General-purpose Model Research Articles

Dementia risk prediction using decision-focused content selection from medical notes

Several general-purpose language model (LM) architectures have been proposed with demonstrated improvement in text summarization and classification. Adapting these architectures to the medical domain requires additional considerations. For instance, the medical history of the patient is documented in the Electronic Health Record (EHR) which includes many medical notes drafted by healthcare providers. Direct processing of these notes may not be possible because the computational complexity of LMs imposes a limit on the length of input text. Therefore, previous applications resorted to content selection using truncation or summarization of the text. Unfortunately, these text processing techniques may lead to information loss, redundancy or irrelevance. In the present paper, a decision-focused content selection technique is proposed. The objective of this technique is to select a subset of sentences from the medical notes of a patient that are relevant to the target outcome over a predefined observation period. This decision-focused content selection methodology is then used to develop a dementia risk prediction model based on the Longformer LM architecture. The results show that the proposed framework delivers an AUC of 78.43 when the summary is restricted to 1024 tokens, outperforming previously proposed content selection techniques. This performance is notable given that the model estimates dementia risk with a one year prediction horizon, relies on an observation period of only one year and solely uses medical notes without other EHR data modalities. Moreover, the proposed techniques overcome the limitation of machine learning models that use a tabular representation of the text by preserving contextual content, enable feature engineering from raw text and circumvent the computational complexity of language models.

Improving the experimental estimation of the incident angle modifier of evacuated tube solar collectors with heat pipes

This article focuses on the thermal performance testing of evacuated tube solar collectors with heat pipes (ETC-HP) using the ISO 9806:2017 standard test methods: Steady-state testing (SST) and Quasi-dynamic testing (QDT). The main objective of this work is to improve the experimental estimation of the incident angle modifier (IAM) for these types of solar collectors in both test methods. For the QDT method, a novel model for the IAM is presented and validated against SST results. This IAM model, recently developed for flat plate collectors under the SST framework, has demonstrated superior performance compared to other available models. This study marks its first application to ETC-HP technology, showcasing its adaptability across different technologies and test methods. While this work primarily focuses on ETC-HP collectors, the results are applicable to evacuated tubes in general. Thus, the generality of this model and its consistency with the SST method make it suitable for implementation in test standards as a general-purpose model. Regarding the SST method, and aiming to enhance consistency between testing methods, an improved parameter conversion from SST to QDT is also proposed, reducing IAM differences between test methods by 1 to 19 percentage points, with greater improvement at higher incidence angles.

A critical review of large language models: Sensitivity, bias, and the path toward specialized AI

Abstract This paper examines the comparative effectiveness of a specialized compiled language model and a general-purpose model such as OpenAI’s GPT-3.5 in detecting sustainable development goals (SDGs) within text data. It presents a critical review of large language models (LLMs), addressing challenges related to bias and sensitivity. The necessity of specialized training for precise, unbiased analysis is underlined. A case study using a company descriptions data set offers insight into the differences between the GPT-3.5 model and the specialized SDG detection model. While GPT-3.5 boasts broader coverage, it may identify SDGs with limited relevance to the companies’ activities. In contrast, the specialized model zeroes in on highly pertinent SDGs. The importance of thoughtful model selection is emphasized, taking into account task requirements, cost, complexity, and transparency. Despite the versatility of LLMs, the use of specialized models is suggested for tasks demanding precision and accuracy. The study concludes by encouraging further research to find a balance between the capabilities of LLMs and the need for domain-specific expertise and interpretability.

Optimal Large Language Model Characteristics to Balance Accuracy and Energy Use for Sustainable Medical Applications.

Background Large language models (LLMs) for medical applications use unknown amounts of energy, which contribute to the overall carbon footprint of the health care system. Purpose To investigate the tradeoffs between accuracy and energy use when using different LLM types and sizes for medical applications. Materials and Methods This retrospective study evaluated five different billion (B)-parameter sizes of two open-source LLMs (Meta's Llama 2, a general-purpose model, and LMSYS Org's Vicuna 1.5, a specialized fine-tuned model) using chest radiograph reports from the National Library of Medicine's Indiana University Chest X-ray Collection. Reports with missing demographic information and missing or blank files were excluded. Models were run on local compute clusters with visual computing graphic processing units. A single-task prompt explained clinical terminology and instructed each model to confirm the presence or absence of each of the 13 CheXpert disease labels. Energy use (in kilowatt-hours) was measured using an open-source tool. Accuracy was assessed with 13 CheXpert reference standard labels for diagnostic findings on chest radiographs, where overall accuracy was the mean of individual accuracies of all 13 labels. Efficiency ratios (accuracy per kilowatt-hour) were calculated for each model type and size. Results A total of 3665 chest radiograph reports were evaluated. The Vicuna 1.5 7B and 13B models had higher efficiency ratios (737.28 and 331.40, respectively) and higher overall labeling accuracy (93.83% [3438.69 of 3665 reports] and 93.65% [3432.38 of 3665 reports], respectively) than that of the Llama 2 models (7B: efficiency ratio of 13.39, accuracy of 7.91% [289.76 of 3665 reports]; 13B: efficiency ratio of 40.90, accuracy of 74.08% [2715.15 of 3665 reports]; 70B: efficiency ratio of 22.30, accuracy of 92.70% [3397.38 of 3665 reports]). Vicuna 1.5 7B had the highest efficiency ratio (737.28 vs 13.39 for Llama 2 7B). The larger Llama 2 70B model used more than seven times the energy of its 7B counterpart (4.16 kWh vs 0.59 kWh) with low overall accuracy, resulting in an efficiency ratio of only 22.30. Conclusion Smaller fine-tuned LLMs were more sustainable than larger general-purpose LLMs, using less energy without compromising accuracy, highlighting the importance of LLM selection for medical applications. © RSNA, 2024 Supplemental material is available for this article.

Advancing Vietnamese Visual Question Answering with Transformer and Convolutional Integration

Visual Question Answering (VQA) has recently emerged as a potential research domain, captivating the interest of many in the field of artificial intelligence and computer vision. Despite the prevalence of approaches in English, there is a notable lack of systems specifically developed for certain languages, particularly Vietnamese. This study aims to bridge this gap by conducting comprehensive experiments on the Vietnamese Visual Question Answering (ViVQA) dataset, demonstrating the effectiveness of our proposed model. In response to community interest, we have developed a model that enhances image representation capabilities, thereby improving overall performance in the ViVQA system. Therefore, we propose AViVQA-TranConI (Advancing Vietnamese Visual Question Answering with Transformer and Convolutional Integration). AViVQA-TranConI integrates the Bootstrapping Language-Image Pre-training with frozen unimodal models (BLIP-2) and the convolutional neural network EfficientNet to extract and process both local and global features from images. This integration leverages the strengths of transformer-based architectures for capturing comprehensive contextual information and convolutional networks for detailed local features. By freezing the parameters of these pre-trained models, we significantly reduce the computational cost and training time, while maintaining high performance. This approach significantly improves image representation and enhances the performance of existing VQA systems. We then leverage a multi-modal fusion module based on a general-purpose multi-modal foundation model (BEiT-3) to fuse the information between visual and textual features. Our experimental findings demonstrate that AViVQA-TranConI surpasses competing baselines, achieving promising performance. This is particularly evident in its accuracy of 71.04% on the test set of the ViVQA dataset, marking a significant advancement in our research area. The code is available at https://github.com/nngocson2002/ViVQA.

The diagnostic and triage accuracy of the GPT-3 artificial intelligence model: an observational study

Artificial intelligence (AI) applications in health care have been effective in many areas of medicine, but they are often trained for a single task using labelled data, making deployment and generalisability challenging. How well a general-purpose AI language model performs diagnosis and triage relative to physicians and laypeople is not well understood. We compared the predictive accuracy of Generative Pre-trained Transformer 3 (GPT-3)'s diagnostic and triage ability for 48 validated synthetic case vignettes (<50 words; sixth-grade reading level or below) of both common (eg, viral illness) and severe (eg, heart attack) conditions to a nationally representative sample of 5000 lay people from the USA who could use the internet to find the correct options and 21 practising physicians at Harvard Medical School. There were 12 vignettes for each of four triage categories: emergent, within one day, within 1 week, and self-care. The correct diagnosis and triage category (ie, ground truth) for each vignette was determined by two general internists at Harvard Medical School. For each vignette, human respondents and GPT-3 were prompted to list diagnoses in order of likelihood, and the vignette was marked as correct if the ground-truth diagnosis was in the top three of the listed diagnoses. For triage accuracy, we examined whether the human respondents' and GPT-3's selected triage was exactly correct according to the four triage categories, or matched a dichotomised triage variable (emergent or within 1 day vs within 1 week or self-care). We estimated GPT-3's diagnostic and triage confidence on a given vignette using a modified bootstrap resampling procedure, and examined how well calibrated GPT-3's confidence was by computing calibration curves and Brier scores. We also performed subgroup analysis by case acuity, and an error analysis for triage advice to characterise how its advice might affect patients using this tool to decide if they should seek medical care immediately. Among all cases, GPT-3 replied with the correct diagnosis in its top three for 88% (42/48, 95% CI 75-94) of cases, compared with 54% (2700/5000, 53-55) for lay individuals (p<0.0001) and 96% (637/666, 94-97) for physicians (p=0·012). GPT-3 triaged 70% correct (34/48, 57-82) versus 74% (3706/5000, 73-75; p=0.60) for lay individuals and 91% (608/666, 89-93%; p<0.0001) for physicians. As measured by the Brier score, GPT-3 confidence in its top prediction was reasonably well calibrated for diagnosis (Brier score=0·18) and triage (Brier score=0·22). We observed an inverse relationship between case acuity and GPT-3 accuracy (p<0·0001) with a fitted trend line of -8·33% decrease in accuracy for every level of increase in case acuity. For triage error analysis, GPT-3 deprioritised truly emergent cases in seven instances. A general-purpose AI language model without any content-specific training could perform diagnosis at levels close to, but below, physicians and better than lay individuals. We found that GPT-3's performance was inferior to physicians for triage, sometimes by a large margin, and its performance was closer to that of lay individuals. Although the diagnostic performance of GPT-3 was comparable to physicians, it was significantly better than a typical person using a search engine. The National Heart, Lung, and Blood Institute.

Many-Body Function Corrected Neural Network with Atomic Attention (MBNN-att) for Molecular Property Prediction.

Recent years have seen a surge of machine learning (ML) in chemistry for predicting chemical properties, but a low-cost, general-purpose, and high-performance model, desirable to be accessible on central processing unit (CPU) devices, remains not available. For this purpose, here we introduce an atomic attention mechanism into many-body function corrected neural network (MBNN), namely, MBNN-att ML model, to predict both the extensive and intensive properties of molecules and materials. The MBNN-att uses explicit function descriptors as the inputs for the atom-based feed-forward neural network (NN). The output of the NN is designed to be a vector to implement the multihead self-attention mechanism. This vector is split into two parts: the atomic attention weight part and the many-body-function part. The final property is obtained by summing the products of each atomic attention weight and the corresponding many-body function. We show that MBNN-att performs well on all QM9 properties, i.e., errors on all properties, below chemical accuracy, and, in particular, achieves the top performance for the energy-related extensive properties. By systematically comparing with other explicit-function-type descriptor ML models and the graph representation ML models, we demonstrate that the many-body-function framework and atomic attention mechanism are key ingredients for the high performance and the good transferability of MBNN-att in molecular property prediction.

The statistics of cognitive variability: Explaining common patterns in individuals, groups and financial markets

Psychological variability (i.e., “noise”) displays interesting structure which is hidden by the common practice of averaging over trials. Interesting noise structure, termed ‘stylized facts’, is observed in financial markets (i.e., behaviors from many thousands of traders). Here we investigate the parallels between psychological and financial time series. In a series of three experiments (total N = 202), we successively simplified a market-based price prediction task by first removing external information, and then removing any interaction between participants. Finally, we removed any resemblance to an asset market by asking individual participants to simply reproduce temporal intervals. All three experiments reproduced the main stylized facts found in financial markets, and the robustness of the results suggests that a common cognitive-level mechanism can produce them. We identify one potential model based on mental sampling algorithms, showing how this general-purpose model might account for behavior across these very different tasks.

Graph Atomic Cluster Expansion for Semilocal Interactions beyond Equivariant Message Passing

The atomic cluster expansion provides local, complete basis functions that enable efficient parametrization of many-atom interactions. We extend the atomic cluster expansion to incorporate graph basis functions. This naturally leads to representations that enable the efficient description of semilocal interactions in physically and chemically transparent form. Simplification of the graph expansion by tensor decomposition results in an iterative procedure that comprises current message-passing machine learning interatomic potentials. We demonstrate the accuracy and efficiency of the graph atomic cluster expansion for a number of small molecules, clusters, and a general-purpose model for carbon. We further show that the graph atomic cluster expansion scales linearly with the number of neighbors and layer depth of the graph basis functions. Published by the American Physical Society 2024

Nose-to-Brain Drug Delivery and Physico-Chemical Properties of Nanosystems: Analysis and Correlation Studies of Data from Scientific Literature.

In the last few decades, nose-to-brain delivery has been investigated as an alternative route to deliver molecules to the Central Nervous System (CNS), bypassing the Blood-Brain Barrier. The use of nanotechnological carriers to promote drug transfer via this route has been widely explored. The exact mechanisms of transport remain unclear because different pathways (systemic or axonal) may be involved. Despite the large number of studies in this field, various aspects still need to be addressed. For example, what physicochemical properties should a suitable carrier possess in order to achieve this goal? To determine the correlation between carrier features (eg, particle size and surface charge) and drug targeting efficiency percentage (DTE%) and direct transport percentage (DTP%), correlation studies were performed using machine learning. Detailed analysis of the literature from 2010 to 2021 was performed on Pubmed in order to build "NANOSE" database. Regression analyses have been applied to exploit machine-learning technology. A total of 64 research articles were considered for building the NANOSE database (102 formulations). Particle-based formulations were characterized by an average size between 150-200 nm and presented a negative zeta potential (ZP) from -10 to -25 mV. The most general-purpose model for the regression of DTP/DTE values is represented by Decision Tree regression, followed by K-Nearest Neighbors Regressor (KNeighbor regression). A literature review revealed that nose-to-brain delivery has been widely investigated in neurodegenerative diseases. Correlation studies between the physicochemical properties of nanosystems (mean size and ZP) and DTE/DTP parameters suggest that ZP may be more significant than particle size for DTP/DTE predictability.

Foresight—a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study

An electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments). Foresight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital [KCH], South London and Maudsley [SLaM], and the US Medical Information Mart for Intensive Care III [MIMIC-III]), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall. Foresight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% [95% CI 91-100]) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required. Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes. National Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.

Untrained and Unmatched: Fast and Accurate Zero-Training Classification for Tabular Engineering Data

Abstract In engineering design, navigating complex decision-making landscapes demands a thorough exploration of the design, performance, and constraint spaces, often impeded by resource-intensive simulations. Data-driven methods can mitigate this challenge by harnessing historical data to delineate feasible domains, accelerate optimization, or evaluate designs. However, the implementation of these methods usually demands machine learning expertise and multiple trials to choose the right method and hyperparameters. This makes them less accessible for numerous engineering situations. Additionally, there is an inherent trade-off between training speed and accuracy, with faster methods sometimes compromising precision. In our paper, we demonstrate that a recently released general-purpose transformer-based classification model, TabPFN, is both fast and accurate. Notably, it requires no dataset-specific training to assess new tabular data. TabPFN is a prior-data fitted network, which undergoes a one-time offline training across a broad spectrum of synthetic datasets and performs in-context learning. We evaluated TabPFN’s efficacy across eight engineering design classification problems, contrasting it with seven other algorithms, including a state-of-the-art automated machine learning (AutoML) method. For these classification challenges, TabPFN consistently outperforms in speed and accuracy. It is also the most data-efficient and provides the added advantage of being differentiable and giving uncertainty estimates. Our findings advocate for the potential of pre-trained models that learn from synthetic data and require no domain-specific tuning to make data-driven engineering design accessible to a broader community and open ways to efficient general-purpose models valid across applications. Furthermore, we share a benchmark problem set for evaluating new classification algorithms in engineering design.

Towards a general-purpose foundation model for computational pathology.

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks, requiring the objective characterization of histopathological entities from whole-slide images (WSIs). The high resolution of WSIs and the variability of morphological features present significant challenges, complicating the large-scale annotation of data for high-performance applications. To address this challenge, current efforts have proposed the use of pretrained image encoders through transfer learning from natural image datasets or self-supervised learning on publicly available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using more than 100 million images from over 100,000 diagnostic H&E-stained WSIs (>77 TB of data) across 20 major tissue types. The model was evaluated on 34 representative CPath tasks of varying diagnostic difficulty. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient artificial intelligence models that can generalize and transfer to a wide range of diagnostically challenging tasks and clinical workflows in anatomic pathology.

Mountain Streambed Roughness and Flood Extent Estimation from Imagery Using the Segment Anything Model (SAM)

Machine learning models facilitate the search for non-linear relationships when modeling hydrological processes, but they are equally effective for automation at the data preparation stage. The tasks for which automation was analyzed consisted of estimating changes in the roughness coefficient of a mountain streambed and the extent of floods from images. The Segment Anything Model (SAM) developed in 2023 by Meta was used for this purpose. Images from many years from the Wielka Puszcza mountain stream located in the Polish Carpathians were used as the only input data. The model was not additionally trained for the described tasks. The SAM can be run in several modes, but the two most appropriate were used in this study. The first one is available in the form of a web application, while the second one is available in the form of a Jupyter notebook run in the Google Colab environment. Both methods do not require specialized knowledge and can be used by virtually any hydrologist. In the roughness estimation task, the average Intersection over Union (IoU) ranges from 0.55 for grass to 0.82 for shrubs/trees. Ultimately, it was possible to estimate the roughness coefficient of the mountain streambed between 0.027 and 0.059 based solely on image data. In the task of estimation of the flood extent, when selecting appropriate images, one can expect IoU at the level of at least 0.94, which seems to be an excellent result considering that the SAM is a general-purpose segmentation model. It can therefore be concluded that the SAM can be a useful tool for a hydrologist.

Evaluating capabilities of large language models: Performance of GPT-4 on surgical knowledge assessments

BackgroundArtificial intelligence has the potential to dramatically alter health care by enhancing how we diagnose and treat disease. One promising artificial intelligence model is ChatGPT, a general-purpose large language model trained by OpenAI. ChatGPT has shown human-level performance on several professional and academic benchmarks. We sought to evaluate its performance on surgical knowledge questions and assess the stability of this performance on repeat queries. MethodsWe evaluated the performance of ChatGPT-4 on questions from the Surgical Council on Resident Education question bank and a second commonly used surgical knowledge assessment, referred to as Data-B. Questions were entered in 2 formats: open-ended and multiple-choice. ChatGPT outputs were assessed for accuracy and insights by surgeon evaluators. We categorized reasons for model errors and the stability of performance on repeat queries. ResultsA total of 167 Surgical Council on Resident Education and 112 Data-B questions were presented to the ChatGPT interface. ChatGPT correctly answered 71.3% and 67.9% of multiple choice and 47.9% and 66.1% of open-ended questions for Surgical Council on Resident Education and Data-B, respectively. For both open-ended and multiple-choice questions, approximately two-thirds of ChatGPT responses contained nonobvious insights. Common reasons for incorrect responses included inaccurate information in a complex question (n = 16, 36.4%), inaccurate information in a fact-based question (n = 11, 25.0%), and accurate information with circumstantial discrepancy (n = 6, 13.6%). Upon repeat query, the answer selected by ChatGPT varied for 36.4% of questions answered incorrectly on the first query; the response accuracy changed for 6/16 (37.5%) questions. ConclusionConsistent with findings in other academic and professional domains, we demonstrate near or above human-level performance of ChatGPT on surgical knowledge questions from 2 widely used question banks. ChatGPT performed better on multiple-choice than open-ended questions, prompting questions regarding its potential for clinical application. Unique to this study, we demonstrate inconsistency in ChatGPT responses on repeat queries. This finding warrants future consideration including efforts at training large language models to provide the safe and consistent responses required for clinical application. Despite near or above human-level performance on question banks and given these observations, it is unclear whether large language models such as ChatGPT are able to safely assist clinicians in providing care.

A Versatile Surrogate Model of the Power Distribution Grid Described by a Large Number of Parameters

This paper aims to present a general-purpose Surrogate Model for the probabilistic analysis of power distribution grids with a large number of input parameters. The distinctive feature of the novel technique is the employment of the partial derivatives of output variables versus input parameters to tame the “curse of dimensionality” problem exhibited by prior surrogate model calculation techniques. The second important feature of the proposed Surrogate Model method is that it does not require any a priori assumption about the nature or statistical distribution of the input parameters. In fact, it can be applied whenever design parameters are deterministic variables as well as when they are uncertain and represented by continuous and/or discrete random variables. Relevant applications presented in the paper refer to the probabilistic analysis of the distribution grid in the presence of a large number of photovoltaic sources and electric vehicle charging stations.

PIMFP: An accurate tool for the prediction of intramuscular fat percentage in live pigs using ultrasound images based on deep learning

Intramuscular fat (IMF) percentage is the proportion of fat between the muscle fibers of the loin eye, which contributes significantly to the flavor and tenderness of the pork. Traditional IMF percentage is measured after slaughter, which requires a high cost, and the slaughtered pig with high IMF percentage can not be directly retained for breeding. Instead of slaughter, using ultrasound images to predict IMF percentage has been gradually proposed as an alternative measurement. However, due to the high cost of dataset construction and limited feature extraction capability of traditional image analysis methods, there is still a lack of an accurate and robust method based on the large-scale dataset for predicting IMF percentage. Here, to establish an accurate model for non-invasive prediction of IMF percentage in pigs, a total number of 4,552 ultrasound images and their corresponding IMF percentage of 945 pigs are collected in this study. We proposed a general-purpose model, PIMFP, to accurately predict IMF percentage based on the deep convolutional neural network. The PIMFP model comprises three primary modules: image preprocessing, feature extraction, and IMF percentage prediction. The preprocessing procedures for the raw ultrasound images include channel conversion, region of interest selection, and contrast enhancement. The feature extraction module characterizes the preprocessed images using the residual neural network as the backbone to extract features. The image features are then delivered to the IMF percentage prediction module depending on the fully connected layer. Our proposed model exhibits significant advantages over existing models in predictive performance, computational speed, classification ability, robustness, and interpretability. For easier use, we also provide a user-friendly web tool for predicting IMF percentage automatically in a single step. In conclusion, our study demonstrates the power of the PIMFP model for predicting IMF percentage, which has great potential in future breeding and highlights the application of artificial intelligence algorithms in livestock.

Memory Enhancer Games: A General-purpose Game-based Intelligent Tutoring System

Students of today are exposed to technologies that are either educationally effective or distractive. Most of them are having a hard time learning in a traditional classroom setup, are easily distracted, and have difficulty remembering lessons just learned and prerequisite skills needed in learning new lessons. Game-Based Intelligent Tutoring System (GB-ITS) is a technology that provides an individualized learning experience based on student’s learning needs. GB-ITS mimics a teacher doing one-on-one teaching, also known as tutoring, which is more cost-efficient than human tutors. This study developed a general-purpose Memory Enhancer Games system, in a form of a GB-ITS. This study was conducted at Calasiao Comprehensive National High School, identified the game type that best enhances memory and the game features for this proposed system through a questionnaire by (9) ICT teacher respondents. The developed system in this study has undergone validity testing by (8) ICT teachers and professors from Schools Division I of Pangasinan, and of a University in Dagupan City, and acceptability testing by (100) senior high school students of Calasiao Comprehensive National High School, 1st semester of school year 2022-2023, using Likert scale to determine its appropriateness as an intelligent learning tool. The results of the game design questionnaire confirmed the studies of which elements were ideal for a GB-ITS, and both the validity and acceptability survey questionnaires with overall weighted means of 4.57 and 4.08, show that the system is a valid and acceptable intelligent learning tool. The developed MEG can also be of use for testing game features for educational effectiveness and can also contribute to any future study which will conduct to test whether a general-purpose GBL or GB-ITS model would compare; if won’t equal the effectiveness of GBLs designed for delivering specific contents or subjects.

Register differences and intra-register variation of elicited texts

Abstract This study examines functional differences between texts elicited under different scenarios (both between- and intra-register variation). Text elicitation is used (in linguistics and other disciplines) to control for the conditions of production and in the hopes of observing different reactions to scenarios emulating real-life situations. However, it entails a series of questions: How well does the collected data correspond to real-world situations? How to design scenarios to be meaningfully distinct in terms of the language they elicit? In order to examine the linguistic variability of scenarios and to assess their ecological validity, the present study maps Czech elicited texts onto a previously established general-purpose multi-dimensional model of register variability. One of the takeaways is that scenarios mimicking informal situations are particularly conducive to obtaining responses with high intra-register variation, which makes them more likely than formal ones to reflect variability induced by for example different psychological characteristics of participants.

Looking for related posts on GitHub discussions.

Software teams increasingly adopt different tools and communication channels to aid the software collaborative development model and coordinate tasks. Among such resources, software development forums have become widely used by developers. Such environments enable developers to get and share technical information quickly. In line with this trend, GitHub announced GitHub Discussions-a native forum to facilitate collaborative discussions between users and members of communities hosted on the platform. Since GitHub Discussions is a software development forum, it faces challenges similar to those faced by systems used for asynchronous communication, including the problems caused by related posts (duplicated and near-duplicated posts). These related posts can add noise to the platform and compromise project knowledge sharing. Hence, this article addresses the problem of detecting related posts on GitHub Discussions. To achieve this, we propose an approach based on a Sentence-BERT pre-trained general-purpose model: the RD-Detector. We evaluated RD-Detector using data from three communities hosted in GitHub. Our dataset comprises 16,048 discussion posts. Three maintainers and three Software Engineering (SE) researchers manually evaluated the RD-Detector results, achieving 77-100% of precision and 66% of recall. In addition, maintainers pointed out practical applications of the approach, such as providing knowledge to support merging the discussion posts and converting the posts to comments on other related posts. Maintainers can benefit from RD-Detector to address the labor-intensive task of manually detecting related posts.