Automatic Generation Research Articles

Automatic generation of physics items with Large Language Models (LLMs)

High-quality items are essential for producing reliable and valid assessments, offering valuable insights for decision-making processes. As the demand for items with strong psychometric properties increases for both summative and formative assessments, automatic item generation (AIG) has gained prominence. Research highlights the potential of large language models (LLMs) in the AIG process, noting the positive impact of generative AI tools like ChatGPT on educational assessments, recognized for their ability to generate various item types across different languages and subjects. This study fills a research gap by exploring how AI-generated items in secondary/high school physics aligned with educational taxonomy. It utilizes Bloom's taxonomy, a well-known framework for designing and categorizing assessment items across various cognitive levels, from low to high. It focuses on a preliminary assessment of LLMs ability to generate physics items that match the Bloom’s taxonomy application level. Two leading LLMs, ChatGPT (GPT-4) and Gemini, were chosen for their strong performance in creating high-quality educational content. The research utilized various prompts to generate items at different cognitive levels based on Bloom's taxonomy. These items were assessed using multiple criteria: clarity, accuracy, absence of misleading content, appropriate complexity, correct language use, alignment with the intended level of Bloom's taxonomy, solvability, and assurance of a single correct answer. The findings indicated that both ChatGPT and Gemini were skilled at generating physics assessment items, though their effectiveness varied based on the prompting methods used. Instructional prompts, particularly, resulted in excellent outputs from both models, producing items that were clear, precise, and consistently aligned with the Application level of Bloom's taxonomy.

Exploring generative AI in higher education: a RAG system to enhance student engagement with scientific literature.

This study explores the implementation and evaluation of OwlMentor, an AI-powered learning environment designed to assist university students in comprehending scientific texts. OwlMentor was developed participatorily and then integrated into a course, with development and evaluation taking place over two semesters. It offers features like document-based chats, automatic question generation, and quiz creation. We used the Technology Acceptance Model to assess system acceptance, examined learning outcomes, and explored the influence of general self-efficacy on system acceptance and OwlMentor use. The results indicated complex relationships between perceived ease of use, perceived usefulness, and actual use, suggesting the need for more dynamic models of system acceptance. Although no direct correlation between OwlMentor use and learning gains was found, descriptive results indicated higher gains among users compared to non-users. Additionally, general self-efficacy was strongly related to perceived usefulness, intention to use, and actual use of the system. These findings highlight the importance of aligning AI tools with students' needs and existing learning strategies to maximize their educational benefits.

Exploring prompt pattern for generative artificial intelligence in automatic question generation

ABSTRACT The construction of questions is an essential component in educational assessment and student learning processes. However, manually constructing questions is a complex task that requires not only professional training, substantial experience, and extensive resources from teachers but is also time-consuming. This article introduces an Automatic Question Generation (AQG) technology based on a prompt pattern to alleviate this burden and address the ongoing need for new questions in education. The essence of this method lies in constructing a prompt pattern grounded on a collective knowledge base derived from teachers, thereby enhancing the quality of the questions produced. Practical applications and expert evaluations demonstrate that integrating a prompt pattern with a collective knowledge base into Large Language Models (LLMs) results in high-quality questions with statistically significant results. These questions not only meet educational standards but also approach the quality of manually constructed questions by teachers in certain aspects. Our research further emphasizes the feasibility of AI-teacher collaboration in education.

A Bi‐level stacked LSTM‐DNN‐based decoder network for AGC dispatch under regulation market framework in presence of VPP and EV aggregators

AbstractThe consideration of mileage settlement in the frequency regulation market has encouraged fast‐acting units, such as converter‐interfaced generators (CIG) and electric vehicle stations, to actively participate in load‐generation balancing through automatic generation control (AGC). Conventional frequency regulation faces challenges in coping with the growing variability of CIGs and also lacks effective incentives for rapid‐responding units. In this context, a bi‐level AGC dispatch approach based on a stacked long short‐term memory (LSTM)‐deep neural network (DNN)‐based decoder framework is proposed for a power system comprising diverse CIGs forming a virtual power plant and electric vehicle aggregators. The proposed decoder network is comprised of stacked LSTM and DNN, wherein the cascaded LSTM layers are introduced to accurately capture temporal information from time series input. The inclusion of a dropout mechanism further enhances the model’s generalisability in unforeseen environments. The proposed dispatch framework uses mileage‐based compensation criteria to optimally allocate instructions among various participating units with differing regulation characteristics. The performance of the proposed method is analysed by considering packet loss, delay, unexpected generation failure, and denial of service attacks. The evaluation of the proposed approach reveals its superior performance compared to proportionality, particle swarm optimisation, decision tree, and DNN methods.

Possibilities and challenges of Artificial Intelligence in the teaching and learning process of Journalism Writing. The experience in Spanish universities

The research aims to assess the possibilities and challenges of artificial intelligence (AI) for the development of the teaching and learning of journalistic writing techniques in the university educational context. The main objective consists of analysing the abilities of AI to solve the composition of different journalistic texts¸ both informative and opinion, and the quality of the result, as well as other applications of AI in journalistic writing. The text tries to contribute to the knowledge on the use of AI by teachers and students in the teaching and learning process. A mixed methodology has been used to develop the research: on the one hand, descriptive and comparative, based on surveys to university professors in Spain specialised in this subject and to students taking related contents in their studies, also in this context; on the other hand, an experimental research is included among professors trained in the field of Journalistic Writing, who are asked for the qualified correction of an exam, anonymous, actually carried out with the AI system, ChatGPT. After weighing the results, each of them is interviewed in depth about the quality of the texts, their strengths, and weaknesses. The results show that AI is beginning to be used in the university context by students and professors. In the specific field of journalistic writing, its use for the moment is limited to assisting tasks in the writing process or suggesting topics, while the automatic generation of content is not widely accepted due to the ethical implications that it entails, especially those related to the originality of content. Teachers value the potential of this technology for writing simple and informative pieces but observe limitations at deeper levels of knowledge and in hybrid texts.

Randomized Controlled Trial to Assess the Feasibility of a Novel Clinical Decision Support System Based on the Automatic Generation of Alerts through Remote Patient Monitoring

Background/Objectives: Early identification of complications in chronic and infectious diseases can reduce clinical deterioration, lead to early therapeutic interventions and lower morbidity and mortality rates. Here, we aimed to assess the feasibility of a novel clinical decision support system (CDSS) based on the automatic generation of alerts through remote patient monitoring and to identify the patient profile associated with the likelihood of severe medical alerts. Methods: A prospective, multicenter, open-label, randomized controlled trial was conducted. Patients with COVID-19 in home isolation were randomly assigned in a 1:1 ratio to receive either conventional primary care telephone follow-up plus access to a mobile app for self-reporting of symptoms (control group) or conventional primary care telephone follow-up plus access to the mobile app for self-reporting of symptoms and wearable devices for real-time telemonitoring of vital signs (case group). Results: A total of 342 patients were randomized, of whom 247 were included in the per-protocol analysis (103 cases and 144 controls). The case group received a more exhaustive follow-up, with a higher number of alerts (61,827 vs. 1825; p < 0.05) but without overloading healthcare professionals thanks to automatic alert management through artificial intelligence. Baseline factors independently associated with the likelihood of a severe alert were having asthma (OR: 1.74, 95% CI: 1.22–2.48, p = 0.002) and taking corticosteroids (OR: 2.28, 95% CI: 1.24–4.2, p = 0.008). Conclusions: The CDSS could be successfully implemented and enabled real-time telemonitoring of patients’ clinical status, providing valuable information to physicians and public health agencies.

Automated Repair of Smart Contract Vulnerabilities: A Systematic Literature Review

The substantial value held by smart contracts (SCs) makes them an enticing target for malicious attacks. The process of fixing vulnerabilities in SCs is intricate, primarily due to the immutability of blockchain technology. This research paper introduces a systematic literature review (SLR) that evaluates rectification systems designed to patch vulnerabilities in SCs. Following the guidelines set forth by the PRISMA statement, this SLR meticulously reviews a total of 31 papers. In this context, we classify recently published SC automated repair frameworks based on their methodologies for automatic program repair (APR), rewriting strategies, and tools for vulnerability detection. We argue that automated patching enhances the reliability and adoption of SCs, thereby allowing developers to promptly address identified vulnerabilities. Furthermore, existing automated repair tools are capable of addressing only a restricted range of vulnerabilities, and in some cases, patches may not be effective in preventing the targeted vulnerabilities. Another key point that should be taken into account is the simplicity of the patch and the gas consumption of the modified program. Alternatively, large language models (LLMs) have opened new avenues for automatic patch generation, and their performance can be improved by innovative methodologies.

Comfortable sound design based on auditory masking with chord progression and melody generations using automatic composition

Unpleasant noise is a crucial problem, that we often face in daily life. One of such a problem is in the case of dental treatment. A dental instrumental noise that includes peaky components in the high-frequency band makes doctors and patients discomfort. To reduce discomfort, we proposed a method to mask unpleasant noise with a comfortable sound. The proposed method was automatically generating a comfortable cord progression. In previous subjective test results, it shows that degree of discomfort reduces. The remaining problem is that degree of comfort improves. This is due to the fact that the previous method utilizes the musical element of chord, but does not introduce the musical elements of melody and rhythm. Therefore, in this paper, we propose a new method to introduce the melody generation with automatic composition (AI composition) into the previous method based on the automatic generation of the chord progression. The proposed method automatically generates a chord progression to follow the peak frequency of dental treatment sounds and to add a melody following the chord progression with AI composition assistance tool to improve comfort and to design comfortable sound.

Aging-aware co-optimization of topology, parameter and control for multi-mode input- and output-split hybrid electric powertrains

Existing research has focused on battery intrinsic optimization, Hybrid Energy Storage System (HESS), and powertrain control perspectives to enhance battery life. However, the impact of powertrain physical architecture -control multi-layer co-optimization on battery life has been neglected. Therefore, this study innovatively proposes a multi-mode dedicated hybrid transmission (DHT)—from the perspective of powertrain architecture—to reduce battery life degradation by switching between input split (IS) and output split (OS) modes. In order to fully optimize the battery degradation potential, a topology-parameter-control multi-layer co-optimization (TPCMC) method is proposed in this paper. In the topology layer, graph theory method is used for automatic generation, screening and modeling. In the parameter and control layer, a novel near-optimal energy management strategy, Rapid Dynamic Programming+ (Rapid-DP+), is proposed by introducing Pareto optimization, slope filtering, and Battery Life Aging Optimization (BLAO) methods, which improves the computational efficiency by 3500 times with 9.09–21.1 % battery life optimization. The results show that, relative to the Toyota Prius, the optimized powertrain improves the acceleration by 41.3 %, fuel economy by 6.08 %–8.1 %, and battery life degradation by 9.9 %–22.5 % under different driving cycles. This paper contributes to battery life degradation in the electrified transportation through an advanced TPCMC approach.

A chest imaging diagnosis report generation method based on dual-channel transmodal memory network

Medical imaging is critical for clinical diagnosis. In the past few years, medical imaging data has been steadily growing at an annual rate of 30%, while the annual growth rate in the number of radiologists is only 4. 1%. The traditional manual methods of chest imaging reports result in high information load and workload with low relevance of images and texts. Here we propose a chest CT imaging diagnosis report generation network to effectively integrate image and text feature information, improve the relevance of the cross-modal networks and automatically generate imaging diagnosis reports. The network includes three major modules: a novel ResNetII for information extraction, an image–text dual-channel transmodal memory network (DCTMN), and a dual-channel decoder module combined with LSTM gate. We validate the effectiveness of the proposed network on the IU X-ray and the MIMIC-CXR datasets. Our analysis indicates that the proposed method can strengthen the relationship between chest imaging and text information, ultimately achieving the automatic generation of chest imaging diagnosis reports.

HF-CMN: a medical report generation model for heart failure.

Heart failure represents the ultimate stage in the progression of diverse cardiac ailments. Throughout the management of heart failure, physicians require observation of medical imagery to formulate therapeutic regimens for patients. Automated report generation technology serves as a tool aiding physicians in patient management. However, previous studies failed to generate targeted reports for specific diseases. To produce high-quality medical reports with greater relevance across diverse conditions, we introduce an automatic report generation model HF-CMN, tailored to heart failure. Firstly, the generated report includes comprehensive information pertaining to heart failure gleaned from chest radiographs. Additionally, we construct a storage query matrix grouping based on a multi-label type, enhancing the accuracy of our model in aligning images with text. Experimental results demonstrate that our method can generate reports strongly correlated with heart failure and outperforms most other advanced methods on benchmark datasets MIMIC-CXR and IU X-Ray. Further analysis confirms that our method achieves superior alignment between images and texts, resulting in higher-quality reports.

Automatic medical report generation combining contrastive learning and feature difference

The automatic medical report generation is a challenging task because it requires accurate capture and description of abnormal regions, especially for those discrepancies between patient and normal. In most cases, normal region descriptions dominate the entire medical report, and existing methods may fail to focus on abnormal regions due to data bias. Medical reports can be automatically generated by combining contrastive learning with feature difference in order to capture and describe abnormal regions effectively. By capturing discrepancy attributes between the input image and normal images, this method can provide more accurate diagnostic reports and better represent the visual features of abnormal regions. Specifically, we propose the feature difference approach to make the model focus more on abnormal regions, and on the other hand, we propose the combination of contrastive learning for enhancing the visual representation of feature difference based on the feature difference approach, thus improving the performance of the model. Experimental results on the IU-Xray and MIMIC-CXR datasets demonstrate the effectiveness of our approach.

Automated construction safety reporting system integrating deep learning-based real-time advanced detection and visual question answering

The construction sector is globally acknowledged as one of the most hazardous industries, owing to the vulnerability of its workers to accidents, injuries, and even loss of life. Effective precautionary measures are necessary and ensuring the use of personal protective equipment (PPE) by workers is crucial for protecting them from accidents. Existing deep learning-based PPE detection systems mainly use simple vision-based target detection methods for tasks such as the identification of helmets or vests, and they tend to be task-specific. However, the identification of specific PPE based on respective job types and maintaining detailed safety records, requires further innovative approaches. In this paper, we propose an innovative intelligent system that not only accurately recognizes specific PPE according to the needs of different work types but also automatically generates safety inspection reports and establishes complete safety records, thus providing critical data to support accident investigations. The proposed system integrates a target detection model, visual question answering model, and text-based analysis of the relevant regulations to realize real-time detection of PPE and automatic generation of safety inspection reports. The experimental results show that the proposed YOLOv8n-DCA network strikes a good balance between performance and computational cost—, with a mAP value of 86%. Compared to the original YOLOv8n network, the mAP value is improved by 5.1%, while the model parameters and size are significantly reduced. Further, the visual question answering model exhibited a precision is 95.9. Finally, the automatic generation of safety inspection reports was successfully realized, verifying the feasibility of the developed system. This innovative system promises a comprehensive and efficient PPE management solution for the construction industry to ensure worker safety and provide strong data support.

HVCMM: A Hybrid-View Abstractive Model of Automatic Summary Generation for Teaching.

With the continuous development of educational informatization, more and more emerging technologies are applied in teaching activities. These technologies provide massive and multidimensional information for teaching research, but at the same time, the information obtained by teachers and students presents an explosive increase. Extracting the core content of the class record text through text summarization technology to generate concise class minutes can significantly improve the efficiency of teachers and students to obtain information. This article proposes a hybrid-view class minutes automatic generation model (HVCMM). The HVCMM model uses a multilevel encoding strategy to encode the long text of the input class records to avoid memory overflow in the calculation after the long text is input into the single-level encoder. The HVCMM model uses the method of coreference resolution and adds role vectors to solve the problem that the excessive number of participants in the class may lead to confusion about the referential logic. Machine learning algorithms are used to analyze the topic and Section of the sentence to capture structural information. We test the HVCMM model on the Chinese class minutes dataset (CCM) and the augmented multiparty interaction (AMI) dataset, and the results show that the HVCMM model outperforms other baseline models on the ROUGE metric. With the help of the HVCMM model, teachers can improve the efficiency of reflection after class and improve the teaching level. Students can review the key content to strengthen their understanding of what they have learned with the help of the class minutes automatically generated by the model.

Automatic closed captions and subtitles in academic video presentations: possibilities and shortcomings

In light of the increasing number of academic events being recorded or held online since the onset of the COVID-19 pandemic, the present work combines automation processes in audiovisual translation and academic texts–more specifically, video presentations. The research questions are whether the automatic generation of captions is functional to ensure accessibility in academic events and how much post-editing effort would such content require in case a machine translation of the subtitles is to be applied. The research method comprises several phases. First, in a corpus of video presentations of specialised content in English, captions were generated automatically using YouTube Studio to ascertain the general quality and the type of errors generated in the automatically generated closed captions according to Multidimensional Quality Metrics (MQM) framework. These auto-generated captions were corrected and annotated by considering the following parameters: a) pre-editing time, b) type of error according to MQM framework, and c) severity of the error. Second, the auto-generated captions and corrected were machine translated into Spanish. Furthermore, errors detected in the machine translation of the subtitles (English-Spanish) were post-edited and errors were analysed following the MQM. Reception by a potential audience was also studied, as evaluated by academics from the same field of expertise. The main conclusion is that most errors in machine-translated subtitles stem from incorrect caption segmentation and lack of context awareness, making it essential to correct the closed captions before translation. This thesis is supported by the reception study in which the level of comprehension was higher when the transcription was pre-edited, as most of the problems arise from the closed captions rather than from the translation itself.

Can input reconstruction be used to directly estimate uncertainty of a dose prediction U-Net model?

The reliable and efficient estimation of uncertainty in artificial intelligence (AI) models poses an ongoing challenge in many fields such as radiation therapy. AI models are intended to automate manual steps involved in the treatment planning workflow. We focus in this study on dose prediction models that predict an optimal dose trade-off for each new patient for a specific treatment modality. They can guide physicians in the optimization, be part of automatic treatment plan generation or support decision in treatmentindication. Most common uncertainty estimation methods are based on Bayesian approximations, like Monte Carlo dropout (MCDO) or Deep ensembling (DE). These two techniques, however, have a high inference time (i.e., require multiple inference passes) and might not work for detecting out-of-distribution (OOD) data (i.e., overlapping uncertainty estimate for in-distribution (ID) and OOD). In this study, we present a direct uncertainty estimation method and apply it for a dose prediction U-Net architecture. It can be used to flag OOD data and give information on the quality of the doseprediction. Our method consists in the addition of a branch decoding from the bottleneck which reconstructs the CT scan given as input. The input reconstruction error can be used as a surrogate of the model uncertainty. For the proof-of-concept, our method is applied to proton therapy dose prediction in head and neck cancer patients. A dataset of 60 oropharyngeal patients was used to train the network using a nested cross-validation approach with 11 folds (training: 50 patients, validation: 5 patients, test: 5 patients). For the OOD experiment, we used 10 extra patients with a different head and neck sub-location. Accuracy, time-gain, and OOD detection are analyzed for our method in this particular application and compared with the popular MCDO andDE. The additional branch did not reduce the accuracy of the dose prediction model. The median absolute error is close to zero for the target volumes and less than 1% of the dose prescription for organs at risk. Our input reconstruction method showed a higher Pearson correlation coefficient with the prediction error (0.620) than DE (0.447) and MCDO (between 0.599 and 0.612). Moreover, our method allows an easier identification of OOD (no overlap for ID and OOD data and a Z-score of 34.05). The uncertainty is estimated simultaneously to the regression task, therefore requires less time and computationalresources. This study shows that the error in the CT scan reconstruction can be used as a surrogate of the uncertainty of the model. The Pearson correlation coefficient with the dose prediction error is slightly higher than state-of-the-art techniques. OOD data can be more easily detected and the uncertainty metric is computed simultaneously to the regression task, therefore faster than MCDO or DE. The code and pretrained model are available on the gitlab repository: https://gitlab.com/ai4miro/ct-reconstruction-for-uncertainty-quatification-of-hdunet.

Calculation of critical endpoints and phase diagrams of highly asymmetric binary systems

The computation of Global Phase Equilibrium Diagrams (GPED) for binary systems, including critical and three-phase equilibrium curves, is crucial for analyzing process conditions and assessing thermodynamic models. In the past two decades, algorithmic strategies and GPEC software have become essential tools. However, numerical problems can arise with the original algorithm for highly asymmetric systems, such as gases or water with heavy compounds or polymers, hindering the completion of GPED and related diagrams.This study presents an innovative calculation methodology to address these challenges. Our approach extends existing algorithms to achieve automatic GPED generation without user intervention, focusing on nearly pure phases. We apply our methodology to systems such as methane or water with heavy alkanes, and CO2 + silicones. The proposed algorithmic strategies effectively handle asymmetric systems, different types of phase behavior, and the estimation of extremely low concentrations in nearly pure phases along the vapor-liquid-liquid equilibrium curve.

Design and Development of an Automatic Penetration Test Generation Methodology for Security of Web Applications

Design and Development of an Automatic Penetration Test Generation Methodology for Security of Web Applications

Multi-reference coupled cluster theory using the normal ordered exponential ansatz.

Properly spin-adapted coupled-cluster theory for general open-shell configurations remains an active area of research in electronic structure theory. In this contribution we examine Lindgren's normal-ordered exponential ansatz to correlate specific spin states using spin-free excitation operators, with the aid of automatic equation generation software. We present an intermediately normalised and size-extensive reformulation of the unlinked working equations, and analyse the performance of the method with single and double excitations for simple molecular systems in terms of accuracy and size-consistency.

Hyperspectral endmember extraction using convexity based purity index

The endmember extraction is a challenging problem in spectral unmixing (SU) of a mixed pixel in hyperspectral imagery. There are plenty of attempts to solve the endmember extraction problem. Still, the pure pixel assumption-based algorithms have probably been used most in solving the endmember extraction of SU due to the light computational burden. These pure pixel assumption-based algorithms usually follow one of the criteria: (1) Maximum simplex volume or (2) Extreme projection on a subspace. We propose a novel integrated framework that uses both the criteria mentioned above and the proposed one is referred to as the Convexity-based Pure Index (CPI) algorithm. The CPI generates a fixed number of convex sets based on the number of available bands in the hyperspectral image. The algorithm defines the purity score based on the availability of pixels in the convex sets for the two-band data. The CPI has been compared with contemporary algorithms such as Automatic Target Generation Process (ATGP), Vertex Component Analysis (VCA), Pixel Purity Index (PPI), Successive Volume MAXimization (SVMAX), Alternating Volume MAXimization (AVMAX), TRIple-P: P-norm based Pure Pixel identification (TRIP), Successive Decoupled Volume Max–Min (SDVMM), Negative ABundance-Oriented (NABO), and Entropy-based Convex Set Optimization (ECSO). The metrics, Spectral Angle Distance (SAD) and Spectral Information Divergence (SID) used in the comparison were improved up to 5.9% and 9%, respectively. The CPI outperforms prevailing algorithms on real benchmark data and new AVIRIS-NG data. The robustness of the CPI is also tested for various noisy synthetic data. The efficacy of the proposed algorithm is also tested by using qualitative analysis by visualizing the spectra comparison, and abundance maps for all real data.