Search

A This paper proposes a modified real-time transient modelling (MRTTM) framework to address the critical challenge of leak detection and localization in pipeline transmission systems. Pipelines are essential infrastructure for transporting liquids and gases, but they are susceptible to leaks, with severe environmental and economic impacts. MRTTM tackles this challenge with a three-stage operational process. First, "Data Collection" gathers sensor data from designated observation points. Second, the "Detection" stage identifies leaks. Finally, "Decision-Making" utilizes MRTTM to pinpoint the exact leak magnitude and location. This paper introduces an innovative method designed to significantly enhance pipeline leak detection and localization through the application of artificial intelligence and advanced signal processing techniques. The improved MRTTM framework integrates AI for pattern recognition, state space modelling for leak segment identification, and an extended Kalman filter (EKF) for precise leak location estimation, addressing the limitations of traditional methods. This paper showcases the application of MRTTM through a case study using the K-nearest neighbors (KNN) method on a water transmission pipeline for leak detection. KNN aids in classifying leak patterns and identifying the most likely leak location. Additionally, MRTTM incorporates the EKF, enabling real-time updates during transient events for faster leak identification. Preprocessing sensor data before comparison with the leakage pattern bank (LPB) minimizes false alarms and enhances detection reliability. Overall, the AI-powered MRTTM framework offers a powerful solution for swift and precise leak detection and localization in pipeline systems. The functionality of the framework is examined, and the results effectively approve the effectiveness of this methodology. The experimental results validate the practical utility of the MRTTM framework in real-world applications, demonstrating up to 90% detection accuracy and an F1 score of 0.92. [ABSTRACT FROM AUTHOR]

This paper reviews alarm processing methods in electrical power systems, focusing on evolving strategies beyond traditional fault analysis to accommodate modern grid complexities. Historically, alarm processing has predominantly aimed at fault analysis, increasingly merging with technological advances in communication and computing. However, it still needs to fully meet the challenges posed by the dynamic characteristics of modern power systems. This review points out certain inadequacies in current practices, notably their limited adaptation to new grid conditions. The authors propose a novel generation of alarm processing methodologies designed for future grids, emphasizing managing rare events and enhancing operator decision-making through advanced anomaly detection and explainable artificial intelligence. This synthesis presents a prospective direction for future research and applications in alarm processing, advocating for methodologies better suited to supporting system operators amidst technological advancements. [ABSTRACT FROM AUTHOR]

Background: The future of smart factories and pharmaceutical industries has evolved significantly since the 19th century. Computers have been used in the pharmaceutical field since the 1980s with the emergence of Artificial Intelligence (AI). In addition, automation and robotics are used in the pharmaceutical industry to improve the efficiency of pharmaceutical development and production. Purpose: The present review article covers the future roles of AI, automation and robotics in pharmaceutical industries. Methodology: The current review article employed a comprehensive search strategy across relevant databases, including PubMed, Scopus and Web of Science, utilizing keywords such as AI, Automation, Robotics and Pharmaceutical Industries. The articles considered a focus on recent advancements and emerging trends in the intersection of AI, automation and robotics within pharmaceutical sectors. Results: AI, incorporating predictive machine learning and reasoning techniques, aids in the preclinical identification of molecules and forecasting potential lead compounds before conducting clinical trials. automation offers significant benefits in monitoring and predictive maintenance of production lines, power distribution and control machines. Robotic process automation improves efficiency by connecting computer terminals to handle various manufacturing process elements. Conclusion: Artificial intelligence, automation and Robotics have sparked innovations in the healthcare business, benefiting the global ecosystem and healthcare delivery. Incorporating these advanced tools in pharmaceutical industries from raw material selection to final product development could improve the quality and safety of the pharmaceutical products and reduce the time and cost. [ABSTRACT FROM AUTHOR]

The electrophysiological basis of emotion regulation (ER) has gained increased attention since efficient emotion recognition and ER allow humans to develop high emotional intelligence. However, no methodological standardization has been established yet. Therefore, this paper aims to provide a critical systematic review to identify experimental methodologies that evoke emotions and record, analyze and link electrophysiological signals with emotional experience by statistics and artificial intelligence, and lastly, define a clear application of assessing emotion processing. A total of 42 articles were selected after a search based on six scientific browsers: Web of Science, EBSCO, PubMed, Scopus, ProQuest and ScienceDirect during the first semester of 2020. Studies were included if (1) electrophysiological signals recorded on human subjects were correlated with emotional recognition and/or regulation; (2) statistical models, machine or deep learning methods based on electrophysiological signals were used to analyze data. Studies were excluded if they met one or more of the following criteria: (1) emotions were not described in terms of continuous dimensions (valence and arousal) or by discrete variables, (2) a control group or neutral state was not implemented, and (3) results were not obtained from a previous experimental paradigm that aimed to elicit emotions. There was no distinction in the selection whether the participants presented a pathological or non-pathological condition, but the condition of subjects must have been efficiently detailed for the study to be included. The risk of bias was limited by extracting and organizing information on spreadsheets and participating in discussions between the authors. However, the data size selection, such as the sample size, was not considered, leading to bias in the validity of the analysis. This systematic review is presented as a consulting source to accelerate the development of neuroengineering-based systems to regulate the trajectory of emotional experiences early on. [ABSTRACT FROM AUTHOR]

The classical formulation of the transmission switching problem as a mixed‐integer problem is intractable for large systems in real‐time control settings. Several heuristics have been proposed in the past to speed up the computation time, which only limits the number of switchable lines. In this paper, a real‐time switching heuristic based on neural networks that provides almost instantaneous switching actions, are presented. The findings are shown on case studies of the IEEE 118‐bus test system, and the results show that the proposed heuristic is robust to out of distribution data. Additionally, the proposed heuristic has significant computational savings while all other performance metrics like accuracy are similar to state‐of‐the‐art machine learning methods proposed for transmission switching. [ABSTRACT FROM AUTHOR]

Hydrogen energy is a promising renewable resource for the sustainable development of society. As a key member of the fuel cell (FC) family, the solid oxide fuel cell (SOFC) has attracted a lot of attention because of characteristics such as having various sources as fuel and high energy conversion efficiency, and being pollution-free. SOFC is a highly coupled, nonlinear, and multivariable complex system, and thus it is very important to design an appropriate control strategy for an SOFC system to ensure its safe, reliable, and efficient operation. This paper undertakes a comprehensive review and detailed summary of the state-of-the-art control approaches of SOFC. These approaches are divided into eight categories of control: proportional integral differential (PID), adaptive (APC), robust, model predictive (MPC), fuzzy logic (FLC), fault-tolerant (FTC), intelligent and observer-based. The SOFC control approaches are carefully evaluated in terms of objective, design, application/scenario, robustness, complexity, and accuracy. Finally, five perspectives are proposed for future research directions. [ABSTRACT FROM AUTHOR]

Purpose: The benefits of artificial intelligence (AI) related technologies for manufacturing firms are well recognized, however, there is a lack of industrial AI (I-AI) maturity models to enable companies to understand where they are and plan where they should go. The purpose of this study is to propose a comprehensive maturity model in order to help manufacturing firms assess their performance in the I-AI journey, shed lights on future improvement, and eventually realize their smart manufacturing visions. Design/methodology/approach: This study is based on (1) a systematic review of literature on assessing I-AI-related technologies to identify relevant measured indicators in the maturity model, and (2) semi-structured interviews with domain experts to determine maturity levels of the established model. Findings: The I-AI maturity model developed in this study includes two main dimensions, namely "Industry" and "Artificial Intelligence", together with 12 first-level indicators and 35 second-level indicators under these dimensions. The maturity levels are divided into five types: planning level, specification level, integration level, optimization level, and leading level. Originality/value: The maturity model integrates indicators that can be used to assess AI-related technologies and extend the existing maturity models of smart manufacturing by adding specific technical and nontechnical capabilities of these technologies applied in the industrial context. The integration of the industry and artificial intelligence dimensions with the maturity levels shows a road map to improve the capability of applying AI-related technologies throughout the product lifecycle for achieving smart manufacturing. [ABSTRACT FROM AUTHOR]

Artificial intelligence has the potential to revolutionize modern society in all its aspects. Encouraged by the variety and vast amount of data that can be gathered from patients (e.g., medical images, text, and electronic health records), researchers have recently increased their interest in developing AI solutions for clinical care. Moreover, a diverse repertoire of methods can be chosen towards creating performant models for use in medical applications, ranging from disease prediction, diagnosis, and prognosis to opting for the most appropriate treatment for an individual patient. In this respect, the present paper aims to review the advancements reported at the convergence of AI and clinical care. Thus, this work presents AI clinical applications in a comprehensive manner, discussing the recent literature studies classified according to medical specialties. In addition, the challenges and limitations hindering AI integration in the clinical setting are further pointed out. [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) plays a significant part in artificial intelligence and computer vision. However, most of facial expression recognition methods have not obtained satisfactory results based on low-level features. The existed methods used in facial expression recognition encountered the major issues of linear inseparability, large computational burden, and data redundancy. To obtain satisfactory results, we propose an innovative deep learning (DL) model using the kernel entropy component analysis network (KECANet) and directed acyclic graph support vector machine (DAGSVM). We use the KECANet in the feature extraction stage. In the stage of output, binary hashing and blockwise histograms are adopted. We sent the final output features to the DAGSVM classifier for expression recognition. We test the performance of our proposed method on three databases of CK+, JAFFE, and CMU Multi-PIE. According to the experiment results, the proposed method can learn high-level features and provide more recognition information in the stage of training, obtaining a higher recognition rate. [ABSTRACT FROM AUTHOR]

This paper presents a new fault detection system in hypnotic sensors used for general anesthesia during surgery. Drug infusion during surgery is based on information received from patient monitoring devices; accordingly, faults in sensor devices can put patient safety at risk. Our research offers a solution to cope with these undesirable scenarios. We focus on the anesthesia process using intravenous propofol as the hypnotic drug and employing a Bispectral Index (BISTM) monitor to estimate the patient's unconsciousness level. The method developed identifies BIS episodes affected by disturbances during surgery with null clinical value. Thus, the clinician--or the automatic controller--will not take those measures into account to calculate the drug dose. Our method compares the measured BIS signal with expected behavior predicted by the propofol dose provider and the electromyogram (EMG) signal. For the prediction of the BIS signal, a model based on a hybrid intelligent system architecture has been created. The model uses clustering combined with regression techniques. To validate its accuracy, a dataset taken during surgeries with general anesthesia was used. The proposed fault detection method for BIS sensor measures has also been verified using data from real cases. The obtained results prove the method's effectiveness. [ABSTRACT FROM AUTHOR]

By monitoring a hydraulic system using artificial intelligence, we can detect anomalous data in a manufacturing workshop. In addition, by analyzing the anomalous data, we can diagnose faults and prevent failures. However, artificial intelligence, especially deep learning, needs to learn much data, and it is often difficult to get enough data at the real manufacturing site. In this paper, we apply augmentation to increase the amount of data. In addition, we propose real-time monitoring based on a deep-learning model that uses convergence of a convolutional neural network (CNN), a bidirectional long short-term memory network (BiLSTM), and an attention mechanism. CNN extracts features from input data, and BiLSTM learns feature information. The learned information is then fed to the sigmoid classifier to find out if it is normal or abnormal. Experimental results show that the proposed model works better than other deep-learning models, such as CNN or long short-term memory (LSTM). [ABSTRACT FROM AUTHOR]

A vast majority of the archaeological record, globally, is understudied and increasingly threatened by climate change, economic and political instability, and violent conflict. Archaeological data are crucial for understanding the past, and as such, documentation of this information is imperative. The development of machine intelligence approaches (including machine learning, artificial intelligence, and other automated processes) has resulted in massive gains in archaeological knowledge, as such computational methods have expedited the rate of archaeological survey and discovery via remote sensing instruments. Nevertheless, the progression of automated computational approaches is limited by distinct geographic imbalances in where these techniques are developed and applied. Here, I investigate the degree of this disparity and some potential reasons for this imbalance. Analyses from Web of Science and Microsoft Academic searches reveal that there is a substantial difference between the Global North and South in the output of machine intelligence remote sensing archaeology literature. There are also regional imbalances. I argue that one solution is to increase collaborations between research institutions in addition to data sharing efforts. [ABSTRACT FROM AUTHOR]