Application of AI

Generative AI applications are increasingly being used in higher education to support teachers and students as well as to take on tasks in the area of teaching support and administration. However, little is known about the specific use and institutional framework conditions in individual cases. The HIS Institute for Higher Education Development (HIS-HE) has therefore investigated the use of AI tools in teaching and learning as part of an exploratory study commissioned by the "University Forum on Digitalisation" (Hochschulforum Digitalisierung). As part of a call for contributions, 77 use cases from 51 German universities were identified. This article provides an overview of the results of the analysis and evaluation of these tried-and-tested use cases, describes trends in the current use of AI in teaching and learning and gives an insight into the added value and conditions for success of AI use.

This paper explores a proactive model of healthcare that integrates quantum computing, artificial intelligence, and multi-omics with traditional and integrative medicine. It outlines five pillars: (1) shifting from reactive “sick care” to proactive health, (2) precision and personalized prevention, (3) AI for early detection and quality improvement, (4) quantum computing for accelerated discovery and advanced imaging, and (5) new operating models with ethical frameworks. The paper highlights real-world pilots, market growth data, and evidence-based integrative approaches, providing a blueprint for clinicians, researchers, and policymakers to shape the future of medicine.

Purpose: The purpose of this research is to explore how Orange, a powerful information extraction and predictive modeling software, can be applied in the pharmaceutical industry to assess and visualize the effectiveness of cancer prevention medicines. By focusing on pharmaceutical companies like Genentech Inc. (USA), AstraZeneca Pharmaceutical PLC (UK), Boehringer Ingelheim (Germany), and Chugai Pharmaceutical Co. Ltd. (Japan), this study seeks to evaluate which cancer-preventing drugs from these companies provide the best efficacy while minimizing side effects for patients. The goal is to assist healthcare professionals (doctors and pharmacists) in making informed decisions about the most suitable medications for cancer prevention, ensuring patient safety and optimal treatment outcomes. Design/Methodology/Approach: This research utilizes Orange software's machine learning and data visualization tools, specifically scatterplot graphs, to analyze complex datasets related to cancer prevention drugs. By using scatterplots to concurrently examine multiple parameters, such as Company Name, Drug Class, Medicine Name, Prevention of Cancer Diseases, and Side Effects Percentage the study aims to identify patterns and correlations that can help pharmaceutical companies and healthcare professionals assess drug efficacy and safety. The approach involves analyzing the relationship between drug characteristics and side effects, providing actionable insights into how different treatments might interact with patient health conditions. Findings/Results: The findings suggest that Orange's scatterplot visualizations provide valuable insights into the effectiveness of various cancer prevention medicines across different pharmaceutical companies. By enabling the simultaneous analysis of multiple parameters, the software helps to identify which drugs are most effective in preventing cancer while minimizing side effects. This provides a clearer understanding of the correlations between drug characteristics, prevention outcomes, and side effects, supporting data-driven decision-making in pharmaceutical development and healthcare practices. Originality/Value: The originality of this study lies in the application of Orange's data mining and machine learning capabilities to visualize complex relationships within pharmaceutical datasets. The use of scatterplots to analyze drug efficacy, prevention outcomes, and side effects is an innovative approach that offers a richer, more nuanced understanding of cancer prevention drugs. This study contributes valuable insights into optimizing drug choice and treatment strategies, ultimately improving patient safety and therapeutic outcomes. Paper Type: This is an analytical research paper that applies machine learning and data mining techniques to assess the effectiveness and safety of cancer prevention medicines. The research focuses on using Orange software's visualization tools to extract and interpret complex data, providing actionable insights for pharmaceutical companies and healthcare professionals.

Generative Artificial Intelligence technologies such as ChatGPT have shown great potential in facilitating better teaching and learning experiences in the EFL context. While the literature posits that ChatGPT can generate naturalistic human-like language when prompted, it remains unclear the extent to which it can simulate the lexico-grammatical choices of human writing, given real-life situational contexts. Using two corpora, ChatGPT Corpus of Academic Writing (GPT-CAW) and The Varieties of English for Specific Purposes Database (VESPA), the study draws on key feature analysis to identify and compare the pervasive lexico-grammatical features of AI-generated academic essays to student-authored ones. Statistical analyses indicate that ChatGPT relies extensively on features associated with informational density such as common nouns, pre-modifying nouns, and prepositions while EFL students focus on stance, involvement, and informational density. This suggests, that at the lexico-grammatical level, functionally interpretable linguistic differences exist between ChatGPT-generated and EFL-written academic essays. Informed by previous research, it was also confirmed that AI expresses explicit referentiality more frequently than students, although both AI and students underuse persuasion features. These findings complement previous research on the linguistic characteristics of EFL writing and present new insights into ChatGPT's lexicogrammatical choices within academic writing. The pedagogical implications of these results are also considered.

The integration of Machine Learning (ML) and Artificial Intelligence (AI) into networking has initiated a transformative shift in how communication systems are designed, optimized, and managed. This paper explores the emerging trends, research highlights, and real-world industry applications of ML and AI in modern networking infrastructures. Key advancements such as intelligent traffic prediction, anomaly detection, dynamic resource allocation, and self-healing networks are examined in detail. The study also reviews the latest research developments from both academic and industrial perspectives, highlighting the synergy between data-driven approaches and next-generation network architectures, including 5G and beyond. Furthermore, this paper identifies current challenges—such as data privacy, scalability, and model interpretability—and outlines future directions for sustainable and intelligent network evolution. The insights provided aim to guide researchers, engineers, and decision-makers in understanding the potential and limitations of AI and ML technologies in building smarter, more adaptive networking systems.

Artificial intelligence (AI) is increasingly dominating several aspects of human existence, including the realm of English pronunciation instruction. Reading progress is an AI-driven application created by Microsoft in Microsoft Teams to aid language learners in honing their pronunciation skills. Nevertheless, there is a scarcity of research accessible about this use. The objective of this research is to examine students' assessments of the tool's effectiveness in facilitating the acquisition of English pronunciation. This study used a questionnaire consisting of five questions, created using Google Forms, to collect data from 123 students who are enrolled in different English classes at a university located in northern Vietnam. The focus of the research is on the students' pronunciation skills. The study results suggest that learners have a favorable opinion of and see reading progress as a valuable tool for honing their pronunciation skills. This outcome enhances the body of research on the implementation of reading progress in the context of teaching English pronunciation in Vietnam and globally. Thus, learners and English instructors may consult and implement it in order to enhance the efficiency of learning and teaching.

Sea water covers more than two-thirds of the surface of the earth. For a long period, seawater has been known as the most corrosive environment in nature for engineering materials, especially for many metals and alloys. Corrosion can vary to some extent depending on the geographical position, yet every seawater environment is naturally corrosive in a normal state anywhere in the world. That is why the study of corrosion of various materials is an important aspect of research. The corrosion of metal structures not only costs up to 4% of global gross domestic product annually but also poses a major threat to those who work in those areas. Predicting these risks will cause many problems to be prevented before it is too late. The integration of new technologies in the field of artificial intelligence into the chemical field makes it possible to solve the current issues. However, the lack of standardized image information, scientific research, and the number of experts aware of both fields undermine the timely integration of these fields. This study has used new algorithms for strengthening the outcome of a previous Worcester University study which used a collection of 600 photographic data in order to classify the corrosion. As a result, a model that can correctly classify corrosion with 83.5% accuracy has been taught

All the world’s a stage, according to William Shakespeare. Alexa Alice Joubin believes this dynamic translates to human interactions with artificial intelligence (AI). “AI is very performative,” Joubin explained. “When we interact with AI, it’s putting on a somewhat improvised performance for us. AI’s interfaces are modeled on a chat experience.” Applying these theories led Joubin to develop two actionable strategies to help mitigate the challenges of AI use in the humanities in higher education. To address the challenge of false singularity, Joubin teaches students an iterative process of using AI to fine-tune their research questions. Students have AI ask them questions related to or oppositional to their initial draft question. To help students avoid mistaking synthesis for domain knowledge, Joubin helps students develop meta-cognitive skills. Students build their draft thesis before using AI to simulate historical pro and con arguments about the topic. ::: https://trustworthyai.gwu.edu/gw-tai-professor-alexa-alice-joubin-explores-role-ai-humanities

Earthquake prediction is one of the most challenging and vital tasks that demands new methodologies for improving the accuracy of predictions. The research aims to present how radon gas concentration fluctuations are associated with the prediction of earthquakes in the Eurasian-Indo-Australian Plates. The paper discusses a statistical method of forecasting earthquake magnitudes greater than M4.5 from real-time radon gas monitoring close to the Grindulu Fault, Pacitan, East Java, Indonesia. This developed model has had the least errors in the form of mean absolute error (MAE), 0.30; mean absolute percentage error (MAPE), 0.06; root mean square error (RMSE), 0.55; mean squared error (MSE), 0.30; symmetric mean absolute percentage error (SMAPE), 0.06; complex normalized mean absolute percentage error (cnMAPE), 0.97; error absolute average (EAA), 0.30; and error relative average (ERA),-0.11, showing great accuracy and uniformity in prediction. These observations support the model's efficiency that may be adopted in earthquake early warning systems for better disaster preparedness. Predictive errors are reduced, and there is support for improved disaster management strategy, public safety education, and effective emergency response personnel training. This study can be used as a foothold for further advances in earthquake prediction methodologies and refinement of early warning systems.

Background Machine learning has become critical in AI software development, speeding up data processing and improving predictive insights. Optimized ML pipelines increase accuracy and efficiency, which benefits industries such as healthcare, finance, and automation. Methods This work uses Recursive Feature Elimination (RFE), Extreme Learning Machine (ELM), and Sparse Representation Classification (SRC) to develop a high-performance ML pipeline for feature selection, quick training, and efficient data representation. Objectives To evaluate the usefulness of RFE, ELM, and SRC in optimizing AI pipelines by improving feature selection, training speed, and classification accuracy, resulting in an efficient framework for real-time applications. Results The proposed RFE + ELM + SRC technique outperformed existing models with 95% accuracy and 92% F1 score. This hybrid technique improves machine learning performance for complicated, real-time AI applications. Conclusion Integrating RFE, ELM, and SRC improves machine learning operations by balancing accuracy and computing efficiency. This optimized pipeline offers a scalable solution for high-performance AI jobs, fulfilling the needs of a variety of fields that require rapid and precise prediction skills.

The project investigated responses to an AI displaying emotional qualities like fear through a mixed-methods approach. Participants were randomly assigned to one of two scenarios—one featuring an AI coworker and the other a human coworker and evaluated for emotional attachment and loss. Results revealed that professionals exhibited significant emotional responses to the potential "termination" of an AI team member. Qualitative analysis identified eight themes, including emotional responses and termination. Findings suggest that emotionally expressive AI activates psychological processes akin to human relationships, with implications for AI design, workplace dynamics, and ethical considerations surrounding AI termination

In the face of climate change, rapid population growth, and increasing resource limitations, promoting sustainable environmental practices has become a global priority. The use of rice husk ash (RHA) sandcrete blocks as an eco-friendly building material has attracted considerable interest in recent years. However, accurately predicting their engineering properties remains a challenging task. This study proposes an artificial intelligence-based approach to predict the compressive strength of RHA sandcrete blocks. A comprehensive dataset comprising 182 samples, each characterized by four input variables, was used to train and evaluate various models. The models assessedinclude multiple linear regression, support vector machine, and artificial neural network. The results demonstrated that all models provided reasonable accuracy in predicting compressive strength, with the artificial neural network model outperforming the others by achieving a coefficient of determination (R2) of 0.94. This high level of predictive accuracy highlights the potential of AI in enhancing the reliability and efficiency of material property predictions. By integrating AI technology into the assessment process, this study advances sustainable construction practices and supports the optimization of mix design and production strategies.

In recent year, Northeast India emerges as pivotal for economic sustenance through the rapid development of tourism industries. This study analyzed seasonal variations in tourist flows, emphasizing the need for enhanced management strategies. It also explored how the constructed environment can serve as an effective approach to sustaining the region's tourism industry. Covid-19 impact on the region's tourism industries remains largely unexplored, lacking in-depth research to track the extent of the industries' decline and assess their recovery. To present an overview of the region's tourism industry, a descriptive methodology was employed in the case study. This involved collecting monthly data from each state's tourism department and analyzing it in relation to the study objectives. This study emphasizes the need for stakeholders to adopt a rational approach that aligns with both seasonal and off-season tourism trends, highlighting the constructed environment as a key strategy for managing and sustaining industry development. A key objective is to address logistical and investment perspectives often overlooked in previous research. By establishing strategic indices, the study underscores the necessity of informed policy formulation and investment confidence. It aims to enhance the practicality of tourism management by aligning development activities with tourist demands during both peak and off-season periods, ultimately fostering economic vitality. One of the key takeaways of the study is the suggestion to various stakeholders to be competent and conscientious in understanding tourist psychology, managing assets effectively during the peak season, and devising strategies to ensure the sustainable growth of tourism in Northeast India.

Artificial Intelligence (AI) has emerged as a transformative force, reshaping industries through innovation, operational efficiency, and enhanced customer engagement. This systematic literature review investigates AI adoption across various sectors, with a focus on tourism and its intersection with sustainability, ethics, and emerging technologies. Leveraging a robust PRISMA methodology, 115 studies were reviewed to examine opportunities, challenges, and strategies for responsible AI integration. The findings highlight AI's potential to drive innovation, optimize resource use, and foster sustainability. In tourism, AI-powered tools like chatbots and predictive analytics enhance customer experiences and promote eco-friendly practices. However, adoption is hindered by challenges such as ethical concerns, data privacy, cultural barriers, infrastructure limitations, and socioeconomic disparities. Addressing these challenges requires interdisciplinary collaboration, ethical frameworks, and strategic alignment with sustainability metrics. The study underscores the importance of balancing innovation with ethical responsibility by integrating anticipatory ethics, human oversight, and stakeholder engagement. Transparent practices and inclusive policies are pivotal for fostering trust and equitable AI adoption. The review concludes that responsible AI integration can catalyze sustainable development and socioeconomic equity while ensuring technological advancements benefit diverse industries and communities. Future research should focus on scalability, inclusivity, and the ethical implications of AI in emerging global contexts.

La inteligencia artificial generativa se presenta como una herramienta transformadora en la educación superior, capaz de personalizar y mejorar la experiencia de aprendizaje. Sin embargo, su integración en el sistema educativo enfrenta desafíos significativos que deben ser abordados de manera proactiva, incluyendo la capacitación del personal y la consideración de cuestiones éticas y de equidad. La implementación efectiva de la IAG puede llevar a una educación más accesible, eficiente y adaptada a las necesidades de los estudiantes en un mundo en constante evolución.

Purpose: Artificial intelligence (AI) is poised to play a major role in medical diagnostics. Periodontal disease is one of the most common oral diseases. The early diagnosis of periodontal disease is essential for effective treatment and a favorable prognosis. This study aimed to assess the effectiveness of AI in diagnosing periodontal bone loss through radiographic analysis. Materials and Methods: A literature search involving 5 databases (PubMed, ScienceDirect, Scopus, Health and Medical Collection, Dentistry and Oral Sciences) was carried out. A specific combination of keywords was used to obtain the articles. The PRISMA guidelines were used to filter eligible articles. The study design, sample size, type of AI software, and the results of each eligible study were analyzed. The CASP diagnostic study checklist was used to evaluate the evidence strength score. Results: Seven articles were eligible for review according to the PRISMA guidelines. Out of the 7 eligible studies, 4 had strong CASP evidence strength scores (7-8/9). The remaining studies had intermediate CASP evidence strength scores (3.5-6.5/9). The highest area under the curve among the reported studies was 94%, the highest F1 score was 91%, and the highest specificity and sensitivity were 98.1% and 94%, respectively. Conclusion: AI-based detection of periodontal bone loss using radiographs is an efficient method. However, more clinical studies need to be conducted before this method is introduced into routine dental practice. (Imaging Sci Dent 20230092

This study advocates for the integration of artificial intelligence (AI) in the tourism industry. It synthesizes literature to comprehensively examine this concept, emphasizing the importance of tourist satisfaction and industry development. The study pursues two main objectives: elucidating AI's workings and analyzing its application in tourism. Employing a descriptive methodology, it gathers secondary data from diverse sources. The findings highlight the potential benefits of AI implementation in policy, strategy, and operational aspects of tourism. Moreover, it underscores the importance of AI education for stakeholders, including institutions, policymakers, and tour management teams, to leverage cutting-edge technologies effectively.
This paper is an endeavour to shed light on the specific ways AI is utilized within the tourism sector, offering insights that can inform industry practices and academic discourse.
This research contributes to the discourse on AI's role in enhancing tourism experiences and industry efficiency, offering insights for future strategies and implementations.

This paper reports on our work for defining a methodology for applying energy and other polices into smart buildings that use Internet of Things enabled devices. The goal is to automate decisions on a variety of issues where there is a conflict of policies between the priorities of different users and roles. We use computational argumentation and a method for compiling meta-policies to automate the decision-making process with the capability to offer human-readable explanations and, at the same time, to achieve increased energy efficiency. IoT sensors take the necessary measurements and data using the KNX standard. To validate our methodology we used an energy related scenario. The case study is applied on a building in the Technical University of Crete, where there are suitable sensors for measuring basic parameters (or data), such as temperature, lighting conditions, motion, and, carbon dioxide levels. The building's energy consumption data is imported by the Open Studio/Energy plus application. A web-based service for hierarchical argumentation, Gorgias Cloud, is used to process the data and make decisions.

Este  estudio  explora  las  percepciones  de  la  Inteligencia Artificial  Generativa  (IAG)  entre  docentes  de  educación superior,  utilizando  una  metodología  cualitativa  para profundizaren  las  oportunidades  y  desafíos  que  presenta esta  tecnología  emergente.  Los  hallazgos  destacan  el potencial    de    la    IAG    para    repensar    las    prácticas pedagógicas  en  la  enseñanza  superior,  al  tiempo  que revelan  inquietudes  en  torno  a  cuestiones  éticas  y  de integridad    académica.    Asimismo,    se    enfatiza    la importancia  de  la  formación  docente  continua  y  la generación  de  espacios  de  reflexión  colectiva  para repensar  las  prácticas  de  enseñanza  en  la  universidad.  El estudio  apunta  a  la  necesidad  de  un  abordaje  situado y colaborativo, que reconozca tanto las oportunidades como las implicaciones complejas que conlleva la incorporación de  herramientas  de  IAG  en  la  educación  superior contemporánea

The current study aims at predicting the strength of the problematic clayey soils treated with combinations of pozzolan of natural sources and lime powder when added as soil additives at a nano scale. Multiple linear regression (MLR), artificial neural networks (ANN) and fuzzy logic (FL) tools were employed in the analytical study. The variables of the present study include the following: nano pozzoaln of natural source (NNP) content, nano lime content (NL), median particle size of NNP, active silica content of NNP (SiO 2active), Initial liquid limit (ILL) and initial plastic limit (IPL) of the investigated soils. NNP was added at five percentages, i.e. 0%, 0.5%, 1%, 1.5% and 2%, while NL was added at five percentages, i.e. 0%, 0.3%, 0.6%, 0.9% and 1.2%. Three median particle sizes namely 50, 100 and 500 nm size were studied. Based on the different investigated soils and combinations, 120 soil mixtures were prepared and tested. California bearing ratio (CBR) and plasticity index (PI) were particularly examined. CBR tests were conducted at a soaked condition on specimens compacted to a maximum dry density (MDD) at the optimum moisture content (OMC). PI values were obtained following the Atterberg limits test. Based on the results of the performance criteria of the developed predictive models, it can be concluded that the CBR and PI of the expansive clayey soils can be effectively predicted using ANN and FL techniques. The results obtained by MLR were far from those obtained by both ANN & FL. In addition, ANN tool was slightly more accurate than FL as far as prediction of CBR and PI is concerned. The higher capability of ANN & FL models in predicting CBR & PI values, which generally obtained through time-consuming and expensive tests, could be useful for geotechnical engineers to assess or design a new pavement project. Further, it is recommended to do a re-evaluation of the current study in future, particularly when more data is available in the literature.

The current study aims at predicting the strength of the problematic clayey soils treated with combinations of pozzolan of natural sources and lime powder when added as soil additives at a nano scale. Multiple linear regression (MLR), artificial neural networks (ANN) and fuzzy logic (FL) tools were employed in the analytical study. The variables of the present study include the following: nano pozzoaln of natural source (NNP) content, nano lime content (NL), median particle size of NNP, active silica content of NNP (SiO 2active), Initial liquid limit (ILL) and initial plastic limit (IPL) of the investigated soils. NNP was added at five percentages, i.e. 0%, 0.5%, 1%, 1.5% and 2%, while NL was added at five percentages, i.e. 0%, 0.3%, 0.6%, 0.9% and 1.2%. Three median particle sizes namely 50, 100 and 500 nm size were studied. Based on the different investigated soils and combinations, 120 soil mixtures were prepared and tested. California bearing ratio (CBR) and plasticity index (PI) were particularly examined. CBR tests were conducted at a soaked condition on specimens compacted to a maximum dry density (MDD) at the optimum moisture content (OMC). PI values were obtained following the Atterberg limits test. Based on the results of the performance criteria of the developed predictive models, it can be concluded that the CBR and PI of the expansive clayey soils can be effectively predicted using ANN and FL techniques. The results obtained by MLR were far from those obtained by both ANN & FL. In addition, ANN tool was slightly more accurate than FL as far as prediction of CBR and PI is concerned. The higher capability of ANN & FL models in predicting CBR & PI values, which generally obtained through time-consuming and expensive tests, could be useful for geotechnical engineers to assess or design a new pavement project. Further, it is recommended to do a re-evaluation of the current study in future, particularly when more data is available in the literature.

This paper presents the implementation of Generative Artificial Intelligence (GAI) for providing descriptive feedback on 578 responses to pedagogical cases written by a cohort of students (n = 347) from seven initial teacher education programs at a Faculty of Education in Chile. To deliver feedback on these responses, a process called RECaP GPT was developed, which incorporates human action and utilizes ChatGPT-4 as
a teaching support tool. The feedback provided is based on pre-established criteria known to the students. The feedback generated by the GAI was validated and delivered to the students to enhance their evidence of learning throughout a semester of classes.
The paper discusses the capacity of this tool to offer formative and extensive feedback on students’ written work in a short period of time. Furthermore, it raises limitations observed in the implementation process that necessitate further research.

Today, nanotechnology is widely utilized across various industries, ranging from molecular biology to electronics, textiles to food, and beyond. Within the cosmetics sector, this emerging trend has been extensively adopted by manufacturers to enhance their existing products and develop new ones. Nanomaterials are employed to offer improved UV protection, deeper skin penetration, longer-lasting effects, enhanced color and finish quality, and more. Inorganic nanoparticles like TiO2 and ZnO are commonly utilized as UV filters in sunscreens. Additionally, cosmetics and personal care products incorporate various encapsulation and delivery systems such as liposomes, niosomes, dendrimers, nanoemulsions, and solid lipid nanoparticles. This comprehensive review article presents valuable insights into the types of nanomaterials employed in cosmetic products, as well as the potential benefits and risks associated with their usage.

A zero carbon footprint stabilization approach has been adopted in this research to improve the swelling potential (SP) of clayey soils for a greener construction approach. Construction activities like earthworks during the cement stabilization of unstable soils utilized as reconstituted subgrade materials is responsible for the emission of unhealthy amount of carbon oxides into the atmosphere contributing to ozone layer depletion and eventual global warming. This has been substituted by using eco-friendly cementing materials, quicklime activated rice husk ash (QARHA), formulated in this research work. The SP of clayey soil treated with QARHA has been predicted using the learning abilities of genetic programming (GP), artificial neural network (ANN) and the evolutionary polynomial regression (EPR). This was aimed at reducing the over dependence on repeated laboratory visits and experiments prior to infrastructure (pavement) designs, construction and future monitoring of the performa...

The California bearing ratio (CBR) is one of the basic subgrade strength characterization properties in road pavement design for evaluating the bearing capacity of pavement subgrade materials. In this research, a new model based on the Gaussian process regression (GPR) computing technique was trained and developed to predict CBR value of hydrated lime-activated rice husk ash (HARHA) treated soil. An experimental database containing 121 data points have been used. The dataset contains input parameters namely HARHA—a hybrid geometrical binder, liquid limit, plastic limit, plastic index, optimum moisture content, activity and maximum dry density while the output parameter for the model is CBR. The performance of the GPR model is assessed using statistical parameters, including the coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), Relative Root Mean Square Error (RRMSE), and performance indicator (ρ). The obtained results through GPR model yiel...

Purpose: Artificial intelligence (AI) is poised to play a major role in medical diagnostics. Periodontal disease is one of the most common oral diseases. The early diagnosis of periodontal disease is essential for effective treatment and a favorable prognosis. This study aimed to assess the effectiveness of AI in diagnosing periodontal bone loss through radiographic analysis. Materials and Methods: A literature search involving 5 databases (PubMed, ScienceDirect, Scopus, Health and Medical Collection, Dentistry and Oral Sciences) was carried out. A specific combination of keywords was used to obtain the articles. The PRISMA guidelines were used to filter eligible articles. The study design, sample size, type of AI software, and the results of each eligible study were analyzed. The CASP diagnostic study checklist was used to evaluate the evidence strength score. Results: Seven articles were eligible for review according to the PRISMA guidelines. Out of the 7 eligible studies, 4 had strong CASP evidence strength scores (7-8/9). The remaining studies had intermediate CASP evidence strength scores (3.5-6.5/9). The highest area under the curve among the reported studies was 94%, the highest F1 score was 91%, and the highest specificity and sensitivity were 98.1% and 94%, respectively. Conclusion: AI-based detection of periodontal bone loss using radiographs is an efficient method. However, more clinical studies need to be conducted before this method is introduced into routine dental practice. (Imaging Sci Dent 20230092

Resilient modulus and deviatoric stress of cemented soils treated with crushed waste ceramics (CWC) for pavement subgrade construction Útalapozás készítéséhez alkalmazott zúzott hulladékkerámiával (CWC) kezelt cementált talajok rugalmassági mudulusa és deviátoros feszültsége kennedy cHibuzor onyelowe  Department of Civil Engineering,

Earthquakes are vibrations of the Earth's surface that can cause ground shaking, fires, tsunamis, landslides and fissures. These natural phenomena can cause destruction and kill lives. When there is a possibility of an earthquake, an accurate prediction can save lives and avoid infrastructure damage. Due to the probabilistic nature of an earthquake occurring and the challenge of achieving an efficient and dependable model for an earthquake prediction, efforts to predict earthquakes have been met with mixed results. Therefore, new methods are constantly sought. A deep learning-based technique, specifically a transformer algorithm, was applied to predict earthquake magnitudes using available data for the Horn of Africa. The problem was formulated as multi-variant time series regression, and predictions were made for earthquakes magnitudes greater than or equal to 3 for the next three months. A comparison of the results was made with the output obtained from long short-term memory (LSTM), bidirectional long short-term memory (BILSTM), and bidirectional long short-term memory with attention (BILSTM-AT) models. The results showed that the transformer model outperformed the other three models with 0.276, 0.147, 0.383, 28.868% mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE) respectively in predicting earthquake magnitudes in the Horn of Africa.

Oil pollution causes deterioration of the physical, chemical, mechanical, and geotechnical characteristics of affected soil leading to loss of soil productivity for engineering purposes. Different stabilization methods serve as a remedy for such soil to regain its loss engineering properties. This study was concerned with the utilization of lime to stabilize crude oil contaminated soil and to investigate its efficacy for soil stabilization. The study also focused on determining the geotechnical properties of crude oil contamination and matching the result with standard specifications established for engineering works. Hydrated lime, expansive clayey soil, contaminated soil, and potable water were the materials used for the experimental investigation. The contaminated soil was treated with 6.5% lime and 0–20% crude oil contaminated materials obtained from oil exploration sites in North-Eastern Nigeria and per standard test method for laboratory evaluation of consistency limits, compa...

Previous language modeling approaches to information retrieval have focused primarily on single terms. The use of bigram models has been studied, but the restriction on word order and adjacency may not be justified for information retrieval. We propose a new language modeling approach to information retrieval that incorporates lexical anities, or pairs of words that occur near each other, without

Artificial neural network (ANN) was adapted in this research study for the modelling of the shrinkage properties, consistency indices and swelling potentials of expansive clayey soil stabilized using HARHA as chemical additive. RHA is obtained from the milling of rice as an agricultural or industrial waste which encourages the utilization and recycling of solid waste derivatives for engineered infrastructure to offer greater economic and environmental benefit to the construction industry. Varying ratios of HARHA was utilized in treatment of the expansive clayey soil ranging from 0 % to 12 % and the laboratory responses were obtained which provides expert historical data for the ANN model development; with the soil-HARHA replacement ratio and corresponding Atterberg limit responses as the network input variables while the shrinkage, clay activity and swelling characteristics were utilized as the network output parameters. The optimized network architecture for the network based on R-values and MSE performance criteria produced NN 5-9-6 using Levernberg Marquardt training and feed-forward back propagation algorithm in MATLAB toolbox. The developed ANN model's performance was evaluated using loss function parameter (RMSE) and the computed results is further compared with MLR model results to produce mean coefficient of determination of 98.27 as against 99.99 obtained from the generated ANN model which signifies a better performance in terms of estimation accuracy for the prediction of the expansive clayey soil-HARHA mixture characteristics.