. In summary, these data provide a potential rationale for the combination of brusatol and lapatinib on the treatment of HER2-positive cancers.

With the advances and growth of various wireless technologies, it is imperative to implement robust Intrusion Detection Systems (IDS). This paper proposes the implementation of Deep Gated Recurrent Unit (DGRU) Based classifier as well as a wrapper-based feature extraction algorithm for Wireless IDS. We assess the performance of the DRGU IDS using the NSL-KDD benchmark dataset. Furthermore, we compare our framework to several popular algorithms including Artificial Neural Networks, Deep Long–Short Term Memory, Random Forest, Naive Bayes and Feed Forward Deep Neural Networks. The experimental outcomes demonstrate that the DGRU IDS displays a significant increase in performance over existing methods.

Algorithms are used to optimize both single and multi-objective system limits. This research aimed to detect the optimal location and size of the DGs, which can significantly minimize power loss and improve the stability of the voltage. The research uses binary particle swarm optimization and shuffled frog leap (BPSO-SLFA) algorithms for simulation and testing of an optimal power flow (OPF) on 33 and 69 bus radial distribution system. The result shows that the algorithms give better DG allocation and minimizes the power losses but at the nascent stage of advancement. The power losses associated with the system have significantly reduced up to 31.8244kW using multi-DGs reconfiguration placement. The outcomes are established to verify the potency of the recommend algorithm to minimize losses, general improvement in voltage profiles and cost saving for various distribution system. However, the proposed methodology can be used as a reliable method in DG settings and sizing in distribution network system which produce better outputs rather than hybrid grey wolf optimization (GWO) and hybrid big bang big crunch.

Wireless networks have evolved over the years and they have become some of the most prominent communication media. These networks generally transmit large volumes of information at any given time. This has engendered a number of security threats and privacy concerns. This paper presents a Deep Long Short-Term Memory (DLSTM) based classifier for wireless intrusion detection system (IDS). Using the NSL-KDD dataset, we compare the DLSTM IDS to existing methods such as Deep Feed Forward Neural Networks, Support Vector Machines, k-Nearest Neighbors, Random Forests and Naïve Bayes. The experimental results suggest that the DLSTM IDS outperformed existing approaches.

Load frequency control or automatic generation control is one of the main operations that take place daily when considering a modern power system or not. The objectives of load frequency control are to maintain power balance between interconnected areas and to control the power flow in the tie-lines. Electric power cannot be stocked in large quantity that why its production must be equal to the consumption in each time. This equation constituted the key for a good management of any power system and introduces the need of more controllers when taking into account the integration of renewable energy sources into the traditional power system. More controllers are presented in the literature and the presents work proposes a review of those called traditional and those who combined the traditional controller and artificial intelligence algorithms. Keywords: Load frequency control, Power system, Controllers, Artificial intelligence

Background: Common buckwheat (Fagopyrum esculentum) is an important staple food crop in southwest China, where drought stress is one of the largest limiting factors that lead to decreased crop production. To reveal the molecular mechanism of common buckwheat in response to drought stress, we performed a comprehensive transcriptomics study to evaluate gene expression profiles of common buckwheat during PEG-mediated drought treatment. Results: In total, 45 million clean reads were assembled into 53,404 unigenes with an average length of 749 bp and N50 length of 1296 bp. A total of 1329 differentially expressed genes (DEGs) were identified by comparing well-watered and drought-treated plants, out of which 666 were upregulated and 663 were downregulated. Furthermore, we defined the functional characteristics of DEGs using GO and KEGG classifications. GO enrichment analysis showed that the DEGs were significantly overrepresented in four categories, namely, “oxidoreductase activity,” “oxidation–reduction process,” “xyloglucan:xyloglucosyl transferase activity,” and “apoplast.” Using KEGG pathway analysis, a large number of annotated genes were overrepresented in terms such as “plant hormone signal transduction,” “phenylpropanoid biosynthesis,” “photosynthesis,” and “carbon metabolism.” Conclusions: These results can be further exploited to investigate the molecular mechanism of common buckwheat in response to drought treatment and could supply with valuable molecular sources for abiotic-tolerant elite breeding programs in the future.How to cite: Wu Q, Zhao G, Bai X et al. Characterization of the transcriptional profiles in common buckwheat (Fagopyrum esculentum) under PEG-mediated drought stress. Electron J Biotechnol 2019;39. https://doi.org/10.1016/j.ejbt.2019.03.005. Keywords: Abiotic stress, Aluminum, Chlorophyll-binding proteins, Common buckwheat (Fagopyrum esculentum), Differentially expressed genes (DEGs), Drought stress, RNA sequencing, Transcription factor, Transferase, Triticum

Many real-world machine learning applications require building models using highly imbalanced datasets. Usually, in medical datasets, the healthy patients or samples are dominant, making them the majority class, while the sick patients are few, making them the minority class. Researchers have proposed numerous machine learning methods to predict medical diagnosis. Still, the class imbalance problem makes it difficult for classifiers to adequately learn and distinguish between the minority and majority classes. Cost-sensitive learning and resampling techniques are used to deal with the class imbalance problem. This research focuses on developing robust cost-sensitive classifiers by modifying the objective functions of some well-known algorithms, such as logistic regression, decision tree, extreme gradient boosting, and random forest, which are then used to efficiently predict medical diagnosis. Meanwhile, as opposed to resampling techniques, our approach does not alter the original data distribution. Firstly, we implement the standard versions of these algorithms to provide a baseline for performance comparison. Secondly, we develop their corresponding cost-sensitive algorithms. For the proposed approaches, it is not necessary to change the distribution of the original data as the modified algorithms consider the imbalanced class distribution during training, thereby resulting in more reliable performance than when the data is resampled. Four popular medical datasets, including the Pima Indians Diabetes, Haberman Breast Cancer, Cervical Cancer Risk Factors, and Chronic Kidney Disease datasets, are used in the experiments to validate the performance of the proposed approach. The experimental results show that the cost-sensitive methods yield superior performance compared to the standard algorithms.

Summary: Kingdonia uniflora, an alpine herb, has an extremely narrow distribution and represents a model for studying evolutionary mechanisms of species that have adapted to undisturbed environments for evolutionarily long periods of time. We assembled a 1,004.7-Mb draft genome (encoding 43,301 genes) of K. uniflora and found significant overrepresentation in gene families associated with DNA repair, underrepresentation in gene families associated with stress response, and loss of most plastid ndh genes. During the evolutionary process, the overrepresentation of gene families involved in DNA repair could help asexual K. uniflora reduce the accumulation of deleterious mutations, while reducing genetic diversity, which is important in responding to environment fluctuations. The underrepresentation of gene families related to stress response and functional loss of ndh genes could be due to lack or loss of ability to respond to environmental changes caused by long-term adaptation to a relatively stable ecological environment.

Heart disease is the leading cause of death globally, and early detection is crucial in preventing the progression of the disease. In this paper, an improved machine learning method is proposed for the prediction of heart disease risk. The technique involves randomly partitioning the dataset into smaller subsets using a mean based splitting approach. The various partitions are then modeled using classification and regression tree (CART). A homogeneous ensemble is then created from the different CART models using an accuracy based weighted aging classifier ensemble, which is a modification of the weighted aging classifier ensemble (WAE). The approach ensures optimal performance is achieved. The experimental results on the Cleveland and Framingham datasets achieved classification accuracies of 93% and 91%, respectively, which outperformed other machine learning algorithms and similar scholarly works. The receiver operating characteristic curves further validates the improved performance of the proposed ensemble learning approach. The results show that heart disease risk can be predicted effectively by the proposed ensemble.

In this paper a two stage method is proposed to effectively predict heart disease. The first stage involves training an improved sparse autoencoder (SAE), an unsupervised neural network, to learn the best representation of the training data. The second stage involves using an artificial neural network (ANN) to predict the health status based on the learned records. The SAE was optimized so as to train an efficient model. The experimental result shows that the proposed method improves the performance of the ANN classifier, and is more robust as compared to other methods and similar scholarly works. Keywords: Sparse autoencoder, Deep learning, Unsupervised learning, ANN, Heart disease