Applying Optimization Techniques Research Articles

Optimization of machine learning models through quantization and data bit reduction in healthcare datasets

This study focuses on enhancing complex machine learning models through quantization and data bit reduction. The primary goal is to reduce processing time while maintaining model performance, which is particularly relevant for intricate models with prolonged execution times. The research employs two medical datasets, namely Heart Disease Prediction and Breast Cancer Detection, and applies optimization techniques to K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) machine-learning models. To achieve optimization, the study employs effective quantization and data bit reduction techniques such as QuantileTransformer, Numpy.round, and KBinsDiscretizer functions. These techniques are utilized to convert input data from float64 to float32 and int32, resulting in a streamlined data representation. The trade-off between processing time and model accuracy is explored, acknowledging that some compromise in accuracy might occur after optimization. The experimentation reveals that there is a noticeable reduction in time complexity after optimization, with a marginal impact on model accuracy. Interestingly, the study concludes that the outcome and efficiency of optimization techniques are influenced not only by the specific technique used but also by the nature of the dataset and machine learning model under consideration. This comprehensive research showcases the applicability of optimization techniques, specifically quantization and data bit reduction, in complex machine learning models. By conducting experiments on medical datasets and analyzing KNN and SVM models, the study underscores the delicate balance between processing time and model accuracy. The findings emphasize that the success of optimization strategies is context-dependent, relying not only on the chosen technique but also on the interplay between the technique, model, and dataset.

Simple retrieval of the real part of the refractive index for ambient aerosols using extinction coefficient analysis via camera and volume size distribution

This study explored a novel approach for estimating the variations in the refractive index (RI) of aerosols, which is a crucial optical parameter that contains information about particle scattering and absorption. RI is often subject to constraints related to observation time, wavelength selection, and analysis methods. To overcome these limitations, we employed real-time continuous measurements using a camera and optical particle counter (OPC) equipment and applied optimization techniques based on the Mie theory to reverse-calculate changes in the refractive index. Our methodology uses a camera to measure the aerosol extinction coefficients at three different wavelengths within the RGB spectrum (597 nm, 534 nm, and 459 nm), whereas OPC observations provide information on particle size distribution (0.127–17.58 μm as radius). Because the extinction efficiency at known wavelengths varies with the refractive index according to the Mie theory, we retrieved the refractive index, which is an unknown variable, from the extinction coefficient equation. We focused on the real part of the RI because it is challenging to discern the imaginary part of the RI from the visible wavelengths. Our observations were conducted in areas near Busan Harbor and in mixed residential regions. The real part of the RI was determined to be 1.53 ± 0.12. During periods of observed dust events, the refractive index's real part was 1.62 ± 0.05, while during periods anticipated to have emissions of fine aerosols, it was 1.51 ± 0.10. The retrieved RI fell within a range similar to that in other studies, and the changes in the refractive index showed meaningful patterns when analyzed for variations in the particle size distribution and changes in the scattering coefficient. This approach has the potential to advance our understanding of aerosol optical properties and can be applied to real-time analyses with a relatively simple equipment setup, thereby opening new possibilities for its use as a critical variable in optical measurements and environmental models.

A novel brain EEG clustering based on Minkowski distance to improve intelligent epilepsy diagnosis

This paper introduces a novel clustering approach based on Minkowski's mathematical similarity to improve EEG feature selection for classification and have efficient Particle Swarm Optimization (PSO) in the context of machine learning. Given the intricacy of high-dimensional medical datasets, feature selection plays a critical role in preventing disease and promoting public health. By employing Minkowski clustering, the objective is to group dataset records into two clusters exhibiting high feature coherence, thereby improving accuracy by applying optimization techniques like PSO to select the most optimal features. Furthermore, the proposed model can be extended to intelligent datasets, including EEG and others. As fewer features are needed for precise categorization, intelligent feature selection is an advanced step of machine learning. This paper investigates the key factors influencing feature selection in the EEG Bonn University dataset. The proposed system is compared against various optimization and feature selection methods, demonstrating superior performance in analyzing and classifying EEG signals based on accuracy measures. The experimental results have confirmed the effectiveness of the suggested model as a valuable tool for EEG data classification, achieving up to 100% accuracy. The outcomes of this research have the potential to benefit medical experts in related specialties by streamlining the process of identifying and diagnosing brain disorders. Technically, the machine learning algorithms RF, KNN, SVM, NB, and DT are employed to classify the selected features.

Investigation of Simulated Annealing and Ant Colony Optimization to Solve Delivery Routing Problem in Surabaya, Indonesia

This research emphasizes the importance of efficient goods delivery services because it is essential in maintaining the sustainable supply chain's continuity and applying optimization techniques, specifically the Traveling Salesman Problem (TSP), in determining optimal transportation routes. It compares the effectiveness of the Simulated Annealing (SA) and Ant Colony Optimization (ACO) in finding the shortest routes to minimize operational costs. This study compares the performance of the SA and ACO algorithms. It shows that both provide improved routes compared to the existing routes, with the SA achieving shorter distances, 17.4% smaller than the existing route.

Optimal Strategies for Climate Change Mitigation

This work explores methods to address climate change by applying optimization techniques in a top-down approach. A decision model is proposed to minimize temperature anomalies compared to pre-industrial levels between 2025 and 2100 by varying greenhouse gases (GHG), namely CO2 and CH4. Two objective functions are minimized. The first one considers the overall sum of the temperature anomalies by 2100, while the latter minimizes the temperature anomaly at the end of the century. Two different emission trends are assumed: a gradual (gaussian) fall in emissions or a fast (exponential) decline. The reduction of GHG emissions is constrained to a set of IPCC scenarios identified by assessing economic, social, and technological trends in the next decades. The uncertainty analysis of the decision problem solutions suggests that temperature anomalies can be limited to the range of 0.8–2°C.

Deep convolutional neural network (CNN) model optimization techniques—Review for medical imaging

The field of artificial intelligence (AI) and machine learning (ML) has been expanding and is explored by researchers in various fields. In medical diagnosis, for instance, the field of AI/ML is being explored because if medical diagnostic devices are built and designed with a backend of AI/ML, then the benefits would be unprecedented. Automated diagnostic tools would result in reduced health care costs, diagnosis without human intervention, overcoming human errors, and providing adequate and affordable medical care to a wider portion of the population with portions of the actual cost. One domain where AI/ML can make an immediate impact is medical imaging diagnosis (MID), namely the classification of medical images, where researchers have applied optimization techniques aiming to improve image classification accuracy. In this paper, we provide the research community with a comprehensive review of the most relevant studies to date on the use of deep CNN architecture optimization techniques for MID. As a case study, the application of these techniques to COVID-19 medical images were made. The impacts of the related variables, including datasets and AI/ML techniques, were investigated in detail. Additionally, the significant shortcomings and challenges of the techniques were touched upon. We concluded our work by affirming that the application of AI/ML techniques for MID will continue for many years to come, and the performance of the AI/ML classification techniques will continue to increase.

Modeling of Dung Beetle Optimization-based Sink Node Localization Approach for Wireless Sensor Networks

Wireless sensor network (WSN) performs monitoring of each aspect of the area of interest by detecting the surrounding physical phenomena with sensor nodes and transferring the information to the gateway through the corresponding system. Several researcher workers have introduced localization methods to accomplish high accuracy of localization. An intelligent optimization technique has attracted various researcher workers due to its advantages such as strong optimization capability and few parameters to optimize the localization performance of the DV-Hop method. Sink node localization (NL) using metaheuristics in WSN includes applying optimization techniques inspired by human behavior or natural phenomena to define the geographical coordinates of the sink nodes within the network coverage region. WSNs can accomplish better localization performance, especially in dynamic or complex environments, improving the efficiency and reliability of network management and data transmission by leveraging metaheuristics. In this view, this manuscript develops a Dung Beetle Optimization based Sink Node Localization Approach (DBO-SNLA) for WSN. In the DBO-SNLA technique, the DBO algorithm involved is based on the social behavior of dung beetle populations and is developed with five updated rules to assist in finding high-quality solutions. In addition, the DBO-SNLA technique addresses the issues of defining the sink node location with lowest localization error once the data between the nodes is transferred wirelessly. Finally, the localization errors are calculated and the location of the different unknown nodes is computed. A detailed set of simulation takes place to examine the performance of the DBO-SNLA technique. The empirical analysis stated the betterment of the DBO-SNLA method than other techniques

Formulation of Radiality Constraints for Optimal Microgrid Formation

Forming microgrids (MG) in distribution systems (DSs) is an operational measure proposed to enhance power system flexibility. The computational performance of the applied optimization techniques varies greatly according to the constraints ensuring network radiality. Formulations of radiality constraints differ from each other by model complexity and the search space of the relaxed linear programming (LP) problem. In this paper, widely used formulations of radiality constraints are first revisited and flexibly enhanced to address the complex operating environment of modern DSs. To incorporate various radiality constraints and provide an optimization basis for comparison, a flexible MG formation problem is proposed with the ability to automatically allocate distributed generators (DGs) into multiple MGs. Combined formulations with parent-child (PC) constraints are then developed to shrink the LP feasible region. Moreover, to accelerate the branching process by applying the branch-and-cut (B&C) algorithm, an efficient formulation of radiality constraints is proposed by adding extra constraints that exclude fundamental loops into the single-commodity flow formulation. To further accelerate the branching process, a dynamic constraint generation algorithm is developed without substantially increasing the complexity of the LP problem. DSs of various complexities and sizes are employed to verify the computational efficiency of the proposed formulations. The paper concludes by suggesting the most efficient formulations of radiality constraints according to the scale of the targeted DS.

The performance optimization of 4-bit absolute-value detector

Absolute-Value Detection is a popular algorithm used for sorting spiking signals, and the 4-bit Absolute-Value Detector is a fundamental circuit in the spike-sorting field. This paper presents three distinct approaches for designing an absolute-value detector, along with optimization techniques used in these circuits. The paper begins by discussing the circuit’s structure, followed by using logical effort theory to calculate critical path delays. Next, the paper compares the critical path delays and transistor numbers of the three designs. Finally, the paper identifies the optimal design among the three circuits, which provides the best delay performance at a low cost. Applying optimization techniques to the optimal absolute-value detector resulted in a significant improvement in its performance. These findings have important implications for the future development of related industries, as they can help further refine and enhance the performance of spike-sorting algorithms. Overall, this paper provides valuable insights into the design and optimization of absolute-value detectors, which will be of great interest to researchers and practitioners in the field.

A Comparative Study of Evolutionary and Swarm Intelligence Algorithms for Job Scheduling on Identical Parallel Machines

In parallel computing systems, job scheduling plays a crucial role in enhancing system efficiency and minimizing the makespan. In recent years, evolutionary and swarm intelligence algorithms have gained prominence as effective approaches for solving combinatorial optimization problems. In the present work, we have considered genetic algorithm (GA) for evolutionary algorithms and particle swarm optimization (PSO) for swarm intelligence algorithms. Evolutionary algorithms (EA) and swarm intelligence algorithms (SIA) have shown promising results in solving job scheduling challenges. In this study, we collate the performance of EA and SIA approaches for job scheduling on parallel machines. We use different benchmark instances to evaluate the algorithms' makespan and computational time performance. The results show that SIA algorithms outperform EA algorithms regarding makespan and computational time for all benchmark instances. Furthermore, the study provides insights into the strengths and weaknesses of EA and SIA algorithms for job scheduling on parallel machines. Our findings provide useful insights for researchers and practitioners interested in applying optimization techniques to solve job scheduling problems on parallel machines.

Kinematic Analysis of a Tendon-Driven Hybrid Rigid–Flexible Four-Bar; Application to Optimum Dimensional Synthesis

In design matters, mechanisms with deformable elements are a step behind those with rigid bars, particularly if dimensional synthesis is considered a fundamental part of mechanism design. For the purposes of this work, a hybrid rigid–flexible four-bar mechanism has been chosen, the input bar being a continuum tendon of constant curvature. The coupler curves are noticeably more complex but offer more possibilities than the classical rigid four-bar counterpart. One of the objectives of this work is to completely characterize the coupler curves of this hybrid rigid–flexible mechanism, determining the number and type of circuits as well as constituent branches. Another important aim is to apply optimization techniques to the dimensional synthesis of path generation. Considerable progress in finding the best design solutions can be obtained if all the acquired knowledge about the coupler curves of this hybrid mechanism is integrated into the optimization algorithm.

Zero-Carbon AC/DC Microgrid Planning by Leveraging Vehicle-to-Grid Technologies

This paper explores the strategic planning required for a zero-carbon-emission AC/DC microgrid, which integrates renewable energy sources and electric vehicles (EVs) within its framework. It considers the rapidly growing adoption of EVs and the advent of vehicle-to-grid (V2G) technology, which allows EVs to return energy to the grid during peak demand. The study aims to apply optimization techniques to minimize the installation cost associated with various microgrid components. In the case of microgrids, there are decision-making scenarios where multiple alternatives are present; optimization is a valuable technique for efficiently planning and designing microgrids. This work showcases case studies and sensitivity analysis plots, illustrating how output power fluctuates due to uncertainty in renewable energy sources and the absence of EVs. The findings show how V2G contributes to the demand when renewable generation is low. The sensitivity analysis also provides insights into how the unit cost is affected by demand fluctuations. In summary, the principal contribution of this study is developing a comprehensive planning framework for AC/DC microgrids. This framework considers the escalating adoption of EVs and offers practical solutions for future microgrid designs.

Concern Condition for Applying Optimization Techniques with Reservoir Simulation Model for Searching Optimal Rule Curves

This paper presents a comprehensive review of optimization algorithms utilized in reservoir simulation-optimization models, specifically focusing on determining optimal rule curves. The study explores critical conditions essential for the optimization process, including inflow data, objective and smoothing functions, downstream water demand, initial reservoir characteristics, evaluation scenarios, and stop criteria. By examining these factors, the paper provides valuable insights into the effective application of optimization algorithms in reservoir operations. Furthermore, the paper discusses the application of popular optimization algorithms, namely the genetic algorithm (GA), particle swarm optimization (PSO), cuckoo search (CS), and tabu search (TS), highlighting how researchers can utilize them in their studies. The findings of this review indicate that identifying optimal conditions and considering future scenarios contribute to the derivation of optimal rule curves for anticipated situations. The implementation of these curves can significantly enhance reservoir management practices and facilitate the resolution of water resource challenges, such as floods and droughts.

Carbon Capture, Utilization, and Storage in Saline Aquifers: Subsurface Policies, Development Plans, Well Control Strategies and Optimization Approaches—A Review

To mitigate dangerous climate change effects, the 195 countries that signed the 2015 Paris Agreement agreed to “keep the increase in average global surface temperature below 2 °C and limit the increase to 1.5 °C” by reducing carbon emissions. One promising option for reducing carbon emissions is the deployment of carbon capture, utilization, and storage technologies (CCUS) to achieve climate goals. However, for large-scale deployment of underground carbon storage, it is essential to develop technically sound, safe, and cost-effective CO2 injection and well control strategies. This involves sophisticated balancing of various factors such as subsurface engineering policies, technical constraints, and economic trade-offs. Optimization techniques are the best tools to manage this complexity and ensure that CCUS projects are economically viable while maintaining safety and environmental standards. This work reviews thoroughly and critically carbon storage studies, along with the optimization of CO2 injection and well control strategies in saline aquifers. The result of this review provides the foundation for carbon storage by outlining the key subsurface policies and the application of these policies in carbon storage development plans. It also focusses on examining applied optimization techniques to develop CO2 injection and well control strategies in saline aquifers, providing insights for future work and commercial CCUS applications.

Application of Optimization Techniques for Searching Optimal Reservoir Rule Curves: A Review

This paper reviews applications of optimization techniques connected with reservoir simulation models to search for optimal rule curves. The literature reporting the search for suitable reservoir rule curves is discussed and examined. The development of optimization techniques for searching processes are investigated by focusing on fitness function and constraints. There are five groups of optimization algorithms that have been applied to find the optimal reservoir rule curves: the trial and error technique with the reservoir simulation model, dynamic programing, heuristic algorithm, swarm algorithm, and evolutionary algorithm. The application of an optimization algorithm with the considered reservoirs is presented by focusing on its efficiency to alleviate downstream flood reduction and drought mitigation, which can be explored by researchers in wider studies. Finally, the appropriate future rule curves that are useful for future conditions are presented by focusing on climate and land use changes as well as the participation of stakeholders. In conclusion, this paper presents the suitable conditions for applying optimization techniques to search for optimal reservoir rule curves to be effectively applied in future reservoir operations.

Topology Optimization of fiber reinforced structures considering stress constraint and optimized penalization

The use of materials reinforced with fibers has been increasing due to their advantages, for example, the ratio between its mass and strength. For this reason, new additive manufacturing technologies have been developed for this material type. Some technologies allow tailoring fiber orientation, creating space for applying optimization techniques. On this account, many works dedicated to optimizing fiber orientation have been currently published. However, the critical issue of the stress yield criteria should be addressed. Thus, this work proposes to solve the Topology Optimization problem of minimizing the volume of the structure considering local stress constraints, determining the material distribution and the fiber orientation by using a proposed method named NDFO-adapt. The penalization used in the method is a field optimized together with the material distribution and the fiber angle. The same approach is extended to the penalization of SIMP and β parameters of threshold projection. This strategy enlarges the solution space and facilitates the discovery of previously unachievable local minima while eliminating the need for a heuristic selection of continuation methods. The Augmented Lagrangian method is used to deal with the local stress constraints. A mesh refinement scheme developed in the FEniCS project is proposed. Numerical examples are presented to illustrate the performance of the proposed method.

Change in glottic view during intubation using a KoMAC videolaryngoscope: A retrospective analysis.

Intubation with videolaryngoscopy has become popular in various clinical settings. However, despite the use of a videolaryngoscope, difficult intubation still exists and intubation failure has been reported. This retrospective study assessed the efficacy of the 2 maneuvers in improving the glottic view during videolaryngoscopic intubation. The medical records of patients who underwent videolaryngoscopic intubation and whose glottal images were stored in electronic medical charts were reviewed. The videolaryngoscopic images were divided into 3 categories according to the applied optimization techniques as follows: conventional method, with the blade tip located in the vallecular; backward-upward-rightward pressure (BURP) maneuver; and epiglottis lifting maneuver. Four independent anesthesiologists scored the visualization of the vocal folds using the percentage of glottic opening (POGO, 0-100%) scoring system. A total of 128 patients with 3 laryngeal images were analyzed. The glottic view was the most improved in the epiglottis lifting maneuver among all the techniques. The median POGO scores were 11.3, 36.9, and 63.1 in the conventional method, BURP, and epiglottis lifting maneuver, respectively (P < .001). There were significant differences in the distribution of POGO grades according to the application of BURP and epiglottis lifting maneuvers. In the POGO grades 3 and 4 subgroups, the epiglottis lifting maneuver was more effective than the BURP maneuver in improving the POGO score Inadequate visualization of the vocal folds occurred even when intubation was performed using a videolaryngoscope. The application of optimization maneuvers, such as BURP and epiglottis lifting by the blade tip, could improve the glottic view.

MASISCo—Methodological Approach for the Selection of Information Security Controls

As cyber-attacks grow worldwide, companies have begun to realize the importance of being protected against malicious actions that seek to violate their systems and access their information assets. Faced with this scenario, organizations must carry out correct and efficient management of their information security, which implies that they must adopt a proactive attitude, implementing standards that allow them to reduce the risk of computer attacks. Unfortunately, the problem is not only implementing a standard but also determining the best way to do it, defining an implementation path that considers the particular objectives and conditions of the organization and its availability of resources. This paper proposes a methodological approach for selecting and planning security controls, standardizing and systematizing the process by modeling the situation (objectives and constraints), and applying optimization techniques. The work presents an evaluation of the proposal through a methodology adoption study. This study showed a tendency of the study subjects to adopt the proposal, perceiving it as a helpful element that adapts to their way of working. The main weakness of the proposal was centered on ease of use since the modeling and resolution of the problem require advanced knowledge of optimization techniques.

Enhancing Experiential Learning to Address Loss of Hands-on Laboratory Due to Covid-19 Pandemic

All sectors of life have been hit hard by the pandemic caused by covid-19. This impact has been brutal on streams like engineering in the educational sector, where practical or laboratory courses play a vital role in learning. Due to the limitations of online learning, the students could not explore the full extent of hands-on learning in their Fourth semester ARM microcontroller course. In order to compensate for the loss, the laboratory activities in the Fifth semester RTOS (Real-Time Operating System) Laboratory course are enhanced to provide students with a hands-on learning experience in building applications in both the ARM and RTOS environment. The extended activities enhanced student learning in the ARM environment, which they were previously deprived of during online instruction. Also, emphasis is provided on applying optimization techniques to memory and timing requirements for a given problem statement. The results show that the extended activities helped students co-relate and integrate concepts addressed during their 4th and 5th-semester courses and build a small application of the embedded systems. Keywords—Embedded Real-time systems; Extended Activity; project-based learning;

Extracting Optimal Operation Rule Curves of Multi-Reservoir System Using Atom Search Optimization, Genetic Programming and Wind Driven Optimization

This research aims to apply optimization techniques using atom search optimization (ASO), genetic programming (GP), and wind-driven optimization (WDO) with a reservoir simulation model for searching optimal rule curves of a multi-reservoir system, using the objective function with the minimum average quantity of release excess water. The multi-reservoir system consisted of five reservoirs managed by a single reservoir that caused severe problems in Sakon Nakhon province, Thailand, which was hit by floods in 2017. These included Huai Nam Bo Reservoir, the Upper Huai Sai-1 Reservoir, the Upper Huai Sai-2 Reservoir, the Upper Huai Sai-3 Reservoir, and the Huai Sai Khamin Reservoir. In this study, the monthly reservoir rule curves, the average monthly inflow to the reservoirs during 2005–2020, the water demand of the reservoirs, hydrological data, and physical data of the reservoirs were considered. In addition, the performance of the newly obtained rule curves was evaluated by comparing the operation with a single reservoir and the operation with a multi-reservoir network. The results showed situations of water shortage and water in terms of frequency, duration, average water, and maximum water. The newly obtained rule curves from the multi-reservoir system case showed an average water excess of 43.722 MCM/year, which was less than the optimal curves from the single reservoir case, where the average water excess was 45.562 MCM/year. An analysis of the downstream reservoir of the multi-reservoir system, which diverts water from the upstream reservoirs, was performed. The results showed that the new optimal rule curves of ASO, GP, and WDO operated as a multi-reservoir system performed better than when operated as a single reservoir. Therefore, this research is suitable for sustainable water management without construction.