Accurate and correct price prediction of gold is significant to maintain the stability and fair operation of gold markets as well as the efficiency and proper functioning of financial markets related to gold trading. Gold prices have a long history of non-linear and non-stationary behavior that generates highly complex datasets which are very difficult to forecast with high accuracy and reliability. At the same time Support Vector Regression (SVR) has been utilized as a robust information for prediction not only gold prices but also overall metal price movements. First, the predictive capability of SVR is highly sensitive to hyperparameter selection which needs to be thoroughly tuned and optimized for potentially optimal performance. Therefore, the suitable and cautious selection of these hyperparameters can play a significant and direct role in determining the success and precision of SVR. In this study, the focus is on proposing a new technique through horse herd optimization (HHO), which can be used for hyperparameter estimation and tuning of support vector regression (SVR) based on the collective behavior of horse herds to achieve efficient forecasting accuracy and reliability in gold prices. The outcomes and conclusions illustrate that the hybrid algorithm can furnish an increase to the general accuracy of our gold prices, showing superior overall performance as in contrast with two classical benchmark techniques on this area. These enhancements are time to market and useful for enabling faster global economic regeneration and restoration, but also enable the demand side characteristics of integrating international trade commodity price discovery mechanisms into explanations for AI techniques in the context of learning tasks and financial oscular analytics.
Unconfined Compressive Strength is considered the most important parameter of rock strength properties affecting the rock failure criteria. Various research have developed rock strength for specific lithology to estimate high-accuracy value without a core. Previous analyses did not account for the formation's numerous lithologies and interbedded layers. The main aim of the present study is to select the suitable correlation to predict the UCS for hole depth of formation without separating the lithology. Furthermore, the second aim is to detect an adequate input parameter among set wireline to determine the UCS by using data of three wells along ten formations (Tanuma, Khasib, Mishrif, Rumaila, Ahmady, Maudud, Nahr Um
... Show MoreTerahertz (THz) technology, which uses radiation lying between microwave and infrared in the electromagnetic spectrum, could revolutionize digital agriculture through terahertz’s ability to assess agricultural materials accurately and non-destructively. The review discusses notable developments in THz applications to digital agriculture: real-time crop monitoring, nutrient and disease detection, soil moisture and contaminant analysis, and supply chain traceability. The developments have emerged from studies in time-domain spectroscopy, imaging, machine learning (ML), and blockchain integration. Despite the promising advances in THz agricultural applications, limitations remain, such as limited penetration depth, high system costs, and ope
... Show MoreTWMS Journal of Applied and Engineering Mathematics | Volume: 16 Issue: 9
This study employs evolutionary optimization and Artificial Intelligence algorithms to determine an individual’s age using a single-faced image as the basis for the identification process. Additionally, we used the WIKI dataset, widely considered the most comprehensive collection of facial images to date, including descriptions of age and gender attributes. However, estimating age from facial images is a recent topic of study, even though much research has been undertaken on establishing chronological age from facial photographs. Retrained artificial neural networks are used for classification after applying reprocessing and optimization techniques to achieve this goal. It is possible that the difficulty of determining age could be reduce
... Show MoreCircular data (circular sightings) are periodic data and are measured on the unit's circle by radian or grades. They are fundamentally different from those linear data compatible with the mathematical representation of the usual linear regression model due to their cyclical nature. Circular data originate in a wide variety of fields of scientific, medical, economic and social life. One of the most important statistical methods that represents this data, and there are several methods of estimating angular regression, including teachers and non-educationalists, so the letter included the use of three models of angular regression, two of which are teaching models and one of which is a model of educators. ) (DM) (MLE) and circular shrinkage mod
... Show MoreIn this paper activated carbon adsorbents produced from waste tires by chemical activation methods and application of microwave assisted KOH activation. The influence of radiation time, radiation power, and impregnation ratio on the yield and oil removal which is one of the major environmental issues nowadays and considered persistent environmental contaminants and many of them are suspected of being carcinogenic. Based on Box-Wilson central composite design, polynomial models were developed to correlate the process variables to the two responses. From the analysis of variance the significant variables on each response were identified. Optimum conditions of 4 min radiation time, 700 W radiation power and 0.5 g/g impregnation ratio
... Show MorePID (proportional-integral-derivative) and Mu controllers are widely used in electro-hydraulic servo systems due to their effectiveness and ease of implementation. This paper explores using particle swarm optimization (PSO) for tuning traditional and robust PID controllers, along with D-K iteration for Mu controller tuning. Three controller types: conventional PID (CPID), robust PID (RPID), and structured singular value controllers are developed, while analyzing multiplicative uncertainty with six uncertain coefficients. Their findings indicated that both PID (CPID and RPID) and Mu controllers maintained system stability. Notably, the Mu controller can handle coefficient uncertainty without a pure integral term, while the RPID controller de
... Show MoreCognitive radios have the potential to greatly improve spectral efficiency in wireless networks. Cognitive radios are considered lower priority or secondary users of spectrum allocated to a primary user. Their fundamental requirement is to avoid interference to potential primary users in their vicinity. Spectrum sensing has been identified as a key enabling functionality to ensure that cognitive radios would not interfere with primary users, by reliably detecting primary user signals. In addition, reliable sensing creates spectrum opportunities for capacity increase of cognitive networks. One of the key challenges in spectrum sensing is the robust detection of primary signals in highly negative signal-to-noise regimes (SNR).In this paper ,
... Show More