Fire detection is crucial for ensuring human safety and minimizing property damage. By utilizing advanced technologies, we can identify fires early, before they escalate. Autonomous fire detection systems are particularly vital in high-risk areas with minimal human presence. To address this need, we propose an automated fire-detection model based on YOLOv8. We modified the architecture of YOLOv8 and achieved impressive performances. Through comprehensive analysis of different YOLO models and their predecessors, we identified and addressed substantial gaps in this field. Also, by augmenting the framework with additional capabilities, we surpassed previous models, enabling real-time fire detection. Our proposed model achieves impressive performances, with 98% accuracy in fire detection and 97.8% in smoke detection. Moreover, recall rates for fire and smoke are 97.1% and 97.4%, respectively, with a mean average precision (mAP) accuracy of 99.1% for both cases. Finally, we applied an explainable artificial intelligence technique to interpret our proposed model and its results. This study lays the foundation for future research aimed at enhancing fire detection efficiency. The reliability of our modified model presents promising opportunities for future advancements, ensuring increased effectiveness and precision in efficient fire detection.

Artificial Intelligence (AI) and Machine Learning (ML) approaches that could learn from large data sources have been identified as useful tools to support clinicians in their decisional process; AI and ML implementations have had a rapid acceleration during the recent COVID-19 pandemic. However, many ML classifiers are “black box” to the final user, since their underlying reasoning process is often obscure. Additionally, the performance of such models suffer from poor generalization ability in presence of dataset shift. Here, we present a comparison between an explainable-by-design (“white box”) model (Bayesian Network (BN)) versus a black-box model (Random Forest), both studied with the aim to support clinicians of Policlinico San Matteo University Hospital in Pavia (Italy) during the triage of COVID-19 patients. Our aim is to evaluate whether the BN predictive performances are comparable with those of a widely used but less explainable ML model such as Random Forest and to test the generalization ability of the ML models across different waves of the pandemic.

AI research and implementations are growing, and so are the risks associated with AI (Artificial Intelligence) developments, especially when it’s difficult to understand exactly what they do and how they work, both at a localized level, and at deployment, in particular when distributed and on a large scale. Governments are pouring massive funding to promote AI research and education, yet research results and claims, as well as the effectiveness of educational programmes, can be difficult to evaluate given the limited reproducibility of computations based on ML (machine learning) and poor explainability, which in turn limits the accountability of the systems and can cause cascading systemic problems and challenges including poor reproducibility, reliability, and overall lack of trustworthiness. This paper addresses some of the issues in Knowledge Representation for AI at system level, identifies a number of knowledge gaps and epistemological challenges as root causes of risks and challenges for AI, and proposes that neurosymbolic and hybrid KR approaches can serve as mechanisms to address some of the challenges. The paper concludes with a postulate and points to related and future research

As the educational landscape evolves, understanding and fostering student adaptability has become increasingly critical. This study presents a comparative analysis of (XAI) techniques to interpret machine learning models aimed at classifying student adaptability levels. Leveraging a robust dataset, we employed several machine learning algorithms with a particular focus on Random Forest, which demonstrated a 91% accuracy. Our study utilizes (SHAP), (LIME), Anchors, (ALE), and counterfactual explanations to reveal the specific contributions of various features impacting adaptability predictions. Consistently, 'Class Duration' and 'Financial Condition' emerge as key factors, while the study also underscores the subtle effects of 'Institution Type' and 'Load-shedding'. This multi-faceted interpretability approach bridges the gap between machine learning performance and educational relevance, presenting a model that not only predicts but also explains the dynamic factors influencing student adaptability. The synthesized insights advocate for educational policies accommodating socioeconomic factors, instructional time, and infrastructure stability to enhance student adaptability. The implications extend to informed and personalized educational interventions, fostering an adaptable learning environment. This methodical research contributes to responsible AI application in education, promoting predictive and interpretable models for equitable and effective educational strategies.

The understanding of water quality and its underlying processes is important for the protection of aquatic environments enabling the rare opportunity of access to a domain expert. Hence, an explainable AI (XAI) framework is proposed that is applicable to multivariate time series resulting in explanations that are interpretable by a domain expert. The XAI combines in three steps a data-driven choice of a distance measure with explainable cluster analysis through supervised decision trees. The multivariate time series consists of water quality measurements, including nitrate, electrical conductivity, and twelve other environmental parameters. The relationships between water quality and the environmental parameters are investigated by identifying similar days within a cluster and dissimilar days between clusters. The XAI does not depend on prior knowledge about data structure, and its explanations are tendentially contrastive. The relationships in the data can be visualized by a topographic map representing high-dimensional structures. Two comparable decision-based XAIs were unable to provide meaningful and relevant explanations from the multivariate time series data. Open-source code in R for the three steps of the XAI framework is provided.

The spread of false information can significantly harm public opinion, underscoring the importance of accurately identifying untrustworthy news. This paper presents an innovative machine learning (ML) tool, TMining, designed to evaluate news credibility and facilitate various text-mining tasks. By examining a range of ML methodologies alongside preprocessing techniques, we aim to boost the system's effectiveness. Our research meticulously assesses different datasets, highlights the impact of applying stemming techniques, and employs Local Interpretable Model-Agnostic Explanations (LIMEs) to shed light on the rationale behind model predictions. The outcomes reveal a notable enhancement in both the precision and clarity of the news verification process. The ultimate version of the model has been made available as an Application Program Interface (API), and its source code has been shared openly, encouraging further exploration and collaboration within the scientific community. This initiative advances our ability to discern manipulative context from fictitious content and promotes transparency and understanding in the domain of ML applications.

According to the World Health Organization (WHO), dementia is the seventh leading reason of death among all illnesses and one of the leading causes of disability among the world’s elderly people. Day by day the number of Alzheimer’s patients is raising. Considering the increasing rate and the dangers, Alzheimer’s disease should be diagnosed carefully. Machine learning is a potential technique for Alzheimer’s diagnosis but general users do not trust machine learning models due to the black-box nature. Even, some of those models do not provide the best performance because of using only neuroimaging data. To solve these issues, this paper proposes a novel explainable Alzheimer’s disease prediction model using a multimodal dataset. This approach performs a data-level fusion using clinical data, Freesurfer MRI segmentation data, and psychological data. For Alzheimer’s disease vs cognitively normal prediction, the random forest classifier provides 100% accuracy. Furthermore, Alzheimer’s disease and non-Alzheimer’s dementia should be classified properly because their symptoms are similar. To the best of our knowledge, we are the first to present a three-class classification on Alzheimer’s disease vs cognitively normal vs non-Alzheimer’s dementia and achieved 99.86% accuracy using an ensemble model. Besides, a novel Alzheimer’s patient management architecture is also proposed in this work..

Background: Ovarian, cervical, and endometrial cancers stand as fatal health killers for women's mental and physical health, especially affecting female reproductive systems. Exploiting weakly supervised learning and explainable AI techniques are crucial for fast, accurate, and robust automatic marker detection, efficient prevention, and primary treatment of gynecological tumors. Methods: With respect to the PRIMSA methodology, weakly supervised learning schemes and deep learning-based schemes are investigated in the cross-subject fields of clinical diagnostic imaging and explainable AI technology. Related methods, opening research problems, and challenging subjects are explored in the screening and treatment of gynecological tumors and performing cancer image diagnosis in the latest study. Results: Keynote approaches combining ultrasound medicine, explainable AI, and clinical imaging technology are summarized. In combination with learning-based methods with medical imaging, prospective insights are put forward for refreshed concepts on treatments in the area of gynecological oncology, with a feasible range of applications for their corresponding AI techniques. Conclusions: Explainable AI and deep learning-based approaches are capable of performing accurate classification between benign and malignant tumors, yielding a pathway to care for women's health, improving the survival rate of patients, pacing with disease prediction, and matching the strategic goal of "Healthy China 2030".

Advances in early detection of Breast cancer and treatment improvements have significant-ly increased survival rates. Traditional screening methods, including mammography, MRI, ultrasound, and biopsies, while effective, often come with high costs and risks. Recently, thermal imaging has gained attention due to its minimal risks compared to mammography, although it is not widely adopted as a primary detection tool since it depends on identifying skin temperature changes and lesions. The advent of machine learning (ML) and deep learning (DL) has enhanced the effectiveness of breast cancer detection and diagnosis using this technology. In this study a novel methodology for developing an interpretable computer-aided diagnosis (CAD) system for breast cancer detection, leveraging explaina-ble Artificial Intelligence (XAI) throughout its various phases. To achieve these goals, we proposed a new multi-objective optimization approach named Hybrid Particle Swarm Optimization algorithm (HPSO) and Hybrid spider Monkey Optimization algorithm (HSMO). These algorithms simultaneously combine the continuous and binary representations of PSO and SMO to effectively manage trade-offs between Accuracy, feature selection and hyperparameter tuning. We evaluate several CAD models and investigate the impact of handcrafted methods such as Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gabor filters, and edge detection. We further shedding light on the effect of feature selection and optimization on feature attribution and model decision-making processes using the SHapley Additive exPlanations (SHAP) framework, with a particular emphasis on cancer classification using the DMR-IR dataset. The results of our experiments demonstrate in all trials that the performance of the model is improved. Also with HSMO our models achieved a high accuracy of 98.27% and F1- score of 98.15% while selecting only 25.78% of the HOG features. This approach not only boosts the performance of CAD models but also ensures comprehensive interpretability. This method emerges as a promising and transparent tool for early breast cancer diagnosis.

Malaria and Typhoid fever are prevalent diseases in tropical regions, exacerbated by unclear protocols, drug resistance, and environmental factors. Prompt and accurate diagnosis is crucial to improve accessibility and reduce mortality rates. Traditional diagnosis methods cannot effectively capture the complexities of these diseases due to the presence of confusable symptoms. Although machine learning (ML) models offer accurate predictions, they operate as "black boxes" with non-interpretable decision-making processes, making it challenging for healthcare providers to comprehend how the conclusions are reached. This study employs explainable AI (XAI) models such as Local Interpretable Model-agnostic Explanations (LIME), and Large Language Models (LLMs) like ChatGPT, Gemini, and Perplexity, to clarify diagnostic results for healthcare workers, building trust and transparency in medical diagnostics. The models were implemented on Google Colab and Visual Studio Code because of their rich libraries and extensions. Results showed that the Random Forest model outperformed Extreme Gradient Boost and Support Vector Machines and important features for predicting Malaria and Typhoid were identified with the LIME plots. Among LLMs, ChatGPT 3.5 demonstrates a comparative advantage over Gemini and Perplexity, hence highlighting how crucial it is to use a hybrid strategy that combines ML, XAI, and LLMs to improve diagnostic performance and reliability in healthcare applications. The study recommends implementing the integrated ML, LIME, and LLM processes because it streamlines the development and maintenance process's workflow overall, makes use of resources more effectively, and improves explainability by allowing the LLM to consider the complete context that LIME provides.

One of the most prevalent illnesses, diabetes does not directly result in patient mortality. But, it increases the risk of death. Any disease that may be predicted in its early stages can lessen its fatal effects while also enhancing the quality of the healthcare system. For the early-stage prediction of diabetes or such types of non-communicable diseases, we need the proper set of influential features. This research has developed a machine learning-based disease prediction model to identify the influential features for diabetes prediction and give a near-perfect classification accuracy. This model includes Min-Max normalization for data normalization, Isolation Forest (iForest) for outlier removal, Synthetic Minority Oversampling Technique (SMOTE) for oversampling, Random Forest based Recursive Feature Elimination (RFE-RF) test, Chi-Square test, and Minimum Redundancy Maximum Relevancy (mRMR) test based feature selection methods for identifying the influential features, and Support Vector Machine (SVM), K Nearest Neighbor (KNN), and Naive Bayes (NB) for the classification. The results clarify that the proposed model outperforms the previous models and studies. The SVM has attained an accuracy of 99.58% in classification using the five features chosen from the Chi-Square test. Lastly, SHAP, an explainable AI model, has been used to assess the classifier model’s performance. These selected features and the classifier model can be used for early-stage diabetes prediction.

Addressing the pressing challenge of global warming, reducing greenhouse gas emissions in the transportation sector is a critical imperative. Battery and fuel-cell electric vehicles have emerged as promising solutions for curbing emissions in this sector. In this study, we conducted a comprehensive life cycle assessment (LCA) for typical passenger vehicles, heavy duty trucks and city buses using either proton-exchange membrane fuel cells or Li-ion batteries with different cell chemistries. To ensure accuracy, we supplemented existing studies with data from the literature, particularly for the recycling phase, as database limitations were encountered. Our results highlight that fuel cell and battery systems exhibit large emissions in the production phase. Recycling can significantly offset some of these emissions, but a comparison of the technologies examined revealed considerable differences. Overall, battery electric vehicles consistently outperform fuel cell electric vehicles regarding absolute greenhouse gas emissions. Hence, we recommend prioritizing battery electric over fuel cell vehicles. However, deploying fuel cell electric vehicles could become attractive in a hydrogen economy scenario where other factors, e. g. the conversion and storage of surplus renewable electricity via electrolysis, become important.

Studying and understanding the behavior of people and vehicles on public roads can be of utmost importance for supporting the activities of many institutional stakeholders. It may allow automated supervision of the ongoing situation in a given place, with warnings or alarms raised in case of anomalies. It may be used to plan their interventions on road and town organization. It may provide them with advanced support to decision-making. The number of involved entities and places to manage makes it infeasible to manually handle all the traffic-related tasks. Moreover, the complexity of the tasks to be carried out requires the adoption of advanced approaches. Many AI solutions are nowadays mature to support these requirements. In some cases, the motivations and objectives of traffic management require the AI outcomes to be understandable, interpretable and explainable. In this paper, we propose TrAnSIT (TRaffic ANalysis Supervision and Interpretation Tool), an AI-based framework that combines several modules, each aimed at tackling a specific traffic-related task, so as to cover a wide landscape of traffic-related issues, from overall urban or suburban traffic management to surveying specific road segments that fall under the scope of one camera. Most of these modules are based on AI techniques that support a human-level understanding of the outcomes.

Deep learning architectures like ResNet and Inception have produced accurate predictions for classifying benign and malignant tumors in the healthcare domain. This enables healthcare institutions to make data-driven decisions and potentially enable early detection of malignancy by employing computer-vision-based deep learning algorithms. These Convolutional Neural Network algorithms, in addition to requiring huge amounts of data, can identify higher and lower-level features that are significant while classifying tumors into benign or malignant. However, these algorithms have limitations concerning explainability and identifying the exact features that are of importance and contributing to the final classification of tumors as benign or malignant. In this paper, we implement several explainable AI techniques, namely, LIME, Saliency Map, Occlusion Analysis, Grad-CAM, SHAP, and Smooth Grad to interpret the results of a custom ResNet60 classifier in the classification of ovarian tumors as benign or malignant. The ResNet60 model attained an accuracy of 97.50% for the test dataset.

Interdisciplinary conferences play a vital role in advancing explainable Artificial Intelligence (AI) within increasingly intersecting healthcare and computational biology arenas. Challenges result-ing from algorithmic bias and the necessity for domain-specific Explainable AI (XAI) techniques underscore the increasing significance of transparent and interpretable AI systems used in patient care. Collaborative efforts between clinicians, data scientists, and various stakeholders are nec-essary to innovate solutions tailored to healthcare needs. Specialized conferences may foster these interdisciplinary interactions, providing platforms for knowledge exchange, networking, and collaborative partnerships. The legal, ethical, and societal dimensions of medical AI advocate for an integrative approach that aligns technological advancements with patient-centered care val-ues. The role of specialized conferences is therefore essential for shaping future directions in ex-plainable AI and computational biology that contribute to improved patient outcomes and healthcare innovations.

Automated charging technologies are becoming increasingly important in the electrification of heavy road freight transport, especially in combination with autonomous driving. This study provides a comprehensive analysis of automated charging technologies for electric heavy-duty vehicles (HDVs). It encompasses the entire spectrum of feasible technologies, including static and dynamic approaches, with each charging technology evaluated for its advantages, potentials, challenges, and technology readiness level (TRL). Static conductive charging methods such as charging robots, underbody-couplers or pantographs show good potential, with pantographs being the most mature option. These technologies are progressing towards higher TRLs, with a focus on standardization and adaptability. While static wireless charging is operational for some prototype solutions, it encounters challenges related to implementation and efficiency. Dynamic conductive charging through an overhead contact line or contact rails holds promise for high-traffic HDV routes with the overhead contact line being the most developed option. Dynamic wireless charging, although facing efficiency challenges, offers potential for seamless integration into roads and minimal wear and tear. Battery swapping is emerging as a practical solution to reduce downtime for charging, with varying levels of readiness across different implementations. To facilitate large-scale deployment further standardization efforts are required. The study emphasizes the necessity for continued research and development to enhance efficiency, decrease costs, and ensure seamless integration into existing infrastructures. Technologies that achieve this best will have the highest potential to significantly contribute to the creation of an efficiently automated and environmentally friendly transport sector.

The aim of this study is to investigate and determine the key factors guiding customer attitudes towards social media influencers, and on that base to explore their effects on purchase intentions towards advertised products or services. A total of 376 fulfilled questionnaires from an online survey were analysed. The main characteristics of digital influencers’ behaviour, affecting consumer perceptions have been systematized and categorized through a combination of both traditional and advanced data analysis methods. Structural Equation Modelling (SEM), machine learning and multi-criteria decision-making (MCDM) methods were selected to uncover the hidden dependencies between variables from the perspective of social media users. The developed models elucidate the underlying relationships that shape the acceptance mechanism of influencers’ messages. The results obtained provide specific recommendations for stakeholders across the social media marketing value chain. Marketers can make informed decisions and optimize influencer marketing strategies to enhance user experience and increase conversion rates. Working collaboratively, marketers and influencers can create impactful and successful marketing campaigns that resonate with the target audience and drive meaningful results. Customers benefit from more tailored and engaging influencer content that aligns with their interests and preferences, fostering a stronger connection with brands and potentially affecting their purchase decisions. As the perception of customer satisfaction is individual and evolving process, stakeholders should organize regular evaluations of influencer marketing data and explore the possibilities to ensure continuous improvement of this e-marketing channel.

This research evaluates the feasibility of addressing computer vision problems with limited resources, particularly in the context of medical data where patient privacy concerns restrict data availability. (1) Background: The study focuses on diagnosing skin diseases using five distinct transfer learning models based on convolutional neural networks. Two versions of the dataset were created, one imbalanced (4092 samples) and the other balanced (5182 samples), using simple data augmentation techniques. Preprocessing techniques were employed to enhance the quality and utility of the data, including image resizing, noise removal, and blur techniques. The performance of each model was assessed using fresh data after preprocessing. According to the research findings, (2) Methods: the VGG-19 model achieved an accuracy of 95.00% on the imbalanced dataset. After applying augmentation on the balanced data, the best-performing model was VGG-16-Aug with an accuracy of 97.07%. (3) Results: These results suggest that low-resource approaches, coupled with preprocessing techniques, can effectively identify skin diseases, particularly when utilizing the VGG-16-Aug model with a balanced dataset. (4) Conclusions: The study addresses rare skin disorders that have received limited attention in past research, including acne, vitiligo, hyperpigmentation, nail psoriasis, and SJS-TEN. The findings highlight the potential of simple data augmentation techniques moreover, explainable AI: Grad-CAM interpreted the model outcome by showing image contours visually as well as identifying uncommon skin conditions and overcoming the data scarcity challenge. The implications of these research findings are significant for the development of machine learning-based diagnostic systems in the medical field. Further investigation is necessary to explore the generalizability of these findings to other medical datasets.

The lack of a generalizable machine learning model for predicting the safety of food for 1 human consumption is a significant challenge for policymakers and responsible authorities. This 2 study provides a step-by-step guide to predict the results of seafood product import inspections, 3 focusing on identifying and understanding the critical factors that influence these results. By compar- 4 ing the performances of an ensemble of machine learning models, this study combines the strengths 5 of multiple algorithms to improve the predictive accuracy and gain insights into the key factors 6 impacting them. The ensemble model based on the soft voting technique achieves superior perfor- 7 mance to that based on the hard voting technique in terms of the recall and area under the curve 8 (AUC) scores. The study discovered that various characteristics, such as the exporting country ratio, 9 major product category, overseas manufacturer ratio, importer ratio, and seasonal variation, had a 10 substantial influence on the models’ decisions. This research guide for predicting seafood product 11 import inspection results could pave the path for other items to follow.

Such rapidly changing external conditions as the COVID-19 pandemic and the war in Ukraine, being pure crisis phenomena, not only determine the geopolitical and geoeconomic situation on the global markets, but also cause structural changes in individual countries. Under these conditions, the level of food self-sufficiency becomes particularly important, as it is one of the factors determining the food security of any country. The aim of the research is to assess Ukraine's food self-sufficiency compared to the European Union and Poland. The self-sufficiency ratio (SSR) index was used to assess food self-sufficiency. This is the ratio of the volume of production of the most important products of plant and animal origin to the volume of domestic consumption. Domestic consumption was defined as the volume of domestic production increased by the volume of imports, reduced by the volume of exports and also included changes in domestic stock levels. The surveyed time frame is 2019–2021. The analyzed data were taken from the State Statistics Service of Ukraine, FAOSTAT, USDA and Statistics Poland. A comparative analysis of self-sufficiency for the main agri-food sectors of Ukraine, the EU, and Poland showed significant differences. Taking into account the production potential and food self-sufficiency indicators of Ukraine, Ukraine's possible accession to the EU can be expected to have a major impact on the EU's supply and demand situation, as it may pose a threat to many EU agri-food sectors.

Let Vn(d) denote the least number such that every collection of nd-cubes with total volume 1 in d-dimensional (Euclidean) space can be packed parallelly into some d-box of volume Vn(d). We show that V3(d)=r1−dd if d≥11 and V3(d)=1r+1rd+1r−rd+1 if 2≤d≤10, where r is the only solution of the equation 2(d−1)kd+dkd−1=1 on 22,1 and (k+1)d(1−k)d−1dk2+d+k−1=kddkd+1+dkd+kd+1 on 22,1, respectively. The maximum volume is achieved by hypercubes with edges x, y, z such that x=2rd+1−1/d, y=z=rx if d≥11, and x=rd+(1r−r)d+1−1/d, y=rx, z=(1r−r)x if 2≤d≤10. We also proved that only for dimensions less than 11 there are two different maximum packings, and for all dimensions greater than 10 the maximum packing has the two smallest cubes the same.

: Mistrust, amplified by numerous artificial intelligence (AI) related incidents, has caused the energy and industrial sectors to be amongst the slowest adopter of AI methods. Central to this issue is the black-box problem of AI, which impedes investments and fast becoming a legal hazard for users. Explainable AI (XAI) is a recent paradigm to tackle this challenge. Being the backbone of the industry, the prognostic and health management (PHM) domain has recently been introduced to XAI. However, many deficiencies, particularly lack of explanation assessment methods and uncertainty quantification, plague this young field. In this paper, we elaborate a framework on explainable anomaly detection and failure prognostic employing a Bayesian deep learning model to generate local and global explanations from the PHM tasks. An uncertainty measure of the Bayesian model is utilized as marker for anomalies expanding the prognostic explanation scope to include model’s confidence. Also, the global explanation is used to improve prognostic performance, an aspect neglected from the handful of PHM-XAI publications. The quality of the explanation is finally examined employing local accuracy and consistency properties. The method is tested on real-world gas turbine anomalies and synthetic turbofan data failure prediction. Seven out of eight of the tested anomalies were successfully identified. Additionally, the prognostic outcome showed 19% improvement in statistical terms and achieved the highest prognostic score amongst best published results on the topic.

The application of Explainable AI (XAI) to improve understanding of complex non-linear SST teleconnections and gain predictive skills is at the frontier of climate research. In this study, we attempt to refine the applications of XAI advancements to ENSO prediction by including SSTA in the western North Pacific (WNP) as a precursor. Our analyses indicate that the baseline accuracy increases from the 60% threshold previously reported for ENSO to >85% for moderate warm, cold, and neutral ENSO states one year in advance when WNP SSTA is included. Precision increases to over 90% for higher magnitude El Niños and La Niñas. Experiments conducted at 4-year lead times yield a strong WNP SSTA signal. A moderate SSTA signal is observed at 3-year lead time with no predictability; however, predictability spikes to over 80% when stratospheric zonal winds are included with WNP SSTA. While additional scientific work is required to make robust connections between XAI and dynamical processes, our results demonstrate a potential to improve long term predictability of ENSO through the ability of XAI in capturing SST patterns evolving at extended spatial and temporal scales.

This paper aims to investigate appropriate mathematical models devoted to optimization of some cleaning processes related to pharmaceutical contaminants removal. In our previous recent works has been reported that a possibility for removal from water sources of this type of micropollutants is to rehabilitate the existing cleaning plants by introducing efficient techniques such as adsorption on granulated active carbon filters, micro-, nano- or ultrafiltration. To have such processes under a better control and to pass from small to large scale treatment stations, specific mathematical models are necessary. Starting from Navier-Stokes equations and imposing proper boundary conditions, some mathematical physics problems are obtained for which adequate solving methods via variational methods and surjectivity results are proposed. The importance of these solution characterizations consists in their continuation in a numerical method and the possibility to visualize the result by using CFD program.

The study conducts a comparative analysis of solar radiation estimation methods, assessing the efficacy of the Heliosat-2 algorithm against ground measurements across seven distinct countries: Netherlands, Spain, Japan, Namibia, South Africa, Saudi Arabia, and India. To achieve this, it utilizes two distinct satellite data sources—Himawari-8 for Japan and Metosat Second Generation-MSG for the rest of the countries—spanning the years Jan 2022 to April 2024. A robust methodology for determining albedo parameters specific to Heliosat-2 was developed. During cloudy days, the estimates provided by Heliosat-2 generally exceeded the ground measurements in all the countries. Conversely, on clear days, there was a tendency for underestimation, as indicated by the median value of the mean bias (MB) across most of the countries. The Heliosat-2 model slightly underestimates daily radiation values, with a median MB ranging from −27.5 to +10.2 W.m⁻². Notably, the median root mean squared error (RMSE) on clear days is significantly lower, with values ranging from 24.8 to 108.7 W.m⁻², compared to cloudy days where RMSE values lie between 75.3 and 180.2 W.m⁻². In terms of R² values, both satellites show a strong correlation between the estimated and actual values, with a median value consistently above 0.86 on a monthly scale and over 92% of daily data points falling within ±2 standard deviation.

Background: Dental education blends theoretical and practical training to prepare students for independent patient care. This study examines the confidence levels of dental students in Umeå regarding independent performance of general dentistry tasks, and whether this confidence changes after clinical training. Methods: Surveys were conducted before and after a summer clinical internship, with s tudents rating their comfort levels on a scale from 0 to 10 for various procedures. Results: Results from 64 initial surveys and 54 follow-up surveys showed no significant difference in confidence before and after the internship. However, confidence levels varied based on whether students had practiced specific tasks during the internship. Students felt least confident in managing acute dental trauma and treating cavities in young children, while they were most confident in tasks like obtaining radiographic surveys and debriding periodontally compromised dentition. Tooth extraction and dental fillings were the most practiced procedures during the internship. Conclusions: The study concludes that the internship between the ninth and tenth semesters does not notably boost students' confidence in specific dental procedures, possibly due to the short duration of the training. Further exploration, including input from clinical supervisors, is suggested to optimize clinical training in dental education.

The rapid convergence of Artificial General Intelligence (AGI), autonomous drones, and applied robotics presents a transformative opportunity for many sectors. However, this advancement also raises critical ethical and existential questions, particularly in warfare. This paper explores the concept of entropy as a metaphor for the potential disorder introduced by these increasingly complex technologies. We examine the risks of AGI surpassing human control in conflict situations, where autonomous decision-making could have disastrous consequences. We then analyze autonomous drones, scrutinizing their impact on warfare tactics and the ethical dilemmas surrounding independent, real-time decision-making. Finally, we investigate applied robotics in military operations, focusing on the delicate balance between enhanced capabilities and the potential for uncontrollable systems. Through a multidisciplinary lens, drawing on technology ethics, military strategy, and AI safety, this paper utilizes the concept of entropy to highlight the need for caution in developing these technologies. We propose a scientifically grounded and ethically sound framework to guide policymakers, technologists, and ethicists in navigating the path between innovation and global stability. This framework concludes with recommendations for responsible development and deployment strategies that can mitigate the risks associated with these powerful tools.

Machine Learning is increasingly and ubiquitously being used in the medical domain. Evaluation metrics like accuracy, precision, and recall may indicate the performance of the models but not necessarily the reliability of their outcomes. This paper assesses the effectiveness of a number of machine learning algorithms applied to an important dataset in the medical domain, specifically, mental health, by employing explainability methodologies. Using multiple machine learning algorithms and model explainability techniques, the project provides insights into the model workings to help determine the reliability of the machine learning algorithm predictions. The results are not intuitive. It was found that the models were focusing significantly on less relevant features and at times, unsound ranking of the features to make the predictions. The paper therefore argues that it is important for research in applied machine learning to provide insights into explainability of the models in addition to other performance metrics like accuracy. This is particularly important for applications in critical domains such as healthcare. A future direction is to investigate methods to quantify the effectiveness of the machine learning models in terms of the insights from their explainability.

Deep learning has already revolutionised the way we process a wide range of data, in many areas of our daily life. The ability to learn abstractions and relationships from heterogeneous data, has provided impressively accurate prediction and classification tools to handle increasingly big datasets. This has a significant impact on the growing wealth of omics datasets, with the unprecedented opportunity for a better understanding of the complexity of living organisms. While this revolution is transforming the way we analyse these data, explainable deep learning is emerging as an additional tool with the potential to change the way we interpret biological data. Explainability addresses critical issues such as transparency, so important when computational tools are introduced especially in clinical environments. Moreover, it empowers artificial intelligence with the capability to provide new insights in the input data, thus adding an element of discovery to these already powerful resources. In this review we provide an overview of the transformative effects explainable deep learning is having on multiple sectors, ranging from genome engineering and genomics, from radiomics to drug design and clinical trials. We offer a perspective to life scientists, to better understand the potential of these tools, and a motivation to implement them in their research, by suggesting learning resources they can use to move their first steps in this field.

Cronbach’s (1957) famous division of scientific psychology into two disciplines is still actual for the fields of cognition (general mechanisms) and intelligence (dimensionality of individual differences). The welcome integration of the two fields requires the construction of mechanistic models of cognition and cognitive development that explain key phenomena in individual differences research. In this paper we argue that network modeling is a promising approach to integrate the processes of cognitive development and (developing) intelligence into one unified theory. Network models are defined mathematically, describe mechanisms on the level of the individual, and are able to explain positive correlations among intelligence subtest scores - the empirical basis for the well-known g-factor - as well as more complex factorial structures. Links between network modeling, factor modeling and item response theory allow for a common metric, encompassing both discrete and continuous characteristics, for cognitive development and intelligence.

Background: Alzheimer's disease (AD) is a leading cause of dementia, significantly influenced by the Apolipoprotein E4 (APOE4) gene and gender. This study aims to use machine learning (ML) algorithms to predict brain age and assess AD risk by considering the effects of APOE4 genotype and gender. Methods: We collected brain volumetric MRI data and medical records from 1100 cognitively unimpaired individuals and 602 AD patients. We applied three ML regression models—XGBoost, Random Forest (RF), and Linear Regression (LR)—to predict brain age. Additionally, we introduced two novel metrics, Brain Age Difference (BAD) and Integrated Difference (ID), to evaluate model performance and analyze the influence of APOE4 genotype and gender on brain aging. Results: AD patients displayed significantly older brain ages compared to their chronological ages, with BADs ranging from 6.5 to 10 years. The RF model outperformed both XGBoost and LR in terms of accuracy, delivering higher ID values and more precise predictions. Comparing APOE4 carriers with non-carriers, the models showed enhanced ID values and consistent brain age predictions, improving overall performance. Gender-specific analyses indicated slight enhancements, with models performing equally well on both genders. It indicates that APOE4 may be a more robust predictor of brain age than gender. Conclusion: Robust ML models for brain age prediction can be pivotal in the early detection of AD risk via MRI brain structural imaging, especially for APOE4 carriers. Such early identification may facilitate timely preventive interventions for AD.

On average, one in ten patients die because of a diagnostic error and medical errors are the third largest cause of death in the word. While LLMs have been proposed to help doctors with diagnoses, no research results have been published on comparing the diagnostic ability of many popular LLMs on an openly accessible real-patient cohort. In thus study, we compare LLMs from Google, OpenAI, Meta, Mistral, Cohere and Anthropic using our previously published evaluation methodology and explore improving their accuracy with RAG.

Large language models (LLMs) have shown impressive performance and versatility. However, their billions of parameters and high computational costs hinder the development of personalized and privacy-preserving AI assistants operating locally on user devices. In this work, we explored the potential of pruning LLMs to create lightweight models suitable for user devices, using the moderate-sized Llama-2 7B model as an example. By adopting a simple yet effective pruning method, we found that up to 60% of the weights in the Llama-2 7B model could be pruned without significantly impairing its language modeling capabilities. Furthermore, despite occasional factual inaccuracies, the pruned model at the sparsity limit generated fluent and helpful answers to daily queries, demonstrating its feasibility of on-device AI assistants. These inaccuracies might originate from forgetting or hallucination due to pruning. We proposed a simple protocol to distinguish between the two mechanisms, as well as future directions to improve the pruned models for local AI assistants.

This paper presents MADS (Multi-Agents for Data Science), an innovative and simple open-source multi-agent framework designed for systemic pipeline execution in applied supervised machine learning. By leveraging the capabilities of multi-agent systems (MAS), we introduce a universal approach to optimize and streamline machine learning pipelines. Our framework highlights the differences between various types of agents, such as reinforcement learning (RL) agents and large language model (LLM) agents, and their distinct contributions to the process. While we currently employ LLM agents to automate and enhance machine learning tasks, we acknowledge the potential of incorporating RL agents in future iterations to further improve performance and adaptability. The primary objective is to enhance the efficiency, scalability, and adaptability of supervised learning applications across various domains. This integration addresses the complexity and manual effort typically associated with machine learning workflows, paving the way for more automated, robust, and scalable solutions. Our approach demonstrates significant improvements in task automation, reduced human intervention, and enhanced model performance. The MADS framework, which will soon be available as an open-source implementation, represents a pivotal contribution to the field of machine learning, promising to facilitate broader adoption and collaborative advancement.

The health status of Hungary's population is unfavorable, with significant differences in health indicators not only compared to the EU15 but also to the Visegrad countries. Unfavorable health indicators can be disproportionate and particularly affect vulnerable groups, such as people with disabilities. The aim of the present study is to compare the health behaviour and indicators of adolescents with disabilities in Hungary with those of the HBSC survey in the Visegrad countries, and to compare the results of the Hungarian special needs adolescent population with those of the Visegrad countries. Eating habits are unfavourable for both the Visegrad countries and the young people we studied. Children with disabilities have significantly higher rates of schoolwork stress compared to other countries. Significantly higher prevalence of somatic complaints and worse mental well-being parameters higher in Hungary than in the other Visegrad countries. The results suggest that further interventions are needed in Hungary and that differentiated, professionalised health promotion is needed for young people with disabilities. The researchers propose to extend the research to adolescents with disabilities living in the Visegrad countries, on the basis of which a methodology for injury-specific health promotion could be developed, including through interna-tional interprofessional cooperation.

Accurate diagnosis for the 400 million people with rare diseases is critical for healthcare decisions, prognosis, understanding disease mechanisms, and identification of treatments. Despite advances in genome sequencing, barriers such as high interpretation costs, diagnostic expertise, throughput associated delays, and uncertain variant classifications persist, with demand exceeding capacity. Many variant classification methods focus narrowly on specific consequences, leading to the use of complex integrative pipelines that often overlook transcript variability and lack prediction transparency. To overcome these limitations, we introduce DITTO. This transparent, transcript-aware machine-learning method demonstrates superior overall performance in accuracy, recall, and precision when compared to existing tools. DITTO is publicly available at https://github.com/uab-cgds-worthey/DITTO

With the increasingly stringent airworthiness standards, the noise generated during the rotorcraft flight is gradually attracting people’s attention. It widely operated helicopters at low altitudes because of their maneuverability. The way to reduce the noise caused by the complex airflow of the helicopter rotor system has progressively become a hot topic for researchers. Using a hybrid acoustic analysis method, this paper investigates the improvement of the noise and thrust of the helicopter’s tail rotor through the tail rotor structural parameters. For the basic model, the turbulence simulation is performed using an incompressible detached eddy simulation (DES) method, and the Lighthill acoustic analog equation is calculated using the finite element method (FEM). We verified the accuracy of the method through wind tunnel tests. We chose a series of structural parameters for sound simulation and fluid simulation calculations. The results indicate that the modified tail rotor noise reduced by 16.5 dBA and the total thrust increased by 19.9% from the prototype model. This work can enhance the duct tail rotor design to improve aerodynamic and aeroacoustic performance.

Promoting the sustainable development of resource-based cities is of great significance to the ecological protection and high-quality development of the Yellow River Basin. Combining the environmental status and economic development, we objectively evaluate the ecological safety level of resource-based cities in the Yellow River Basin, compare and analysis the main factors affecting the ecological safety of different resource-based cities, and formulate precise and differentiated ecological safety protection measures in river basins to achieve high-quality development. Taking the Yellow River Basin as an example, this paper analyses the ecological level of the Yellow River Basin based on the theory of sustainable development, calculates the ecological safety level of 30 resource-based cities in the Yellow River Basin from 2006 to 2020 by TOPSIS model, and makes convergence analysis by classification. Through the DID empirical test of sustainable development planning policy on ecological safety factors, distinguish the development characteristics of different resource-based cities. The results show that: (1) the ecological safety level of resource-based cities in the Yellow River Basin is generally developing well, and there are differences among different types of resource-based cities; (2) the kinetic energy of sustainable development of resource-based cities in the Yellow River Basin is mainly industrial transformation, and the power of science and technology is insufficient; (3) local governments pay limited attention to environmental protection, and the sustainable development planning of resource-based cities in 2013 mainly promotes the adjustment of industrial structure of resource-based cities.

This paper delves into the application of digital twin monitoring techniques for enhancing offshore floating wind turbine performance, with a detailed case study. We explore the practical implementation of digital twins and their efficacy in optimizing operations and predictive maintenance. Our findings emphasize digital twins' potential as a valuable tool for renewable energy, driving efficiency and sustainability in offshore floating wind installations.

Mass spectrometry (MS) has revolutionized clinical chemistry, offering unparalleled capabilities for biomolecule analysis. This review explores the growing significance of MS, particularly when coupled with liquid chromatography (LC-MS), in identifying disease biomarkers and quantifying biomolecules for diagnostic and prognostic purposes. The unique advantages of MS in accurately identifying and quantifying diverse molecules have positioned it as a cornerstone in personalized medicine advancement. MS-based technologies have transformed precision medicine, enabling comprehensive understanding of disease mechanisms and patient-specific treatment responses. LC-MS has shown exceptional utility in analyzing complex biological matrices, while high-resolution MS has expanded analytical capabilities, allowing detection of low-abundance molecules and elucidation of complex biological pathways. The integration of MS with other techniques, such as ion mobility spectrometry, has opened new avenues for biomarker discovery and validation. As we progress towards precision medicine, MS-based technologies will be crucial in addressing the challenges of individualized patient care, driving innovations in disease diagnosis, prognosis, and treatment strategies.

Carnivore protoparvovirus 1 (CPPV-1) is a DNA virus causing gastrointestinal disease and immunosuppression in various terrestrial carnivores. Domestic dogs and cats are considered the primary CPPV-1 reservoirs. The habitat overlaps of wild carnivores and free-roaming dogs increases the threat of CPPV-1 transmission between them. This study explored the CPPV-1 distribution among wild carnivores through PCR screening and compared the DNA sequences of the partial capsid protein (VP2) between wild and domestic carnivores. In total, 181 samples were screened for the CPPV-1 VP2 gene, including 32 masked palm civets (Paguma larvata), 63 Chinese ferret badgers (Melogale moschata), and 86 crab-eating mongooses (Herpestes urva), from 2015 to 2019 in Taiwan. The average prevalence of CPPV-1 was 17.7% (32/181), with the highest prevalence in masked palm civets (37.5%). In addition, a masked palm civet was coinfected with two CPPV-1 strains. Among the 33 partial VP2 gene sequences, 23 were identical to sequences amplified from domestic dogs and cats in Asia and the remaining 10 were identified for the first time. This study demonstrated that CPPV-1 has circulated between domestic and wild carnivores in rural Taiwan. Therefore, further population control and health management of free-roaming domestic carnivores are recommended.

Facial acne is a prevalent dermatological condition regularly observed in the general population. This study introduces a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy-paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrates improvement in performance, offering a novel direction for future acne analysis.

The topic of predictive toxicology has been greatly influenced by recent progress in comprehending drug toxicity processes and enhancing medication development. The integration of omics technologies, such as transcriptomics, proteomics, and metabolomics, with traditional toxicological assessments has yielded extensive knowledge about the biological pathways implicated in drug-induced toxicity. The utilization of a multi-omics method amplifies the ability to identify biomarkers that can detect toxicity at an early stage, hence enhancing the safety profile of novel therapeutic medicines. Machine learning and in silico models, such as QSAR models and multi-task deep learning algorithms, have become essential tools. They have shown great accuracy in predicting toxicity endpoints and have helped in the identification of new biomarkers and therapeutic targets. The introduction of microphysiological systems and PBPK modeling has enhanced the transfer of preclinical discoveries to clinical results, providing more precise forecasts of human reactions to medications. Notwithstanding these progressions, obstacles such as the diversity of data and the complex nature of omics data require sophisticated computational techniques for efficient analysis. Continued cooperation and established procedures are crucial to fully utilize these technologies, guaranteeing the creation of safer and more efficient medicinal agents.

Therapeutic protein engineering has revolutionized medicine by enabling the development of highly specific and potent treatments for a wide range of diseases. This review examines recent advances in computational and experimental approaches for engineering improved protein therapeutics. Key areas of focus include antibody engineering, enzyme replacement therapies, and cytokine-based drugs. Computational methods like structure-based design, machine learning integration, and protein language models have dramatically enhanced our ability to predict protein properties and guide engineering efforts. Experimental techniques such as directed evolution and rational design approaches continue to evolve, with high-throughput methods accelerating the discovery process. Applications of these methods have led to breakthroughs in affinity maturation, bispecific antibodies, enzyme stability enhancement, and the development of conditionally active cytokines. Emerging approaches like intracellular protein delivery, stimulus-responsive proteins, and de novo designed therapeutic proteins offer exciting new possibilities. However, challenges remain in predicting in vivo behavior, scalable manufacturing, immunogenicity mitigation, and targeted delivery. Addressing these challenges will require continued integration of computational and experimental methods, as well as a deeper understanding of protein behavior in complex physiological environments. As the field advances, we can anticipate increasingly sophisticated and effective protein therapeutics for treating human diseases.

Protein dynamics play a crucial role in biological function, encompassing motions ranging from atomic vibrations to large-scale conformational changes. Recent advancements in experimental techniques, computational methods, and artificial intelligence have revolutionized our understanding of protein dynamics. Nuclear magnetic resonance spectroscopy provides atomic-resolution insights, while molecular dynamics simulations offer detailed trajectories of protein motions. The integration of machine learning, exemplified by AlphaFold2, has accelerated structure prediction and dynamics analysis. These approaches have revealed the importance of protein dynamics in allosteric regulation, enzyme catalysis, and intrinsically disordered proteins. The shift towards ensemble representations of protein structures and the application of single-molecule techniques have further enhanced our ability to capture the dynamic nature of proteins. Understanding protein dynamics is essential for elucidating biological mechanisms, designing drugs, and developing novel biocatalysts, marking a significant paradigm shift in structural biology and drug discovery.

The spread of fake news poses a serious threat to public trust and informed decision-making. The emergence of AI-generated fake news exacerbates this issue, as it can be produced more rapidly and convincingly than human-generated content. Addressing this issue, our paper introduces a robust approach to detect AI-generated fake news that is applicable across major disinformation domains: Politics and Elections, Health and Medicine, Science and Technology, and Entertainment and Celebrities. Our models differentiate between AI-generated and human-generated news articles while assessing their truthfulness. Utilizing large language models such as ChatGPT, we curated datasets spanning both AI and human generated fake and genuine news. Following extensive data preprocessing and the application of diverse feature extraction techniques, our models were trained using multiple machine learning algorithms. Our results show the feasibility of accurately identifying AI-generated fake news, thereby adding a significant layer of defense in combating misinformation across various sectors. In addition, we have explored the potential utility of transferable machine learning models trained on data from one domain (e.g., politics), when tested on another domain (e.g., health).

In this paper, we investigate the following chemotaxis-haptotaxis model $$\left\{ \begin{array}{ll} u_{t}=\nabla\cdot (D(u) \nabla u)- \nabla\cdot (H(u)\nabla v)- \nabla\cdot (I(u)\nabla w)+ u(a-\mu u^{k-1}-\lambda w),\\ v_{t}=\triangle v-v+u^{\gamma},\\ w_{t}=-v w \end{array}\right.\eqno(*) $$ under homogenous Neumann boundary condition and for a bounded domain $ \Omega \subset \mathbb{R}^{n} (n\geq2)$, with $\lambda, \mu, \gamma >0$, $k>1$, $a \in \mathbb{R}$, and $D(u)\geq K_{D} (u+1)^{m-1}$, $0\leq H(u)\leq \chi u(u+1)^{-\alpha}$, $0\leq I(u)\leq \xi u(u+1)^{-\beta}$ for $K_{D}, \chi, \xi>0, m, \alpha, \beta\in \mathbb{R}$. It has been demonstrated that (i) For $0\gamma-k+1$ and $\beta>1-k$, problem ($*$) admits a classical solution $(u, v, w)$ which is globally bounded. (ii) For $\frac{2}{n}\gamma-k+\frac{1}{e}+1$ and $\beta>\max\{\frac{(n\gamma-2)(n\gamma+2k-2)}{2n}-k+1, \frac{(n\gamma-2)(\gamma+\frac{1}{e})}{n}-k+1\}$ or $\alpha>\gamma-k+1$ and $\beta>\max\{\frac{(n\gamma-2)(n\gamma+2k-2)}{2n}-k+1, \frac{(n\gamma-2)(\alpha+k-1)}{n}-k+1\}$, problem ($*$) admits a classical solution $(u, v, w)$ which is globally bounded.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

In order to solve the problem of structure damage location and degree identification, the weighted mean of vectors algorithm (INFO), a high-performance optimization one, was first introduced to identify structure damage. The genetic algorithm (GA) are improved to obtain a refined genetic algorithm (RGA). An objective function is constructed by combining the dynamic response transfer-ratio without modal analysis. INFO and RGA algorithms are used to optimize the objective function for damage identification. Though simulations, the INFO, RGA, GA algorithms were used to identify the damage on a simply supported beam and cantilevered plate with different levels of noise and different frequency spacing of pickup points. The simulations verify the effectiveness of the three damage identification methods, and the INFO algorithm has the highest damage identification accuracy, the RGA is second and the GA is the worst.

Effective communication in automated chat systems hinges on the ability to understand and respond to context. Traditional models often struggle with determining when additional context is necessary for generating appropriate responses. This paper introduces Context-Aware BERT (CA-BERT), a transformer-based model specifically fine-tuned to address this challenge. CA-BERT innovatively applies deep learning techniques to discern context necessity in multi-turn chat interactions, enhancing both the relevance and accuracy of responses. We describe the development of CA-BERT, which adapts the robust architecture of BERT with a novel training regimen focused on a specialized dataset of chat dialogues. The model is evaluated on its ability to classify context necessity, demonstrating superior performance over baseline BERT models in terms of accuracy and efficiency. Furthermore, CA-BERT's implementation showcases significant reductions in training time and resource usage, making it feasible for real-time applications. The results indicate that CA-BERT can effectively enhance the functionality of chatbots by providing a nuanced understanding of context, thereby improving user experience and interaction quality in automated systems. This study not only advances the field of NLP in chat applications but also provides a framework for future research into context-sensitive AI developments.

In the dynamic landscape of modern education, characterized by an increasingly active involvement of IT technologies in learning, the imperative to transfer to students the skills necessary to integrate Artificial Intelligence (AI) into the process represents an important goal. This paper presents a novel framework for knowledge transfer, diverging from traditional programming language-centric approaches by integrating PSoC 6 microcontroller technology. This framework establishes a cyclical learning cycle encompassing theoretical fundamentals and practical experimentation, fostering AI literacy at the edge. Through a structured combination of theoretical instruction and hands-on experimentation, students develop proficiency in understanding and harnessing AI capabilities. Emphasizing critical thinking, problem-solving, and creativity, this approach equips students with the tools to navigate the complexities of real-world AI applications effectively. By leveraging PSoC 6 as an educational tool, a new generation of individuals is efficiently cultivated with essential AI skills. These individuals are adept at leveraging AI technologies to address societal challenges and drive innovation, thereby contributing to long-term sustainability initiatives. Specific strategies for experiential learning, curriculum recommendations, and results of knowledge application are presented, aimed at preparing students to excel in a future where AI will be omnipresent and indispensable.

Artificial Intelligence (AI) describes computer systems able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and language translation. Examples of AI techniques are machine learning, neural networks and deep learning. AI can be applied in many different areas, such as econometrics, biometry, e-commerce and the automotive industry. In recent years, AI has found its way into healthcare as well, helping doctors to make better decisions (‘clinical decision support’), localizing tumors in magnetic resonance images, reading and analyzing reports written by radiologists and pathologists, and much more. However, AI has one big risk: it can be perceived as a ‘black box’, limiting trust in its reliability, which is a very big issue in an area in which a decision can mean life or death. As a result, the term Explainable Artificial Intelligence (XAI) has been gaining momentum. XAI tries to ensure that AI algorithms (and the resulting decisions) can be understood by humans. In this narrative review, we will have a look at the current status of XAI in healthcare, describe several issues around XAI, and discuss whether it can really help healthcare to advance, for example by increasing understanding and trust. Finally, alternatives to increase trust in AI are discussed, as well as future research possibilities in the area of XAI.

This study highlighted the core and critical tenets that constitute culturally responsive science assessments (CRSciA) for K-12 education and aligned them with the capabilities of generative AI (GenAI). The tenets were identified based on their dominance in the literature, including Indigenous Language, Race and Ethnicity, Religious Beliefs, Family and Community, and Indigenous Knowledge. These tenets were instrumental in developing the GenAI-CRSciA framework and the subsequent prompts to generate CRSciAs aligned with the Next Generation Science Standards (NGSS) while comparing it with standard prompt strategies. The results showed that the GenAI-CRSciA prompting approach outperformed normal prompting strategies in terms of generating CRSciAs, proving its effectiveness in addressing the ongoing challenges in science assessments. Even though the GenAI-CRSciA framework presented assessments that cover a range of the cultural backgrounds, it presents potential challenges such as compromising curricula core competencies and overgeneralization of students’ backgrounds; overlooking subcultural variations within a country or region, for example differences between urban and rural students, or between different ethnic or linguistic groups within the same nation, which can lead to bias and less effective CRSciA outputs. To address this, we recommend that teachers provide comprehensive and specific background information about their students when using the GenAI-CRSciA prompting, ensuring that the generated content is truly reflective of the students’ unique cultural contexts. In larger class settings, teachers could implement comprehensive local data indexing, where detailed student background information is uploaded and retrievable for use in crafting more personalized CRSciAs. We strongly recommend educators to make conscious efforts to validate the generated assessments with input from human experts, including community or family, educators, and even students who are knowledgeable about the cultural nuances. We also suggest continuous professional development would be necessary to enhance teachers’ understanding of the cultural tenets.

In this paper, Fe-Cr-C-N-Al-Y wear-resistant surfacing alloy was prepared by open arc surfacing with self-shielded flux-cored wire. The wear properties of the surfacing alloy were analyzed by MLS-23 rubber wheel wet sand wear tester. The phase composition and microstructure of the surfacing alloy were analyzed by XRD, SEM, EBSD and TEM, and the strengthening mechanism and wear mechanism of the alloy were discussed. The results show that the microstructure of Fe-Cr-C-N-Al-Y surfacing alloy is composed of M + γ-Fe + M7C3 + AlN. When the content of nano-Y2O3 is 0.456wt. %, the formability of the surfacing alloy is the best and the wetting angle is the smallest, which is 50.8°, AlN and M7C3 precipitate the most, and the microstructure grain is the smallest. At this time, the hardness value of the surfacing alloy is up to 62.3 HRC, which is 11.8 % higher than that of the unmodified surfacing alloy. The minimum wear weight loss is 0.125 g, and the wear resistance is increased by 41.86 %. The wear mechanism of surfacing alloy is mainly plastic deformation mechanism, and the material removal process is micro cutting and furrow wear.

The terrain of Changbai Mountain has great influence on the distribution of atmospheric flows and the occurrence and development of precipitation. This study quantitatively analyzes the regional characteristic of topographic perturbations and the relationship between terrain, wind and precipitation in Changbai Mountain region, by using a spectral analysis of the two-dimensional discrete cosine transform. Three domains with relatively heavy summer precipitation are selected as the study region. The results indicate that the overall terrain of Changbai Mountain region exhibits anisotropic characteristics. The terrain spectra of domain B are less than those of domain A and C across the whole wavelength (λ) bands, indicating that the large-scale topographic perturbations of domain B are relatively weak. The largest topographic spectral peak of domain C shows the most pronounced undulation of terrain among the three domains. The dominant wavelengths of terrain height variance for domain A and C, both close to the respective maximum wavelengths, indicate more prominent large-scale topographic perturbations. For domain A, the variation of the precipitation spectra is consistent with that of the wind spectra at the wavelength bands of λ < 390 km, showing a high correlation between wind field and the occurrence of rainfall. The inverse relationship at larger wavelengths indicates that multiple factors contribute to the occurrence of rainfall. For domain B, there is consistency in the fluctuations of terrain spectra, precipitation spectra, and wind spectra at the wavelength bands of λ < 278.3 km, implying that the smaller-scale terrain has an important effect on the occurrence of summer precipitation. For domain C, the variations of terrain spectra, precipitation spectra, and wind spectra are almost consistent across the whole wavelength bands, indicating that the large-scale terrain and minor terrain both play a crucial role in atmospheric uplift and the occurrence and development of summer rainfall.

The discovery of the quantum tunnelling effect---the transmission of particles through a high potential barrier---was one of the most impressive achievements of quantum mechanics made in the 1920s. Responding to the contemporary challenges, I introduce a novel deep neural network (DNN) architecture that processes information using the effect of quantum tunnelling. I demonstrate the ability of the quantum tunnelling DNN (QT-DNN) to recognise optical illusions like a human. Hardware implementation of QT-DNN is expected to result in an inexpensive and energy-efficient neuromorphic chip suitable for applications in autonomous vehicles. The optical illusions recognition tests developed in this paper should lay foundations for cognitive benchmarking tasks for AI systems of the future, benefiting the fields of sociophysics and behavioural science.

The healthcare situation in Africa is characterized by limited resources and a high burden of disease, presenting significant challenges to the healthcare systems in the region. The integration of Artificial Intelligence (AI) technologies in African healthcare holds immense potential for addressing these challenges and improving health outcomes. This paper aims to provide a comprehensive understanding of the current healthcare landscape in Africa and the urgent need for AI-driven solutions.In addition to discussing the potential applications of AI in African healthcare, such as disease diagnosis, treatment planning, and medical imaging analysis, this manuscript seeks to shed light on the specific challenges hindering the implementation of AI in the region. By providing detailed examples and case studies, we aim to offer insights into the obstacles that need to be overcome and potential solutions that can be pursued.By leveraging AI technologies, Africa has the opportunity to revolutionize its health systems, bridging the gap in access to quality healthcare across the continent. The objective of this review article is to not only highlight the potential benefits that AI can bring to African healthcare but also to emphasize the urgent need for action and collaboration in implementing and scaling up AI innovations in the region. By doing so, African countries can pave the way for improved health outcomes and ensure that their populations receive the healthcare services they deserve.

Pain diagnosis remains a challenging task due to its subjective nature, the variability in pain expression among individuals, and the difficult assessment of the underlying biopsychosocial factors. In this complex scenario, artificial intelligence (AI) can offer the potential to enhance diagnostic accuracy, predict treatment outcomes, and personalize pain management strategies. This review aims at dissecting the current literature on computer-aided diagnosis methods. It also discusses how AI-driven diagnostic methods can be integrated into multimodal models that combine various data sources, such as facial expression analysis, neuroimaging, and physiological signals, with advanced AI techniques. Despite the significant advancements in AI technology, its widespread adoption in clinical settings faces crucial challenges. Ethical considerations related to patient privacy, biases, and lack of reliability and generalizability are the main issues. Furthermore, there is a need for high-quality real-word validation as well as the development of standardized protocols and policy rules to guide the implementation of these technologies in diverse clinical settings.

This work presents a novel approach for the study of the movement of droplets on inclined surfaces under the influence of gravity and chemical heterogeneities. The developed numerical methodology uses data-driven modeling to extend the applicability limits of an analytically derived reduced-order model for the contact line velocity. More specifically, while the reduced-order model is able to capture the effects of the chemical heterogeneities to a satisfactory degree, it does not account for gravity. To alleviate this shortcoming, datasets generated from direct numerical simulations are used to train a data-driven model for the contact line velocity, which is based on the Fourier neural operator and corrects the reduced-order model predictions to match the reference solutions. This hybrid surrogate model, which comprises of both analytical and data-driven components, is then integrated in time to simulate the droplet movement, offering a speedup of five orders of magnitude compared to direct numerical simulations. The performance of this hybrid model is quantified and assessed in different wetting scenarios, by considering various inclination angles and values for the Bond number, demonstrating the accuracy of the predictions as long as the adopted parameters lie within the ranges considered in the training dataset.

Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 811 papers initially identified, 26 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.

Explainable Artificial Intelligence (XAI) plays a vital role in increasing transparency and trust in machine learning models, particularly when applied to tabular data which is used in domains such as finance, healthcare, and marketing. This paper presents an extensive survey of XAI techniques used with tabular data and aims to analyze recent research developments since 2021. The survey classes and describes several XAI techniques pertinent to tabular data, it identifies challenges specific to this domain, and explores potential applications and emerging trends. Future research directions are outlined, concentrating on the need for clear definitions of terminology used, data security, user-centric explanations, enhanced interaction, robust evaluation metrics, and advancements in adversarial example-based analysis. The aim is to contribute to the evolving field of XAI, and provide insights for effective, trustworthy, and transparent decision-making using tabular data.

Building electric energy is characterized by a significant increase of its uses (e.g. vehicle charging), a rapidly declining cost of all related data collection and a proliferation of smart grid concepts, including diverse and flexible electricity pricing schemes. Not surprisingly, an increased number of approaches have been proposed for its modeling and forecasting. In this work, we place our emphasis on three forecasting related issues. First, on the forecasting explainability, i.e. the ability to understand and explain to the user what shapes the forecast. To this extent we rely on concepts and approaches that are inherently explainable, such as the evolutionary approach of genetic programming (GP) and its associated symbolic expressions, as well as the so-called SHAP (SHapley Additive eXplanations) values, which is a well established model agnostic approach for explainability, especially in terms of feature importance. Second, we investigate the impact of the training timeframe on the forecasting accuracy; this is driven by the realization that a fast training would allow for faster deployment of forecasting in real life solutions. And third, we explore the concept of counterfactual analysis on actionable features, i.e. features that the user can really act upon and which therefore present an inherent advantage when it comes to decision support. We have found that SHAP values can provide important insights into the model explainability. As for GP models, we have found comparable and in some cases superior accuracy when compared to its neural-network and time-series counterparts but a rather questionable potential to produce crisp and insightful symbolic expressions, allowing a better insight into the model performance. We have also found, and report here on an important potential especially for practical, decision support, solutions of counterfactuals built on actionable features and short training timeframes.

The field of computational protein engineering has been transformed by recent advancements in machine learning, artificial intelligence, and molecular modeling, enabling the design of proteins with unprecedented precision and functionality. Computational methods now play a crucial role in enhancing the stability, activity, and specificity of proteins for diverse applications in bio-technology and medicine. Techniques such as deep learning, reinforcement learning, and transfer learning have dramatically improved protein structure prediction, optimization of binding affin-ities, and enzyme design. These innovations have streamlined the process of protein engineering by allowing the rapid generation of targeted libraries, reducing experimental sampling, and en-abling the rational design of proteins with tailored properties. Furthermore, the integration of computational approaches with high-throughput experimental techniques has facilitated the development of multifunctional proteins and novel therapeutics. However, challenges remain in bridging the gap between computational predictions and experimental validation, and in ad-dressing ethical concerns related to AI-driven protein design. This review provides a compre-hensive overview of the current state and future directions of computational methods in protein engineering, emphasizing their transformative potential in creating next-generation biologics and advancing synthetic biology.

With buildings accounting for a significant portion of global energy consumption and greenhouse gas emissions, the application of artificial intelligence (AI) holds promise for enhancing sustainability in the building lifecycle. This systematic literature review addresses the current understanding of AI's potential to optimize energy efficiency and minimize environmental impact in building design, construction, and operation. A comprehensive literature review and synthesis were conducted to identify AI technologies applicable to sustainable building practices, examine their influence, and analyze the challenges of implementation. The review was guided by a meticulous search strategy utilizing keywords related to AI application in sustainable building design, construction, and operation. The findings reveal AI's capabilities in optimizing energy efficiency through intelligent control systems, enabling predictive maintenance, and aiding design simulation. Advanced machine learning algorithms facilitate data-driven analysis and prediction, while digital twins provide real-time insights for informed decision-making. Furthermore, the review identifies barriers to AI adoption, including cost concerns, data security risks, and challenges in implementation. AI presents a transformative opportunity to enhance sustainability in the built environment, offering innovative solutions for energy optimization and environmentally conscious practices. However, addressing technical and practical challenges will be crucial for the successful integration of AI in sustainable building practices.

Background: Although several studies have been conducted on the use of Artificial Intelligence (AI) in mammography (MG), research focusing on the diagnosis of metachronous bilateral breast cancer (BC), which is typically more challenging to diagnose, remains limited. This study assessed whether AI could enhance the detection of BC, achieving earlier or more accurate diagnoses than radiologists in cases of metachronous contralateral BC. Methods: The study included patients who underwent unilateral BC surgery and subsequently developed contralateral BC during follow-up. We evaluated the capability of the AI-supported MG diagnostic system FxMammo™ (FathomX Pte Ltd, Singapore) to diagnose BC more accurately or earlier than radiologists' assessments. This evaluation was supplemented by reviewing MG readings by radiologists. Results: Out of 1,101 patients who underwent surgery, 10 patients who had initially received a partial mastectomy and later developed contralateral BC were analyzed. The AI system identified malignancies in 6 cases (60%), while radiologists identified 5 cases (50%). Notably, two cases (20%) were diagnosed solely by the AI system. Additionally, for these cases, the AI system had identified malignancies a year prior to the conventional diagnosis. Conclusions: This study highlights the AI system's effectiveness in diagnosing metachronous contralateral BC via MG. In some cases, the AI system consistently diagnosed cancer at earlier than radiological assessments.

The extraction methods for carotenoids, xanthophylls and chlorophylls are essential processes involved in the recovery of bioactive compounds from a wide variety of natural sources, including plants, marine organisms, microorganisms and animals. These bioactive compounds, characterized by their significant functional and structurally active properties, play a crucial role in various industries, such as pharmaceuticals, nutraceuticals and food. Due to their presence in small quantities and conjugated form in nature, the extraction of these compounds can be laborious and often requires meticulous purification steps. Interestingly, the primary and secondary metabolites present in plants contribute significantly to the production of these bioactive compounds, adding to their complexity and importance. Notably, carotenoids, as natural pigments with antioxidant and nutritional properties, are known for offering numerous health benefits and are instrumental in various biological processes, including the photoprotection of plants and the prevention of chronic degenerative diseases. It is fascinating to observe that by-products generated from agricultural activities and food processing serve as abundant sources of these bioactive compounds, aligning with the principles of the circular economy and sustainable resource management. Given the diverse health benefits and multifaceted applications of these natural pigments, there is a growing interest in not only extracting but also utilizing them for industrial, nutritional and pharmacological purposes.

This research aims to elucidate the organizational patterns of interregional economic interdependence to enhance our comprehension of the national economy's structure at a regional scale. Employing a multilayer network model, this study represents economic interdependence among Indonesian regions, utilizing the InterRegional Input-Output (IRIO) table. Through the application of various metrics, such as degree and strength distribution, assortativity coefficient, and global and local rich club coefficient, to the multilayer IRIO network, we uncover the organizational patterns of economic exchanges between provinces and economic sectors within Indonesia. Our findings demonstrate that a multilayer network approach reveals the heterogeneous and complex structure of the national economy at the regional level. By analyzing the assortativity pattern and global rich-club coefficient, we illustrate that the IRIO network exhibits a hierarchical organization, where significant provincial-sector nodes are interconnected and form dense rich clubs, extending from a few structural cores to peripheral regions. Additionally, we identify distinct connectivity patterns of non-rich nodes based on their incoming and outgoing relations. The insights gained from this study have implications for the macro-control of regional development.

Cloud Computing is a promising and emerging technology that is rapidly being adopted by many IT companies due to a number of benefits that it provides, such as large storage space, low investment cost, virtualization, resource sharing, etc. Users are able to store a vast amount of data and information in the cloud and access it from anywhere, anytime on a pay-per-use basis. Since many users are able to share the data and the resources stored in the cloud, there arises a need to provide access to the data to only those users who are authorized to access it. This can be done through access control schemes which allow the authenticated and authorized users to access the data and deny access to unauthorized users. In this paper, a comprehensive review of all the existing access control schemes has been discussed along with analysis. Keywords: role-based access control, attribute-based access control, attribute-based encryption

In an era where the proliferation of large language models blurs the lines between human and machine-generated content, discerning text authenticity is paramount. This study investigates transformer-based language models—BERT, RoBERTa, and DistilBERT—in distinguishing human-written from machine-generated text. By leveraging a comprehensive corpus, including human-written text from sources such as Wikipedia, WikiHow, various news articles in different languages, and texts generated by OpenAI's GPT-2, we conduct rigorous comparative experiments. Our findings highlight the superior effectiveness of ensemble learning models over single classifiers in this critical task. This research underscores the versatility and efficacy of transformer-based methodologies for a wide range of natural language processing applications, significantly advancing text authenticity detection systems. The results demonstrate competitive performance, with the transformer-based method achieving an F-score score of 0.83 with RoBERTa-large (monolingual) and 0.70 with DistilBERT-base-uncased (multilingual).

Based on the detailed exploration of AI techniques for the early identification of learning difficulties in education, this study underscores the pivotal role of educational data analysis in enhancing student outcomes. Educators can proactively identify and address learning challenges through systematic data collection and analysis, thereby minimizing long-term academic obstacles and emotional stress. The integration of AI, particularly through natural language processing and computer vision technologies, facilitates personalized learning paths and real-time interventions, offering tailored support that maximizes each student's learning potential. These advancements optimize educational resource allocation and foster a more inclusive and effective learning environment, paving the way for future advancements in personalized education and intelligent teaching practices.

Conventional traceability systems in Cambodian agriculture, such as Rubber Supply Chain Management (RSCM), often struggle to provide timely data and fair market prices, leading to mistrust among stakeholders, exploitation by intermediaries, and hindering progress towards ethical sourcing and sustainable practices. This research aims to showcase the potential of integrating blockchain technology, the Internet of Things (IoT), the InterPlanetary File System (IPFS), and Differential Privacy (DP) methods to empower Cambodian rubber farmers. By enhancing transparency, facilitating fair pricing, and promoting sustainable methods in the rubber industry, this integrated approach leverages Hyperledger Fabric (HLF) to create a decentralized and secure system for tracking rubber from its source to the end consumer. Integration with IPFS ensures secure and easily accessible data storage, further enhancing the system’s reliability. Additionally, the implementation of differential privacy techniques safeguards confidential data during information sharing among farmers and supply chain stakeholders, minimizing potential privacy concerns. This comprehensive system encourages consumers to make ethical and sustainable alternative options by providing accessible information on harvesting methods, processing procedures, labor conditions, and environmental impacts. The potential benefits extend beyond Cambodia, serving as a model for other developing countries aiming to modernize and enhance the agricultural distribution networks. Our results show that transaction send rates (TPS) and throughput in systems with and without differential privacy grow with increased transaction volumes. However, the system without differential privacy achieves greater scalability and efficiency above a certain threshold. However, it offers a slightly reduced latency, reflecting a trade-off between privacy and performance efficiency in blockchain-based agricultural traceability systems.

Single-phase-to-ground fault in non-effectively grounded systems poses serious public safety concern. Along with increasing deployment of low-voltage (LV) sensors, new opportunities and ways are created for solving this traditional problem in distribution systems. A new approach, identifying primary single-phase-to-ground line fault and locating it through measurement data from smart sensors deployed in the secondary side of distribution transformers, is proposed in this paper. When a fault occurs in primary distribution feeder, the transient aerial mode voltage (AMV) of each LV smart sensor is calculated. The fault line can be identified by an abrupt change value of AMV at LV side. Next, by finding the position of the maximum value of this AMV from LV sensors on the fault line, the fault location can be pinpointed to two neighboring distribution transformers. The proposed method has been proven to be efficient and reliable by simulation studies.

Peri-implant infective diseases seem to be the most common cause for the late dental implant failure. Therefore, peri-implant microbiota has been intensively studied in modern implantology. Many studies showed a presence of extremely varied microflora in cases of peri-implant infective diseases. The main scope of this observational single-blind study was to analyze the presence of some microbial species in a group of patients with clinical signs of peri-implant mucositis compared to two other groups (patients treated with dental implants but without any clinical signs of peri-implant inflammation and patients treated with no dental implants). The identification of microorganisms was followed by an antibiogram in order to find their sensitivity to various antibiotics. The results showed a microbiota not necessarily specific for each situation (peri-implant infective diseases, healthy tissues around dental implants and healthy natural teeth and gums) with species like Candida albicans, Neisseria mucosa, Prevotella, Staphylococcus aureus, Streptococcus and others. Peri-implant infective diseases presented more bacterial species than other conditions.

Genetic similarity determines the extent to which two genotypes share common genetic material. It can be measured in various ways, such as comparing DNA sequences, proteins, or other genetic markers. The significance of genetic similarity is multifaceted and encompasses various fields, including evolutionary biology, medicine, forensic science, animal and plant breeding, and anthropology. Genetic similarity is an important concept with wide application across different scientific disciplines. In the presented study, six measures for calculating genetic similarity were compared: Euclidean, Jaccard, Kulczyński, Sokal and Michener, Nei, and Rogers. The research material included 21 rapeseed genotypes (ten interspecific Brassicaceae hybrids of F2 generation, and 11 of their parental forms) and 146 alleles, obtained using 21 ISSR molecular markers. The results indicate that the research material was divided into two identical groups using any of the proposed methods, despite differences in the values of genetic similarity coefficients. Two of the presented measures of genetic similarity (Sokal and Michener, and Euclidean) were the same.

Cancer is one of the leading causes of death, making timely diagnosis and prognosis very important. Utilization of AI (artificial intelligence) enables providers to organize and process patient data in a way that can lead to better overall outcomes. This review paper aims to look at the varying uses of AI for diagnosis and prognosis and clinical utility. PubMed and EBSCO databases were utilized for finding publications from January 1, 2013, to December 22, 2023. Articles were collected using key search terms such as “artificial intelligence” and “machine learning.” Included in the collection were studies of the application of AI in determining cancer diagnosis and prognosis using multi-omics data, radiomics, pathomics, clinical and laboratory data. The resulting 89 studies were categorized into eight sections based on the type of data utilized and then further subdivided into two subsections focusing on cancer diagnosis and prognosis, respectively. 8 studies integrated more than one form of omics, namely genomics, transcriptomics, epigenomics, and proteomics. Incorporating AI into cancer diagnosis and prognosis alongside omics and clinical data represents a significant advancement. Given the considerable potential of AI in this domain, ongoing prospective studies are essential to enhance algorithm interpretability and to ensure safe clinical integration.

In an era marked by swift technological progress, the pivotal role of Artificial Intelligence (AI) is increasingly evident across various sectors, including local governments. These governmental bodies are progressively leveraging AI technologies to enhance service delivery to their communities, ranging from simple task automation to more complicated engineering endeavours. While more and more local governments are adopting AI, it is imperative to understand the functions, implications, and consequences of AI. Despite the growing importance of this domain, a significant gap persists within the scholarly discourse. This study strives to bridge this void by exploring the applications of AI technologies within the context of local government service provision and using this inquiry to generate lessons and best practices for similar smart city initiatives. Through a comprehensive grey literature review, we analysed 262 real-world AI implementations across 170 local governments worldwide. The findings underscore several key points: (a) There has been a consistent upward trajectory in the adoption of AI by local governments over the last decade; (b) Local governments from China, the US, and the UK are at the forefront of AI adoption; (c) Among local government AI technologies, Natural Language Processing and Robotic Process Automation emerge as the most prevalent ones; (d) Local governments primarily deploy AI across 28 distinct services; (e) Information management, back-office work, and transportation and traffic management are leading domains in terms of AI adoption. This study enriches the extant body of knowledge by providing an overview of existing AI applications within the sphere of local governance. It offers insights for smart city policymakers and decision-makers considering the adoption, expansion, or refinement of AI technologies in urban service provision. Additionally, it underscores the importance of using these insights to guide the successful integration and optimisation of AI in future smart city projects, ensuring they meet the evolving needs of communities.

1) Background: Several studies have shown the benefit of drawing when learning anatomy. Virtual Reality (VR) also appears to be useful to increase the understanding of the location of anatomical structures. This study aims to describe how students in an Operating Room Nursing (OR nursing) master study program perceive the benefit of active learning methods, including drawing and the use of VR. 2) Methods: We combined these two methods in a class of 29 students. 38 half-finished drawings of anatomical structures were made. The students were to complete these during lectures with guidance from the teacher. The students also attended a two-hour VR session where they were to find various anatomical structures. A paper questionnaire was applied to evaluate the teaching program. Data were analyzed statistically. 3) Results: The students highly appreciated these learning methods. They reported that drawing made them work more actively during lectures and increased their learning outcome. They also perceived that the use of VR technology increased their understanding of the location of anatomical structures. 4) Conclusion: The combination of drawing and VR technology may be of benefit to OR Nursing students when learning anatomy by both increasing student activity and learning outcomes.

This study proposes an image recognition method to assist swine farm managers in collecting health data related to pig feeding and excretion. Analyzing the correlation between sow health data and indoor air quality in the pigsties revealed significant influences of air quality indicators on sow health. Increased levels of TVOC, CO2, and temperature were found to negatively affect feeding health, while increased temperature, humidity, and PM10 were found to negatively impact excretion health. These findings provide a basis for evaluating variables when constructing future sow disease prediction models. Analyzing the correlation between pig health status and air quality can help swine farm managers improve sow production environments, reduce disease risks, enhance production efficiency, and provide valuable insights for future research on disease prediction models.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

This study explores the industrial property market in Hong Kong, a sector characterized by its unique features and atypical market behaviour. Particularly, this research employs machine learning techniques to predict property prices based on a set of features, including location, square footage, floor level, accessibility to mass transit railway station and the like. To ensure transparency and understanding, the Shapley value is employed to quantify the relative importance of each feature in predicting property prices. Our analysis reveals the existence of non–linear relationships among these features, as demonstrated by the wide distribution of SHAP values for most features, which are illustrated in a beeswarm plot that span both sides of the baseline. This finding indicates a complex interaction among such features as square footage, age, floor level, carpark, proximity to mass transit railway stations, location, and property prices. The results contribute valuable insights into the relationships between industrial property characteristics and their corresponding values, thereby equipping stakeholders with enhanced understanding of the market to support informed decision–making.

As artificial intelligence continues to advance, researchers are increasingly using machine learning algorithms to study the factors that make people more susceptible to phishing scams. Most studies in this area have taken one of two approaches: either they explore statistical associations between various factors and susceptibility, or they use complex models such as deep neural networks to predict phishing behavior. However, these approaches have limitations in terms of providing practical insights for individuals to avoid future phishing attacks and delivering personalized explanations regarding their susceptibility to phishing. In this paper, we propose a machine learning approach that leverages explainable artificial intelligence techniques to examine the influence of human and demographic factors on susceptibility to phishing attacks. Our analysis reveals that psychological factors such as impulsivity and conscientiousness, as well as appropriate online security habits, significantly affect an individual's susceptibility to phishing attacks. Furthermore, our individualized case-by-case approach offers personalized recommendations on mitigating the risk of falling prey to phishing exploits, considering the specific circumstances of each individual.

The demand for explainable and transparent models increases with the continued success of reinforcement learning. In this article, we explore the potential of generating shallow decision trees (DT) as simple and transparent surrogate models for opaque deep reinforcement learning (DRL) agents. We investigate three algorithms for generating training data for axis-parallel and oblique DTs with the help of DRL agents ("oracles") and evaluate these methods on classic control problems from OpenAI Gym. The results show that one of our newly developed algorithms, the iterative training, outperforms traditional sampling algorithms, resulting in well-performing DTs that often even surpass the oracle from which they were trained. Even higher dimensional problems can be solved with surprisingly shallow DTs. We discuss the advantages and disadvantages of different sampling methods and insights into the decision-making process made possible by the transparent nature of DTs. Our work contributes to the development of not only powerful but also explainable RL agents and highlights the potential of DTs as a simple and effective alternative to complex DRL models.

The development of plant-based meat analogues has become a significant challenge for the food industry in recent years due to the increasing demand for sustainable and healthier proteins in the context of a global protein transition. Plant-based meat analogues imitate the visual, textural, and chemical properties of traditional meat products and are required to closely resemble meat to appeal to consumers. In addition, consumers demand natural, clean-label, and nutritional and healthy products. To address these challenges, the food industry must develop highly healthy, nutritious, and E-number-free meat analogue products. Understanding the functionality of each ingredient and its role in the food matrix is crucial to being a key player in the innovation of the meat analogues market. This review provides updated information on the primary ingredients utilized for the development of plant-based burger meat alternatives and their functionality. The key components of meat analogue burgers are outlined, including plant proteins, binding agents, fats and oils, flavorings, colorings, preservatives, fortificants, and clean-label considerations.

The rapid and accurate detection of viruses and the discovery of single nucleotide polymorphisms (SNPs) are crucial for disease management and understanding viral evolution. In this study, a pipeline for virus detection, validation, and SNP discovery from next-generation sequencing (NGS) data is presented. By integrating state-of-the-art bioinformatics tools with artificial intelligence, the pipeline processes raw sequencing data to identify viral sequences with high accuracy and sensitivity. Before aligning the reads to the reference genomes, quality control measures and adapter trimming are performed to ensure the integrity of the data. Unmapped reads are subjected to de novo assembly to reveal novel viral sequences and genetic elements. The effectiveness of the pipeline is demonstrated by the identification of virus sequences, illustrating its potential for the detection of known and emerging pathogens. SNP discovery is performed using a custom Python script that compares the entire population of sequenced viral reads to a reference genome. This approach provides a comprehensive overview of viral genetic diversity and identifies dominant variants and a spectrum of genetic variations. The robustness of the pipeline is confirmed by the recovery of complete viral sequences, which improves our understanding of viral genomics. This study highlights the synergy between traditional bioinformatics techniques and modern approaches, providing a robust tool for analyzing viral genomes and contributing to the broader field of viral genomics.

In this paper, we perform the neural cryptanalysis and comprehensively analyze five block ciphers, Data Encryption Standard (DES), Simplified DES (SDES), Advanced Encryption Standard (AES), Simplified AES (SAES), and SPECK. The vulnerability of the block ciphers is investigated in three different attacks, such as Encryption Emulation (EE), Plaintext Recovery (PR), Key Recovery (KR), and Ciphertext Classification (CC) attacks. For the plaintexts, randomly generated block-sized bit arrays and texts are used. The block ciphers apply different numbers of round functions in the encryption of the block-sized bit arrays, and they are investigated by using the deep learning models trained with different numbers of data in EE, PR, and KR attacks. Moreover, the block ciphers use two different text encryption methods, Word-based Text Encryption (WTE) and Sentence-based Text Encryption (STE), to encrypt the texts in various operation modes, and they are analyzed with deep learning models in EE, PR, and CC attacks. As a result, the block ciphers can be vulnerable to deep learning-based EE and PR attacks using a large amount of train data, and STE can improve the strength of the block ciphers, unlike WTE, which shows almost the same classification accuracy as the plaintexts, especially in CC attack. Additionally, when the keys that are the same as the plaintexts are used in encryption, the block ciphers can be perfectly broken in KR attack. Moreover, especially in KR attack, the RNN-based deep learning model shows higher average Bit Accuracy Probability (BAPavg) than the fully connected-based deep learning model, which is used more often in previous works of neural cryptanalysis. Furthermore, although the transformer-based deep learning model is a state-of-the-art model in Natural Language Processing (NLP), the RNN-based deep learning model is more suitable for CC attack and shows higher classification accuracy.

Maritime transport has adapted to recent political and economic shifts by addressing stringent pollution reduction requirements, redrawing transport routes for safety, reducing onboard technical incidents, managing data security risks and transitioning to autonomous vessels. The integration of AI-based technologies for fault diagnosis and decision-making, coupled with proper personnel training, has become essential for optimal ship operation, with AI-assisted predictive maintenance emerging as the key strategy to ensure onboard systems function within desired parameters and enhance equipment availability. This study proposes a machine-learning algorithm for evaluating onboard systems performance by analyzing sensor data and mapping it to fault patterns to estimate functional states, validated through tests on a seawater cooling system from an oil tanker, demonstrating operational efficiency and reliability. The immediate advantage is reduced time for fault diagnosis by rapidly assessing the system using operational data, the algorithm enabling real-time monitoring and fault data management to minimize efforts as part of predictive maintenance assisted by machine learning tools.

This study investigates the transformative impact of ChatGPT, a cutting-edge AI language model developed by OpenAI, on the financial sector. We explore ChatGPT's applications in financial analysis, focusing on its ability to perform tasks traditionally handled by human analysts. By creating a set of multi-step and advanced reasoning financial tasks, and establishing several task-specific evaluation metrics, our experimental results demonstrate that ChatGPT-4o can effectively perform both basic and some complex financial analysis tasks comparable to those executed by humans. However, our empirical evaluation reveals limitations in its performance on complex tasks that require comprehensive understanding and critical thinking. The study highlights the necessity for meticulous task formulation and robust evaluation to achieve consistent functionality. While ChatGPT enhances efficiency in financial analysis, its integration with human expertise remains crucial for effective decision-making. This study contributes to the understanding of AI's role in finance and provides insights into its potential and constraints, guiding future integration of AI technologies in financial practices.

Alkaline and alkaline-thermal activation were used in an attempt to synthesize zeolites using the sedimented illite fraction of raw Devonian clays from the Kuprava clay pit in Latvia. The Si/Al molar ratio of these clays is 2.79. Thermal and hydrothermal treatments were conducted using 6M and 10M NaOH solutions, along with different curing environments. The treated samples were analyzed using XRD, FTIR, and SEM, and were compared to the raw and calcined illite fraction samples. The main phase that forms after alkaline treatment is hydrosodalite (Na8[AlSiO₄]₆(OH)₂∙2H₂O). Using a higher concentration of NaOH leads to a significant increase in hydrosodalite formation. Increasing the curing temperature from 120°C to 600°C slightly reduces hydrosodalite formation due to the crystallization of the nepheline (Na₃K(Al₄Si₄O₁₆)) phase. This phase forms relatively intensively when the chemically treated samples are cured in a nitrogen environment at 600°C, thereby reducing the formation of hydrosodalite. The characteristic layered-fused structure of clay minerals remains in all chemically treated samples when cured at 600°C in air, but it does not remain when cured at the same temperature in nitrogen. The intensive formation of hydrosodalite is mainly achieved through hydrothermal treatment, along with a primary treatment using 10M NaOH. Considering the calculated size of the crystallites, treatment with 6M NaOH and curing at 120°C can also be seen as beneficial for hydrosodalite formation.

Over the last several decades there has been an arms race to acquire credentials as higher education has shifted from an elitist system to mass education. From an individual perspective, given the higher education system and labor market conditions, it is rational to pursue advanced qualifications. However, whether the education system delivers improvements in human capital or is principally a signaling mechanism is questionable. Estimates of the proportion of labor market rewards due to signaling range as high as 80%, suggesting that education is not only expensive but inefficient. In an increasingly transactional environment in which education providers are highly motivated by financial considerations, this situation is only likely to be exacerbated by the rapid developments in AI. The use of AI has the potential to make learning more effective but, given that many students see credential acquisition as transactional, it may reduce both human capital and the value of the signaling effect. If the credibility of the credentials offered is further damaged, the sustainability of the higher education sector in its present form and scale may well be unsustainable. We examine the evidence on credential inflation, returns to education and mismatch of graduates to jobs before analyzing how AI is likely to affect these trends. We then suggest possible responses of prospective students, education providers and employers to the growing adoption of AI in both education and the workplace. We conclude that the current offerings of generalist degrees, as opposed to vocational qualifications, are not sustainable and that to survive, even in a downsized form, the sector must respond to this disruptive technology by changing both the nature of its offerings and its methods of ensuring that the credentials they offer reflect genuine student learning.

This study aims to evaluate the utilization and effectiveness of artificial intelligence (AI) applications in managing symptoms of anxiety and depression. The primary objectives are to identify current AI tools, analyze their practicality and efficacy, and assess their potential benefits and risks. A comprehensive literature review was conducted using databases such as ScienceDirect, Google Scholar, PubMed, and ResearchGate, focusing on publications from the last five years. The search utilized keywords including "artificial intelligence," "applications," "mental health," "anxiety," "LLMs" and "depression". Various AI tools, including chatbots, mobile applications, wearables, virtual reality settings, and large language models (LLMs), were examined and categorized based on their functions in mental health care. The findings indicate that AI applications, including LLMs, show significant promise in symptom management, offering accessible and personalized interventions that can complement traditional mental health treatments. Tools such as AI-driven chatbots, mobile apps, and LLMs have demonstrated efficacy in reducing symptoms of anxiety and depression, improving user engagement and mental health outcomes. LLMs, in particular, have shown potential in enhancing therapeutic chatbots, diagnostic tools, and personalized treatment plans by providing immediate support and resources, thus reducing the workload on mental health professionals. However, limitations include concerns over data privacy, the potential for over-reliance on technology, and the need for human oversight to ensure comprehensive care. Ethical considerations, such as data security and the balance between AI and human interaction, were also addressed. The study concludes that while AI, including LLMs, has the potential to significantly aid mental health care, it should be used as a complement to, rather than a replacement for, human therapists. Future research should focus on enhancing data security measures, integrating AI tools with traditional therapeutic methods, and exploring the long-term effects of AI interventions on mental health. Further investigation is also needed to evaluate the effectiveness of AI applications across diverse populations and settings.

This paper explores innovative approaches to determining eigenvalues and eigenvectors through the combination of neural networks and traditional numerical methods. Traditional methods like the Newton-Raphson and Durand-Kerner algorithms are proven effective but often require good initial approximations and can be sensitive to the choice of starting points. In this study, we propose a hybrid approach that uses neural networks to generate better initial approximations, which are then iteratively refined using traditional methods. By combining the pattern recognition power of neural networks with the adaptability of traditional numerical methods, we demonstrate faster convergence and higher accuracy in determining eigenvalues and eigenvectors. Experimental results on various polynomials of different degrees and characteristics show that our hybrid approach outperforms individual methods, providing a more robust and efficient solution.

The emergence of prosumers, who actively participate in designing and producing goods, has generated interest in domestically manufactured products. Factors such as innovation, design methods, component reuse, prototyping, and digital fabrication empower prosumer designers to realize their ideas and enhance products to meet their specific design requirements. This article presents a case that combines bioinspired design methods with prosumer characteristics from the perspective of a designer who uses biological research results acting as a prosumer. By analyzing prosumer needs, bioinspired design, and domestic fabrication requirements, designers define the methods that best suit their possibilities. As a result of using biological information, the geometry of Samara seeds, propeller sizing, wind tunnel tests, and subsequent improvements, the custom design of a bioinspired microgenerator has been refined to the final design of a bicycle flashlight. The aim is to popularize a working approach that facilitates the interaction of design methods and reinforces domestic manufacturing processes. Implementing bioinspired design methods within the prosumer context offers a methodological alternative to transform the current economic model, promoting systemic sustainability and the development of proprietary technologies.

Object-level Simultaneous Localization and Mapping (SLAM) has gained popularity in recent years since it can provide a means for intelligent robot-to-environment interactions. However, most of these methods assume that the distribution of the errors is gaussian. This assumption is not valid under many circumstances. Further, these methods use a delayed initialization of the objects in the map. During this delayed period, the solution relies on the motion model provided by an Inertial Measurement Unit (IMU). Unfortunately, the errors tend to accumulate quickly due to the dead-reckoning nature of these motion models. Finally, the current solutions depend on a set of salient features on the object’s surface and not the object’s shape. This research proposes an accurate object-level solution to the SLAM problem with a 4.1 to 13.1 cm error in the position (0.005 to 0.021 of the total path). The developed solution is based on Rao-blackwellized Particle Filtering (RBPF) that does not assume any predefined error distribution for the parameters. Further, the solution relies on the shape and thus can be used for objects that lack texture on their surface. Finally, the developed tightly coupled IMU/camera solution is based on an undelayed initialization of the objects in the map.

This article explores the specific impact of artificial intelligence (AI) -driven data visualisation technologies in the user experience of the Internet industry. Through the introduction of machine learning and data mining technologies, AI has significantly improved the intelligence and automation of data visualization tools, promoting innovation in visualization methods and improving the quality and efficiency of data cleaning, processing, and analysis. In addition, AI has also promoted the development of personalised data visualization, providing users with a richer and more intuitive way to present data. This paper analyses the applications of AI-driven data visualization in machine learning, natural language processing, and computer vision. It demonstrates the positive effects of AI data visualization on user understanding and optimisation of models through practical feedback from Yellowbrick tools.

This literature review provides an in-depth exploration of the research conducted on the investigation and measurement of residual stress (RS) in Wire Arc Additive Manufacturing (WAAM) products, particularly focusing on how process parameters influence the phenomenon. RS plays a crucial role in determining the mechanical behavior and structural integrity of WAAM components. This review article gives an understanding of the relationship between process parameters and RS to optimize the WAAM processes and ensure the durability of the final products. It also summarizes key findings, measurement techniques, challenges, and future directions in this evolving field. The review also analyzes a measurement of RS in the products of WAAM as a function of process parameters depending on examining various research studies, techniques, and methodologies employed in their studies. Experimental measuring techniques and numerical analysis of RS to determine the impacts of RS in mechanical response in products of WAAM were discussed. By offering a comprehensive overview of current research trends and insights, this review serves as a valuable resource to guide future investigations, fostering the advancement of WAAM as a robust and efficient manufacturing technology.

The rising challenge of polyethylene terephthalate (PET) waste necessitates efficient collection methods to mitigate environmental impacts. The Analytic Hierarchy Process (AHP) is one of the Multi-Criteria Decision Analysis (MCDA) approaches utilized in this study. The Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) was used to rank each alternative according to the objective weight that AHP had produced. Also, sensitivity analysis was performed to determine how robust the findings were when considering equal weights and entropy weights to maximize PET waste collection techniques. The alternative achieved the objective of obtaining the best collection method, Threshold Plastic Bottle Waste Collection (Tpbw), out of all the three alternatives considered. Another MCDA approach, VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR), was used to compare the results and validate the ranking result achieved by the TOPSIS method. The VIKOR technique's validation of the TOPSIS approach showed that the outcomes were highly consistent. Data for the study were gathered from the archives of waste management companies on possible practices of plastic waste collection addressing costs, environmental impacts, social acceptance, feasibility, and efficiency. The findings provide a prioritized framework for enhancing PET waste collection strategies, contributing to sustainable waste management. Many criteria are considered when deciding the best collecting method for PET waste recycling, making it challenging. By using criteria importance, multi-criteria decision analysis (MCDA) was applied in this study, and the objective weight of the criteria was determined using the analytic hierarchy process (AHP). The five criteria considered in this study are Initial investment cost, Operational cost, Transportation cost, Environmental risk, Employment potential, and the objective weights allocated to them. AHP results 0.4952, 0.1997, 0.1565, 0.0870, and 0.0616 are respectively determined.

Future healthcare professionals can play a significant role in managing those with thoughts of suicide. This scoping review aims to determine healthcare students’ knowledge and attitude towards suicide. A systematic search was conducted across five databases: PubMed, CINAHL, EMBASE, PsycINFO, Cochrane, and DARE. Only primary studies written in English, from database inception until 31st December 2023 were included. A total of 44 studies were included. Overall, healthcare students demonstrated low to moderate confidence in managing patients with thoughts of suicide and low levels of relevant education despite acknowledging their importance in preventing suicide. Increased personal exposure to suicide was associated with increased suicide literacy, confidence in managing patients with thoughts of suicide, and reduced stigma. Demographics and culture were shown to affect knowledge and attitude as well. Further research is needed to better understand various contributing factors to healthcare students’ knowledge and attitude regarding suicide. Evaluating healthcare curricula should be considered to implement effective suicide training program.

This study aimed to evaluate a cantilever beam-type piezoelectric energy harvester operating on train-induced vibrations for powering Wireless Sensor Networks (WSNs) used in railway track monitoring systems. The harvester's behaviors under different conditions are simulated in MATLAB using the analytical model. Natural frequency, maximum deflection, and stress were calculated with greater precision using eigenfrequency and stationary analysis using COMSOL Multiphysics. At a base excitation of 2 g and a resonant frequency of 4.38 Hz, the simulated results showed that the developed energy harvester prototype could generate up to 14 V of AC output voltage and 550 mW of output power. These findings highlight the promising potential of the proposed energy harvester for transforming train mechanical energy into electrical power. This energy harvester's viability and dependability for real-world applications in monitoring railway tracks are supported by developed analytical and simulation models.

This paper introduces an innovative approach that enables automated and precise prediction of the steel's chemical composition based on the desired Jominy curve. The microstructure, and in fact the presence of martensite, is decisive for the hardness of the steel, so the study considered the occurrence of this phase at particular distances from the quenched-end of the Jominy sample. Steels for quenching and tempering and case hardening were investigated. With representative collected dataset of hardness values from quenched-end of Jominy specimen, microstructure and chemical composition of steels, the complex regression model was made using supervised artificial neural networks. The balance between cost and required hardenability can be achieved through optimizing the chemical composition of steel. This model of designing steel with required hardenability can be of great benefit in the mechanical engineering and manufacturing industry. The model is verified experimentally.

Cell viability refers to the proportion of living, healthy cells within a given population. This information is crucial in any cell-based research, especially in toxicology. Over the past century, numerous methods for assessing cell viability have been developed. These methods can be categorized into five main types: non-invasive cell structure damage, invasive cell structure damage, cell growth, cellular metabolism, and cell membrane potential. Each method operates on different principles and has its own advantages and disadvantages, making it essential for researchers to choose the method that best fits their experimental design. Despite the variety of cell viability methods available, most rely on indirect measurements of cell viability, which may compromise their accuracy. In this sense, there is insufficient information regarding their accuracy, highlighting the need for researchers to investigate the accuracy of both existing and future methods.