Human-Like Selective Attention Model with Reinforcement and Inhibition Mechanism

Choi, Se-Hyu; Ban, Sang-Woo

doi:10.1007/978-3-540-30499-9_106

Cited by 41 publications

(91 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…주의는 크게 어떤 한 대상의 감각적 정보에 의존하 는 상향식 주의(bottom-up attention)와 개인의 인지 모듈에 의존하는 하향식 주의(top-down attention)로 구분할 수 있다 (Cheoi & Lee, 2005;Choi, Ban, & Lee, 2004;Itti et al, 1998;Jung & Lee, 2004;Müller & Krummenacher, 2006;Park, Shin, & Lee., 2002;Shin & Shin, 2013b;Tsotsos et al, 1995). 시각처리과정에 대한 대표적인 연구는 Treisman & Gelade (1980)의 특징통합이론(feature-integration theory), Itti et al(1998) 인간은 다양한 외부의 정보를 처리하는 정보처리자이고, 인간의 행동과 학습은 뇌를 기반으로 한 정보처리의 결과이다 (Bermúdez, 2010;Jensen, 2008;Lim, 2005;Shin, 2016 (Shin, 2016).…”

Section: 뇌의 정보처리는 사전 경험을 통하여 형성된 인지구조로 모듈화되 어 있고 시각적 주의 또한 외부자극의 특성과unclassified

An Analysis of Elementary Students' Attention Characteristics through Attention Test and the Eye Tracking on Real Science Classes

Shin¹,

Shin²

2016

Journal of The Korean Association For Science Education

View full text Add to dashboard Cite

The purpose of this research is to analyze elementary students' attention characteristics through attention test and eye tracking on real science classes. The SMI's ETG(eye tracker glasses) mobile eye tracker was used to analyze the attention process of elementary students'. The sampling rate of the ETG is 30Hz. The participants of attention test were elementary 155 6th-grade elementary students and the participants for the eye-tracker were six 6th-grade male students. The eye movements were analyzed using the 'BeGaze Mobile Video Analysis Package program. The results of this research are as follows. First, the attention test results of elementary students showed high correlation between selective attention and sustained attention (.85) and low correlation between selective attention and self-regulation (.32). Second, the attention types of elementary students were divided into four; attention, inattention, easygoing and hasty. Third, elementary students' attention were divided into top-down, bottom-up, default mode network through analysis of elementary students′ eye-movements during real science classes. Also their attention shift occurred frequently due to various reasons in real class situation. There were three reasons that made elementary students fail to handle knowledge-dependent top-down attention; 1) the cognitive failure of target caused by failing to focus attention, 2) the absence of prior knowledge on target object, 3) the analogical failure of prior knowledge. Finally, elementary students' attention process were schematized based on the analysis of students' eye movements and attention test. This research is expected to be utilized as basic data for developing effective teaching strategies, teaching-learning models and instructional materials.

show abstract

Section: 뇌의 정보처리는 사전 경험을 통하여 형성된 인지구조로 모듈화되 어 있고 시각적 주의 또한 외부자극의 특성과unclassified

An Analysis of Elementary Students' Attention Characteristics through Attention Test and the Eye Tracking on Real Science Classes

Shin¹,

Shin²

2016

Journal of The Korean Association For Science Education

View full text Add to dashboard Cite

show abstract

“…Unlike the supervised methods used in building prediction models, patient similarity analysis adopts unsupervised or semi-supervised methods, then calculates the similarity between concepts according to the meaning of clinical concepts, to obtain the distance between patients, and finally predicts the runtime case using the most similar cluster of patients. At present, most of the studies in this field only use the data in static perspective for similarity analysis, lacking of time series characteristics, which cannot fully reflect the dynamic similarity between patients [ 27 ].…”

Section: Discussionmentioning

confidence: 99%

Using predictive process monitoring to assist thrombolytic therapy decision-making for ischemic stroke patients

Pang

Yang

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background: Although clinical guidelines provide the best practice for medical activities, there are some limitations in using clinical guidelines to assistant decision-making in practical application, such as long update cycle and low compliance of doctors with the guidelines. Driven by data of actual cases, process mining technology provides the possibility to remedy these shortcomings of clinical guidelines. Methods: We propose a clinical decision support method using predictive process monitoring, which could be complementary with clinical guidelines, to assist medical staff with thrombolytic therapy decision-making for stroke patients. Firstly, we construct a labeled data set of 1191 cases to show whether each case actually need thrombolytic therapy, and whether it conform to the clinical guidelines. After prefix extraction and filtering the control flow of completed cases, the sequences with data flow are encoded, and corresponding prediction models are trained. Results: Compared with the labeled results, the average accuracy of our prediction models for intravenous thrombolysis and arterial thrombolysis on the test set are 0.96 and 0.91, and AUC are 0.93 and 0.85 respectively. Compared with the recommendation of clinical guidelines, the accuracy, recall and AUC of our predictive models are higher. Conclusions: The performance and feasibility of this method are verified by taking thrombolytic decision-making of patients with ischemic stroke as an example. When the clinical guidelines are not applicable, doctors could be provided with assistant decision-making by referring to similar historical cases using predictive process monitoring.

show abstract

“…Longitudinal-based drug recommendation. Longitudinal-based drug recommendation ( Choi et al , 2016b ; Shang et al , 2019 ; Wu et al , 2022a , b ; Yang et al , 2021a , b ) leverages the temporal dependencies of the longitudinal patient history and captures the sequential dependency between visits to learn the PRs. Most work uses RNN-like methods to model the longitudinal patient information.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, the instance-based methods cannot capture the patient’s historical disease process. In order to overcome this issue, (ii) longitudinal-based drug recommendation ( Choi et al , 2016b ; Shang et al , 2019 ; Wang et al , 2021 ; Wu et al , 2022b ; Yang et al , 2021a , b ) that models longitudinal patient history in the temporal dimension and combines learned PRs with drug representations to predict drug combinations.…”

Section: Introductionmentioning

confidence: 99%

“…(i) Inadequate PR. Most existing works ( Choi et al , 2016b ; Shang et al , 2019 ; Yang et al , 2021b ) only regard the diagnosis and procedure information in the patient’s historical visits as two independent views, these methods encode the medical information separately and concatenate them together to obtain the PR ( Hochreiter and Schmidhuber, 1997 ). However, on the one hand, the obtained PR is not comprehensive, as it neither takes into account the impact of historical prescriptions on the patient’s disease state nor the relationship between medical perspectives on different dimensions of the disease trajectories.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dual Attention and Patient Similarity Network for drug recommendation

Dong

Gao

et al. 2023

Bioinformatics

View full text Add to dashboard Cite

Motivation Artificially making clinical decisions for patients with multi-morbidity has long been considered a thorny problem due to the complexity of the disease. Drug recommendations can assist doctors in automatically providing effective and safe drug combinations conducive to treatment and reducing adverse reactions. However, the existing drug recommendation works ignored two critical information. (1) Different types of medical information and their interrelationships in the patient's visit history can be used to construct a comprehensive patient representation. (2) Patients with similar disease characteristics and their corresponding medication information can be used as a reference for predicting drug combinations. Results To address these limitations, we propose DAPSNet, which encodes multi-type medical codes into patient representations through code-level and visit-level attention mechanisms, while integrating drug information corresponding to similar patient states to improve the performance of drug recommendation. Specifically, our DAPSNet is enlightened by the decision-making process of human doctors. Given a patient, DAPSNet first learns the importance of patient history records between diagnosis, procedure, and drug in different visits, then retrieves the drug information corresponding to similar patient disease states for assisting drug combination prediction. Moreover, in the training stage, we introduce a novel information constraint loss function based on the information bottleneck principle to constrain the learned representation and enhance the robustness of DAPSNet. We evaluate the proposed DAPSNet on the public MIMIC-III dataset, our model achieves relative improvements of 1.33%, 1.20%, and 2.03% in Jaccard, F1, and PR-AUC scores, respectively, compared to state-of-the-art methods. Availability The source code is available at the github repository: https://github.com/andylun96/DAPSNet.

show abstract

Human-Like Selective Attention Model with Reinforcement and Inhibition Mechanism

Cited by 41 publications

References 6 publications

An Analysis of Elementary Students' Attention Characteristics through Attention Test and the Eye Tracking on Real Science Classes

An Analysis of Elementary Students' Attention Characteristics through Attention Test and the Eye Tracking on Real Science Classes

Using predictive process monitoring to assist thrombolytic therapy decision-making for ischemic stroke patients

Dual Attention and Patient Similarity Network for drug recommendation

Contact Info

Product

Resources

About