Search

• Five Machine Learning (ML) models compared for wave height time series prediction. • Complex ML models do not outperform simple AR in wave height time series prediction. • Comment to related papers: signal decomposition in test set series is WRONG. Significant Wave Height (SWH) is crucial in many aspect of ocean engineering. The accurate prediction of SWH has therefore been of immense practical value. Recently, Artificial Intelligence (AI) time series prediction methods have been widely used for single-point short-term SWH time-series forecasting, resulting in many AI-based models claiming to achieve good results. However, the extent to which these complex AI models can outperform traditional methods has largely been overlooked. This study compared five different models - AutoRegressive (AR), eXtreme Gradient Boosting (XGB), Artificial Neural Network (ANN), Long Short-Term Memory (LSTM), and WaveNet - for their performance on SWH time series prediction at 16 buoy locations. Surprisingly, the results suggest that the differences of performance among different models are negligible, indicating that all these AI models have only "learned" the linear auto-regression from the data. Additionally, we noticed that many recent studies used signal decomposition method for such time series prediction, and most of them decomposed the test sets, which is WRONG. [ABSTRACT FROM AUTHOR]

In the framework of Space Traffic Management (STM) the growing number of space debris and the consequent increased risk of collisions have become a topic of great interest. Moreover, the difficulty of detecting and characterizing a Resident Space Object (RSO) in terms of orbital parameters makes this research field very challenging. In most cases the available observations have a very short duration and an accurate estimation of the orbit is very difficult. This paper introduces the Initial Orbit Determination via Artificial intelligence (IODA) algorithm, a reliable and accurate orbit estimator combining metaheuristic and artificial intelligence frameworks to perform precise orbit determination from Very Short Arcs (VSAs). Starting from an initial orbit estimate derived through an Artificial Bee Colony (ABC) algorithm, a Physics Informed Extreme Learning Machine is employed to increase the accuracy of the predicted orbit. Results on simulated data have shown the robustness of the algorithm to random parameters initialization and a percentage of success of 89% of retrieving the reference orbit with an error under 1 km and 0.01 km/s on the initial target's state. • Description of an AI-based orbit determination tool from very short arcs. • Combination of meta-heuristic and machine learning techniques for accurate orbit estimation. • Tests on simulated data for robustness against random parameters initialization. • Montecarlo simulation on simulated data for robustness against random mission scenarios. [ABSTRACT FROM AUTHOR]

As a promising strategy to mitigate carbon emissions, hydrogen enrichment of conventional fuels is gaining increasing interest, but can lead to increased propensity to damaging thermoacoustic instability. This paper demonstrates the ability of machine learning algorithms to reliably predict a key flame behavior relevant to thermoacoustic stability prediction – the flame's nonlinear response to upstream acoustic forcing. Using computational simulations of a laminar premixed flame under difference hydrogen enrichment and equivalence ratio conditions, training data for machine learning are generated. The machine learning models are then used to predict the flame response under new test conditions, including extrapolating into new hydrogen enrichment regimes. The effect of algorithm choice, data structure, data size, and extrapolation distance on the performance of different machine learning models is investigated with particular attention to performance with sparse training data. It is found that a type of neural network known as the multi-layer perceptron (MLP) model outperforms the Gaussian process and random forest models in both interpolation and extrapolation tasks. A physics-informed preprocessing strategy, involving extracting the time delay of the flame response (which can be deduced from geometry and flow parameters) prior to applying machine learning, is found to remarkably improve the accuracy of machine learning models, especially in extrapolation tasks. When the extrapolation into new hydrogen content levels is strong enough, the MLP model no longer performs well. However, for small and intermediate extrapolation, the MLP model shows a commendable level of prediction, even with small data sets, fulfilling needs relevant to thermoacoustic stability prediction. Extending the MLP model to experimental data from turbulent flames, the gain fall-off frequency and phase lag are accurately predicted but not the secondary periodic fluctuations in gain. • AI-assisted prediction of flame response in new hydrogen enrichment regimes. • A physics-informed strategy extracting the time delay improves model performance. • The effects of algorithm choice, data structure and data size are studied. • MLP model shows good predictions in small extrapolation tasks with sparse data. • Extending to turbulent flames, the MLP model captures fall-off frequency in gain. [ABSTRACT FROM AUTHOR]

Traumatic brain injury (TBI) has become a major source of disability worldwide, increasing the interest in algorithms that use artificial intelligence (AI) to optimize the interpretation of imaging studies, prognosis estimation, and critical care issues. In this study we present a bibliometric analysis and mini-review on the main uses that have been developed for TBI in AI. The results informing this review come from a Scopus database search as of April 15, 2023. The bibliometric analysis was carried out via the mapping bibliographic metrics method. Knowledge mapping was made in the VOSviewer software (V1.6.18), analyzing the "link strength" of networks based on co-occurrence of key words, countries co-authorship, and co-cited authors. In the mini-review section, we highlight the main findings and contributions of the studies. A total of 495 scientific publications were identified from 2000 to 2023, with 9262 citations published since 2013. Among the 160 journals identified, The Journal of Neurotrauma, Frontiers in Neurology , and PLOS ONE were those with the greatest number of publications. The most frequently co-occurring key words were: "machine learning", "deep learning", "magnetic resonance imaging", and "intracranial pressure". The United States accounted for more collaborations than any other country, followed by United Kingdom and China. Four co-citation author clusters were found, and the top 20 papers were divided into reviews and original articles. AI has become a relevant research field in TBI during the last 20 years, demonstrating great potential in imaging, but a more modest performance for prognostic estimation and neuromonitoring. [ABSTRACT FROM AUTHOR]

Transcatheter aortic valve replacement (TAVR) is increasingly performed for the treatment of aortic stenosis. Computed tomography (CT) analysis is essential for pre-procedural planning. Currently available software packages for TAVR planning require substantial human interaction. We describe development and validation of an artificial intelligence (AI) powered software to automatically rend anatomical measurements and other information required for TAVR planning and implantation. Automated measurements from 100 CTs were compared to measurements from three expert clinicians and TAVR operators using commercially available software packages. Correlation coefficients and mean differences were calculated to assess precision and accuracy. AI-generated annular measurements had excellent agreements with manual measurements by expert operators yielding correlation coefficients of 0.97 for both perimeter and area. There was no relevant bias with a mean difference of −0.07 mm and − 1.4 mm2 for perimeter and area, respectively. For the ascending aorta measured 5 cm above the annular plane, correlation coefficient was 0.95 and mean difference was 1.4 mm. Instruction for use-based sizing yielded agreement with the effective implant size in 87–88 % of patients for self-expanding valves (perimeter-based sizing) and in 88 % for balloon-expandable valves (area-based sizing). A fully automated software enables accurate and precise anatomical segmentation and measurements required for TAVR planning without human interaction and with high reliability. • Pre-procedural computed tomography analysis is essential for pre-procedural TAVR planning. • With increasing number of procedures performed, time spent to analyze TAVR CTs increases in parallel. • We developed a cloud-based, AI-driven software enabling fully automated and precise TAVR CT analysis. • In this paper, we compared these automated measurements to human expert measurements. • Correlation coefficients for annular perimeter/area and the ascending aorta ranged from 0.95-0.97. [ABSTRACT FROM AUTHOR]

Advances in artificial intelligence (AI) and automated robotics will profoundly influence space operations. By utilising machine learning and deep learning approaches, AI-enabled systems may accomplish tasks as well as improve their own performance. These capabilities are useful in the often-remote settings of outer space and will grow in value as automated space operations become more widespread. As AI extends throughout the space domain, automated algorithms will take on many of the roles that have historically been handled by humans. Artificial intelligence is progressing from theory to implementation in the space environment by exposing new satellites and orbital autonomous vehicles to new data. Even though all initial computational parameters are provided, such systems' outputs can be very unpredictable, putting people, property, and the environment at risk. This paper investigates the application of United Nations space treaties, selected regional AI regulations, and various 'soft-law' instruments and industry initiatives focusing on responsible AI system development to space-based AI systems. Following that, reforms are proposed to clarify the practical relationship between AI systems and the international legal regime that governs space, as well as a 'bottom-up' regulatory approach to better facilitate the future development of regulation governing the use of AI by the global space sector. While this work does not purport to provide a conclusive resolution to these multifaceted matters, its objective is to underscore significant obstacles that arise at the convergence of space law and AI, serving as a preliminary foundation for subsequent discussions on this issue. • Advances in AI and automated robotics will have a profound impact on space operations. Automated algorithms will take on roles traditionally handled by humans as AI becomes more widespread in space. • However, the unpredictable outputs of AI systems can put people, property, and the environment at risk, raising questions about liability. • The paper investigates the application of UN space treaties, regional AI regulations, and industry initiatives to space-based AI systems. • Reforms are proposed to clarify the relationship between AI systems and the international legal regime governing space. • A 'bottom-up' regulatory approach is suggested to facilitate future regulation of AI in the global space sector. [ABSTRACT FROM AUTHOR]

With the ever increasing number of active satellites in space, the rising demand for larger formations of small satellites and the commercialization of the space industry (so-called New Space), the realization of manufacturing processes in orbit comes closer to reality. Reducing launch costs and risks, allowing for faster on-demand deployment of individually configured satellites as well as the prospect for possible on-orbit servicing for satellites makes the idea of realizing an in-orbit factory promising. In this paper, we present a novel approach to an in-orbit factory of small satellites covering a digital process twin, AI-based fault detection, and teleoperated robot-control, which are being researched as part of the "AI-enabled Cyber–Physical In-Orbit Factory" project. In addition to the integration of modern automation and Industry 4.0 production approaches, the question of how artificial intelligence (AI) and learning approaches can be used to make the production process more robust, fault-tolerant and autonomous is addressed. This lays the foundation for a later realization of satellite production in space in the form of an in-orbit factory. Central aspect is the development of a robotic AIT (Assembly, Integration and Testing) system where a small satellite could be assembled by a manipulator robot from modular subsystems. Approaches developed to improving this production process with AI include employing neural networks for optical and electrical fault detection of components. Force sensitive measuring and motion training helps to deal with uncertainties and tolerances during assembly. An AI-guided teleoperated control of the robot arm allows for human intervention while a Digital Process Twin represents process data and provides supervision during the whole production process. Approaches and results towards automated satellite production are presented in detail. • An automated production system for modular small satellites is proposed. • Central element is a force-sensitive robotic assembly, integration & testing system. • AI and machine learning approaches are applied to make the process more robust. • A digital process twin supervises the autonomous production. • A multi-modal shared control approach allows human teleoperation if required. [ABSTRACT FROM AUTHOR]

• In clinical needle EMG interpretation, conventional machine learning methods were more often studied than deep learning methods. • Most studies developed models for classification of contraction signals and a few addressed the classification of rest signals. • Current research has methodological shortcomings, which prevent clinical implementation, but are surmountable. This scoping review provides an overview of artificial intelligence (AI), including machine and deep learning techniques, in the interpretation of clinical needle electromyography (nEMG) signals. A comprehensive search of Medline, Embase and Web of Science was conducted to find peer-reviewed journal articles. All papers published after 2010 were included. The methodological quality of the included studies was assessed with CLAIM (checklist for artificial intelligence in medical imaging). 51 studies were identified that fulfilled the inclusion criteria. 61% used open-source EMGlab data set to develop models to classify nEMG signal in healthy, amyotrophic lateral sclerosis (ALS) and myopathy (25 subjects). Only two articles developed models to classify signals recorded at rest. Most articles reported high performance accuracies, but many were subject to bias and overtraining. Current AI-models of nEMG signals are not sufficient for clinical implementation. Suggestions for future research include emphasizing the need for an optimal training and validation approach using large datasets of clinical nEMG data from a diverse patient population. The outcomes of this study and the suggestions made aim to contribute to developing AI-models that can effectively handle signal quality variability and are suitable for daily clinical practice in interpreting nEMG signals. [ABSTRACT FROM AUTHOR]

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the "interpretability spectrum". The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. It is found that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner. [ABSTRACT FROM AUTHOR]

Trajectory-based fishing vessel behavior recognition is currently a vibrant and dynamic area of investigation within transportation and maritime research. It can provide crucial technical support for combating illegal, unreported, and unregulated (IUU) fishing. Nevertheless, existing studies typically rely on extensive datasets of pre-labeled data to train machine learning models. The acquisition of these labeled datasets is frequently a time-consuming and complicated endeavor, which presents challenges in the practical application. Hence, this paper develops a semi-supervised approach for fishing vessel behavior identification using a small amount of manually labeled trajectory samples. Besides, given that the common vessel behavioral feature parameters provide limited insight into fishing activities, this paper innovatively proposes a set of descriptive trajectory feature parameters. Based on the morphological characteristics of fishing activities and domain knowledge, the proposed trajectory features excel in discerning the intricate pattern of fishing vessel trajectories. Combined with a set of Long Short-Term Memory (LSTM)-based encoding trajectory features, a composed feature engineering scheme that leverages both human intelligence and machine intelligence is proposed. The clustering experiment result confirms that our trajectory feature scheme can successfully recognize different fishing vessel behaviors while the conventional trajectory features can't. In the consequently classification tests, the 90% accuracy achieved by the composed feature scheme exhibits a 10% increase compared to solely using deep learning-based encoding features. This novel trajectory feature engineering method together with the semi-supervised machine learning structure, not reliant on extensive labeled datasets, can be tailored and applied to mobility pattern identification across various domains. • Develop a semi-supervised approach for fishing vessel behavior identification. • Propose a set of descriptive trajectory feature parameters based on domain knowledge. • Combine both human and machine intelligence to compose the feature engineering. • The developed approach identifies fishing vessel behavior with over 90% accuracy. [ABSTRACT FROM AUTHOR]

Alleviating cybersecurity risks associated with centralized AI training and implementation is a burgeoning challenge in the construction industry. This paper addresses two primary questions: (1) What is the knowledge of AI security vulnerability in construction, and (2) How can AI be decentralized using blockchain? To this end, this paper proposes a blockchain-AI integrated framework (BAII), enabling AI to be trained, verified, and applied on a decentralized blockchain. The framework has been successfully validated in an excavator pose recognition scenario, demonstrating acceptable latency and high performance with 95 % accuracy, 94 % precision, and 96 % recall. This research is pivotal for construction managers and IT security professionals, enhancing the reliability and safety of AI applications in construction. The decentralized AI (DAI) approach can also inspire further research into motivating constructors to contribute to AI modeling and training through incentive mechanisms in the blockchain. • Proposed an AI lifecycle management mechanism in a decentralized environment based on ISO/IEC 23894:2023. • Proposed a blockchain-AI integrated (BAII) framework for secure artificial intelligence (AI) in excavator pose recognition. • Developed an AI-enabled smart contract structure in BAII framework for decentralized data training and classification. • Developed a reinforced signing strategy to safeguard the integrity and immutability of AI dependencies in blockchain. • AI performance in the decentralized environment is acceptable with 95 % accuracy, 94 % precision, and 96 % recall. [ABSTRACT FROM AUTHOR]

Artificial intelligence and its subfields, such as machine learning, robotics, optimisation, knowledge-based systems, reality capture and extended reality, have brought remarkable advancements and transformative changes to various industries, including the building deconstruction industry. Acknowledging AI's benefits for deconstruction, this paper aims to investigate AI applications within this domain. A systematic review of existing literature focused on AI applications for planning, implementation and post-implementation activities within the context of deconstruction was carried out. Furthermore, the challenges and opportunities of AI for deconstruction activities were identified and presented in this paper. By offering insights into AI's application for key deconstruction activities, this paper paves the way for realising AI's potential benefits for this sector. • Artificial intelligence, types, and subfields in deconstruction. • AI applications in planning, implementation, and post-implementation activities. • Challenges of adopting AI in the deconstruction industry. • Potential opportunities of AI in deconstruction. • Future studies like extended reality, digital twins, and generative AI. [ABSTRACT FROM AUTHOR]

This study explores the potential of Precision Agriculture (PA) and Smart Farming (SF) using cutting-edge technologies like Artificial Intelligence (AI), the Internet of Things (IoT), and Unmanned Aerial Vehicles (UAVs) to address global challenges such as food shortages and population growth. The research focuses on recent developments in SF, including data collection, analysis, visualization and viable solutions, highlighting the role of IoT and 5G networks. The paper also discusses the application of robots and UAVs in agricultural tasks, showcasing their integration with IoT, AI, Deep Learning (DL), Machine Learning (ML), and wireless communications. Moreover, Smart Decision Support Systems (SDSS) are explored for real-time soil analysis and decision-making. The study underscores the significance of these technologies in PA, propelling traditional farming practices into an era of intelligent and sustainable farming solutions. This Overview is grounded in a thorough analysis of 80 recent research articles, covering the period from 2019 to 2023, within the domain of SF. This study highlights notable trends and advancements in this ever-evolving sector. Furthermore, this paper delves into the nuances of addressing particular challenges prevalent in developing nations, strategies aimed at surmounting constraints related to infrastructure and resource availability, and the pivotal role of governmental and private sector support in fostering the growth of Smart Agriculture (SA). [ABSTRACT FROM AUTHOR]

An increase in population leads to an increase in the water demand. Technological advancements are racing to address water shortages. Recent advances in deep learning (DL), machine learning (ML), and artificial intelligence (AI) have enabled us to effectively manage water scarcity as well as optimize, model, automate, and predict water treatment processes. Additionally, computer-assisted support to complicated problems related to water chemistry, and membrane applications. In the sector of water treatment and desalination processes, various models such as Support Vector Machines (SVM), Random Forest (RF), Genetic Algorithms (GA), K-Nearest Neighbors (KNN), time series models, and Multi-Layer Perceptron (MLP) have been applied to address the issues ranging from optimization of treatment processes to predictive modeling as well as failure/fault detection. Presently, water quality forecasting lacks the much-needed precision and accuracy. Thus, a highly versatile MLP is engineered and designed to approximate any continuous functions and may solve issues that are not linearly separable. Typically, MLPs are used for pattern classification, forecasting performance, and approximation. This review paper presents automatic forecasting of water quality and desalination processes efficiency which resolves the issue of missing values from the data sets. Moreover, this paper examines a wide range of peer-reviewed, vital water-based applications using DL, ML, and AI, including membrane separation, water quality, and performance efficiency. A thorough review of MLP applications in water treatment and seawater desalination is presented here. Furthermore, the conventional modeling approaches are compared with the MLP model. It will also highlight the drawbacks that hinder the implementation of real-world water treatment and desalination processes. In conclusion, the latest developments in membrane processes, seawater desalination, and MLP-based water treatment have been summarised. [Display omitted] • Revolutionizing water treatment and desalination using MLP. • MLP model is an engineered tool for self-monitoring and accurate prediction. • Comparative study of traditional models and MLPs. • Limitations of traditional and MLP modeling approaches. • Water quality forecasting using MLP models for water treatment and desalination processes. [ABSTRACT FROM AUTHOR]

Despite the widespread application of data-centric techniques in Geotechnical Engineering, there is a rising need for building trust in the artificial intelligence (AI)-driven safety assessment of road embankments due to its so-called "black-box" nature. In addition, from the lens of limit equilibrium approaches, e.g., Bishop, Fellenius, Janbu and Morgenstern–Price, and finite element method, it is essential to carefully examine the interplay of both topological and physical/mechanical properties during the safety factor (FoS) predictions. First, aside from having conventional geotechnical inputs for soil in core and foundation and the height of embankments, this paper codifies geometric features innovatively. The number of slope types with different ratios including 1:1, 1.5:1 and 2:1 as well as the number of berms is introduced. Second, a pool of 19 machine learning (ML) techniques is effortlessly trained on the dataset using an automated ML (AutoML) pipeline to identify the most optimized ML algorithm. Finally, to achieve post-hoc interpretability for the internal mechanism of the input–output relationship unbiasedly, a game-theory-based explainable AI (XAI) method called Shapley additive explanations (SHAP) values is applied. SHAP-aided importance analysis provides human-interpretable insights and indicates height, California bearing ratio, slope type 2:1 and cohesion as the most influential parameters. Exclusively, analyzing hazardous embankments by classifying main and joint contributors exhibits a complex and highly variable influence on the FoS. This paper harnesses the power of XAI tools to enhance reliability and transparency for the rapid FoS prediction of slopes. It targets geotechnical researchers, practitioners, decision-makers, and the general public for the first time. • Shedding light on the AI-aided slope stability analysis with SHAP values. • Coupling AutoML and XAI for reliable and easy-to-use FoS prediction of embankments. • Defining novel geometric parameters to capture their impact on geotechnical ones. • Categorizing unstable embankments from the global and local XAI perspectives. • Analyzing hazardous embankments by classifying main and joint contributors. [ABSTRACT FROM AUTHOR]

In recent years, multi-agent reinforcement learning techniques have been widely used and evolved in the field of artificial intelligence. However, traditional reinforcement learning methods have limitations such as long training time, large sample data requirements, and highly delayed rewards. Therefore, this paper systematically and specifically studies the MARL algorithm. Firstly, this paper uses Citespace software to visually analyze the existing literature on multi-agent reinforcement learning and briefly indicates the research hotspots and key research directions in this field. Secondly, the applications of traditional reinforcement learning algorithms under two task objects, namely single-agent and multi-agent systems, are described in detail. Then, the paper highlights the diverse applications, challenges, and corresponding solutions of MARL algorithmic techniques in the field of MAS. Finally, the paper points out future research directions based on the existing limitations of the algorithm. Through this paper, readers will gain a systematic and in-depth understanding of MARL algorithms and how they can be utilized to better address the various challenges posed by MAS. [ABSTRACT FROM AUTHOR]

This paper investigates applying AI models and topic modelling techniques to enhance computational literature reviews in business, management, and information systems. The study highlights the significance of impactful journals and emphasises the need for interdisciplinary and transdisciplinary research, especially in addressing AI's ethical and regulatory challenges. We demonstrate the effectiveness of combining machine learning and ChatGPT in the literature review process. Machine learning is used to identify research topics, and ChatGPT assists researchers in labelling the topics, generating content, and improving the efficiency of academic writing. By leveraging topic modelling techniques and ChatGPT, we uncover and label topics within the literature, shedding light on the thematic structure and content of the research field, allowing researchers to uncover meaningful insights, identify research gaps, and highlight rapidly expanding research areas. Additionally, we contribute to the literature review process by introducing a methodology that identifies impactful papers, helping to bridge the gap between computational literature reviews and traditional literature reviews. [ABSTRACT FROM AUTHOR]

Concept-cognitive learning (CCL), an emerging intelligence learning paradigm, has recently become a popular research subject in artificial intelligence and cognitive computing. A central notion of CCL is cognitive and learning things via concepts. In this process, concepts play a fundamental role when mining and fusing knowledge from data to wisdom. With the in-depth research and expansion of CCL in scopes, goals, and methodologies, some difficulties have gradually emerged, including some vague terminology, ambiguous views, and scattered research. Hence, a systematic and comprehensive review of the development process and advanced research about CCL is particularly necessary at the moment. This paper summarizes the theoretical significance, application value, and future development potential of CCL. More importantly, by synthesizing the reviewed related research, we can acquire some interesting results and answer three essential questions: (1) why examine a cognitive and learning framework based on concept? (2) what is the concept-cognitive learning? (3) how to make concept-cognitive learning? The findings of this work could act as a valuable guide for related studies in quest of a clear understanding of the closely related research issues around concept-cognitive learning. • It is the first paper that attempts to provide an in-depth analysis of the advancement of CCL. • It is a multi-view categorization of CCL in research scopes, goals, and methodologies. • It is an elucidation of the main research gaps and suggestions for the related study of CCL. • It acquires some interesting results by synthesizing the reviewed related research of CCL. [ABSTRACT FROM AUTHOR]

• This paper proposes a ship safety risk early warning model integrating transfer learning and multi-modal learning. • This model uses the transfer learning method to verify whether the data capabilities one area can be effectively applied in another area. • This model can alleviate the management pressure of maritime regulatory institutions. • This model can enhance the safety of the ship. An efficient risk warning model is crucial to the navigation safety of ships. However, existing researches are often limited by data acquisition, resulting in model training limited to specific sea areas, and data transferability among different sea areas has not been fully explored. Therefore, this paper studies the feasibility of some artificial intelligence methods in risk warning and the transferability of pre-trained models among different regions based on sizeable historical weather data sets, thus proposing a ship risk early warning model integrating transfer learning and multi-modal learning. This model integrates ship traffic flow data, weather data, ship accident data, ship parameters and other related data, and uses machine learning algorithms to pre-train the model to analyze possible risks to ship navigation safety driven by high-dimensional data. And discuss the generalization and transferability of the model based on transfer learning methods. Research results show that the ship navigation risk early warning model that integrates transfer learning and multi-modal learning can effectively identify ship navigation risks and has high accuracy in some transfer sea areas. This innovation has important practical significance in ship safety, improving global ship safety levels and providing more comprehensive and reliable decision-making support for risk management in the shipping industry. [ABSTRACT FROM AUTHOR]

The early detection of fuel leaks in filling stations is crucial to minimize environmental risks, such as soil and groundwater contamination. There are some commercial products for fuel leakage detection based on statistical analysis of data from station inventory books. Although they solve the tackled problem, they have some important drawbacks, such as their high price, and issues related to the privacy of station data, which must be shared with the company owning the reconciliation technology. In this work, a solution based on Artificial Intelligence is proposed to address this problem. Machine Learning techniques, specifically two-class supervised classifiers, are applied to data extracted from inventory books of real petrol stations. The classification models used in this paper are trained and tested with real data of days without leaks and simulated data of days with leaks. Thus, the more representative of reality these data are, the better the classifiers will work when implemented in a real filling station. In this sense, the most novel contribution of this paper is the way in which the training sets are constructed to achieve a realistic scenario. These sets are composed of time data windows in which the leak can begin on any day within the window, not necessarily on the first day, as the authors had assumed in a previous contribution. Therefore, they are mixed windows containing a variable number of non-leaking and leaking days. In addition, the design of these data sets complies with the requirements of the current European standard UNE-EN 13160–5. This allows the classifiers to work under even more realistic conditions and thus increase the practical applicability of their results. This work demonstrates that by using two-class classifiers it is possible not only to comply with the standard in terms of the maximum allowable ratio of false positives and false negatives, but also to detect the leak in a shorter time than that established in the norm. [Display omitted] • The detection of fuel leaks in petrol stations is approached as a classification problem. • In order to study compliance with current regulations it is essential to work in a scenario that is as realistic as possible. • Mixed time windows improve the reliability of the results regarding fuel leaks detection. • The proposed solution allows to accomplish the efficiency requirements of current regulations. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is a crucial detection technique extensively employed in various contexts demanding accurate identification of human actions. Currently, mainstream HAR approaches frequently rely on sequential data generated by wearable sensors, with a primary focus on extracting feature representations that align with various human activities. Nevertheless, complex and diverse human activities encompass various kinds of features and substantial variations in the features emphasized across different activities, making it challenging for current artificial intelligence methods to achieve accurate recognition. To address this challenge, this paper introduces a network framework called the Multi-Feature Combining Attention Neural Network (MFCANN). This framework incorporates diverse feature extraction, along with both local and global feature attention mechanisms. It is composed of stacked Multi-Feature Combining Attention Blocks (MFCAB) designed by us. In contrast to traditional convolutional methods, MFCAB parallelly stacks various convolutional components, enabling the extraction of a broader range of features from human activity data. Additionally, we propose the Intra-Module Attention Block (Intra-MAB) and the Inter-Module Attention Block (Inter-MAB), which simultaneously focus on local fine-grained features within module feature maps and global distinguishing features across module feature maps. This aims to achieve more targeted feature learning, reinforcing the network's ability to distinguish between different human activities. Abundant experimental results demonstrate that the proposed MFCANN in this paper outperforms current mainstream deep learning algorithms in HAR tasks, achieving recognition accuracies of 0.9813, 0.9324, and 0.9930 on the UCI-HAR, USC-HAD, and RealWorld datasets respectively. We release our code at https://github.com/RangerHeart/MFCANN. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is a crucial detection technique extensively employed in various contexts demanding accurate identification of human actions. Currently, mainstream HAR approaches frequently rely on sequential data generated by wearable sensors, with a primary focus on extracting feature representations that align with various human activities. Nevertheless, complex and diverse human activities encompass various kinds of features and substantial variations in the features emphasized across different activities, making it challenging for current artificial intelligence methods to achieve accurate recognition. To address this challenge, this paper introduces a network framework called the Multi-Feature Combining Attention Neural Network (MFCANN). This framework incorporates diverse feature extraction, along with both local and global feature attention mechanisms. It is composed of stacked Multi-Feature Combining Attention Blocks (MFCAB) designed by us. In contrast to traditional convolutional methods, MFCAB parallelly stacks various convolutional components, enabling the extraction of a broader range of features from human activity data. Additionally, we propose the Intra-Module Attention Block (Intra-MAB) and the Inter-Module Attention Block (Inter-MAB), which simultaneously focus on local fine-grained features within module feature maps and global distinguishing features across module feature maps. This aims to achieve more targeted feature learning, reinforcing the network's ability to distinguish between different human activities. Abundant experimental results demonstrate that the proposed MFCANN in this paper outperforms current mainstream deep learning algorithms in HAR tasks, achieving recognition accuracies of 0.9813, 0.9324, and 0.9930 on the UCI-HAR, USC-HAD, and RealWorld datasets respectively. We release our code at https://github.com/RangerHeart/MFCANN. [ABSTRACT FROM AUTHOR]

This paper proposes an innovative approach towards real-time earthquake forecasting in Chile by integrating intelligent technologies and machine learning methods. Earthquakes pose significant risks to communities and infrastructure in Chile, making accurate and timely forecasting crucial for disaster preparedness and mitigation. Traditional forecasting methods have limitations in providing real-time insights into seismic activity. In contrast, intelligent technologies such as artificial intelligence (AI) and machine learning offer promising avenues for enhancing prediction accuracy and speed. A new earthquake forecasting method using a modified clustering approach LMSCAN(Local Maxima-based Spatio-Cluster Analysis Network) and enhanced neural network time series analysis LSTM-IC (Long Short Term Memory Inverse Correlation) is presented in this paper. This neural network-based technology has been utilized to forecast earthquakes in the Chile region, one of the countries with the largest seismic activity. This study explores the integration of intelligent systems with machine learning algorithms to analyze seismic data and predict earthquake occurrences in Chile. By leveraging historical seismic data, sensor networks, and advanced predictive models, our approach aims to provide timely warnings and insights into seismic events, thereby improving disaster response and resilience. The proposed framework holds the potential to revolutionize earthquake forecasting by enabling real-time monitoring and proactive measures to safeguard communities and infrastructure in Chile and beyond. The remarkable 95 % accuracy achieved by this model is a testament to its exceptional learning process, which sets it apart from other models. Its ability to learn and adapt to new data is unparalleled, allowing it to forecast incredibly precisely and produce highly reliable results. [ABSTRACT FROM AUTHOR]

Big data, AI, and machine learning have ushered in a transformative era in computer processing and application. AI's capacity to emulate human cognition spans a spectrum of industries, from rudimentary tasks to intricate decision-making processes. Projections indicate that within a short span, AI technology will bestow computers with human-like capabilities, rendering it indispensable. This advancement has substantially bolstered industry autonomy, fortifying security and safety through the integration of electronics, internet connectivity, advanced algorithms, and cutting-edge processing chips. In this context, Automated Guided Vehicles (AGVs) leverage AI-powered systems and sensors to optimize performance and proactively thwart potential failures. Going beyond Advanced Driver Assistance Systems (ADAS), this review scrutinizes the broader spectrum of AI applications. Specifically, it synthesizes pertinent studies encompassing AI's impact on car emissions, predictive maintenance, security, and the realm of connected vehicles. While AGVs can utilize AI algorithms to chart emission-efficient routes and engineer energy-conservative vehicles, AI, through diverse algorithms, proficiently anticipates component failures, substantially enhancing the cost-effectiveness of predictive maintenance and bolstering vehicle reliability. Moreover, AI integrated with sensor technology safeguards vehicles against a spectrum of threats. Neural networks and machine learning further automate security measures for both cargo and passengers. Concurrently, AI and machine learning fortify traffic control and enhance vehicle communication within connected vehicle frameworks, albeit necessitating fortifications in data security, encryption, and system efficiency. This survey paper comprehensively covers the expanse of automotive AI and machine learning applications, extending beyond ADAS. It underscores that the evolving mobility landscape necessitates a thorough evaluation of network architecture, connectivity, and performance metrics, encompassing AGV technology, networking protocols, and swarm dynamics. In this vein, the paper advocates for experts to address existing literature gaps and proactively enhance automotive systems. [ABSTRACT FROM AUTHOR]

• This paper explores the capabilities of machine-learning based fault detection and diagnosis. • The scope of the research is narrowed to the identification of transient events. • The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system. The increasing interest in artificial intelligence and automation within the nuclear industry stems from the hope of elevating the safety and reliability of nuclear power plants by minimizing the impact of human errors. This paper explores the capabilities of machine-learning based fault detection and diagnosis (FDD) models in accurately classifying transient events in a nuclear power plant using the Classification Learners Application from MATLAB. The scope of the research is narrowed to the identification of transient events of the same nature occurring at various locations within the plant. To accomplish this, the Generic Pressurized Water Reactor (GPWR) from the Western Services Cooperation (WSC) was used to simulate 14 transients in the primary system and 10 transients in the secondary system, resulting in two distinct datasets of 108,000 and 79,200 observations. Nine types of classifiers, including Decision Trees, Discriminant Analysis, Support Vector Machines, Logistic Regression, Nearest Neighbors, Naive Bayes, Kernel Approximation, Ensembles, and Neural Networks, with a total of 33 predefined models, were trained and validated. The K-Nearest Neighbors model achieved the highest accuracy of 97% in the primary system, while the Efficient Linear Discriminant and Logistic Regression models achieved the highest average accuracy of 99% in the secondary system. The assessment of the top-performing models was conducted through a comprehensive analysis employing key classification model evaluation metrics, such as the confusion matrix, accuracy, precision, recall, and the F1 score. In an effort to optimize the models, the study integrated feature selection using the minimum Redundancy Maximum Relevance (mRMR) algorithm. Additionally, the investigation explored different validation schemes, including both holdout and k-fold cross-validation schemes, resulting in a substantial reduction in training time without significantly compromising the overall accuracy of the models. The optimized models in this study demonstrated remarkable prediction accuracies, consistently exceeding 94%. Despite the complexity of the models and the intricacies involved in the training process, the training times ranged from 10 to 1800 s, reflecting the efficiency and robustness of the implemented optimization techniques. The results of this study underscore the potential of machine learning models in identifying transient events in nuclear reactors, showcasing their promising capabilities while maintaining low computational and execution costs. This suggests their efficacy in optimizing safe and efficient operational practices within nuclear facilities. [ABSTRACT FROM AUTHOR]

One key driver of sustainable goal development is the transition to sustainable electricity resources. The sustainability impact assessment of power production evaluates all potential impacts on society, the environment, and the economy, as well as finds a reasonable solution to shift towards renewable. Given the multitude of quantitative and qualitative methodologies for sustainability analysis, alongside the absence of a unified procedure, selecting an appropriate method poses a significant challenge in conducting this task. Therefore, this paper conducts an extensive review of the methodologies employed for assessing the sustainability of power generation within the future energy mix, as reflected in scientific publications over the past decade (2013–2024). The main objective of this paper is to compare the methodologies and assess their efficiency as suitable tools for analyzing the sustainability of technologies in different geographical regions. The research methodology, following the screening process, selects 102 papers within the study's scope to undergo a critical examination based on sustainability evaluation approaches. It also provides an overview of novel dynamic methods and the application of artificial intelligence in sustainability assessment. The primary findings indicate a deficiency in a standardized approach for sustainability evaluation within electrical technology. In addressing uncertainties in impact assessment due to various parameters, dynamic methods with multiple temporal accuracies are recommended over a static life cycle. The paper includes a case study comparing methods—multi-criteria decision-making, and ranking, scoring—in the Indonesian context. Considering 15 environmental, social, and economic indicators to evaluate the sustainability in Lombok, results indicate that hydropower, gas, and solar technologies exhibit the highest sustainability scores, respectively. [ABSTRACT FROM AUTHOR]

Property valuation research, evolving with Automated Valuation Models (AVMs) using Artificial Intelligence (AI) and Machine Learning (ML), encounters challenges in handling dynamic market conditions. While the market approach is a practical solution to complement the AVMs, it also suffers from different deficiencies, particularly in relying on subjective valuer judgment. In Australia's diverse real estate market, complete and up-to-date market data derived from recent transactions of the different property types within various suburbs can be crucial for valuers. However, accessing such data often comes at a high cost, and the availability of transaction data is limited, mainly when market analysis necessitates the consideration of property valuation across various property types and bedroom counts. Accordingly, this paper presents a novel multi-step method to estimate the median prices of different property types considering their bedroom counts at the suburban level in the Melbourne Metropolitan area to benefit valuers when adopting the market approach. Nine distinct and ensembled spatially-based imputation techniques of K-Nearest Neighbors (KNN), Inverse Distance Weighted (IDW), Weighted KNN, Weighted IDW, Weighted KNN-IDW, Random Forest (RF), eXtreme Gradient Boosting (XGBoost), RF-IDW-KNN and XGBoost-IDW-KNN are first employed to impute missing data on six market-related parameters obtained from the Real Estate Institute of Victoria (REIV). These parameters include median price (with no consideration of bedroom counts), price change, median rent, rental yield, clearance rate and days on market for houses and units. Next, based on these parameters, three ML algorithms—RF, Support Vector Regression (SVR) and XGBoost—are developed to estimate the median prices. Subsequently, the Long Short-Term Memory (LSTM) technique is employed for Deep Learning (DL)-based spatiotemporal analysis, clustering suburbs based on property value fluctuations. Finally, these clusters are integrated into the ML models developed in the previous step as an auxiliary feature to assess their potential impact on enhancing price estimation accuracy. The results demonstrate promising accuracies for different property types based on different performance assessment metrics. The paper also underscores improved estimation accuracy by incorporating time series-based clustering as a supplementary parameter through transfer learning. [ABSTRACT FROM AUTHOR]

In the last years, the massive deployment of new photovoltaic (PV) power plants has launched the connection of PV inverters to the electrical network. A single medium-sized ground-mounted PV plant may have thousands of these inverters linked to the grid and even more PV panels on the DC side. Upon reaching such a substantial magnitude of devices involved in grid-connected installations, the effective operation, management, predictive maintenance, and fault detection becomes increasingly challenging without integrating advanced prediction and automated anomaly detection systems. Artificial intelligence algorithms, grounded in data measurements, can be pivotal in addressing this challenge. This paper proposes several regression-based methods to predict PV plants' energy generation, which is useful for detecting transient and long-term anomalies. These models are trained using a Recursive Least Squares (RLS) method and require a minimum number of variables to yield satisfactory outcomes, which is one of the paper's contributions. They mainly rely on energy generation measurements and geolocation. Within the scope of this research, two distinct algorithms have been implemented and validated. The first algorithm, a simplified model, is engineered to analyse the daily efficiency variation, prioritizing the identification of faults and abnormal operational profiles in PV plants. On the other hand, the second algorithm adopts a more intricate model tailored to facilitate long-term diagnosis, enabling the assessment of PV efficiency degradation. In this work, both algorithms are described and their performance is validated using the historical data from more than 20 PV plants placed in different climatic regions. • Photovoltaic systems' modelling using linear regression models. • Photovoltaic fault detection using linear regression coefficients evaluation. • Automatic fault detection for photovoltaic plants with low sensors' availability. • Short-term and long-term efficiency trend evaluation of photovoltaic plants. [ABSTRACT FROM AUTHOR]

Low computational cost artificial intelligence (AI) models are vital in promoting the accessibility of real-time medical services in underdeveloped areas. The recent Once-For-All (OFA) network (without retraining) can directly produce a set of sub-network designs with Progressive Shrinking (PS) algorithm; however, the training resource and time inefficiency downfalls are apparent in this method. In this paper, we propose a new OFA training algorithm, namely the Progressive Expansion (ProX) to train the medical image analysis model. It is a reversed paradigm to PS, where technically we train the OFA network from the minimum configuration and gradually expand the training to support larger configurations. Empirical results showed that the proposed paradigm could reduce training time up to 68%; while still being able to produce sub-networks that have either similar or better accuracy compared to those trained with OFA-PS on ROCT (classification), BRATS and Hippocampus (3D-segmentation) public medical datasets. The code implementation for this paper is accessible at: https://github.com/shin-wl/ProX-OFA. [ABSTRACT FROM AUTHOR]

This paper investigates the specific properties of Explainable Artificial Intelligence (xAI), particularly when implemented in AI/ML models across high-stakes sectors, in this case cybersecurity. The authors execute a comprehensive systematic review of xAI properties, various evaluation metrics, and existing frameworks to assess their utility and relevance. Subsequently, the experimental sections evaluate selected xAI techniques against these metrics, delivering key insights into their practical utility and effectiveness. The findings highlight that the proliferation of metrics enhances the understanding of xAI systems but simultaneously exposes challenges such as metric duplication, inefficacy, and confusion. These issues underscore the pressing need for standardized evaluation frameworks to streamline their application and strengthen their effectiveness, thereby improving the overall utility of xAI in critical domains. • Bridging xAI theory and practice. • Systematic review of xAI metrics and frameworks. • Experimental evaluation of various xAI explanations. • The results show many metrics are ine2ective. • The abundance of metrics has pros and cons. [ABSTRACT FROM AUTHOR]

[Display omitted] • Generative LLMs are slowly adopted in clinical trial eligibility parsing. • Standardized benchmarks for parsing eligibility criteria are urgently needed. • The use of pretrained language models and word embeddings is very limited. • The lack of high-quality datasets holds back the development of new NLP models. Automatic eligibility criteria parsing in clinical trials is crucial for cohort recruitment leading to data validity and trial completion. Recent years have witnessed an explosion of powerful machine learning (ML) and natural language processing (NLP) models that can streamline the patient accrual process. In this PRISMA-based scoping review, we comprehensively evaluate existing literature on the application of ML/NLP models for parsing clinical trial eligibility criteria. The review covers 9160 papers published between 2000 and 2024, with 88 publications subjected to data charting along 17 dimensions. Our review indicates insufficient use of state-of-the-art artificial intelligence (AI) models in the analysis of clinical protocols. [ABSTRACT FROM AUTHOR]

This paper presents an integrated Unmanned Aerial Vehicle (UAV) imagery system and artificial intelligence-based smart farming for saffron cultivation. This work is about monitoring the growth of saffron flowers through UAV imagery every week or month during the pre-harvesting time while the percentage of the covered area by leaf and saffron flowers is calculated. This is crucial for predicting saffron growing areas over cultivated regions. From the vertical viewing of UAV imagery from above, it is problematic from the bird's eye perspective to identify the particular saffron-growing areas of things, so the multi-class classification of flowers (subjects) recognition system is proposed. So, the implementation of this work is divided into four phases. The first two phases (Phase 1 and Phase 2) are about the algorithms for Saffron growing region detections and predictions using the modified You Only Look Once (YOLO) higher version model followed by statistical analysis based region corner detections. The outcomes of the first two phases are used to form a database of saffron flowers with different scales, orientations, and deformations. This is further used to build a two-class classification model in the third phase (Phase 3) that discriminates saffron vs. non-saffron flowers. In the fourth phase, the two-class classification model is extended to a multi-class flower recognition model for recognizing 900 flower images database available in the largest social media website dedicated exclusively to gardening in the Phase 4. Extensive experiments are conducted, and the performances are compared with some existing state-of-the-art methods that show the superiority of the proposed system. [ABSTRACT FROM AUTHOR]

Serverless computing has become very popular in recent times which facilitates a greater abstraction in virtualization technology. With the rapid development in serverless computing, a new paradigm has been evolved to design and develop android applications. However, the android platform has become one of the most vulnerable targets due to the increase in the number of users and hence raises a strong security concern to develop an advanced security framework. In this paper, a serverless computing based intelligent malware detection framework, called CloudIntellMal is proposed to detect malware targeting android-based applications. The framework incorporates some popular key cloud services such as Amazon Web Services (AWS) Elastic Cloud Compute (EC2) and Simple Storage Service (S3) to store and pre-process the logs taken from the end user devices. An efficient feature extraction algorithm is designed that employs 'Bag of n-grams' to develop feature vectors. The framework runs the machine learning algorithm in the cloud infrastructure to learn malicious patterns. The decision model is loaded in EC2 at the time of detection phase to classify the monitored apps. A prototype of the approach has been developed and validated using Drebin dataset and results seem to be promising. [ABSTRACT FROM AUTHOR]

Geopolymer has been identified as a promising family of sustainable construction materials alternative to cement-based materials. However, designing geopolymer utilizing solid wastes is a challenging task given the large variations of solid wastes in their physical and chemical properties. To overcome this challenge, this paper proposes a knowledge graph-guided data-driven approach to design geopolymer utilizing solid wastes, aimed at achieving high mechanical properties, low material cost, and low carbon emission, while largely improving material discovery efficiency. The proposed approach seamlessly integrates knowledge graph, machine learning, and multi-objective optimization, and has been utilized to design ultra-high performance geopolymer (UHPG). This approach has two main novelties: (1) The incorporation of knowledge graph imparts geopolymer domain knowledge, making the machine learning model interpretable and compliant with domain knowledge. (2) The consideration of physical and chemical properties of raw materials enables the utilization of various solid wastes. The results show that the proposed approach can reasonably predict geopolymer properties, interpret prediction results, and optimize UHPG design. • An artificial intelligence (AI) approach is presented to design geopolymer with solid wastes. • The AI approach achieves interpretability by combining machine learning and knowledge graph. • Knowledge about the physicochemical reactions and properties of geopolymer is imparted. • The AI approach is applied to low-carbon cost-effective ultra-high-performance geopolymer. • The AI approach can interpret the underlying mechanisms and generate new knowledge. [ABSTRACT FROM AUTHOR]

FPGAs facilitate prototyping and debug, and recently accelerate full-stack simulations due to their rapid turnaround time (TAT). However, this TAT is restrictive in exhaustive design space explorations of parameterized RTL generators, especially DNN accelerators that unleash an explosive full-stack search space. This paper presents Quickloop, an efficient and scalable framework to enable FPGA-accelerated exploration. Quickloop first abstracts away the cumbersome flow of RTL generation, software stack, FPGA toolflow, workload execution and metrics extraction by wrapping these stages into isolated Quicksteps, featuring cascadability, scalability, and replay. Then, we analytically minimize the FPGA toolflow TAT via a novel, data-driven strategy that intelligently utilizes build fragments from previous iterations, enhancing the loop efficiency and simultaneously lowering the toolflow's compute utilization. Quickloop is built around the OpenAI Gym environment framework and thus supports drop-in regression and reinforcement learning explorations. With a Quickloop around a reference Berkeley's Gemmini DNN accelerator, we exhaustively explore its parameter space and discover complex performance patterns, based on full-stack simulation of Imagenet benchmarks as a workload. Compared to conventional FPGA toolflow, we further show that Quickloop effectively reduces episodal time by above 30%, as the episode approaches realistic lengths. • Machine Learning. • Accelerators. • Systolic Array. • Design Space Exploration. [ABSTRACT FROM AUTHOR]

A machine learning approach was used to evaluate the laser beam quality. Nowadays, the beam characterization is performed in a manual manner and with the use of custom setups typically built by the laser owners. The effort, knowledge requirement and the fact that the evaluation process must be conducted by a skillful man prevent laser beam diagnostics to be implemented on a mass scale in industrial, medical and scientific applications. This paper investigates six popular models of classic neural network classifiers. The final results of experiments show that automatic detection of various kinds of diffraction and speckles in the beam footprint can be performed by trained AI algorithms with the accuracy exceeding 99%. During the research, the dataset intended for those experiments was created. The dataset contains six classes that describe the most often occurring problems with the laser systems. The extremely short data processing time at the level of tens of milliseconds allows real-time monitoring of a laser beam quality and the development of a tool allowing implementation of the concept of predictive maintenance in the laser field. [ABSTRACT FROM AUTHOR]

In response to the critical issue of milk adulteration jeopardizing both the nutritional integrity of milk and the health of consumers, this paper presents an innovative Artificial Intelligence (AI) enabled Internet of Things (IoT) based multi-sensor system. The escalating consumption of milk as a pivotal nutritional source necessitates robust measures to ensure its safety and quality. Traditional methods of detecting adulteration have shown limitations, prompting the development of an automated and advanced approach. The proposed system integrates various sensors capable of real-time measurement, including pH, electrical conductivity (EC), temperature, gas parameters, and Volatile Organic Compounds (VOC) parameters. This comprehensive approach extends to measuring key constituents of milk samples like Fat, Protein, Solids Not Fat (SNF), Lactose, and Gravity values. To address specific adulterants—Urea, Starch, Sodium Bicarbonate, Maltodextrin, and Formaldehyde—a machine learning-based ensemble technique is employed for classification. This ensemble method outperforms conventional algorithms like RF, Light GBM, and Extra Trees Classifiers, achieving an impressive 96% accuracy rate in detecting adulterants within the milk dataset. The pivotal contribution of this study lies in the development of an IoT-based data acquisition device that seamlessly integrates with the sensor system, enabling efficient and precise measurements. Additionally, XAI is used to analyse the results obtained by the proposed model. For this, a framework called SHAP (SHapley Additive exPlanations) analysis is employed to elucidate the decision-making process of the ensemble model, enhancing the interpretability of results. By virtue of its real-time monitoring capabilities and accurate classification, the AI-enabled IoT-based multi-sensor system emerges as a promising solution for addressing milk adulteration. This innovation holds the potential to bolster milk quality control measures in the dairy industry. The system's ability to swiftly detect and categorize adulterants underscores its significance in combating the pervasive issue of compromised milk quality, thereby ensuring consumer safety and fostering industry integrity. • AI-enabled IoT-based sensors system for identification of adulteration in raw milk. • Evaluate identification of various adulterants at distinct adulteration ratios. • Integrates various sensors and physical parameters of the milk. • Ensemble method outperforms 96% accuracy detecting adulterants in the milk. • The suggested model utilizes XAI to analyse findings through the SHAP framework. [ABSTRACT FROM AUTHOR]

• Overview of the current state of art of advanced process control and optimization technologies. • Summary of AI and ML-based approaches for closed loop control and optimization. • Application of rigorous model-based optimization, machine learning and hybrid approaches to optimization and control. • Refinery-wide and network-wide optimization. • Autonomous operation – future directions and challenges. Technologies based on Artificial Intelligence (AI) and Machine Learning (ML) concepts are advancing at a rapid pace. The new paradigms are challenging the status-quo of mature automation and control technologies in industry. Autonomous operation is a frequently stated goal of AI evangelists and technology providers. This white paper gives an overview of the current state of art of advanced process control and optimization technologies. It also provides a brief summary of the AI and ML-based approaches that address the closed-loop control and optimization space. Some results from industrial implementations are shared for both conventional and AI/ML-based approaches. Experience from four industrial applications is shared, covering rigorous model-based, machine learning and hybrid approaches to real-time optimization and control problems. The applications range from unit-based control & optimization to refinery & network wide optimization. A set of high-level requirements that need to be satisfied regardless of the underlying technology for closed-loop autonomous operations is reviewed. The article concludes with some future directions and perspectives highlighting areas where the emerging technologies may have significant impact in industry. [ABSTRACT FROM AUTHOR]

Artificial intelligence and machine learning (AI/ML) technologies offer unique opportunities to transform nuclear plant operations and power generation. Benefits will be felt not only within existing analog and digital instrumentation and control, but also within work processes, the integration of people with technology and most importantly, the business case. The application of this new technology can help simplify complex problems and produce more effective decision-making, making nuclear power safer, more efficient, and more economically viable in the current energy market. Nonetheless, there are potential barriers to its adoption that must be overcome. The purpose of this paper is to categorize, review, and discuss barriers to AI/ML adoption within the nuclear power industry, with a focus on existing commercial reactors. Unique considerations for advanced reactors are also offered. We provide a comprehensive overview of the historical, technical, and business barriers that the industry faces, as well as stakeholder readiness, and end-user acceptance. We underscore the importance of user experience and offer potential solutions in overcoming each barrier. These include provisions for easier plant data access, a friendly regulatory environment, and investment in user trust and explainable AI. • AI offers transformative opportunities for nuclear plant operations and maintenance. • A comprehensive overview of the AI barriers to adoption is provided. • The barriers described are historical, technical, and business barriers, stakeholder readiness, and end-user acceptance. • Ways to overcome AI adoption barriers include provisions for easier plant data access, and investment in user trust. [ABSTRACT FROM AUTHOR]

Reinforcement learning (RL) has emerged as a powerful tool for addressing complex decision making problems in various domains, including aviation. This paper provides a comprehensive overview of RL and its applications in the aviation industry. We begin by introducing the fundamental concepts and algorithms of RL, highlighting their unique advantages in learning from interaction and optimizing decision-making processes. We then delve into a detailed examination of the successful implementation of RL methods in aviation, covering areas such as flight control, air traffic management, airline revenue management, aircraft maintenance scheduling, etc. Furthermore, we discuss the potential benefits of RL in enhancing safety, and sustainability within the aviation sector. Finally, we identify and explore open challenges and areas for future research, emphasizing the need for continued innovation and collaboration between the fields of reinforcement learning and aviation. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) has shown significant advancements across several industries, including healthcare, using better fusion methodologies, improved data accessibility, and heightened processing capabilities. Although deep learning algorithms excel in challenging scenarios, their widespread adoption presents a challenge due to their need for more transparency. The advent of Explainable AI (XAI) has addressed this limitation by offering AI-driven systems with attributes such as transparency, interpretability, and reliability. The need for transparency in critical sectors like healthcare has prompted an increased academic focus on investigating and understanding these frameworks. The present paper thoroughly examines the latest research and advancements in Explainable Artificial Intelligence (XAI), specifically focusing on its integration into the Internet of Medical Things (IoMT) in healthcare settings. The last section tackles outstanding issues concerning XAI and IoMT and outlines prospective directions for further research. A thorough investigation was carried out across many scholarly databases and online digital libraries, such as IEEE Xplore, ACM Digital Library, Wiley Interscience, Taylor and Francis, ScienceDirect, Scopus, Springer, Google Scholar, Citeseer Library, Semantic Scholar, and other relevant sources. An analysis was conducted on articles published from March 2004 to February 2024, specifically focusing on AI models that explain different healthcare issues. The search query included "Explainable AI" in conjunction with "Open Black Box, Healthcare, Transparent Models, Interpretable Deep Learning, Machine Learning, Medical Information System, Accountability, Smart Healthcare, and Responsible AI", indicating the field's dynamic nature. The authors also examined various techniques and datasets to elucidate healthcare difficulties, including incorporating the Internet of Medical Things (IoMT). The evaluation included more than 105 published models that used clinical data input to diagnose diverse disorders, focusing on incorporating Internet of Medical Things (IoMT) components. In addition to illness diagnosis, these models also elucidate the decisions made. The models were classified according to the input data, used methodologies, and integration of the Internet of Medical Things (IoMT). The categorization included machine learning and deep learning methodologies, particularly on explainability models connected to the Internet of Medical Things (IoMT). These models were classified as model-agnostic, model-specific, global, local, ante-hoc, and post-hoc. This extensive study examines machine learning, and deep learning models developed based on clinical data and associated with the Internet of Medical Things (IoMT) for illness detection. These models improve efficiency and accuracy and provide essential assistance to medical personnel. Explaining each choice made by individuals contributes to the acceleration of sickness detection, resulting in decreased medical expenses for patients and healthcare systems. The integration of Explainable Artificial Intelligence (XAI) and the Internet of Medical Things (IoMT) highlights a fundamental change in healthcare towards more transparent and linked systems, leading to significant breakthroughs in medical decision-making. • Advancing IoMT fusion with Explainable AI for trustworthy healthcare solutions. • A comprehensive analysis of Explainable AI literature in various application areas. • Exploring the transparency of Explainable AI in healthcare solutions. • Identifying Explainable AI's future with IoMT for better healthcare solutions. • Bridging opportunities and challenges in healthcare with IoMT fusion. [ABSTRACT FROM AUTHOR]

• One-step abductive multi-target learning with diverse noisy samples (OSAMTL-DiNS) is proposed. • OSAMTL-DiNS is applied to tumour segmentation for breast cancer (TSfBC). • OSAMTL-DiNS enables various approaches for noisy labels achieving more rational results in TSfBC. • A predictive model pre-trained with OSAMTL-DiNS for TSfBC is released. Recent studies have demonstrated the effectiveness of the combination of machine learning and logical reasoning, including data-driven logical reasoning, knowledge driven machine learning and abductive learning, in inventing advanced technologies for different artificial intelligence applications. One-step abductive multi-target learning (OSAMTL), an approach inspired by abductive learning, via simply combining machine learning and logical reasoning in a one-step balanced multi-target learning way, has as well shown its effectiveness in handling complex noisy labels of a single noisy sample in medical histopathology whole slide image analysis (MHWSIA). However, OSAMTL is not suitable for the situation where diverse noisy samples (DiNS) are provided for a learning task. In this paper, giving definition of DiNS, we propose one-step abductive multi-target learning with DiNS (OSAMTL-DiNS) to expand the original OSAMTL to handle complex noisy labels of DiNS. Applying OSAMTL-DiNS to tumour segmentation for breast cancer in MHWSIA, we show that OSAMTL-DiNS is able to enable various state-of-the-art approaches for learning from noisy labels to achieve more rational predictions. We released a model pre-trained with OSAMTL-DiNS for tumour segmentation in HE-stained pre-treatment biopsy images in breast cancer, which has been successfully applied as a pre-processing tool to extract tumour-associated stroma compartment for predicting the pathological complete response to neoadjuvant chemotherapy in breast cancer. [ABSTRACT FROM AUTHOR]

Artificial intelligence models encounter significant challenges due to their black-box nature, particularly in safety-critical domains such as healthcare, finance, and autonomous vehicles. Explainable Artificial Intelligence (XAI) addresses these challenges by providing explanations for how these models make decisions and predictions, ensuring transparency, accountability, and fairness. Existing studies have examined the fundamental concepts of XAI, its general principles, and the scope of XAI techniques. However, there remains a gap in the literature as there are no comprehensive reviews that delve into the detailed mathematical representations, design methodologies of XAI models, and other associated aspects. This paper provides a comprehensive literature review encompassing common terminologies and definitions, the need for XAI, beneficiaries of XAI, a taxonomy of XAI methods, and the application of XAI methods in different application areas. The survey is aimed at XAI researchers, XAI practitioners, AI model developers, and XAI beneficiaries who are interested in enhancing the trustworthiness, transparency, accountability, and fairness of their AI models. [ABSTRACT FROM AUTHOR]

Green artificial intelligence (AI) is more environmentally friendly and inclusive than conventional AI, as it not only produces accurate results without increasing the computational cost but also ensures that any researcher with a laptop can perform high-quality research without the need for costly cloud servers. This paper discusses green AI as a pivotal approach to enhancing the environmental sustainability of AI systems. Described are AI solutions for eco-friendly practices in other fields (green-by AI), strategies for designing energy-efficient machine learning (ML) algorithms and models (green-in AI), and tools for accurately measuring and optimizing energy consumption. Also examined are the role of regulations in promoting green AI and future directions for sustainable ML. Underscored is the importance of aligning AI practices with environmental considerations, fostering a more eco-conscious and energy-efficient future for AI systems. • Green AI emphasizes sustainable and energy-efficient AI and ML models. • Strategies for designing energy-efficient systems are explored (green-in AI). • Also explored are AI approaches to enhancing eco-friendly practices (green-by AI). • Several options exist for green AI innovations in algorithm and hardware optimization. • Future trends are discussed. [ABSTRACT FROM AUTHOR]

Pursuing high-performance conductive hydrogels is still hot topic in development of advanced flexible wearable devices. Herein, a tough, self-healing, adhesive double network (DN) conductive hydrogel (named as OSA-(Gelatin/PAM)-Ca, O-(G/P)-Ca) was prepared by bridging gelatin and polyacrylamide network with functionalized polysaccharide (oxidized sodium alginate, OSA) through Schiff base reaction. Thanks to the presence of multiple interactions (Schiff base bond, hydrogen bond, and metal coordination) within the network, the prepared hydrogel showed outstanding mechanical properties (tensile strain of 2800 % and stress of 630 kPa), high conductivity (0.72 S/m), repeatable adhesion performance and excellent self-healing ability (83.6 %/79.0 % of the original tensile strain/stress after self-healing). Moreover, the hydrogel-based sensor exhibited high strain sensitivity (GF = 3.66) and fast response time (<0.5 s), which can be used to monitor a wide range of human physiological signals. Based on this, excellent compression sensitivity (GF = 0.41 kPa−1 in the range of 90–120 kPa), a three-dimensional (3D) array of flexible sensor was designed to monitor the intensity of pressure and spatial force distribution. In addition, a gel-based wearable sensor was accurately classified and recognized ten types of gestures, achieving an accuracy rate of >96.33 % both before and after self-healing under three machine learning models (the decision tree, SVM, and KNN). This paper provides a simple method to prepare tough and self-healing conductive hydrogel as flexible multifunctional sensor devices for versatile applications in fields such as healthcare monitoring, human-computer interaction, and artificial intelligence. • O-(G/P)-Ca hydrogel was prepared by bridging gelatin and polyacrylamide with oxidized sodium alginate. • The hydrogel-based sensor has outstanding strain as well as compression sensitivity. • The hydrogel can be applied for health monitoring, spatial pressure sensing, and machine learning-based gesture recognition. [ABSTRACT FROM AUTHOR]

As an important branch of emerging artificial intelligence algorithms, multi-agent reinforcement learning (MARL) has shown strong performance in collaborative environments. It can utilize multiple agents to find the optimal set of strategies for solving sequential decision problem through trial-and-error. One of the main challenges facing multi-agent system is the non-stationarity problem, which brings poor convergence and seriously affects its performance. Clustering is a commonly used unsupervised analytical method in machine learning, which aims to group samples with similar internal properties into the same cluster. In this paper, we propose a MARL clustering algorithm based on silhouette coefficient (SC-MARLC), and use the trial-and-error strategy to find the best cluster groups. In SC-MARLC, we establish a mapping relationship between multi-agent and samples, construct a novel clustering model based on MARL, and design a good clustering subset structure based on the sample silhouette coefficient. The designed structure is helpful for multi-agent system to solve the non-stationary problem. Finally, we compare the performance of SC-MARLC with 11 existing clustering algorithms on fifteen public datasets. The results show that the new clustering algorithm performs best on ten datasets. [Display omitted] [ABSTRACT FROM AUTHOR]

Hyperspectral images are increasingly being used in classification and identification. Data users prefer hyperspectral imagery with high spatial resolution, finer spectral resolution, and high signal-to-noise ratio (SNR). However, tradeoffs exist in these core parameters in imagery acquired by different hyperspectral sensor systems. Data users may find it difficult to utilize all the advantages of hyperspectral imagery. How to select hyperspectral data with optimal parameter configuration has been one of the essential issues for data users, which also affects the back-end applications. With advancements in computer science, various artificial intelligence algorithms from conventional machine learning to deep learning have been utilized for hyperspectral images classification and identification. Few researchers study the mechanism between the core parameters of hyperspectral imaging spectrometers and advanced artificial intelligence algorithms, which affects the application efficiency and accuracy. In this paper, we delved into the evolution of machine learning and deep learning models applied to imagery acquired by different hyperspectral sensor systems having different SNR, spectral, and spatial resolutions. Additionally, we also considered the tradeoffs among the core parameters of hyperspectral imagers. We used two conventional machine learning models, including the classification and regression tree (CART) and random forest (RF), two deep learning methods based on convolution neural network architectures—3D convolutional neural network (3D-CNN) and hamida, and two deep learning methods based on vision transformers architectures—transformer models vision transformer (VIT) and robust vision transformer (RVT), to compare the characteristics of different algorithms. In addition, five hyperspectral datasets with different species categories and scene distributions and aggregated datasets with different spatial resolutions, spectral resolutions, and SNRs were used to validate our study. The experimental results indicate that: (1) The overall accuracy (OA) using CART, RF, 3D-CNN, and VIT models decreased with coarser spectral resolution, but almost remained unchanged using the RVT classifier. The number of class and classification species affect the results. (2) The influence of spatial resolution on classification accuracy is related to the scene complexity, target size, and classification purpose. The coarser spatial resolution can achieve higher OA than the original spatial resolution for the uniform scene distribution. For the datasets with small objects and intersections of different species, OA first increased, plateaued, and then decreased with coarser spatial resolution. (3) The SNR has an obvious impact on OA for the CART and RF classifiers, and the impact decreased for deep learning models, especially for the VIT and RVT models, which were almost unaffected by SNR. Additionally, slight variations in experimental results were observed for datasets with different scene distributions and categories. Furthermore, we conducted a detailed analysis of the role of traditional machine learning and deep learning models in the experimental outcomes. The study can provide insights into understanding the relationship between the core parameters of hyperspectral imager and the artificial intelligence algorithms used for hyperspectral classification. It serves to bridge the knowledge gap between the front-end hyperspectral imager, mid-end model, and back-end applications, and further promote the development of hyperspectral imaging technology. • Optimize the processing chain for the design and application of hyperspectral sensor. • Analysis the role of hyperspectral imager parameters on classification accuracy. • Bridge the gap between front-end hyperspectral sensor design and back-end application. • Improve the classification accuracy by suitable sensor configuration. [ABSTRACT FROM AUTHOR]

This paper presents VisualSiteDiary , a Vision Transformer-based image captioning model which creates human-readable captions for daily progress and work activity log, and enhances image retrieval tasks. As a model for deciphering construction photologs, VisualSiteDiary incorporates pseudo-region features, utilizes high-level knowledge in pretraining, and fine-tunes for diverse captioning styles. To validate VisualSiteDiary , a new image captioning dataset, VSD, is presented. This dataset includes many realistic yet challenging cases commonly observed in commercial building projects. Experimental results using five different metrics demonstrate that VisualSiteDiary provides superior-quality captions compared to the state-of-the-art image captioning models. Excluding the task of object recognition, the presented model also outperformed mPLUG –the state-of-the-art visual-language model– in the image retrieval task by 0.6% in precision and 0.9% in recall, respectively. Detailed discussions illustrate practical examples on how VisualSiteDiary improves the process of creating daily construction reports, paving the way for future developments in the field. [Display omitted] • New vision-language transformer model replacing costly convolutional operations. • A method for automated daily construction reporting and image retrieval. • Pseudo-region features and high-level knowledge pretraining improve the quality of captions. • New construction image-caption dataset with two different styles serving user preference. [ABSTRACT FROM AUTHOR]

• The paper explores AI decision-making to enhance transparency of CIN diagnosis using colposcopy images. • The study presents interpretable insights for clinical validation using different XAI methods. • Saliency method showed best result, using gradients to reveal likely malignancy traits. • Expert Clinic Validation of results conducted, along with statistical analyses. Although artificial intelligence techniques have performed well in analysing medical images, it is essential to consider the degree of understanding or interpretation in evaluations. This is especially important when diagnostic support is involved, as the trustworthiness of machine learning predictions needs to be clarified and evaluated. For deep learning algorithms to be translated into clinical practice, they must be made less opaque. To examine the classification of cervical dysplasia-diagnosed patients, we will explore explainable artificial intelligence (XAI) approaches, by implementing seven different interpretation techniques (Saliency, XRAI, Integrated Gradients, Smooth Gradients, Smooth Integrated Gradients, Grad-CAM, Smoothgrad-CAM). These XAI techniques shall be explored in order to assess the performance of four Convolutional Neural Network models (AlexNet, VGG16, MobileNet, and InceptionNet). Our results show that saliency qualities most closely match expert annotations, and there is a moderate to strong association between a model's sensitivity and the agreement between humans and computers. We also discovered a relevant relationship between expert insights and computational learning. This highlights the potential role of human expertise in influencing effective computer learning. [ABSTRACT FROM AUTHOR]