Search Optimization Research Articles

UAV swarm path planning approach based on integration of multi-population strategy and adaptive evolutionary optimizer

Abstract Addressing the optimal path planning problem encountered by swarm of Unmanned Aerial Vehicle (UAV) in three-dimensional space under multiple constraints, the Multi-population Adaptive Cuckoo Search and Grey Wolf Optimizer (MACSGWO) integrates Multi-Population (MP) strategies and adaptive evolutionary optimizer including the enhanced Adaptive Grey Wolf Optimizer (AGWO) and Adaptive Cuckoo Search (ACS).
The optimizer strategically divides the initial population into multiple sub-groups, enabling each sub-group to independently iterate. 
During the iteration process, the algorithm adaptively adjusts parameters based on the optimal fitness values obtained by each sub-group after each iteration. The iteration cycle is divided into two stages: during the global exploration phase, each sub-group autonomously executes AGWO and periodically shares the fitness information of the Alpha wolf with other sub-groups, accelerating convergence.
In the subsequent local optimization phase, MACSGWO dynamically decides whether to initiate ACS based on the disparity in the best fitness of each sub-group after each iteration, assisting the algorithm in escaping local optima. 
In experiments involving various complex benchmark functions and swarm path planning scenarios, MACSGWO demonstrated significant superiority in solution stability, convergence speed, and optimal convergence value compared to multiple existing variant algorithms. The integration of MACSGWO with the best relay UAV selection strategy further optimized the communication efficiency within the swarm. MACSGWO ensures the efficient resolution of UAV swarm path planning problems, providing robust support for optimization challenges in complex, multi-constraint scenarios.

MoistNet: Machine vision-based deep learning models for wood chip moisture content measurement

Quick and reliable measurement of wood chip moisture content is an everlasting problem for numerous forest-reliant industries such as biofuel, pulp and paper, and bio-refineries. Moisture content is a critical attribute of wood chips due to its direct relationship with the final product quality. Conventional techniques for determining moisture content, such as oven-drying, possess some drawbacks in terms of their time-consuming nature, potential sample damage, and lack of real-time feasibility. Furthermore, alternative techniques, including NIR spectroscopy, electrical capacitance, X-rays, and microwaves, have demonstrated potential; nevertheless, they are still constrained by issues related to portability, precision, and the expense of the required equipment. Hence, there is a need for a moisture content determination method that is instant, portable, non-destructive, inexpensive, and precise. This study explores the use of deep learning and machine vision to predict moisture content classes from RGB images of wood chips. A large-scale image dataset comprising 1,600 RGB images of wood chips has been collected and annotated with ground truth labels, utilizing the results of the oven-drying technique. Two high-performing neural networks, MoistNetLite and MoistNetMax, have been developed leveraging Neural Architecture Search (NAS) and hyperparameter optimization. The developed models are evaluated and compared with state-of-the-art deep learning models. Results demonstrate that MoistNetLite achieves 87% accuracy with minimal computational overhead, while MoistNetMax exhibits exceptional precision with a 91% accuracy in wood chip moisture content class prediction. With improved accuracy (9.6% improvement in accuracy by MoistNetMax compared to the best baseline model ResNet152V2) and faster prediction speed (MoistNetLite being twice as fast as MobileNet), our proposed MoistNet models hold great promise for the wood chip processing industry to be efficiently deployed on portable devices, such as smartphones.

Connected Dominating Set Construction Using the Hunger Games Search Optimisation Algorithm in Wireless Sensor Networks

Wireless Sensor Networks (WSNs) play a significant role in monitoring changes in the physical environment, relying on a subset of designated nodes known as the Connected Dominating Set (CDS) to facilitate communication and serve as the network's virtual backbone for routing and clustering. Despite the various algorithms for CDS construction, the challenges persist in terms of construction cost and scalability. In this context, this paper introduces the utilisation of the Hunger Games Search Optimisation Algorithm (HGSOA) for Connected Dominating Set Construction in Wireless Sensor Networks (HGSOA-CDS-WSN). The primary intention of this paper is “to develop a technique capable of constructing small-sized CDS with reduced construction costs, particularly suitable for uniformly or randomly distributed nodes”. The proposed HGSOA-CDS-WSN method is implemented in MATLAB based on various metrics. The results are compared with those of existing techniques, such as the Parallel Structure from Motion for UAV Pictures using Weighted CDS (PSfM-CDS-WSN), Polyhedra Associated with Locating-Dominating, Open Locating-Dominating, and Locating Total-Dominating Sets in Graphs (PAL-CDS-WSN), and Sustainable Maintenance of Connected Dominating Set by Solar Energy Harvesting for Internet of Things Networks (SHE-CDS-WSN). The proposed technique achieves lower delay by 13.24%, 25.64%, and 9.96%, and higher throughput by 18.34%, 24.55%, and 23.04% compared to the existing methods. This systematic evaluation underscores the efficacy and superiority of the proposed HGSOA-CDS-WSN technique in terms of connected dominating set size, construction time, energy efficiency, network stability, and overall performance, highlighting its potential to advance wireless sensor network applications.

Hybrid machine learning approach integrating GMDH and SVR for heavy metal concentration prediction in dust samples.

In agricultural regions prone to dust storms, heavy metal contamination of soil and crops from airborne particulates poses significant risks to food safety and public health. This study has assessed the potential of machine learning models for predicting concentrations of toxic heavy metals like arsenic, chromium, and lead in dust from the agricultural Sistan region of southeastern Iran. This region experiences frequent dust storms mobilizing particulates from local dried lakes onto agricultural lands. The metals including nickel, copper, magnesium, cobalt, zinc, chromium, arsenic, and lead were measured in summer dust samples during 2012-2018 across 15 stations. Two hybrid models were developed combining group method of data handling (GMDH) and support vector regression (SVR) machine learning with harmony search optimization (H) so as to predict toxic metals arsenic, chromium, and lead using nickel, copper, magnesium, cobalt, and zinc inputs. Standard error maps were uncertainty higher in southern and western areas, and they are most impacted by dust storms. Results demonstrated that the hybrid GMDH + H and SVR + H models improved the accuracy of individual GMDH and SVR models in predicting heavy metals. The GMDH + H model performed the best for the lead with an agreement index (d-index) of 0.98, root mean square error (RMSE) of 2.87ppm, normalized RMSE (NRMSE) of 0.12, and coefficient of determination (RR) of 0.96. The SVR + H model showed the highest accuracy for arsenic and chromium, obtaining d-index 0.96, RMSE 0.47ppm, NRMSE 0.09, and RR 0.92 for arsenic, and d-index 0.96, RMSE 11.24ppm, NRMSE 0.16, and RR 0.93 for chromium. Taylor's diagram and heatmap analysis confirmed the superiority of the hybrid techniques. This work demonstrates the utility of state-of-the-art computing for addressing complex environmental health challenges.

An efficient cluster head selection in WSNs using transient search optimization (TSO) algorithm

SummaryIn this manuscript, a nature‐inspired optimization method, named transient search optimization (TSO), is proposed. Energy‐based monetary custom is a serious issue on the wireless sensor network (WSN). Here, the network clustering is an effectual technique to reduce node energy depletion and increased network lifetime. The proposed method aims to improve the efficiency of sensor nodes (SNs) by reducing their detachment, minimizing energy transmission, and protecting excessive energy stored in the nodes. This approach helps decrease delays, reduce traffic flow, and optimize network performance. The execution is implemented on the NS2 software. The experimental outcomes exhibit that the proposed system performs better based on two wireless sensor architectures, such as 50 nodes and 100 nodes. The parameter produces 52.24%, 54.38%, and 56.37% better network lifetime; 44.71%, 46.24%, and 49.45% higher alive node; and 39.26%, 36.26%, and 28.65% lesser dead SNs compared with existing techniques like multi‐objective cluster head (CH)–based energy‐aware optimized routing approach in wireless sensor network (MOCH‐ORR‐WSN), energy effective CH selection with improved sparrow search algorithm in WSN (ECH‐ISS‐WSN), and energy effectual cluster basis routing protocol under butterfly optimization along ant colony optimization algorithms for WSN (EEC‐BOA‐ACO‐WSN).

Impact of crop management practices on maize yield: Insights from farming in tropical regions and predictive modeling using machine learning

Understanding the influence of crop management practices on maize yield is crucial amidst the changing environmental conditions. Smallholder farming in tropical regions has long puzzled decision-makers in terms of maize management. Balancing alternative management practices, environmental factors, and economic outcomes is essential. In this study, we examine the relationships between maize yield and various factors including climate variables, soil quality parameters, cultivars, tillage practices, and fertilizer usage in Chiapas, Mexico. Pearson's correlation coefficient and T-test were employed to determine the statistical significance of the correlations. Our findings reveal strong positive associations between maize yields and factors such as planting, cultivar, vapor pressure, temperature, solar radiations and fertilizer inputs for nitrogen, phosphorus, and potassium in lower elevation farms. Conversely, there is a negative correlation with elevation, slope, and system. Extensive data analysis was conducted to investigate the impact of different crop management practices on yield, utilizing both data visualization and analytics. Additionally, maize yield prediction was performed using six hybrid machine learning (ML) models, employing Grid Search and Random Search optimization techniques. Based on evaluation, Grid Search-based XGBoost exhibited the most accurate prediction results. Furthermore, explainable artificial intelligence (XAI) was employed to assess the individual impact of each input parameter on the ML model output.

Sand cat swarm optimization based maximum power point tracking technique for photovoltaic system under partial shading conditions

Maximum power point tracking (MPPT) plays a crucial role in photovoltaic systems (PVS). In partial shading conditions (PSCs), the P-V characteristic curves of PVS exhibit multiple peaks. Traditional MPPT algorithms, like perturbation and observation (P&O), may fall into local maximum power points (LMPP) and fail to identify the global maximum power point (GMPP). To address the drawbacks of conventional optimal search algorithms, this paper introduces a bio-inspired approach named Sand Cat Swarm Optimization (SCSO) for maximizing the power output of individual PVS. The SCSO can mitigate the adverse effects of partial shadows on PVS performance by precisely identifying the GMPP. In comparison to other bio-inspired algorithms, SCSO exhibits lower complexity and higher efficiency by utilizing only one optimization parameter. SCSO’s performance is evaluated in four scenarios: uniform irradiance, complex partial shading conditions, step-varying stochastic irradiance, and gradual irradiance. A comparative analysis is conducted with Particle Swarm Optimization (PSO), Cuckoo Search Algorithm (CSA), Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), Moth-Flame Optimization (MFO), Crow Search Algorithm (CSA), Slap-Swarm Optimization (SSA) and P&O, focusing on factors such as high efficiency, accuracy, convergence time, and implementation simplicity. Simulation results demonstrate that, on average, the tracking time improves by 19.91%, achieving an efficiency of over 98% while maximizing energy yield. Simultaneously, experimental results indicate that the SCSO is capable of tracking to a larger power output in a shorter time, with an average tracking efficiency improvement of 3.16%.

Research on Off-Axis Integrated Cavity Output Spectrum Signal Denoising Based on CSGWO-SVMD-SVD method

To mitigate the susceptibility of absorption lines to noise interference during gas measurement using the off-axis integrated cavity output spectroscopy (OA-ICOS) technique, thereby enhancing measurement accuracy, this paper introduces a novel denoising method. This method synergistically integrates Grey Wolf Optimization (GWO) and Cuckoo Search (CS) with Singular Value Decomposition (SVD) and Sequential Variational Mode Decomposition (SVMD). Initially, the optimal solution for the quadratic penalty coefficient in SVMD is ascertained via iterative optimization using the CSGWO algorithm. Subsequently, a circulant matrix is established to extract the singular values of each modal component. A threshold is set to discriminate between noise and useful signals, and the singular values corresponding to noise are nullified. The useful signal components are then reconstructed, yielding the final processed signal. The proposed algorithm was applied to both simulated and experimental target signals and compared with common filtering algorithms such as WT, VMD-WTD, and S-G. In the experimental signal processing results, the signal-to-noise ratio (SNR) of the absorption spectrum signal improved from 21.4 to 39.95, and the correlation coefficient increased from 0.99715 to 0.99946. Results indicate that the proposed algorithm exhibits superior identification and noise suppression capabilities compared to other algorithms. After signal processing using the CSGWO-SVMD-SVD algorithm, the accuracy and stability of signal data detected based on off-axis integration cavity output spectroscopy technology have been greatly improved.

Efficient allocation of energy storage and renewable energy system for performance and reliability improvement of distribution system

This paper aims to investigate the impact of optimal planning of renewable energy systems and independent battery energy storage systems (BESS) on the performance and reliability of distribution systems (DS). A unique energy management scheme (EMS) controls the charging and discharging schedules of the BESS. The transit search optimization (TSO) algorithm determines the optimal allocation of wind turbine (WT) and solar photovoltaic (SPV) generator units, along with BESS units. The optimization focuses on improving the DS reliability in terms of energy supply, increasing the feeder security margin, and reducing apparent power loss. Multiple case studies are designed to study the efficacy of the problem outcomes and are validated using Bus 4 of the Roy Bollington Test System (RBTS). To obtain results that are close to actual operating conditions, the modelling process takes into account the time-varying load profile and the dynamic power outputs from the SPV and WT units. The findings show that the suggested method works well by enhancing the feeder security margin by a maximum of 11.25%, reducing expected energy not supplied (EENS) by 4.3%, and improving the power loss profile by 11.5%. In addition, the feeder upgrade deferral (FUD) years also show a maximum improvement of 20.8%.

Atlantic Blue Marlin, Boops, Chironex Fleckeri, and General Practitioner – Sick Person Optimization Algorithms mization Algorithms

In this paper Atlantic blue marlin (ABM) optimization algorithm, Boops optimization (BO) algorithm, Chironex fleckeri Search Optimization (CSO) algorithm, General practitioner -Sick person (PS) optimization algorithm are applied for solving factual power loss reduction problem. The regular actions of Atlantic blue marlin are emulated to design the Atlantic blue marlin (ABM) optimization algorithm and populace in the examination space is capriciously stimulated. Boops optimization (BO) algorithm is designed by imitating the actions of Boops. Boops possess the obliging stalking physiognomies. As a cluster they stalk the quarry by forming the key and subordinate clusters CSO is based on the drive and search behaviour of Chironex fleckeri. Obviously Chironex fleckeri will exploit the limbs to paralyze the pray by injecting the rancour. In real time world a General practitioner will treat the Sick person with various procedures and it has been imitated to model the Projected PS algorithm. In general people will be inoculated and then with respect to disorder and disease- medical treatment will be given by medicines. Inoculation, medicine and operation are the procedures have been considered as the phases of the projected PS algorithm. Atlantic blue marlin (ABM) optimization algorithm, Boops optimization (BO) algorithm, Chironex fleckeri Search Optimization (CSO) algorithm, General practitioner -Sick person (PS) optimization algorithm validated in IEEE 57, 300 systems and 220 KV network. Factual power loss lessening, power divergence restraining, and power constancy index amplification has been attained.

An improved Coati Optimization Algorithm with multiple strategies for engineering design optimization problems

Aiming at the problems of insufficient ability of artificial COA in the late optimization search period, loss of population diversity, easy to fall into local extreme value, resulting in slow convergence and lack of exploration ability; In this paper, an improved COA algorithm based on chaotic sequence, nonlinear inertia weight, adaptive T-distribution variation strategy and alert updating strategy is proposed to enhance the performance of COA (shorted as TNTWCOA). The algorithm introduces chaotic sequence mechanism to initialize the position. The position distribution of the initial solution is more uniform, the high quality initial solution is generated, the population richness is increased, and the problem of poor quality and uneven initial solution of the Coati Optimization Algorithm is solved. In exploration phase, the nonlinear inertial weight factor is introduced to coordinate the local optimization ability and global search ability of the algorithm. In the exploitation phase, adaptive T-distribution variation is introduced to increase the diversity of individual population under low fitness value and improve the ability of the algorithm to jump out of the local optimal value. At the same time, the alert update mechanism is proposed to improve the alert ability of COA algorithm, so that it can search within the optional range. When Coati is aware of the danger, Coati on the edge of the population will quickly move to the safe area to obtain a better position, while Coati in the middle of the population will randomly move to get closer to other Coatis. IEEE CEC2017 with 29 classic test functions were used to evaluate the convergence speed, convergence accuracy and other indicators of TNTWCOA algorithm. Meanwhile, TNTWCOA was used to verify 4 engineering design optimization problems, such as pressure vessel optimization design and welding beam design. The results of IEEE CEC2017 and engineering design Optimization problems are compared with Improved Coati Optimization Algorithm (ICOA), Coati Optimization Algorithm (COA), Golden Jackal Optimization Algorithm (GJO), Osprey Optimization Algorithm (OOA), Sand Cat Swarm Optimization Algorithm (SCSO), Subtraction-Average-Based Optimizer (SABO). The experimental results show that the improved TNTWCOA algorithm significantly improves the convergence speed and optimization accuracy, and has good robustness. Three‑bar truss design problem, The Gear Train Design Problem, Speed reducer design problem shows a strong solution advantage. The superior optimization ability and engineering practicability of TNTWCOA algorithm are verified.

Design of Vibration and Noise Reduction for Ultra-Thin Cemented Carbide Circular Saw Blades in Woodworking Based on Multi-Objective Optimization

Cemented carbide circular saw blades are widely used for wood cutting, but they often suffer from vibration and noise issues. This study presents a multi-objective optimization method that integrates ANSYS and MATLAB to optimize the design of noise reduction slots in circular saw blades. A mathematical model was developed to correlate the emitted sound power with the overall vibration intensity. A multi-objective optimization model was then formulated to map the slot shape parameters to the deformation, equivalent stress, and vibration intensity during sawing. The ABAQUS thermal–mechanical coupling analysis was used to determine the sawing force and temperature field. The NSGA-II algorithm was applied on the ANSYS–MATLAB platform to iteratively compute slot shape parameters and conduct optimization searches for a globally optimal solution. Circular saw blades were fabricated based on the optimization results, and experimental results showed a significant reduction in sawing noise by 2.4 dB to 3.0 dB on average. The noise reduction effect within the specified frequency range closely agreed with the simulation results, validating the method’s efficiency. This study provides a feasible and cost-effective solution to the multi-objective optimization design problem of noise reduction slots for circular saw blades.

Novel AI-driven Malaria Prediction for Optimizing Public Health Management

Malaria is an unmoving real common well-being apprehension in Asian nations like the Republic of India, where the state characterizes approximately 55% of the session events cutting-edge the infirmaries. They are usually distinguished by the absence of appropriate therapeutic care provision and the often late and error-prone diagnosis of the condition. In particular, commonly used devices such as the Rapid Diagnosis Test (RDT) are not completely dependable. They are primarily notable for their failure to provide adequate medical treatment and their tendency to diagnose the disease late and incorrectly. For example, widely used devices like the RDT are not consistent. To improve public health management actions, this work offers a unique augmented tree with penguin search optimization (AT+PSO) methodology for malaria forecasting. The suggested method combines the PSO algorithm with the augmented tree model, also known as random forest (RF). In the preprocessing stage, raw data samples are subjected to data normalization. Then, we applied the PSO to improve the characteristics of the RF model after successfully predicting malaria with the RF. The Python program is used to implement the suggested technique and analyze performance using a range of measures, including accuracy (0.988), sensitivity (0.987), specificity (0.991), F1-score (0.988), and MCC (0.975). In summary, our suggested approach produced the best results in terms of accuracy as opposed to other current strategies for predicting malaria to improve governance of public health.

An enhanced snow ablation optimizer for UAV swarm path planning and engineering design problems

The Snow Ablation Optimizer (SAO) is an advanced optimization algorithm. However, it suffers from slow convergence and a tendency to become trapped in local optima. To address these limitations, we propose an Enhanced Snow Ablation Optimization algorithm (ESAO). Initially, an adaptive T-distribution control strategy is employed to improve the algorithm's exploratory position adjustments, facilitating the identification of the global optimum. Furthermore, we introduce a Cauchy mutation strategy, endowing individuals with a robust capability to escape local extrema and steer the population towards more favorable directions. A leader-based boundary control strategy is also proposed to enhance the optimizer's search performance, significantly increasing the accuracy, speed, and stability of the algorithm in tackling complex problems. To validate the performance of ESAO, we utilize 29 CEC2017 benchmark functions for comparison against eight popular algorithms across various dimensions. Our algorithm ranked first in all comparisons, demonstrating ESAO's effectiveness. Additionally, to evaluate the practical applicability of the proposed method, we mathematically modeled the UAV swarm and solved the UAV swarm path planning problem using various competitor algorithms. Furthermore, we applied different competitor algorithms to two engineering design problems. The results demonstrate that ESAO performs the best. In general, ESAO outperforms its counterparts in terms of solution quality and stability, showcasing its superior application potential.

Harmony search for hyperparameters optimization of a low resource language transformer model trained with a novel parallel corpus Ocelotl Nahuatl – Spanish

Nahuatl, a low-resource language, does not have an online translator application. Instead, resources are limited to dictionaries, web pages, or digital books. Given this condition, it is vital to provide as much support to the language as possible. This research aims to enhance the BLEU score in machine translation by applying the harmony search heuristic method to state-of-the-art transformers models. This is conducted by finding the optimal hyperparameter settings for the models. Models are trained and tested using a fresh moderate-size parallel corpus of 1.5k phrases. By utilizing harmony search, the study shows an improvement in the BLEU score, enhancing it by 2.569%. In order to accomplish this, various factors related to the hyperparameters need to be considered. The application of harmony search with transformers can be extended to various parallel corpora or models, taking these considerations into account.

Deep Learning-Driven Workload Prediction and Optimization for Load Balancing in Cloud Computing Environment

Abstract Cloud computing revolutionizes as a technology that succeeds in serving large-scale user demands. Workload prediction and scheduling tend to be factors dictating cloud performance. Forecasting the future workload in due to avoid unfair resource allocation, emerges to be a crucial inspecting feature for enhanced performance. The aforementioned issues of interest are addressed in our work by soliciting a Deep Learning driven Max-out prediction model, which efficiently forecasts the future workload by providing a balanced approach for enhanced scheduling with the Tasmanian Devil-Bald Eagle Search (TDBES) optimization algorithm. The results obtained proved that the TDBES scored efficacy in makespan with 16.75%, migration cost with 14.78%, and a migration efficiency rate of 9.36% over other existing techniques like DBOA, WACO, and MPSO, with additional error analysis of prediction performance using RMSE, MAP, and MAE, among which our contributed approach overrides traditional methods with least error.

Bone age estimation with HS-optimized Resnet and Yolo for child growth disorder

Bone Age Assessment (BAA) plays a significant part in assessing skeletal maturity for preventing different types of skeletal disorders in the human body. Predicting BAA helps clinicians make decisions about the patient’s biological maturity. An increase or decrease in bone age (BA) causes serious issues for pediatricians who need advanced equipment for BA consistency with the chronological age. Recent techniques fail to accurately estimate the region over interest (ROI) of hand-wrist images to predict BA under low time complexity accurately. Hence, this article brings novel deep learning (DL) techniques to assess the BA to overcome child growth disorders accurately. The proposed methodology undergoes three major stages: pre-processing, ROI detection, and BA detection. In the pre-processing stage, contrast-limited fuzzy adaptive histogram equalization (CLFAHE) is done to maintain the originality of the hand image. The size of the image is also increased by using data augmentation. After pre-processing, the required hand bone region with ROI detection approaches you only live once version 3 (YOLOv3). At the final stage, the BA is predicted using the residual network-152 (ResNet152) technique. Finally, the weight updation takes place in the ResNet152 model using harmony search (HS) optimization techniques. The dataset used in this research is collected from the RSNA bone age dataset. The performance measures such as mean absolute error (MAE), root mean square error (RMSE), and root mean squared percentage error (RMSPE) are analyzed and compared with other existing measures. In an experimental scenario, the MAE of 2.59, RMSE of 2.97, and RMSPE of 0.35 for the male gender is obtained.

Evaluation of metaheuristic optimization algorithms applied to path planning

The development of autonomous ground vehicles is a topic widely discussed by the international scientific community. Path planning for these robots is an essential element to achieving a satisfactory fulfillment of missions without human intervention. This work adopts and improves the metaheuristic optimization methods harmony search and ant colony optimization, developing strategies based on the enhanced harmony search and improved ant colony optimization to achieve short, collision-free paths for robot movement. A description of the original methods and improvement procedures is presented, and their performance in path planning is compared through simulation. Theoretical results are supported by simulated experiments, which highlight the situations in which each metaheuristic algorithm is preferable and the benefits they bring to the path planning strategy.

Flood risk decomposed: Optimized machine learning hazard mapping and multi-criteria vulnerability analysis in the city of Zaio, Morocco

Urban flood risk mapping has become crucial for effective mitigation and urban planning. This study assesses and maps flood risk in the city of Zaio, Morocco, using machine learning and Multi-Criteria Decision Analysis (MCDA) techniques to overcome data scarcity challenges. We employed the Random Forest (RF) model with nine flood conditioning factors for flood hazard and the Analytical Hierarchy Process (AHP) for vulnerability assessment. To enhance RF model performance, we compared three hyperparameter tuning techniques: Bayesian Optimization (RF-BO), Genetic Algorithm (RF-GA), and Grid Search (RF-GS). RF-BO demonstrated superior accuracy in flood hazard modelling. Flood vulnerability was assessed using AHP, incorporating social and physical factors. The final flood risk map was produced by combining the RF-BO hazard model with the AHP vulnerability assessment. Results indicate that flood hazard in Zaio is significantly affected by factors such as topography and distance to rivers. Moreover, areas with high population density closer to rivers, especially in the south-western residential area, were found to be more exposed to flood risk. The findings highlight the utility of ML models, MCDA, and hyperparameter optimization in urban flood risk mapping, enabling the identification of high-risk urban areas that should be prioritized for flood protection efforts. This approach proves especially valuable in ungauged regions with limited hydrological data.

Enhancing Ovarian Cancer Detection Using Self-Organizing Maps and Improved Recurrent Neural Networks with Extended Harmony Search Optimization

Background: Ovarian cancer (OC) is a highly fatal malignancy of the female reproductive system, characterized by its high mortality rate and the challenges associated with clinical research due to the disease's complexity and late-stage diagnosis. Advances in technology, such as the Internet of Medical Things (IoMT), offer new opportunities for improving OC detection and diagnosis. Objective: This study aimed to develop and evaluate a novel method for OC detection using IoMT data, leveraging Self-Organizing Maps (SOM) and Improved Recurrent Neural Networks (IRNN) enhanced with the Extended Harmony Search Optimization (EHSO) algorithm to improve feature selection and classification accuracy. Methods: The study utilized OC data from the IoMT and applied SOM for feature selection, which helps in managing and classifying large datasets. SOM was employed to improve data representation and address challenges in labeling and classifying data. The IRNN model, optimized using the EHSO algorithm, was developed to enhance classification performance. The model was tested using a dataset from Kaggle comprising 179 benign and 172 malignant OC images with 50 attributes. Results: The IRNN model with EHSO demonstrated superior performance compared to other methods. In the training dataset, it achieved an accuracy of 95.72% and a Root Mean Square Error (RMSE) of 4.8%. For the testing dataset, the model maintained a high accuracy of 90.4% and an RMSE of 6.8%. The IRNN with EHSO outperformed alternative methods in terms of specificity and sensitivity, while the Genetic Algorithm (GA) showed the lowest performance across all metrics. Conclusion: The proposed method using SOM and IRNN with EHSO significantly improves the detection of ovarian cancer by optimizing feature selection and classification accuracy. This approach offers a promising advancement in utilizing IoMT data for early and accurate OC diagnosis, potentially enhancing patient outcomes through more effective detection and treatment strategies.