Search

The mandibular condyle is a rounded bony projection with an upper biconvex, oval surface in the axial plane. Its form differs significantly among different individuals and age groups. This study aims to address the variability in mandibular condyle morphology, which can be indicative of Temporomandibular Joint disorders (TMD). Given the clinical importance of accurate condyle characterization, we developed a novel detection method leveraging deep learning and feature selection technologies. This method explicitly employs the YOLOv8 network to initially identify the region of interest (ROI) in digital panoramic images. Subsequently, the MobileViT system extracts detailed features from these regions. We introduced a modified Mountaineering Team-Based Optimization Algorithm to refine the feature selection process, which efficiently isolates the most relevant features from the extracted set. Our experimental design involved a robust dataset of 3000 digital panoramic images, classified into four distinct morphological types: round, pointed, angled, and flat. We assessed the performance of our developed method through various metrics, focusing on its ability to detect and describe the morphology of the condyle. The results demonstrate a high capability of the model, achieving an accuracy of 81.5% in binary classification and 83.5% in multi-classification scenarios.

The integration of metaheuristics with machine learning methodologies presents significant advantages, particularly in optimization and computational intelligence. This amalgamation leverages the global search capabilities of metaheuristics alongside the pattern recognition and predictive prowess of machine learning, facilitating enhanced convergence rates and solution quality in complex problem spaces. The Quantum Long Short-Term Memory (QLSTM) emerges as a highly efficient deep learning model tailored to tackle such intricate engineering problems. The QLSTM's architecture, comprising data encoding, variational, and quantum measurement layers, facilitates the effective encoding and processing of civil engineering data, leading to heightened prediction accuracy. However, the task of determining optimal values for QLSTM parameters presents challenges due to its NP-problem nature and time-consuming characteristics. To address this, we propose an alternative technique to optimize the QLSTM based on a modified Electric Eel Foraging Optimization (MEEFO). The MEEFO is a modified version of the original EEFO that applies triangular mutation operators to boost the search capability of the traditional EEFO. Thus, the MEEFO optimizes the QLSTM and boosts its prediction performance. To validate the efficacy of our proposed method, we conduct comprehensive experiments utilizing five real-world engineering datasets related to construction and structure engineering. The evaluation outcomes unequivocally demonstrate that the MMEFO significantly enhances the performance of the QLSTM.

Aerial photography is a remote sensing technique used for target detection, enabling both qualitative and quantitative analysis. The segmentation process is considered one of the most important processes to improve the analysis of Aerial images. In this study, we introduce an alternative multilevel threshold image segmentation based on a modified Snow ablation optimizer (SAO) algorithm. This modification is conducted using the strengths of Comprehensive learning and Double attractors which aims to enhance the exploration and exploitation abilities of the SAO during the process of discovering the optimal threshold levels that are used to segment the Aerial photography image. To validate the quality of the modified version of SAO, named DCSAO, a set of experimental series is conducted using the CEC2022 benchmark function and sixteen Aerial images at different threshold levels. In addition, we compared the results of DCSAO with different well-known Metaheuristic techniques. The results show the superior performance of DCSAO in comparison to other algorithms according to the performance metrics.

In the rapidly evolving realm of remote sensing technology, the classification of Hyperspectral Images (HSIs) is a pivotal yet formidable task. Hindered by inherent limitations in hyperspectral imaging, enhancing the accuracy and efficiency of HSI classification remains a critical and much-debated issue. This review study focuses on a key application area in HSI classification: Land Use/Land Cover (LULC). Our study unfolds in fourfold approaches. First, we present a systematic review of LULC hyperspectral image classification, delving into its background and key challenges. Second, we compile and analyze a number of datasets specific to LULC hyperspectral classification, offering a valuable resource. Third, we explore traditional machine learning models and cutting-edge methods in this field, with a particular focus on deep learning, and spectral decomposition techniques. Finally, we comprehensively analyze future developmental trajectories in HSI classification, pinpointing potential research challenges. This review aspires to be a cornerstone resource, enlightening researchers about the current landscape and future prospects of hyperspectral image classification.

Applications for the internet of things (IoT) have grown significantly in popularity in recent years, and this has caused a huge increase in the use of cloud services (CSs). In addition, cloud computing (CC) efficiently processes and stores generated application data, which is evident in the lengthened response times of sensitive applications. Moreover, CC bandwidth limitations and power consumption are still unresolved issues. In order to balance CC, fog computing (FC) has been developed. FC broadens its offering of CSs to target end users and edge devices. Due to its low processing capability, FC only handles light activities; jobs that require more time will be done via CC. This study presents an alternative task scheduling in an IoT environment based on improving the performance of the golden jackal optimization (GJO) using the artificial hummingbird algorithm (AHA). To test the effectiveness of the developed task scheduling technique named golden jackal artificial hummingbird (GJAH), we conducted a large number of experiments on two separate datasets with varying data sizing. The GJAH algorithm provides better performance than those competitive task scheduling methods. In particular, GJAH can schedule and carry out activities more effectively than other algorithms to reduce the makespan time and energy consumption in a cloud-fog computing environment.

The vision transformer (ViT) has demonstrated performance comparable to that of convolutional neural networks (CNN) in the hyperspectral image classification domain. This is achieved by transforming images into sequence data and mining global spectral-spatial information to establish remote dependencies. Nevertheless, both the ViT and CNNs have their own limitations. For instance, a CNN is constrained by the extent of its receptive field, which prevents it from fully exploiting global spatial-spectral features. Conversely, the ViT is prone to excessive distraction during the feature extraction process. To be able to overcome the problem of insufficient feature information extraction caused using by a single paradigm, this paper proposes an MLP-mixer and a graph convolutional enhanced transformer (MGCET), whose network consists of a spatial-spectral extraction block (SSEB), an MLP-mixer, and a graph convolutional enhanced transformer (GCET). First, spatial-spectral features are extracted using SSEB, and then local spatial-spectral features are fused with global spatial-spectral features by the MLP-mixer. Finally, graph convolution is embedded in multi-head self-attention (MHSA) to mine spatial relationships and similarity between pixels, which further improves the modeling capability of the model. Correlation experiments were conducted on four different HSI datasets. The MGEET algorithm achieved overall accuracies (OAs) of 95.45%, 97.57%, 98.05%, and 98.52% on these datasets.

The best way to achieve sustainable construction is to choose materials with a smaller environmental impact. In this regard, specialists and architects are advised to take these factors into account from the very beginning of the design process. This study offers a framework for selecting the optimal sustainable building material. The core goal of this article is to depict a novel structure of a neutrosophic soft expert set hybrid called an interval-valued neutrosophic soft expert set for utilization in construction supply chain management to select a suitable supplier for a construction project. This study applies two different techniques. One is an algorithmic technique, and the other is set-theoretic. The first one is applied for the structural characterization of an interval-valued neutrosophic expert set with its necessary operators like union and OR operations. The second one is applied for the construction of a decision-making system with the help of pre-described operators. The main purpose of the algorithm is to be used in supply chain management to select a suitable supplier for construction. This paper proposes a new model based on interval-valued, soft expert and neutrosophic settings. In addition to considering these settings jointly, this model is more flexible and reliable than existing ones because it overcomes the obstacles of existing studies on neutrosophic soft set-like models by considering interval-valued conditions, soft expert settings and neutrosophic settings. In addition, an example is presented to demonstrate how the decision support system would be implemented in practice. In the end, analysis, along with benefits, comparisons among existing studies and flexibility, show the efficacy of the proposed structure.

Wind power can be considered one of the most important green sources of electric power. The prediction of wind power is necessary to boost the power grid operations’ efficiency and increase power market competitiveness. Artificial neural networks (ANNs) are widely used in prediction applications, including wind power. The Random Vector Functional Link (RVFL) is an efficient ANN model that can be employed in time-series forecasting applications. However, the configuration process of the RVFL needs to be improved. Thus, in this paper, we presented an optimized RVFL network using a new naturally inspired technique called the Capuchin search algorithm (CapSA). The main function of the CapSA is to boost the configuration of the traditional RVFL and enhance its prediction capability. We implement extensive evaluation experiments using public datasets from four wind turbines located in France, using several evaluation measures called RMSE, MAE, MAPE, and R2. The evaluation outcomes reveal that the CapSA-RVFL obtained the best prediction accuracy compared to the original RVFL and several variants of the RVFL model, which verifies that the application of CapSA has a significant contribution to improving the prediction capability of the RVFL.

Due to the lack of analytical solutions for the wear rates prediction of nanocomposites, we present a modified machine learning method named Dendritic Neural (DN) to predict the wear performance of copper-alumina (Cu-Al2O3) nanocomposites that have large applicability in electronics. This modification aims at determining the optimal weights of DN since they have largest influence on its performance. To achieve this improvement a new meta-heuristic technique named Artificial Hummingbird Algorithm (AHA) was used. The modified model was applied to predict the wear rates and coefficient of friction of Cu-Al2O3 nanocomposites that was developed in this study. Electroless coating of Al2O3 nanoparticles with silver (Ag) was performed to improve the wettability followed by ball milling and compaction to consolidate the composites. The microstructural, mechanical and wear properties of the produced composites with different Al2O3 content were characterized. The wear rates and coefficient of friction were evaluated using sliding wear test at different load and speeds. The developed model using AHA algorithm showed excellent predictability of the wear rate and coefficient of friction for Cu-Al2O3 nanocomposites with reinforcement content up to 10%.

The Social Internet of Things (SIoT) has revolutionized user experience through various applications and networking services like Social Health Monitoring, Social Assistance, Emergency Alert Systems, and Collaborative Learning Platforms. However, transferring different types of data between the interconnected objects in the SIoT environment, including sensor data, user-generated data, and social interaction data, poses challenges due to their high dimensionality. This paper presents an alternative SIoT method that improves resource efficiency, system performance, and decision-making using the Barnacles Mating Optimizer (BMO). The BMO incorporates Triangular mutation and dynamic Opposition-based learning to enhance search space exploration and prevent getting stuck in local optima. Two experiments were conducted using UCI datasets from different applications and SIoT-related datasets. The results demonstrate that the developed method, DBMT, outperforms other algorithms in predicting social-related datasets in the IoT environment.

Abstract InSAR-based deformation analysis and the geomorphic hypsometric integral (HI) technique are powerful tools for assessing the susceptibility and comparison of seismic sites to earthquakes. Therefore, this paper mainly focuses on surface deformation analysis associated with the Mw 5.0 earthquake (2019) in Mach and Quetta, Balochistan, Pakistan. Sentinel-1 IW data was used to perform PS-InSAR time series analysis. SRTM DEM of 30 m spatial resolution was utilized for the geomorphic Hypsometry Integral (HI) method. The obtained results of the Interferogram indicate the changes in velocity and vertical displacement during pre-seismic, co-seismic, and post-seismic activity. Integral values were calculated using Hypsometry curves delineating the future probability and comparison of vulnerable seismological sites in Mach, Quetta, Ghazaband, Chamman and surroundings of Balochistan region. The combined results of HI and PS-InSAR revealed that Mach and Quetta regions are in between two lines known as the mature stages. Class 1_moderate (0.35 ≤ HI ≤ 0.52); with an integral value of HIMach = 0.398 and HIQuetta = 0.435 with a modest seismic forthcoming rate in future and susceptible to both erosion/uplifting with a vertical displacement rate more than existing ± 55 mm/year. Class 2_high (HI ˃ 0.53) with the younger and more tectonically active region surrounded by Chaman fault, which possesses a future susceptible tendency towards subsidence more than an existing velocity rate ~ 8 mm/year and Ghazaband fault towards uplifting more than 5–6 mm/year. No region of the study area was found at Monadnock: class 3_Low (HI ˂ 0.35) stabilized condition, all sites are unstable and tectonically active. Therefore, obtained results through combined PS-InSAR and HI techniques can be used for the identification of most vulnerable seismic sites and can ascertain future safe metropolitan planning.

ABSTRACTOil production estimation plays a critical role in economic plans for local governments and organizations. Therefore, many studies applied different Artificial Intelligence (AI) based methods to estimate oil production in different countries. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is a well-known model that has been successfully employed in various applications, including time-series forecasting. However, the ANFIS model faces critical shortcomings in its parameters during the configuration process. From this point, this paper works to solve the drawbacks of the ANFIS by optimizing ANFIS parameters using a modified Aquila Optimizer (AO) with the Opposition-Based Learning (OBL) technique. The main idea of the developed model, AOOBL-ANFIS, is to enhance the search process of the AO and use the AOOBL to boost the performance of the ANFIS. The proposed model is evaluated using real-world oil production datasets collected from different oilfields using several performance metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2), Standard Deviation (Std), and computational time. Moreover, the AOOBL-ANFIS model is compared to several modified ANFIS models include Particle Swarm Optimization (PSO)-ANFIS, Grey Wolf Optimizer (GWO)-ANFIS, Sine Cosine Algorithm (SCA)-ANFIS, Slime Mold Algorithm (SMA)-ANFIS, and Genetic Algorithm (GA)-ANFIS, respectively. Additionally, it is compared to well-known time series forecasting methods, namely, Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Seasonal Autoregressive Integrated Moving Average (SARIMA), and Neural Network (NN). The outcomes verified the high performance of the AOOBL-ANFIS, which outperformed the classic ANFIS model and the compared models.