Patient symptoms play a critical role in disease progression and diagnosis, yet they are most often captured in unstructured clinical notes. This study explores use of large language models (LLMs) for extracting patient symptoms from clinical notes, comparing their performance against rule-based information extraction (IE) systems, like BioMedICUS. By fine-tuning an LLM on diverse corpora from multiple healthcare institutions, we aimed to improve symptom extraction accuracy and efficiency with symptoms related to acute and post-acute sequelae of SARS-CoV-2. We also conducted prevalence analysis to highlight significant differences in symptom prevalence across corpora and performed fairness analysis to assess the model's equity across race and gender. Our findings indicate that while LLMs can match the effectiveness of rule-based IE methods, they face significant challenges related to demographic bias and generalizability due to variability in training corpora. This evaluation revealed overfitting and insufficient generalization, especially when models were trained predominantly on limited datasets with single annotator bias. This study also revealed that LLMs offer substantial advantages in efficiency, adaptability, and scalability for biomedical IE, marking a transformative shift in clinical data extraction processes. These results provide real-world evidence of the necessity for diverse, high-quality training datasets and robust annotation processes to enhance LLM’s performance and reliability in clinical applications.

This project aims to create a virtual assistant with AI integration to improve Siemens Energy's internal processes. Using cloud-based technologies, microservice architecture, and large language models (LLMs), the project seeks to create a reliable, effective, and user-friendly assistant customized to Siemens Energy's requirements. The first significant business difficulty identified by the study was the time engineers had to spend looking for information in large volumes of company papers. The proposed virtual assistant responds with precision and context awareness to optimize productivity. The assistant uses a microservice architecture to guarantee scalability, flexibility, and integration for various use scenarios. Tasks like document retrieval, translation, summarization, and comparison can now be handled effectively. Utilizing Amazon Web Services (AWS) for cost-effectiveness and scalability, the backend is cloud-deployed, backed by a frontend created for natural user interaction. To increase precision and relevance, the system uses cutting-edge AI, such as vector databases and Retrieval Augmented Generation (RAG). The assistant expedites document management procedures, improves data accessibility, and reduces search time. The results highlight how it may enhance workflow efficiency for Siemens Energy engineers and how flexible it can be for future AI-driven applications.

Large Language Models (LLMs) have emerged as powerful tools in the domain of artificial intelligence, specifically enhancing natural language processing capabilities. These models leverage extensive datasets and sophisticated algorithms to automate and enhance tasks traditionally performed by humans, thereby revolutionizing innovation and entrepreneurship. LLMs accelerate product development, streamline business operations, and enable precise and rapid decision-making, all of which are crucial for maintaining competitiveness in dynamic markets. This paper categorizes the applications of LLMs in innovation and entrepreneurship into three main areas: technological innovation, strategic decision-making, and process automation. By exploring various integrations of LLMs in entrepreneurial ventures, this work offers both theoretical insights and practical examples, underscoring the transformative impact of LLMs in shaping modern business landscapes.

In-situ production of PC components is the same process as in a factory, with the order of installing processed rebar, pouring concrete, curing, and storage. In-situ production not only reduces environmental impact by more than 14.58% compared to factory production, but also reduces costs by up to 39.4% compared to factory production when increasing the number of in-situ produced PC components. The stock yard area is more than 5 times larger than the production area, which accounts for a significantly higher proportion. Research on in-situ production of PC components is mainly focused on the production area. PC component yard layout planning for in-situ production can effectively reduce carbon dioxide emissions and improve construction efficiency. Therefore, the purpose of this study is to develop an environmental impact minimization model for in-situ production of PC components. As a result of applying the developed model, the improved dung beetle optimization algorithm optimization improved the adjacent correlation by 22.79% and reduced carbon dioxide emissions by 18.33% compared to the dung beetle optimization algorithm, which verifies its efficiency. The proposed environmental impact minimization model can support the construction, reconstruction, and functional upgrade of logistics centers, contributing to low carbon dioxide in the logistics industry.

Large language models (LLMs) are essential to the field of natural language processing, and as their applications expand, security risks have become increasingly prominent. This paper introduces a novel benchmark for evaluating LLMs security, termed CS-Eval, designed to effectively assess the models' ability to address vulnerabilities. CS-Eval targets seven key security risks: ethical dilemmas, marginal topics, error detection, detailed event handling, cognitive bias, logical reasoning, and privacy identification, and establishes a Multi-Security Hazard Dataset (MSHD). The evaluated models include GPT-4o, Llama-3-70B, Claude-3-Opus, ERNIE-4.0, Abab-6.5, Qwen1.5-110B, Gemini-1.5-Pro, Doubao-Pro, SenseChat-V5, and GLM-4. We analyzed each model's performance in relation to these security risks and provided recommendations for improvement. Experimental results demonstrate varying levels of effectiveness across models, with GPT-4o exhibiting the best overall performance. Moreover, the relationship between security enhancement and model capa-bility is nonlinear, indicating that improving safety requires a multifaceted approach, considering various factors in both development and application.

Wave and tidal energy, recognized as vital renewable resources, harness the ocean's kinetic and potential power. This study aims to provide an in-depth patent analysis of the technological landscape within these sectors. We applied a dual approach: first, a descriptive analysis was conducted to explore patent publication trends, technology lifecycle stages, patent activity by country, top assignees, and IPC classifications. Our analysis provided a detailed overview of the sector's growth and the key players involved. Second, we utilized topic modeling, specifically BERTopic enhanced with large language models (LLMs), to identify and fine-tune key technolog-ical themes within the patent data. In this study, we identified seven distinct clusters each for wave and tidal energy using this approach. This method led to a novel categorization of the pa-tents, revealing latent themes within the patent data. Although our categorization differs from traditional methods, it provides deeper insights into the thematic focus of the patents, highlight-ing emerging trends and areas of innovation within wave and tidal energy technologies to better exploit and optimize ocean energy conversion infrastructure.

In this paper, we propose "Synergized Efficiency Optimization for Large Language Models" (SEO-LLM), a groundbreaking approach that integrates advanced data utilization and model compression techniques to significantly enhance the performance, efficiency, and scalability of large language models (LLMs). Our method synergistically combines Adaptive Data Augmentation (ADA), Transfer- Active Learning (TAL), Adaptive Iterative Pruning (AIP), and Synergistic Quantization and Distillation (SQD). These components work together to reduce the training data requirement by 30%, compress model size by 67.6%, and improve inference speed by up to 50%, while preserving or even enhancing model accuracy across various NLP tasks. ADA dynamically adjusts augmentation strategies to optimize model generalization, while TAL leverages pre-trained models to focus learning on the most informative data samples. AIP intelligently prunes less significant weights, and SQD harmonizes quantization with knowledge distillation to achieve high compression rates without significant performance loss. The synergy between these techniques makes SEO-LLM a robust solution for deploying LLMs in resource-constrained environments, maintaining state-of-the-art performance with a fraction of the computational and data resources.

With the sharp increase in the number of vehicles, the issue of parking difficulties has emerged as an urgent challenge that many cities need to address promptly. In the task of predicting large-scale urban parking data, existing research often lacks effective deep learning models and strategies. To tackle this challenge, this paper proposes an innovative framework for predicting large-scale urban parking graphs leveraging real-time service capabilities, aimed at improving the accuracy and efficiency of parking predictions. Specifically, we introduce a graph attention mechanism that assesses the real-time service capabilities of parking lots to construct a dynamic parking graph that accurately reflects real preferences in parking behavior. To effectively handle large-scale parking data, this study combines graph coarsening techniques with temporal convolutional autoencoders to achieve unified dimension reduction of the complex urban parking graph structure and features. Subsequently, we use a spatio-temporal graph convolutional model to make predictions based on the coarsened graph, and a pre-trained autoencoder-decoder module restores the predicted results to their original data dimensions, completing the task. Our methodology has been rigorously tested on a real dataset from parking lots in Shenzhen. The experimental results indicate that compared to traditional parking prediction models, our framework achieves improvements of 46.8% and 30.5% in accuracy and efficiency, respectively. Remarkably, with the expansion of the graph’s scale, our framework’s advantages become even more apparent, showcasing its substantial potential for solving complex urban parking dilemmas in practical scenarios.

This study evaluates the ability of six popular chatbots; ChatGPT-3.5, ChatGPT-4.0, Gemini, Copilot, Chatsonic, and Perplexity to provide reliable answers to questions concerning keratoconus. Methods: Chatbots responses were assessed using mDISCERN and Global Quality Score (GQS) metrics. Readability was evaluated using nine validated readability assessments. We also addressed the quality and accountability of websites from which the questions originated. Results: We analyzed 20 websites, 65% "Private practice or independent user" and 35% "Official patient education materials." The mean JAMA Benchmark score was 1.5±0.68, indicating low accountability. Reliability, measured using mDISCERN, ranged from 42.9±3.16 (ChatGPT-3.5) to 46.95±3.53 (Copilot). The most frequent question was "What is Keratoconus?" with 70% of websites providing relevant information. This received the highest mDISCERN score (49.33±4.96) and a relatively high GQS score (3.50±0.55), with an Automated Readability Level Calculator score of 13.17±2.13. Moderate positive correlations were determined between the website numbers and both mDISCERN (?=0.265,?=0.25) and GQS (?=0.453,?=0.05) scores. The quality of information, assessed using the GQS, ranged from 3.01±0.51 (ChatGPT-3.5) to 3.3±0.65 (Gemini) (p=0.34). The differences between the texts were statistically significant. Gemini emerged as the easiest to read, while ChatGPT-3.5 and Perplexity were the most difficult. Based on mDISCERN scores, Gemini and Copilot exhibited the highest percentage of responses in the "Good" range (51-62 points). For the GQS, the Gemini model exhibited the highest percentage of responses in the "Good" quality range, with 40% of its responses scoring 4-5. Conclusions: While all chatbots performed well, Gemini and Copilot showed better reliability and quality. However, their readability often exceeded recommended levels. Continuous improvements are essential to match information with patients' health literacy for effective use in ophthalmology.

The rapid development of specific-purpose Large Language Models (LLMs), such as Med-PaLM, MEDITRON-70B, and Med-Gemini, has significantly impacted healthcare, offering unprecedented capabilities in clinical decision support, diagnostics, and personalized health monitoring. This paper reviews the advancements in medicine-specific LLMs, the integration of Retrieval-Augmented Generation (RAG) and prompt engineering, and their applications in improving diagnostic accuracy and educational utility. Despite the potential, these technologies present challenges, including bias, hallucinations, and the need for robust safety protocols. The paper also discusses the regulatory and ethical considerations necessary for integrating these models into mainstream healthcare. By examining current studies and developments, this paper aims to provide a comprehensive overview of the state of LLMs in medicine and highlight the future directions for research and application. The study concludes that while LLMs hold immense potential, their safe and effective integration into clinical practice requires rigorous testing, ongoing evaluation, and continuous collaboration among stakeholders.

While Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), it also presents challenges that can affect model accuracy and performance. Practical applications show that RAG can mask the intrinsic capabilities of LLMs. Firstly, LLMs may become overly dependent on external retrieval, underutilizing their own knowledge and inference abilities, which can reduce responsiveness. Secondly, RAG techniques might introduce irrelevant or low-quality information, adding noise to the LLM. This can disrupt the normal generation process, leading to inefficient and low-quality content, especially when dealing with complex problems. This paper proposes a RAG framework that uses reflective tags to control retrieval. This framework evaluates retrieved documents in parallel and incorporates the Chain of Thought (CoT) technique for step-by-step content generation. The model selects the highest quality and most accurate content for final generation. The main contributions include: 1) Reducing the hallucination problem by selectively utilizing high-scoring document, 2) Enhancing real-time performance through timely external database retrieval, and 3) Minimizing negative impacts by filtering out irrelevant or unreliable information through parallel content generation and reflective tagging. These advancements aim to optimize the integration of retrieval mechanisms with LLMs, ensuring high-quality and reliable outputs.

Background: Existing human cell immortalization methods made the cells obtain oncogenesis phenotype and/or caused the cells gain and/or lose chromosomes. Immortalized normal human T cells lines provide critical in vitro models for basic research and therapeutic products development.Methods: We utilized a CRISPR/Cas9 system to replace a single copy of the exon 2 of the cell cycle inhibitor gene CDKN2A (encoding p16 and p14 proteins) with a single copy of human telomerase reverse transcriptase (hTERT) to immortalize human primary CD8⁺ T cells (hCD8⁺T-TERT). By using Cas9 protein and low donor DNA copies/cell, we successfully immortalized hCD8⁺T cells with a single copy of hTERT transgene, which also avoided uncontrolled insertion of Cas9 gene and guide RNA vector.Results: Human primary CD8+ cells were immortalized and expanded more than 2.6 × 10⁷ times. Characterization of the cells revealed that the immortalized CD8⁺ T-TERT cells retained most of the cell surface markers and normal karyotype. The CD8⁺ T-TERT cells also retained the dependence of IL-2 and CD3/CD28 activator for survival and expansion.Conclusion: we established a stable immortalized CD8⁺ T cell line that had a phenotype consistent with T cells and will be a useful research model.

Dirac's Large Number Hypothesis (LNH), proposed in 1937, has captivated the scientific community with its exploration of profound correlations between cosmic and atomic scales. This hypothesis delves into the intricate interplay between the infinitesimally small and the vastly large, offering potential insights into the fundamental nature of the universe. As we continue to uncover the mysteries of the cosmos, the LNH oscillates on the precipice of scientific acceptance—neither fully validated nor entirely dismissed. In this review paper, we embark on a comprehensive journey through Dirac's LNH, shedding light on its theoretical underpinnings, its implications for universe models, and its resonance with the Anthropic Principle. We delve into the possibilities of variable gravitational constants and continuous mass creation, inviting further exploration into the intricacies of our cosmic symphony. By embracing the ongoing quest for understanding, we endeavor to unravel the profound harmonies that connect the infinitesimal with the infinite, contributing to the symphony of knowledge in theoretical physics and cosmology.

Large language models have recently made significant progress in natural language processing, and there is observation that these models exhibit reasoning abilities when they are sufficiently large. This has sparked considerable research interest since reasoning is a hallmark of human intelligence that is widely considered missed in artificial intelligence systems. Due to large size of these models, evaluation of LLMs’ reasoning ability is largely empirical. Creating datasets to evaluate the reasoning ability of LLMs is therefore an important area of LLM research. A key open question is whether LLMs reason or simply recite memorized texts they have encountered during their training phase. This work conducts simple experiments using Cheryl’s Birthday Puzzle and Cheryl’s Age Puzzle and their variants created in this work to investigate whether LLMs recite or reason and discovers that LLMs tend to recite memorized answers for well-known questions, which appear more frequently on the internet, even though such answers may not be sensible for the modified versions of the questions. When presented with less well-known questions, it is observed that LLMs answer with correct reasoning more frequently. A possible inference is that LLMs tend to reason on less well-known questions but recite memorized answers on popular questions. As a result, to accurately evaluate the reasoning ability of LLMs, it is essential to create new datasets to ensure that LLMs are elicited to truly use their reasoning ability to generate responses to the presented questions. In view of the finding, this work proposes a new dataset comprising of unseen questions requiring semantic and deductive logical reasoning skills to elicit reasoning ability from LLMs. The proposed evaluation framework is based on the intuition that some questions or puzzles can only be answered through the mastery of reasoning needed for situational awareness, and the dataset consists of 84 logical reasoning questions on room assignment subject to constraints. The proposed evaluation framework has several desirable properties, including resilience to training data contamination, ease of response verification, extensibility, usefulness and automated test case generation. This work then applies the proposed dataset to evaluate the reasoning ability of state-of-the-art LLMs, including GPT-3, GPT-4, Llama-3.1, Gemini-1.5 and Claude-3.5, and compare their performance with the performance of human intelligence on the dataset.

In 2021, Japan's medical expenses will exceed 45 trillion yen, and the shortage of doctors, especially in remote and mountainous areas, is becoming serious, making it difficult to maintain the medical system. We have conducted a study of 800 health consultation text data. We developed an on-premise health counseling LLM system by constructing a dialogue flow based on 800 health counseling text data. We conducted a Turing test of this system using 200 test data and verified its effectiveness with three medical professionals. The Turing test was a comparison experiment between this system and a conventional LLM system. The health counseling LLM infrastructure focuses on exercise guidance and analyzes gender, height, weight, body fat percentage, and muscle mass. While the accuracy of the conventional LLM system was 87.5%, this system showed a higher accuracy of 93.1%. Although telemedicine has been slow to spread in Japan, the introduction of a health consultation system using Personal Health Record and Large Language Models has the potential to reduce the burden on physicians. In the future, we aim to improve the accuracy of the system by using Japanese language and medical-specific evaluation scales.

As Large Language Models (LLMs) increasingly accommodate larger inputs, context windows spanning hundreds of thousands or even millions of tokens are touted as promising for a wide array of applications. However, the potential decay in reasoning ability for larger inputs may compromise their utility. This study introduces a new benchmark called Find the Origin, which progressively tests the efficacy of LLMs on a simple intellectual task as the size of the context window increases. The test, conducted on 14 different LLMs for comparative analysis, demonstrated that reasoning ability is dependent on input size. Additionally, three independent tests were performed with the GPT-4 Turbo model to demonstrate its reasoning degradation in different contexts as input size increases.

Countless disasters have resulted from climate change, causing severe damage to infrastructure and the economy. These disasters have significant societal impacts, necessitating mental health services for the millions affected. To prepare for and respond effectively to such events, it is crucial to understand people's emotions and the life incidents they experience both before and after a disaster strikes. In this case study, we mined the emotions and life incidents expressed on Twitter during the 2017 Hurricane Harvey. Between August 20 and August 30, we collected a dataset of approximately 400,000 public tweets related to the storm. Using a BERT-based model, we predicted the emotions associated with each tweet. Following emotion prediction, we applied various natural language processing techniques to analyze the content of the tweets, aiming to uncover the 'topics' discussed alongside specific 'emotions.' To efficiently identify these topics, we utilized the Latent Dirichlet Allocation (LDA) technique for topic modeling, which allowed us to bypass manual content analysis and extract meaningful patterns from the data. However, rather than stopping at topic identification, we further refined our analysis by integrating Graph Neural Networks (GNN) and Large Language Models (LLM). The GNN was employed to generate embeddings and construct a similarity graph of the tweets, which was then used to optimize clustering. This step ensured that related tweets were accurately grouped together based on their content and context. Subsequently, we used an LLM to automatically generate descriptive names for each event cluster. This advanced approach allowed us to identify and label life incidents automatically, providing a nuanced understanding of the key issues faced by the community during the hurricane. The results revealed significant emotional shifts as the hurricane reached its most devastating phase. These shifts coincided with pressing concerns and demands from the population, such as evacuation plans, animal safety, safety updates, public policy, help requests, flood impacts, and the spread of fake news. By combining GNN and LLM for automatic event name prediction, our study not only mapped out the emotions but also accurately categorized the specific life incidents that were most relevant during the disaster, offering critical insights for disaster preparedness and response strategies.

The advent of Large Language Models like Generative Pre-trained Transformer 4 (GPT-4) has introduced a revolutionary approach to bridging the communication gap between complex radiology reports and patient comprehension. This review article explores the pivotal role of GPT-4 in generating patient-friendly summaries of radiology reports, aiming to demystify medical jargon and enhance patient engagement and understanding. Through an examination of the technological underpinnings of GPT-4, this article highlights its capability to accurately interpret and simplify radiological findings into layman's terms. It assesses the impact of such advancements on patient satisfaction, adherence to treatment plans, and overall healthcare outcomes. Furthermore, the review delves into the potential challenges and ethical considerations associated with implementing AI-driven summaries in clinical practice, including accuracy, privacy, and the need for human oversight. By offering insights into the current applications, benefits, and limitations of GPT-4 in radiology, this short review underscores the transformative potential of AI in fostering a more inclusive and patient-centric healthcare communication paradigm.

The measurement of the grounding resistance of protection grids in large installations as well as grounding electrodes in urban areas is addressed in this article. The resistance value is obtained using a three-pin array by measuring the fall-of-potential on the ground surface. The resistance measured by this method is corrected using the so-called correction factor that adjusts the measured resistance value to its real value. The proposed measurement method obtains correct values of the grounding resistance even when the auxiliary and potential electrodes of the tree-pin array are close to the electrode to be measured. Thus, it can be applied to large electrodes as well as electrodes in urban areas. Several simulated examples are used to illustrate the method, and some real cases with field measurements are presented for a final validation of the method.

Accurate stock market predictions following earnings reports are crucial for investors. Traditional methods, particularly classical machine learning models, struggle with these predictions because they cannot effectively process and interpret extensive textual data contained in earnings reports and often overlook nuances that influence market movements. This paper introduces an advanced approach by employing Large Language Models (LLMs) instruction fine-tuned with a novel combination of instruction-based techniques and quantized low-rank adaptation (QLoRA) compression. Our methodology integrates ‘base factors’, such as financial metric growth and earnings transcripts, with ‘external factors’, including recent market indices performances and analyst grades, to create a rich, supervised dataset. This comprehensive dataset enables our models to achieve superior predictive performance in terms of accuracy, weighted F1, and Matthews correlation coefficient (MCC), especially evident in the comparison with benchmarks such as GPT-4. We specifically highlight the efficacy of the llama-3-8b-Instruct-4bit model, which showcases significant improvements over baseline models. The paper also discusses the potential of expanding the output capabilities to include a ‘Hold’ option and extending the prediction horizon, aiming to accommodate various investment styles and time frames. This study not only demonstrates the power of integrating cutting-edge AI with fine-tuned financial data but also paves the way for future research in enhancing AI-driven financial analysis tools.

The study objective is to evaluate the reliability of the Göttingen Mini-pig (G-MP) as a large animal model for preclinical studies addressing articular cartilage treatment procedures. Second this work compared the G-MP to the domestic pig (DP) in terms of surgical anatomy, postoperative management, and follow-up period possibilities and challenges. Six G-MP and four DP underwent a two-stage surgical procedure including cartilage harvesting using a superolateral approach followed by cartilage implantation using a medial parapatellar tendon approach. The superolateral approach exposed 11% (SD ± 5) of the entire trochlea in G-MP and 20% in the DP model. The medial parapatellar tendon approach in G-MP exposed 63% (SD ± 4) of the trochlear surface and exposed 34% (SD ± 13) of the medial femoral condyle, allowing 4 trochlear lesions of 6mm of diameter and one to the medial condyle in 4 out of 6 G-MP and in all DPs. Cartilage thickness was under 1mm in G-MP compared to more than 2mm in DP. Weight-progression was + 4 kg/week in DP and + 0.2 kg/week for G-MP. The G-MP is a feasible model for cartilage research, with adequate access to the joint via the dual approach. Thus enabling 4-5 lesions of 6mm, however a thinner cartilage in the G-MP needs to be considered.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

Sentiment analysis is a technique used to understand the publics’ opinion towards an event, product, or organization. For example, positive or negative opinion or attitude towards electric vehicle (EV) brands. This provides companies with valuable insight about the public's opinion of their products and brands. In the field of natural language processing (NLP), transformer models have shown great performances over the traditional machine learning algorithms. However, these models have not been explored extensively in the EV domain. EV companies are becoming signif-icant competitors in the automotive industry and are projected to cover up to 30% of the United States light vehicle market by 2030 [1]. In this study, we present a comparative study of large language models (LLMs) including bidirectional encoder representations from transformers (BERT), robustly optimized BERT approach and generalized autoregressive pretraining for language un-derstanding using Lucid motors and Tesla motors YouTube datasets. Results evidenced LLMs like BERT and her variants are off-the-shelf algorithms for sentiment analysis, specifically, when fi-ne-tuned. Furthermore, our findings presents the need for domain adaptation whilst utilizing LLMs. Finally, the experimental results showed that RoBERTa achieved consistent performance across the EV datasets with a F1 score of at least 92%.

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.

A recently published article posited the use of polymer matrix composites (PMCs) as a replacement material for low-carbon steel (LCS) in large power transformer (LPT) tanks [1]. PMCs offer potential advantages such as weight reduction, corrosion prevention, and self-healing of the tank material which may not be achievable with traditional LCS. LCS can arrest ballistic projectiles at relatively low velocities, but at higher velocities, penetration can occur leading to a potential major transformer failure. Numerical simulations of steel projectile impacts upon LCS plates and glass and/or carbon fiber polymer composite laminates showed that with sufficient thickness both could prevent projectile penetration. This prevention was especially efficient when the plates were coated with a high strain rate sensitive material such as polyurea (PU). Our simulations show that the addition of a 3 mm coating of PU to a standard 10 mm thick LCS plate used in LPT tanks could prevent penetration of a 400 m/s steel projectile. For PMC plates, the simulations with the same projectile velocity showed three times faster deceleration with a 3 mm PU coating than without the coating. Thus, two realistic approaches to improving the ballistic protection of LPTs are presented. In addition to their other advantages, this research clearly shows that PMCs with the coating could provide significant ballistic protection for the next generation of LPT tanks.

The implementation of morphing wing mechanisms holds promise in enhancing aircraft perfor-mance, as indicated in current literature. The Clean Sky 2 AirGreen 2 European project is currently conducting ground and wind tunnel tests to validate innovative studies on morphing wing structures. The project aims to showcase the effectiveness of these morphing architectures on a potentially flying demonstrator at true scale. This article describes design methodology and struc-tural testing of a scaled morphing flap structure capable of 3 different morphing modes required for low-speed (take-off/landing) and high-speed (cruise) conditions. A significant scale factor of 1:3 was selected to enhance the importance and relevance of the wind tunnel test campaign. Geometrical scaling to the real flap prototype was deemed impractical due to limitations associated with scaling the embedded mechanisms and actuators responsible for shape changing. Static analyses were performed using the finite element method to address the most critical loads determined through three-dimensional CFD analysis. The Finite Element (FE) analysis results were briefly outlined, and comparisons were drawn between the obtained results and the empirical data collected during the structural test. Good correlations were observed between the results and numerical predictions, encompassing static deflections under applied loads and elastic deformations. Consequently, the modeling approaches utilized during the design and testing phases were considered highly suc-cessful. Therefore, based on the results extrapolated from simulations under ultimate load condi-tions relevant to the wind tunnel test campaign, the scaled flap prototype was deemed suitable for testing.

Recommender Systems (RecSys) are crucial in managing information overload and enhancing user satisfaction across various digital platforms, including e-commerce and entertainment. Evolving from traditional models to Deep Neural Networks (DNNs) and, more recently, Large Language Models (LLMs), these systems leverage sophisticated algorithms to analyze user behaviors and preferences. LLMs, such as GPT-4, are trained on extensive datasets to comprehend and generate natural language, significantly advancing their ability to deliver personalized recommendations. This tutorial explores the transformative impact of LLMs on RecSys, discussing their development, application in handling complex datasets, and the integration of contextual insights. Real-world examples illustrate how LLMs enhance recommendation accuracy and user experience, highlighting challenges and future directions in the field.

This article explores the potential of the Unreal Engine game engine as a tool for creating highly realistic 3D visualizations of GIS data, specifically in the context of significant historical areas. The research will focus on the computational techniques used in the 3D visualization of GIS data and the Unreal Engine software and its potential applications in geomatics. The article also presents several relevant scientific studies and projects that have successfully used game engines for similar purposes, explores the potential for using GIS data within a game engine, including plug-ins that provide additional functionality to GIS software, and the use of procedural modeling to create 3D objects through the CityEngine software plug-in. Finally, the research is applied to a dataset of the historical Vltava Valley covering an area of 1670 km2 to demonstrate the capabilities of Unreal Engine in creating realistic visualizations of large historical landscapes, and the resulting visualizations are presented. This practical application of the research provides valuable insights into the potential of the Unreal Engine as a powerful tool for creating highly realistic 3D visualizations of large historical areas with potential applications in the field of geomatics.

The integration of generative AI (GAI) into the financial sector has brought about significant advancements, offering new solutions for various financial tasks. This review paper provides a comprehensive examination of recent trends and developments at the intersection of GAI and finance. By utilizing an advanced topic modeling method, BERTopic, we systematically categorize and analyze existing research to uncover predominant themes and emerging areas of interest. Our findings reveal the transformative impact of finance-specific large language models (LLMs), the innovative use of generative adversarial networks (GANs) in synthetic financial data generation, and the pressing necessity of a new regulatory framework to govern the use of GAI in the finance sector. This paper aims to provide researchers and practitioners with a structured overview of the current landscape of GAI in finance, offering insights into both the opportunities and challenges presented by these advanced technologies.

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).

The Hyper-Torus Universe Model (HTUM) proposes a novel framework to unify quantum mechanics, cosmology, and consciousness. This paper introduces HTUM's core concept: a higher-dimensional hyper-torus encompassing all possible states of existence. HTUM suggests that the universe functions as a quantum system where all outcomes are inherently connected, with consciousness playing a significant role in actualizing reality. The model introduces several key innovations, including the universe's 4-dimensional toroidal structure (4DTS), providing a new geometric interpretation of spacetime. HTUM presents dark matter and dark energy as nonlinear probabilistic phenomena within this toroidal framework, offering a unique perspective on their nature and interactions. The model proposes a mechanism for wave function collapse through universal self-observation, bridging quantum mechanics and gravity. It introduces a Topological Vacuum Energy Modulator (TVEM) function, offering a potential resolution to the cosmological constant problem. Furthermore, HTUM integrates consciousness as a fundamental aspect of the universe, influencing quantum state actualization and potentially resolving the hard problem of consciousness. The model explores the implications of a timeless singularity and the emergence of time as a product of causal relationships within the toroidal structure. This framework addresses critical challenges in modern physics, including the nature of quantum entanglement, the origin and fate of the universe, and the relationship between mind and matter. The paper discusses the mathematical formulation of HTUM, its implications for quantum mechanics and cosmology, and its potential to bridge the gap between science and philosophy. We present detailed predictions for the cosmic microwave background (CMB) power spectrum, gravitational wave signatures, and large-scale structure formation, demonstrating how HTUM differs from the standard ΛCDM model. Our analysis reveals distinctive oscillatory patterns in the relative difference between HTUM and ΛCDM predictions, with deviations reaching up to ±20% at certain scales. The paper also explores the unification of fundamental forces within the HTUM framework, proposing novel approaches to particle physics and quantum field theory. It introduces the concept of unified mathematical operations, suggesting a more holistic approach to mathematical thinking that aligns with the model's interconnected view of the universe. Additional testable predictions and proposed experimental approaches are discussed, including advanced space-based tests and laboratory experiments probing quantum gravity effects. These specific, quantifiable predictions offer multiple avenues for empirical validation, highlighting HTUM's potential to be distinguished from ΛCDM and other alternative cosmological models. HTUM represents a significant new perspective in our understanding of the universe, inviting further research and exploration into the nature of reality, consciousness, and the fundamental structure of the cosmos. By providing a comprehensive framework that unifies various aspects of physics, cosmology, and consciousness studies, HTUM offers a promising path toward a more complete understanding of our universe.

The shear stress generated by wall turbulence is the main cause of wall friction resistance in turbulent flow through pipes. This paper investigates the impact of inserting rest periods (regions of constant Reynolds number) within the pulsating operating cycle of velocity on the fully turbulent flow at large time-averaged Reynolds numbers, using the Large Eddy Simulation (LES) method. The study aims to explore the effect of increasing rest periods within pulsations on drag resistance. The dimensionless shear stress and drag reduction rates during different time periods of rest were analyzed. Numerical simulation results indicate that the pulsating velocity operation mode does not necessarily lead to drag reduction; it may even result in increased resistance. Inserting rest periods within the pulsation cycle can achieve drag reduction effects, with the maximum drag reduction rate reaching 21.8\%. Comparisons with experimental data and Direct Numerical Simulation (DNS) from the literature validate the feasibility of using the LES method for pipe pulsating operation modes.

The use of chimeric antigen receptors (CAR-T cells) for the treatment of patients with malignant haematological diseases has become a well-established application, for conditions such as refractory or relapsed B cell acute lymphoblastic leukaemia (B-ALL), B cell lymphomas (BCL), and multiple myeloma (MM). Nearly 35,000 patients have received autologous CAR-T cells for the treatment of these conditions only in the USA. Since their approval by the Food and Drug Administration (FDA) in 2017, over 1200 clinical trials have been initiated globally and there are at least 10 different CAR-T cells with approval by different regulatory agencies around the globe. In the USA the Food and Drug Administration (FDA) has approved 6 commercial CAR-T cells that are widely distributed worldwide. At the time of this writing, several clinical trials have been performed in patients with solid tumours such as glioblastoma, renal and pancreatic cancer, as well as in patients with autoimmune conditions such as systemic lupus erythematosus (SLE), idiopathic inflammatory myositis (IIM), and systemic sclerosis (SS). There are also several studies showing the potential benefit of CAR-T cells for other non-malignant diseases such as asthma and even fungal infections. In this review, without pretending to cover all the current areas of treatments with CAR-T cells, we offer a brief summary of some of the most relevant aspects of the use of CAR-T cells for some of these conditions.

Disaster issue consultation is crucial for effective emergency management, requiring timely and accurate information to support decision-making processes. This paper explores the integration of large language models (LLMs) with advanced prompt engineering to enhance the performance of AI systems in disaster management. We propose a novel multi-round prompt engineering approach that guides LLMs to iteratively refine their responses based on evolving disaster scenarios. Our method leverages diverse disaster-related datasets and employs a combination of accuracy metrics and a customized GPT-4 scoring system for evaluation. We conduct comprehensive experiments across multiple LLM platforms, including Qwen2, ChatGPT, Claude, and GPT-4, comparing our approach with baseline models and the Tree of Thoughts (ToT) method. The results demonstrate significant improvements in both accuracy and response quality, highlighting the effectiveness of our method in providing contextually relevant and actionable insights. Additional analysis confirms the robustness and generalizability of our approach across various disaster scenarios, establishing it as a valuable tool for enhancing disaster management practices.

Since the beginning of the internet era, there has been an explosion of growth in structured data (such as numbers, symbols, and labels) as well as unstructured data (including images, videos, and text). Efficient and accurate mixed query of these two types of data is a key technology to achieve high-quality information retrieval, and it is also a major challenge that needs to be solved urgently in the industry. In this study, we employ an advanced Transformer model that combines strategies and fine-tuning techniques for multi-task learning. Specifically, the model is first pre-trained on a large-scale, general-purpose dataset to learn different types of data representations and basic language comprehension skills. After that, we fine-tuned the parameters of the model to better suit these specific data processing tasks for specific application scenarios, such as image annotation, video content analysis, and structured data query. At the heart of the model is the self-attention mechanism, which allows the model to automatically emphasize the important parts and ignore irrelevant information when processing the input data. In addition, we have introduced task-specific adaptation layers that are designed to add additional processing power to the original Transformer architecture, such as a semantic analysis layer for unstructured text data and a relational extraction layer for structured data. This combination of general pre-training and task-specific fine-tuning allows the model to flexibly process and integrate information from different data sources, improving processing efficiency and accuracy. Experimental results show that the model performs well in a variety of data processing tasks, significantly improves the accuracy and efficiency of information retrieval, and verifies the strong potential and adaptability of large language models in processing mixed data types.

In a trip planning service, travelers first set a starting point, a destination, and a sequential list of specific points of interest types (e.g., museums, restaurants, and parks). Based on this information, the service searches the spatial database to customize the best travel itinerary for the tourist. However, in previous studies, planners only considered the time factor when designing the optimal route, and failed to fully consider the quality of each point of interest. In this study, we specifically leveraged the capabilities of large language model to parse and respond to complex travel-related user queries. To apply large language model to route planning, we fine-tuned the model to understand geotagging and user travel preferences. We have introduced a novel graph search algorithm combined with large language model output, which optimizes the route search process to provide optimal travel recommendations by taking into account various factors such as distance length, budget constraints, and popularity of tourist attractions. In addition, we have integrated real-time traffic data and historical travel data to further improve the prediction accuracy and application usefulness of the model. In the experimental validation phase, we designed a series of benchmarks to compare the performance of the system with traditional algorithms and other machine learning-based route planning methods. Experimental results show that our model has a significant improvement compared with traditional methods in improving the speed and accuracy of path selection.

The world health organisation (WHO) revealed approximately 280 million people in the world suffer from depression. Yet, existing studies on early-stage depression detection using machine learning (ML) techniques are limited. Prior studies have applied a single stand-alone algorithm which are unable to deal with data complexities, prone to overfitting and limited in generalisation. To this end, our paper examined the performance of several ML algorithms for early-stage depression detection using two benchmark social media datasets (D1 and D2). More specifically, we incorporated sentiment indicator to improve our model performance. Our experimental results showed that sentence bidirectional encoder representations from transformers (SBERT) numerical vectors fitted into stacking ensemble model achieved comparable F1 scores of 69% in dataset (D1) and 76% in dataset (D2). Our findings suggest that utilising sentiment indicators as additional feature for depression detection yields an improved model performance and thus, we recommend the development of depressive term corpus for future work.

Three-dimensional (3D) geological modeling technology offers intricate geological information services and technical support for the research of urban geological conditions and their evolutionary mechanisms. It further facilitates the analysis of environmental geological problems, encompassing their distinguishing features and genetic mechanisms. The precision of such three-dimensional models is predominantly influenced by the caliber of modeling data, the chosen modeling methodologies, and the intricacy of the modeled geological objects. This research, exemplified by the three-dimensional geological structure modeling of the Wuhan metropolitan development area, aims to explore a comprehensive three-dimensional modeling framework for urban geology, particularly in scenarios with large-scale and complex geological conditions. This study holds significant technical value in enhancing the application of 3D geological modeling, as well as practical importance for urban geological investigations and research.

Background P53 gene mutation is a very common event in human neoplasia, and genetic mutations in the P53 gene in a single allele are responsible for a hereditary cancer susceptibility syndrome (Li Fraumeni). These variants encode distinct isoforms of the p53 protein, which may disrupt its transcriptional activity. These point mutant proteins are more stable than the normal protein and the mutant product accumulates at a high level that allows obtaining important information about p53 gene expression in malignant cells, especially in Chronic Lymphocytic Leukemia, (CLL). By Enzyme Linked Immune-Absorbent Assay method, (ELISA), was analyzed the frequency of p53 protein expression to 20 eligible patients diagnosed with CLL for to investigate the relationship of this protein in the stages of the disease and the impact on treatment response and survival. In ELISA technique was used the specific antibodies for isoform p53 protein, PAb 240 antibodies. These antibodies bind specifically to denatured p-53 protein. Species reactivity is for human in conformity with the prospect from Manual, Catalog No. LS-F174, Bio-Rad. Results The average concentrations of p53 proteins in 17 of 20 cases were found 16.76 μg / dl, with CV = 0.5% and the probability index p = 0.034. Very high pathological values in the 3 cases of isoform p53 protein were calculated in 2 men, (PM) in the value of 60 µg / dL, respectively at 40 µg / dL and in the case of females, (PW), in 40 µg / dL value, with the transformation into Diffuse Large Lymphoma, (DLL). Conclusion This ELISA method has proven to be a useful prognostic tool for the application of personalized treatment of on-immune therapy, in cases diagnosed with the type B-CLL.

The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of this data present substantial challenges in data modeling and analysis, which have been tamed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of Large Language Models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and generation of human behavior through the lens of wearable sensor data. This survey explores current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensors data, the capabilities and limitations of LLMs to model them and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensors data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensors data and LLMs, offering insights into the current state and future prospects of this emerging field.

This study presents a strategic approach to developing applications focused on implementing Large Language Models using the Langchain framework in Python. Three language models are highlighted: GPT-3.5 (turbo mode), LLaMA 2, and Vicuna 7B, each with their distinctive features and capabilities. The methodology used is described in detail, including data extraction from medical reports using zero-shot prompting data extraction techniques, interaction with language models, and structured storage of results. The performance of the models in data extraction is evaluated, presenting metrics such as precision, recall, and F1 score. The results demonstrate high model capability in extracting information, although areas for improvement are identified, particularly in data extraction precision. In conclusion, the efficacy of the models in extracting information from medical histories is not considerably acknowledged, with an emphasis on the importance of improving precision and increasing the volume of trained data for future research in healthcare digitalization.

This survey provides a comprehensive overview of in-context learning (ICL) in large language models (LLMs), a phenomenon where models can adapt to new tasks without parameter updates by leveraging task-relevant information within the input context. We explore the definition and mechanisms of ICL, investigate the factors contributing to its emergence, and discuss strategies for optimizing and effectively utilizing ICL in various applications. Through a systematic review of recent literature, we first clarify what ICL is, distinguishing it from traditional fine-tuning approaches and highlighting its unique characteristics. We then delve into the underlying causes of ICL, examining theories ranging from implicit meta-learning during pre-training to the emergence of task vectors in LLMs. The survey also covers various approaches to enhance ICL performance, including prompt engineering techniques, demonstration selection strategies, and methods for improving generalization across diverse tasks. Additionally, we discuss the limitations and challenges of ICL, such as its sensitivity to demonstration ordering and potential biases. By synthesizing findings from numerous studies, we aim to provide researchers and practitioners with a clear understanding of the current state of ICL research, its practical implications, and promising directions for future investigation. This survey serves as a valuable resource for those seeking to leverage ICL capabilities in LLMs and contributes to the ongoing discourse on the remarkable adaptability of these models.

Large Language Models (LLMs) have demonstrated promising capabilities to solve complex tasks in critical sectors such as healthcare. However, LLMs are limited by their training data which is often outdated, the tendency to generate inaccurate ("hallucinated") content and a lack of transparency in the content they generate. To address these limitations, retrieval augmented generation (RAG) grounds the responses of LLMs by exposing them to external knowledge sources. However, in the healthcare domain there is currently a lack of systematic understanding of which datasets, RAG methodologies and evaluation frameworks are available. This review aims to bridge this gap by assessing RAG-based approaches employed by LLMs in healthcare, focusing on the different steps of retrieval, augmentation and generation. Additionally, we identify the limitations, strengths and gaps in the existing literature. Our synthesis shows that proprietary models such as GPT-3.5/4 are the most used for RAG applications in healthcare. Also, there is a lack of standardized evaluation frameworks for RAG-based applications. In addition, the majority of the studies do not assess or address ethical considerations related to RAG in healthcare. It is important to account for ethical challenges that are inherent when AI systems are implemented in the clinical setting. Lastly, we highlight the need for further research and development to ensure responsible and effective adoption of RAG in the medical domain.

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinizes the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs like GPT-4, GPT-3, and LLAMA, adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluate these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain accuracy, efficiency, and scalability. Our results reveal that while conventional models excel with structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

The use of Retrieval-augmented generation (RAG) using large language models (LLMs) has shown potential for addressing issues such as hallucinations and inadequately contextualized responses. A pivotal stage in the RAG process involves a retriever for retrieving chunks based on semantic similarity with the query. In this study, we advocate for and provide experimental evidence supporting integrating and maintaining questions and answers (QA) formatted databases to improve retrieved-context representations and response quality. Our experiments evaluate our approach on benchmark RAG datasets using standard evaluation metrics and provide comparative analyses against state-of-the-art retrieval methods, showing the potential of our approach.

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.

Artificial intelligence technologies based on deep convolutional neural networks and large lan-guage models have made significant breakthroughs in many tasks such as image recognition, target detection, semantic segmentation and natural language processing, but also face the problem of contradiction between the high computational capacity of the algorithms and the limited deployment resources. Quantization, which converts floating-point neural networks into low-bit-width integer networks, is an important and essential technique for efficient deploy-ment and cost reduction in edge computing. This paper analyze various existing quantization methods, showcase the deployment accuracy of advanced techniques, and discuss the future challenges and trends in this domain.

Good communication skills are essential for prospective workers, particularly college students, to clearly convey their abilities and understanding during job interviews. Despite the high demand for strong communication skills among employers, many students struggle with inadequate experience and skills, leading to reduced confidence and lower chances of securing desired jobs. Existing tools and resources for improving communication skills are limited, especially free ones, leaving students underprepared and less confident in interviews. To address this issue, a comprehensive solution is needed that provides free, customizable tools to enhance students' interview communication skills. Invisor is a web-based self-interview training application that leverages AI and Machine Learning to analyze users' behavior, responses, and facial expressions during simulated interviews. Accessible via desktop, laptop, or mobile devices, Invisor offers interactive and voice-recorded feedback to help students prepare for interviews effectively. By employing AI technologies, Invisor generates personalized interview questions based on job descriptions, enhancing the realism of the interview experience and providing tailored feedback to improve users' responses. Developed using agile methodologies, Invisor has undergone iterative enhancements, integrating user and stakeholder feedback promptly to improve usability and functionality. The combination of AI-driven simulations and agile development practices enables Invisor to meet current user needs and anticipate future demands, providing a robust tool for interview preparation in a competitive job market. This paper outlines the development and implementation of Invisor, demonstrating its effectiveness in enhancing interview skills and confidence among students and job seekers.

Securing funding is a critical yet complex task for organizations and individuals. This study presents an innovative chatbot designed to streamline the process using advanced Natural Language Processing (NLP) techniques and, specifically, a Retrieval-Augmented Generation (RAG) pipeline optimized for real-world applications. Our chatbot assists users in identifying suitable public tenders for financial support through natural language queries and a comprehensive public data database. The chatbot operates in a two-stage interaction model, initially providing summarized tender information for exploratory brainstorming, followed by detailed data upon user selection. A custom filtering mechanism ensures that the user interface elements responsible for swapping the interaction stages are consistent with the responses generated by the conversational agent. Human-evaluation tests demonstrated an average accuracy of 90.4% in document retrieval, with an average of 2.11 interactions required to find a specific tender. User satisfaction, rated on a scale of 1 to 5, averaged 3.14 (±1.73), indicating generally positive user experience with room for improvement. This approach addresses challenges of relevance, accuracy, and conversational flow, resulting in a reliable chatbot that simplifies the process of finding funding opportunities.

Abstract: Giant Cell Arteritis (GCA) is an autoimmune/autoinflammatory disease affecting large vessels in patients over 50 years old. The disease presents as an acute inflammatory response with two phenotypes, cranial-GCA and Large Vessel Vasculitis (LV)-GCA, involving the thoracic aor-ta and its branches. 18F-fluorodeoxyglucose positron emission tomography-computed tomogra-phy (18F-FDG PET-CT) is among the imaging techniques contributing to diagnosis of patients with systemic disease. However, its association with soluble inflammatory markers is still elu-sive. This proof-of-concept study aims to identify novel soluble serum biomarkers in PET/CT pos-itive patients with LV-GCA and associate them with active (0 months) and inactive disease (6 months following treatment), in sequential samples. The Most-Disease-Segment Target-to-Background Ratio (TBRMDS) was calculated for 9 LV-GCA patients, while 12 cranial-GCA and 7 Polymyalgia Rheumatica patients with negative initial PET/CT served as disease controls. Serum macrophage-related cytokines were evaluated by Cytometric Bead Array (CBA). Finally, previously published NMR-metabolomics data acquired at the same blood sampling were associated with PET/CT findings. TBRMDS was significantly increased in active versus inactive disease (3.45 vs. 2.55, p=0.008). The analysis identified 6 serum metabolites, as more sensitive to change from the active to inactive state. Among them, choline levels were exclusively altered in the LV-GCA group, but not the disease controls. Cytokine levels were not associated with PET/CT activity. Combining with CRP, ESR, and TBRMDS a composite index was generated to depict well the differences between active and inactive systemic LV-GCA (25.45 vs 11.45, p=0.0039). These preliminary results could pave the way for more extensive studies integrating serum metabolomic parameters with PET/CT imaging data to extract sensitive composite disease indexes useful for the everyday clinical practice.

: Multimodal Large Language Models (MLLMs) harness comprehensive knowledge spanning text, images, and audio to adeptly tackle complex problems, including zero-shot in-context learning scenarios. This study explores the ability of MLLMs in visually solving the Traveling Salesman Problem (TSP) and Multiple Traveling Salesman Problem (mTSP) using images that portray point distributions on a two-dimensional plane. We introduce a novel approach employing multiple specialized agents within the MLLM framework, each dedicated to optimizing solutions for these combinatorial challenges. Our experimental investigation includes rigorous evaluations across zero-shot settings and introduces innovative multi-agent zero-shot in-context scenarios. The re-sults demonstrated that both multi-agent models—Multi-Agent 1, which includes the Initializer, Critic, and Scorer agents, and Multi-Agent 2, which comprises only the Initializer and Critic agents—significantly improved solution quality for TSP and mTSP problems. Multi-Agent 1 ex-celled in environments requiring detailed route refinement and evaluation, providing a robust framework for sophisticated optimizations. In contrast, Multi-Agent 2, focusing on iterative re-finements by the Initializer and Critic, proved effective for rapid decision-making scenarios. These experiments yield promising outcomes, showcasing the robust visual reasoning capabilities of MLLMs in addressing diverse combinatorial problems. The findings underscore the potential of MLLMs as powerful tools in computational optimization, offering insights that could inspire further advancements in this promising field.

Primary bone lymphoma of the spine (PBL) is a rare entity and the most shared type of non-Hodgkin lymphoma (LNH) appearing in bone lesions deprived of nodal or extra-nodal in-volvement and accounting for approximately 2% of all lymphomas. Most PBL are diffuse large B-cell lymphomas (DLBCL) and commonly involve the appendicular skeleton. Due to its atypical location and non-specific clinical imaging features mimicking certain neoplastic or infectious processes, this pathology may be misdiagnosed, thus complicating and delaying diagnosis. Our case reports a patient in her sixties who had been suffering from chronic low back pain for a year, and had gradually started to develop cruralgia and fever. She underwent a blood sample, magnetic resonance imaging (MRI), and positron emission tomography (18F-FDG-PET/CT) which revealed significant inflammatory syndrome, a pattern of spondylodiscitis at the L3-L4 level associated with morphological and metabolic invasion extending posteriorly, raising suspicion of epiduritis. No other lesions were found on the rest of the body. Neurosurgical management was performed and a biopsy was made. Histological results showed aggressive and diffuse large B-cell lymphoma, suggesting a diagnosis of PBL. This case highlights the first case of spondylodiscitis mimicking PBL in the lumbar spine, the intricacies of the diagnostic work-up, and the complexity of discriminating with an infectious process in the spine, as both have a similar, non-specific clinical presentation with different prognosis and therapeutic management.

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.

As large language models (LLMs) continue to advance, evaluating their comprehensive capabilities becomes significant for their application in various fields. This research study comprehensively evaluates the language, vision, speech, and multimodal capabilities of GPT-4o. The study employs standardized exam questions, reasoning tasks, and translation assessments to assess the model's language capability. Additionally, GPT-4o's vision and speech capabilities are tested through image classification and object recognition tasks, as well as accent classification. The multimodal evaluation assesses the model's performance in integrating visual and linguistic data. Our findings reveal that GPT-4o demonstrates high accuracy and efficiency across multiple domains in language and reasoning capabilities, excelling in tasks that require few-shot learning. GPT-4o also provides notable improvements in multimodal tasks compared to its predecessors. However, the model shows variability and faces limitations in handling complex and ambiguous inputs, particularly in audio and vision capabilities. This paper highlights the need for more comprehensive benchmarks and robust evaluation frameworks, encompassing qualitative assessments involving human judgment as well as error analysis. Future work should focus on expanding datasets, investigating prompt-based assessment, and enhancing few-shot learning techniques to test the model's practical applicability and performance in real-world scenarios.

Interaction with social agents employing natural language have been discussed especially since Weizenbaum (1966) observed the social effects of his chatbot named 'Eliza', which imitated a cli-ent-centered conversation. With Nass and Reeves’ media equation theory and computers as social actors paradigm, a well-tested framework has been introduced to the study of human-computer interaction. In the 1990s, there was a renewed focus on natural language analysis, which has be-come a crucial area of research in machine learning. Recent advancements in data processing and storage capacities have led to the development of AI-generated utterances that closely resemble human utterances. As a result, AI-based systems can now mimic social relationships to a signifi-cant extent. In light of these technological developments, the article explores whether quasi-social relationships should be considered within the field of social psychology and examines the poten-tial advantages and challenges of this approach.

Graphene was synthesized through a two-step pyrolysis method using waste candlenut (Aleurites moluccanus) shells as the precursor. Cerium (Ce)/graphene composites were prepared via an impregnation technique. The resulting graphene and Ce/graphene were characterized using various analytical methods, including Scanning Electron Microscopy with Energy-Dispersive Spectroscopy (SEM-EDS), X-ray Diffraction (XRD), X-ray Photoelectron Spectroscopy (XPS), Transmission Electron Microscopy (TEM), Thermo Gravimetric Analysis (TGA), Fourier Transform Infrared (FTIR) spectroscopy, Cyclic Voltammetry (CV), and Linear Sweep Voltammetry (LSV). The bio-carbon produced predominantly exhibited a graphene structure with flat carbon morphology and an interlayer distance of 0.33 nm. This structural information is supported by XRD data, which shows a broad and weak peak at 2θ = 26° corresponding to the C (002) plane, indicative of graphene presence. FTIR, XPS, and Raman spectroscopy further confirmed the presence of graphene through the detection of Csp2 aromatic bonds and the characteristic D, G, and 2D peaks. Notably, the performance of cerium can be enhanced by the incorporation of graphene, attributed to the large surface area and chemical interactions between Ce and graphene. Consequently, candlenut-derived graphene shows potential as a supportive material for modifying the properties of cerium, thereby opening avenues for various advanced applications, such as sustainable and high-performance energy storage systems.

Artificial intelligence methods, especially artificial neural networks (ANNs), have increasingly been utilized for the mathematical description of physical phenomena in (metallic) material processing. Traditional methods often fall short in explaining the complex, real-world data ob-served in production. While ANN models, typically functioning as "black boxes," improve pro-duction efficiency, a deeper understanding of the phenomena, akin to that provided by explicit mathematical formulas, could enhance this efficiency further. This article proposes a general framework that leverages (CAE) ANNs to explain predicted results alongside their graphical presentation, marking a significant improvement over previous approaches and those relied on expert assessments. Unlike existing Explainable AI (XAI) methods, the proposed framework mimics the standard scientific methodology, utilizing minimal parameters for the mathematical representation of physical phenomena and their derivatives. Additionally, it analyzes the relia-bility and accuracy of the predictions using well-known statistical metrics, transitioning from deterministic to probabilistic descriptions for better handling of real-world phenomena. The proposed approach addresses both aleatory and epistemic uncertainties inherent in the data. The concept is demonstrated through the hot extrusion of aluminum alloy 6082, where CAE ANN models and predicts key parameters, and ChatGPT explains the results, enabling researchers and/or engineers to better understand the phenomena and outcomes obtained by ANNs.

Given the widespread use of AI language models such as ChatGPT, there is an urgent need 1 to understand their political biases in different languages. This study aims to uncover such biases. To 2 investigate this issue, we applied IDRLabs’ Political Coordinates Test to ChatGPT based on GPT-4 3 in four languages - English, French, German, and Italian. The results confirm previous studies that 4 identified a left-libertarian bias in ChatGPT. There was remarkable consistency in political orientation 5 across all four languages, although minor variations were found. Differences in ChatGPT response 6 distributions across languages could indicate culturally determined differences in interpretation 7 of political questions. The results highlight the need to diversify and optimize data collection and 8 model training methods to ensure greater fairness and neutrality and minimize the influence of bias. 9 Our study highlights the importance of cultural differences in the processing and interpretation of 10 political information by AI models.

In China, "new quality productive forces" have become an important focus for high-quality development; accelerating this development is an important task for the Chinese government in 2024. Such development relies on the traction of the digital economy. In view of this, developing “new quality productive forces” driven by the Chinese digital economy requires focusing on blocking points, such as the insufficient vitality of data, inadequate algorithmic regulation, the uneven distribution of computing power resources and the immature market environment. In order to dredge these blocking points, it is necessary to establish basic rules on data, strengthening algorithm supervision, building a national integrated computing power network, and optimizing the market environment.

In the rapidly evolving landscape of AI-supported programming education, there's a growing interest in leveraging such tools to support students helping about what good code makes out. This study investigates the impact of ChatGPT on code quality among part-time undergraduate students enrolled in introductory Java programming courses. With no prior Java experience, students from two separate groups completed identical programming exercises emphasizing coding conventions and code quality. Utilizing static code analysis tools, we assessed adherence to a common coding convention ruleset and calculated cyclomatic and cognitive complexity metrics for submitted code. Our comparative analysis highlights significant improvements in code quality for the ChatGPT-assisted group (treatment group), with marked reductions in rule violations and both cyclomatic and cognitive complexities. Specifically, the treatment group demonstrated greater adherence to coding standards, with fewer violations across several rules, and produced code with lower complexity. These results suggest that ChatGPT can be a valuable tool in programming education, aiding students in writing cleaner, less complex code and better adhering to coding conventions. However, the study's limitations, including the small sample size and the novice status of the participants, necessitate further research with larger, more diverse populations and in different educational contexts.

Takayasu arteritis is an inflammatory vasculitis that mainly impacts the large vessels including the aorta and its branches. Ocular manifestations may include retinal ischemia, optic neuropathy, cataracts, and retinal artery occlusion. We present two cases where central retinal artery occlusion was found in patients with Takayasu arteritis and wish to highlight to consider Takayasu arteritis in young patients with unexplained retinal artery occlusion.

Unmanned aerial vehicles (UAVs) have increasingly become integral to multi-access edge computing (MEC) due to their flexibility and cost-effectiveness, especially in the B5G and 6G eras. This paper aims to enhance the Quality of Experience (QoE) in large-scale UAV-MEC networks by minimizing the shrinkage ratio through optimal decision-making in computation mode selection for each user device (UD), UAV flight trajectory, bandwidth allocation, and computing resource allocation at edge servers. However, the interdependencies among UAV trajectory, binary task offloading mode, and computing/network resource allocation across numerous IoT nodes pose significant challenges. To address these challenges, we formulate the shrinkage ratio minimization problem as a mixed-integer nonlinear programming (MINLP) problem and propose a two-tier optimization strategy. To reduce the scale of the optimization problem, we first design a low-complexity UAV partition coverage algorithm based on the Welzl method and determine the UAV flight trajectory by solving a Traveling Salesman Problem (TSP). Subsequently, we develop a coordinate descent (CD) based method and an alternating direction method of multipliers (ADMM) based method for network bandwidth and computing resource allocation in the MEC system. The CD-based method is simple to implement and has a low computational complexity, while the ADMM-based method can further enhance the optimization result through joint optimization. Extensive simulations demonstrate that our proposed algorithms perform well in large-scale edge networks and outperform other representative benchmark methods.

Generating executable code from natural language instructions using Large Language Models (LLMs) presents challenges such as semantic understanding and handling ambiguous input. This study focuses on the SantaCoder model and explores the impact of in-context learning on code generation using the MBPP and HumanEval datasets for evaluation. Our results demonstrate significant improvements in three key metrics (defined in the paper): correctness@k, similarity@k and pass@k. To address the problem of selecting optimal demonstrations to maximize correctness and pass rates, we investigate two methods: latent concept selection and random selection in this paper. These findings highlight the effectiveness of in-context learning and the critical role of demonstration selection in enhancing the accuracy, efficiency, and versatility of the SantaCoder model in code generation.

Obsessive-Compulsive Disorder (OCD) is a mental health condition marked by recurrent intrusive thoughts or sensations that compel individuals to perform repetitive behaviors or mental acts. Obsessions and compulsions significantly disrupt daily life and cause considerable distress. Early identification and intervention improve long-term outcomes. This study aimed to evaluate the ability of four advanced artificial intelligence models (ChatGPT-3.5, ChatGPT-4, Claude, and Bard) to accurately recognize OCD compared to human professionals and to assess recommended therapies and stigma attributions. This study was conducted during March 2024 utilizing 12 vi-gnettes. Each vignette depicted a client, either a young adult or a middle-aged male or female, attending an initial therapy session. Each vignette was evaluated ten times, resulting in 480 evaluations. The results were compared with those of a human sample of 514 psychotherapists, as reported by Canavan. Significant differences were found. AI models demonstrated higher OCD recognition rates and confidence levels than human professionals and showed 100% confidence in recognition, compared to 87% among psychotherapists. AI models also recommended evi-dence-based interventions more frequently, with ChatGPT-3.5 and Claude at 100%, ChatGPT-4 at 90%, and Bard at 60%, compared to 61.9% among psychotherapists. Additionally, AI models ex-hibited significantly lower stigma and danger estimations, though both AI and psychotherapists demonstrated high willingness to treat the described cases. The findings suggest that AI models surpass human professionals in recognizing OCD and recommending evidence-based treatments while also demonstrating lower stigma. These results highlight the potential of AI tools to enhance OCD diagnosis and treatment in clinical settings.

This paper presents data supporting the IC Regimen for potentiating the effectiveness of lorlatinib in treating ALK positive cancers, and specifically non-small cell lung cancer. Lorlatinib is an effective treatment for ALK driven non-small cell lung cancer and other ALK driven cancers. Lorlatinib inhibits ALK kinase and achieves good brain tissue levels, a common site for metastases in lung cancers. However, resistance to lorlatinib usually supervenes and the cancer awakens and starts growing again, resistant to lorlatinib. This paper analyses data indicating that adding two common generic drugs, itraconazole and cilostazol, to lorlatinib treatment may delay resistance development. Itraconazole is marketed worldwide as a generic antifungal drug that also inhibits Hedgehog signaling, CYP3A4, and the p-gp efflux pump. Cilostazol is a generic anti-thrombosis, phosphodiesterase 3 inhibiting drug that carries minimal bleeding risk. Cilostazol may enhance lorlatinib by deprivation of trophic growth factors supplied by platelets. Itraconazole may enhance lorlatinib effectiveness by reducing or stopping a Hedgehog centered amplifying feedback loop with ALK kinase. The combination of metastatic non-small cell lung cancer being a low-survival disease and the general safety itraconazole plus cilostazol augmentation, make a clinical trial of this trio worthwhile.

In the context of rapid urbanization, the spatiotemporal patterns of socio-economic exposed to high seismic hazard in large cities lacks quantitative assessment, thus, it is difficult to understand the evolution of earthquake catastrophe risk there. In this paper, exposure change rate, and absolute and relatively exposure indices were proposed to quantitatively study the changes of spatiotemporal exposure to high seismic hazard in urban areas of large cities (i.e., permanent residents in urban areas more than 1 million) in Chinese mainland, using a set of multi-temporal population, GDP, and built-up datasets and a seismic hazard zoning map. The results show that, 64 out of 78 large cities are entirely or partially located in high seismically hazardous zones. Although the urban areas of large cities in high seismically hazardous zones (HSHUAs) cover only 1.73% (167177 km²) of mainland China, their share of population, GDP, and built-up land amounted to 18.14%, 30.24% and 24.55%, respectively, in 2015. Unprecedented urbanization has led to a dramatic exposure growth in HSHUAs between 1990 and 2015. The population, GDP, and built-up land in HSHUAs increased by 110 million people (with an average annual growth rate of 2.37%), 273.71 trillion USD(average annual growth rate of 11.15%), and 10593 km2 (average annual growth rate of 2.02%), respectively. HSHUAs experienced much faster population and GDP growth than the whole country, while relatively slower growth in built-up land. Exposure growth in HSHUAs also was varied for different types of large cities. Megacities had a higher proportion of increased GDP and population in HSHUAs, induced by industry and population agglomeration. Whereas, Type II large cities had a higher proportion of increased built-up land in HSHUAs, driven mainly by urban sprawl. Our analysis indicates that, for large cities under rapid urbanization, it is an urgent need to strengthen resilient urban planning, renewal and construction.

The accurate diagnosis and effective treatment of mental health disorders such as depression remain challenging owing to the complex underlying causes and varied symptomatology. Traditional information extraction methods struggle to adapt to evolving diagnostic criteria such as the Diagnostic and Statistical Manual of Mental Disorders fifth edition (DSM-5) and to contextualize rich patient data effectively. This study proposes a novel approach for enhancing information extraction from mental health data by integrating medical knowledge graphs and large language models (LLMs). Our method leverages the structured organization of knowledge graphs specifically designed for the rich domain of mental health combined with the powerful predictive capabilities and zero-shot learning abilities of LLMs. This research enhances the quality of knowledge graphs through entity linking and demonstrates superiority over traditional information extraction techniques, making a significant contribution to the field of mental health. It enables a more fine-grained analysis of the data and the development of new applications. Our approach redefines the manner in which mental health data are extracted and utilized. By integrating these insights with existing healthcare applications, the groundwork is laid for the development of real-time patient monitoring systems. The performance evaluation of this knowledge graph highlights its effectiveness and reliability, indicating significant advancements in automating medical data processing and depression management.

The growing usage of Generative AI tools in scientific writing requires a critical examination of their benefits and challenges. This literature review is aimed at comprehensively analyzing current empirical research articles focused on the application of Generative AI in scientific writing. The Google Scholar database was used to search for the literature. The following keywords were used: "Generative AI" and "academic writing", "LLM" (Large Language Models) and "academic writing", "Generative AI" and "Scientific writing", and "ChatGPT" and "Scientific Writing". The search was restricted to articles published between January 1, 2023, and April 30, 2024. 15 articles were selected as appropriate for the study and analyzed. It was found that, thus far, ChatGPT is the most exploited tool in the studies. AI tools such as Bard (Gemini), Bing, Claude2, and Elicit were also tested. The benefits of Generative AI usage in scientific writing were found to be omnipresent. It can aid in the generation of structured abstracts, titles, introductions, literature reviews, and conclusions of a scientific article. Generative AI also makes writing more efficient and time-saving. Its capabilities in improving language and proofreading are well-established. However, the generation of inaccurate content and references by current commercially available LLMs poses a serious problem. The lack of critical thinking and tendency to produce non-original content are significant drawbacks. Generative AI should be employed with human oversight, serving as an assistant rather than a replacement. Transparency in AI usage in scientific writing is essential, along with the necessity for proper legal regulation.

California has experienced a surge in wildfires, prompting research into contributing factors, including weather and climate conditions. This study investigates the complex, multiscale interactions between large-scale climate patterns, such as the Boreal Summer Intraseasonal Oscillation (BSISO), El Niño Southern Oscillation (ENSO), and the Pacific Decadal Oscillation (PDO), and their influence on moisture and temperature fluctuations, and wildfire dynamics in California. The combined impacts of PDO and BSISO on intraseasonal fire weather changes, the interplay between Fire Weather Index (FWI), relative humidity, vapor pressure deficit (VPD), and temperature in assessing wildfire risks, and geographical variations in the relationship between FWI and climatic factors within California are examined. The study employs a multi-pronged approach, analyzing wildfire frequency and burned areas alongside climate patterns and atmospheric conditions. Findings reveal significant variability in wildfire activity across different climate conditions, with heightened risks during specific BSISO phases, La-Niña, and cool PDO. The influence of BSISO varies depending on its interaction with PDO. Temperature, relative humidity, and VPD show strong predictive significance for wildfire risks, with significant relationships between FWI and temperature in elevated regions (correlation, r > 0.7, p ≤ 0.05) and FWI and relative humidity along the Sierra Nevada Mountains (r ≤ -0.7, p ≤ 0.05).

Software systems are often maintained by a group of experienced software developers, in order to ensure that faults which may bring the system down are less likely. Large turnover in organizations such as CERN makes it important to think of ways of onboarding newcomers on a technical project rapidly. This paper focuses on optimizing the way that people get up-to-speed on the business logic and technologies used on the project, using a knowledge-imbued large language model that is enhanced using domain-specific knowledge from the group or team’s internal documentation.

Product attribute extraction is an growing field in e- commerce business, with several applications including product ranking, product recommendation, future assortment planning and improving online shopping customer experiences. Under- standing the customer needs is critical part of online business, specifically fashion products. Retailers uses assortment planning to determine the mix of products to offer in each store and channel, stay responsive to market dynamics and to manage inventory and catalogs. The goal is to offer the right styles, in the right sizes and colors, through the right channels. When shoppers find products that meet their needs and desires, they are more likely to return for future purchases, fostering customer loyalty. Product attributes are a key factor in assortment planning. In this paper we present PAE, a product attribute extraction algorithm for future trend reports consisting text and images in PDF format. Most existing methods focus on attribute extraction from titles or product descriptions or utilize visual information from existing product images. Compared to the prior works, our work focuses on attribute extraction from PDF files where upcoming fashion trends are explained. This work proposes a more comprehensive framework that fully utilizes the different modalities for attribute extraction and help retailers to plan the assortment in advance. Our contributions are three-fold: (a) We develop PAE, an efficient framework to extract attributes from unstructured data (text and images); (b) We provide catalog matching methodology based on BERT representations to discover the existing attributes using upcoming attribute values; (c) We conduct extensive experiments with several baselines and show that PAE is an effective, flexible and on par or superior (avg 92.5% F1-Score) framework to existing state-of-the-art for attribute value extraction task.

Civic participation is of great significance to urban management decision-making. In order to facilitate citizens to participate in city management decision-making, this paper proposes a large-scale group decision-making (LSGDM) method based on multi-granular probabilistic linguistic preference relations (MG-PLPRs). First, each decision maker selects a language terms set from the multi-granularity language terms set to represent individual preference relations and the MG-PLPRs are obtained by statistical calculation to represent sub-group’s preferences information. Then, an optimization model based on the expected consistency of PLPR and consensus measure of groups is established to achieving consensus reaching processes, which can ensure satisfactory individual consistency and group consensus. Finally, the validity and applicability of the proposed method is verified by a case of a city "shared garden" site selection with the participation of citizens.

This paper presents the work done to transition the lab scale synthesis (1 g) to a large scale (400 g) synthesis of the 3-5-diamino-1H-Pyrazole Disperazol; a new pharmaceutical for treatment of antibiotic resistant Pseudomonas aeruginosa biofilm infections. The potentially hazardous diazotisation step in the lab scale synthesis was transformed to a safe and easy to handle flow chemistry step. Additionally, the paper presents an OSHA recommended safety assessment of the active compound E, performed by Fauske and Associates, LLC.

With the rapid growth of large language models (LLMs), there is increasing demand for memory and computation in LLMs. Recent efforts on post-training pruning of LLMs aim to reduce the model size and computation requirements, yet the performance is still sub-optimal. In this paper, we present a plug-and-play solution for post-training pruning of LLMs. The proposed solution has two innovative components: 1) Relative Importance and Activations (RIA), a new pruning metric that jointly considers the weight and activations efficiently on LLMs; and 2) Channel Permutation, a new approach to maximally preserve important weights under N:M sparsity. The two proposed components can be readily combined to further enhance the N:M semi-structured pruning of LLMs. Our empirical experiments show that RIA alone can already surpass all existing post-training pruning methods on prevalent LLMs, e.g., LLaMA ranging from 7B to 65B. Furthermore, N:M semi-structured pruning with channel permutation can even outperform the original LLaMA2-70B on zero-shot tasks, together with practical speed-up on specific hardware. Our code is available at: https://github.com/biomedical-cybernetics/Relative-importance-and-activation-pruning

This paper explores the role of open-source large language models in IoT cybersecurity world. The threats of malicious activity on the Internet and the loss of private information are very real and lead to serious consequences. The purpose of this paper is to investigate how open source-large language models can help to defend against the growing threat of cyber-crimes. We conducted our experiments in two directions. The first one is a security assistant that helps with cybersecurity best practices advices. The second one is a how large language model can simulate a vulnerable IoT system. For both types of experiments, the interactive mode of operation of the language model is used. In the context of the cybersecurity research, a major advantage of the locally installed open-sourced large language models is that they do not share sensitive data with a remote system in a cloud. The paper concludes by discussing the potential impact of open-source large language models on cybersecurity research and recommends future research directions.

This paper integrates carrier manifolds from control theory and hybrid systems modeling to develop a novel mathematical framework for Artificial General Intelligence (AGI). Carrier manifolds represent the state space of complex AGI systems, while hybrid systems model discrete and continuous dynamics together. The proposed architecture embeds carrier manifold into GPTProX, a hybrid AI solver combining conversational AI, logic programming, and optimization.

Although the spanwise periodicity within the gap between two tandem circular cylinders has been observed by some researchers, there is a lack of systematic study on the properties of this pe-riodicity. For the spanwise periodicity within the gap, this study aims to ascertain its characteris-tics, its influences on the flow field, and its variation trend with increasing spacing ratio. By nu-merically simulating the flow around two tandem circular cylinders with a diameter ratio of d/D=0.6 and seventeen spacing ratios (L/D=1.00~6.00) at Re=3900, this study shows four flow re-gimes: Reattachment Flow (L/D=1.00~3.15), Bi-stable Flow (L/D=3.24), Intermittent Lock-in Co-shedding (L/D= 3.30~3.50) and Subharmonic Lock-in Co-shedding (L/D=4.00~6.00). Further, de-pending on the spanwise periodicity length of the time-averaged flow structures (i.e. Pz) within the gap, Reattachment Flow is, for the first time, subdivided into three new sub-flow regimes: Small-scale Periodic Reattachment (L/D=1.00~1.50, Pz/D=(0, 4]), Large-scale Periodic Reattachment (L/D=2.00~2.25, Pz/D>4) and Non-periodic Reattachment (L/D=2.50~3.15, no spanwise periodicity). The formation mechanisms are elaborated by analyzing the combined effect of both the L/D value and the spanwise-averaged time-averaged reattachment angle of the downstream cylinder. Moreover, this study proves that the newly-defined Small-scale Periodic Reattachment and Large-scale Periodic Reattachment are responsible for the pronounced asymmetry of the flow along the transverse direction within the gap. In addition, detailed flow properties and statistical pa-rameters are provided for each flow regime, such as velocity, vorticity, force coefficient, separa-tion/reattachment angle, Strouhal number and Q-criterion.

Land cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. In this article, we focus on the land cover segmentation tasks and complete the following research work: Firstly, to address the issues of uneven distribution of foreground and background and significant differences in target scales in remote sensing images, we propose a decoder called MDCFD based on multi-dilation rate convolution fusion. The decoder utilizes dilated convolution to expand the receptive field, enhancing the model's ability to capture global features and thus improving the model's ability to distinguish between foreground and background. Meanwhile, we design a multi-dilation rate convolution fusion module (MDCFM), which fuses the outputs of different dilation rate convolution layers. Secondly, aiming at the problems of diverse scenes, significant differences between categories, and many background interferences in remote sensing images, we propose a hybrid attention module called LKSHAM based on large kernel convolution. This module combines spatial attention and channel attention mechanisms and combines the two attention modules in series. By introducing large kernel convolution, the model's ability to extract contextual information is improved. At the same time, we adopt a strategy of decomposing large kernel convolution into multiple depthwise convolutions to reduce computational complexity. The improved network models designed by this paper can achieve an improvement of over 1.1% in the mIoU metric on segmentation tasks on the Potsdam and Vaihingen datasets.

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).

This paper aims to demonstrate how the detection of communities for epidemiological networks can be used to reduce the dimensionality of optimal control problems. A range of planted partition stochastic blockmodels are generated, where the underlying communities in the model vary in detectability. A high-performance computing workflow is then used to simulate and estimate reduced model dynamics for the networks, which in turn is used to find optimal control solutions.

Despite the growing capabilities of large language models, concerns exist about the biases they develop. In this paper, we propose a novel, automated mechanism for debiasing through specified dataset augmentation in the lens of bias producers that can be useful in a variety of industries, especially ones that are “restricted” and have limited data. We consider that bias can occur due to intrinsic model architecture and dataset quality. The two aspects are evaluated using two different metrics we created. We show that our dataset augmentation algorithm reduces bias as measured by our metrics.

Structured science summaries or research contributions using properties or dimensions beyond traditional keywords enhances science findability. Current methods, such as those used by the Open Research Knowledge Graph (ORKG), involve manually curating properties to describe research papers' contributions in a structured manner, but this is labor-intensive and inconsistent between the domain expert human curators. We propose using Large Language Models (LLMs) to automatically suggest these properties. However, it's essential to assess the readiness of LLMs like GPT-3.5, Llama 2, and Mistral for this task before application. Our study performs a comprehensive comparative analysis between ORKG's manually curated properties and those generated by the aforementioned state-of-the-art LLMs. We evaluate LLM performance through four unique perspectives: semantic alignment and deviation with ORKG properties, fine-grained properties mapping accuracy, SciNCL embeddings-based cosine similarity, and expert surveys comparing manual annotations with LLM outputs. These evaluations occur within a multidisciplinary science setting. Overall, LLMs show potential as recommendation systems for structuring science, but further finetuning is recommended to improve their alignment with scientific tasks and mimicry of human expertise.

Scaffold guided breast tissue regeneration (SGBTR) can both transform reconstructive and cosmetic breast surgery. Implant-based surgery is the most common method. However, there are inherent limitations as there is replacement of tissue rather than regeneration. Regenerating autologous soft tissue has the potential to provide a more like-for-like reconstruction with minimal morbidity. Our SGBTR approach regenerates soft tissue by implanting additively manufactured bioresorbable scaffolds filled with autologous fat graft. A pre-clinical large animal study was conducted implanting 100 ml breast scaffolds (n=55) made from medical-grade polycaprolactone in 11 minipigs for 12 months. Various treatment groups were investigated where immediate or delayed autologous fat graft, as well as platelet rich plasma were added to scaffolds. Computed Tomography and Magnetic Resonance Imaging was performed on explanted scaffolds to determine volume and distribution of regenerated tissue. Histological analysis was performed to confirm tissue type. At 12 months we were able to regenerate and sustain a mean soft tissue volume of 60.9 4.5 ml (95% CI) across all treatment groups. There was no evidence of capsule formation. There were no immediate or long-term post-operative complications. In conclusion, we were able to regenerate clinically relevant soft tissue volumes utilizing SGBTR in a pre-clinical large animal model.

ChatGPT, a Large Language Model (LLM) utilizing Natural Language Processing (NLP), has caused concerns about its impact on job sectors, including cybersecurity. In this study, we assessed ChatGPT’s impacts in non-managerial cybersecurity roles using the NICE Framework and Technological Displacement theory. We also explored its potential in passing top cybersecurity certification exams. Findings revealed ChatGPT’s promise in streamlining some jobs, especially those requiring memorization. Moreover, we highlighted ChatGPT’s challenges and limitations, such as ethical implications, LLM limitations, and Artificial Intelligence (AI) security. The study suggests that LLMs like ChatGPT could transform the cybersecurity landscape, causing job losses, skill obsolescence, labor market shifts, and mixed socioeconomic impacts. We recommend a shift in focus from memorization to critical thinking, and collaboration between LLM developers and cybersecurity professionals.

LLMs are a compressed repository of a vast corpus of valuable information on which they are trained. Therefore, this work hypothesizes that LLMs such as Llama, Orca, Falcon, and Mistral can be used for misinformation detection by making them cross-check new information with the repository on which they are trained. Accordingly, this paper describes the findings from the investigation of the abilities of LLMs in detecting misinformation on multiple datasets. The results are interpreted using explainable AI techniques such as LIME, SHAP, and Integrated Gradients. The LLMs themselves are also asked to explain their classification. These complementary approaches aid in better understanding the inner workings of misinformation detection using LLMs and lead to conclusions about their effectiveness at the task.

Background: This study addresses the burgeoning impact of Large Language Models (LLMs) such as ChatGPT on the integrity of online examinations and seeks to demonstrate latent and advanced LLM reasoning capabilities. The research devises an iterative self-reflective strategy for invoking critical thinking and higher-order reasoning in LLMs based on multimodal exam questions using visuals and text. Methods: The proposed strategy was demonstrated and evaluated on real exam questions by subject experts and the performance of ChatGPT (GPT-4) with vision was estimated on an additional dataset of 600 text descriptions of multimodal exam questions, focusing on its response to complex, visual, and textual prompts. Results: The results indicate that latent multi-hop reasoning capabilities can be invoked using the proposed self-reflective strategy, which can effectively steer ChatGPT towards correct answers by integrating critical thinking from each modality into the final response. Meanwhile, ChatGPT demonstrated considerable proficiency in being able to answer multimodal exam questions across 12 subjects. Conclusions: This work challenges findings from recent studies which claim that existing LLMs are unable to reason on complex multimodal tasks, and therefore this study underscores the need for enhanced online exam security measures like proctoring software, that can mitigate the potential misuse of AI technologies in educational settings.

To conduct high-precision and high-resolution numerical simulation of complex flow structures in turbomachinery, a high-order finite volume weighted essentially non-oscillatory (WENO) scheme for the large eddy simulation (LES) is improved and embedded into the three-dimensional viscous unsteady CFD solver NUAA-Turbo. Firstly, the spectral characteristics and unsteady convergence of the improved WENO scheme are studied. Compared with the classical WENO scheme, the improved WENO scheme has better dissipation and dispersion characteristics and faster convergence speed. Then, the coefficient CW of the Wall-Adapting Local Eddy-viscosity (WALE) model is calibrated by decaying homogeneous isotropic turbulence (DHIT) test case. Finally, the scheme is applied to conduct high-precision LES calculations of turbulent boundary layer flow, supersonic compression corner flow, and low-pressure turbine cascade separation flow. The numerical simulation results show that this WENO scheme has excellent shock wave capture ability and turbulence resolution and can capture more flow field details with less mesh size, greatly reducing the computational cost and laying a foundation for large-scale engineering application of LES.

This study delves into the performance evaluation of an avant-garde technology in mobile communications known as Large Intelligent Surface (LIS), poised to be an integral component of the sixth-generation (6G) networks. This groundbreaking technology has the potential to markedly augment the Signal-to-Interference plus Noise Ratio (SINR) by orchestrating signals originating from the base station through a network of digitally controlled reflectors meticulously engineered to modulate the phase of incoming electromagnetic waves. A LIS can establish a Line of Sight (LoS) within channels that inherently do not have a LoS. In addition, it can also be optimized to increase transmission security by ensuring that the signal reaches only the target users of the message with better quality. In this study, analytical expressions were derived to calculate the distribution parameters, the bit error probability, and the secrecy outage probability. These calculations consider the presence of an eavesdropper link, highlighting the potential of the LIS to increase the confidentiality of digital communication systems. The accuracy of the proposed formulas was demonstrated by showing how the performance of the LIS varies with different design parameters and environmental fading.

Subgrid scale models for unresolved turbulent fluxes are investigated with a focus on combustion for space propulsion applications. An extension to the gradient model is proposed, introducing a dependency on the local burning regime. The dynamic behavior of the model's coefficients is investigated, and scaling laws are studied. The discussed models are validated using a DNS database of a high-pressure turbulent fuel-rich methane-oxygen diffusion flame. The operating point and turbulence characteristics are selected to resemble those of modern combustors for space propulsion applications to support the future usage of the devised model in this context.

This research presents a comprehensive framework for efficiently generating forest fire datasets from Google Earth Engine data sources. The primary contribution of this work lies in providing a methodology to swiftly extract forest fire factors without the need for permissions or access to private datasets, rendering the dataset openly accessible and shared without barriers. Furthermore, given that the remote sensing data used is a global dataset, it can be applied in any region without restrictions. In this study, Peninsular Malaysia is chosen as a case study to demonstrate the framework's effectiveness. The generated dataset includes essential variables including the climate and environment, landcover, topography, and anthropogenic factors facilitating the analysis of fire occurrences. The methodology empowers data scientists, enabling them to leverage their analytical skills on the extracted dataset without requiring specialized remote sensing knowledge. Additionally, this study also showcases the adoption of large language models, specifically GPT-4 with the Noteable plugin, as a tool for conducting preliminary analyses on the generated dataset. Sample analyses reveal that several key features, including the KBDI, LST, PDSI, climate water deficit, and precipitation, significantly impact forest fire occurrences in Peninsular Malaysia. Despite the successful application of the GPT-4 with Noteable plugin, certain limitations and challenges are identified, highlighting the necessity for further validation of the tool's applicability and limitations. This study encourages future research to (1) adopt the proposed framework in other regions, (2) explore more detailed analyses encompassing all variables, and (3) leverage machine learning for advanced forecasting.

The recent past has witnessed a growing interest in technologies for creating chatbots. Advances in Large Language Models for natural language processing are underpinning rapid progress in chatbot development, and experts predict revolutionary changes in the labour market as many manual tasks are replaced by virtual assistants in a range of business functions. As the new technology becomes more accessible and advanced, more companies are exploring the possibilities of implementing virtual assistants to automate routine tasks and improve service. This article reports on qualitative inductive research undertaken within a chatbot development team operating in a major international enterprise. The findings identify critical success factors for chatbot projects, and, based on the in-depth case study, a model is put forward to aid the manageability of chatbot implementation. The presented model can serve as an exemplar guide for researchers and practitioners working on the design, development and implementation of virtual assistants. It is flexible and applicable in a wide range of business contexts, linking strategic business goals with execution steps. It is particularly applicable for teams with no experience of chatbot implementation, reducing uncertainty and managing decisions and risks throughout the project lifecycle, thereby increasing the likelihood of project success.

The attitude dynamics and orbit dynamics of large rigid space structures are coupled with each other under gravity gradient, which may affect the stability of the large rigid space structures. In this paper, the gravity gradient stability of a large rigid space structure is studied under both small and large disturbances. Based on the rigid body dynamics and orbit dynamics, an accurate dynamic model without any linearization of the large rigid space structure is established via the natural coordinate formulation (NCF), which is able to describe the large overall motions of the structures. By using the generalized-α algorithm, the gravity gradient stability of the large rigid space structure is simulated and analyzed via various examples, including the influence of large disturbance angles, the positions at the stabilization and unstabilization regions. Finally, the relationship between spinning stability and gravity gradient stability is also investigated via a large spinning space structure.

With the trend of public infrastructure becoming more sustainable, large multi-purpose sports venues (LMPSVs) have become one of the world's most complex architectural projects and one of the landmark buildings of an international city. LMPSVs will lead the world in sustainable design, construction and operational innovations, and play a crucial role in raising awareness of sustainability around the world. System Thinking (ST), System Dynamics (SD) and Sustainable System Development (SSD) theories are three interrelated concepts that together form a methodological framework for solving complex system problems and driving strategies. The purpose of this study is to examine how LMPSVs can implement environmental, social, governance, and innovation (ESGI) enterprise transformation strategy (ETS) based on a sustainable systems development (SSD) framework. In view of the current global environmental challenges and social responsibility requirements, the motivation of this study is to provide an integrated transformation pathway for LMPSVs to achieve the goal of sustainable development and to contribute to the field of related disciplines. The methodology of this research adopts a combination of literature review and case study analysis, and the theoretical basis is mainly drawn from cutting-edge research in the fields of sustainable development, corporate social responsibility (CSR) and environmental management. Then, by analyzing successful transformation cases in China, we extract data and information to explore the application and effectiveness of these strategies in practice. The results of the study show that by implementing ESGI-based transformation strategy, LMPSVs can not only make significant progress in terms of environmental protection, social responsibility, and governance structure, but also drive long-term corporate growth and competitiveness through innovation. Specifically, these results are realized in terms of increased efficiency in energy use, improved waste management, community involvement and increased stakeholder satisfaction. The study concludes by emphasizing that the SSD-based ESGI Transformation Strategic framework provides a sustainable pathway for LMPSVs. In the future, the extension of this transformation strategy will help a wider range of industry sectors to achieve sustainable development goals, and has wide application potential and far-reaching social significance.

Unmanned aerial vehicle (UAV), or drone is recognized for its potential to improve efficiency and address last-mile delivery issues. As a result, there has been a lot of activity in recent years in the field of drone scheduling and routing. Unlike the vehicle routing problem, drone route design is difficult due to several operational characteristics, such as speed optimization, multitrip operation, and energy consumption estimation. On the one hand, drone energy consumption is a complex nonlinear function of both speed and payload in practice. On the other hand, the high operating speed of drones can significantly curtail the drone range, thereby limiting the efficiency of drone delivery systems. Most of the existing drone delivery models either assume constant drone speed or do not consider the effect of drone speed and parcel weight on energy consumption, leading to costly or energy-infeasible routes. This paper addresses the trade-off between speed and flight range in a multi-trip drone routing problem with variable flight speeds (DRP-VFS), in which a team of homogeneous drones is employed for delivery services. We propose a new model to particularly consider energy constraints using a nonlinear energy consumption model and treat drone speeds as decision variables so that various drone speeds can be adopted in applications. The DRP-VFS is initially formulated as mixed-integer linear programming (MILP) to minimize total energy consumption. To solve large-scale instances, we propose a three-phase adaptive large neighborhood search (ALNS) algorithm. The experimental results demonstrate that suboptimal solutions can be found effectively in practical scenarios using the proposed method. Furthermore, results indicate that operating drones at variable speeds leads to about 21% of energy savings compared to fixed speeds, boasting advantages in cost-savings and range extensions.

Introduction. Intra-abdominal cystic formations represent heterogeneous pathologies with varied localization and clinical manifestation. The first challenge of a giant intra-abdominal cystic lesion is identifying the organ of origin. The clinical presentation of intra-abdominal cystic lesions varies from acute manifestations to non-specific symptoms or accidental discovery. Case presentation: A 2-year-old girl presents to the emergency unit with a fever of 38.5 Celsius, loss of appetite, and apathy. The investigations showed a gigantic intra-abdominal mass whose organ belonging could not be specified. Postoperatively, a giant mesenteric lymphangioma was evident, which was completely excised. Discussions Giant cystic formations modify the anatomical reports and become space-replacing formations, and the starting point is even more challenging to assess preoperatively. Nevertheless, the careful evaluation of the characteristics of the formation, the effect on the adjacent organs, the age of the patient, and the clinical picture can provide elements of differential diagnosis.

The purpose of this paper is to explore the implementation of Retrieval-Augmented Gen- 14 eration (RAG) technology with open-source Large Language Models (LLMs). For this purpose, a 15 web-based application named PaSSER that integrates RAG with three models - Mistral:7b, 16 Llama2:7b: Orca2:7b, is developed. In its development various technologies are used, including 17 Blockchain for managing and storing assessment results of built-in testing modules. PaSSER em- 18 ploys a set of evaluation metrics for LLMs’ performance - METEOR, ROUGE, BLEU, Perplexity, 19 Cosine similarity, Pearson correlation, and F1 score. The specialized knowledge base is in the smart 20 agriculture domain. As an illustration, the paper presents results and analysis of two tests. First one 21 is assessing the performance of LLMs across different hardware configurations, the other is deter- 22 mining the model that delivers most accurate and contextually relevant responses within the RAG. 23 The paper also discusses the integration of blockchain technology with LLMs to manage and store 24 assessment results within a blockchain environment. The tests revealed that Mistral:7b demon- 25 strates the best results across most of the evaluated metrics. The discussion section comments on 26 technical and hardware considerations that affect the performance of LLMs. Future development 27 will focus in leveraging new larger pre-trained open-source LLMs, exploring different finetuning 28 approaches, and further integration with Blockchain and IPFS.

The pursuit of Artificial Intelligence (AI) that emulates human cognitive processes is a cornerstone of ethical AI development, ensuring that emerging technologies can integrate seamlessly into societal frameworks requiring nuanced understanding and decision-making. Zero-Shot Instance Retrieval (ZSIR) stands at the forefront of this endeavour, potentially providing a robust platform for AI systems, particularly large visual language models, to demonstrate and refine cognition-aligned learning without the need for direct experience. In this paper, we critically evaluate current cognition alignment methodologies within traditional zero-shot learning paradigms, using visual attributes and word embedding generated by large AI models. We propose a unified similarity function that quantifies the cognitive alignment level, bridging the gap between AI processes and human-like understanding. Through extensive experimentation, our findings illustrate that this similarity function can effectively mirror the visual-semantic gap, steering the model towards enhanced performance in zero-shot instance retrieval. This work not only benchmarks the cognition alignment of AI, but also sets a new precedent for the development of visual language models attuned to the complexities of human cognition.}

Confusion, fear and mixed sentiments prevail in the minds of people towards what is arguably one of the most important of dynamics of modern human society: Artificial Intelligence (AI). This study aims to explore the contributions of news media towards this phenomenon - we analyze nearly seventy thousand recent news headlines on AI, using natural language processing (NLP) informatics methods, machine learning (ML) and large language models (LLMs) to draw insights and discover dominant themes. Our theoretical framework was derived from extant literature which posits the power of fear producing articles and news headlines which produce significant impacts on public behavior even when available in small quantities. We applied extensive textual informatics methods using word and phrase frequency analytics, sentiment analysis and human experts based thematic analysis to discover insights on AI phobia inducing news headlines. Our rigorous analysis of nearly seventy thousand headlines using multiple validation methods in NLP (exploratory informatics including BERT, Llama 2 and Mistral based topic identification), ML (supervised informatics) and LLMs (neural nets for sentiment classification, with BERT, Llama 2 and Mistral) demonstrates the presence of an unreasonable level of emotional negativity and fear inducing verbiage in AI news headlines. The framing of AI as being dangerous or as being an existential threat to humanity can have a profound impact on public perception, and the resulting AI phobia and confusion in public perceptions are inherently detrimental to the science of AI. Furthermore, this can also impact AI policy and regulations, and harm society. We conclude with a discussion deducing implications for society and make recommendations for education and policies that could support human identity and dignity.

Background: Large-cell neuroendocrine carcinoma presents significant treatment challenges owing to its rarity and limited therapeutic options. The LANCE study was designed to explore the survival benefits of incorporating atezolizumab in chemotherapy for metastatic LCNEC. Methods: In this non-randomized study, patients with metastatic LCNEC were treated with ei-ther standard chemotherapy plus atezolizumab or standard chemotherapy alone. The primary outcomes measured were progression-free survival (PFS) and overall survival (OS), with an ex-ploratory analysis of miR375 in plasma as a potential biomarker. Results: Of the 22 screened patients, 17 met the inclusion criteria and were stratified into the atezolizumab and chemotherapy (n=10) or chemotherapy alone(n=7) groups. After a median follow-up of 23.3 months, the 12-month survival rate for the atezolizumab group was 57.1% (95% CI: 32.6%-100%) and 45.7% at 24 months (95% CI: 22.4%-93.2%). In contrast, the chemotherapy group had a 14.3% survival rate at both 12 and 24 months (95% CI: 2.33%-87.7%). The log-rank test for survival showed a statistically significant difference in the atezolizumab-treated group (chi-squared = 4, df = 1, p = 0.04). A non-significant correlation was found between disease pro-gression and elevated levels of miR375. Conclusions: This pilot study suggests that atezolizumab combined with chemotherapy may be effective in treating metastatic LCNEC. The non-significant correlation between plasma miR375 levels and disease progression suggests its biomarker potential, warranting further validation research.

This study introduces a specialized Automatic Speech Recognition (ASR) system, leveraging the Whisper Large-v2 model, specifically adapted for radiological applications in French language. Our methodology focused on adapting the model to accurately transcribe medical terminology and diverse accents within the French language context, achieving a notable Word Error Rate (WER) of 17.121%. The research involved extensive data collection and preprocessing, utilizing a wide range of French medical audio content. The results demonstrate the system's effectiveness in transcribing complex radiological data, underscoring its potential to enhance medical documentation efficiency in French-speaking clinical settings. The discussion extends to the broader implications of this technology in healthcare, including its potential integration with Electronic Health Records (EHRs) and its utility in medical education. The study also explores future research directions, such as tailoring ASR systems to specific medical specialties and languages. Overall, this research contributes significantly to the field of medical ASR systems, presenting a robust tool for radiological transcription in the French language and paving the way for advanced technology-enhanced healthcare solutions.