• Journal of Information Processing Systems
• /
• 제13권3호
• /
• pp.435-447
• /
• 2017

Associative and bidirectional associative memories are examples of associative structures studied intensively in the literature. The underlying idea is to realize associative mapping so that the recall processes (one-directional and bidirectional ones) are realized with minimal recall errors. Associative and fuzzy associative memories have been studied in numerous areas yielding efficient applications for image recall and enhancements and fuzzy controllers, which can be regarded as one-directional associative memories. In this study, we revisit and augment the concept of associative memories by offering some new design insights where the corresponding mappings are realized on the basis of a related collection of landmarks (prototypes) over which an associative mapping becomes spanned. In light of the bidirectional character of mappings, we have developed an augmentation of the existing fuzzy clustering (fuzzy c-means, FCM) in the form of a so-called collaborative fuzzy clustering. Here, an interaction in the formation of prototypes is optimized so that the bidirectional recall errors can be minimized. Furthermore, we generalized the mapping into its granular version in which numeric prototypes that are formed through the clustering process are made granular so that the quality of the recall can be quantified. We propose several scenarios in which the allocation of information granularity is aimed at the optimization of the characteristics of recalled results (information granules) that are quantified in terms of coverage and specificity. We also introduce various architectural augmentations of the associative structures.

• 전자통신동향분석
• /
• 제34권4호
• /
• pp.43-54
• /
• 2019

Currently, a majority of artificial intelligence is used to secure big data; however, it is concentrated in a few of major companies. Therefore, automatic data augmentation and efficient learning algorithms for small-scale data will become key elements in future artificial intelligence competitiveness. In addition, it is necessary to develop a technique to learn meanings, correlations, and time-related associations of complex modal knowledge similar to that in humans and expand and transfer semantic prediction/knowledge inference about unknown data. To this end, a neural memory model, which imitates how knowledge in the human brain is processed, needs to be developed to enable knowledge expansion through modality cooperative learning. Moreover, declarative and procedural knowledge in the memory model must also be self-developed through human interaction. In this paper, we reviewed this essential methodology and briefly described achievements that have been made so far.

• Archives of Plastic Surgery
• /
• 제39권5호
• /
• pp.540-545
• /
• 2012

Background Patients have anxiety and fear of complications due to general anesthesia. Through new instruments and local anesthetic drugs, a variety of anesthetic methods have been introduced. These methods keep hospital costs down and save time for patients. In particular, the target-controlled infusion (TCI) system maintains a relatively accurate level of plasma concentration, so the depth of anesthesia can be adjusted more easily. We conducted this study to examine whether intravenous anesthesia using the TCI system with propofol and remifentanil would be an effective method of anesthesia in breast augmentation. Methods This study recruited 100 patients who underwent breast augmentation surgery from February to August 2011. Intravenous anesthesia was performed with 10 mg/mL propofol and 50 ${\mu}g/mL$ remifentanil simultaneously administered using two separate modules of a continuous computer-assisted TCI system. The average target concentration was set at 2 ${\mu}g/mL$ and 2 ng/mL for propofol and remifentanil, respectively, and titrated against clinical effect and vital signs. Oxygen saturation, electrocardiography, and respiratory status were continuously measured during surgery. Blood pressure was measured at 5-minute intervals. Information collected includes total duration of surgery, dose of drugs administered during surgery, memory about surgery, and side effects. Results Intraoperatively, there was transient hypotension in two cases and hypoxia in three cases. However, there were no serious complications due to anesthesia such as respiratory difficulty, deep vein thrombosis, or malignant hypertension, for which an endotracheal intubation or reversal agent would have been needed. All the patients were discharged on the day of surgery and able to ambulate normally. Conclusions Our results indicate that anesthetic methods, where the TCI of propofol and remifentanil is used, might replace general anesthesia with endotracheal intubation in breast augmentation surgery.

• 동의신경정신과학회지
• /
• 제29권4호
• /
• pp.207-221
• /
• 2018

Objectives: The objective of this study was to observe the anti-amnesic effects of Yukmijihwang-tang (YMJHT), on the scopolamine (Sco)-induced memory impairment in C57BL/6 mice through its favorable acetylcholine (ACh). Also, to observe acetylcholinesterase (AChE) activity, Choline acetyltransferase (ChAT) mRNA expressions, and antioxidant effect. Methods: Six groups, with a total of 20 normal and 100 Sco treated mice were selected based on their body weights after 1 week of acclimatization, were used in this study as follows. Half of the mice in each group were used for passive avoidance task tests and hippocampus ACh content, AChE activity and ChAT mRNA expression measurement, and the remaining half in each group used for Morris water maze test and measurement of cerebral antioxidant defense system. Results: Amnesia due to AChE activations and destroyed cerebral cortex antioxidant defense systems were markedly and dose-dependently inhibited after 28 days of continuous oral pre-treatment with YMJHT 400, 200 and 100 mg/kg, respectively. The overall effects of YMJHT 400 mg/kg were similar to those of tacrine 10 mg/kg. Conclusions: Based on the results, it was established that oral administration of YMJHT favorably alleviates Sco-induced memory impairment, through preservation of ACh, mediated by up-regulation of ChAT mRNA expressions and related AChE inhibition and augmentation of cerebral antioxidant defense system, at least in a condition of this experiment. The overall effects of YMJHT 400 mg/kg were similar to those of tacrine 10 mg/kg.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.246-256
• /
• 2022

Recently, parents and teachers consider physical education as a minor subject for students in elementary and secondary schools. Physical education performance has become increasingly significant as parents and schools pay more attention to physical schooling. The sports mining with distribution analysis model considers different factors, including the games, comments, conversations, and connection made on numerous sports interests. Using different machine learning/deep learning approach, children's athletic and academic interests can be tracked over the course of their academic lives. There have been a number of studies that have focused on predicting the success of students in higher education. Sports interest prediction research at the secondary level is uncommon, but the secondary level is often used as a benchmark to describe students' educational development at higher levels. An Automated Student Interest Prediction on Sports Mining using DL Based Bi-directional Long Short-Term Memory model (BiLSTM) is presented in this article. Pre-processing of data, interest classification, and parameter tweaking are all the essential operations of the proposed model. Initially, data augmentation is used to expand the dataset's size. Secondly, a BiLSTM model is used to predict and classify user interests. Adagrad optimizer is employed for hyperparameter optimization. In order to test the model's performance, a dataset is used and the results are analysed using precision, recall, accuracy and F-measure. The proposed model achieved 95% accuracy on 400^th instances, where the existing techniques achieved 93.20% accuracy for the same. The proposed model achieved 95% of accuracy and precision for 60%-40% data, where the existing models achieved 93% for accuracy and precision.

• 한국항해항만학회지
• /
• 제29권4호
• /
• pp.349-355
• /
• 2005

The use of the internet to facilitate commerce among companies promises vast benefits. Lots of e-marketplaces are building for several industries such as chemistry, airplane, and automobile industries. This study provides the new B2B EC business model for the shipping industry which concerns relatively massive fixed assets to be fully utilized. To be successful the proposed model gives participants useful information. To do this the expert system is constructed with the hybrid prediction system of neural network (NN) and memory based reasoning (MBR) with self-organizing map (SOM) and knowledge augmentation technique using qualitative reasoning (QR). The expert system supports participants useful information coping with dynamic market environment. with this shipping companies are induced to participate in the proposed e-marketplace and helped for exchanges easily. Also participants would utilize their assets fully through B2B exchanges.

• 반도체디스플레이기술학회지
• /
• 제20권4호
• /
• pp.151-156
• /
• 2021

Low-end IoT devices do not have enough computation and memory resources for DNN learning and inference. Integer quantization of real-type neural network models can reduce model size, hardware computational burden, and power consumption. This paper describes the design and implementation of a web-based quantization platform for CNN deep learning accelerator chips. In the web service platform, we implemented visualization of the model through a convenient UI, analysis of each step of inference, and detailed editing of the model. Additionally, a data augmentation function and a management function of files that store models and inference intermediate results are provided. The implemented functions were verified using three YOLO models.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.201-203
• /
• 2022

최근 5년간 당뇨병으로 진료받은 환자가 322만 명으로 27.7% 증가하였으며 여전히 손가락 채혈을 통해 혈당을 확인하므로 연속적인 혈당 측정과 혈당 피크 확인이 어렵고 고통스러워한다. 이를 해결하기 위해 14일 간 측정한 혈당 데이터를 기반으로 인공지능 기술을 사용하여 3개월간의 혈당 예측 데이터를 당뇨 환자들에게 제공해준다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2304-2320
• /
• 2021

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.