• Electronics and Telecommunications Trends
• /
• v.36 no.2
• /
• pp.32-42
• /
• 2021

The rapid growth of deep-learning applications has invoked the R&D of artificial intelligence (AI) processors. A dedicated software framework such as a compiler and runtime APIs is required to achieve maximum processor performance. There are various compilers and frameworks for AI training and inference. In this study, we present the features and characteristics of AI compilers, training frameworks, and inference engines. In addition, we focus on the internals of compiler frameworks, which are based on either basic linear algebra subprograms or intermediate representation. For an in-depth insight, we present the compiler infrastructure, internal components, and operation flow of ETRI's "AI-Ware." The software framework's significant role is evidenced from the optimized neural processing unit code produced by the compiler after various optimization passes, such as scheduling, architecture-considering optimization, schedule selection, and power optimization. We conclude the study with thoughts about the future of state-of-the-art AI compilers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1462-1477
• /
• 2024

With the evolving complexity of connected vehicle features, the volume and diversity of data generated during driving continue to escalate. Enabling data sharing among interconnected vehicles holds promise for improving users' driving experiences and alleviating traffic congestion. Yet, the unintentional disclosure of users' private information through data sharing poses a risk, potentially compromising the interests of vehicle users and, in certain cases, endangering driving safety. Federated learning (FL) is a newly emerged distributed machine learning paradigm, which is expected to play a prominent role for privacy-preserving learning in autonomous vehicles. While FL holds significant potential to enhance the architecture of the Internet of Vehicles (IoV), the dynamic mobility of vehicles poses a considerable challenge to integrating FL with vehicular networks. In this paper, a novel clustered FL framework is proposed which is efficient for reducing communication and protecting data privacy. By assessing the similarity among feature vectors, vehicles are categorized into distinct clusters. An optimal vehicle is elected as the cluster head, which enhances the efficiency of personalized data processing and model training while reducing communication overhead. Simultaneously, the Local Differential Privacy (LDP) mechanism is incorporated during local training to safeguard vehicle privacy. The simulation results obtained from the 20newsgroups dataset and the MNIST dataset validate the effectiveness of the proposed scheme, indicating that the proposed scheme can ensure data privacy effectively while reducing communication overhead.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.7
• /
• pp.493-503
• /
• 2018

Recently, as living standards have improved, many people are becoming more interested in health, and self-training is increasing through exercise to prevent and manage pre-illness. In general, an imbalance of muscles causes asymmetry of posture, which can cause various diseases by accompanying an adjustment force, circulation action, displacement of internal organs, etc.. In this study, the development of fitness software that can be self - training among smart wears has attracted considerable attention in recent years. In this study, a technology was proposed for the commercialization of self - trainer fitness wear by a simulation through Android - based applications. Self - trainer fitness software was developed by combining a conductive polymer, fashion design, sewing, and electric and electronic technology to monitor the unbalance of the muscles during exercise and make smart wear that can calibrate the asymmetry by oneself. In particular, a polymer sensor was fabricated by deriving the optimal MWCNT concentration, and the electrode signal was collected by attaching the electrode to the optimal position, where the electrode signal line using the conductive fiber was designed and attached to collect the signal. A signal module that converts the bio-signals collected through electrical signal conversion and transmits them using Bluetooth communication was designed and manufactured. Self-trainer fitness software that can be commercialized was developed by combining noise cancellation with Android-based self-training application using a software algorithm method.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.25-34
• /
• 2020

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.8
• /
• pp.631-640
• /
• 2020

Currently, aircraft simulator has drawn a great attention because it has significant advantages of economic, temporal, and spatial costs compared with pilot training with real aircraft. Among the components of the aircraft simulator, flight dynamic model plays a key role in simulating the flight of an actual aircraft. Hence, it is important to verify the fidelity of flight dynamic model with an automated tool. In this paper, we develop a software to automatically verify the fidelity of the flight mechanics model for the efficient development of the aircraft simulator. After designing the software structure and GUI based on the requirements derived from the fidelity verification process, the software is implemented with C # language in Window-based environment. Experimental results on CTSW models show that the developed software is effective in terms of function, performance and user convenience.

• Physical Therapy Korea
• /
• v.7 no.3
• /
• pp.62-71
• /
• 2000

The purpose of this study was to find a more effective balance training method. The subjects of this study were 14 children with cerebral palsy (7 males, 7 females) being treated at Seran Pediatric Developmental Research Center in Taegu. Two groups of children with cerebral palsy (everyday trained group, every-other-day trained group) were evaluated with visual & auditory feedback. Evaluation and training device was Balance Performance Monitor (BPM) Dataprint Software Version 5.3. There was statistically significant difference of the balance score between the pre-and the post-training in both group (p<.05), but there was no difference of the balance score between two groups (p<.05). In conclusion, it is likely that the visual and auditory feedback in children with cerebral palsy was effective in improving standing balance, but there was no difference between everyday trained group and every-other-day trained group.

• Journal of KIISE:Software and Applications
• /
• v.34 no.2
• /
• pp.112-122
• /
• 2007

Training a statistical model for semantic role labeling requires a large amount of manually tagged corpus. However. such corpus does not exist for Korean and constructing one from scratch is a very long and tedious job. This paper suggests a modified algorithm of self-training, an unsupervised algorithm, which trains a semantic role labeling model from any raw corpora. For initial training, a small tagged corpus is automatically constructed iron case frames in Sejong Electronic Dictionary. Using the corpus, a probabilistic model is trained incrementally, which achieves 83.00% of accuracy in 4 selected adverbial cases.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.22 no.4
• /
• pp.537-548
• /
• 2016

Purpose: This study aims to develop a Korean version of a tool to measure uncivil behavior in clinical training to examine the experiences of nursing students. Methods: The "Uncivil Behavior in Clinical Nursing Education Scale" was developed by Anthony and Yastik in 2011. This study procedure was based on DeVellis' instrument development guidelines. Data were collected from 220 senior-year nursing students from four different universities in four different locations. Two hundreds surveys were analyzed using SPSS software and AMOS. Results: Out of 20 questions, 13 were selected after reviewing the content validity, face validity, construct validity, and reliability. The factors of the Korean version scale were specified as "exclusion", "contempt", and "refusal." The general characteristics of the subjects that showed significant differences in the occurrence of incivility were gender, age, transfer student status, level of satisfaction with clinical training, and level of satisfaction with the clinical training environment. Conclusion: The "Korean-Uncivil Behavior in Clinical Nursing Education Scale" was partially modified to account for differences in language and culture, but its validity and reliability were verified. We suggest that nurse educators and supervisors will be able to better understand the relationship between nurses and nursing students in clinical training.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.107-113
• /
• 2020

A number of studies have been conducted on predicting software faults, but most of them have been supervised models using labeled data as training data. Very few studies have been conducted on unsupervised models using only unlabeled data or semi-supervised models using enough unlabeled data and few labeled data. In this paper, we produced new semi-supervised models using tree algorithms in the self-training technique. As a result of the model performance evaluation experiment, the newly created tree models performed better than the existing models, and CollectiveWoods, in particular, outperformed other models. In addition, it showed very stable performance even in the case with very few labeled data.

• The Journal of Korean Physical Therapy
• /
• v.33 no.2
• /
• pp.91-96
• /
• 2021

Purpose: This study investigated the effects of cryotherapy on the ankle joint muscle strength and balance ability in stroke patients with ankle joint muscles. Methods: In this study, 20 patients with chronic stroke were recruited from a rehabilitation hospital. The patients were divided into two groups: a cryotherapy group (10 patients) and a control group (10 patients). The cryotherapy group performed sit-to-stand training for 15 minutes and then cryotherapy for the minutes. In the control group, after sit-to-stand training for 15 minutes, blocked cryotherapy was provided for three minutes. In both groups, the interventions were provided five times a week for three weeks. The strength of the ankle joint muscles was measured before and after the training using the Biodex systems 3. The static balance ability was measured using balancia software, and the dynamic balance ability was measured by performing the sit-to-stand test (FTSST) five times. Results: After the training periods, the cryotherapy group showed significant improvement in the ankle dorsiflexor strength, ankle plantarflexor strength, weight distribution of the affected side, and FTSST compared to the control group (p<0.05). Conclusion: Based on these results, cryotherapy could be considered an effective method to improve the strength of ankle joint muscles. Cryotherapy improves muscle strength as it increases the motor neuron excitability. Therefore, cryotherapy may be considered to improve the strength of the ankle joint muscles of stroke patients.