Search

Thyroid nodules are common clinical entities, with a significant proportion being malignant. Early, accurate, and non-invasive tools to differentiate benign and malignant nodules can optimize patient management and reduce unnecessary surgery. This study aimed to evaluate the efficacy and accuracy of near-infrared spectroscopy (NIRS) in distinguishing benign from malignant thyroid nodules. A diffuse reflectance spectrum for a total of 20 thyroid nodule samples (10 samples as colloid goiter and 10 samples as thyroid cancer), were acquired in the wavelength range from 1000 to 2500 nm. Spectral data from NIRS were analyzed by means of principal component analysis (PCA), quadratic discriminant analysis (QDA), and linear discriminant analysis (LDA) to classify and differentiate thyroid nodule samples. The present study found that NIRS effectively distinguished colloid goiter and thyroid cancer using the first two principal components (PCs), explaining 90% and 10% of the variance, respectively. QDA discrimination plot displayed a clear separation between colloid goiter and thyroid cancer with minimal overlap, aligning with reported 95% accuracy. Additionally, applying LDA to seven PCs from PCA achieved a 100% accuracy rate in classifying colloid goiter and thyroid cancer from near-infrared spectral data. In conclusion, NIRS offers a promising, non-invasive complementing diagnostic tool for differentiating benign from malignant thyroid nodules with high accuracy. Future work should integrate these results into predictive model development, emphasizing external validation, alternative performance metrics, and protecting against potential overfitting translation of a machine learning model to a clinical setting. [ABSTRACT FROM AUTHOR]

Students who learn the language of instruction as an additional language represent a heterogeneous group with varying linguistic and cultural backgrounds, contributing to classroom diversity. Because of the manifold challenges these students encounter while learning the language of instruction, additional barriers arise for them when engaging in chemistry classes. Adapting teaching practices to the language skills of these students, for instance, in formative assessments, is essential to promote equity and inclusivity in chemistry learning. For this reason, novel educational practices are needed to meet each student's unique set of language capabilities, irrespective of course size. In this study, we propose and validate several approaches to allow undergraduate chemistry students who are not yet fluent in the language of instruction to complete a formative assessment in their preferred language. A technically easy-to-implement option for instructors is to use translation tools to translate students' reasoning in any language into the instructor's language. Besides, instructors could also establish multilingual machine learning models capable of automatically analyzing students' reasoning regardless of the applied language. Herein, we evaluated both opportunities by comparing the reliability of three translation tools and determining the degree to which multilingual machine learning models can simultaneously assess written arguments in different languages. The findings illustrate opportunities to apply machine learning for analyzing students' reasoning in multiple languages, demonstrating the potential of such techniques in ensuring equal access for learners of the language of instruction. [ABSTRACT FROM AUTHOR]

Automatic conversion of sign language into text or speech can be really useful in communicating among deaf or mute people with no sign language knowledge. The present need is to create an automated system that can translate ISL signals into regular text and vice versa. It is advantageous for both groups to communicate their needs to one another while using publicly accessible services, such as banking, traffic signaling, and ticketing. In this manuscript, Indian Sign Language Recognition using Transfer Learning with Efficient Net (ISLR-EfficientNetB0) is proposed for Indian sign language recognition. Initially, the input images are gathered via the Indian Sign Language (ISL) dataset. The input image is pre-processing by Fairness-aware Collaborative Filtering (FACF) method. In pre-processing stage noise are removed from input images and image resizing is done. Then, Efficient Net B0 is employed to identify ISL. The proposed model is implemented on Python. Then the efficiency of the proposed approach is compared with existing models. The accuracy, precision, specificity, sensitivity, F1-score, computational time, error rate and RoC of the suggested approaches are all assessed. The proposed ISLR-EfficientNetB0 method attains 31.42%, 26.04%, and 20.45% higher accuracy, 19.24%, 26.35%, and 24.02% higher precision, 15.84%, 18.91%, and 28.16% higher specificity and 17.06%, 21.36%, and 32.47% higher sensitivity compared with existing methods, such as Indian sign language recognition under machine learning methods (ISLR-KNN), ISL recognition scheme utilizing SURF with SVM and CNN (ISLR-SVM-CNN) and Benchmarking deep neural network methods for ISL recognition (ISLR-VGG16) respectively. [ABSTRACT FROM AUTHOR]

The growth of the global construction market has attracted international companies to participate in overseas projects. Overseas projects are extremely dynamic with numerous uncertainties, raising the need to collect information about construction in host countries. Due to the vast amounts of text data in the construction industry, an automated method, specifically information retrieval, is required to find the necessary information. Previous studies have suggested automated methods to review various construction documents. However, these studies required substantial manual effort and mainly focused on only one language, resulting in loss of vital information because it is buried in documents written in the host country's language. To address these limitations, this study proposes a cross-lingual information retrieval (CLIR) framework using pretrained Bidirectional Encoder Representations from Transformers (BERT) models to retrieve information from multilingual construction documents. The proposed framework employs language models (i.e., monolingual, multilingual, and cross-lingual) and trains these models on a construction data set to enhance their ability in construction-specific text. The framework achieved reliable performance of retrieval, even with minimal additional training using domain-specific data. The results indicate that training on the domain data set raises the level of retrieval, increasing the mean reciprocal rank of a specific task by up to 0.2128. With the employment of a monolingual model with machine translation, CLIR in a specific domain could be performed effectively without the need for a labeled data set. The suggested CLIR framework offers a practical alternative for dealing with construction documents in overseas projects, reducing time and cost while improving risk identification and mitigation. [ABSTRACT FROM AUTHOR]

End-to-end speech translation (ST) has attracted substantial attention due to its less error accumulation and lower latency. Based on triplet ST data ⟨ speech-transcription-translation ⟩ , multitask learning (MTL) that utilizes machine translation ⟨ transcription-translation ⟩ or automatic speech recognition ⟨ speech-transcription ⟩ task to assist in training ST model is widely employed. However, current MTL methods often suffer from subnet role mismatch, semantic inconsistency, or usually focus only on transferring knowledge from automatic speech recognition (ASR) or machine translation (MT) task, leading to insufficient transferring of cross-task knowledge. To solve these problems, we propose the multitask co-training network (MCTN) to jointly model ST, MT, and ASR tasks. Specifically, the ASR task enables the acoustic encoder to better capture local information of speech frames, and the MT task enhances the translation capability of the model. MCTN benefits from three key aspects: a well-designed multitask framework to fully exploit the association between tasks, a model decoupling and parameter sharing method to maintain consistency in subnet roles, and a co-training strategy to utilize task information in triplet ST data. Our experiments show that MCTN achieves state-of-the-art results, when using only MuST-C dataset, and significantly outperforms strong end-to-end ST baselines and cascaded systems when external data are available. [ABSTRACT FROM AUTHOR]

Deep learning models adapted from natural language processing offer new opportunities for the prediction of active compounds via machine translation of sequential molecular data representations. For example, chemical language models are often derived for compound string transformation. Moreover, given the principal versatility of language models for translating different types of textual representations, off-the-beaten-path design tasks might be explored. In this work, we have investigated generative design of active compounds with desired potency from target sequence embeddings, representing a rather provoking prediction task. Therefore, a dual-component conditional language model was designed for learning from multimodal data. It comprised a protein language model component for generating target sequence embeddings and a conditional transformer for predicting new active compounds with desired potency. To this end, the designated "biochemical" language model was trained to learn mappings of combined protein sequence and compound potency value embeddings to corresponding compounds, fine-tuned on individual activity classes not encountered during model derivation, and evaluated on compound test sets that were structurally distinct from training sets. The biochemical language model correctly reproduced known compounds with different potency for all activity classes, providing proof-of-concept for the approach. Furthermore, the conditional model consistently reproduced larger numbers of known compounds as well as more potent compounds than an unconditional model, revealing a substantial effect of potency conditioning. The biochemical language model also generated structurally diverse candidate compounds departing from both fine-tuning and test compounds. Overall, generative compound design based on potency value-conditioned target sequence embeddings yielded promising results, rendering the approach attractive for further exploration and practical applications. Scientific contribution: The approach introduced herein combines protein language model and chemical language model components, representing an advanced architecture, and is the first methodology for predicting compounds with desired potency from conditioned protein sequence data. [ABSTRACT FROM AUTHOR]

Although tool use may enhance resource utilization, its fitness benefits are difficult to measure. By examining longitudinal data from 196 radio-tagged southern sea otters (Enhydra lutris nereis), we found that tool-using individuals, particularly females, gained access to larger and/or harder-shelled prey. These mechanical advantages translated to reduced tooth damage during food processing. We also found that tool use diminishes trade-offs between access to different prey, tooth condition, and energy intake, all of which are dependent on the relative prey availability in the environment. Tool use allowed individuals to maintain energetic requirements through the processing of alternative prey that are typically inaccessible with biting alone, suggesting that this behavior is a necessity for the survival of some otters in environments where preferred prey are depleted. [ABSTRACT FROM AUTHOR]

Transient Luminous Events (TLEs) are short-lived, upper-atmospheric optical phenomena associated with thunderstorms. Their rapid and random occurrence makes manual classification laborious and time-consuming. This study presents an effective approach to automating the classification of TLEs using state-of-the-art Convolutional Neural Networks (CNNs) and a Vision Transformer (ViT). The ViT architecture and four different CNN architectures, namely, ResNet50, ResNet18, GoogLeNet, and SqueezeNet, are employed and their performance is evaluated based on their accuracy and execution time. The models are trained on a dataset that was augmented using rotation, translation, and flipping techniques to increase its size and diversity. Additionally, the images are preprocessed using bilateral filtering to enhance their quality. The results show high classification accuracy across all models, with ResNet50 achieving the highest accuracy. However, a trade-off is observed between accuracy and execution time, which should be considered based on the specific requirements of the task. This study demonstrates the feasibility and effectiveness of using transfer learning and pre-trained CNNs for the automated classification of TLEs. [ABSTRACT FROM AUTHOR]

Background: Aphasia is one of the most common complications of stroke. Mirror therapy (MT) is promising rehabilitation measure for the treatment of post-stroke aphasia. Although some studies suggested that MT is effective and safe for aphasia, the effects and safety remain uncertain due to lacking strong evidence, such as the relevant systematic review and meta- analysis. Methods: This study will search PubMed, Web of Science, Cochrane Library, EMBASE, Medline, China Knowledge Network (CNKI), WANFANG, China Biomedical Literature Database (CBM), from inception to 1th May 2023 to identify any eligible study. No language or date of publication shall be limited. We will only include randomised controlled trials of MT in the Treatment of poststroke aphasia. Two investigators will work separately on the study selection, data extraction, and study quality assessment. The western aphasia battery (WAB) and aphasia quotient (AQ) will be included as the main outcomes. Boston diagnostic aphasia examination method (BDAE), Chinese standard aphasia examination (CRRCAE) will be included as the secondary outcomes. The statistical analysis will be conducted by RevMan V.5.4 software. The risk of bias of included studies will be assessed by the Cochrane 'Risk of bias' tool. The quality of proof of the results will be evaluated by using the Grading of Recommendations Assessment, Development and Evaluation guidelines. Results: The finding will be presented in a journal or related conferences. Conclusion: This study will provide a basis for whether mirror therapy (MT) is effective and safe in the treatment of post-stroke aphasia. Trial registration: Systematic review registration INPLASY registration number: INPLASY 202340054. [ABSTRACT FROM AUTHOR]

Probabilistic hesitant fuzzy sets (PHFSs) are superior to hesitant fuzzy sets (HFSs) in avoiding the problem of preference information loss among decision makers (DMs). Owing to this benefit, PHFSs have been extensively investigated. In probabilistic hesitant fuzzy environments, the correlation coefficients have become a focal point of research. As research progresses, we discovered that there are still a few unresolved issues concerning the correlation coefficients of PHFSs. To overcome the limitations of existing correlation coefficients for PHFSs, we propose new correlation coefficients in this study. In addition, we present a multi-criteria group decision-making (MCGDM) method under unknown weights based on the newly proposed correlation coefficients. In addition, considering the limitations of DMs' propensity to use language variables for expression in the evaluation process, we propose a method for transforming the evaluation information of the DMs' linguistic variables into probabilistic hesitant fuzzy information in the newly proposed MCGDM method. To demonstrate the applicability of the proposed correlation coefficients and MCGDM method, we applied them to a comprehensive clinical evaluation of orphan drugs. Finally, the reliability, feasibility and efficacy of the newly proposed correlation coefficients and MCGDM method were validated. [ABSTRACT FROM AUTHOR]

Coding transcript-derived siRNAs (ct-siRNAs) produced from specific endogenous loci can suppress the translation of their source genes to balance plant growth and stress response. In this study, we generated Arabidopsis mutants with deficiencies in RNA decay and/or post-transcriptional gene silencing (PTGS) pathways and performed comparative sRNA-seq analysis, revealing that multiple RNA decay and PTGS factors impede the ct-siRNA selective production. Genes that produce ct-siRNAs often show increased or unchanged expression and typically have higher GC content in sequence composition. The growth and development of plants can perturb the dynamic accumulation of ct-siRNAs from different gene loci. Two nitrate reductase genes, NIA1 and NIA2, produce massive amounts of 22-nt ct-siRNAs and are highly expressed in a subtype of mesophyll cells where DCL2 exhibits higher expression relative to DCL4, suggesting a potential role of cell-specific expression of ct-siRNAs. Overall, our findings unveil the multifaceted factors and features involved in the selective production and regulation of ct-siRNAs and enrich our understanding of gene silencing process in plants. Research on Arabidopsis indicates that RNA decay, PTGS pathway, GC content, and spatial-temporal gene expression impact ct-siRNA production, vital for gene silencing during plant growth and stress responses. [ABSTRACT FROM AUTHOR]

The existing in vitro toxicological models lack translational potential, which makes difficult the application of gathered information to clinical usage. To tackle this issue, we built a model with four different types of primary liver cells: hepatic sinusoidal endothelial cells, hepatic stellate cells, Kupffer cells and hepatocytes. We cultured them in different combinations of composition and volumes of cell medium, hepatocyte proportions of total cells and additions of extracellular matrixes. We added rifampicin (RIF), ibuprofen (IBU) and 5-fluorouracil (5-FU) to this model and observed the microanatomy and physiology changes for a week with preclinical and clinical instruments. Among the different model configurations, we selected the feature combination of the in vitro model that had similar biomarker values to those measured in clinical diagnostics. When we exposed the selected model configuration to RIF, IBU and 5-FU, we observed similar glucose, triglyceride and albumin dynamics as in vivo (from clinical data). Therefore, we have built an in vitro liver model that resembles the liver microenvironment, and we have analysed it with clinical instrumentation to facilitate data translation. Furthermore, during these observations, we found that Kupffer and LSEC cells are suitable candidates for the search for clinical diagnostic markers of liver function. [ABSTRACT FROM AUTHOR]

Rheumatoid arthritis (RA) is a chronic inflammatory disease. Despite new methods of diagnostics and treatment as well as extensive biological and immunosuppressive treatment, the etiology of RA is not fully understood. Moreover, the problem of diagnosis and treatment of RA patients is still current and affects a large group of patients. It is suggested that endoplasmic reticulum (ER)-related features may impair adaptation to chronic stress, inferring the risk of rheumatoid arthritis. The main goal in this study was evaluation of changes in mRNA translation to determine chronic ER stress conditions in rheumatoid arthritis patients. The study group consist of 86 individuals including a total of 56 rheumatoid arthritis patients and 30 healthy controls. The expression level of mRNA form blood samples of RA patients as well as controls of the unfolded protein response (UPR)-associated genes (p-eIF2, BCL-2, PERK, ATF4, and BAX) were investigated using real-time qPCR. GAPDH expression was used as a standard control. Considering the median, the expression levels of PERK, BCL-2, p-eIF2, ATF4, and BAX were found to be significantly increased in the blood of RA patients compared with the control group. The p-value for the PERK gene was 0.0000000036, the p-value for the BCL-2 gene was 0.000000014, the p-value for the p-eIF2 gene was 0.006948, the p-value for the ATF4 gene was 0.0000056, and the p-value for the BAX gene was 0.00019, respectively. Thus, it can be concluded that the targeting of the components of the PERK-dependent UPR signaling pathway via small-molecule PERK inhibitors may contribute to the development of novel, innovative treatment strategies against rheumatoid arthritis. [ABSTRACT FROM AUTHOR]

To develop a magnetic resonance imaging (MRI)-based radiomics model for the preoperative identification of mesenchymal transition (MT) subtype in high-grade serous ovarian cancer (HGSOC). One hundred and eighty-nine patients with histopathologically confirmed HGSOC were enrolled retrospectively. Among the included patients, 55 patients were determined as the MT subtype and the remaining 134 were non-MT subtype. After extracting a total of 204 features from T2-weighted imaging (T2WI) and contrast-enhanced (CE)-T1WI images, the Mann–Whitney U -test, Spearman correlation test, and Boruta algorithm were adopted to select the optimal feature set. Three classifiers, including logistic regression (LR), support vector machine (SVM), and random forest (RF), were trained to develop radiomics models. The performance of established models was evaluated from three aspects: discrimination, calibration, and clinical utility. Seven radiomics features relevant to MT subtypes were selected to build the radiomics models. The model based on the RF algorithm showed the best performance in predicting MT subtype, with areas under the curves (AUCs) of 0.866 (95 % confidence interval [CI]: 0.797–0.936) and 0.852 (95 % CI: 0.736–0.967) in the training and testing cohorts, respectively. The calibration curves, supported with Brier scores, indicated very good consistency between observation and prediction. Decision curve analysis (DCA) showed that the RF-based model could provide more net benefit, which suggested favorable utility in clinical application. The RF-based radiomics model provided accurate identification of MT from the non-MT subtype and may help facilitate personalised management of HGSOC. • Preoperative identification of MT subtype is of importance for patients with HGSOC. • RF-based radiomics model performed best in the prediction of MT subtype. • RF-based radiomics model had favorable calibration performance and clinical utility. [ABSTRACT FROM AUTHOR]

Sentiment analysis is an essential task in natural language processing that involves identifying a text's polarity, whether it expresses positive, negative, or neutral sentiments. With the growth of social media and the Internet, sentiment analysis has become increasingly important in various fields, such as marketing, politics, and customer service. However, sentiment analysis becomes challenging when dealing with foreign languages, particularly without labelled data for training models. In this study, we propose an ensemble model of transformers and a large language model (LLM) that leverages sentiment analysis of foreign languages by translating them into a base language, English. We used four languages, Arabic, Chinese, French, and Italian, and translated them using two neural machine translation models: LibreTranslate and Google Translate. Sentences were then analyzed for sentiment using an ensemble of pre-trained sentiment analysis models: Twitter-Roberta-Base-Sentiment-Latest, bert-base-multilingual-uncased-sentiment, and GPT-3, which is an LLM from OpenAI. Our experimental results showed that the accuracy of sentiment analysis on translated sentences was over 86% using the proposed model, indicating that foreign language sentiment analysis is possible through translation to English, and the proposed ensemble model works better than the independent pre-trained models and LLM. [ABSTRACT FROM AUTHOR]

The aim of the study is to compare two different approaches to machine translation—statistical and neural—using automatic MT metrics of error rate and residuals. We examined four available online MT systems (statistical Google Translate, neural Google Translate, and two European commission's MT tools—statistical mt@ec and neural eTranslation) through their products (MT outputs). We propose using residual analysis to improve the accuracy of machine translation error rate. Residuals represent a new approach to comparing the quality of statistical and neural MT outputs. The study provides new insights into evaluating machine translation quality from English and German into Slovak through automatic error rate metrics. In the category of prediction and syntactic-semantic correlativeness, statistical MT showed a significantly higher error rate than neural MT. Conversely, in the category of lexical semantics, neural MT showed a significantly higher error rate than statistical MT. The results indicate that relying solely on the reference when determining MT quality is insufficient. However, when combined with residuals, it offers a more objective view of MT quality and facilitates the comparison of statistical MT and neural MT. [ABSTRACT FROM AUTHOR]

The absence of instructional support during peer feedback prevents students from engaging with peer feedback. This study adopted regulated dialogic feedback as the instructional foundation and investigated its impact on students' engagement using an experimental research design. Students in the experimental group (n = 26) performed the feedback practice with a regulated dialogic feedback approach through three phases, each involving a different regulation type: 1. negotiation and coordination of feedback activities involving shared regulation of learning (SSRL); 2. feedback provision and discussion to support its uptake involving co-regulation of learning (CoRL); and 3. translation of feedback into task progress involving self-regulation of learning (SRL). Students in the control group (n = 25) performed the feedback practice without the regulated dialogic feedback approach in an online discussion forum. The study lasted for 10 weeks for both groups. The research data included students' responses to peer feedback engagement surveys, students' learning behaviors, and the transcripts of interviews with students. The survey results show that the regulated dialogic feedback led to a higher cognitive, emotional, and behavioral engagement with the feedback practice. Based on the feedbackrelated learning behaviors, this study found that the SSRL, SRL, and CoRL processes can potentially promote cognitive, emotional, and behavioral engagement. Extreme case analysis demonstrated how the support for SSRL, SRL, and CoRL promoted engagement in all three areas (cognitive, behavioral, and emotional). Pedagogical implications were provided for creating engaging dialogic feedback practices. [ABSTRACT FROM AUTHOR]

The article discusses the importance of integrating molecular data into electronic health records (EHRs) for oncology treatment. It highlights the challenges of the current system, where molecular profiling results are often buried in PDF reports and require manual workflows. However, advancements in EHRs and data interoperability standards have allowed for the transmission of discrete molecular data elements into EHRs. This integration enables clinicians to access precision medicine features, such as AI tools, user interfaces for finding molecular results, clinical decision support, and clinical trial enrollment. The article also mentions specific examples of EHR systems that have successfully integrated molecular data. The authors emphasize the need to move from simply delivering molecular information to delivering actionable insights and call for collaboration between molecular technology companies, EHR systems, clinicians, and other stakeholders to achieve this goal. [Extracted from the article]

Automatic program repair (APR) is crucial to improve software quality. Recently, neural machine translation (NMT) based modeling for bug fixes has demonstrated great potential. However, these approaches still have two major challenges. One is that their search space is limited due to the out-of-vocabulary (OOV) problem. The other is that the NMT-based APR models tend to ignore past translation information, which often leads to over-translation and under-translation. To address the above challenges, we propose MNRepair, a new NMT-based APR approach that combines multiple mechanisms to fix bugs in source code. Specifically, we devise an encoder-decoder NMT framework with the attention mechanism. Our framework combines the copy mechanism to overcome the OOV problem that occurs with source code. To deal with the over-translation and under-translation, we utilize a coverage mechanism to record past translation information. MNRepair is able to capture a wide range of repair operators and fix 26 bugs in Defects4J. Our evaluation shows the effectiveness of multiple mechanisms in the repair process. [ABSTRACT FROM AUTHOR]

The analgesic efficacy of acupuncture has been widely recognized. However, the mechanism by which manual acupuncture-generated mechanical stimuli translate into biological signals remains unclear. This study employed a CFA-induced inflammatory pain rat model. Acupuncture intervention was then performed following standardized procedures. Enzyme-linked immunosorbent assay (ELISA) assessed inflammatory cytokines levels, while immunofluorescence and qRT-PCR screened the level of p38 and F-actin expression in the ST36 acupoint area of rats. Results indicated increased inflammatory factors, including IL-1β and TNFα, with reduced paw withdrawal mechanical threshold (PWMT) and paw withdrawal thermal latency (PWTL) in CFA rats compared to unmodeled rats. After acupuncture intervention, the heightened expression level of F-actin and p38 mRNA and the phosphorylation of p38 in the acupoint area was observed alongside decreased inflammatory factors in diseased ankle joints. The application of lifting and thrusting manipulations further enhanced the effect of acupuncture, in which the molecular expression level of muscle and connective tissue increased most significantly, indicating that these two tissues play a major role in the transformation of acupuncture stimulation. Moreover, antagonizing p38 expression hindered acupuncture efficacy, supporting the hypothesis that p38 MAPK-mediated F-actin transduces mechanical signals generated by acupuncture and related manipulation into biological signals. [ABSTRACT FROM AUTHOR]

Recently, generative artificial intelligence (GAI) has impressed the world with its ability to create text, images, and videos. However, there are still areas in which GAI produces undesirable or unintended results due to being "uncertain". Before wider use of AI-generated content, it is important to identify concepts where GAI is uncertain to ensure the usage thereof is ethical and to direct efforts for improvement. This study proposes a general pipeline to automatically quantify uncertainty within GAI. To measure uncertainty, the textual prompt to a text-to-image model is compared to captions supplied by four image-to-text models (GIT, BLIP, BLIP-2, and InstructBLIP). Its evaluation is based on machine translation metrics (BLEU, ROUGE, METEOR, and SPICE) and word embedding's cosine similarity (Word2Vec, GloVe, FastText, DistilRoBERTa, MiniLM-6, and MiniLM-12). The generative AI models performed consistently across the metrics; however, the vector space models yielded the highest average similarity, close to 80%, which suggests more ideal and "certain" results. Suggested future work includes identifying metrics that best align with a human baseline to ensure quality and consideration for more GAI models. The work within can be used to automatically identify concepts in which GAI is "uncertain" to drive research aimed at increasing confidence in these areas. [ABSTRACT FROM AUTHOR]

Fuzzy matching techniques are the presently used methods in translating the words. Neural machine translation and statistical machine translation are the methods used in MT. In machine translator tool, the strategy employed for translation needs to handle large amount of datasets and therefore the performance in retrieving correct matching output can be affected. In order to improve the matching score of MT, the advanced techniques can be presented by modifying the existing fuzzy based translator and neural machine translator. The conventional process of modifying architectures and encoding schemes are tedious process. Similarly, the preprocessing of datasets also involves more time consumption and memory utilization. In this article, a new spider web based searching enhanced translation is presented to be employed with the neural machine translator. The proposed scheme enables deep searching of available dataset to detect the accurate matching result. In addition, the quality of translation is improved by presenting an optimal selection scheme for using the sentence matches in source augmentation. The matches retrieved using various matching scores are applied to an optimization algorithm. The source augmentation using optimal retrieved matches increases the translation quality. Further, the selection of optimal match combination helps to reduce time requirement, since it is not necessary to test all retrieved matches in finding target sentence. The performance of translation is validated by measuring the quality of translation using BLEU and METEOR scores. These two scores can be achieved for the TA‐EN language pairs in different configurations of about 92% and 86%, correspondingly. The results are evaluated and compared with other available NMT methods to validate the work. [ABSTRACT FROM AUTHOR]

The performance of three-dimensional (3D) point cloud reconstruction is affected by dynamic features such as vegetation. Vegetation can be detected by near-infrared (NIR)-based indices; however, the sensors providing multispectral data are resource intensive. To address this issue, this study proposes a two-stage framework to firstly improve the performance of the 3D point cloud generation of buildings with a two-view SfM algorithm, and secondly, reduce noise caused by vegetation. The proposed framework can also overcome the lack of near-infrared data when identifying vegetation areas for reducing interferences in the SfM process. The first stage includes cross-sensor training, model selection and the evaluation of image-to-image RGB to color infrared (CIR) translation with Generative Adversarial Networks (GANs). The second stage includes feature detection with multiple feature detector operators, feature removal with respect to the NDVI-based vegetation classification, masking, matching, pose estimation and triangulation to generate sparse 3D point clouds. The materials utilized in both stages are a publicly available RGB-NIR dataset, and satellite and UAV imagery. The experimental results indicate that the cross-sensor and category-wise validation achieves an accuracy of 0.9466 and 0.9024, with a kappa coefficient of 0.8932 and 0.9110, respectively. The histogram-based evaluation demonstrates that the predicted NIR band is consistent with the original NIR data of the satellite test dataset. Finally, the test on the UAV RGB and artificially generated NIR with a segmentation-driven two-view SfM proves that the proposed framework can effectively translate RGB to CIR for NDVI calculation. Further, the artificially generated NDVI is able to segment and classify vegetation. As a result, the generated point cloud is less noisy, and the 3D model is enhanced. [ABSTRACT FROM AUTHOR]

The attention mechanism performs well for the Neural Machine Translation (NMT) task, but heavily depends on the context vectors generated by the attention network to predict target words. This reliance raises the issue of long-term dependencies. Indeed, it is very common to combine predicates with postpositions in sentences, and the same predicate may have different meanings when combined with different postpositions. This usually poses an additional challenge to the NMT study. In this work, we observe that the embedding vectors of different target tokens can be classified by part-of-speech, thus we analyze the Natural Language Processing (NLP) related Content-Adaptive Recurrent Unit (CARU) unit and apply it to our attention model (CAAtt) and embedding layer (CAEmbed). By encoding the source sentence with the current decoded feature through the CARU, CAAtt is capable of achieving translation content-adaptive representations, which attention weights are contributed and enhanced by our proposed L 1 exp N x normalization. Furthermore, CAEmbed aims to alleviate long-term dependencies in the target language through partial recurrent design, performing the feature extraction in a local perspective. Experiments on the WMT14, WMT17, and Multi30k translation tasks show that the proposed model achieves improvements in BLEU scores and enhancement of convergence over the attention-based plain NMT model. We also investigate the attention weights generated by the proposed approaches, which indicate that refinement over the different combinations of adposition can lead to different interpretations. Specifically, this work provides local attention to some specific phrases translated in our experiment. The results demonstrate that our approach is effective in improving performance and achieving a more reasonable attention distribution compared to the state-of-the-art models. [ABSTRACT FROM AUTHOR]

This article works to show that machine translation and interpretation technologies can play significant roles in addressing language barriers in democratic polities, including beyond the state. Numerous shared‐language or interpretation models have been proposed to address such barriers, while possible machine models have largely been dismissed in the literature. Yet, online translation is now ubiquitous globally, and governments and international organizations increasingly use machine translation and some interpretation applications. Such technologies, it is shown, can greatly expand information uptake and participation by ordinary citizens in linguistically diverse polities. They also can avoid key fairness and cost concerns faced by other models, or help address them in hybrid configurations, especially in online settings. While speech‐to‐speech applications may never achieve the seamless vernacular "Babel fish" interpretations implied as necessary for some deliberative modes, machine models can be seen as valuable for addressing language barriers within a range of approaches to democracy. [ABSTRACT FROM AUTHOR]

The User Experience Questionnaire (UEQ) is a standard, widely used questionnaire for evaluating user experience with many (software) products and services. This article describes UEQ translation into Croatian, which involved English and German language experts, and its verification based on an online survey conducted among 231 university students about perceived experience with different video conferencing tools in online learning during the COVID-19 lockdown. The sample was large enough to confirm the construct validity of the questionnaire. Psychometric evaluation and validation relied on factor and reliability analyses of all six scales of the full, 26-item UEQ and of the pragmatic and hedonic scales in the short, 8-item UEQ version. All scales show a rather high internal reliability, which confirms the validity of the Croatian translation. Croatian-speaking user experience researchers and practitioners can use it with confidence. [ABSTRACT FROM AUTHOR]

The article discusses the concept of Artificial General Intelligence (AGI) and its distinction from Artificial Narrow Intelligence (ANI). AGI refers to machines that can perform any intellectual task that a human can, while ANI is limited to specific programmed tasks. The article provides a brief history of AI research and the efforts made to achieve AGI. It also highlights the limitations of current AI systems and the need for a hybrid approach that combines symbolic AI and statistical AI. The article concludes by mentioning the papers included in a special issue on neuro-symbolic AI, covering topics such as depression detection, ontology matching, explainable AI, sentiment analysis, text classification, legal judgment analysis, and thunderstorm occurrence categorization. [Extracted from the article]

The utilization of monolingual data has been shown to be a promising strategy for addressing low-resource machine translation problems. Previous studies have demonstrated the effectiveness of techniques such as back-translation and self-supervised objectives, including masked language modeling, causal language modeling, and denoise autoencoding, in improving the performance of machine translation models. However, the manner in which these methods contribute to the success of machine translation tasks and how they can be effectively combined remains an under-researched area. In this study, we carry out a systematic investigation of the effects of these techniques on linguistic properties through the use of probing tasks, including source language comprehension, bilingual word alignment, and translation fluency. We further evaluate the impact of pre-training, back-translation, and multi-task learning on bitexts of varying sizes. Our findings inform the design of more effective pipelines for leveraging monolingual data in extremely low-resource and low-resource machine translation tasks. Experiment results show consistent performance gains in seven translation directions, which provide further support for our conclusions and understanding of the role of monolingual data in machine translation. [ABSTRACT FROM AUTHOR]

A highly controlled experimental setting using a sample of questions from the European Social Survey (ESS) and European Values Study (EVS) was used to test the effects of integrating machine translation and post-editing into the Translation, Review, Adjudication, Pretesting, and Documentation (TRAPD) approach in survey translation. Four experiments were conducted in total, two concerning the language pair English-German and two in the language pair English-Russian. The overall results of this study are positive for integrating machine translation and post-editing into the TRAPD process, when translating survey questionnaires. The experiments show evidence that in German and Russian languages and for a sample of ESS and EVS survey questions, the effect of integrating machine translation and post-editing on the quality of the review outputs—with quality understood as texts output with the fewest errors possible—can hardly be distinguished from the quality that derives from the setting with human translations only. [ABSTRACT FROM AUTHOR]

In this article, I provide a retrospective look at the emergence of translation technologies and summarise the pros and cons of the use of neural machine translation and generative AI tools in medical translation. I will examine both the advantages and the risks for the medical translator. [ABSTRACT FROM AUTHOR]

The article informs about the importance of precise medical translation, highlighting a case of mistranslation that led to medical errors. Topics include the role of CAT tools in aiding human translators, the distinction between CAT tools and machine translation (MT), and the increasing demand for standardized medical content translation.

Low-resource language in machine translation systems poses multiple complications regarding accuracy in translation due to insufficient incorporation of linguistic information. The difference in the linguistic information between the language pair also significantly impacts the dataset creation for improving translation accuracy. Although neural machine translation achieves a state-of-the-art approach, dealing with low-resource language is challenging since it struggled with limited resources. This paper attempts to address the data scarcity problem using augmentation of synthetic parallel sentences, source-target phrase pairs, and language models at the target side for English-to-Mizo and Mizo-to-English translation via transformer-based neural machine translation. We have attained state-of-the-art results for both directions of translation. [ABSTRACT FROM AUTHOR]

Since the dawn of the digital web era, web-based learning resources have become more and more significant in the field of education. To a certain extent, the visual communication design of these resources influences how well students learn. In view of this, the study proposes a deep learning-based approach to visual communication design. Convolutional neural networks are introduced to automatically construct the visual communication interface, a recommendation algorithm is used to develop the system's recommendation function, and machine translation is used to translate the language description text. The study method's efficacy was evaluated. According to the experimental results, the research method's runtime in a color environment was only about 37.7 seconds at 4k resolution; in a non-color environment, the method's F1 value was 0.87 at a recommended list length of 35, which was higher than that of other methods; and when it came to the interface solutions in real terms, the research method produced 526 at 30 buttons. The aforementioned findings demonstrate that the suggested approach can successfully increase the visual communication's design speed and performance in online learning materials and offer a suitable answer to the needs of real-world applications. [ABSTRACT FROM AUTHOR]

As the typical distant language pair, Chinese and Vietnamese vary widely in syntactic structure, which significantly influences the performance of Chinese-Vietnamese machine translation. To address this problem, we present a simple approach with a pre-reordering model for closing syntactic gaps of the Chinese-Vietnamese language pair. Specifically, we first propose an algorithm for recognizing the modifier inverse, one of the most representative syntactic different in Chinese-Vietnamese language pair. Then we pre-train a pre-reordering model based on the former recognition algorithm and incorporate it into the attention-based translation framework for syntactic different reordering. We conduct empirical studies on Chinese-Vietnamese neural machine translation task, the results show that our approach achieves average improvement of 2.75 BLEU points in translation quality over the baseline model. In addition, the translation fluency can be significantly improved by over 2.44 RIBES points. [ABSTRACT FROM AUTHOR]

The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local or cloud-based GPU machines are used to train them. However, inference is now shifting to miniature, mobile, IoT devices and even micro-controllers. Due to their colossal memory and computing requirements, mapping RNNs directly onto resource-constrained platforms is arcane and challenging. The efficacy of edge-intelligent RNNs (EI-RNNs) must satisfy both performance and memory-fitting requirements at the same time without compromising one for the other. This study's aim was to provide an empirical evaluation and optimization of historic as well as recent RNN architectures for high-performance and low-memory footprint goals. We focused on Human Activity Recognition (HAR) tasks based on wearable sensor data for embedded healthcare applications. We evaluated and optimized six different recurrent units, namely Vanilla RNNs, Long Short-Term Memory (LSTM) units, Gated Recurrent Units (GRUs), Fast Gated Recurrent Neural Networks (FGRNNs), Fast Recurrent Neural Networks (FRNNs), and Unitary Gated Recurrent Neural Networks (UGRNNs) on eight publicly available time-series HAR datasets. We used the hold-out and cross-validation protocols for training the RNNs. We used low-rank parameterization, iterative hard thresholding, and spare retraining compression for RNNs. We found that efficient training (i.e., dataset handling and preprocessing procedures, hyperparameter tuning, and so on, and suitable compression methods (like low-rank parameterization and iterative pruning) are critical in optimizing RNNs for performance and memory efficiency. We implemented the inference of the optimized models on Raspberry Pi. [ABSTRACT FROM AUTHOR]

Knowledge on the spatial and temporal distribution of the activities carried out in the marine environment is key to manage available space optimally. However, frequently, little or no information is available on the distribution of the largest users of the marine space, namely fishers. Tracking devices are being increasingly used to obtain highly resolved geospatial data of fishing activities, at intervals from seconds to minutes. However, to date no standardized method is used to process and analyse these data, making it difficult to replicate analysis. We develop a workflow to identify individual vessel trips and infer fishing activities from highly resolved geospatial data, which can be applied for large-scale fisheries, but also considers nuances encountered when working with small-scale fisheries. Recognizing the highly variable nature of activities conducted by different fleets, this workflow allows the user to choose a path that best aligns with the particularities in the fishery being analysed. A new method to identify anchoring sites for small-scale fisheries is also presented. The paper provides detailed code used in each step of the workflow both in R and Python language to widen the application of the workflow in the scientific and stakeholder communities and to encourage its improvement and refinement in the future. [ABSTRACT FROM AUTHOR]

In recent years, significant progress has been made in the field of non-autoregressive machine translations. However, the accuracy of non-autoregressive models still lags behind their autoregressive counterparts. This discrepancy can be attributed to the abundance of repetitive tokens in the target sequences generated by non-autoregressive models. In this study, we delve into this phenomenon and propose a novel approach to train a non-autoregressive model using unlikelihood loss. We evaluate our method on three widely used benchmark tasks. The experimental results demonstrating that our proposed approach significantly reduces the number of repetitive tokens while improving the overall performance of non-autoregressive machine translations. Compared to the baseline model "Mask-Predict", the average number of repetitions on IWSLT 14 DE → EN valid set is reduced from 0.48 to 0.17, resulting in a remarkable 62% decrease. [ABSTRACT FROM AUTHOR]

Spectral transform, known as a curvelet, enables sparse representations of complex data. Denoising wave propagation in disordered media and pattern recognition are just a few of the numerous domains in which denoising has a potential application. Based on directional basis functions, this spectral method represents objects with discontinuities along a smooth curve. In this study, we used this technique to eliminate ground roll, an unwanted feature signal that can be seen in seismic data obtained by sonating the earth's geological formations. Additionally, we improved the curvelet transform threshold denoising method combined with a fast non-local mean to remove seismic random noise. First, cyclic translation and block complex domain threshold methods were introduced into the curvelet transform threshold denoising, and the traditional curvelet threshold denoising method was improved to obtain the best denoising results; Subsequently, the removed noise was filtered using a fast non-local mean method to obtain a valid signal. Finally, the data obtained in the above two steps were added to obtain the final denoising result. The results of the model tests and actual seismic data denoising showed that the denoising results obtained using this method had a higher signal-to-noise ratio and fidelity than that using the other methods. [ABSTRACT FROM AUTHOR]

Contact inhibition (CI) represents a crucial tumor-suppressive mechanism responsible for controlling the unbridled growth of cells, thus preventing the formation of cancerous tissues. CI can be further categorized into two distinct yet interrelated components: CI of locomotion (CIL) and CI of proliferation (CIP). These two components of CI have historically been viewed as separate processes, but emerging research suggests that they may be regulated by both distinct and shared pathways. Specifically, recent studies have indicated that both CIP and CIL utilize mechanotransduction pathways, a process that involves cells sensing and responding to mechanical forces. This review article describes the role of mechanotransduction in CI, shedding light on how mechanical forces regulate CIL and CIP. Emphasis is placed on filamin A (FLNA)-mediated mechanotransduction, elucidating how FLNA senses mechanical forces and translates them into crucial biochemical signals that regulate cell locomotion and proliferation. In addition to FLNA, trans-acting factors (TAFs), which are proteins or regulatory RNAs capable of directly or indirectly binding to specific DNA sequences in distant genes to regulate gene expression, emerge as sensitive players in both the mechanotransduction and signaling pathways of CI. This article presents methods for identifying these TAF proteins and profiling the associated changes in chromatin structure, offering valuable insights into CI and other biological functions mediated by mechanotransduction. Finally, it addresses unanswered research questions in these fields and delineates their possible future directions. [ABSTRACT FROM AUTHOR]

Manual term extraction is similar to literal meaning: A translator browses text, classifies words, and prepares for translation. Terminology, as a centralized carrier of expertise, creation, popularization, and disappearance, dynamically reflects the development and evolution of an industry. The automatic extraction of terminology is a key technology for creating a professional terminology database, and it is also a key topic in the field of natural language processing. The purpose of this paper is to study how to analyse a term extraction algorithm based on machine learning and a comprehensive feature strategy. Focusing on the problems of poor generality and single statistical features of current term extraction algorithms, this paper proposes an improved domain ontology term extraction algorithm based on a comprehensive feature strategy. Moreover, automatic term extraction experiments based on a word-based maximum entropy model and a conditional random field model based on machine learning are conducted in this paper. Its word-based conditional random field model outperforms the maximum entropy model. The experimental results show that the algorithm based on the comprehensive feature strategy improves the accuracy by 8.6% compared with the TF-IDF algorithm and the C-value term extraction algorithm. This algorithm can be used to effectively extract the terms in a text and has good generality. [ABSTRACT FROM AUTHOR]

Drawing on the framework of Ideological Square Model, this paper carries out a corpus-based analysis of the ways in which group relations and the image of China are re-shaped in the English translation (ET) and the Chinese translation (CT) of Korean news discourse about China with intensifiers as an entry of inquiry. The results show that (1) There is a statistically significant difference regarding faithfulness between the ET and the CT of intensifiers (χ2 = 38.11>3.84, p<0.05), with the ET having more translation shifts. Additionally, the Chi-square test of a 3x3 contingency table (T = 49.77>5.99, P<0.05) indicates that there is a difference between the distribution of translation shifts at the 3 levels between ET and CT. (2) The ET of Korean news about China aligns more closely with van Dijk's ideological square model, while CT violates. It is argued that South Korean media have ideological factors to consider when it comes to Chinese readers accepting CT. (3) There is an alteration of the ideological square model in the target texts. The results indicate that in the translation of a target language, the translation propensity for relevant topics of the target country in which the language is spoken obeys the rules of "Us", the ingroup, but not "them", the outgroup. [ABSTRACT FROM AUTHOR]

The image‐to‐image translation (I2IT) task aims to transform images from the source domain into the specified target domain. State‐of‐the‐art CycleGAN‐based translation algorithms typically use cycle consistency loss and latent regression loss to constrain translation. In this work, it is demonstrated that the model parameters constrained by the cycle consistency loss and the latent regression loss are equivalent to optimizing the medians of the data distribution and the generative distribution. In addition, there is a style bias in the translation. This bias interacts between the generator and the style encoder and visually exhibits translation errors, e.g. the style of the generated image is not equal to the style of the reference image. To address these issues, a new I2IT model termed high‐quality‐I2IT (HQ‐I2IT) is proposed. The optimization scheme is redesigned to prevent the model from optimizing the median of the data distribution. In addition, by separating the optimization of the generator and the latent code estimator, the redesigned model avoids error interactions and gradually corrects errors during training, thereby avoiding learning the median of the generated distribution. The experimental results demonstrate that the visual quality of the images produced by HQ‐I2IT is significantly improved without changing the generator structure, especially when guided by the reference images. Specifically, the Fréchet inception distance on the AFHQ and CelebA‐HQ datasets are reduced from 19.8 to 10.2 and from 23.8 to 17.0, respectively. [ABSTRACT FROM AUTHOR]

Textural translations from diverse foreign languages require reference corpora for providing error-free readability. This applies to any foreign language example English or any other language translation to Japanese. Therefore Japanese corpus repository verifies the consistency of the translated texts, words, and sentences for its readability. This article introduces a Semantic Translation Model (STM) using Fuzzy Control (FC) for supporting the aforementioned fact. The proposed model analyzes the translated word semantics based on its sentence occurrence and meaning. These two factors are analyzed using two-level fuzzy control; the first level identifies the word placement/occurrence-based readability and the second level identifies the meaning retention. If any inconsistency is observed in the first level, the second is not carried out preventing readability errors. The fuzzy control process relies on near-to-same Japanese corpus inputs for improving readability. If the case fails then a new word replacement or displacement of the semantics is enforced. Therefore the fuzzy control levels are expanded based on different word occurrences, preventing time complexity. [ABSTRACT FROM AUTHOR]

Comparative sequence analysis permits unraveling the molecular processes underlying gene evolution. Many statistical methods generate candidate positions within genes, such as fast or slowly evolving sites, coevolving groups of residues, sites undergoing positive selection, or changes in evolutionary rates. Understanding the functional causes of these evolutionary patterns requires combining the results of these analyses and mapping them onto molecular structures, a complex task involving distinct coordinate referential systems. To ease this task, we introduce the site/group extended data format, a simple text format to store (groups of) site annotations. We developed a toolset, the SgedTools, which permits site/group extended data file manipulation, creating them from various software outputs and translating coordinates between individual sequences, alignments, and three-dimensional structures. The package also includes a Monte-Carlo procedure to generate random site samples, possibly conditioning on site-specific features. This eases the statistical testing of evolutionary hypotheses, accounting for the structural properties of the encoded molecules. [ABSTRACT FROM AUTHOR]

Geographic information system-based mineral prospectivity mapping (MPM) aims to generate targets by combining multiple proxy layers containing geology, geochemistry, and geophysics information based on an available understanding of geological processes and translating it into critical targeting criteria. However, factors such as an imperfect geological understanding with numerous heuristic natures and intrinsic biases, the inaccuracy and sparsity of datasets, and multiple selections of predictive methods adversely affect the results of MPM and jeopardize the reliability of decision-making in exploration. Thus, a series of knowledge-driven and data-driven MPM approaches to counterbalance these disadvantages have been proposed. Uncertainty is defined as a metric of the various scales of the likelihood and consequences, which is helpful to quantitatively represent the above risks. In this paper, the uncertainty in the final three-dimensional prospectivity map is analyzed and interpreted in terms of quantification, visualization, and comparison of different predictive approaches, and a novel technology is proposed based on a (1 + ε) approximate global optimum strategy derived from the truth discovery society. It outputs the globally optimal truth (p*) as the overall mathematical expectation and a set of weights w i as the representation of reliability. Here, a previous study of the Haoyaoerhudong gold deposit, which is one of the largest black-rock-series-type gold mines in China, was reevaluated. The method demonstrated the following advantages: (i) sorted the reliability of potential models built by multiple predictive variables and different mathematical methods, (ii) provided a "best-guess-decision" prospectivity result by combining the best reliability model from w i and the signal-to-noise ratio (SNR) of the risk–return model, and (iii) provided a statistically final uncertainty model by combining p* and risk information. [ABSTRACT FROM AUTHOR]

The discovery of novel therapeutic compounds through de novo drug design represents a critical challenge in the field of pharmaceutical research. Traditional drug discovery approaches are often resource intensive and time consuming, leading researchers to explore innovative methods that harness the power of deep learning and reinforcement learning techniques. Here, we introduce a novel drug design approach called drugAI that leverages the Encoder–Decoder Transformer architecture in tandem with Reinforcement Learning via a Monte Carlo Tree Search (RL-MCTS) to expedite the process of drug discovery while ensuring the production of valid small molecules with drug-like characteristics and strong binding affinities towards their targets. We successfully integrated the Encoder–Decoder Transformer architecture, which generates molecular structures (drugs) from scratch with the RL-MCTS, serving as a reinforcement learning framework. The RL-MCTS combines the exploitation and exploration capabilities of a Monte Carlo Tree Search with the machine translation of a transformer-based Encoder–Decoder model. This dynamic approach allows the model to iteratively refine its drug candidate generation process, ensuring that the generated molecules adhere to essential physicochemical and biological constraints and effectively bind to their targets. The results from drugAI showcase the effectiveness of the proposed approach across various benchmark datasets, demonstrating a significant improvement in both the validity and drug-likeness of the generated compounds, compared to two existing benchmark methods. Moreover, drugAI ensures that the generated molecules exhibit strong binding affinities to their respective targets. In summary, this research highlights the real-world applications of drugAI in drug discovery pipelines, potentially accelerating the identification of promising drug candidates for a wide range of diseases. [ABSTRACT FROM AUTHOR]

To improve the quality and efficiency of machine translation (MT) for low-resource languages (LRLs), this paper analyzes the application of genetic algorithm (GA) under the background of cloud computing (CC). By using GA to optimize MT for LRL, this study aims to address the limitations and challenges of traditional methods on LRL. Firstly, GA under the background of the CC platform is analyzed in detail. The CC platform offers powerful computing and storage capabilities that provide the basis for large-scale optimization using GA. GA is an optimization algorithm based on the principle of biological evolution, which seeks the optimal solution by simulating genes' genetic and evolutionary processes. In MT of LRL, GA can be used to optimize model parameters, select translation rules, and improve translation quality, thereby improving translation results. Secondly, the present situation of MT for LRL is described. Finally, the traditional LRL-oriented MT and the GA-optimized LRL-oriented MT are compared and analyzed. The results reveal that the traditional LRL-oriented MT has low accuracy and low customer satisfaction (CS). Considering the translation time, accuracy, and resource utilization rate (RUR), the highest rate is only about 47%. In contrast, GA-optimized LRL-oriented MT significantly improves translation accuracy and CS, reaching approximately 94%. The final evaluation results indicate that the accuracy of the model is usually above 70%, and up to 94%. Therefore, GA plays an important role in optimization for LRL-oriented MT. This paper provides technical support for optimizing LRL-oriented MT and contributes to the further development of MT technology. By applying GA, the limitations of traditional methods in LRL can be overcome and the quality and efficiency of translation can be improved. It is of great significance to improve the development of translation technology of LRL, enhance cross-language communication, and promote global cultural exchange. [ABSTRACT FROM AUTHOR]