Damage quantification in truss structures by limited sensor-based surrogate model

A comparative study of learning techniques for the compressible aerodynamics over a transonic RAE2822 airfoil

This paper is intended to explore the research done on identifying the diseased plants and crops using Machine Learning (ML) and Deep Learning (DL) techniques during last 10 years using bibliometric methods. In this study, we used Scopus database to analyze on “Plant disease” or “Crop disease” using “Machine Learning” or “Deep Learning” or “Neural Networks”. This paper focuses on the importance of ML and DL techniques in identifying plant or crop diseases. The database collected from the Scopus is analyzed using VOSviewer software of version 1.6.16. The study is limited to publications from conferences, journals with subject areas are limited to Computer Science, Engineering and languages limited to English and Chinese. Scopus search outputs 824 articles on Plant or Crop diseases with ML, DL and Neural Networks covering conference papers and journal articles. Statistics showed that more articles were published during the last five years and major contributions were from India. By analyzing database on Authors, Subject area, Keywords, Affiliation, Source type it is evident that there is plenty of research scope in this area. Network analysis on diverse parameters specifies that there is a good scope to do research in this topic using advanced deep learning techniques.

The increasing volume of vehicle traffic and climate change significantly impact the performance of road infrastructure, necessitating comprehensive analyses throughout the road lifecycle to ensure its resilience. While traditional visual inspections remain prevalent for road assessment, they are hampered by high costs and subjective biases. Additionally, concrete pavement presents specific evaluation challenges due to its high stiffness and susceptibility to cracking, spalling, and faulting, requiring precise detection techniques. In response to these challenges, deep data-based systems emerge as a promising solution. This research introduces a novel system for detecting, locating, and quantifying damages in concrete pavement by combining convolutional neural networks with classical computer vision techniques. The system studies various CNNs and ultimately selects UNet ResNext-101 for its superior performance. Additionally, the system applies perspective transformations, Hough Transform, and thresholding techniques to enhance feature extraction and improve damage quantification precision. This combination mitigates the high data requirements typically associated with neural networks alone. By limiting the inspection area to specific slabs, the system improves efficiency. It is trained and tested using high-resolution images from the LanammeUCR. This innovative approach could significantly transform the maintenance and monitoring processes of road infrastructure, leading to safer and more reliable transportation networks. • Automated damage inspection reduces time and costs: The proposed system automates the inspection process, significantly reducing the time required for analysis. This enables decision-makers to address pavement issues more promptly, preventing damage from worsening and thereby reducing maintenance costs. • Comprehensive system tailored to concrete pavement inspection standards: The system identifies and segments individual concrete slabs, aligning with established road inspection norms that use slabs as the primary evaluation unit. Damage quantification is then conducted at the slab level, ensuring a methodical and standardized approach. • Efficiency through advanced deep learning techniques: The system leverages state-of-the-art computer vision and deep neural networks to enhance data processing efficiency. By targeting relevant regions of interest, the approach minimizes computational overhead and maximizes the utility of training datasets. • Highly adaptable to diverse conditions: The system's models can be fine-tuned to accommodate varying camera angles, concrete pavement types, and road conditions, making it versatile and scalable for different contexts and regions. • Open data for reproducibility: The training datasets used in this research are publicly shared alongside the manuscript, promoting transparency, reproducibility, and further innovation in the field.

Need for developing efficient non-destructive damage detection procedures for civil engineering structures is growing rapidly. This paper presents a methodology for detection and quantification of structural damage using modal information obtained from transfer matrix technique. Vibration characteristics of beam-like structure have been determined using the computer program developed based on the formulations presented in the paper. It has been noted from reported literature that detection and quantification of damage using mode shape information is difficult and further, extraction of mode shape information has practical difficulties and limitations. Hence, a methodology for detection and quantification of damage in structure using tranfer matrix technique based on the changes in the natural frequencies has been developed. With an assumption of damage at a particular segment of the beam-like structure, an iterative procedure has been formulated to converge the calculated and measured frequencies by adjusting flexural rigidity of elements and then, the intersections are used for detection and quantification of damage. Eventhough the developed methodology is iterative, computational effort is reduced considerably by using transfer matrix technique. It is observed that the methodology is capable of predicting the location and magnitude of damage quite accurately.

PurposeOne of the paramount challenges in the field of structural health monitoring (SHM) is the precise assessment of structural damage. Recently, many methods have been proposed to diagnose damage in structures using time series data. Nevertheless, these techniques are restricted in their ability to capture the bidirectional temporal and spatial relationships among the data. To remedy these shortcomings, this study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN.Design/methodology/approachThis study proposes an advanced deep learning (DL) technique that integrates one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks, termed BiLSTM-1DCNN. The novelty of BiLSTM-1DCNN comes in its effective fusion of 1DCNN’s local feature extraction and BiLSTM’s capacity to capture long-term information from both directions (forward and backward).FindingsValidation using a dataset from the Nam O steel truss bridge demonstrates that the proposed method surpasses conventional models, including 1DCNN (87.9%), LSTM (72.5%), BiLSTM (76.1%) and LSTM-1DCNN (91.1%), achieving an accuracy rate of 96.4%. This approach provides a significant advancement in SHM, paving the way for more accurate and reliable damage detection.Research limitations/implicationsThe study’s limitations include potential overfitting due to the model’s complexity and the high computational resources required. The BiLSTM-1DCNN model’s performance is also influenced by the quality and quantity of the training data as well as the specific characteristics of the dataset. Additionally, while the model performs well in detecting damage in the Nam O steel truss bridge, its generalizability to other types of structures and environmental conditions remains untested.Practical implicationsThe BiLSTM-1DCNN model offers significant practical benefits for structural health monitoring by enhancing damage detection accuracy. Its ability to effectively capture both local features and long-term temporal dependencies makes it a valuable tool for real-time monitoring and early detection of structural issues. This can lead to more timely maintenance actions, potentially reducing repair costs and improving safety. The model’s high accuracy in detecting damage can also support infrastructure management decisions, contributing to better resource allocation and enhanced overall safety of critical structures.Social implicationsThe BiLSTM-1DCNN model’s advanced damage detection capabilities have positive social implications, such as improving the safety and reliability of public infrastructure like bridges. Enhanced structural health monitoring can reduce the risk of catastrophic failures, protecting lives and reducing accidents. By providing more accurate and timely assessments, the model can also lead to more efficient use of maintenance and repairs, ensuring that resources are allocated effectively.Originality/valueThe originality of the BiLSTM-1DCNN model lies in its innovative integration of one-dimensional convolutional neural networks (1DCNN) with bidirectional long short-term memory (BiLSTM) networks. This unique combination leverages 1DCNN’s strength in local feature extraction and BiLSTM’s capacity to capture temporal dependencies in both directions, addressing the limitations of existing methods. The model’s high accuracy in detecting structural damage, as demonstrated by its performance on the Nam O steel truss bridge dataset, highlights its value in advancing structural health monitoring technologies and offers a significant improvement over traditional approaches.

ABSTRACTIn recent years, there has been a significant surge in the utilisation of deep learning and machine learning techniques for addressing complex and time‐intensive problems. The significance of employing deep learning becomes increasingly evident as the complexity of the problem increases. In the field of electromagnetics, the utilisation of deep learning techniques has exhibited exceptional efficacy across many applications, especially in wireless communications. In wireless communications, providing a structure that can simultaneously generate multiple beams and beamform them involves complexity and specific constraints. In this article, the time modulation technique is utilised to generate harmonics in the sidebands alongside the fundamental beam in various planar antenna arrays. By demonstrating the nonlinear shaping of the harmonic beams relative to each other, a novel approach is proposed that leverages deep learning techniques for the beamforming of both the fundamental beam and harmonic beams. In this regard, two models are proposed: a deep neural network (DNN) and a convolutional neural network (CNN). The input of CNN is comprised of two‐dimensional patterns of the main beam and harmonics. The input to DNN, on the other hand, includes useful details about the main beam and harmonics, such as their scanning angles, side lobe levels and directivities. The output of the models consists of the time modulation parameters of the array elements, including the pulse width and the pulse delay. The results demonstrate that DNN has achieved better accuracy and a shorter processing time in comprehending the relationship between the time modulation of array elements with different array dimensions and the radiation pattern of the fundamental beam and harmonic beams. Additionally, several samples are presented to evaluate the proposed model. The results demonstrate a high level of accuracy in fundamental beamforming, as well as in harmonic beamforming and beam steering.

A systematic review of deep learning techniques for rice disease recognition: Current trends and future directions

Nowadays, multiple sources of information about proteins are available such as protein sequences, 3D structures, Gene Ontology (GO), etc. Most of the works on protein-protein interaction (PPI) identification had utilized these information about proteins, mainly sequence-based, but individually. The new advances in deep learning techniques allow us to leverage multiple sources/modalities of proteins, which complement each other. Some recent works have shown that multi-modal PPI models perform better than uni-modal approaches. This paper aims to investigate whether the performance of multi-modal PPI models is always consistent or depends on other factors such as dataset distribution, algorithms used to learn features, etc. We have used three modalities for this study: Protein sequence, 3D structure, and GO. Various techniques, including deep learning algorithms, are employed to extract features from multiple sources of proteins. These feature vectors from different modalities are then integrated in several combinations (bi-modal and tri-modal) to predict PPI. To conduct this study, we have used Human and S. cerevisiae PPI datasets. The obtained results demonstrate the potentiality of a multi-modal approach and deep learning techniques in predicting protein interactions. However, the predictive capability of a model for PPI depends on feature extraction methods as well. Also, increasing the modality does not always ensure performance improvement. In this study, the PPI model integrating two modalities outperforms the designed uni-modal and tri-modal PPI models.

Brain tumor disease is a serious and complex health problem worldwide. Early and accurate detection of brain tumors has a major impact on patient care and prognosis. Magnetic Resonance Imaging (MRI) has become one of the main diagnostic tools in detecting brain tumors, manual interpretation of MRI images requires high clinical expertise and requires a long time. In recent years, advances in deep learning techniques and image processing have opened up new opportunities in the detection of brain tumors via MRI images. Deep learning techniques, especially the use of Vision Transformers (ViTs) models, have been successful in various complex pattern recognition tasks in images. The Vision Transformers model was chosen due to the performance improvements shown in many image recognition tasks, outperforming convolutional neural networks (CNN) based methods. Tensorflow and Keras are used as frameworks for development and training models, which have been proven effective and efficient in various previous studies. This study focuses on the performance of the Vision Transformer (ViT) in detecting brain tumors through two Magnetic Resonance Imaging (MRI) image datasets, with different numbers of datasets, as well as the maximum accuracy value that can be achieved from the ViT architecture. From several experimental parameters on ViT, the number of datasets and iterations, the results obtained from the first dataset with 253 image data obtained an accuracy value of 88%, and in the second study by combining the two datasets, with 3.123 data images obtained an accuracy of 97.9%.

Two-stage structural damage detection using fuzzy neural networks and data fusion techniques

Recently, deep neural networks (DNNs) have been widely studied and achieved tremendous success in a variety of real-world applications, such as computer vision, natural language processing, medical diagnosis, and machine translation. Deep reinforcement learning (DRL), as an emerging powerful deep learning technique, combines DNNs with reinforcement learning into an interactive system that enables the agent to learn the best policy from the environment to optimize their rewards. DRL opens up many new applications in domains such as healthcare, robotics, and smart grids. With the rapid evolution of IT infrastructures, cloud computing has been witnessed as the most common computing paradigm. The underlying infrastructure of cloud computing relies on a large amount of data centers. Nowadays, with the fast development of communication technologies, such as 5G, cloud computing is now evolving into yet another new paradigm called edge computing, providing for emerging applications, especially in the Internet-of-Things. The energy efficiency issue from both "cloud" and "edge" are becoming more crucial and calls for more attention. To solve the real-world energy efficiency problems, we take advantage of the deep learning and deep reinforcement learning techniques for efficient modeling of both "edge" and "cloud" applications. On the "edge" side, wearable technologies and the Internet of Things (IoT) are becoming increasingly popular in both personal and commercial applications with the employment of the embedded system technologies. Non-Volatile Processors (NVPs) have been proposed for the intermittent power supply problem, to ensure the instant on/off for embedded systems under the unstable power supply. We proposed neural network-based prediction techniques to derive the best power extraction policy and converter parameters optimization technique for NVPs. In cloud computing, we formulated a novel optimal power management problem of data centers to minimize the total cost by proposing the long short term memory (LSTM) neural network-based method for the prediction of future data center power consumption, and further we presented a novel DRL-based hierarchical framework for solving the overall resource allocation and power management problem in cloud computing systems. Furthermore, we explored the effectiveness of the DRL-based framework for high dimensional action and state spaces problem-dynamic treatment regimes, to model real-life complexity in heterogeneous disease progression and treatment choices, to provide doctors and patients the data-driven personalized decision recommendations. Last but not least, we explored the efficiency of deep neural networks. Structured weight pruning is a representative model compression technique of DNNs to reduce both the storage and computation requirements and meanwhile accelerate inference. An automatic hyperparameter determination process is necessary due to a large number of flexible hyperparameters. We propose an automatic structured pruning framework to compress the DNNs. Our framework outperforms the prior works on automatic model compression by up to 33× in pruning rate (120× reduction in the actual parameter count) under the same accuracy. Significant inference speedup has been observed from the proposed framework on actual measurements on the smartphone.

Recent progress on machine learning techniques for flow field optimization toward performance and commercial scale proton exchange membrane fuel cell: A systematic review

Nowadays, structural health monitoring has attracted much attention, due to the construction of important and complex structures and their safety. One branch of structural health monitoring is damage detection, estimating the location and extent of eventual damages in the structural systems. In this study, an efficient method is introduced to determine the location and extent of damage in the frame, beam and truss structures using time domain response and an optimization algorithm. First of all, the structural damage detection problem is formulated as a standard optimization problem. So that, the optimization objective function is defined by using the acceleration of damaged structures and analytical model acceleration. The acceleration is obtained using Newmark method. Damage is simulated by reducing the elasticity modulus of structural members. Then, damage problem converted to an optimization problem are solved by teaching–learning-based optimization (TLBO) algorithm therefore, the exact location and extent of damage in structure can be determined. In order to show the capabilities of the proposed approach for identifying structural damage, four illustrative test examples are considered with considering measurement noise effect. The results clearly show that the proposed method is as a powerful method to detect multiple damage in structures.

To classify the texts accurately, many machine learning techniques have been utilized in the field of Natural Language Processing (NLP). For many pattern classification applications, great success has been obtained when implemented with deep learning models rather than using ordinary machine learning techniques. Understanding the complex models and their respective relationships within the data determines the success of such deep learning techniques. But analyzing the suitable deep learning methods, techniques, and architectures for text classification is a huge challenge for researchers. In this work, a Contiguous Convolutional Neural Network (CCNN) based on Differential Evolution (DE) is initially proposed and named as Evolutionary Contiguous Convolutional Neural Network (ECCNN) where the data instances of the input point are considered along with the contiguous data points in the dataset so that a deeper understanding is provided for the classification of the respective input, thereby boosting the performance of the deep learning model. Secondly, a swarm-based Deep Neural Network (DNN) utilizing Particle Swarm Optimization (PSO) with DNN is proposed for the classification of text, and it is named Swarm DNN. This model is validated on two datasets and the best results are obtained when implemented with the Swarm DNN model as it produced a high classification accuracy of 97.32% when tested on the BBC newsgroup text dataset and 87.99% when tested on 20 newsgroup text datasets. Similarly, when implemented with the ECCNN model, it produced a high classification accuracy of 97.11% when tested on the BBC newsgroup text dataset and 88.76% when tested on 20 newsgroup text datasets.

Signature is an essential biometric modality used in daily life to authenticate one person on his claim. Due to the widespread usage of stamps in office work, banks, forensic documents, etc., it captures the great interest of the researchers for the past many years. With the advancement in the technology and internet, automatic signature verification considered with renewed interest by the researchers. In this paper, we present the state-of-the-art signature verification mechanism and a novel method to perform signature verification in the RGB images. We train our model using advanced deep learning technique (Deep Neural network (DNN)) to differentiate between genuine and forged classes of signatures. The proposed algorithm evaluated on 4NSigComp2010 and 4NSigComp2012 datasets with the same experimental setup. The results showed that the proposed algorithm outperforms the systems presented in the competitions with an EER of 12 and 11.75, respectively.