Addressing the issue of high school non-completion poses a crucial challenge for contemporary education. This research introduces a machine learning-based methodology to identify students at risk of failure and abando...
ISBN:
(纸本)9783031643019;9783031643026
Addressing the issue of high school non-completion poses a crucial challenge for contemporary education. This research introduces a machine learning-based methodology to identify students at risk of failure and abandonment in a specific Brazilian state, aiming to establish an early warning system utilizing academic, socioeconomic, and performance indicators for proactive interventions. The methodology followed here ensures the explainability of predictions and guards against bias in relation to certain features. The analysis of data from 79,165 students resulted in the creation of six accurate classification models, with accuracy rates ranging from 69.4% to 92.7%. This underscores the methodology's effectiveness in identifying at-risk students, highlighting its potential to alleviate failure and abandonment. The implementation of this methodology could positively influence proactive educational policies and enhance educational metrics within the state.
This paper introduces a multi-agent reinforcement learning (MARL) model for the pension ecosystem, aiming to optimise the contributor's saving and investment strategies. The multi-agent approach enables the examin...
ISBN:
(纸本)9783031610332;9783031610349
This paper introduces a multi-agent reinforcement learning (MARL) model for the pension ecosystem, aiming to optimise the contributor's saving and investment strategies. The multi-agent approach enables the examination of endogenous and exogenous shocks, business cycle impacts, and policy decisions on contributor behaviour. The model generates synthetic income trajectories to develop inclusive savings strategies for a broad population. Additionally, this research innovates by developing a multi-agent model capable of adapting to various environmental changes, contrasting with traditional econometric models that assume stationary employment and market dynamics. The non-stationary nature of the model allows for a more realistic representation of economic systems, enabling a better understanding of the complex interplay between agents and their responses to evolving economic conditions (A variation of this article was included as a chapter in the PhD Thesis of Ozhamaratli, F. submitted on 22 Jan 2024).
This study proposes an ensemble model to incorporate sensory features of lexical items in English from external resources into neural affective analysis frameworks. This allows the models to take the combined effects ...
ISBN:
(纸本)9789819705856;9789819705863
This study proposes an ensemble model to incorporate sensory features of lexical items in English from external resources into neural affective analysis frameworks. This allows the models to take the combined effects of bi-directional feeling between the sensory lexicon and the writer to infer human affective knowledge. We evaluate our model on two affective analysis tasks. The ensemble model exhibits the best accuracy and the results with 1% F1-score improvement over the baseline LSTM model in the sentiment analysis task. The performance shows that perceptual information can contribute to the performance of sentiment classification tasks significantly. This study also provides a support for the linguistic finding that correlations exist between sensory features and sentiments in the language.
First of all, this paper analyzed the status quo of domestic and foreign research on controller capability assessment and capability improvement. Then, based on 10 dimensions, such as professional character, language ...
ISBN:
(纸本)9783031607301;9783031607318
First of all, this paper analyzed the status quo of domestic and foreign research on controller capability assessment and capability improvement. Then, based on 10 dimensions, such as professional character, language ability, reaction ability, mathematical application ability, spatial orientation ability, short-term memory ability, logical inference ability, situational awareness ability, attention switching ability, multitasking ability, the controller ability evaluation model was established. The rationality of the model was verified by selecting controllers at different stages for evaluation. Finally, based on 10 capability dimensions of controllers, a controller capability enhancement model was established. The research of this paper has important theoretical and practical significance, filling the theoretical gap in Chinese controller capability assessment and capability improvement research, and laying a good theoretical foundation for improving the overall capability of the controller team and ensuring flight safety.
Professional developers, and especially students learning to program, often write poor documentation. While automated assessment for programming is becoming more common in educational settings, often using unit tests ...
ISBN:
(纸本)9783031643019;9783031643026
Professional developers, and especially students learning to program, often write poor documentation. While automated assessment for programming is becoming more common in educational settings, often using unit tests for code functionality and static analysis for code quality, documentation assessment is typically limited to detecting the presence and the correct formatting of a docstring based on a specified style guide. We aim to investigate how machine learning can be utilised to aid in automating the assessment of documentation quality. We classify a large set of publicly available human-annotated relevance scores between a natural language string and a code string, using traditional approaches, such as Logistic Regression and Random Forest, fine-tuned large language models, such as BERT and GPT, and Low-Rank Adaptation of large language models. Our most accurate mode was a fine-tuned CodeBERT model, resulting in a test accuracy of 89%.
An analogy is a relation which operates between two pairs of terms representing two distant domains. It operates by transferring meaning from a concept that is known to another that one would like to clarify or define...
ISBN:
(纸本)9783031705625;9783031705632
An analogy is a relation which operates between two pairs of terms representing two distant domains. It operates by transferring meaning from a concept that is known to another that one would like to clarify or define. In this report, we address analogy both from the aspect of modeling and by automatically explaining it. We will then propose a system of resolution of analogical equations in their notation in symbol chains. The model, based on the common sense knowledge base JeuxDeMots (a semantic network), operates by generating a list of potential candidates from which it chooses the most suitable solution. We conclude by evaluating our model on a collection of equations, and reflecting upon future work.
This study applies AI technology to build academic Chinese corpora. Python was employed to extract lexical chunks of various lengths, including 3-gram, 4-gram, 5-gram, and 6-gram. The identification of these lexical c...
ISBN:
(纸本)9789819705856;9789819705863
This study applies AI technology to build academic Chinese corpora. Python was employed to extract lexical chunks of various lengths, including 3-gram, 4-gram, 5-gram, and 6-gram. The identification of these lexical chunks was performed using the New-MI algorithm and filtered based on semantic relevance completeness. Subsequently, manual intervention was applied to eliminate duplicate entries and identify 1431 continuous word chunks. These lexical chunks were classified into three categories according to their functions: research-oriented, text-oriented, and participation-oriented. It was found that there were some differences in the use of chunks between Korean Chinese learners and native Chinese writers, with research-oriented chunks being used more frequently in both groups than in other categories. Korean Chinese learners used research-oriented, text-oriented, and participant-oriented chunks less frequently than native speakers. This study might provide a reference for academic Chinese writing and academic Chinese textbook development for Chinese language learners.
Middle school students learned about astronomy and STEM concepts while exploring Minecraft simulations of hypothetical Earths and exoplanets. Small groups (n = 24) were tasked with building feasible habitats on Mars. ...
ISBN:
(纸本)9783031642982;9783031642999
Middle school students learned about astronomy and STEM concepts while exploring Minecraft simulations of hypothetical Earths and exoplanets. Small groups (n = 24) were tasked with building feasible habitats on Mars. In this paper, we present a scoring scheme for habitat assessment that was used to build novel multi/mixed-input AI models. Using Spearman's rank correlations, we found that our scoring scheme was reliable with regards to team size and face-to-face instruction time and validated with self-explanation scores. We took an exploratory approach to analyzing image and block data to compare seven different input conditions. Using one-way ANOVAs, we found that the means of the conditions were not equal for accuracy, precision, recall, and F1 metrics. A post hoc Tukey HSD test found that models built using images only were statistically significantly worse than conditions that used block data on the metrics. We also report the results of optimized models using block only data on additional Mars bases (n = 57).
As the only general classifier in modern Chinese, the attribute of Ge (up arrow) inevitably leads to semantic overlap with other classifiers resulting in misuse, which is worthy of further research. This study conduct...
ISBN:
(纸本)9789819705825;9789819705832
As the only general classifier in modern Chinese, the attribute of Ge (up arrow) inevitably leads to semantic overlap with other classifiers resulting in misuse, which is worthy of further research. This study conducts a comparative analysis of Ge and its near-synonyms, Zhong (sic) and Jian (sic), based on corpus research. It shows that Ge and Jian have co-occurrence contexts when measuring nouns about events, but the use of Ge is usually limited to colloquial language, while Jian is applicable to both colloquial and written language. The noun Shijian (sic) 'event' is usually modified by Ge not by Jian. There is no semantic overlap between Ge and *** and they cannot be used interchangeably. Some nouns can appear simultaneously in the Num/RNum+Ge/***+N structure, and choosing which classifier is only determined by quantitative or categorical concepts they expressed.
This work proposes a novel stream-based Active Learning (AL) approach applied to Speech Emotion Recognition (SER) in reallife scenarios where new data are generated from different domains. The goal is to address major...
ISBN:
(纸本)9783031705656;9783031705663
This work proposes a novel stream-based Active Learning (AL) approach applied to Speech Emotion Recognition (SER) in reallife scenarios where new data are generated from different domains. The goal is to address major challenges in this field, including the lack of large-labeled data, the difficulty in the annotation, and the retrieval of representative emotional data. AL aims to address these problems by selecting/querying a small and valuable subset to be annotated with optimized labeling efforts and minimum resources. To this end, we consider a stream-based AL methodology leveraging MLOps principles and human-in-the-loop methods to continuously adapt previously trained deep learning models, ensuring both challenging and diverse audio samples and reducing the performance gap related to data diversity, cross-domain contexts, and continuous data ingestion. The considered pipeline was tested across several domains within three distinct scenarios, including both no stream- and stream-based approaches, as well as a pocket stream alternative to only update the previously trained models when significant improvements are obtained. The experimental outputs show that our proposed method achieved competitive results following an AL pocket stream-based strategy with just 20% of the original training data. This ensures good performance with a low allocated budget and continuous adaptation for practical, real-world environments.
暂无评论