Civil infrastructure crack detection using deep learning and image segmentation-based techniques

Failure of civil infrastructure, such as, bridges and pipelines, can cause large public safety and economic consequences. Structural health monitoring (SHM) plays a significant role in preventing and mitigating the course of structural damage. In this work, a multi-scale SHM framework based on Hadoop Ecosystem (MS-SHM-Hadoop) to monitor and evaluate the serviceability of civil infrastructure is proposed. Through utilizing fault-tolerant distributed file system called Hadoop Distributed File System (HDFS) and high-performance parallel data processing engine called MapReduce programming paradigm, MS-SHM-Hadoop has high scalability and robustness in data ingestion, fusion, processing, retrieval, and analytics. MS-SHM-Hadoop is a multi-scale reliability analysis framework including nationwide civil infrastructure survey, global structural integrity analysis, and structural components’ reliability analysis. The nationwide civil infrastructure survey uses deep-learning techniques to evaluate their serviceability according to real-time sensory data or archived civil infrastructure related data such as traffic status, weather conditions and civil infrastructure’s structural configuration. The global structural integrity analysis of a targeted civil infrastructure is made by processing and analyzing the measured vibration signals incurred by external loads such as wind and traffic flow. Component-wise reliability analysis is also enabled by deep learning technique, where the input data is derived from the measured structural load effect, hyper-spectral and 3D point cloud images, and moisture measurement about structural component. As one of its major contributions, this work employs Bayesian network to formulate the integral serviceability of a civil infrastructure according to components’ serviceability and inter-component correlations. Here the inter-component correlations are jointly specified using statistics-oriented machine learning method (e.g., association rule learning) or structural mechanics modeling and simulation.

Structural Health Monitoring (SHM) is essential for ensuring the long-term safety, durability, and reliability of civil infrastructure by enabling early detection of cracks, abnormal vibrations, tilting, and deformation. Conventional inspection techniques remain limited due to their manual nature, lack of real-time capabilities, restricted accessibility, and susceptibility to human error. To address these limitations, this project proposes an intelligent SHM framework that integrates Internet of Things (IoT) sensing, cloud computing, and deep learning–based crack detection. The system utilizes an ESP32 microcontroller interfaced with an ADXL345 accelerometer, a vibration sensor, and a flex sensor to continuously monitor structural responses such as tilt, tremors, and surface bending. Sensor data is displayed locally through an LCD module and uploaded to the ThingSpeak cloud for remote access and long- term trend analysis. A Telegram Bot is incorporated to deliver instant alerts whenever abnormal sensor patterns are detected, ensuring rapid awareness and timely intervention. Furthermore, an AI-driven crack detection module based on YOLOv5 analyzes high-resolution surface images and accurately identifies crack presence using advanced object-detection techniques. By combining IoT-based sensing with real-time cloud analytics and deep learning image interpretation, the proposed system offers a cost-effective, scalable, and highly reliable solution for preventive maintenance and enhanced structural safety in modern infrastructure.

The Internet of Things (IoT) has transformed many aspects of modern life, from healthcare and transportation to home automation and industrial control systems. However, the increasing number of connected devices has also led to an increase in security threats, particularly from botnets. To mitigate these threats, various machine learning (ML) and deep learning (DL) techniques have been proposed for IoT botnet attack detection. This systematic review aims to identify the most effective ML and DL techniques for detecting IoT botnets by delving into benchmark datasets, evaluation metrics, and data pre-processing techniques in detail. A comprehensive search was conducted in multiple databases for primary studies published between 2018 and 2023. Studies were included if they reported the use of ML or DL techniques for IoT botnet detection. After screening 1,567 records, 25 studies were included in the final review. The findings suggest that ML and DL techniques show promising results in detecting IoT botnet attacks, outperforming traditional signature-based methods. However, the effectiveness of the techniques varied depending on the dataset, features, and evaluation metrics used. Based on the synthesis of the findings, this review proposes a taxonomy for ML and DL techniques in IoT botnet attack detection and provides recommendations for future research in this area. This review illuminates the considerable potential of ML and DL approaches in bolstering the detection of IoT botnet attacks, thereby offering valuable insights to researchers involved in the domain of IoT security.

Environmental-assisted cracks in pipeline steels usually undergo the following three sequential stages prior to the failure: • Stage 1 – crack initiation and early stage crack growth, in which cracks initiate at imperfections but grow slowly depth-wise with time. Crack length may be seen to increase either because of merging with new small cracks in the vicinity of an existing crack or faster crack growth at the crack tip. Some cracks pose little threat to pipeline steel integrity if they remain dormant. • Stage 2 – Increased crack growth rate where crack growth can be dictated by mechanical driving forces and crack growth rate increases with time. • Stage 3 – The final stage of crack growth where crack growth rate is very high. Typical crack management programs mitigate cracks prior to entering Stage III. It is of great importance that pipeline steels with Stage II cracks are detected, monitored, and managed to ensure operational pipeline integrity. Although a range of crack in-line inspection and detection techniques with varied detection limits are available, it is not clear how their detection limits match the threshold geometrical dimensions of Stage 2-cracks. This investigation is aimed to define critical geometrical dimensions of cracks that are considered to be Stage 2 cracks. The determination of critical geometrical dimensions of Stage 2 cracks was made with a consideration of a wide range of situations including pipeline operating conditions, susceptible environments for crack growth, metallurgical, fabrication and construction conditions of pipeline steels. A comparison of the threshold geometrical dimensions of Stage 2 cracks with the crack detection limits of modern crack inspection and detection techniques are made at the end of the paper.

Coastal aquifers are vital for sustaining ecosystems and providing freshwater for agriculture and domestic use. However, rising groundwater salinity in these regions demands innovative approaches for accurate modeling and prediction. In recent decades, machine learning (ML) and deep learning (DL) techniques have been extensively used across various water resource management fields, often yielding promising outcomes. This review examines the growing usage of ML and DL techniques in modeling groundwater salinity in coastal aquifers. The analysis is based on 104 peer-reviewed journal articles including the review articles indexed in PubMed, ScienceDirect, Google Scholar, Scopus, and SpringerLink using keywords like "saltwater intrusion", "machine learning", “deep learning”, and "groundwater salinity". The review discusses recent advancements, challenges, and future directions for improving ML model accuracy and applicability. Studies reveal an increasing reliance on ML techniques to predict groundwater salinity and manage seawater intrusion across various coastal geological settings. Researchers have employed a range of ML models, from traditional methods like Artificial Neural Networks and Adaptive Neuro Fuzzy Inference Systems to advanced DL-based models like Convolutional Neural Networks and Long Short-Term Memory Networks, often using ensemble methods to enhance accuracy. Key findings include the top-tier output of ensemble and optimized models, including Random Forest and Grasshopper Optimization Algorithm-XGBoost. These studies highlight the importance of model selection, input variable ranking, and computational efficiency, demonstrating ML's global relevance in environmental management. The review highlights the prospects of ML, DL, and ensemble models to redefine groundwater management in coastal aquifers, offering more effective and sustainable solutions to the challenges posed by groundwater salinity and saltwater intrusion. Future advancements will focus on further integrating DL, explainable artificial intelligence, and ensemble approaches, along with other innovative techniques, to explore sparsely studied variables, model new or unique study areas, and apply ML methods for managing groundwater salinity.

With the development of information and technology, especially with the boom in big data, healthcare support systems are becoming much better. Patient data can be collected, retrieved, and stored in real time. These data are valuable and meaningful for monitoring, diagnosing, and further applications in data analysis and decision-making. Essentially, the data can be divided into three types, namely, statistical, image-based, and sequential data. Each type has a different method of retrieval, processing, and deployment. Additionally, the application of machine learning (ML) and deep learning (DL) in healthcare support systems is growing more rapidly than ever. Numerous high-performance architectures are proposed to optimize decision-making. As reliability and stability are the most important factors in the healthcare support system, enhancing the predicted performance and maintaining the stability of the model are always the top priority. The main idea of our study comes from ensemble techniques. Numerous studies and data science competitions show that by combining several weak models into one, ensemble models can attain outstanding performance and reliability. We propose three deep ensemble learning (DEL) approaches, each with stable and reliable performance, that are workable on the above-mentioned data types. These are deep-stacked generalization ensemble learning, gradient deep learning boosting, and deep aggregation learning. The experiment results show that our proposed approaches achieve more vigorous and reliable performance than traditional ML and DL techniques on statistical, image-based, and sequential benchmark datasets. In particular, on the Heart Disease UCI dataset, representing the statistical type, the gradient deep learning boosting approach dominates the others with accuracy, recall, F1-score, Matthews correlation coefficient, and area under the curve values of 0.87, 0.81, 0.83, 0.73, and 0.91, respectively. On the X-ray dataset, representing the image-based type, the deep aggregation learning approach shows the highest performance with values of 0.91, 0.97, 0.93, 0.80, and 0.94, respectively. On the Depresjon dataset, representing the sequence type, the deep-stacked generalization ensemble learning approach outperforms the others with values of 0.91, 0.84, 0.86, 0.8, and 0.94, respectively. Overall, we conclude that applying DL models using our proposed approaches is a promising method for the healthcare support system to enhance prediction and diagnosis performance. Furthermore, our study reveals that these approaches are flexible and easy to apply to achieve optimal performance.

Millions of people worldwide suffer from Parkinson’s disease (PD), a neurodegenerative disorder marked by motor symptoms such as tremors, bradykinesia, and stiffness. Accurate early diagnosis is crucial for effective management and treatment. This article presents a novel review of Machine Learning (ML) and Deep Learning (DL) techniques for PD detection and progression monitoring, offering new perspectives by integrating diverse data sources. We examine the public datasets recently used in studies, including audio recordings, gait analysis, and medical imaging. We discuss the preprocessing methods applied, the state-of-the-art models utilized, and their performance. Our evaluation included different algorithms such as support vector machines (SVM), random forests (RF), convolutional neural networks (CNN). These algorithms have shown promising results in PD diagnosis with accuracy rates exceeding 99% in some studies combining data sources. Our analysis particularly showcases the effectiveness of audio analysis in early symptom detection and gait analysis, including the Unified Parkinson’s Disease Rating Scale (UPDRS), in monitoring disease progression. Medical imaging, enhanced by DL techniques, has improved the identification of PD. The application of ML and DL in PD research offers significant potential for improving diagnostic accuracy. However, challenges like the need for large and diverse datasets, data privacy concerns, and data quality in healthcare remain. Additionally, developing explainable AI is crucial to ensure that clinicians can trust and understand ML and DL models. Our review highlights these key challenges that must be addressed to enhance the robustness and applicability of AI models in PD diagnosis, setting the groundwork for future research to overcome these obstacles.

Deep and machine learning techniques for medical imaging-based breast cancer: A comprehensive review

Designing of VehiNet Using Convolutional Neural Networks and Deep Learning Techniques

This work aims to improve the accuracy of traditional models for analyzing the hydraulic properties of unsaturated soil by integrating digital imaging measurement with deep learning techniques. The work first reviews current research on the basic characteristics of unsaturated soil and the applications of deep learning in this field. Next, it examines the impact of soil specimens’ physical properties on their hydraulic properties. This includes acquiring hydraulic parameters and the soil-water characteristic curve through full-surface digital imaging measurements. Finally, a soil hydraulic property model based on the backpropagation neural network (BPNN) is implemented, trained, and validated. Results indicate that the model’s predicted soil-water characteristic curve aligns closely with the experimental findings from previous studies. Moreover, the proposed BPNN-based unsaturated soil hydraulic property model uses the Levenberg–Marquardt algorithm, which reduces computational time and noise compared to alternative algorithms. Meanwhile, analysis of the model parameters suggests that ten neurons in the hidden layer provide optimal performance. By incorporating correlations between physical parameters, such as soil particle size and soil hydraulic properties, the model demonstrates lower error rates compared to other literature models. Overall, this BPNN model effectively represents the relationship between soil’s physical and hydraulic parameters, streamlining traditional soil correlation coefficient estimation.

This review examines the recent developments in deep learning (DL) techniques applied to multimodal fusion image segmentation for liver cancer. Hepatocellular carcinoma is a highly dangerous malignant tumor that requires accurate image segmentation for effective treatment and disease monitoring. Multimodal image fusion has the potential to offer more comprehensive information and more precise segmentation, and DL techniques have achieved remarkable progress in this domain. This paper starts with an introduction to liver cancer, then explains the preprocessing and fusion methods for multimodal images, then explores the application of DL methods in this area. Various DL architectures such as convolutional neural networks (CNN) and U-Net are discussed and their benefits in multimodal image fusion segmentation. Furthermore, various evaluation metrics and datasets currently used to measure the performance of segmentation models are reviewed. While reviewing the progress, the challenges of current research, such as data imbalance, model generalization, and model interpretability, are emphasized and future research directions are suggested. The application of DL in multimodal image segmentation for liver cancer is transforming the field of medical imaging and is expected to further enhance the accuracy and efficiency of clinical decision making. This review provides useful insights and guidance for medical practitioners.

Recently, the construction industry has benefited from the increased application of smart construction led by the core technologies of the fourth industrial revolution, such as BIM, AI, modular construction, and AR/VR, which enhance productivity and work efficiency. In addition, the importance of “Off-Site Construction (OSC)”, a factory-based production method, is being highlighted as modular construction increases in the domestic construction market as a means of productivity enhancement. The problem with OSC construction is that the quality inspection of Precast Concrete (PC) members produced at the factory and brought to the construction site is not carried out accurately and systematically. Due to the shortage of quality inspection manpower, a lot of time and money is wasted on inspecting PC members on-site, compromising inspection efficiency and accuracy. In this study, the major inspection items to be checked during the quality inspection are classified based on the existing PC member quality inspection checklist and PC construction specifications. Based on the major inspection items, the items to which AI technology can be applied (for automatic quality inspection) were identified. Additionally, the research was conducted focusing on the detection of cracks, which are one of the major types of defects in PC members. However, accurate detection of cracks is difficult since the inspection mostly relies on a visual check coupled with subjective experience. To automate the detection of cracks for PC members, video images of cracks and non-cracks on the surface were collected and used for image training and recognition using Convolutional Neural Network (CNN) and object detection, one of the deep learning technologies commonly applied in the field of image object recognition. Detected cracks were classified according to set thresholds (crack width and length), and finally, an automated PC member crack detection system that enables automatic crack detection based on mobile and web servers using deep learning and imaging technologies was proposed. This study is expected to enable more accurate and efficient on-site PC member quality inspection. Through the smart PC member quality inspection system proposed in this study, the time required for each phase of the existing PC member quality inspection work was reduced. This led to a reduction of 13 min of total work time, thereby improving work efficiency and convenience. Since quality inspection information can be stored and managed in the system database, human errors can be reduced while managing the quality of OSC work systematically and accurately. It is expected that through optimizing and upgrading our proposed system, quality work for the precise construction of OSC projects can be ensured. At the same time, systematic and accurate quality management of OSC projects is achievable through inspection data. In addition, the smart quality inspection system is expected to establish a smart work environment that enables efficient and accurate quality inspection practices if applied to various construction activities other than the OSC projects.

Deep learning techniques have rapidly become important as a preferred method for evaluating medical image segmentation. This survey analyses different contributions in the deep learning medical field, including the major common issues published in recent years, and also discusses the fundamentals of deep learning concepts applicable to medical image segmentation. The study of deep learning can be applied to image categorization, object recognition, segmentation, registration, and other tasks. First, the basic ideas of deep learning techniques, applications, and frameworks are introduced. Deep learning techniques that operate the ideal applications are briefly explained. This paper indicates that there is a previous experience with different techniques in the class of medical image segmentation. Deep learning has been designed to describe and respond to various challenges in the field of medical image analysis such as low accuracy of image classification, low segmentation resolution, and poor image enhancement. Aiming to solve these present issues and improve the evolution of medical image segmentation challenges, we provide suggestions for future research.

Deep learning has been successfully explored in addressing different multimedia topics recent years, ranging from object detection, semantic classification, entity annotation, to multimedia captioning, multimedia question answering and storytelling. Open source libraries and platforms such as Tensorflow, Caffe, MXnet significantly help promote the wide deployment of deep learning in solving real-world applications. On one hand, deep learning practitioners, while not necessary to understand the involved math behind, are able to set up and make use of a complex deep network. One recent deep learning tool based on Keras even provides the graphical interface to enable straightforward 'drag and drop' operation for deep learning programming. On the other hand, however, some general theoretical problems of learning such as the interpretation and generalization, have only achieved limited progress. Most deep learning papers published these days follow the pipeline of designing/modifying network structures - tuning parameters - reporting performance improvement in specific applications. We have even seen many deep learning application papers without one single equation. Theoretical interpretation and the science behind the study are largely ignored. While excited about the successful application of deep learning in classical and novel problems, we multimedia researchers are responsible to think and solve the fundamental topics in deep learning science. Prof. Guanrong Chen recently wrote an editorial note titled 'Science and Technology, not SciTech' [1]. This panel falls into similar discussion and aims to invite prestigious multimedia researchers and active deep learning practitioners to discuss the positioning of deep learning research now and in the future. Specifically, each panelist is asked to present their opinions on the following five questions: 1)How do you think the current phenomenon that deep learning applications are explosively growing, while the general theoretical problems remain slow progress? 2)Do you agree that deployment of deep learning techniques is getting easy (with a low barrier), while deep learning research is difficult (with a high barrier) 3)What do you think are the core problems for deep learning techniques? 4)What do you think are the core problems for deep learning science? 5)What's your suggestion on the multimedia research in the post-deep learning era?

Agriculture has been a vital sector for the majority of people, especially in countries like India. However, the increasing need for food production has led to intensive farming practices that have resulted in the deterioration of soil quality. This deterioration in soil quality poses significant challenges to both agricultural productivity and environmental sustainability. To address these challenges, advanced soil nutrient prediction systems that utilize machine learning and deep learning techniques are being developed. These advanced soil nutrient prediction systems utilize various sources of data, such as soil parameters, plant diseases, pests, fertilizer usage, and changes in weather patterns. By mapping and analyzing these data sources, machine learning algorithms can accurately predict the distribution of soil nutrients and other properties essential for precise agricultural practices. A previous study compared machine learning algorithms like SVM and Random Forest with deep learning algorithms CNN and LSTM for predicting crop yields. The most appropriate model is a significant challenge, but several studies have evaluated recommendation system models using deep machine learning techniques. Deep learning models attain accuracy above 90%, while many ML models achieve rates between 90% and 93%. Furthermore, the research seeks to propose specific crop suggestions grounded in soil nutrients for precision agriculture to enhance crop productivity.