Search Results (22,052)

Carbon dioxide corrosion is a pervasive issue in pipelines and the petroleum industry, posing substantial risks to equipment safety and longevity. Accurate prediction of corrosion rates and severity is essential for effective material selection and equipment maintenance. This paper begins by addressing the limitations of traditional corrosion prediction methods and explores the application of machine learning algorithms in CO₂ corrosion prediction. Conventional models often fail to capture the complex interactions among multiple factors, resulting in suboptimal prediction accuracy, limited adaptability, and poor generalization. To overcome these limitations, this study systematically organized and analyzed the data, performed a correlation analysis of the data features, and examined the factors influencing corrosion. Subsequently, prediction models were developed using six algorithms: Random Forest (RF), K-Nearest Neighbors (KNN), Gradient Boosting Decision Tree (GBDT), Support Vector Machine (SVM), XGBoost, and LightGBM. The results revealed that SVM exhibited the lowest performance on both training and test sets, while RF achieved the best results with R² values of 0.92 for the training set and 0.88 for the test set. In the classification of corrosion severity, RF, LightGBM, SVM, and KNN were utilized, with RF demonstrating superior performance, achieving an accuracy of 99% and an F1-score of 0.99. This study highlights that machine learning algorithms, particularly Random Forest, offer substantial potential for predicting and classifying CO₂ corrosion. These algorithms provide innovative approaches and valuable insights for practical applications, enhancing predictive accuracy and operational efficiency in corrosion management. Full article

Intelligent mobile image sensing powered by deep learning analyzes images captured by cameras from mobile devices, such as smartphones or smartwatches. It supports numerous mobile applications, such as image classification, face recognition, and camera scene detection. Unfortunately, mobile devices often lack the resources necessary for deep learning, leading to increased inference latency and rapid battery consumption. Moreover, the inference accuracy may decline over time due to potential data drift. To address these issues, we introduce a new cost-efficient framework, called Corun, designed to simultaneously handle multiple inference queries and continual model retraining/fine-tuning of a pre-trained model on a single commodity GPU in an edge server to significantly improve the inference throughput, upholding the inference accuracy. The scheduling method of Corun undertakes offline profiling to find the maximum number of concurrent inferences that can be executed along with a retraining job on a single GPU without incurring an out-of-memory error or significantly increasing the latency. Our evaluation verifies the cost-effectiveness of Corun. The inference throughput provided by Corun scales with the number of concurrent inference queries. However, the latency of inference queries and the length of a retraining epoch increase at substantially lower rates. By concurrently processing multiple inference and retraining tasks on one GPU instead of using a separate GPU for each task, Corun could reduce the number of GPUs and cost required to deploy mobile image sensing applications based on deep learning at the edge. Full article

The phonocardiogram (PCG) is a crucial tool for the early detection, continuous monitoring, accurate diagnosis, and efficient management of cardiovascular diseases. It has the potential to revolutionize cardiovascular care and improve patient outcomes. The PhysioNet/CinC Challenge 2016 database, a large and influential resource, encourages contributions to accurate heart sound state classification (normal versus abnormal), achieving promising benchmark performance (accuracy: 99.80%; sensitivity: 99.70%; specificity: 99.10%; and score: 99.40%). This study reviews recent advances in analytical techniques applied to this database, and 104 publications on PCG signal analysis are retrieved. These techniques encompass heart sound preprocessing, signal segmentation, feature extraction, and heart sound state classification. Specifically, this study summarizes methods such as signal filtering and denoising; heart sound segmentation using hidden Markov models and machine learning; feature extraction in the time, frequency, and time-frequency domains; and state-of-the-art heart sound state recognition techniques. Additionally, it discusses electrocardiogram (ECG) feature extraction and joint PCG and ECG heart sound state recognition. Despite significant technical progress, challenges remain in large-scale high-quality data collection, model interpretability, and generalizability. Future directions include multi-modal signal fusion, standardization and validation, automated interpretation for decision support, real-time monitoring, and longitudinal data analysis. Continued exploration and innovation in heart sound signal analysis are essential for advancing cardiac care, improving patient outcomes, and enhancing user trust and acceptance. Full article

Peptides are bioactive molecules whose functional versatility in living organisms has led to successful applications in diverse fields. In recent years, the amount of data describing peptide sequences and function collected in open repositories has substantially increased, allowing the application of more complex computational models to study the relations between the peptide composition and function. This work introduces AMP-Detector, a sequence-based classification model for the detection of peptides’ functional biological activity, focusing on accelerating the discovery and de novo design of potential antimicrobial peptides (AMPs). AMP-Detector introduces a novel sequence-based pipeline to train binary classification models, integrating protein language models and machine learning algorithms. This pipeline produced 21 models targeting antimicrobial, antiviral, and antibacterial activity, achieving average precision exceeding 83%. Benchmark analyses revealed that our models outperformed existing methods for AMPs and delivered comparable results for other biological activity types. Utilizing the Peptide Atlas, we applied AMP-Detector to discover over 190,000 potential AMPs and demonstrated that it is an integrative approach with generative learning to aid in de novo design, resulting in over 500 novel AMPs. The combination of our methodology, robust models, and a generative design strategy offers a significant advancement in peptide-based drug discovery and represents a pivotal tool for therapeutic applications. Full article

Cybersecurity is normally defined as protecting systems against all kinds of cyberattacks; however, due to the rapid and permanent expansion of technology and digital transformation, the threats are also increasing. One of those new threats is ransomware, which is a form of malware that aims to steal user’s money. Ransomware is a form of malware that encrypts a victim’s files. The attacker then demands a ransom from the victim to restore access to the data upon a large payment. Ransomware is a way of stealing money in which a user’s files are encrypted and the decrypted key is held by the attacker until a ransom amount is paid by the victim. This systematic literature review (SLR) highlights recent papers published between 2020 and 2024. This paper examines existing research on early ransomware detection methods, focusing on the signs, frameworks, and techniques used to identify and detect ransomware before it causes harm. By analyzing a wide range of academic papers, industry reports, and case studies, this review categorizes and assesses the effectiveness of different detection methods, including those based on signatures, behavior patterns, and machine learning (ML). It also looks at new trends and innovative strategies in ransomware detection, offering a classification of detection techniques and pointing out the gaps in current research. The findings provide useful insights for cybersecurity professionals and researchers, helping guide future efforts to develop strong and proactive ransomware detection systems. This review emphasizes the need for ongoing improvements in detection technologies to keep up with the constantly changing ransomware threat landscape. Full article

Due to the complexity and illegibility of medical images, it brings inconvenience and difficulty to the diagnosis of medical personnel. To address these issues, an optimization algorithm called GSL(Gradient sine linear) based on Adam algorithm improvement is proposed in this paper, which introduces gradient pruning strategy, periodic adjustment of learning rate, and linear interpolation strategy. The gradient trimming technique can scale the gradient to prevent gradient explosion, while the periodic adjustment of the learning rate and linear interpolation strategy adjusts the learning rate according to the characteristics of the sinusoidal function, accelerating the convergence while reducing the drastic parameter fluctuations, improving the efficiency and stability of training. The experimental results show that compared to the classic Adam algorithm, this algorithm can demonstrate better classification accuracy, the GSL algorithm achieves an accuracy of 78% and 75.2% on the MobileNetV2 network and ShuffleNetV2 network under the Gastroenterology dataset; and on the MobileNetV2 network and ShuffleNetV2 network under the Glaucoma dataset, an accuracy of 84.72% and 83.12%. The GSL optimizer achieved significant performance improvement on various neural network structures and datasets, proving its effectiveness and practicality in the field of deep learning, and also providing new ideas and methods for solving the difficulties in medical image recognition. Full article

Introduction: Vertebral compression fractures (VCFs) pose a considerable healthcare burden and are linked to elevated morbidity and mortality. Despite available anti-osteoporotic treatments (AOTs), guideline adherence is lacking. This study aims to evaluate subsequent hip fracture incidence after index VCF and to elucidate AOT prescribing patterns in VCF patients, further assessing the impact of surgical interventions on these patterns. Materials and Methods: Patients with index VCFs between 2010 and 2021 were identified using the PearlDiver database. Diagnostic and procedural data were recorded using International Classification of Diseases (ICD-9, ICD-10) and Current Procedural Terminology (CPT) codes. Patients under age 50 and follow-up <one year following index VCF were excluded. Patients were categorized based on whether they received AOT within one year, preceding and after index VCF, and were subsequently propensity-matched 1:3 based on age, sex, and Elixhauser Comorbidity Index (ECI) score to compare hip fracture incidence following index VCF. Sub-analysis was performed for operatively managed VCFs (kyphoplasty/vertebroplasty). Statistical tests included Chi-squared for categorical outcomes, and Kruskal–Wallis for continuous measures. Results: Of 637,701 patients, 72.6% were female. The overall subsequent hip fracture incidence was 2.6% at one year and 12.9% for all-time follow-up. Propensity-matched analysis indicated higher subsequent hip fracture rates in patients initiated on AOT post-index VCF (one year: 3.8% vs. 3.5%, p = 0.0013; all-time: 14.3% vs. 13.0%, p < 0.0001). Conclusions: The study reveals an unexpected increase in subsequent hip fractures among patients initiated on AOT post-index VCF, likely due to selection bias. These findings highlight the need for refined osteoporosis-management strategies to improve guideline adherence, thereby mitigating patient morbidity and mortality. Full article

Pressure ulcers are serious healthcare concerns, especially for the elderly with reduced mobility. Severe pressure ulcers are accompanied by pain, degrading patients’ quality of life. Thus, speedy and accurate detection and classification of pressure ulcers are vital for timely treatment. The conventional visual examination method requires professional expertise for diagnosing pressure ulcer severity but it is difficult for the lay carer in domiciliary settings. In this study, we present a mobile healthcare platform incorporated with a light-weight deep learning model to exactly detect pressure ulcer regions and classify pressure ulcers into six severities such as stage 1–4, deep tissue pressure injury, and unstageable. YOLOv8 models were trained and tested using 2800 annotated pressure ulcer images. Among the five tested YOLOv8 models, the YOLOv8m model exhibited promising detection performance with overall classification accuracy of 84.6% and a mAP@50 value of 90.8%. The mobile application (app) was also developed applying the trained YOLOv8m model. The mobile app returned the diagnostic result within a short time (≒3 s). Accordingly, the proposed on-device AI app can contribute to early diagnosis and systematic management of pressure ulcers. Full article

This study involves the development of a hybrid forecasting framework that integrates two different models in a framework to improve prediction capability. Although the concept of hybridization is not a new issue in forecasting, our approach presents a new structure that combines two standard simple forecasting models uniquely for superior performance. Hybridization is significant for complex data sets with multiple patterns. Such data sets do not respond well to simple models, and hybrid models based on the integration of various forecasting tools often lead to better forecasting performance. The proposed architecture includes serially connected ARIMA and ANN models. The original data set is first processed by ARIMA. The error (i.e., residuals) of the ARIMA is sent to the ANN for secondary processing. Between these two models, there is a classification mechanism where the raw output of the ARIMA is categorized into three groups before it is sent to the secondary model. The algorithm is tested on well-known forecasting cases from the literature. The proposed model performs better than existing methods in most cases. Full article

Recent advancements in digital technologies and automated analysis techniques applied to Historic Built Environment (HBE) demonstrate significant advantages in efficiently collecting and interpreting data for building conservation activities. Integrating digital image processing through Artificial Intelligence approaches further streamlines data analysis for diagnostic assessments. In this context, this paper presents a scoping review based on Scopus and Web of Science databases, following the PRISMA protocol, focusing on applying Deep Learning (DL) architectures for image-based classification of decay phenomena in the HBE, aiming to explore potential implementations in decision support system. From the literature screening process, 29 selected articles were analyzed according to methods for identifying buildings’ surface deterioration, cracks, and post-disaster damage at a district scale, with a particular focus on the innovative DL architectures developed, the accuracy of results obtained, and the classification methods adopted to understand limitations and strengths. The results highlight current research trends and the potential of DL approaches for diagnostic purposes in the built heritage conservation field, evaluating methods and tools for data acquisition and real-time monitoring, and emphasizing the advantages of implementing the adopted techniques in interoperable environments for information sharing among stakeholders. Future challenges involve implementing DL models in mobile apps, using sensors and IoT systems for on-site defect detection and long-term monitoring, integrating multimodal data from non-destructive inspection techniques, and establishing direct connections between data, intervention strategies, timing, and costs, thereby improving heritage diagnosis and management practices. Full article

In recent years, contrastive learning has been a highly favored method for self-supervised representation learning, which significantly improves the unsupervised training of deep image models. Self-supervised learning is a subset of unsupervised learning in which the learning process is supervised by creating pseudolabels from the data themselves. Using supervised final adjustments after unsupervised pretraining is one way to take the most valuable information from a vast collection of unlabeled data and teach from a small number of labeled instances. This study aims firstly to compare contrastive learning with other traditional learning models; secondly to demonstrate by experimental studies the superiority of contrastive learning during classification; thirdly to fine-tune performance using pretrained models and appropriate hyperparameter selection; and finally to address the challenge of using contrastive learning techniques to produce data representations with semantic meaning that are independent of irrelevant factors like position, lighting, and background. Relying on contrastive techniques, the model efficiently captures meaningful representations by discerning similarities and differences between modified copies of the same image. The proposed strategy, involving unsupervised pretraining followed by supervised fine-tuning, improves the robustness, accuracy, and knowledge extraction of deep image models. The results show that even with a modest 5% of data labeled, the semisupervised model achieves an accuracy of 57.72%. However, the use of supervised learning with a contrastive approach and careful hyperparameter tuning increases accuracy to 85.43%. Further adjustment of the hyperparameters resulted in an excellent accuracy of 88.70%. Full article

Background: Inflammatory bowel disease (IBD) prevalence in Eastern Europe is increasing. The 30-day readmission rate is a crucial quality metric in healthcare, reflecting the effectiveness of initial treatment and the continuity of care post-discharge; however, such parameters are rarely analyzed. The aim of this study was to explore the trends in 30-day readmissions among patients with inflammatory bowel disease in Latvia between 2014 and 2020. Methods: This is a retrospective trends study in IBD—ulcerative colitis and Crohn’s disease (UC and CD)—patients in Latvia between 2014 and 2020, involving all IBD patients identified in the National Health service database in the International Classification of Diseases-10 (ICD) classification (K50.X and K51.X) and having at least one prescription for IBD diagnoses. We assessed all IBD-related hospitalizations (discharge ICD codes K50X and K51X), as well as hospitalizations potentially related to IBD comorbidities. We analyzed hospitalization trends and obtained the 30 day all-cause readmission rate, disease specific readmission rate and readmission proportion for specific calendar years. Trends in readmissions and the mean length of stay (LOS) for CD and UC were calculated. Results: Despite a decrease in admission rates observed in 2020, the total number of readmissions for CD and UC has increased. Female patients prevailed through the study period and were significantly older than male patients in both the CD and UC groups, p < 0.05. We noted that there was no trend for 30 day all-cause readmission rate for CD (p > 0.05); however, there was a statistically significant trend for 30 day all-cause readmission for UC patients (p-trend = 0.018) in the period from 2014 to 2019. There was a statistically significant trend for CD-specific readmission rate (p < 0.05); however, no statistically significant trend was observed for UC-specific readmission (p > 0.05). An exploratory analysis did not reveal any statistically significant differences between treated and not-treated IBD patients (p > 0.05). The increasing trend is statistically significant over the period 2014–2018 (p < 0.05); however, the trend interrupts in 2020, which can be associated with the COVID-19 global pandemic and the related changes in admission flows where the gastroenterology capacity was reallocated to accommodate increasing numbers of COVID-19 patients. More studies are needed to evaluate the long-term impact of COVID-19 pandemic and 30-day readmissions. No significant dynamics were observed in the mean total hospitalization costs over the 2014–2020 period. Full article

The role of robotic systems in human assistance is inevitable with the bots that assist with interactive and voice commands. For cooperative and precise assistance, the understandability of these bots needs better input analysis. This article introduces a Comparable Input Assessment Technique (CIAT) to improve the bot system’s understandability. This research introduces a novel approach for HRI that uses optimized algorithms for input detection, analysis, and response generation in conjunction with advanced neural classifiers. This approach employs deep learning models to enhance the accuracy of input identification and processing efficiency, in contrast to previous approaches that often depended on conventional detection techniques and basic analytical methods. Regardless of the input type, this technique defines cooperative control for assistance from previous histories. The inputs are cooperatively validated for the instruction responses for human assistance through defined classifications. For this purpose, a neural classifier is used; the maximum possibilities for assistance using self-detected instructions are recommended for the user. The neural classifier is divided into two categories according to its maximum comparable limits: precise instruction and least assessment inputs. For this purpose, the robot system is trained using previous histories and new assistance activities. The learning process performs comparable validations between detected and unrecognizable inputs with a classification that reduces understandability errors. Therefore, the proposed technique was found to reduce response time by 6.81%, improve input detection by 8.73%, and provide assistance by 12.23% under varying inputs. Full article

Background: This study aims to assess systemic risk factors in diabetes mellitus (DM) patients and predict diabetic retinopathy (DR) using a Random Forest (RF) classification model. Methods: We included DM patients presenting to the retina clinic for first-time DR screening. Data on age, gender, diabetes type, treatment history, DM control status, family history, pregnancy history, and systemic comorbidities were collected. DR and sight-threatening DR (STDR) were diagnosed via a dilated fundus examination. The dataset was split 80:20 into training and testing sets. The RF model was trained to detect DR and STDR separately, and its performance was evaluated using misclassification rates, sensitivity, and specificity. Results: Data from 1416 DM patients were analyzed. The RF model was trained on 1132 (80%) patients. The misclassification rates were 0% for DR and ~20% for STDR in the training set. External testing on 284 (20%) patients showed 100% accuracy, sensitivity, and specificity for DR detection. For STDR, the model achieved 76% (95% CI-70.7%–80.7%) accuracy, 53% (95% CI-39.2%–66.6%) sensitivity, and 80% (95% CI-74.6%–84.7%) specificity. Conclusions: The RF model effectively predicts DR in DM patients using systemic risk factors, potentially reducing unnecessary referrals for DR screening. However, further validation with diverse datasets is necessary to establish its reliability for clinical use. Full article

In the construction industry, the professional evaluation of construction schemes represents a crucial link in ensuring the safety, quality and economic efficiency of the construction process. However, due to the large number and diversity of construction schemes, traditional expert review methods are limited in terms of timeliness and comprehensiveness. This leads to an increasingly urgent requirement for intelligent check of construction schemes. This paper proposes an intelligent compliance checking method for construction schemes that integrates knowledge graphs and large language model (LLM). Firstly, a method for constructing a multi-dimensional, multi-granular knowledge graph for construction standards is introduced, which serves as the foundation for domain-specific knowledge support to the LLM. Subsequently, a parsing module based on text classification and entity extraction models is proposed to automatically parse construction schemes and construct pathways for querying the knowledge graph of construction standards. Finally, an LLM is leveraged to achieve an intelligent compliance check. The experimental results demonstrate that the proposed method can effectively integrate domain knowledge to guide the LLM in checking construction schemes, with an accuracy rate of up to 72%. Concurrently, the well-designed prompt template and the comprehensiveness of the knowledge graph facilitate the stimulation of the LLM’s reasoning ability. This work contributes to exploring the application of LLMs and knowledge graphs in the vertical domain of text compliance checking. Future work will focus on optimizing the integration of LLMs and domain knowledge to further improve the accuracy and practicality of the intelligent checking system. Full article