Data-driven multi-objective optimization with neural network-based sensitivity analysis for semiconductor devices

The factor evaluation for sustainability implementation in post-disaster reconstruction projects was conducted using artificial neural network (ANN)-based sensitivity analysis. The current study involves the utilization of Levenberg-Marquardt algorithm (LMA) for the ANN model development. The findings demonstrated that the governing network structure is 10-3-1 utilizing input parameters (IP) including waste management (Sl), environmental impact management (S2), support of management (S3), construction cost (S4), public health and safety (S5), user security (S6), noise pollution (S7), energy consumption (S8), public services (S9), and recycling (S10). The results revealed that the governing model (GM) has a performance of correlation (R) = 0.99813 and Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) of 0.00110 and 0.4240/0, respectively. Moreover, a sensitivity analysis (SA) using Garson's algorithm (GA) reveals a trend of the relative value (RV) was observed to be construction cost > public services > support of management > user security > environmental impact management> noise pollution> public health and safety> energy consumption > recycling > waste management wherein the construction cost is the most influential parameter to the sustainability rating in post-disaster reconstruction projects (PDRP). The study shows how well ANN can detect the crucial elements that determine a project's sustainability rating in the post-disaster reconstruction projects.

Dengue Fever is among the world’s fastest-spreading mosquito-borne illnesses. In Indonesia, more than 33 percent of the world community is in danger. The Coastal Zone is one of the region most at risk of contracting dengue fever, particularly from the social and environmental sectors, so an early diagnostic study must deal with this efficiently and effectively. This research aimed to predict and identify the coastal areas with the most severe dengue fever potential to avoid dengue fever. The methodology used is a neural network-based sensitivity Analysis and multiple linear regression. Bagan Deli, Sibolga, Tapanuli Tengah, Langkat, Medan are samples of the coastal regions used in this study. The reports used was secondary data for dengue fever patients suffering and meteorological parameters, the model used in [5-5-1] for prediction, for five years from 2014-2019. The results showed which Langkat (0.4936), Serdang Bedagai (0.4695), The Middle Of Tapanuli (0.4399), Medan (0.4313), and Sibolga (0.3133) are perhaps the most prevalent areas affected by dengue fever with a value of 89.8 percent. The Result is temperature and humidity are the conditions that most affect the transmission of dengue fever.

Thermal load prediction is a key part of energy system management and control in buildings, and its accuracy plays a critical role to improve building energy performance and efficiency. Regarding thermal load prediction, various types of prediction model have been considered and studied, such as physics-based, statistical, and machine learning models. Physical models can be accurate but require extended lead time for model development. Statistical models are relatively simple to develop and require less computation time, but they may not provide accurate results for complex energy systems with intricate nonlinear dynamic behaviors. This study proposes an artificial neural network (ANN) model, one of the prevalent machine learning methods to predict building thermal load, combining with the concept of nonlinear autoregressive with exogenous inputs (NARX). NARX-ANN prediction model is distinguished from typical ANN models because the NARX concept can address nonlinear system behaviors effectively based on its recurrent architectures and time indexing features. To examine the suitability and validity of NARX-ANN model for building thermal load prediction, a case study is carried out using the field data of an academic campus building at Mississippi State University (MSU). Results show that the proposed NARX-ANN model can provide an accurate and robust prediction performance and effectively address nonlinear system behaviors in the prediction.

Non-destructive evaluation of reinforced concrete structures is essential for effective maintenance and safety assessments. This study explores the combined use of active microwave thermography and deep learning to detect and localize steel reinforcement within concrete elements. Numerical simulations were developed to model the thermal response of reinforced concrete subjected to microwave excitation, generating synthetic thermal images representing the surface temperature patterns of reinforced concrete, influenced by subsurface steel reinforcement. These images served as training data for a deep neural network designed to identify and localize rebar positions based on thermal patterns. The model was trained exclusively on simulation data and subsequently validated using experimental measurements obtained from large-format concrete slabs incorporating a structured layout of embedded steel reinforcement bars. Surface temperature distributions obtained through infrared imaging were compared with model predictions to evaluate detection accuracy. The results demonstrate that the proposed method can successfully identify the presence and approximate location of internal reinforcement without damaging the concrete surface. This approach introduces a new pathway for contactless, automated inspection using a combination of physical modeling and data-driven analysis. While the current work focuses on rebar detection and localization, the methodology lays the foundation for broader applications in non-destructive testing of concrete infrastructure.

The analytical modeling of nanoscale devices is an important area of computer-aided design for fast and accurate nanoelectronic design and optimization. In the present paper, a new approach for modeling semiconductor devices, nanoscale double gate DG MOSFETs, by use of the gradual channel approximation (GC) approach and genetic algorithm optimization technique (GA) is presented. The proposed approach combines the universal optimization and fitting capability of GA and the cost-effective optimization concept of quantum correction, to achieve reliable, accurate and simple compact models for nanoelectronic circuit simulations. Our compact models give good predictions of the quantum capacitance, threshold voltage shift, quantum inversion charge density and drain current. These models have been verified with 2D self-consistent results from numerical calculations of the coupled Poisson-Schrödinger equations. The developed models can also be incorporated into nanoelectronic circuit simulators to study the nanoscale CMOS-based devices without impact on the computational time and data storage.

The growing use of artificial intelligence (AI) in physical education (PE) has led to an urgent need to develop robust methodologies that can be used to choose the most suitable algorithms in uncertain and vague environments. This paper introduces a new hybrid decision-making (DM) model that incorporates the weighted aggregated sum product assessment (WASPAS) technique into the q-rung linear Diophantine fuzzy set (q-RLDFS) framework. The primary objective is to address the gap in the lack of structured and uncertainty-resistant methods for assessing AI models based on multiple, frequently conflicting criteria in the domain of PE. The proposed model presents a two-layer framework, where the WASPAS method enables a flexible scoring system by combining both the weighted sum model (WSM) and the weighted product model (WPM). On the other hand, the q-RLDFS framework facilitates high-order fuzzy modelling and accounts for hesitation in expert ratings, thereby making the decision results more interpretable and robust. To determine the effectiveness of the model, five AI algorithms named convolutional neural network-based motion analysis (CNN-MA), reinforcement learning based training optimizer (RL-TO), expert system for exercise prescription (ES-EP), hybrid AI tutor with natural language processing (HAI-NLP), and wearable sensor data mining algorithm (WSDMA) are evaluated against eight key criteria relevant to PE. Results revealed that CNN-MA is the most effective solution to implement, followed by RL-TO. The sensitivity and comparative analysis are thoroughly conducted to determine the validity of the model in terms of its robustness and reliability. The research offers distinct practical implications and actionable recommendations to educators, administrators, and policymakers, informing the strategic implementation of AI technologies within the PE domain. In general, the research makes a significant contribution to the adoption of AI in PE, as it provides a scalable, transparent, and practically applicable decision-support model.

Log analysis plays a crucial role in understanding system behavior and detecting anomalies in various domains. This article presents the results of our autoencoder type neural network trained for log analysis and anomaly detection based on the reconstruction error of each entry. Furthermore, the article focuses on the challenge of text vectorization, specifically employing a bag-of-words method for representing log messages in a numerical format suitable for neural network models. The bag-of-words approach captures the frequency-based representation of log messages. The study also acknowledges the limitations of this method in capturing semantic information. It is important to note that this study represents only a starting point in the journey of log analysis and text vectorization. The field encompasses a wide range of existing working methods, and further research and exploration are necessary to uncover the full potential of log analysis techniques for various applications.

Air pollution is one of the most common concerns for human health. Air contamination has many pollutants like NO2, PM2.5, PM10, and other harmful gases, which are harmful to the living system on the earth. The quality of air gets affected by these particulate matters. This paper proposes a neural network-based prediction model for detection and prediction of air pollution. Performance measurement of Bayesian Regularization (BR) algorithm, Levenberg–Marquardt (LM) algorithm, and Scaled Conjugate Gradient (SCG) algorithm has been analyzed.

Global or continental-scale land cover mapping with remote sensing data is limited by the spatial characteristics of satellites. Subpixel-level mapping is essential for the successful description of many land cover patterns with spatial resolution of less than /spl sim/1 km and also useful for finer resolution data. This paper presents a novel adaptive resonance theory MAP (ARTMAP) neural network-based mixture analysis model-ART mixture MAP (ART-MMAP). Compared to the ARTMAP model, ART-MMAP has an enhanced interpolation function that decreases the effect of category proliferation in ART/sub a/ and overcomes the limitation of class category in ART/sub b/. Results from experiments demonstrate the superiority of ART-MMAP in terms of estimating the fraction of land cover within a single pixel.

In this paper, the proxy model of the functional function is constructed by using the BP neural network fitting method, and the inertia weight index of the traditional particle swarm algorithm is improved, and the slope safety factor solution method of the improved particle swarm algorithm combined with the BP neural network is formed, which is verified and solved through practical engineering cases, and the method of fitting the response surface of the functional function using the BP neural network is proposed. In this study, the LSTM deep learning network model is introduced, combined with the chaotic characteristic analysis of slope deformation. An effective slope deformation prediction method was successfully constructed. This method not only has high prediction accuracy and generalization ability, but also has important practical value and application prospects. In the future, we will continue to study the application of LSTM model in slope deformation prediction, in order to further improve the prediction accuracy and practicability. It can effectively solve the problem that the functional function cannot be explicitly expressed when solving the reliability of complex structures.

Ash content is a critical coal quality indicator that determines coal grade and commercial applications, making its rapid and accurate measurement essential. Traditional slow ashing methods are operationally cumbersome, time-consuming, and pose environmental and safety concerns. Hyperspectral imaging technology offers a promising alternative with its non-contact detection and superior spatial-spectral information fusion capabilities. However, existing machine learning and deep learning approaches, while capable of modeling complex spectral-analyte relationships, often overlook spatial information and struggle to effectively capture the heterogeneous distribution characteristics of ash minerals in coal samples. Therefore, this study proposes a fast estimation method of hyperspectral coal ash based on graph neural network, using a hybrid GCN-GAT encoder and an adaptive spatial-spectral edge construction strategy. This method models the mineral distribution pattern by constructing a spatial graph, constructs a spectrogram to capture the mineral spectral characteristics, and optimizes it for different ash content ranges. In the experiments of concentrated coal (ash range from 9% to 18%) and tailings coal samples (ash range from 49% to 77 %), the average absolute errors of this method are 0.862 % and 1.18 %, respectively, which are significantly better than traditional machine learning methods and deep learning methods. The interpretability analysis shows that the absorption characteristics of hydroxyl-containing minerals corresponding to the 1200-1400 nm band contribute the most to the ash estimation, which verifies the effectiveness of the graph neural network in coal quality analysis and provides practical guidance for coal automatic characterization and industrial quality control.

Lung cancer continues to be a leading contributor to global cancer mortality, highlighting the need for rapid and reliable diagnostic techniques to enhance patient survival rates. Non-Small Cell Lung Cancer (NSCLC), the most prevalent subtype, requires advanced computational methods to support accurate classification and clinical interpretation. Despite remarkable progress in neural network-based imaging analysis, the opacity of these models often limits their clinical acceptance. This work introduces an explainable neural network framework designed to categorize NSCLC subtypes while ensuring interpretability in its decision process. The model integrates knowledge transfer from pre-trained DenseNet, ResNet50, and VGG16 architectures to distinguish among adenocarcinoma, squamous cell carcinoma, large cell carcinoma, and normal tissue in histopathological scans. To promote transparency, the GradCAM technique is incorporated to generate color-weighted overlays that reveal the image regions most influential in each classification. Experimental findings demonstrate that DenseNet achieved an overall accuracy of 93% with balanced precision, recall, and F1-scores across all subtypes. The interpretive heatmaps confirmed that the model's focus corresponded with pathologically relevant regions, improving both trust and diagnostic utility. The proposed approach highlights the potential of explainable neural networks as dependable tools for computer-assisted lung cancer diagnosis.

The efficacy of a novel fuzzy neural network classifier for the characterization of ultrasonic liver images based on texture analysis techniques is investigated. Classification features are extracted with the use of image texture analysis techniques such as fractal dimension texture analysis, spatial gray-level dependence matrices, gray-level difference statistics, gray-level run-length statistics, and first-order gray-level parameters. These features are fed to a neural network classifier based on geometrical fuzzy sets. Starting from the construction of the Voronoi diagram of the training patterns, an aggregation of Voronoi regions is performed, leading to the identification of larger regions belonging exclusively to one of the pattern classes. The resulting scheme is a constructive algorithm that defines fuzzy clusters of patterns. Based on observations concerning the grade of membership of the training patterns to the created regions, decision probabilities are computed through which the final classification is performed.

A simplified example of building a neural network using TensorFlow is presented in this article.A single-layer neural network, trained with a small dataset of seven data points and optimized with Stochastic Gradient Descent and a mean squared error loss function, is defined for predicting house prices based on the number of rooms.A prediction for a new value is then made with the trained model.This example serves as a demonstration of the potential for neural networks, in combination with TensorFlow, to bring about increased efficiency, productivity, and improved decision making in business and the economy through automation of tasks and processes.This article demonstrates how the use of neural networks can bring increased efficiency and productivity in business operations through the automation of data processing tasks.The implications and possibilities of using neural networks are also analyzed.This paper will serve as a resource for researchers and practitioners interested in using TensorFlow and neural networks for machine learning and data processing.By automating data analysis and prediction, businesses can make more informed decisions and respond more quickly to market changes, resulting in improved financial performance.

Diabetic Retinopathy (DR) is a leading cause of vision im-pairment and blindness among diabetic patients worldwide.Early detec-tion and timely intervention are crucial to preventing severe visual loss.Convolutional Neural Networks (CNNs) have emerged as a powerful tool for image analysis and have shown great potential in medical image di-agnostics.This study explores the application of CNNs for the early diagnosis of DR using retinal fundus images.By leveraging deep learn-ing techniques, our CNN model is trained to automatically detect and classify various stages of DR with high accuracy.The proposed method utilizes a large dataset of annotated retinal images to ensure robustness and generalizability.Experimental results demonstrate that the CNN-based approach significantly outperforms traditional methods, offering a reliable and efficient solution for early DR detection.This advancement in automated image analysis can facilitate timely and precise diagnosis, potentially reducing the burden of diabetic complications and improving patient outcomes.