Ideal Parameter Setting Research Articles

Improving Alzheimer’s Disease and Brain Tumor Detection Using Deep Learning with Particle Swarm Optimization

Convolutional Neural Networks (CNNs) have exhibited remarkable potential in effectively tackling the intricate task of classifying MRI images, specifically in Alzheimer’s disease detection and brain tumor identification. While CNNs optimize their parameters automatically through training processes, finding the optimal values for these parameters can still be a challenging task due to the complexity of the search space and the potential for suboptimal results. Consequently, researchers often encounter difficulties determining the ideal parameter settings for CNNs. This challenge necessitates using trial-and-error methods or expert judgment, as the search for the best combination of parameters involves exploring a vast space of possibilities. Despite the automatic optimization during training, the process does not guarantee finding the globally-optimal parameter values. Hence, researchers often rely on iterative experimentation and expert knowledge to fine-tune these parameters and maximize CNN performance. This poses a significant obstacle in developing real-world applications that leverage CNNs for MRI image analysis. This paper presents a new hybrid model that combines the Particle Swarm Optimization (PSO) algorithm with CNNs to enhance detection and classification capabilities. Our method utilizes the PSO algorithm to determine the optimal configuration of CNN hyper-parameters. Subsequently, these optimized parameters are applied to the CNN architectures for classification. As a result, our hybrid model exhibits improved prediction accuracy for brain diseases while reducing the loss of function value. To evaluate the performance of our proposed model, we conducted experiments using three benchmark datasets. Two datasets were utilized for Alzheimer’s disease: the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and an international dataset from Kaggle. The third dataset focused on brain tumors. The experimental assessment demonstrated the superiority of our proposed model, achieving unprecedented accuracy rates of 98.50%, 98.83%, and 97.12% for the datasets mentioned earlier, respectively.

Parameter Optimization of Gas Metal Arc Welding Process for Welding Dissimilar Steels

Welding is a method of joining similar and dissimilar metals through the use of coalescence. GMAW is a semi-mechanized, fully-mechanized, or automatic process that is widely used in fabrication. GMAW is expected to evolve further to allow for better arc control, bead contour control, deposition control, and higher productivity. The goal of this study is to enhance welding process variables for dissimilar steel metal joints made of duplex stainless steel (DSS) to ASTM/UNS S32205 and erosional steel CORTEN-A to ASTM A242. Such a dissimilar metal joint finds use in the transportation sector, particularly in the construction of rail cars. The square butt joint between two 2 mm-thick sheets was investigated using the gas metal arc welding (GMAW) process with CO₂ as the shielding gas and flux-cored wire of grade 309L as the filler material. The L₉ Taguchi array was used to optimize the tensile strength of the resulting weld joint, which was the desired quality characteristic. GMAW process parameters such as voltage, wire feed rate, and welding speed are optimized at three levels. Using ANOVA, the effects of each factor have been studied. It was found that the ideal set of parameters exists and that the voltage is the most crucial factor. A confirmation test was performed to validate the results, and it was accompanied by a figure and tables.

Gas Metal Arc Welding Process Variables Enhancement for Welding Significantly different Steels

The goal of this study is to enhance welding process variables for dissimilar steel metal joints made of duplex stainless steel (DSS) to ASTM/UNS S32205 and erosional steel CORTEN-A to ASTM A242. Such a dissimilar metal joint finds use in the transportation sector, particularly in the construction of rail cars. The square butt joint between two 2mm thick sheets was investigated using the gas metal arc welding (GMAW) process with CO2 as the shielding gas and flux cored wire of grade 309L as the filler material. The L9 Taguchi array was used to optimize the tensile strength of the resulting weld joint, which was the desired quality characteristic. GMAW process parameters such as voltage, wire feed rate, and welding speed are optimized at three levels. Using ANOVA, the effects of each factor have been studied. It was found that the ideal set of parameters exists, and that the voltage is the most crucial factor. A confirmation test was performed to validate the results, and it was accompanied by a figure and tables.

Application of Taguchi methods (DOE) in composite engineering

In the paper, a design of experiment (DOE) in terms of the Taguchi method was used for the optimization of the manufacturing process. This approach makes it possible to do fewer experiments while still getting the desired outcomes. This research programme will use this tool to optimize the resin casting process by monitoring manufacturing parameters like temperature, curing time, and flame-retardant concentration. Thus, this study aims to determine the ideal set of parameters for the resin casting of composite materials. Based on experimental results, it was possible to find crucial factors and their influence on the fracture strength of resin for composite manufacturing systems.

Effect of High Speed Machining on Surface Roughness Characteristics Ra, Rq, RZ

Today’s machining industries experience a variety of challenges, but achieving high quality in terms of dimensional accuracy, surface quality, and production rate is their key concern. An effort has been made in the current study to investigate the impact of HSM process parameters on different Surface Roughness characteristics Ra, Rq, and Rz. The trials were conducted on Ti-6Al-4V, a material that finds extensive use in the automotive, aerospace, and biomedical industries. Depth of cut, feed rate, cutting speed, and step over were taken into account as HSM inputs for the experiment. Similar to this, the output characteristics Surface roughness parameters Ra, Rq, and Rz were used. The trials were carried out using Taguchi’s standard L9 Orthogonal Array, and the optimization of multi responses was carried out using Grey analysis. The most significant influences on the parameters of surface roughness were found to be cutting speed and depth of cut. A confirmation experiment was performed using the ideal set of parameters to validate the study, and the results were found to be in good agreement with those of the experiment. According to the findings, the HSM method produced a superior surface quality.

MILP performance improvement strategies for short-term batch production scheduling: a chemical industry use case

This paper presents the development and mathematical implementation of a production scheduling model utilizing mixed-integer linear programming (MILP). A simplified model of a real-world multi-product batch plant constitutes the basis. The paper shows practical extensions to the model, resulting in a digital twin of the plant. Apart from sequential arrangement, the final model contains maintenance periods, campaign planning and storage constraints to a limited extend. To tackle weak computational performance and missing model features, a condensed mathematical formulation is introduced at first. After stating that these measures do not suffice for applicability in a restrained time period, a novel solution strategy is proposed. The overall non-iterative algorithm comprises a multi-step decomposition approach, which starts with a reduced scope and incrementally complements the schedule in multiple subproblem stages. Each of those optimizations holds less decision variables and makes use of warmstart information obtained from the predecessor model. That way, a first feasible solution accelerates the subsequent improvement process. Furthermore, the optimization focus can be shifted beneficially leveraging the Gurobi solver parameters. Findings suggest that correlation may exist between certain characteristics of the scheduling scope and ideal parameter settings, which yield potential for further investigation. Another promising area for future research addresses the concurrent multi-processing of independent MILPs on a single machine. First observations indicate that significant performance gains can be achieved in some cases, though sound dependencies were not discovered yet.

A Study for an Ideal Password Management System

Abstract: The growing number of online services needs users to have control over their password management system (generation, storage, recall). But the demand for total randomness and exclusivity of passwords is impractical in day-to-day life. Each component of a password management system comes with its cognitive burden on a user. There are many password management solutions available for users but every one of them has some drawbacks. Password managers have the ability to help users manage their passwords more successfully while also addressing many of the problems about password-based authentication. In this study, We're analyzing various previous studies regarding the effectiveness, usability, and security of password managers of all categories. Also, we're trying to come up with an ideal set of parameters to build the best possible password management system in 2022. This study will help to understand the key parameters and algorithms that we can use while building the ideal password generation, storage, and recall system for the user.

Validation scheme for solar coronal models: Constraints from multi-perspective observations in EUV and white light

Context. In this paper, we present a validation scheme to investigate the quality of coronal magnetic field models, which is based on comparisons with observational data from multiple sources. Aims. Many of these coronal models may use a range of initial parameters that produce a large number of physically reasonable field configurations. However, that does not mean that these results are reliable and comply with the observations. With an appropriate validation scheme, which is the aim of this work, the quality of a coronal model can be assessed. Methods. The validation scheme was developed with the example of the EUropean Heliospheric FORecasting Information Asset (EUHFORIA) coronal model. For observational comparison, we used extreme ultraviolet and white-light data to detect coronal features on the surface (open magnetic field areas) and off-limb (streamer and loop) structures from multiple perspectives (Earth view and the Solar Terrestrial Relations Observatory – STEREO). The validation scheme can be applied to any coronal model that produces magnetic field line topology. Results. We show its applicability by using the validation scheme on a large set of model configurations, which can be efficiently reduced to an ideal set of parameters that matches best with observational data. Conclusions. We conclude that by using a combined empirical visual classification with a mathematical scheme of topology metrics, a very efficient and objective quality assessment for coronal models can be performed.

Leveraging network using controlled weight learning approach for thyroid cancer lymph node detection

Identification of cervical metastatic lymph nodes (LN) on I-131 post-ablation whole-body planar scans (WBS) for cancer staging is crucial for patients with papillary thyroid cancer (PTC). The existing deep network is plagued by instability in finding the under-represented LN classes on highly complex WBS, where end-to-end tuned models that can account for this uncertainty region for multi-class locations are needed. Hence, as a key contribution of this study, we designed a novel leveraging segmentation network with input guidance (LSIG) end-to-end training model without pre and post-processing features that can learn ideal parameter settings depending on the quantity of multiple-object instances. To improve the co-occurrence of classes and control the false positive regions, we proposed a re-weighting negative control (RNC) mechanism that combines two key components, namely the re-weighting (Rw) term and the negative control function (NcF). This unified approximation of weighted training would leverage the network to control and learn the desired weights of true positives towards the LN region. As an end-to-end network training, we utilize a Unet-like convolution neural network (CNN) model. The performance of the LSIG is compared with the CNN-based networks, based on the ground truth (GT) mask developed using post-ablation single-photon emission computed tomography (SPECT/CT). Furthermore, the effectiveness of the two components used in the LSIG framework is evaluated on WBS datasets. Our proposed LSIG with a fully guided (Fg) LS-FgCNN model yielded a superior performance with high AUC value of 94.9%, which is 14.6% higher than the previous network for PTC.

Using CANARY event detection software for water quality analysis in the Milwaukee River

Urban water sources are susceptible to various contamination events as a result of natural, accidental, and human-induced occurrences. An early warning monitoring system provides timely information on changes in urban water quality. In this study, an analysis was made with CANARY event detection software (EDS) to monitor water quality parameters in river water and to identify the onset of anomalous water quality periods. Water quality signals including pH, conductivity, and turbidity from the Milwaukee River over specified periods during the summer season of 2018–2020 were employed as inputs to event detection algorithms in CANARY. The data analysis results show that CANARY can be useful as an early warning system for monitoring contamination in urban water sources and help to identify abnormal conditions quickly. The sensibility of the model relies on optimizing the configuration parameters, which involves selecting the ideal set of parameters for the event detection algorithm and adjusting the BED parameters to increase or decrease the probability of generating an alarm. The number of events reported between the Linear Prediction Correction Filter (LPCF) and Multivariate Nearest Neighbor (MVNN) algorithms varied as a result of different residual calculation mechanisms. Climate factors that contributed to the abnormal water quality events in the river were examined. The analysis of rainfall on water quality was carried out using a statistical method by determining whether there is a significant difference (p-value) between the seasonal mean water quality data and the mean value of water parameters during the sampling duration. Regression analysis was also performed to estimate the best model that describes the relationship between each of the water quality parameters and temperature.

Synergy of Viscosity Wedge and Squeeze Under Zero Entrainment Velocity in EHL Contacts

In an elastohydrodynamic lubricated (EHL) contact under Zero Entrainment Velocity (ZEV) condition, surfaces cannot be separated by hydrodynamic lift. In this work, two other phenomena responsible for a film thickness build-up in ZEV contacts are studied using a numerical model. First, the thermal effect called “viscosity wedge” is investigated in steady-state conditions. Second, the “squeeze” effect is described in an environment where dynamic (time dependent) loads are considered. Then, both the viscosity wedge and squeeze effects are considered together. For each one of the two mechanisms, a characteristic time is considered. The ratio of these two times allows the identification of a dominant effect. Depending on this ratio, a prediction is attempted using semi-analytical models describing each effect. For an ideal set of parameters, it is shown that the combination of squeeze and viscosity wedge in EHL contact under ZEV allows for an enhanced performance.

Evaluating the grinding ratio and surface quality of Ti-6Al-4V under varying grinding pass count and depth of cut

Surface finishing of advanced difficult-to-machine materials through grinding is posing a significant challenge to the manufacturing industries. However, one of these materials, Ti-6Al-4V has a significantly high usage in several cutting-edge sectors. Thus, finding optimum grinding conditions for processing of this material becomes critical. Present article represents an experimental investigation dedicated towards analysing the effects of varying grinding pass counts and infeed values on the surface roughness, hardness, visible surface burns and grinding ratio of Ti-6Al-4V applying alumina wheel. Experiments are performed to reveal the trend of the surface properties and hardness of Ti-6Al-4V, ground at 10 μm and 20 μm infeed values with different sets of grinding passes. The results indicate that grinding at 15 pass count under 10 μm and 20 μm infeed values are the ideal set of parameters for the operating ranges considered herein.

Machines as Craftsmen: Localized Parameter Setting Optimization for Fused Filament Fabrication 3D Printing

AbstractQuality control and repeatability of 3D printing must be enhanced to fully unlock its utility beyond prototyping and noncritical applications. Machine learning is a potential solution to improving 3D printing performance and is explored for areas including flaw identification and property prediction. However, critical problems must be resolved before machine learning can truly enable 3D printing to reach its potential, including the very large data sets required for training and the inherently local nature of 3D printing where the optimum parameter settings vary throughout the part. This work outlines an end‐to‐end tool for integrating machine learning into the 3D printing process. The tool selects the ideal parameter settings at each location, taking into consideration factors such as geometry, hardware and material response times, and operator priorities. The tool demonstrates its usefulness by correcting for visual flaws common in fused filament fabrication parts. An image recognition neural network classifies local flaws in parts to create training data. A gradient boosting classifier then predicts the local flaws in future parts, based on location, geometry, and parameter settings. The tool selects optimum parameter settings based on the aforementioned factors. The resulting prints show increased quality over prints that use global parameters only.

Additive Manufacturing of H11 with Wire-Based Laser Metal Deposition

Abstract Laser additive manufacturing (LAM) is a near-net-shape production technique by which a part can be built up from 3D CAD model data, without material removal. Recently, these production processes gained attention due to the spreading of polymer-based processes in private and commercial applications. However, due to the insufficient development of metal producing processes regarding design, process information and qualification, resistance on producing functional components with this technology is still present. To overcome this restriction further studies have to be undertaken. The present research proposes a parametric study of additive manufacturing of hot work tool steel, H11. The selected LAM process is wire-based laser metal deposition (LMD-W). The study consists of parameters optimization for single beads (laser power, travel speed and wire feed rate) as well as lateral and vertical overlap for layer-by-layer technique involved in LMD process. Results show that selection of an ideal set of parameters affects substantially the surface quality, bead uniformity and bond between substrate and clad. Discussion includes the role of overlapping on the soundness of parts based on the height homogeneity of each layer, porosity and the presence of gaps. For the conditions tested it was shown that once the deposition parameters are selected, lateral and vertical overlapping determines the integrity and quality of parts processed by LAM.

Urban landcover classification from multispectral image data using optimized AdaBoosted random forests

ABSTRACTWith an ever growing need to classify multispectral images, the accuracy of the classification becomes a matter of concern, especially when mapping heterogeneous environments such as urban areas. Not all of the features of a high-resolution multispectral image would equally contribute to the formulation of an ideal hypothesis, some of which might be redundant and might hinder the classification itself. Random forests (RF), an ensemble of decision trees, would assist in the removal of such extraneous features. While RF has proved to be one of the most efficient classifiers for spectral imagery, it holds untapped potential which could be honed to yield much more accurate prediction rates. This article discusses the application of AdaBoosted random forest (ABRF) to classify landcover segments from multispectral satellite or aerial imagery. A stage-wise optimization procedure is applied to achieve the best possible performance. It involves genetic feature selection and strategic empirical calibration to determine the ideal set of parameters. The application of boosting to RF resulted in the increase in the overall accuracy from 84.42% to 88.8% with an increase in kappa coefficient from 0.804 to 0.859.

Using Domain Knowledge to Improve Monte-Carlo Tree Search Performance in Parameterized Poker Squares

Poker Squares is a single-player card game played on a 5 x 5 grid, in which a player attempts to create as many high-scoring Poker hands as possible. As a stochastic single-player game with an extremely large state space, this game offers an interesting area of application for Monte-Carlo Tree Search (MCTS). This paper describes enhancements made to the MCTS algorithm to improve computer play, including pruning in the selection stage and a greedy simulation algorithm. These enhancements make extensive use of domain knowledge in the form of a state evaluation heuristic. Experimental results demonstrate both the general efficacy of these enhancements and their ideal parameter settings.

Genetic Algorithm Application in Optimization of Wireless Sensor Networks

There are several applications known for wireless sensor networks (WSN), and such variety demands improvement of the currently available protocols and the specific parameters. Some notable parameters are lifetime of network and energy consumption for routing which play key role in every application. Genetic algorithm is one of the nonlinear optimization methods and relatively better option thanks to its efficiency for large scale applications and that the final formula can be modified by operators. The present survey tries to exert a comprehensive improvement in all operational stages of a WSN including node placement, network coverage, clustering, and data aggregation and achieve an ideal set of parameters of routing and application based WSN. Using genetic algorithm and based on the results of simulations in NS, a specific fitness function was achieved, optimized, and customized for all the operational stages of WSNs.

Fundamental Analysis of High Frequent Electrical Process Signals for Advanced Technology Developments in W-EDM

Technology development in EDM is very time consuming especially for the application of new materials or in the case of unfavorable machining conditions. Due to the large number of influencing factors and their interdependencies it is not possible to predict the machining conditions only by interpretation of the used generator parameters. Therefore it is difficult to link the machining results directly to the parameter setting. As a consequence a large number of test series are typically performed in a trial and error approach to find the ideal set of parameters for each machining task. But in this case the resulting technology is limited to the machining of the same material, geometry and the used machine tool.For an intelligent model based technology development the direct influence of the generator parameters on the actual process conditions need to be identified. In this paper the actual physical values for current and voltage as well as pulse on- and off-time of each discharge is determined by monitoring the electrical process signals. By tracking these values over time the quality of the whole process is evaluated by determination of the actual discharge frequency, the percentage of misdischarges and the resulting duty cycle. These parameters are then linked to the output variables cutting rate and surface roughness. Using this approach the specific influence of the machined material as well as other special machining conditions on the EDM process can be identified. With this fundamental knowledge the needed test series for future developments can be reduced and the transferability of the resulting technology will be improved significantly.

The optimal process mean problem: Integrating predictability and profitability into an experimental factor space

For complex manufacturing systems, process or product optimization can be instrumental in achieving a significant economic advantage. To reduce costs associated with product non-conformance or excessive waste, engineers often identify the most critical quality characteristics and then use methods to obtain their ideal parameter settings. The optimal process mean problem is one such statistical method; it begins with the assumption of the characteristic parameters, whereby the ideal settings are determined based upon the tradeoff among various processing costs. Unfortunately, however, the ideal parameter settings for a characteristic mean can be unpredictable, as it is directly influenced by changes in the process variability, tolerance, and cost structure. In this paper, a method is proposed that relates the optimal process mean to the ideal settings through experimental design. With the method, one may gain greater predictability of the new optimal process mean when the process conditions are altered. The methodology is illustrated for a process with multiple mixed quality characteristics; such an optimal process mean problem is seldom treated in the literature.

A Truly Random Number Generator Based on a Pulse-Excited Cross-Coupled Chaotic Oscillator

A non-autonomous cross-coupled chaotic circuit is presented with its derivation mechanism. To guarantee robust chaotic behavior of the circuit against parameter variations, an ideal set of parameters is determined by constructing bifurcation diagrams. A truly random number generator (TRNG), which relies on generating non-invertible binary sequences according to regional distributions of underlying chaotic signal, is also introduced. Simulation and experimental results verifying the feasibility of the circuit are given. The proposed TRNG offers much higher and constant throughput rates, allows for offset compensation and fulfills the NIST-800-22 statistical test suite without further post-processing.